CN118919002B

CN118919002B - A green production method and system for cable materials

Info

Publication number: CN118919002B
Application number: CN202411397904.2A
Authority: CN
Inventors: 李兵
Original assignee: Jiangsu Tongshang New Material Technology Co ltd
Current assignee: Jiangsu Tongshang New Material Technology Co ltd
Priority date: 2024-10-09
Filing date: 2024-10-09
Publication date: 2024-12-27
Anticipated expiration: 2044-10-09
Also published as: CN118919002A

Abstract

The invention discloses a green production method and system for cable materials, and relates to the technical field of data processing. The method comprises: obtaining the component ratio constraint and preparation environment constraint of the cable material formula; constructing a cable material degradation state prediction network; performing green correlation analysis on the component ratio constraint and preparation environment constraint; optimizing the cable material formula based on the cable material degradation state prediction network according to the forward attribute set and the reverse attribute set, with the component ratio constraint and preparation environment constraint as restrictions, generating the cable material formula optimization result; and executing the cable material production management according to the cable material formula optimization result. The technical problem that the existing cable materials are difficult to degrade in the natural environment, resulting in long-term pollution of the ecological environment, is solved, and the technical effect of improving the degradability of the cable materials and realizing green production is achieved.

Description

Green production method and system for cable material

Technical Field

The application relates to the technical field of data processing, in particular to a green production method and system of a cable material.

Background

With the increasing severity of global environmental problems, sustainable development and green production are focused on various industries, cable materials are used as base materials for power transmission and communication, environmental influences generated in the production and use processes of the cable materials cannot be ignored, traditional cable materials, such as polyvinyl chloride (PVC) and Polyethylene (PE), depend on fossil energy sources as power sources in production, and are synthesized and processed by adopting a large amount of chemical raw materials, and the cable materials have good electrical performance and physical performance, are difficult to degrade in natural environments, and the environmental problems and resource consumption problems caused by the degradation of the cable materials are also gradually highlighted, are accumulated in soil and water for a long time, and form potential threats to the ecological environment.

Therefore, in the related technology of the current cable material production, the technical problem of long-term pollution of ecological environment caused by difficult degradation in natural environment exists.

Disclosure of Invention

The application solves the technical problems of difficult degradation in natural environment and long-term pollution of ecological environment of the existing cable material by providing the green production method and system of the cable material and adopting the technical means of association analysis, construction of degradation state prediction network and the like, and achieves the technical effects of improving the degradability of the cable material and realizing green production.

The application provides a green production method of a cable material, which comprises the steps of obtaining component proportion constraint and preparation environment constraint of a cable material formula, constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint, carrying out green correlation analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set, carrying out cable material formula optimization based on the cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint and carrying out cable material production management according to the cable material formula optimization result, wherein the forward attribute set and the reverse attribute set are limited by the component proportion constraint and the preparation environment constraint.

In a possible implementation manner, a cable material degradation state prediction network is constructed according to the component proportion constraint and the preparation environment constraint, and the processing is performed to collect cable material test record data, wherein the cable material test record data comprises component proportion record information, preparation environment record information and preset time length degradation proportion record information, the cable material test record data is divided into 3 equal parts and is set into a first data set, a second data set and a third data set, the first data set is used as a monitor based on the first data set, the component proportion record information and the preparation environment record information are used as inputs, a first front channel is configured, the second data set is used as a monitor based on the second data set, the component proportion record information and the preparation environment record information are used as inputs, a second front channel is configured based on the third data set, the preset time length proportion record information is used as a monitor, the component proportion record information and the preparation environment record information are used as inputs, the first front channel, the second front channel is integrated with the preset time length degradation proportion record information and the preparation environment record information are used as inputs, the first front channel, the second front channel is integrated with the first front channel is integrated with the second front channel is integrated with the preparation environment record value, the second front channel is integrated with the output, the first front channel is integrated with the second front channel is integrated with the preparation time length of the first front channel, the first front channel is integrated with the second front channel is integrated with the front channel.

In a possible implementation manner, based on the first data set, taking the degradation proportion record information of the preset duration as supervision, taking the composition proportion record information and the preparation environment record information as input, configuring a first pre-channel, performing the following processing of selecting the second data set or/and a fourth data set of preset data quantity of the third data set to verify the first pre-channel to obtain a first verification mean residual error when the first pre-channel meets preset training times, completing configuration of the first pre-channel when the first verification mean residual error module value is smaller than or equal to a residual error module value threshold, building a first residual error sub-channel of the first pre-channel according to the first verification mean residual error, fitting the first residual error sub-channel to output of the first pre-channel according to the first data set, fitting the first pre-channel and the first pre-channel until the first residual error module value is smaller than or equal to a first residual error module value threshold, and continuing fitting the first pre-channel until the first residual error sub-channel is sequentially fitted to the first pre-channel.

In a possible implementation manner, green relevance analysis is performed on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set, and further the following processing is performed, wherein a reference sequence is constructed according to a preset time degradation proportion based on big data, grey relevance analysis is performed on an attribute set construction comparison sequence of the component proportion constraint and the preparation environment constraint, a first attribute set with relevance greater than or equal to a relevance threshold is extracted, any one attribute of the first attribute set is used as a unique variable, an attribute progressive sequence and a preset time degradation proportion sequence are acquired, relevance analysis is performed according to the preset time degradation proportion sequence and the attribute progressive sequence to generate a pearson correlation coefficient, and the forward attribute set and the reverse attribute set are extracted from the first attribute set according to the pearson correlation coefficient.

In a possible implementation manner, according to the forward attribute set and the reverse attribute set, the component proportion constraint and the preparation environment constraint are used as limits, the cable material formula optimization is carried out based on the cable material degradation state prediction network, a cable material formula optimization result is generated, further, according to the component proportion constraint and the preparation environment constraint, an initial solution set is generated through a random uniform distribution function, the cable material initial solution set is analyzed through the cable material degradation state prediction network, an initial solution adaptation set is generated, jie Shi degrees refer to degradation ratios in a preset time period, a first number of optimal solutions are selected from the cable material initial solution set according to the initial Jie Shi degrees set to be set as a first selected solution, a second number of worst solutions are selected from the cable material initial solution set according to the initial Jie Shi degrees set to be set as a second selected solution, the cable material variation optimization result is generated through the first selected solutions according to the forward attribute set and the reverse attribute set.

In a possible implementation manner, the second selected solution is subjected to variation optimizing according to the forward attribute set and the reverse attribute set by the first selected solution to generate a cable material formula optimizing result, the following processing is further performed, wherein a solution to be varied is randomly selected from the second selected solution, a variation reference solution is randomly selected from the first selected solution, a variable attribute set and a variable direction set are selected according to the solution to be varied and the variation reference solution on the basis of the forward attribute set and the reverse attribute set, a variation step length mark is performed according to the variable direction set and the solution to be varied on the basis of the component proportion constraint and the preparation environment constraint to generate a variable step length threshold set, a plurality of random disturbances are performed on the solution to be varied on the basis of the variable attribute set, the variable direction set and the variable step length threshold set to generate a cable material variation solution set, when the cable material variation solution set is larger than or equal to a preset number, a cable material variation state is predicted by the cable material degradation state prediction network, the cable material variation solution is generated according to the cable material degradation state prediction network, the cable material variation solution is subjected to the initial solution is subjected to the preset, the circulation degree is updated to the optimal circulation degree is performed, and the circulation degree is updated according to the optimal circulation degree is performed, and the circulation degree is satisfied when the optimal circulation degree is satisfied.

In a possible implementation manner, when the cycle number meets the preset number, outputting an optimal solution, setting the optimal solution as the cable material formula optimization result, and further executing the following processing of configuring a convergence fitness threshold value, when the cycle number does not meet the preset number, judging whether the solution meeting the convergence fitness threshold value exists before each cycle begins, and if so, setting the optimal solution as the cable material formula optimization result.

The application also provides a green production system of the cable material, which comprises:

The cable material constraint obtaining module is used for obtaining component proportion constraint and preparation environment constraint of the cable material formula;

The cable material degradation state prediction network construction module is used for constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint;

The green relevance analysis module is used for carrying out green relevance analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set;

the cable material formula optimization module is used for carrying out cable material formula optimization based on the cable material degradation state prediction network by taking the component proportion constraint and the preparation environment constraint as limits according to the forward attribute set and the reverse attribute set, and generating a cable material formula optimization result;

And the cable material production management module is used for performing cable material production management according to the cable material formula optimization result.

The green production method and system for the cable material are used for obtaining component proportion constraint and preparation environment constraint of a cable material formula, constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint, performing green correlation analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set, performing cable material formula optimization based on the cable material degradation state prediction network according to the forward attribute set and the reverse attribute set by taking the component proportion constraint and the preparation environment constraint as limitations, and performing cable material production management according to the cable material formula optimization result. The technical problems of difficult degradation in natural environment and long-term pollution of ecological environment of the existing cable material are solved, and the technical effects of improving the degradability of the cable material and realizing green production are achieved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly describe the drawings of the embodiments of the present disclosure, in which flowcharts are used to illustrate operations performed by a system according to embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic flow chart of a green production method of a cable material according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a green production system for cable materials according to an embodiment of the present application.

Reference numerals illustrate the cable material constraint obtaining module 10, the cable material degradation state prediction network constructing module 20, the green correlation analyzing module 30, the cable material formulation optimizing module 40, and the cable material production management module 50.

Detailed Description

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.

The embodiment of the application provides a green production method of a cable material, as shown in fig. 1, comprising the following steps:

step S100, obtaining component proportion constraint and preparation environment constraint of the cable material formula. The composition ratio constraint of the cable material means that the composition ratio of various raw materials needs to meet certain requirements and limitations when the cable material is designed according to a formula, and is usually based on the performance requirements, cost consideration, environmental friendliness and other factors of the cable material, for example, according to the service environment and functional requirements of the cable, the conductivity, heat resistance, cold resistance, corrosion resistance and other performance parameters of the material need to be determined, so that the composition ratio of the raw materials is determined, on the premise of meeting the performance requirements, the cost of the material needs to be reduced as much as possible, the influence on the environment of the cable material needs to be reduced as much as possible in the production and waste processes, the environmental friendliness of the raw materials needs to be considered in the design, substances harmful to the environment are avoided to be used, or the use amount of the substances is reduced, the preparation environment constraint of the cable material refers to the environmental conditions which the cable material needs to meet in the production process, mainly comprises temperature control, humidity control, ventilation control, dust-free and static electricity free, and the like, and particularly, the production process of the cable material needs to be conducted in a certain temperature, humidity and light range, the performance and quality of the material are influenced by too high or too low temperature and humidity, for example, the material is possibly moisture absorption is reduced in the premise of meeting the performance requirements, the environmental protection is caused by the environmental protection of the material, the material is required to be good in the production environment-friendly material, the dust-free of the cable material is kept in the production, the dust-free from the dust-free environment, and the environmental protection is guaranteed, and the environmental protection of the dust-friendly material is required to be good, and the dust-free from the dust-free and the environmental pollution is guaranteed.

And step 200, constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint. According to the component proportion constraint and the preparation environment constraint of the cable material formula, a network model capable of predicting the degradation state of the cable material is constructed, degradation degrees or degradation trends of the cable material under different time and different environment conditions are predicted by analyzing factors such as components and preparation environment of the cable material, specifically, characteristics related to the degradation state of the cable material are selected from formula data and preparation environment data, a prediction model is constructed based on a neural network, the model is trained by using collected data, model parameters are adjusted to optimize prediction performance, and finally, a cable material degradation state prediction network is constructed and obtained, so that real-time monitoring and prediction of the degradation state of the cable material are realized.

In a possible implementation manner, step S200 further includes step S210, limited by the component proportion constraint and the preparation environment constraint, of collecting cable material test record data, where the cable material test record data includes component ratio record information, preparation environment record information, and degradation proportion record information of a preset duration. When the performance test of the cable material is carried out, relevant data of the cable material are recorded according to specific component proportion and preparation environment requirements, the relevant data comprise component proportion recording information, preparation environment recording information and preset time degradation proportion recording information, the component proportion recording information refers to specific proportions of all components in the cable material, the content of each raw material in the cable material is accurately calculated and recorded according to the formula optimization result of the cable material, the preparation environment recording information comprises environmental parameters such as temperature, humidity, pressure and ventilation condition related to the preparation process of the cable material, the preset time degradation proportion recording information refers to the degradation proportion of the cable material in a specific time period, the degradation proportion is an important index for evaluating the durability and stability of the cable material, and the preset time period can be a time period set according to the service environment and service life requirements of the cable material. The method also comprises a step S220 of dividing the cable material test record data into 3 equal parts, and setting the equal parts as a first data set, a second data set and a third data set. The method further comprises step S230, based on the first data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input, configuring a first front channel. A specific processing path or channel, i.e. a first pre-channel, is set for the input data (composition ratio record information and preparation environment record information) based on a given first data set and specific supervision information (preset duration degradation ratio record information). and step S240, based on the second data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input to configure a second front channel. A specific processing path or channel, i.e. a second pre-channel, is set for the input data (composition ratio record information and preparation environment record information) based on a given second data set and specific supervision information (preset duration degradation ratio record information). And step S250, based on the third data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input to configure a third front channel. A specific processing path or channel, i.e. a third pre-channel, is set for the input data (composition ratio record information and preparation environment record information) based on a given third data set and specific supervision information (preset duration degradation ratio record information). And step S260, wherein the first output value of the first pre-channel, the second output value of the second pre-channel and the third output value of the third pre-channel are used as inputs, and the degradation proportion record information of the preset duration is used as supervision to configure an integrated fusion channel. And step S270, combining the first pre-channel, the second pre-channel, the third pre-channel and the integrated fusion channel to generate the cable material degradation state prediction network. the generated cable material degradation state prediction network is a complex network structure integrated with a plurality of front channels and integrated fusion channels, can process various types of data at the same time, extracts key characteristics related to cable material degradation state prediction, and improves the accuracy and reliability of prediction by fusing the characteristics.

In a possible implementation manner, step S230 further includes step S231, when the first pre-channel meets the preset training number, selecting the second data set or/and the fourth data set of the preset data amount of the third data set to perform verification on the first pre-channel, so as to obtain a first verification mean residual. When the model reaches the preset training times, a part of the second data set or/and the third data set (the fourth data set with preset data quantity) is selected as a verification data set, the trained first front channel is tested on the verification data set, the difference between the predicted value and the actual value of the model is calculated, the difference is usually called residual error, the residual error of all verification data samples is calculated, and the average value is taken, so that a first verification average value residual error can be obtained, the prediction capability of the model on unseen data (namely the verification data set) is reflected, and if the first verification average value residual error is smaller, the prediction performance of the model on the verification data set is better. And step S232, when the first verification mean residual error module value is smaller than or equal to a residual error module value threshold value, the first pre-channel configuration is completed. The residual modulus threshold is a preset value, and is used for judging whether the prediction performance of the model on the verification data set meets the requirement, and when the first verification mean residual modulus (i.e. the absolute value of the first verification mean residual) is smaller than or equal to the preset residual modulus threshold, the configuration process of the first front channel is completed, and the performance of the channel on the verification data set meets the expected standard. And step S233, when the first verification mean residual error module value is greater than the residual error module value threshold, building a first residual error fitting sub-channel of the first front-end channel according to the first verification mean residual error, where the first residual error fitting sub-channel is used for fitting the output of the first front-end channel. When the first verification mean residual error module value is greater than the preset residual error module value threshold value, the performance of the first front-end channel on the verification data set is not up to the expected standard, namely, a certain error exists in the model in prediction, a first residual error fitting sub-channel of the first front-end channel can be built according to the first verification mean residual error, specifically, the first residual error fitting sub-channel is used for further adjusting or correcting the output of the first front-end channel so as to reduce the prediction error, for example, the residual error is +2, it is indicated that each error is greater than 2, and the residual error fitting channel is obtained by subtracting 2 from the output of the original model. And step S234, according to the first data set, training the first pre-channel and the first residual fitting sub-channel until the Nth verification mean residual modulus value is smaller than or equal to the residual modulus value threshold value, and sequentially connecting the first residual fitting sub-channel, the second residual fitting sub-channel and the Nth residual fitting sub-channel in series with the output layer of the first pre-channel to complete the configuration of the first pre-channel. If the first verification mean residual error module value is larger than a preset residual error module value threshold value, the prediction performance of the first front-end channel is further improved, a first residual error fitting sub-channel is built according to the first verification mean residual error, the first front-end channel and the first residual error fitting sub-channel are subjected to joint training based on a first data set, after training is completed, a fourth data set is used for verification again, a second verification mean residual error module value is calculated, the process is repeated until the Nth verification mean residual error module value is smaller than or equal to the preset residual error module value threshold value, and the first residual error fitting sub-channel and the second residual error fitting sub-channel until the Nth residual error fitting sub-channel are sequentially connected in series with an output layer of the first front-end channel, so that the first front-end channel comprising a plurality of residual error fitting sub-channels is formed.

And step S300, performing green correlation analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set. The analysis of green relevance is performed on the component proportion constraint and the preparation environment constraint of the cable material formula, namely, the degree of relevance between the two constraint conditions is systematically examined to identify the degree of relevance between the two constraint conditions and the green performance (namely, environmental friendliness) of the cable material, so as to find out which factors (attributes) have positive influence (namely, positive attributes) on the green performance of the cable material and which factors have negative influence (namely, negative attributes), specifically, the positive attribute set refers to factors or attributes capable of enhancing the green performance of the cable material, and is generally related to the aspects of recoverability, degradability, low toxicity, low energy consumption production and the like of the cable material, for example, renewable or bio-based raw materials are used as main components of the cable material, toxic and harmful chemical substances are reduced or avoided in the formula, energy-saving technologies such as low temperature and low pressure are adopted in the preparation process, and additives or auxiliary agents with small influence on the environment are selected, and the negative attribute set refers to factors or attributes capable of reducing the green performance of the cable material are generally related to factors or attributes of the cable material, such as difficult recovery, difficult degradation, high toxicity, high-energy consumption and the like are related to aspects of the cable material can be degraded, such as high-quality and high-quality petroleum-quality and high-quality materials are not required to cause the large-quality and high-quality environmental pollution to be degraded by the large-quality materials and high-quality materials in the preparation process and the large-quality waste materials are difficult to cause the long-term degradation and the environmental pollution.

In a possible implementation manner, step S300 further includes step S310, based on big data, constructing a reference sequence with a degradation ratio of a preset duration, constructing a comparison sequence with the attribute sets of the component ratio constraint and the preparation environment constraint, performing gray correlation analysis, and extracting a first attribute set with a correlation greater than or equal to a correlation threshold. The reference sequence is a sequence formed by degradation ratios of the preset duration, represents a reference line of the degradation performance of the cable material changing along with time, the comparison sequence is a sequence formed by values of the attributes under different time or different conditions, each attribute corresponds to a subsequence in the comparison sequence to jointly form a complete comparison sequence, gray correlation analysis is a data analysis method based on gray system theory and is used for analyzing the correlation degree between different factors in a system and evaluating the correlation degree between various attributes (such as component ratios, preparation environments and the like) and the degradation ratios, in the degradation performance analysis of the cable material, the gray correlation degree between the reference sequence and each comparison subsequence is calculated to be a numerical value between 0 and 1, the correlation degree between the reference sequence and each comparison subsequence is expressed, the larger the correlation degree is, the influence of the attribute on the degradation ratio is expressed, after the correlation degree between all comparison subsequences and the reference sequence is calculated, the first attribute set is formed according to a preset correlation degree threshold (usually a positive number close to 1) in a screening out the correlation degree is larger than or equal to the threshold. And step S320, wherein any one attribute of the first attribute set is taken as a unique variable, and an attribute progressive sequence and a preset duration degradation proportion sequence are acquired. One attribute is selected from the first set of attributes as the sole variable of the study, and a series of different values are designed for the selected attribute, which values constitute a progressive sequence of the attribute, e.g., if the selected attribute is a proportion of a certain component, the progressive sequence may include different scale values from low to high, for each value in the progressive sequence of attributes, a corresponding sample of cable material is prepared, differing only in the selected attribute, while other factors (e.g., manufacturing environment, other component proportions, etc.) should remain consistent. And step S330, performing correlation analysis according to the degradation proportion sequence with the preset duration and the attribute progressive sequence to generate a pearson correlation coefficient. And carrying out correlation analysis according to a degradation proportion sequence and an attribute progressive sequence of a preset duration to generate a pearson correlation coefficient, and quantitatively evaluating the linear correlation degree between the two sequences, wherein the pearson correlation coefficient is used for measuring the linear relation strength and direction between two variables, the value range is between-1 and 1, when the coefficient is close to 1, the two sequences are completely positively correlated, namely, as one sequence is increased, the other sequence is increased, the variation amplitude is basically consistent, when the coefficient is close to-1, the two sequences are completely negatively correlated, and when r is close to 0, the two sequences are not linearly correlated. Further comprising a step S340 of extracting the forward set of attributes and the reverse set of attributes from the first set of attributes according to the pearson correlation coefficient. All the attributes positively correlated with the degradation ratio (i.e. pearson correlation coefficient is positive) are extracted from the first set of attributes to form a forward set of attributes, indicating that increasing the attribute values would tend to increase the degradation ratio, and all the attributes negatively correlated with the degradation ratio (i.e. pearson correlation coefficient is negative) are extracted from the first set of attributes to form a reverse set of attributes, indicating that increasing the attribute values would tend to decrease the degradation ratio.

And step S400, carrying out cable material formula optimization based on the cable material degradation state prediction network by taking the component proportion constraint and the preparation environment constraint as constraints according to the forward attribute set and the reverse attribute set, and generating a cable material formula optimization result. According to the forward attribute set and the reverse attribute set, component proportion constraint and preparation environment constraint of a cable material formula are taken as limiting conditions, a cable material formula optimization result is generated based on a cable material degradation state prediction network, green performance and environment friendliness of the cable material are improved, specifically, a target of the cable material formula optimization is defined based on the forward attribute set, a composition proportion range of various raw materials in the cable material and environmental conditions required to be met in a production process are set according to the component proportion constraint and the preparation environment constraint, the cable material degradation state prediction network is integrated into an optimization model, formula parameters (such as raw material composition proportion) of the cable material are taken as decision variables, green performance (such as degradation state prediction result) of the cable material is taken as an objective function, different formula parameter combinations are tried continuously, green performance of the combinations is evaluated through the cable material degradation state prediction network, the formula parameters are continuously adjusted according to the evaluation result, a formula meeting the limiting conditions and the green performance is optimized is searched, and finally, namely the cable material formula optimizing result meeting the limiting conditions and the green performance is converged.

In a possible implementation, step S400 further includes step S410 of generating an initial solution set of the cable material by a random uniform distribution function according to the component proportion constraint and the preparation environment constraint. According to the component proportion constraint and the preparation environment constraint, a set of possible cable material formulas or preparation conditions are generated as an initial solution set by randomly sampling through a random uniform distribution function, specifically, the random uniform distribution function is used for generating random numbers uniformly distributed in a specified range, namely, the value range of the random numbers is determined according to the component proportion constraint and the preparation environment constraint, each random number represents one parameter of the cable material formulas or the preparation conditions, the parameters are combined to form an initial solution of the cable material, and an initial solution set containing a plurality of initial solutions can be generated by repeating the process for a plurality of times. And step S420, analyzing the cable material initial solution set through the cable material degradation state prediction network to generate an initial solution adaptation degree set, wherein Jie Shi degrees refer to degradation ratios of preset time periods. Jie Shi degrees of fitness refer to degradation ratios of each initial solution (namely a cable material formula or combination of preparation conditions) within a preset time period, each solution in the initial solution set of the cable material is input into a cable material degradation state prediction network to obtain degradation ratios of each solution within the preset time period, and fitness of all solutions are combined to form an initial Jie Shi degrees of fitness set. Further comprising step S430 of selecting a first number of optimal solutions from the initial solution set of cable materials based on the initial Jie Shi strain sets, set as a first selected solution. And sequencing each fitness value (namely the degradation proportion of the preset duration corresponding to each initial solution) in the initial solution fitness set, selecting a first number of optimal solutions from the initial solution set of the cable material, and setting the first number of optimal solutions as a first selected solution. Further comprising a step S440 of selecting a second number of worst solutions from said initial set of solutions of cable material according to said initial Jie Shi set of measures, setting a second selected solution. A second number of worst solutions is selected from the initial solution set of cable material, the second selected solution being set with relatively poor performance in the initial solution set. And step S450, performing variation optimization on the second selected solution by using the first selected solution according to the forward attribute set and the reverse attribute set, and generating the cable material formula optimization result. Based on the forward attribute set and the reverse attribute set, the existing excellent solution (the first selected solution) is used for improving and optimizing the poor solution (the second selected solution), specifically, the attribute values in the second selected solution are finely adjusted according to the forward attribute set and the reverse attribute set, so that the attribute values are closer to the attribute value distribution in the first selected solution, after the variation optimization, the performance of the second selected solution can be possibly improved, a new cable material formula candidate solution is generated, and the cable material formula with the optimal performance is screened out as a final optimization result.

In a possible implementation, step S450 further includes step S451 of randomly selecting a solution to be mutated from the second selected solution and randomly selecting a mutation reference solution from the first selected solution. One or more solutions are randomly selected from the second selected solutions to serve as solutions to be mutated, one or more solutions are randomly selected from the first selected solutions to serve as mutation reference solutions, and the mutation reference solutions provide improved directions and bases for the solutions to be mutated. Step S452 is further included, according to the solution to be mutated and the mutation reference solution, to select a mutated attribute set and a mutated direction set based on the forward attribute set and the reverse attribute set. For each selected variant attribute, the direction of variation (i.e. increasing or decreasing the attribute value) needs to be determined, and if the value of the attribute in the variant reference solution is better than that of the solution to be mutated, the direction of mutation is usually approaching the direction of the variant reference solution (i.e. increasing or decreasing the attribute value to approach the value of the variant reference solution), for example, the a attribute is bigger, the degradation period is shorter, and the a attribute of the variant reference solution is bigger than the a attribute of the solution to be mutated, the mutation direction is smaller. Step S453 is further included, according to the variable direction set and the solution to be mutated, mutation step length identification is performed based on the component proportion constraint and the preparation environment constraint, and a variable step length threshold set is generated. According to the attribute value of the solution to be mutated, the mutated direction set and the preset constraint condition, a proper mutated step length or mutated amplitude is determined for each mutated attribute, and the mutated step length threshold set is a set containing the maximum and minimum mutated step length (or mutated amplitude) of each mutated attribute and is used for limiting the variation range of the attribute in the subsequent mutation process. Step S454 is further included, where the solution to be mutated is randomly perturbed for several times based on the mutated attribute set, the mutated direction set and the mutated step threshold set, so as to generate a mutated solution set of the cable material. For each variable attribute, the algorithm randomly selects a step length to change within an allowable range according to the variable direction and the variable step length threshold set, and a group of new cable material formula candidate solutions, namely a cable material variable solution set, are generated after a plurality of random disturbance. And step S455, when the variation solution set of the cable material is greater than or equal to the preset number, analyzing the variation solution set of the cable material through the cable material degradation state prediction network to generate a variation Jie Shi corresponding degree set. And (3) taking each variation solution in the cable material variation solutions as input, transmitting the input to a cable material degradation state prediction network, processing and analyzing the variation solutions by the cable material degradation state prediction network, predicting the degradation state or performance of the cable material under the formula, generating an adaptability value for each variation solution according to the output result of the cable material degradation state prediction network, wherein the adaptability value is represented by the performance of the variation solution under an optimization target, the higher the adaptability value is, the better the performance of the variation solution is, the closer the performance of the variation solution is to the optimization target, and the variation Jie Shi adaptability set is a set of adaptability values comprising all variation solutions in the cable material variation solutions. And step S456, the initial solution set of the cable material is updated according to the variation degree of adaptability, and then the loop is executed. Based on the variant solution fitness set, the algorithm screens variant solutions with higher fitness values and adds them to the cable material initial solution set, while possibly eliminating some solutions with lower fitness values, the cable material initial solution set is updated to contain a new set of more excellent candidate solutions, and then the updating is repeated. And S457, outputting an optimal solution when the cycle times meet the preset times, and setting the optimal solution as the cable material formula optimization result.

In one possible implementation, step S457 further includes step S457, configuring a convergence fitness threshold. A parameter is set to determine when to stop updating the initial solution set of cable material, in particular, when the algorithm fails to find a new solution with a fitness value below the threshold in successive rounds of iterations, the algorithm may consider it to have converged around the optimal solution and stop searching. And step S4572, when the number of cycles does not meet the preset number of cycles, judging whether the solution meeting the convergence fitness threshold is available before each cycle is started, and if yes, setting the solution as the cable material formula optimization result. When the number of loops does not reach the preset number of loops, in order to ensure that the algorithm does not meaningfully continue to iterate, and simultaneously, in order to capture possible excellent solutions in time, whether a solution meeting the convergence fitness threshold exists in the current solution set is generally judged before each loop starts, if the solution meeting the convergence fitness threshold exists, the solution is set as a cable material formula optimization result, and the solution is terminated in advance before the preset number of loops is reached, so that calculation resources are saved and the optimization efficiency is improved.

And S500, performing cable material production management according to the cable material formula optimization result. The optimized cable material formula is applied to the actual production process, and the whole production process is comprehensively managed to ensure that the quality and performance of the cable material meet the optimization targets, meanwhile, the green production is realized, the production efficiency and economic benefit are improved, and the market demand and the environmental protection requirement are met.

Hereinabove, a green production method of a cable material according to an embodiment of the present invention is described in detail with reference to fig. 1. Next, a green production system of a cable material according to an embodiment of the present invention will be described with reference to fig. 2.

The green production system of the cable material is used for solving the technical problem that the existing cable material is difficult to degrade in the natural environment and causes long-term pollution of the ecological environment, and achieves the technical effects of improving the degradability of the cable material and realizing green production. The green production system of the cable material comprises a cable material constraint obtaining module 10, a cable material degradation state prediction network construction module 20, a green correlation analysis module 30, a cable material formula optimization module 40 and a cable material production management module 50.

A cable material constraint obtaining module 10, wherein the cable material constraint obtaining module 10 is used for obtaining component proportion constraint and preparation environment constraint of a cable material formula;

The cable material degradation state prediction network construction module 20, wherein the cable material degradation state prediction network construction module 20 is used for constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint;

The green relevance analysis module 30 is used for performing green relevance analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set;

The cable material formula optimization module 40 is configured to perform cable material formula optimization based on the cable material degradation state prediction network with the component proportion constraint and the preparation environment constraint as constraints according to the forward attribute set and the reverse attribute set, and generate a cable material formula optimization result;

a cable material production management module 50, wherein the cable material production management module 50 is used for performing cable material production management according to the cable material formula optimization result.

Next, the specific configuration of the cable material degradation state prediction network construction module 20 will be described in detail. The cable material degradation state prediction network construction module 20 further includes collecting cable material test record data, wherein the cable material test record data includes component ratio record information, preparation environment record information and preset duration degradation ratio record information, dividing the cable material test record data into 3 equal parts, setting the 3 equal parts as a first data set, a second data set and a third data set, configuring a first front channel based on the first data set by taking the preset duration degradation ratio record information as a monitor, configuring a first front channel by taking the component ratio record information and the preparation environment record information as an input, configuring a second front channel based on the second data set by taking the preset duration degradation ratio record information as a monitor, taking the component ratio record information and the preparation environment record information as an input, configuring a third front channel based on the third data set by taking the preset duration degradation ratio record information as a monitor, configuring a fusion of the first front channel, the second front channel and the third front channel as an integrated state, and generating a fusion of the first front channel, the second front channel and the third front channel as an integrated state.

Next, the specific configuration of the cable material degradation state prediction network construction module 20 will be described in further detail. The cable material degradation state prediction network construction module 20 may further include verifying the first pre-channel with a fourth data set of a preset data amount of the second data set or/and the third data set when the first pre-channel meets a preset training number, obtaining a first verification mean residual, completing configuration of the first pre-channel when the first verification mean residual is smaller than or equal to a residual threshold, building a first residual fitting sub-channel of the first pre-channel according to the first verification mean residual, wherein the first residual fitting sub-channel is used for fitting an output of the first pre-channel, continuing training the first pre-channel and the first residual fitting sub-channel according to the first data set until an nth verification mean residual is smaller than or equal to the residual threshold, completing configuration of the first residual fitting sub-channel, and sequentially building the first residual fitting sub-channel, the second residual fitting sub-channel until an nth verification mean residual is sequentially smaller than or equal to the residual threshold, and completing configuration of the first pre-channel.

Next, the specific configuration of the green relevance analysis module 30 will be described in detail. The green relevance analysis module 30 may further include constructing a reference sequence with a degradation ratio of a preset duration based on big data, performing gray relevance analysis with an attribute set construction comparison sequence of the component proportion constraint and the preparation environment constraint, extracting a first attribute set with a relevance greater than or equal to a relevance threshold, collecting an attribute progressive sequence and a degradation ratio sequence of the preset duration with any one attribute of the first attribute set as a unique variable, performing relevance analysis according to the degradation ratio sequence of the preset duration and the attribute progressive sequence to generate pearson correlation coefficients, and extracting the forward attribute set and the reverse attribute set from the first attribute set according to the pearson correlation coefficients.

Next, the specific configuration of the cable material formulation optimization module 40 will be described in detail. The cable material formulation optimization module 40 still further includes generating an initial solution set of cable material through a random uniform distribution function according to the component proportion constraint and the preparation environment constraint, analyzing the initial solution set of cable material through the cable material degradation state prediction network to generate an initial solution fitness set, wherein Jie Shi degrees refer to degradation proportions for a preset time period, selecting a first number of optimal solutions from the initial solution set of cable material according to the initial Jie Shi degrees set to be set as a first selected solution, selecting a second number of worst solutions from the initial solution set of cable material according to the initial Jie Shi degrees set to be set as a second selected solution, performing variation optimization on the second selected solution according to the forward attribute set and the reverse attribute set by the first selected solution, and generating a cable material formulation optimization result.

The specific configuration of the cable material formulation optimization module 40 will be described in further detail below. The cable material formulation optimization module 40 still further includes randomly selecting a solution to be mutated from the second selected solution, randomly selecting a mutation reference solution from the first selected solution, selecting a mutated set of properties and a mutated set of directions based on the forward set of properties and the reverse set of properties according to the solution to be mutated and the mutation reference solution, identifying mutated step sizes based on the component ratio constraint and the preparation environment constraint according to the mutated set of directions and the solution to be mutated, generating a mutated step size threshold set, randomly perturbing the solution to be mutated a number of times based on the mutated set of properties, the mutated set of directions and the mutated step size threshold set, generating a mutated solution set of cable material, analyzing the mutated solution set of cable material through the cable material degradation state prediction network when the mutated solution set of cable material is greater than or equal to a preset number, generating a mutated solution fitness set, updating the initial solution set of cable material according to the mutated solution fitness set, performing a cycle after updating, and outputting the optimal cable material formulation when the cycle number satisfies the preset number.

The specific configuration of the cable material formulation optimization module 40 will be described in further detail below. The cable material formulation optimization module 40 may further include configuring a convergence fitness threshold, and determining whether a solution satisfying the convergence fitness threshold is present before each cycle begins when the number of cycles does not satisfy a preset number of cycles, and if so, setting the solution as the cable material formulation optimization result.

The green production system of the cable material provided by the embodiment of the invention can execute the green production method of the cable material provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Although the present application makes various references to certain modules in a system according to an embodiment of the present application, any number of different modules may be used and run on a user terminal and/or a server, and each unit and module included are merely divided according to functional logic, but are not limited to the above-described division, so long as the corresponding functions can be implemented, and in addition, specific names of each functional unit are only for convenience of distinguishing from each other, and are not intended to limit the scope of protection of the present application.

The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.

Claims

1. A green production method of a cable material, comprising:

Obtaining component proportion constraint and preparation environment constraint of a cable material formula;

constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint;

performing green correlation analysis on the component proportion constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set;

according to the forward attribute set and the reverse attribute set, carrying out cable material formula optimization based on the cable material degradation state prediction network by taking the component proportion constraint and the preparation environment constraint as limits, and generating a cable material formula optimization result;

performing cable material production management according to the cable material formula optimization result;

Constructing a cable material degradation state prediction network according to the component proportion constraint and the preparation environment constraint, wherein the cable material degradation state prediction network comprises the following components:

Collecting cable material test record data, which includes component ratio record information, preparation environment record information and degradation proportion record information of preset duration, by limiting the component proportion constraint and the preparation environment constraint;

dividing the cable material test record data into 3 equal parts, and setting the data into a first data set, a second data set and a third data set;

based on the first data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input, configuring a first front-end channel;

Based on the second data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input, configuring a second front-end channel;

Based on the third data set, taking the degradation proportion record information of the preset duration as supervision, and taking the component ratio record information and the preparation environment record information as input, configuring a third front-end channel;

The first output value of the first preposed channel, the second output value of the second preposed channel and the third output value of the third preposed channel are taken as inputs, and the degradation proportion record information of the preset duration is taken as supervision to configure an integrated fusion channel;

Combining the first pre-channel, the second pre-channel, the third pre-channel and the integrated fusion channel to generate the cable material degradation state prediction network;

Based on the first data set, taking the degradation proportion record information of the preset duration as supervision, taking the component ratio record information and the preparation environment record information as input, configuring a first front-end channel, comprising:

When the first pre-channel meets the preset training times, the first pre-channel is verified by selecting the second data set or/and a fourth data set of the preset data amount of the third data set, and a first verification mean residual error is obtained;

When the first verification mean residual error module value is smaller than or equal to a residual error module value threshold value, the first pre-channel configuration is completed;

When the first verification mean residual error module value is larger than the residual error module value threshold value, building a first residual error fitting sub-channel of the first front-end channel according to the first verification mean residual error, wherein the first residual error fitting sub-channel is used for fitting the output of the first front-end channel;

and according to the first data set, training the first pre-channel and the first residual fitting sub-channel until the Nth verification mean residual modulus value is smaller than or equal to the residual modulus value threshold value, and sequentially connecting the first residual fitting sub-channel, the second residual fitting sub-channel and the Nth residual fitting sub-channel in series with the output layer of the first pre-channel to complete the configuration of the first pre-channel.

2. A green production method of a cable material according to claim 1, wherein the green correlation analysis is performed on the component ratio constraint and the preparation environment constraint to generate a forward attribute set and a reverse attribute set, comprising:

Constructing a reference sequence according to degradation proportion of a preset duration based on big data, constructing a comparison sequence according to attribute sets of the component proportion constraint and the preparation environment constraint, executing gray correlation analysis, and extracting a first attribute set with the correlation greater than or equal to a correlation threshold;

Taking any one attribute of the first attribute set as a unique variable, and collecting an attribute progressive sequence and a preset duration degradation proportion sequence;

Performing correlation analysis according to the degradation proportion sequence of the preset duration and the attribute progressive sequence to generate a pearson correlation coefficient;

and extracting the forward attribute set and the reverse attribute set from the first attribute set according to the Pearson correlation coefficient.

3. The green production method of a cable material according to claim 1, wherein the cable material formulation optimization is performed based on the cable material degradation state prediction network with the component ratio constraint and the preparation environment constraint as constraints according to the forward attribute set and the reverse attribute set, and the cable material formulation optimization result is generated, comprising:

Generating an initial solution set of the cable material through a random uniform distribution function according to the component proportion constraint and the preparation environment constraint;

analyzing the cable material initial solution set through the cable material degradation state prediction network to generate an initial solution adaptation set, wherein Jie Shi degrees refer to degradation ratios of preset time periods;

selecting a first number of optimal solutions from the initial solution set of cable materials according to the initial Jie Shi fitness set, and setting the first number of optimal solutions as first selected solutions;

selecting a second number of worst solutions from the initial solution set of cable materials according to the initial Jie Shi fitness set, and setting a second selected solution;

and performing variation optimization on the second selected solution by using the first selected solution according to the forward attribute set and the reverse attribute set, and generating the cable material formula optimization result.

4. A method of green production of a cable material according to claim 3, wherein performing a variational optimization on the second selected solution with the first selected solution based on the forward set of attributes and the reverse set of attributes to generate the cable material formulation optimization result comprises:

Randomly selecting a solution to be mutated from the second selected solution, and randomly selecting a mutation reference solution from the first selected solution;

Selecting a variable attribute set and a variable direction set based on the forward attribute set and the reverse attribute set according to the solution to be mutated and the mutation reference solution;

According to the variable direction set and the solution to be mutated, mutation step length identification is carried out based on the component proportion constraint and the preparation environment constraint, and a variable step length threshold set is generated;

Performing a plurality of random perturbations on the solution to be mutated based on the mutated attribute set, the mutated direction set and the mutated step length threshold set to generate a cable material mutated solution set;

When the cable material variation solution set is larger than or equal to a preset number, analyzing the cable material variation solution set through the cable material degradation state prediction network to generate a variation solution adaptability set;

Performing circulation after updating the initial solution set of the cable material according to the variation solution fitness;

And when the circulation times meet the preset times, outputting an optimal solution, and setting the optimal solution as the cable material formula optimization result.

5. The green production method of a cable material according to claim 4, wherein when the number of cycles satisfies a preset number, outputting an optimal solution, which is set as the cable material formulation optimization result, comprising:

Configuring a convergence fitness threshold;

and when the cycle times do not meet the preset times, judging whether solutions meeting the convergence fitness threshold are available before each cycle is started, and if yes, setting the solution as the cable material formula optimization result.

6. A green production system for a cable material, wherein the system is adapted to carry out a green production method for a cable material according to any one of claims 1-5, the system comprising:

the cable material degradation state prediction network construction module is used for constructing a cable material degradation state prediction network based on the component proportion constraint and the preparation environment constraint;