CN108354591A - A kind of operating personnel's degree of safety method of discrimination and equipment - Google Patents

Abstract

The invention discloses a method and equipment for judging the safety degree of an operator. The method includes the following steps: extracting the ECG data index and the exercise data index of the operator, the ECG data index includes a time domain index and a frequency domain index, and the Exercise data indicators include operation time WT, operation degree WD, state coefficient K, fall posture P1, and fall posture P2; input the ECG data indicators into the SVM that has been trained and calibrated to obtain the fatigue level Gn; The degree of fatigue of personnel is judged, where X=f*Gn+(1‑f)*WT*WD*K+(P1+P2)/(P1*P2+1); where f ranges from 0 to 1. Based on the fusion of their own physiological signals and operating postures, the operator's fatigue level is judged, and the combination of support vector machine SVM and ECG data can quickly and accurately achieve technical results.

Description

A method and device for judging the safety degree of workers

technical field

The invention relates to the field of electric power operation safety management and control, in particular to a method and equipment for judging the safety degree of an operator.

Background technique

The traditional safety management and control of the power application industry is mainly in two aspects: one is, including the specification of the process system, the arrangement of the work order process, the team coordination mechanism, etc., and the informatization means for this purpose; The safety control means under the system, as well as the protection device or auxiliary monitoring system derived from it. It can be seen that the traditional power application safety management and control mechanism mainly starts from the process and equipment, and improves the safety management and control degree by controlling the workflow or early detection of equipment failures and dangerous areas. However, these technical means have two disadvantages: one is that the most complex object in safety management and control-the state of the operator itself is ignored, and there is no method for judging the safety of the operator; The construction of other safety control measures is delayed, and the operators are the first to be placed in this scene.

Working with sickness, fatigue, or emergencies are the difficulties of safety management and control.

Contents of the invention

In order to solve the above technical problems, the present invention provides a method and equipment for judging the safety degree of workers.

The present invention realizes through following technical scheme:

A method for judging the safety degree of an operator, comprising the following steps:

A. Extract the ECG data index and motion data index of the operator, the ECG data index includes time domain index and frequency domain index, and the motion data index includes operation time WT, operation degree WD, state coefficient K, and fall posture P1 , Falling posture P2;

B. Input the ECG data index into the SVM that has been trained and calibrated for multi-classification to obtain the fatigue level Gn;

C. Calculate X, and judge the fatigue degree of the operator according to X, among which,

X=f*Gn+(1-f)*WT*WD*K+(P1+P2)/(P1*P2+1); where f ranges from 0 to 1.

The ECG signal is the potential change generated by the human heart activity on the body surface, which has a strong periodicity. The ECG waveform of a normal human body can be kept relatively stable within a certain period of time. The ECG signal of the same individual varies with fatigue, environment Adaptation, physical condition and other factors produce differences. Physiological signals will largely be mental fatigue, and the results of operating posture statistics and emergency recognition are likely to be physical fatigue. More accurately, the fatigue judgment based on ECG signals is based on the principle of ECG difference, and is judged by indicators such as heart rate variability. The whole solution combines machine learning and engineering experience with ECG data, that is, the combination of support vector machine SVM and ECG data, which can achieve fast and accurate technical effects.

Preferably, the time domain index includes R wave number HR and R wave interval standard deviation SD; the frequency domain index includes high frequency power value HF, low frequency power value LF, and very low frequency power value VLF. As we all know, the more parameters related to the degree of fatigue are selected, the higher the accuracy of fatigue recognition is. However, the more parameters, the more complex the indicators. Whether it is in the training process of SVM or in the process of discrimination, It has a large amount of calculation, and it is difficult to improve the accuracy after increasing the discrimination time and reaching a certain level. time.

As preferably, the training method of described SVM is:

Select the personnel who have been fatigued and those who have not been fatigued in the electric power work scene to collect ECG data and obtain the data set;

Extracting ECG data indicators from the data set, the ECG data indicators include time domain indicators and frequency domain indicators;

The input SVM that extracts the ECG data indicators is used to complete the training and calibration.

A device for judging the safety degree of workers, comprising:

The upper case used to collect the ECG signal of the wearer's hand;

The lower case for collecting the ECG signal of the wearer's other hand;

An ECG collection and preprocessing circuit module used to collect the potential difference between the two upper and lower cases to obtain ECG signals and complete signal preprocessing;

A motion sensing acquisition and preprocessing circuit module for acquiring the acceleration and angular velocity of the three-axis space to obtain the three-dimensional space attitude;

A digital signal processor used for the fusion of ECG signals and three-dimensional space attitude data and extracting, training, and judging the safety characteristics of operators according to the above steps;

A discrimination data output module for outputting the discrimination signal of the digital signal processor.

Preferably, the discrimination data output module is a display or a wireless signal transmission module.

Compared with the prior art, the present invention has the following advantages and beneficial effects:

1. The present invention judges the degree of fatigue of the operator based on the fusion of its own physiological signal and operation posture, and combines the support vector machine (SVM) with the ECG data to achieve fast and accurate technical effects.

Description of drawings

The drawings described here are used to provide a further understanding of the embodiments of the present invention, constitute a part of the application, and do not limit the embodiments of the present invention.

Figure 1 is a flowchart of the method.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples and accompanying drawings. As a limitation of the present invention.

Example 1

A method for judging the safety degree of an operator as shown in Figure 1 includes the following steps:

A. Extract the ECG data index and motion data index of the operator, the ECG data index includes time domain index and frequency domain index, and the motion data index includes operation time WT, operation degree WD, state coefficient K, and fall posture P1 , Falling posture P2;

B. Input the ECG data index into the SVM that has been trained and calibrated to obtain the fatigue level Gn;

C. Calculate X, and judge the fatigue degree of the operator according to X, among which,

X=f*Gn+(1-f)*WT*WD*K+(P1+P2)/(P1*P2+1); where f ranges from 0 to 1.

Example 2

Based on the principles of the foregoing embodiments, this embodiment discloses a specific embodiment.

Train SVMs:

Select the personnel who have been fatigued and those who have not been fatigued in the electric power work scene to collect ECG data and obtain the data set;

Extract ECG data indicators from the data set, the ECG data indicators include time domain indicators and frequency domain indicators, time domain indicators include R wave number HR, R wave interval standard deviation SD; frequency domain indicators include high frequency band power value HF, low frequency band Power value LF, very low frequency band power value VLF.

The input SVM that extracts the ECG data indicators is used to complete the training and calibration.

A. Extract the ECG data indicators and exercise data indicators of the workers. The ECG data indicators include time domain indicators and frequency domain indicators. The exercise data indicators include operating time WT, operating degree WD, state coefficient K, fall posture P1, and fall posture P2 ; Time domain indicators include R wave number HR, R wave interval standard deviation SD; frequency domain indicators include high frequency band power value HF, low frequency band power value LF, and very low frequency band power value VLF. Among them, the working time WT is the recorded cumulative continuous vibration time, WD is the mean square error of the motion data, and K is the normalization coefficient of the hand-raising state time. Taking the worker's working time as an example of 8 hours, the workload index W=WT/8*K*WD is calculated.

B. The operator collects ECG data for 2 minutes, and inputs the ECG data indicators into the above-mentioned SVM that has been trained and calibrated to obtain the fatigue level Gn. Fatigue can be divided into 5 grades, good condition, mild fatigue, fatigue, moderate fatigue and very fatigue, which correspond to G1 to G5 respectively, and the values are 1 to 5.

C. Calculate X, and judge the fatigue degree of the operator according to X. The smaller X is, the higher the safety degree is. Among them,

X=f*Gn+(1-f)*WT*WD*K+(P1+P2)/(P1*P2+1); where f ranges from 0 to 1.

According to the above data, X=0.55*Gn+0.45*W after simplification. Since P1 and P2 events do not occur, then P1=P2=0.

The inertial measurement unit usually includes a micro-accelerometer and a micro-gyroscope. Through the quadratic integration of the acceleration signal and the integration of the gyroscope signal, the position information and orientation information of the object to be measured can be obtained. Through the inertial measurement scheme, labor statistics and emergency warnings can be performed on the attitude of the operators. Labor statistics are mainly reflected in the degree of labor and workload, and emergency warnings are mainly for the identification of falls and falls.

Example 3

Based on the embodiments of the above method, this embodiment discloses a device for implementing the above method.

A device for judging the safety degree of workers, comprising:

The upper case used to collect the ECG signal of the wearer's hand;

The lower case for collecting the ECG signal of the wearer's other hand;

An ECG collection and preprocessing circuit module used to collect the potential difference between the two upper and lower cases to obtain ECG signals and complete signal preprocessing;

A motion sensing acquisition and preprocessing circuit module for acquiring the acceleration and angular velocity of the three axes of space to obtain a three-dimensional spatial attitude; the above-mentioned falling posture P1 and falling posture P2 can be obtained through the motion sensing collection and preprocessing circuit module;

A digital signal processor for the fusion of electrocardiographic signals and three-dimensional space attitude data and extracting, training, and judging the safety characteristics of operators according to the above-mentioned embodiments;

A discrimination data output module for outputting the discrimination signal of the digital signal processor.

The discrimination data output module is a display or a wireless signal transmission module.

The upper watch case and the lower watch case are used as two electrodes for data acquisition, and the motion sensing acquisition and preprocessing circuit module can use an inertial nine-axis sensor, the model is MPU9250. The wireless signal transmission module can adopt GPRS/4G/WIFI module, and the identification data output module can not only display through the LCD screen of the watch, but also communicate and connect the identification data with other devices through wireless means.

The entire device can be a wearable device, such as a smart watch, and a wearable smart watch is used for the collection of physiological signals and operation postures, which not only meets long-term real-time monitoring, but also does not affect the normal operation of operators. The wearable smart watch has a certain computing power, can calculate the safety degree in real time in the device, and upload it wirelessly in real time, and remind the operators and background supervisors at the first time.

The specific embodiments described above have further described the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention and are not intended to limit the scope of the present invention. Protection scope, within the spirit and principles of the present invention, any modification, equivalent replacement, improvement, etc., shall be included in the protection scope of the present invention.

Claims (5)

1. A method for judging the degree of safety of operating personnel, characterized in that, comprising the following steps: A. Extract the ECG data index and motion data index of the operator, the ECG data index includes time domain index and frequency domain index, and the motion data index includes operation time WT, operation degree WD, state coefficient K, and fall posture P1 , Falling posture P2; B. Input the ECG data index into the SVM that has been trained and calibrated to obtain the fatigue level Gn; C. Calculate X, and judge the fatigue degree of the operator according to X, among which, X=f*Gn+(1-f)*WT*WD*K+(P1+P2)/(P1*P2+1); where f ranges from 0 to 1. 2. A method for discriminating the degree of safety of workers according to claim 1, wherein the time-domain indicators include the R-wave number HR and the R-wave interval standard deviation SD; the frequency-domain indicators include high-frequency band power values HF, low Frequency band power value LF, very low frequency band power value VLF. 3. A kind of operator's safety degree discrimination method according to claim 1, is characterized in that, the training method of described SVM is: Select the personnel who have been fatigued and those who have not been fatigued in the electric power work scene to collect ECG data and obtain the data set; Extracting ECG data indicators from the data set, the ECG data indicators include time domain indicators and frequency domain indicators; The input SVM that extracts the ECG data indicators is used to complete the training and calibration. 4. A device for judging the safety degree of an operator, characterized in that it comprises, The upper case used to collect the ECG signal of the wearer's hand; The lower case for collecting the ECG signal of the wearer's other hand; An ECG collection and preprocessing circuit module used to collect the potential difference between the two upper and lower cases to obtain ECG signals and complete signal preprocessing; A motion sensing acquisition and preprocessing circuit module for acquiring the acceleration and angular velocity of the three-axis space to obtain the three-dimensional space attitude; A digital signal processor for merging ECG signals and three-dimensional space attitude data and extracting, training, and judging the safety features of workers according to the steps of any one of claims 1 to 3; A discrimination data output module for outputting the discrimination signal of the digital signal processor. 5 . The equipment for judging the safety degree of workers according to claim 4 , wherein the judging data output module is a display or a wireless signal transmission module. 5 .