CN118242564B - An intelligent adaptive natural gas odorant concentration control system and control method - Google Patents

Abstract

The present invention provides an intelligent adaptive natural gas odorant concentration control system and control method, belonging to the field of natural gas odorant concentration monitoring, the system includes a gas flow sensor, an odorant injection pump, an odorant concentration monitoring device, an environmental parameter sensor, an odorant characteristic sensor and a controller. The controller includes a data processing module, an odorant injection strategy determination module and a control module. The data processing module receives and processes real-time data including real-time gas flow detection data, real-time odorant concentration detection data, real-time environmental parameters and real-time odorant characteristic parameters; the odorant injection strategy determination module outputs the optimal odorant injection strategy based on a deep learning neural network model combined with real-time data; the control module controls multiple parameters of the odorant injection pump according to the optimal odorant injection strategy. The present invention realizes precise control and optimization of the odorant injection process through intelligent and adaptive control.

Description

An intelligent adaptive natural gas odorant concentration control system and control method

Technical Field

The present invention relates to the field of natural gas odorant concentration monitoring and control, and in particular to an intelligent self-adaptive natural gas odorant concentration control system and a control method.

Background technique

Natural gas is a colorless and odorless gas. In order to ensure that it can be detected in time when it leaks, odorants are usually added to natural gas to give it a distinct smell. However, traditional odorant injection systems usually rely on fixed injection volumes or simple control algorithms, which are difficult to adapt to changes in natural gas flow and environmental conditions, resulting in unstable odorant concentrations, affecting the safety and use of natural gas.

In addition, the traditional system lacks intelligence and adaptive capabilities, and cannot dynamically adjust the injection strategy of the odorant according to real-time data, resulting in waste of odorants and increased operating costs. In addition, when faced with complex environmental conditions and variable natural gas flow, the traditional system is difficult to ensure the uniform distribution and concentration stability of the odorant, further affecting the safety of natural gas use and user experience.

Therefore, there is an urgent need for an intelligent adaptive natural gas odorant concentration control system to achieve precise control and optimization of the odorant injection process.

Summary of the invention

In view of this, an embodiment of the present invention provides an intelligent adaptive natural gas odorant concentration control system and control method to solve the above technical problems.

To achieve the above-mentioned object, in a first aspect, an intelligent adaptive natural gas odorant concentration control system is provided, which comprises: a gas flow sensor, an odorant injection pump, an odorant concentration monitoring device, an environmental parameter sensor, an odorant characteristic sensor and a controller;

The gas flow sensor is used to obtain real-time gas flow detection data in the natural gas pipeline;

The odorant concentration monitoring device is used to obtain real-time odorant concentration detection data in natural gas;

The environmental parameter sensor is installed around the natural gas pipeline and is electrically connected to the controller to obtain real-time environmental parameters including ambient temperature, ambient humidity and atmospheric pressure;

The odorant characteristic sensor is used to detect the real-time odorant characteristic parameters in the natural gas in real time;

The odorant injection pump is connected to the odorant storage tank and is used to inject the odorant in the odorant storage tank into the natural gas pipeline under the control of the controller;

The controller comprises:

A data processing module, for receiving and processing real-time data including the real-time gas flow detection data, real-time odorant concentration detection data, real-time environmental parameters and real-time odorant characteristic parameters;

An odorant injection strategy determination module, which is used to output an optimal odorant injection strategy based on a deep learning neural network model in combination with the real-time data;

A control module is used to control multiple parameters of the odorant injection pump according to the optimal odorant injection strategy, wherein the multiple parameters include injection rate, injection duration, injection frequency and injection amount distribution.

In some possible implementations, the odorant concentration monitoring device comprises:

Odorant analysis module, used to detect the concentrations of different types of odorants in natural gas and obtain real-time odorant concentration detection data;

A temperature compensation module, used to perform temperature compensation on the real-time odorant concentration detection data according to the ambient temperature data acquired in real time, so as to obtain the odorant concentration detection data after temperature compensation;

An environmental humidity compensation module, used to perform humidity compensation on the temperature-compensated odorant concentration detection data according to the environmental humidity data acquired in real time, so as to obtain humidity-compensated odorant concentration detection data;

The atmospheric pressure compensation module is used to perform pressure compensation on the humidity-compensated odorant concentration detection data according to the atmospheric pressure data obtained in real time, so as to obtain the pressure-compensated odorant concentration detection data.

In some possible implementations, the temperature compensation module adopts the following temperature compensation algorithm:

Ctemp_comp = Craw + ktemp ×( T-Tref ); where Ctemp_comp is the odorant concentration detection data after temperature compensation, Craw is the real-time odorant concentration detection data of the preliminary detection, ktemp is the temperature compensation coefficient, T is the current real-time ambient temperature data, and Tref is the reference ambient temperature data;

The ambient humidity compensation module adopts the following temperature compensation algorithm:

Chum_comp = Ctemp_comp + k hum1 × H + k _hum2 × H2 ; wherein Chum_comp is the odorant concentration detection data after humidity compensation, Ctemp_comp is the odorant concentration detection data after temperature compensation, k _hum1 and k hum2 are humidity compensation coefficients, _and H ^is _the current real-time acquired environmental humidity data;

The atmospheric pressure compensation module adopts the following pressure compensation algorithm:

Cpress_comp = Chum_comp + kpress ×( P－Pref ); wherein , Cpress_comp is the odorant concentration detection data after pressure compensation, Chum_comp is the odorant concentration detection data after humidity compensation, kpress is the pressure compensation coefficient, P is the current real-time atmospheric pressure data, and Pref is the reference atmospheric pressure data.

In some possible implementations, the odorant characteristic sensor includes:

A density sensor for detecting the density of the odorant;

an odor intensity sensor for detecting the intensity of an odor emitted by the odorant;

Volatility sensors, used to detect the volatility characteristics of odorants in natural gas;

Surface adsorption analyzer, used to measure the adsorption characteristics of odorants on the surfaces of different materials;

Conductivity sensor, used to detect the conductivity of the odorant.

In some possible implementations, the density sensor is installed on the natural gas pipeline, electrically connected to the controller via a cable or wireless communication, and transmits the detected density data to the controller;

The odor intensity sensor is installed on the natural gas pipeline, electrically connected to the controller via a cable or wireless communication, and transmits the detected odor intensity data to the controller;

The volatility sensor is installed on the natural gas pipeline, electrically connected to the controller via a cable or wireless communication, and transmits the detected volatility data to the controller;

The surface adsorption analyzer is installed on the natural gas pipeline, electrically connected to the controller via a cable or wireless communication, and transmits the detected adsorption data to the controller;

The conductivity sensor is installed on the natural gas pipeline, and is electrically connected to the controller via a cable or wireless communication to transmit the detected conductivity data to the controller.

In some possible embodiments, the volatility sensor includes a gas chromatograph, a mass spectrometer, or a Fourier transform infrared spectrometer for detecting volatile organic compounds of the odorant;

The odor intensity sensor comprises an electronic nose, wherein the electronic nose is composed of a plurality of chemical sensors, each chemical sensor being sensitive to a different odor component;

The surface adsorption analyzer evaluates the adsorption characteristics of odorant molecules on the solid surface by measuring the adsorption amount and adsorption rate.

In some possible implementations, the deep learning-based neural network model includes:

The input layer is used to receive standardized historical data, including gas flow detection data, odorant concentration detection data, environmental parameters and odorant characteristic parameters;

A plurality of hidden layers, each of which includes a plurality of neurons, wherein the neurons use a linear rectification function as an activation function to extract and process features of input historical data;

The output layer is used to output the optimal odorant injection strategy according to the characteristics of the historical data, and the output of the output layer includes injection rate, injection duration, injection frequency and injection amount distribution.

In some possible implementations, when the hidden layer uses a multilayer perceptron structure, each hidden layer includes multiple neurons, all neurons are fully connected, and each neuron receives the output of all neurons in the previous layer and performs nonlinear transformation through an activation function;

When the hidden layer uses a convolutional neural network structure, each hidden layer includes multiple convolution kernels, each convolution kernel slides on the input data, performs local connection and weight sharing, and extracts local features;

When the hidden layer uses a long short-term memory network LSTM structure, each hidden layer includes multiple LSTM units, each LSTM unit controls the flow of information through an input gate, a forget gate and an output gate to capture long-term and short-term dependencies in sequence data.

In some possible embodiments, the controller further includes: a prediction alarm module, for calculating the consumption rate of the odorant in the natural gas pipeline based on the real-time gas flow detection data and the real-time odorant concentration detection data, and predicting the remaining amount of the odorant storage tank based on the calculated odorant consumption rate, and triggering an odorant replenishment alarm when the remaining amount is lower than a preset threshold.

In a second aspect, the present invention provides a control method according to any one of the intelligent adaptive natural gas odorant concentration control systems as described above, the control method comprising:

S1: Obtain real-time gas flow detection data in the natural gas pipeline;

S2: Obtain real-time odorant concentration detection data in natural gas;

S3: Acquire real-time environmental parameters including ambient temperature, ambient humidity and atmospheric pressure;

S4: Acquire the real-time odorant characteristic parameters in the detected natural gas;

S5: receiving and processing real-time data including the real-time gas flow detection data, real-time odorant concentration detection data, real-time environmental parameters and real-time odorant characteristic parameters;

S6: Based on the deep learning neural network model, combined with the real-time data, output the optimal odorant injection strategy;

S7: According to the optimal odorant injection strategy, multiple parameters of the odorant injection pump are controlled, the multiple parameters including injection rate, injection duration, injection frequency and injection amount distribution, and the odorant is injected into the natural gas pipeline.

The above technical solution has the following beneficial technical effects:

Through the coordinated work of gas flow sensors, odorant concentration monitoring devices, environmental parameter sensors and odorant characteristic sensors, the system can obtain high-precision detection data in real time to ensure the accuracy and reliability of the data.

Based on the deep learning neural network model, the system can combine real-time data and historical data to output the optimal odorant injection strategy and realize intelligent control. The strategy can dynamically adjust the injection rate, injection duration, injection frequency and injection volume distribution to adapt to different operating conditions and environmental changes.

The system can dynamically adjust the odorant injection strategy based on real-time data and prediction results, and has strong adaptive capabilities. Whether under high or low flow conditions, the system can maintain the stability and uniformity of the odorant concentration.

By optimizing the odorant injection strategy, the system can effectively reduce odorant waste, improve energy efficiency and reduce operating costs.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

FIG1 is a logical structure block diagram of an intelligent adaptive natural gas odorant concentration control system according to an embodiment of the present invention;

2 is a logical structure diagram of an odorant concentration monitoring device according to an embodiment of the present invention;

3 is a logical structure diagram of the odorant characteristic sensor according to an embodiment of the present invention;

FIG4 is a logical structure block diagram of a prediction alarm module according to an embodiment of the present invention;

FIG5 is a flow chart of an intelligent adaptive natural gas odorant concentration control method according to an embodiment of the present invention;

FIG. 6 is a block diagram of a logical structure of an electronic device according to an embodiment of the present invention.

Detailed ways

The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

Embodiment 1

As shown in FIG1 , this embodiment provides an intelligent adaptive natural gas odorant concentration control system, including a gas flow sensor, an odorant injection pump, an odorant concentration monitoring device, an environmental parameter sensor, an odorant characteristic sensor, and a controller.

Gas flow sensors are installed on natural gas pipelines to obtain real-time gas flow detection data in natural gas pipelines. For example, using ultrasonic flow meters, high-precision flow detection can be achieved.

The odorant concentration monitoring device is installed on the natural gas pipeline to obtain real-time odorant concentration detection data in the natural gas. For example, using an electrochemical sensor, the concentrations corresponding to different types of odorants can be detected.

Environmental parameter sensors are installed around the natural gas pipeline and electrically connected to the controller to obtain real-time environmental parameters including ambient temperature, ambient humidity and atmospheric pressure. For example, using an integrated temperature, humidity and pressure sensor module, multiple environmental parameters can be obtained simultaneously.

Odorant characteristic sensors are used to detect the real-time odorant characteristic parameters in natural gas in real time. For example, using density sensors, refractive index sensors, and conductivity sensors, the characteristics of odorants can be fully detected.

Density sensor is used to detect the density of odorant. Density is the relationship between the mass and volume of odorant, which affects the accuracy of injection amount. By detecting density in real time, the injection strategy can be adjusted according to density changes to ensure accurate injection of odorant.

Refractive index sensor, used to detect the refractive index of odorants. Refractive index is an indicator of the purity and quality of odorants, affecting their effectiveness. By detecting the refractive index in real time, the purity of the odorant can be evaluated to ensure its quality consistency.

Conductivity sensor, used to detect the conductivity of odorant. Conductivity is an indicator of the ion concentration and chemical properties of the odorant, affecting its chemical stability. By detecting conductivity in real time, the ion concentration of the odorant can be evaluated to ensure its chemical properties are stable.

The odorant injection pump is connected to the odorant storage tank and is used to inject the odorant in the odorant storage tank into the natural gas pipeline under the control of the controller. For example, using a precision metering pump, the injection amount of the odorant can be accurately controlled.

The controller includes a data processing module, an odorant injection strategy determination module and a control module. The data processing module is used to receive and process real-time data including real-time gas flow detection data, real-time odorant concentration detection data, real-time environmental parameters and real-time odorant characteristic parameters. The odorant injection strategy determination module is used to output the optimal odorant injection strategy based on a deep learning neural network model combined with the real-time data as input. The control module is used to control multiple parameters of the odorant injection pump according to the optimal odorant injection strategy, and the multiple parameters include injection rate, injection duration, injection frequency and injection amount distribution. Injection amount distribution refers to the specific way and mode in which the odorant injection pump injects odorant into the natural gas pipeline within a certain period of time. It includes aspects such as the amount of each injection and the uniformity of the injection. Specifically, uniformity refers to whether the odorant is evenly distributed in the natural gas pipeline. For example, whether it is evenly distributed over the entire length of the pipeline or concentrated in certain specific areas.

In some embodiments, the uniform distribution of the odorant in the natural gas pipeline can be determined by the following methods:

Multi-point sampling analysis: Install multiple odorant concentration monitoring devices at different locations of the natural gas pipeline to detect the odorant concentration at each location in real time. By comparing the odorant concentration data at different locations, the uniformity of odorant distribution in the pipeline can be evaluated.

Gas chromatography analysis: Collect gas samples from different locations in the natural gas pipeline and use a gas chromatograph to analyze the odorant concentration in the samples. The analysis results are used to evaluate the uniformity of the odorant distribution in the pipeline.

Spectral analysis: Use spectral analysis techniques (such as Fourier transform infrared spectrometer FTIR) to detect the concentration of odorant at different locations in the natural gas pipeline. The spectral data can be used to evaluate the uniformity of the odorant distribution in the pipeline.

Fluid dynamics simulation: Computational Fluid Dynamics (CFD) is used to simulate the flow of natural gas and odorant in the pipeline. The simulation results are used to evaluate the uniformity of the odorant distribution in the pipeline.

Evenly distributed odorants can ensure that leaks at any location can be detected in time when natural gas leaks, thereby improving the safety of natural gas. If the odorant is unevenly distributed, the odorant concentration in some areas may be too low, resulting in the failure to detect leaks in time, increasing safety hazards. By real-time monitoring of the uniformity of odorant distribution, the odorant injection strategy can be dynamically adjusted to ensure uniform distribution of odorants in the pipeline. For example, when it is detected that the odorant concentration in some areas is low, the odorant injection amount in that area can be increased to ensure overall uniform distribution.

The intelligent adaptive natural gas odorant concentration control system embodies its intelligent adaptive characteristics through real-time data collection and processing, intelligent decision-making based on deep learning, dynamic adjustment of injection strategy, prediction and early warning functions, and self-learning and optimization. The system can dynamically adjust the odorant injection strategy based on real-time data and historical data to ensure the uniform distribution of odorants in the natural gas pipeline and improve the safety and use effect of natural gas.

The working method of the intelligent adaptive natural gas odorant concentration control system includes the following steps:

S11: Data acquisition. The gas flow sensor acquires the gas flow detection data in the natural gas pipeline in real time and transmits the data to the controller. The odorant concentration monitoring device acquires the odorant concentration detection data in the natural gas in real time and transmits the data to the controller. The environmental parameter sensor acquires environmental parameters such as ambient temperature, ambient humidity and atmospheric pressure in real time and transmits the data to the controller. The odorant characteristic sensor detects the characteristic parameters of the odorant in real time and transmits the data to the controller.

S12: Data processing: The data processing module receives and processes the above real-time data, performs data cleaning and preprocessing, and ensures the accuracy and consistency of the data.

S13: Strategy calculation. The odorant injection strategy determination module outputs the optimal odorant injection strategy based on the deep learning neural network model and the processed real-time data. For example, the neural network model can be trained and optimized based on historical data and real-time data to improve the accuracy and robustness of the strategy. The output layer of the neural network model outputs the optimal odorant injection strategy, including injection rate, injection duration, injection frequency, and injection amount distribution.

S14: Control execution. The control module controls multiple parameters of the odorant injection pump, including injection rate, injection duration, injection frequency and injection volume distribution, according to the output optimal odorant injection strategy. For example, under high flow conditions, the control module can increase the injection rate and injection frequency to ensure the stability of the odorant concentration. By adjusting the injection rate, injection duration, injection frequency and injection volume distribution in real time, it is beneficial to ensure the stability and uniformity of the odorant concentration and improve the safety of natural gas. By dynamically adjusting the injection parameters, excessive or insufficient odorant injection can be avoided, the waste of odorants can be reduced, and the efficiency of resource utilization can be improved. Through real-time data and deep learning models, the system can adapt to different flow rates and environmental conditions, flexibly adjust the injection strategy, and ensure the stability of the odorant concentration. By optimizing the injection strategy, the waste of odorants and operating costs can be reduced, and the economy of the system can be improved.

The following example illustrates that, in a natural gas pipeline system, the gas flow sensor detects that the current natural gas flow is 500 cubic meters per hour, the odorant concentration monitoring device detects that the current odorant concentration is 10 ppm, the environmental parameter sensor detects that the ambient temperature is 25 degrees Celsius, the ambient humidity is 60%, and the atmospheric pressure is 1013 hPa, and the odorant characteristic sensor detects that the density of the odorant is 0.8 g/cm³, the odor intensity is 50 ppm, the volatility characteristic is 20 kPa, the adsorption amount on the metal surface is 0.5 mg/m², and the conductivity is 0.1 S/m. The data processing module of the controller receives and processes the above data, and the odorant injection strategy determination module calculates the optimal odorant injection strategy based on the deep learning neural network model and real-time data. According to the strategy, the control module controls the injection rate of the odorant injection pump to be 0.5 liters per hour, the injection time to be 10 minutes, the injection frequency to be once per hour, and the injection amount distribution to be uniform.

In some embodiments, the intelligent adaptive natural gas odorant concentration control system has a self-learning module, which continuously optimizes and updates the odorant injection strategy based on historical data and real-time data to improve the system's adaptability and accuracy. Through self-learning and optimization, the system can adapt to different operating conditions and environmental changes, and realize intelligent and adaptive odorant injection control.

The training process of the deep learning-based neural network model includes the following steps:

S21: Data collection and preprocessing.

First, the system needs to collect various data generated during operation, including gas flow detection data, odorant concentration detection data, environmental parameters (ambient temperature, ambient humidity, atmospheric pressure) and odorant characteristic parameters (density, odor intensity, volatility, adsorption characteristics, conductivity). These data are cleaned to remove outliers and noise, and fill in missing values. Next, standardize data of different dimensions to the same range (for example, standardize all data to the range of 0-1) to improve the training effect of the model. Finally, divide the data set into training set, validation set and test set, with a ratio of 70% training set, 15% validation set, and 15% test set.

S22: Model construction.

The structure of the neural network model includes an input layer, a hidden layer, and an output layer. The input layer receives preprocessed input data, including gas flow, odorant concentration, environmental parameters, and odorant characteristic parameters. The hidden layer includes multiple neuron layers, which are used to extract and process the features of the input data. Structures such as Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), or Long Short-Term Memory (LSTM) can be used. The output layer outputs the optimal odorant injection strategy, including injection rate, injection duration, injection frequency, and injection amount distribution. In an example, the hidden layer uses 3 layers, each layer contains 64 neurons, and the activation function is ReLU.

In the neural network model, the structure of the hidden layer can adopt different architectures such as multi-layer perceptron (MLP), convolutional neural network (CNN) or long short-term memory network (LSTM). Each hidden layer is composed of multiple neurons, which have different functions and connection methods in different network architectures. The following is the logical relationship between these architectures and neurons:

In a multi-layer perceptron (MLP), each hidden layer consists of multiple neurons, and all neurons are fully connected. Each neuron receives the output of all neurons in the previous layer, and performs a nonlinear transformation through an activation function (such as ReLU), and outputs it to all neurons in the next layer. Assume that a hidden layer has 64 neurons, and each neuron receives the output of all neurons in the previous layer and processes it through the ReLU activation function.

In a convolutional neural network (CNN), each hidden layer consists of multiple convolutional filters, each of which is equivalent to a neuron. The convolutional kernel slides over the input data, performs local connections and weight sharing, and extracts local features. The convolutional layer is usually followed by a pooling layer to reduce the data dimension. Assume that a convolutional layer has 32 convolutional kernels, each of which slides over the input data, extracts local features, and is processed by the ReLU activation function.

In a long short-term memory network (LSTM), each hidden layer consists of multiple LSTM units, and each LSTM unit is equivalent to a neuron. LSTM units control the flow of information through input gates, forget gates, and output gates, and can capture long-term and short-term dependencies in sequence data. Assume that an LSTM layer has 128 LSTM units, each unit receives the output of the previous layer and its own state, and processes them through a gating mechanism.

S23: Model training.

During the model training process, a suitable loss function (such as Mean Square Error (MSE)) is selected to measure the difference between the model's predicted value and the true value, and an optimization algorithm (such as Adam (Adaptive Moment Estimation) and SGD (Stochastic Gradient Descent)) is used to minimize the loss function and adjust the model parameters. The model is trained through multiple iterations (epochs), and each iteration uses a batch of data for parameter update. Hyperparameters such as learning rate, batch size, number of hidden layers, and number of neurons also need to be adjusted during training to find the optimal model structure. The learning rate controls the step size of the parameter update. Too large or too small a learning rate will affect the convergence of the model. The batch size is the amount of data used in each iteration, and the batch size affects the training speed and model performance.

In one example, the following parameters are used for model training: the loss function is mean square error (MSE), the optimization algorithm is Adam, the learning rate is 0.001, the batch size is 32, and the training iteration is 5000. During the training process, the model learns the characteristics of the data through multiple iterations (epochs) and continuously adjusts the parameters to minimize the loss function. Compared with the models in the prior art, the application of the neural network model based on deep learning in the intelligent adaptive natural gas odorant concentration control system of this embodiment has the following advantages: using the mean square error (MSE) as the loss function can effectively measure the difference between the model prediction value and the true value, ensuring the high-precision prediction of the model; using the Adam optimization algorithm, the learning rate can be adaptively adjusted to improve the convergence speed and stability of the model; the model learns the characteristics of the data through multiple iterations (epochs) and continuously adjusts the parameters to minimize the loss function, and can dynamically adapt to real-time data and environmental changes to provide the optimal odorant injection strategy; using the mini-batch gradient descent method with a batch size of 32, it can improve the generalization ability of the model while ensuring the training speed and avoid overfitting; deep learning models (such as multi-layer perceptron MLP, convolutional neural network CNN, long short-term memory network LSTM) have powerful feature extraction and representation capabilities, can extract useful features from complex multidimensional data, and improve the prediction and control capabilities of the model; deep learning models are highly flexible and scalable, and the model structure and parameters can be adjusted according to specific application requirements to adapt to different operating conditions and environmental changes.

S24: Model validation and testing.

During the model validation process, the validation set data is used to evaluate the performance of the model and adjust the hyperparameters to improve the generalization ability of the model. The stability and reliability of the model are further verified through the cross-validation method. During the model testing process, the test set data is used to evaluate the performance of the final model to ensure that the model has good predictive ability on unseen data.

S25: Model deployment and application.

The trained model is deployed to the controller, which receives and processes input data in real time and outputs the optimal odorant injection strategy. The controller dynamically adjusts multiple parameters of the odorant injection pump according to the injection strategy output by the model to achieve intelligent and adaptive odorant injection control. In one example, for example, the injection strategy output by the model is: injection rate 0.5 liters/hour, injection duration 10 minutes, injection frequency once per hour, and injection volume evenly distributed.

In some embodiments, dynamic adjustment of the injection rate can be achieved. The control module dynamically adjusts the injection rate of the odorant according to the real-time gas flow rate, odorant concentration, ambient temperature and ambient humidity. In the case of high flow rate and high temperature, the injection rate is increased; in the case of low flow rate and low temperature, the injection rate is reduced. For example, when the gas flow rate increases to 600 cubic meters per hour, the injection rate is automatically adjusted to 0.6 liters per hour.

In some embodiments, dynamic adjustment of the injection duration can be achieved. The control module dynamically adjusts the duration of each injection according to the fluctuation of the natural gas flow, the change of the odorant concentration and the ambient humidity. When the flow fluctuation is large and the humidity is high, the injection duration is extended to ensure the concentration is stable; when the flow is stable and the humidity is low, the injection duration is shortened. For example, when the flow fluctuation is large, the injection duration is automatically adjusted to 15 minutes.

In some embodiments, dynamic adjustment of the injection frequency can be achieved. The control module dynamically adjusts the interval between injection operations according to the natural gas flow rate, the frequency of change of the odorant concentration, and the ambient pressure. In the case of frequent flow changes and low pressure, the injection frequency is increased; in the case of stable flow and high pressure, the injection frequency is reduced. For example, when the flow changes frequently, the injection frequency is automatically adjusted to once every 30 minutes.

In some embodiments, dynamic adjustment of the injection amount distribution can be achieved. The control module dynamically adjusts the distribution of the odorant according to the pipeline length, natural gas flow characteristics and odorant characteristic parameters. In the case of long-distance pipelines and high-volatility odorants, a multi-point injection method is used to ensure uniform distribution of the odorant; in the case of short-distance pipelines and low-volatility odorants, a single-point injection method is used. For example, in a long-distance pipeline, the injection amount distribution is automatically adjusted to a multi-point uniform distribution.

For example, in a natural gas pipeline system, the gas flow sensor detects that the current natural gas flow is 500 cubic meters per hour, and the odorant concentration monitoring device detects that the current odorant concentration is 10 ppm. The environmental parameter sensor detects that the ambient temperature is 25 degrees Celsius, the ambient humidity is 60%, and the atmospheric pressure is 1013 hPa. The odorant characteristic sensor detects that the density of the odorant is 0.8 g/cm³, the odor intensity is 50 ppm, the volatility characteristic is 20 kPa, the adsorption amount on the metal surface is 0.5 mg/m², and the conductivity is 0.1 S/m. The system obtains the above data in real time and performs data cleaning and preprocessing. The odorant injection strategy determination module calculates the optimal odorant injection strategy based on the deep learning neural network model and real-time data. The control module dynamically adjusts multiple parameters of the odorant injection pump according to the output optimal odorant injection strategy. For example, the current optimal odorant injection strategy is: injection rate 0.5 liters/hour, injection time 10 minutes, injection frequency once an hour, and injection volume distribution is uniform. The dynamic adjustment is as follows: When the gas flow rate increases to 600 cubic meters per hour, the control module automatically adjusts the injection rate to 0.6 liters per hour. When the flow rate fluctuates greatly and the ambient humidity is high, the control module automatically adjusts the injection duration to 15 minutes. When the flow rate changes frequently and the atmospheric pressure is low, the control module automatically adjusts the injection frequency to once every 30 minutes. In the case of long-distance pipelines and high volatility of the odorant, the control module automatically adjusts the injection volume distribution to a multi-point uniform distribution.

The intelligent adaptive natural gas odorant concentration control system of this embodiment realizes precise control of the odorant injection process by integrating multiple sensors and a control algorithm based on deep learning, and has the following technical effects:

Through the coordinated work of gas flow sensors, odorant concentration monitoring devices, environmental parameter sensors and odorant characteristic sensors, the system can obtain high-precision detection data in real time to ensure the accuracy and reliability of the data.

Based on the deep learning neural network model, the system can combine real-time data and historical data to output the optimal odorant injection strategy and realize intelligent control. The strategy can dynamically adjust the injection rate, injection duration, injection frequency and injection volume distribution to adapt to different operating conditions and environmental changes.

The system can dynamically adjust the odorant injection strategy based on real-time data and prediction results, and has strong adaptive capabilities. Whether under high or low flow conditions, the system can maintain the stability and uniformity of the odorant concentration.

By optimizing the odorant injection strategy, the system can effectively reduce odorant waste, improve energy efficiency and reduce operating costs.

Embodiment 2

As shown in FIG. 2 , this embodiment provides an odorant concentration monitoring device for an intelligent adaptive natural gas odorant concentration control system, including an odorant analysis module, a temperature compensation module, an ambient humidity compensation module, and an atmospheric pressure compensation module.

The odorant analysis module is used to detect the concentrations of different types of odorants in natural gas and obtain real-time odorant concentration detection data. In some embodiments, a spectral analysis module, a gas chromatography module and a semiconductor gas sensor may be used. The gas chromatography module is used to detect the concentrations of different types of odorants in natural gas and obtain real-time odorant concentration detection data. The gas chromatography module is a technology based on gas separation and detection, which can detect multiple gas components at the same time. The gas chromatography module separates the components in the mixed gas through a separation column, and then detects the concentration of each component through a detector. The spectral analysis module is used to detect the concentrations of different types of odorants in natural gas and obtain real-time odorant concentration detection data. Spectral analysis technology determines the concentration of gas molecules by detecting their light absorption or emission characteristics. Specifically, the spectral analysis module includes a light source, a sample cell, a spectrometer and a detector. The light source emits light in a specific wavelength range, and ultraviolet light, visible light or infrared light can be used. The selection of the light source depends on the light absorption or emission characteristics of the gas molecules to be measured. The gas to be measured passes through the sample cell, and the light emitted by the light source passes through the gas molecules in the sample cell. The design of the sample cell ensures that the light can pass through the gas sample evenly. The spectrometer is used to separate and analyze the light after passing through the sample cell, decompose the light into spectra of different wavelengths, and measure the light intensity of each wavelength. Gas molecules absorb or emit light within a specific wavelength range, resulting in characteristic absorption peaks or emission peaks in the spectrum. The detector is used to measure the light intensity output by the spectrometer and convert it into an electrical signal. The output signal of the detector is proportional to the concentration of the gas molecules. The processor receives the output signal of the detector and performs data processing through the spectrum analysis software, and determines the concentration of the odorant gas molecules by comparing the intensity and position of the characteristic absorption peaks or emission peaks in the spectrum.

The temperature compensation module is used to perform temperature compensation on the real-time odorant concentration detection data according to the ambient temperature data obtained in real time, so as to obtain the temperature-compensated odorant concentration detection data.

The environmental humidity compensation module is used to perform humidity compensation on the temperature-compensated odorant concentration detection data according to the environmental humidity data acquired in real time, so as to obtain the humidity-compensated odorant concentration detection data.

The atmospheric pressure compensation module is used to perform pressure compensation on the humidity-compensated odorant concentration detection data according to the atmospheric pressure data acquired in real time, so as to obtain the pressure-compensated odorant concentration detection data.

The working process of the odorant concentration monitoring device includes the following steps:

S31: Data collection.

The odorant analysis module detects the odorant concentration in natural gas in real time and obtains preliminary odorant concentration detection data. The temperature sensor obtains the ambient temperature data in real time, the humidity sensor obtains the ambient humidity data in real time, and the pressure sensor obtains the atmospheric pressure data in real time.

S32: Temperature compensation.

The temperature compensation module performs temperature compensation on the preliminary detected odorant concentration detection data based on the temperature compensation algorithm according to the real-time acquired ambient temperature data, and obtains the temperature-compensated odorant concentration detection data. The temperature compensation algorithm can use a linear regression model, assuming that the effect of ambient temperature on odorant concentration is a linear relationship:

Ctemp _ comp = Craw + ktemp × ( T - Tref ).

Wherein, Ctemp_comp is the odorant concentration detection data after temperature compensation, Craw is the real-time odorant concentration detection data of preliminary detection, ktemp is the temperature compensation coefficient, T is the current real-time acquired ambient temperature data, and Tref is the reference ambient temperature data.

S33: Humidity compensation.

The ambient humidity compensation module performs humidity compensation on the temperature-compensated odorant concentration detection data based on the ambient humidity data obtained in real time, and obtains humidity-compensated odorant concentration detection data. The humidity compensation algorithm can use a polynomial regression model, assuming that the effect of humidity on concentration is a nonlinear relationship:

Chum_comp = Ctemp_comp + k _hum1 × H + k _hum2 ^× H2

Wherein, Chum_comp is the odorant concentration detection data after humidity compensation, Ctemp_comp is the odorant concentration detection data after temperature compensation, k _{hum 1} and k _{hum 2} are humidity compensation coefficients, and H is the current real-time acquired environmental humidity data.

S33: Pressure compensation.

The atmospheric pressure compensation module performs pressure compensation on the humidity-compensated odorant concentration detection data based on the atmospheric pressure data obtained in real time, and obtains the pressure-compensated odorant concentration detection data. The pressure compensation algorithm can use a linear regression model, assuming that the effect of pressure on concentration is a linear relationship:

Cpress_comp = Chum_comp + kpress × ( P－Pref ).

Wherein, Cpress_comp is the odorant concentration detection data after pressure compensation, Chum_comp is the odorant concentration detection data after humidity compensation, kpress is the pressure compensation coefficient, P is the atmospheric pressure data currently acquired in real time, and Pref is the reference atmospheric pressure data.

The odorant concentration monitoring device of this embodiment integrates the odorant analysis module, the temperature compensation module, the ambient humidity compensation module and the atmospheric pressure compensation module to achieve high-precision detection and multiple compensation of the odorant concentration in natural gas, and has the following specific technical effects:

The odorant analysis module uses an electrochemical sensor that can detect the concentration of different types of odorants in natural gas with high sensitivity and selectivity. The electrochemical sensor can accurately detect low-concentration odorant components through the principle of electrochemical reaction, ensuring the reliability and accuracy of the test results.

The temperature compensation module uses the real-time acquired ambient temperature data to perform temperature compensation on the odorant concentration test data. The temperature compensation algorithm can eliminate the influence of ambient temperature on the test results and ensure the consistency and accuracy of the test results under different temperature conditions. For example, when the ambient temperature changes greatly, the temperature compensation module can dynamically adjust the test data and provide accurate concentration values after temperature compensation.

The ambient humidity compensation module uses the ambient humidity data acquired in real time to perform humidity compensation on the odorant concentration test data after temperature compensation. The humidity compensation algorithm can eliminate the influence of ambient humidity on the test results and ensure the stability and reliability of the test results under different humidity conditions. For example, in a high humidity environment, the humidity compensation module can effectively adjust the test data and provide accurate concentration values after humidity compensation.

The atmospheric pressure compensation module uses the atmospheric pressure data acquired in real time to perform pressure compensation on the odorant concentration test data after humidity compensation. The pressure compensation algorithm can eliminate the influence of atmospheric pressure on the test results and ensure the accuracy and consistency of the test results under different pressure conditions. For example, in high-altitude or low-altitude environments, the pressure compensation module can dynamically adjust the test data and provide accurate concentration values after pressure compensation.

By integrating temperature compensation, humidity compensation and pressure compensation modules, the odorant concentration monitoring device realizes a multiple compensation mechanism. The multiple compensation mechanism can comprehensively consider the impact of ambient temperature, humidity and pressure on the detection results, and provide high-precision odorant concentration detection data after multiple compensation. The multiple compensation mechanism ensures the stability and reliability of the detection results and is suitable for odorant concentration detection under various complex environmental conditions.

The odorant concentration monitoring device can monitor the odorant concentration in natural gas in real time and make dynamic adjustments based on the environmental parameters obtained in real time. The real-time monitoring and dynamic adjustment functions ensure the real-time and accuracy of the test data, can promptly reflect changes in environmental conditions, and provide accurate odorant concentration test results.

Through high-precision odorant concentration detection and multiple compensation mechanisms, the odorant concentration monitoring device can provide accurate detection data for the intelligent adaptive natural gas odorant concentration control system. Accurate detection data can improve the overall performance of the system, ensure the accuracy and effectiveness of the odorant injection strategy, optimize the use of odorants, and improve the intelligence and adaptability of the system.

Embodiment 3

As shown in FIG3 , this embodiment provides an odorant characteristic sensor for an intelligent adaptive natural gas odorant concentration control system, including any multiple of a density sensor, an odor intensity sensor, a volatility sensor, a surface adsorption analyzer, and a conductivity sensor.

The density sensor is installed on the natural gas pipeline to detect the density of the odorant in the gas state in real time. The density sensor is electrically connected to the controller through a cable and transmits the detected density data to the controller. The working process of the gas density sensor is to calculate its density by measuring the mass and volume of the gas.

The odor intensity sensor is installed on the natural gas pipeline to detect the odor intensity emitted by the odorant in real time. The odor intensity sensor is electrically connected to the controller via a cable and transmits the detected odor intensity data to the controller. The working process of the odor intensity sensor is to generate an electrical signal proportional to the odor intensity by detecting the chemical reaction between gas molecules and the sensor surface.

The volatility sensor is installed on the natural gas pipeline to detect the volatility characteristics of the odorant in the natural gas in real time. The volatility sensor is electrically connected to the controller through a cable or wireless communication to transmit the detected volatility data to the controller. The working process of the volatility sensor is to evaluate the volatility of the gas molecules by measuring their vapor pressure.

The surface adsorption analyzer is installed on the natural gas pipeline to measure the adsorption characteristics of odorants on the surfaces of different materials. The surface adsorption analyzer is electrically connected to the controller via a cable or wireless communication to transmit the detected adsorption data to the controller. The working process of the surface adsorption analyzer is to evaluate the adsorption characteristics of gas molecules by measuring the amount of adsorption on the surfaces of different materials.

The conductivity sensor is installed on the natural gas pipeline to detect the conductivity of the odorant in the gas state in real time. The conductivity sensor is electrically connected to the controller through a cable or wireless communication to transmit the detected conductivity data to the controller. The working process of the gas conductivity sensor is to evaluate the ion concentration and chemical properties of the gas by measuring its conductivity.

All sensors (density sensor, odor intensity sensor, volatility sensor, surface adsorption analyzer and conductivity sensor) are installed on the natural gas pipeline, adjacent to each other, forming a sensor array. This ensures that all sensors can simultaneously detect the characteristic parameters of the odorant when the natural gas flows through the pipeline. All sensors are electrically connected to the controller through cables or wireless communication. The output of each sensor is connected to the input of the controller through cables or wireless communication, and the controller receives and processes the detection data from each sensor.

Specifically, volatility refers to the ability or tendency of an odorant to evaporate in a gas. Substances with higher volatility tend to change easily from a liquid or solid state to a gas state, and therefore are more likely to be evenly distributed in natural gas. Volatility characteristics are very important for odorants because they directly affect the rate and effectiveness of the odorant's diffusion, which in turn affects the odor perception of natural gas when it is used.

When testing volatility, a certain amount of natural gas sample is first extracted from the natural gas pipeline through a sampling device. The sampling device needs to ensure the representativeness of the sample and prevent the sample from changing during the collection process.

The volatile organic compounds were then tested using the following analytical equipment:

Gas Chromatograph (GC): A gas chromatograph is a device that detects volatile organic compounds. A gas sample is injected into the gas chromatograph and the components in the sample are separated in the chromatographic column by the carrier gas (such as helium or nitrogen). Different components move at different speeds in the chromatographic column according to their chemical properties and are eventually detected at the detector. The detector converts these signals into a chromatogram, which shows the relative concentration and volatility of each component.

Mass spectrometer (MS): The combination of gas chromatograph and mass spectrometer (GC-MS) can further improve the detection accuracy. After the sample is separated in the gas chromatography column, it enters the mass spectrometer, which identifies the chemical structure and concentration of each component by ionizing and detecting the mass-charge ratio of molecular fragments. This method can provide very accurate qualitative and quantitative information of volatile organic compounds.

Fourier Transform Infrared Spectrometer (FTIR): FTIR can analyze the composition and concentration of volatile organic compounds by detecting their absorption characteristics in the infrared spectral region. The gas sample is introduced into the FTIR, and when infrared light passes through the sample, various components absorb infrared light of specific wavelengths, thereby producing characteristic absorption spectra. By analyzing these spectra, the type and content of volatile organic compounds can be determined.

Electronic nose: The electronic nose is a sensor system that simulates the human sense of smell. It consists of multiple chemical sensors, each of which is sensitive to different volatile organic compounds. When the sample gas passes through the sensor array, the response signal generated by each sensor is processed and pattern recognized to obtain the characteristic fingerprint of the volatile components in the sample. This method can quickly detect and distinguish different volatile organic compounds.

Volatility testing is essential to ensure uniform distribution of natural gas odorants throughout the pipeline system. Highly volatile odorants diffuse quickly, ensuring that they can be sensed by smell even at low concentrations, thereby improving the safety of natural gas. In addition, testing the volatility characteristics of odorants can also help optimize the formulation and use strategy of odorants, improving their effectiveness and economy.

Specifically, odor intensity refers to the degree to which a substance is perceived by the sense of smell in the gas phase. Odor intensity is related to volatility, but it depends not only on the volatility of the substance, but also on its chemical properties and the sensitivity of the human olfactory system. The equipment for detecting odor intensity is as follows: Odor sensor (electronic nose), which consists of multiple chemical sensors, each of which is sensitive to different odor components, simulating the human olfactory system. Volatility focuses on the ability and speed of a substance to enter the gaseous state, which mainly affects the distribution of the substance in the gas phase. Odor intensity focuses on the effect of a substance on the sense of smell in the gas phase, which mainly affects the strength of the odor perceived by humans. The detection of volatility mainly relies on equipment such as gas chromatography, mass spectrometry, and infrared spectroscopy, which analyze the chemical composition and concentration of substances. The detection of odor intensity relies more on odor sensors (electronic noses), which focus on the effect of substances on the sense of smell.

Specifically, adsorption characteristics refer to the adsorption behavior of odorants on the inner wall of natural gas pipelines or containers. This behavior describes how odorant molecules are captured and retained by surface materials when they contact solid surfaces (such as pipeline walls, storage tank inner walls, etc.). Adsorption characteristics have an important impact on the effectiveness and concentration control of odorants. Excessive adsorption will cause the odorant to be captured by the solid surface during transportation, reducing its effective concentration in natural gas, thereby affecting the function of the odorant. At the same time, understanding the adsorption characteristics helps to select suitable pipeline materials and coatings to reduce the loss of odorants. The surface adsorption analyzer evaluates its adsorption characteristics by measuring the adsorption amount and adsorption rate of odorant molecules on the solid surface.

The working process of the odorant characteristic sensor includes the following steps:

S41, Density detection: Natural gas flows through the density sensor, which measures the mass and volume of the gas, calculates its density, and transmits the density data to the controller.

S42. Odor intensity detection: Natural gas flows through the odor intensity sensor. The sensor detects the chemical reaction between gas molecules and the sensor surface, generates an electrical signal proportional to the odor intensity, and transmits the odor intensity data to the controller.

S43, Volatility detection: Natural gas flows through the volatility sensor, which evaluates its volatility by measuring the vapor pressure of gas molecules and transmits the volatility data to the controller.

S44, Surface adsorption detection: Natural gas flows through the surface adsorption analyzer. The sensor evaluates its adsorption characteristics by measuring the amount of gas molecules adsorbed on the surfaces of different materials and transmits the adsorption data to the controller.

S45, Conductivity detection: Natural gas flows through the conductivity sensor, which measures the conductivity of the gas, evaluates its ion concentration and chemical properties, and transmits the conductivity data to the controller.

Assume that in a natural gas pipeline system, the following are the detection data of various sensors: The density sensor detects that the current odorant density in the natural gas is 0.8 g/cm³. The odor intensity sensor detects that the current odorant odor intensity is 50 ppm. The volatility sensor detects that the current vapor pressure of the odorant is 20 kPa. The surface adsorption analyzer detects that the current adsorption amount of the odorant on the metal surface is 0.5 mg/m². The conductivity sensor detects that the current conductivity of the odorant is 0.1 S/m. The controller receives and processes the above data, and combines the data from other sensors to calculate the optimal odorant injection strategy.

In the intelligent adaptive natural gas odorant concentration control system, adding odorant characteristic sensors and real-time detection of various characteristic parameters of the odorant (density, odor intensity, volatility, surface adsorption, conductivity) can significantly improve the accuracy and intelligence of the system.

By real-time detection of odorant density, odor intensity, volatility, surface adsorption and conductivity and other characteristic parameters, the system can fully understand the physical and chemical properties of the odorant, so as to formulate a more accurate injection strategy. For example, density detection can help determine the mass and volume relationship of the odorant to ensure the accuracy of the injection amount; odor intensity detection can ensure that the odor effect of the odorant meets the expectations; volatility detection can evaluate the diffusion capacity of the odorant in natural gas to ensure its uniform distribution; surface adsorption detection can evaluate the adsorption of the odorant on the inner wall of the pipeline to avoid the loss of the odorant; conductivity detection can evaluate the ion concentration and chemical properties of the odorant to ensure its chemical stability.

By real-time monitoring of various characteristic parameters of the odorant, the system can dynamically adjust the injection strategy according to real-time data to ensure the best effect of the odorant under different environmental conditions. For example, in a high temperature and high humidity environment, the odorant with higher volatility needs to increase the injection frequency and injection amount; in a low temperature and low humidity environment, the odorant with higher density needs to extend the injection time and increase the injection rate; in the case of severe adsorption on the inner wall of the pipeline, the injection amount distribution needs to be adjusted to ensure the uniform distribution of the odorant in the pipeline.

By comprehensively analyzing the various characteristic parameters of the odorant, the system can adaptively adjust the injection strategy to adapt to different operating conditions and environmental changes, and improve the system's adaptive ability. For example, the system can predict the consumption rate and remaining amount of the odorant based on real-time data and historical data, and adjust the injection strategy in advance to avoid insufficient or excessive odorant; the system can optimize the injection strategy based on the characteristic parameters of the odorant to ensure the uniform distribution of the odorant under different pipe lengths and flow characteristics.

By precisely controlling the injection amount and distribution of the odorant, the system can ensure the odor effect and safety of natural gas and improve the user experience. For example, evenly distributed odorants can ensure that natural gas leaks can be detected in time, improving the safety of natural gas; precisely controlled odorant injection amount can ensure that natural gas has a consistent odor perception when used, improving the user's experience.

By precisely controlling the injection volume and distribution of odorants, the system can reduce odorant waste, improve resource utilization efficiency, and reduce operating costs. For example, by real-time monitoring and dynamically adjusting the injection strategy, the system can avoid excessive or insufficient odorant injection and reduce odorant waste; by optimizing the injection strategy, the system can improve the efficiency of odorant use and reduce operating costs.

The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

Embodiment 4

As shown in FIG4 , this embodiment provides a prediction alarm module for an intelligent adaptive natural gas odorant concentration control system. The prediction alarm module is used to calculate the consumption rate of the odorant in the natural gas pipeline according to the real-time gas flow detection data and the real-time odorant concentration detection data, and predict the remaining amount of the odorant storage tank according to the calculated odorant consumption rate. When the remaining amount is lower than a preset threshold, an odorant replenishment alarm is triggered.

The prediction alarm module is installed in the controller and is electrically connected to the gas flow sensor and the odorant concentration monitoring device through a cable or wireless communication. The prediction alarm module receives and processes real-time data from the gas flow sensor and the odorant concentration monitoring device.

The working process of the prediction alarm module includes the following steps:

S51, data collection: the prediction alarm module receives in real time the gas flow data detected by the gas flow sensor and the odorant concentration data detected by the odorant concentration monitoring device.

S52, consumption rate calculation: The prediction alarm module calculates the consumption rate of the odorant in the natural gas pipeline based on the real-time gas flow detection data and the real-time odorant concentration detection data. The calculation formula of the consumption rate is as follows:

Consumption rate = gas flow rate × odorant concentration.

S53, Remaining quantity prediction: The prediction alarm module uses advanced prediction algorithms, such as time series analysis (ARIMA (Autoregressive Integrated Moving Average) model), machine learning algorithms (such as random forest, support vector machine) or deep learning algorithms (such as LSTM) to predict the remaining quantity of the odorant tank. The prediction algorithm not only considers the current consumption rate, but also combines historical data and environmental parameters for comprehensive analysis.

During the operation of the prediction alarm module, the prediction algorithm not only considers the current consumption rate, but also conducts a comprehensive analysis in combination with historical data and environmental parameters to improve the accuracy and reliability of the prediction. Specifically, the current consumption rate is calculated using real-time gas flow detection data and odorant concentration detection data. Prediction algorithms such as time series analysis (ARIMA model), machine learning algorithms (such as random forests, support vector machines), or deep learning algorithms (such as LSTM) will use the current consumption rate as one of the input variables. At the same time, the prediction algorithm will also use historical data, including past gas flow, odorant concentration, ambient temperature, ambient humidity, atmospheric pressure and other parameters, to capture the time dependency and trend in the data. In addition, environmental parameters such as temperature, humidity and pressure will also be used as input variables to help the algorithm better understand and predict the consumption pattern of the odorant. By comprehensively analyzing the current consumption rate, historical data and environmental parameters, the prediction algorithm can more accurately predict the remaining amount of the odorant tank, trigger the alarm in time, and ensure the normal operation of the system and the timely replenishment of the odorant.

S54, alarm triggering: when the predicted remaining amount of the odorant storage tank is lower than a preset threshold, the prediction alarm module triggers an odorant replenishment alarm to notify the operator to replenish the odorant.

Assume that in a natural gas pipeline system, the gas flow sensor detects that the current natural gas flow is 500 cubic meters per hour, and the odorant concentration monitoring device detects that the current odorant concentration is 10 ppm. The initial storage capacity of the odorant storage tank is 1000 liters, and the preset threshold is 100 liters.

In the data collection step, the predictive alarm module receives gas flow data (500 m3/h) and odorant concentration data (10 ppm) in real time.

In the consumption rate calculation step, the prediction alarm module calculates the consumption rate of the odorant:

Consumption rate = 500 cubic meters/hour × 10ppm = 5 liters/hour.

In the remaining quantity prediction step, the prediction alarm module uses the LSTM model to predict the remaining quantity. The LSTM model predicts the future odorant consumption by learning historical data and current data. Assuming that after 100 hours of operation, the LSTM model predicts the consumption rate for the next 80 hours as follows:

Future consumption rate = [5.1, 5.2, 5.0, 4.9, 5.3, …] L/h.

Based on the predicted consumption rate, calculate the total consumption for the next 80 hours:

.

Assuming the total consumption is 400 liters, the remaining volume is forecasted as follows:

Remaining volume = 1000 liters − 400 liters = 600 liters.

In the alarm triggering step, when the predicted remaining amount of the odorant tank is lower than the preset threshold (100 liters), the prediction alarm module triggers the odorant replenishment alarm. Assuming that after 180 hours of operation, the LSTM model predicts that the total consumption in the next 20 hours will be 100 liters, the remaining amount is calculated as follows:

Remaining volume = 600 liters − 100 liters = 500 liters.

At this time, the prediction alarm module triggers the odorant replenishment alarm to notify the operator to replenish the odorant.

The prediction alarm module uses advanced prediction algorithms, combined with real-time monitoring and historical data, to accurately predict the remaining amount of the odorant tank and trigger an alarm when necessary to ensure the normal operation of the system and timely replenishment of the odorant.

Embodiment 5

As shown in FIG5 , this embodiment provides an intelligent adaptive natural gas odorant concentration control method, comprising the following steps:

S1: Obtain real-time gas flow detection data in the natural gas pipeline.

The gas flow sensor installed on the natural gas pipeline can obtain the gas flow detection data in the natural gas pipeline in real time. For example, the gas flow sensor detects that the current natural gas flow is 500 cubic meters per hour.

S2: Obtain real-time odorant concentration detection data in natural gas.

The odorant concentration monitoring device installed on the natural gas pipeline can obtain the odorant concentration detection data in real time. For example, the odorant concentration monitoring device detects that the current odorant concentration is 10 ppm.

S3: Acquire real-time environmental parameters including ambient temperature, ambient humidity and atmospheric pressure.

Environmental parameters such as ambient temperature, ambient humidity and atmospheric pressure are obtained in real time through environmental parameter sensors installed around natural gas pipelines. For example, the environmental parameter sensor detects that the ambient temperature is 25 degrees Celsius, the ambient humidity is 60%, and the atmospheric pressure is 1013 hPa.

S4: Obtain real-time odorant characteristic parameters in natural gas.

The odorant characteristic sensor detects the odorant characteristic parameters in natural gas in real time. For example, the odorant characteristic sensor detects that the density of the odorant is 0.8 g/cm³, the odor intensity is 50 ppm, the volatility is 20 kPa, the adsorption amount on the metal surface is 0.5 mg/m², and the conductivity is 0.1 S/m.

S5: receiving and processing real-time data including the real-time gas flow detection data, real-time odorant concentration detection data, real-time environmental parameters and real-time odorant characteristic parameters.

The data processing module of the controller receives and processes the above real-time data, performs data cleaning and preprocessing to ensure the accuracy and consistency of the data.

S6: Based on the deep learning neural network model, combined with the real-time data, output the optimal odorant injection strategy.

The odorant injection strategy determination module is based on a deep learning neural network model and combines real-time data to calculate the optimal odorant injection strategy. The neural network model extracts and processes the features of the input data through structures such as multi-layer perceptron (MLP), convolutional neural network (CNN) or long short-term memory network (LSTM) to output the optimal odorant injection strategy.

S7: According to the optimal odorant injection strategy, multiple parameters of the odorant injection pump are controlled, wherein the multiple parameters include injection rate, injection duration, injection frequency and injection amount distribution, and the odorant is injected into the natural gas pipeline.

The control module controls multiple parameters of the odorant injection pump according to the calculated optimal odorant injection strategy, including injection rate, injection duration, injection frequency and injection amount distribution. For example, the control module controls the injection rate of the odorant injection pump to be 0.5 liters/hour, the injection duration to be 10 minutes, the injection frequency to be once per hour, and the injection amount distribution to be uniform.

This embodiment demonstrates the working principle of the intelligent adaptive natural gas odorant concentration control method. Various sensors work together to detect various characteristic parameters of the odorant under the gas state in real time, and transmit the data to the controller. The controller calculates the optimal odorant injection strategy based on the deep learning neural network model, thereby realizing intelligent and adaptive odorant injection control.

Embodiment 6

An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the control method of any one of the above-mentioned intelligent adaptive natural gas odorant concentration control systems is implemented.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. Of course, there are other forms of readable storage media, such as quantum memory, graphene memory, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

The present invention also provides an electronic device. The electronic device of the embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the control method of the intelligent adaptive natural gas odorant concentration control system provided by the present invention.

6, which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an electronic device of an embodiment of the present invention. The electronic device shown in FIG6 is only an example and should not limit the functions and scope of use of the embodiment of the present invention.

As shown in FIG6 , the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

The following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I/O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and/or installed from the removable medium 611. When the computer program is executed by the central processing unit 601, the above functions defined in the system of the present invention are executed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, and the names of these units do not limit the units themselves in some cases.

The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims (6)

1. An intelligent adaptive natural gas odorizing agent concentration control system, comprising: a gas flow sensor, an odorizing agent injection pump, an odorizing agent concentration monitoring device, an environmental parameter sensor, an odorizing agent characteristic sensor and a controller;

the gas flow sensor is used for acquiring real-time gas flow detection data in the natural gas pipeline;

The odorizing agent concentration monitoring device is used for acquiring real-time odorizing agent concentration detection data in the natural gas;

The environment parameter sensor is arranged around the natural gas pipeline and is electrically connected with the controller and used for acquiring real-time environment parameters including environment temperature, environment humidity and atmospheric pressure;

the odorizing agent characteristic sensor is used for detecting real-time odorizing agent characteristic parameters in the natural gas in real time;

the odorizing agent injection pump is connected with the odorizing agent storage tank and is used for injecting the odorizing agent in the odorizing agent storage tank into the natural gas pipeline under the control of the controller;

the controller includes:

The data processing module is used for receiving and processing real-time data comprising the real-time gas flow detection data, the real-time odorizing agent concentration detection data, the real-time environment parameters and the real-time odorizing agent characteristic parameters;

The odorizing agent injection strategy determining module is used for outputting an optimal odorizing agent injection strategy based on the deep learning neural network model by combining the real-time data;

the control module is used for controlling a plurality of parameters of the odorizing agent injection pump according to the optimal odorizing agent injection strategy, wherein the parameters comprise injection rate, injection duration, injection frequency and injection quantity distribution;

the odorizing agent concentration monitoring device includes:

The odorizing agent analysis module is used for detecting the concentrations of different types of odorizing agents in the natural gas respectively and obtaining real-time odorizing agent concentration detection data;

The temperature compensation module is used for carrying out temperature compensation on the real-time odorizing agent concentration detection data according to the environmental temperature data obtained in real time to obtain odorizing agent concentration detection data after temperature compensation;

the environment humidity compensation module is used for performing humidity compensation on the temperature-compensated odorizing agent concentration detection data according to the environment humidity data acquired in real time to obtain the humidity-compensated odorizing agent concentration detection data;

the atmospheric pressure compensation module is used for performing pressure compensation on the humidity-compensated odorizing agent concentration detection data according to the atmospheric pressure data acquired in real time to obtain the pressure-compensated odorizing agent concentration detection data;

the odorizing agent characteristic sensor includes:

A density sensor for detecting the density of the odorizing agent;

An odor intensity sensor for detecting the intensity of odor emitted by the odorizing agent;

A volatility sensor for detecting the volatility characteristics of the odorizing agent in the natural gas;

the surface adsorption analyzer is used for measuring the adsorption characteristics of the odorizing agent on the surfaces of different materials;

a conductivity sensor for detecting the conductivity of the odorizing agent;

The neural network model based on deep learning comprises:

the input layer is used for receiving standardized historical data, including gas flow detection data, odorizing agent concentration detection data, environmental parameters and odorizing agent characteristic parameters;

A plurality of hidden layers, each hidden layer comprising a plurality of neurons, the neurons adopting a linear rectification function as an activation function for extracting and processing characteristics of input history data;

The output layer is used for outputting an optimal odorizing agent injection strategy according to the characteristics of the historical data, and the output of the output layer comprises injection rate, injection duration, injection frequency and injection quantity distribution;

When the hidden layers use a multi-layer perceptron structure, each hidden layer comprises a plurality of neurons which are fully connected, each neuron receives the output of all neurons of the previous layer and carries out nonlinear transformation through an activation function;

when the hidden layers use a convolutional neural network structure, each hidden layer comprises a plurality of convolutional kernels, each convolutional kernel slides on input data, local connection and weight sharing are carried out, and local features are extracted;

When the hidden layers use the LSTM structure of the long-short-period memory network, each hidden layer comprises a plurality of LSTM units, each LSTM unit controls the information to flow through an input gate, a forget gate and an output gate, and long-short-period dependency relations in sequence data are captured.

2. The intelligent adaptive natural gas odorizing agent concentration control system of claim 1, characterized in that,

The temperature compensation module adopts the following temperature compensation algorithm:

Ctemp_comp=craw+ ktemp × (T-Tref); wherein ctemp_comp is odorizing agent concentration detection data after temperature compensation, craw is real-time odorizing agent concentration detection data of preliminary detection, ktemp is temperature compensation coefficient, T is environmental temperature data acquired in real time at present, tref is reference environmental temperature data;

The environmental humidity compensation module adopts the following temperature compensation algorithm:

Chum_comp=ctemp_comp+k _hum1×H+k_hum2×H²; wherein Chum_comp is the odorant concentration detection data after humidity compensation, ctemp_comp is the odorant concentration detection data after temperature compensation, k _hum1 and k _hum2 are humidity compensation coefficients, and H is the environmental humidity data acquired in real time currently;

the atmospheric pressure compensation module adopts the following pressure compensation algorithm:

Cpress _comp=chum_comp+ kpress × (P-Pref); wherein Cpress _comp is the odorant concentration detection data after pressure compensation, chum_comp is the odorant concentration detection data after humidity compensation, kpress is the pressure compensation coefficient, P is the current atmospheric pressure data acquired in real time, and Pref is the reference atmospheric pressure data.

3. The intelligent adaptive natural gas odorizing agent concentration control system of claim 1, characterized in that,

The density sensor is arranged on the natural gas pipeline and is electrically connected with the controller through a cable or a wireless communication mode, and detected density data are transmitted to the controller;

The odor intensity sensor is arranged on the natural gas pipeline and is electrically connected with the controller through a cable or a wireless communication mode, and detected odor intensity data are transmitted to the controller;

The volatile sensor is arranged on the natural gas pipeline and is electrically connected with the controller through a cable or a wireless communication mode, and detected volatile data are transmitted to the controller;

The surface adsorption analyzer is arranged on a natural gas pipeline and is electrically connected with the controller through a cable or a wireless communication mode, and detected adsorption data are transmitted to the controller;

the conductivity sensor is arranged on the natural gas pipeline and is electrically connected with the controller through a cable or a wireless communication mode, and detected conductivity data are transmitted to the controller.

4. The intelligent adaptive natural gas odorizing agent concentration control system of claim 1, characterized in that,

The volatile sensor comprises a gas chromatograph, a mass spectrometer or a Fourier transform infrared spectrometer and is used for detecting volatile organic compounds of the odorizing agent;

The odor intensity sensor comprises an electronic nose composed of a plurality of chemical sensors, each chemical sensor being sensitive to a different odor component;

The surface adsorption analyzer evaluates adsorption characteristics of odorizing agent molecules by measuring adsorption amounts and adsorption rates thereof on a solid surface.

5. The intelligent adaptive natural gas odorizing agent concentration control system of claim 1, wherein said controller further comprises: and the prediction alarm module is used for calculating the consumption rate of the odorizing agent in the natural gas pipeline according to the real-time gas flow detection data and the real-time odorizing agent concentration detection data, predicting the residual quantity of the odorizing agent storage tank according to the calculated consumption rate of the odorizing agent, and triggering an odorizing agent supplementing alarm when the residual quantity is lower than a preset threshold value.

6. A control method of an intelligent adaptive natural gas odorizing agent concentration control system of any one of claims 1-5, characterized in that the control method comprises:

s1: acquiring real-time gas flow detection data in a natural gas pipeline;

s2: acquiring real-time odorizing agent concentration detection data in the natural gas;

S3: acquiring real-time environmental parameters including ambient temperature, ambient humidity and atmospheric pressure;

s4: acquiring and detecting real-time odorizing agent characteristic parameters in the natural gas;

s5: receiving and processing real-time data including the real-time gas flow detection data, the real-time odorizing agent concentration detection data, the real-time environmental parameters and the real-time odorizing agent characteristic parameters;

s6: based on the neural network model of deep learning, combining the real-time data, and outputting an optimal odorizing agent injection strategy;

S7: and controlling a plurality of parameters of the odorizing agent injection pump according to the optimal odorizing agent injection strategy, wherein the parameters comprise injection rate, injection duration, injection frequency and injection quantity distribution, and injecting the odorizing agent into the natural gas pipeline.