Electric shock prevention early warning and protection method and device for power box

Abstract

The invention relates to the technical field of electric shock prevention, in particular to an electric shock prevention early warning and protection method and device for a power box, and the method comprises the steps: collecting leakage current data, in-box temperature data, in-box humidity data and out-box humidity data of the power box in each time period; analyzing the correlation degree of the temperature data in the box and the humidity data in the box to the leakage current data, and obtaining a leakage current first influence coefficient, a leakage network second influence coefficient and a leakage current comprehensive influence coefficient in combination with a data change trend; according to the change trend and data distribution of the humidity data outside the box in each time period, obtaining an electric shock risk degree outside the box, and obtaining an electric shock risk coefficient of each time period; and according to the electric shock risk coefficient of the continuous time period, combining a neural network model to obtain an anti-electric shock safety distance and determining whether to give an alarm. The anti-electric shock safety distance of the power box is obtained, and the accuracy and reliability of anti-electric shock early warning are improved.

Description

Technical Field

[0001] This application relates to the technical field of electric shock prevention, and specifically relates to a method and device for electric shock early warning and protection of a power box. Background Art

[0002] The power box is an important part of the power grid, and it is very important to carry out electric shock early warning and protection for the power box. Electric shock accidents may cause serious personal injuries or even death. By implementing electric shock early warning and protection measures, potential electric shock risks can be detected and responded to in a timely manner to protect the safety of operators and surrounding personnel.

[0003] Traditional methods for electric shock early warning and protection of power boxes mainly rely on sensors to monitor the distance between personnel and the power box and compare it with a preset safe distance to issue warnings. However, the preset safe distance in this method is usually a fixed value set according to the voltage level of the distribution network. In fact, under different environmental conditions, even if the distance between personnel and the power box is the same, the risk of electric shock will be different, making the fixed safe distance may not fully adapt to all situations, resulting in the accuracy and reliability of electric shock early warning being affected. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method and device for electric shock early warning and protection of a power box to solve the above problems.

[0005] According to one aspect of the present application, a method for electric shock early warning and protection of a power box is provided, and the method includes:

[0006] Collect leakage current data, in-box environment monitoring data, and out-box humidity data for each time period of the power box; wherein, the in-box environment monitoring data includes in-box temperature data and in-box humidity data;

[0007] Analyze the correlation degree of the in-box environment monitoring data with the leakage current data in a preset historical time period, and combine the change trend of the in-box environment monitoring data for each time period to obtain the first influence coefficient of the leakage current for each time period;

[0008] Combine the in-box environment monitoring data for each time period and the preset number of time periods before it, and combine with a preset environment threshold to obtain the second influence coefficient of the leakage current for each time period, and obtain the comprehensive influence coefficient of the leakage current for each time period;

[0009] According to the change trend and data distribution of the out-box environment monitoring data for each time period, obtain the out-box electric shock risk degree of the power box for each time period; combine the distribution of the leakage current data for each time period, the leakage current comprehensive influence index, and the out-box electric shock risk degree to obtain the electric shock risk coefficient for each time period;

[0010] Obtain the anti-electric shock safety distance for each time period according to the electric shock risk coefficient in consecutive time periods and in combination with the neural network model;

[0011] Judge whether to issue an alarm according to the distance between the person and the power supply box and the anti-electric shock safety distance for the corresponding time period.

[0012] Among them, obtaining the first influence coefficient of leakage current for each time period is specifically as follows:

[0013] Extract the sequence composed of the in-box temperature data in the preset historical time period and denote it as the historical in-box temperature sequence; use the same method as the historical in-box temperature sequence to obtain the historical in-box humidity sequence and the historical leakage current sequence respectively according to the in-box humidity data in the preset historical time period and the leakage current data in the preset historical time period;

[0014] Perform correlation analysis on the historical in-box temperature sequence and the historical leakage current sequence to obtain the correlation degree W1 of the in-box temperature data to the leakage current data; perform correlation analysis on the historical in-box humidity sequence and the historical leakage current sequence to obtain the correlation degree W2 of the in-box humidity data to the leakage current data;

[0015] Perform trend decomposition on all the in-box temperature data for each time period to obtain a trend item sequence; divide each element in the first-order difference sequence of the trend item sequence by its position serial number to obtain the adjacent temperature trend for each time period ; use the same acquisition method as the adjacent temperature trend to obtain the adjacent humidity trend L3 for each time period according to all the in-box humidity data for each time period;

[0016] Denote the first influence coefficient of leakage current for each time period as S1, and its formula form is: .

[0017] Among them, obtaining the adjacent temperature trend for each time period is specifically the result of fusing the normalized value of the position serial numbers of all elements in the first-order difference sequence with the corresponding elements.

[0018] Among them, obtaining the second influence coefficient of leakage current for each time period is specifically as follows:

[0019] Denote the sequence composed of all the in-box temperature data for each time period and the previous preset number of time periods as the recent in-box temperature sequence; obtain the negative correlation mapping of the difference between each data point in the recent in-box temperature sequence and the preset temperature threshold to obtain a temperature suitability sequence;

[0020] Use the same acquisition method as the temperature suitability sequence to obtain a humidity suitability sequence according to all the in-box humidity data for each time period and the previous preset number of time periods;

[0021] According to the distribution of the means of the elements at the same positions in the temperature suitability sequence and the humidity suitability sequence, the second influence coefficient of the leakage current for each time period is obtained.

[0022] Among them, the comprehensive influence coefficient of the leakage current for each time period is specifically the mean of the normalized value of the first influence coefficient of the leakage current and the normalized value of the second influence coefficient of the leakage current.

[0023] Among them, the process of obtaining the risk degree of electric shock outside the power supply box for each time period includes:

[0024] Using the same acquisition method as the adjacent temperature trend, according to all the humidity data outside the box for each time period, the adjacent humidity trend outside the box for each time period is obtained;

[0025] According to the adjacent humidity trend outside the box for each time period, combined with the distribution of all the humidity data outside the box for each time period, the risk degree of electric shock outside the box for each time period is obtained.

[0026] Among them, the process of obtaining the electric shock risk coefficient for each time period is specifically:

[0027] Denote the electric shock risk coefficient of the power supply box in the t-th time period as F(t), and its formula form is: , where a1 represents the maximum value of all the leakage current data in the t-th time period; a represents the preset leakage current safety threshold of the leakage current; S(t) represents the comprehensive influence coefficient of the leakage current of the power supply box in the t-th time period; f(t) represents the risk degree of electric shock outside the box of the power supply box in the t-th time period; exp() represents the exponential function with the natural constant as the base.

[0028] Among them, the process of obtaining the anti-electric shock safety distance for each time period includes:

[0029] Form the electric shock risk coefficient sequence of the t-th time period by combining the electric shock risk coefficients of the t-th time period and the previous consecutive n time periods; form the electric shock safety distance prediction sequence of the t-th time period by combining the anti-electric shock safety distances from the (t - n - 1)-th time period to the (t - 1)-th time period. Take the electric shock risk coefficient sequence and the electric shock safety distance prediction sequence of the t-th time period as the input of the long short-term memory neural network to obtain the anti-electric shock safety distance of the t-th time period; where n is a preset value.

[0030] Among them, the judgment of whether to issue an alarm is specifically: when it is detected that the distance between a person and the power supply box is less than or equal to the anti-electric shock safety distance of the corresponding time period, an alarm is issued.

[0031] According to another aspect of the present application, there is provided an anti-electric shock early warning and protection device for a power supply box, including:

[0032] A data acquisition module, which is used to acquire the leakage current data, the in-box environment monitoring data, and the out-box humidity data of the power supply box in each time period; among them, the in-box environment monitoring data includes the in-box temperature data and the in-box humidity data;

[0033] A data processing unit, which is used to analyze the correlation degree between the in-box environment monitoring data and the leakage current data in a preset historical time period, and combine the change trend of the in-box environment monitoring data in each time period to obtain the first influence coefficient of the leakage current in each time period; combine the in-box environment monitoring data of each time period and a preset number of time periods before it, and combine the preset environment threshold to obtain the second influence coefficient of the leakage current in each time period, and obtain the comprehensive influence coefficient of the leakage current in each time period; according to the change trend and data distribution of the out-box environment monitoring data in each time period, obtain the out-box electric shock risk degree of the power supply box in each time period; combine the distribution of the leakage current data in each time period, the leakage current comprehensive influence index, and the out-box electric shock risk degree to obtain the electric shock risk coefficient in each time period; according to the electric shock risk coefficient in continuous time periods, and combine the neural network model to obtain the anti-electric shock safety distance in each time period;

[0034] An early warning module, which is used to judge whether to issue an alarm according to the distance between the person and the power supply box and the anti-electric shock safety distance in the corresponding time period.

[0035] This application has at least the following beneficial effects:

[0036] 1. By analyzing the change trend of the temperature and humidity in the power supply box, this application constructs the first influence coefficient of the leakage current, which reflects the influence of the change of the insulation performance of the insulating material of the electrical equipment in the power supply box caused by the temperature and humidity on the leakage current; constructs the second influence coefficient of the leakage current and obtains the comprehensive influence coefficient of the leakage current. Its beneficial effect is that it considers the influence of the change of the air and the insulation performance of the electrical equipment in the power supply box caused by the temperature, humidity and mildew in the power supply box on the leakage current, and can more accurately evaluate the change trend of the leakage current of the power supply box.

[0037] 2. By analyzing the influence of the environmental humidity outside the power supply box on human electric shock, this application constructs the out-box electric shock risk degree, and combines the leakage current comprehensive influence coefficient and the out-box electric shock risk degree to construct the electric shock risk coefficient. Its beneficial effect is that it considers the influence of the environmental humidity outside the power supply box on human electric shock, and can more accurately evaluate the possibility of human electric shock.

[0038] 3. This application calculates the anti-electric shock safety distance based on the constructed electric shock risk coefficient, and completes the anti-electric shock safety warning and protection of the power supply box based on the calculated anti-electric shock safety distance. The beneficial effect is that it takes into account the influence of environmental factors inside and outside the power supply box on the electric shock of the human body caused by the leakage current, and adjusts the setting of the anti-electric shock safety distance of the power supply box accordingly, improving the accuracy and reliability of the anti-electric shock warning, and thus being able to better carry out anti-electric shock warning and protection for the personnel near the power supply box. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of the steps of the anti-electric shock warning and protection method for the power supply box provided by this application;

[0040] Figure 2 It is a schematic diagram for obtaining the first influence coefficient of the leakage current provided by this application;

[0041] Figure 3 It is a schematic diagram for obtaining the second influence coefficient of the leakage current provided by this application;

[0042] Figure 4 It is a schematic diagram for obtaining the electric shock risk coefficient provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In the description of the embodiments of this application, words such as "exemplary", "or", "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "or", "for example" is intended to present relevant concepts in a specific manner.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used in the description of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0045] In addition, it should be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects and are not used to describe a specific order or sequence. For the methods disclosed in the embodiments of this application or the methods shown in the flowcharts, including one or more steps for implementing the methods, without departing from the scope of this application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0046] Please refer to Figure 1 , which shows a flowchart of the steps of the anti-electric shock warning and protection method for the power supply box provided by an embodiment of this application. The method includes the following steps:

[0047] Step 1: Collect the leakage current data, the in-box environment monitoring data, and the out-box humidity data of the power supply box at each time period; among them, the in-box environment monitoring data includes the in-box temperature data and the in-box humidity data.

[0048] The anti-electric shock warning and protection device in this application includes a data acquisition module, a data processing unit, and a warning module; among them, the data acquisition module includes a leakage current acquisition module, an environmental data acquisition module, and a human body perception and ranging module.

[0049] In the leakage current acquisition module, use a leakage current detector to collect the leakage current data of the line where the power supply box is located, and transmit the collected data to the data processing unit; in the environmental data acquisition module, use a temperature and humidity sensor to collect the in-box environment monitoring data and the out-box environment monitoring data of the power supply box, and transmit the collected data to the data processing unit. In this embodiment, the in-box environment monitoring data includes the in-box temperature data and the in-box humidity data, and the out-box environment monitoring data includes the out-box humidity data; in the human body perception and ranging module, use a human body infrared sensor to monitor the personnel entering the monitoring range, and use a laser rangefinder to obtain the real-time distance value between the personnel and the power supply box, and transmit the obtained real-time distance value to the warning module; the data processing unit is responsible for calculating the anti-electric shock safety distance of the power supply box, and transmitting the calculated safety distance to the warning module; the warning module is responsible for issuing warnings and displaying warning information. Among them, the data acquisition time intervals of the leakage current, the in-box temperature, the in-box humidity, the out-box humidity, and the distance value are all set to 30 seconds, and the calculation time interval of the anti-electric shock safety distance is 1 hour. The implementer can adjust the data acquisition time interval and the calculation time interval according to the actual situation, and this application does not limit this.

[0050] Taking the t-th calculation of the anti-electric shock safety distance in this application as an example, that is, the t-th time period corresponding to the anti-electric shock safety distance, hereinafter simply referred to as the t-th time period. Arrange the leakage current data, the in-box temperature data, the in-box humidity data, and the out-box humidity data of this time period in ascending order according to the data acquisition time for each type of data obtained, and respectively obtain the leakage current sequence A1, the in-box temperature sequence A2, the in-box humidity sequence A3, and the out-box humidity sequence A4 in the t-th time period, which are used to characterize the data change of the leakage current, temperature, and the humidity inside and outside the power supply box over time in the t-th time period of the power supply box.

[0051] Step 2: Analyze the correlation degree of the in-box environment monitoring data to the leakage current data in the preset historical time period, and combine the change trend of the in-box environment monitoring data in each time period to obtain the first leakage current influence coefficient in each time period.

[0052] Generally, in power equipment in a power supply box, many places rely on air gaps for insulation. In an environment with high humidity, the number of water molecules in the air increases. These water molecules can act as conductive media, reducing the insulation performance of the air and thus increasing the risk of current leakage in the power equipment in the power supply box. In addition, the magnitude of the leakage current is usually also related to temperature. The higher the temperature, the greater the leakage current. This is because when the temperature rises, the polarization in the insulating medium of the power equipment intensifies, the conductance increases, resulting in a reduction in the insulation resistance of the power equipment and thus an increase in the leakage current.

[0053] Based on the above analysis, obtain the internal temperature data, internal humidity data, and leakage current data of the power supply box in a preset historical time period. The time length of the historical time period is 1 month, and the historical data collection time interval is 1 hour. The historical time period and the data collection time interval can be set by the implementer himself. Sort all the historical data of the internal temperature of the box according to the data collection time to form a historical internal temperature sequence; use the same method as the historical internal temperature sequence to extract the historical data of the internal humidity and leakage current of the box respectively to obtain a historical internal humidity sequence and a historical leakage current sequence.

[0054] Take the historical internal temperature sequence, historical internal humidity sequence, and historical leakage current sequence as the inputs of the grey relational analysis algorithm, and output the relational degree W1 of the internal temperature to the leakage current and the relational degree W2 of the internal humidity to the leakage current, which are used to characterize the influence degree of the temperature and humidity in the power supply box on its leakage current. Among them, the grey relational analysis algorithm is a well-known technology, and the specific process will not be elaborated.

[0055] Taking the internal temperature sequence A2 of the box as an example, use the Seasonal-Trend Decomposition using LOESS (STL) decomposition algorithm to obtain the trend term sequence B2 of the internal temperature sequence A2 of the box to reduce the influence of noise data in the collected humidity data on the subsequent analysis of the change trend of humidity over time. Among them, the STL decomposition algorithm is a well-known technology, and the specific process will not be elaborated.

[0056] Perform a first-order difference process on the trend term sequence B2 to obtain a first-order difference sequence , which is used to characterize the instantaneous change rate of the data points in the internal temperature sequence A2 of the box. Among them, the first-order difference process is a well-known technology, and the specific process will not be elaborated.

[0057] In a short time range, the changes in temperature and humidity often have strong inertia. Therefore, the change trend of temperature in the next time period can be characterized by the change trend of temperature in the current time period. Denote the adjacent temperature trend in the t-th time period as L2(t), which is used to characterize the trend of the change in the internal temperature of the power supply box in the t-th time period on its air insulation performance. Its formula form is: , where represents the first-order difference sequence The i-th data point in can represent the instantaneous change rate of the temperature inside the box; I represents the first-order difference sequence The number of data points in; b2(i) represents the position serial number of the i-th data point in the first-order difference sequence The position serial number of the i-th data point in; softmax() represents the Softmax function, which is used to normalize the data.

[0058] The first-order difference sequence The later the data acquisition time of the temperature data inside the box corresponding to the i-th data point in is, that is, the larger b2(i) is, the more the instantaneous change rate of the temperature inside the box corresponding to the data point B2(i) can reflect the temperature change trend in the (t + 1)-th time period, then the weight of the instantaneous change rate should be larger, that is The larger, and then the larger L2(t) is, the larger the change range of the temperature inside the power supply box in adjacent time periods is, then the greater the possibility that the insulation performance of the air inside the power supply box shows a downward trend in this time period.

[0059] Using the same method as the adjacent temperature trend L2(t), replacing the box temperature sequence A2 with the box humidity sequence A3, the adjacent humidity trend L3(t) is obtained, which is used to characterize that in the t-th time period, the change of the humidity inside the power supply box may affect the insulation resistance of the electrical equipment, and further affect the air insulation performance of the power supply box. If the humidity change trend L3(t) is large in adjacent time periods, it means that the humidity change range inside the power supply box is large, and thus the insulation resistance of the electrical equipment may show a downward trend.

[0060] Furthermore, the first leakage current influence coefficient S1(t) of the power supply box in the t-th time period is obtained, which is used to characterize that in the t-th time period, the changes of the temperature and humidity inside the power supply box affect the insulation performance of the air inside the power supply box and the insulation resistance of the electrical equipment, and thus affect the leakage current in the (t + 1)-th time period. Its formula form is: , where W2(t) and W3(t) respectively represent the correlation degrees of the temperature and humidity inside the box in the t-th time period on the leakage current; L2(t) and L3(t) respectively represent the adjacent temperature trend and adjacent humidity trend in the t-th time period.

[0061] Among them, the schematic diagram for obtaining the first leakage current influence coefficient is as Figure 2 shown.

[0062] If the possibility of an increasing trend in the temperature and humidity inside the power supply box during the (t + 1)-th time period is greater, that is, the larger L2(t) and L3(t) are, the more likely the insulation performance of the air inside the power supply box and the insulation resistance of the electrical equipment will show a downward trend during the (t + 1)-th time period, and thus the more likely it is to cause an increasing trend in the leakage current of the power supply box during the (t + 1)-th time period.

[0063] Step 3: Combine the in-box environment monitoring data of each time period with the in-box environment monitoring data of a preset number of time periods before it, and combine with a preset environment threshold to obtain the second influence coefficient of the leakage current for each time period, and obtain the comprehensive influence coefficient of the leakage current for each time period.

[0064] Since a humid environment is conducive to the growth of mold, when the temperature is 25 - 30 degrees and the relative humidity is 75% - 95%, it is a good condition for the growth of mold. The acidic substances secreted by mold during metabolism, such as acetic acid and citric acid, will interact with the insulating materials of the electrical equipment in the power supply box, resulting in changes in the chemical structure and physical properties of the insulating materials, thereby reducing their insulation performance, and further increasing the risk of current leakage of the electrical equipment in the power supply box.

[0065] Based on the above analysis, the sequence composed of the in-box temperature sequences of the t-th time period and a total of a preset number of time periods before it is denoted as the recent in-box temperature sequence. The recent in-box humidity sequence is obtained by the same method, which is used to reflect the changes in the temperature and humidity inside the power supply box during the t-th time period and the previous time periods. In this embodiment, the preset number is taken as 24. The implementer can adjust it according to the actual situation, and this application does not limit it.

[0066] Obtain the difference between each data point in the recent in-box temperature sequence and the preset temperature threshold to obtain the temperature suitability sequence. In this embodiment, calculate the reciprocal of the absolute value of the difference between each data point in the recent in-box temperature sequence and the temperature threshold, and arrange all the obtained reciprocals in ascending order according to the serial numbers of the corresponding data points to obtain the temperature suitability sequence, which is used to characterize the degree of temperature suitability for mold growth corresponding to each data point in the recent in-box temperature sequence. Among them, the temperature threshold is set to 27.5, that is, the bisecting value of the optimal growth temperature range of mold. In addition, in order to prevent the denominator from being 0, a constant greater than zero needs to be added to the denominator. The value of this constant in this embodiment is 0.01.

[0067] Using the same acquisition method as the temperature suitability sequence, replace the recent in-box temperature sequence and temperature threshold with the recent in-box humidity sequence and humidity threshold respectively. In this embodiment, the humidity threshold is set to 85, which is the bisecting number of the optimal growth humidity range of mildew, to obtain the humidity suitability sequence, which is used to characterize the degree of humidity suitable for mildew growth corresponding to each data point in the recent in-box humidity sequence.

[0068] Denote the sequence composed of the means of the corresponding position elements from left to right in the temperature suitability sequence and the humidity suitability sequence as the mildew growth suitability sequence of the power supply box, which is used to characterize the degree of humidity and temperature in the power supply box at the corresponding moments of the temperature and humidity data in the t-th time period and the previous time periods that are suitable for mildew growth. The larger the value of the data point in the mildew growth suitability sequence, the more suitable the corresponding moment is for mildew growth.

[0069] Denote the mean of all data points in the mildew growth suitability sequence as the second leakage current influence coefficient S2(t) of the power supply box, which is used to characterize the influence of mildew in the power supply box on the change of the insulation performance of the insulating material of the electrical equipment in the t-th time period, and the effect of this change on the leakage current in the (t + 1)-th time period. The larger the second leakage current influence coefficient, the more suitable the environment in the power supply box is for mildew growth, and the more likely it is to cause a decrease in the insulation performance of the insulating material of the electrical equipment in the power supply box, and then the greater the possibility of an increase in the leakage current in the (t + 1)-th time period.

[0070] Among them, the schematic diagram for obtaining the second leakage current influence coefficient is as Figure 3 shown.

[0071] Furthermore, perform Min-Max normalization processing on the first leakage current influence coefficient S1(t) in the t-th time period and the second leakage current influence coefficient S2(t) in the t-th time period respectively, and denote the mean of the two obtained normalization results as the comprehensive leakage current influence coefficient S(t) of the power supply box, which is used to characterize the influence of the changes in the air and the insulation performance of the electrical equipment in the power supply box caused by the temperature, humidity and mildew in the power supply box in the t-th time period on the leakage current in the (t + 1)-th time period. The larger the comprehensive leakage current influence coefficient, the greater the possibility of an increase in the leakage current in the (t + 1)-th time period.

[0072] Step 4: Obtain the out-of-box electric shock risk degree of the power supply box in each time period according to the change trend and data distribution of the out-of-box environmental monitoring data in each time period; comprehensively consider the data distribution of the leakage current in each time period, the comprehensive leakage current influence index and the out-of-box electric shock risk degree to obtain the electric shock risk coefficient in each time period.

[0073] The greater the ambient humidity outside the power supply box, the more likely it is to cause electric shock to the human body. This is because in a high-humidity environment, the moisture in the air increases the conductivity of the human body surface, resulting in a decrease in human body resistance. This not only increases the possibility of current passing through the human body but also increases the magnitude of the current passing through the human body, thereby increasing the risk of electric shock to the human body.

[0074] Using the same acquisition method as the adjacent temperature trend L2(t), replacing the in-box temperature sequence A2 with the out-box humidity sequence A4, the adjacent out-box humidity trend L4(t) is obtained, which is used to characterize the change trend of the ambient humidity outside the power supply box in the t-th time period. The greater the adjacent out-box humidity trend L4(t), the greater the possibility that the ambient humidity in the (t + 1)-th time period will increase.

[0075] Calculate the product between the result of adding 1 to the adjacent out-box humidity trend L4(t) and the mean value of the out-box humidity sequence A4, and record the Min-Max normalization result of the product as the out-box electric shock risk degree f(t) of the power supply box in the t-th time period, which is used to characterize the possibility of the ambient humidity outside the power supply box increasing the risk of electric shock to the human body in the (t + 1)-th time period.

[0076] Furthermore, obtain the electric shock risk coefficient F(t) of the power supply box in the t-th time period, which is used to characterize the possibility of the leakage current of the power supply box causing electric shock to the human body in the out-box environment in the (t + 1)-th time period. Its formula form is: , where a1 represents the maximum value of the leakage current sequence A1 in the t-th time period, that is, it represents the maximum value of all leakage current data in the t-th time period; a represents the preset leakage current safety threshold, which is taken as 50 milliamperes in this embodiment; S(t) represents the comprehensive influence coefficient of the leakage current of the power supply box in the t-th time period; f(t) represents the out-box electric shock risk degree of the power supply box in the t-th time period; exp() represents the exponential function with the natural constant as the base.

[0077] Among them, the schematic diagram for obtaining the electric shock risk coefficient is as Figure 4 shown.

[0078] The greater the leakage current value of the power supply box in the t-th time period is greater than the leakage current safety threshold, that is, the greater exp(a1 - a); and the greater the comprehensive influence index of the leakage current in the t-th time period, that is, the weaker the insulation performance of the air and electrical equipment in the power supply box caused by the temperature, humidity, and mildew in the power supply box, the greater the possibility of leakage current increase; the greater the electric shock risk coefficient in the t-th time period, that is, the greater the possibility of the ambient humidity outside the power supply box increasing the risk of electric shock to the human body, and thus the greater the possibility of the leakage current of the power supply box causing electric shock to the human body in the out-box environment, that is, the greater the electric shock risk coefficient F(t).

[0079] Step 5: Based on the electric shock risk coefficients for consecutive time periods and in combination with the neural network model, obtain the anti-electric shock safety distances for each time period.

[0080] Obtain the initial anti-electric shock safety distance d, which is set according to the voltage level of the line where the power supply box is located. In this application, the value of d is 9 meters for a 500 kV voltage level.

[0081] Obtain the electric shock risk coefficients for the t-th time period and the previous consecutive n time periods. In this embodiment, the value of n is 10. Arrange all the obtained electric shock risk coefficients in ascending order according to the time sequence to obtain the electric shock risk coefficient sequence FN(t) corresponding to the t-th time period. If t - n < 0, perform zero-padding on the missing data before the electric shock risk coefficient sequence until the length of the electric shock risk coefficient sequence is equal to n.

[0082] In the warning module, obtain the anti-electric shock safety distances calculated each time from the (t - n - 1)-th time period to the (t - 1)-th time period. Arrange all the obtained anti-electric shock safety distances in ascending order according to the time sequence to obtain the anti-electric shock safety distance prediction sequence DN(t) for the t-th time period. If t - n < 0, supplement before the first data point of the obtained electric shock risk coefficient sequence, and the supplemented value is the initial anti-electric shock safety distance d until the length of the anti-electric shock safety distance prediction sequence is equal to n.

[0083] Take the electric shock risk coefficient sequence for each time period as a sample, and take the anti-electric shock safety distance prediction sequence for each time period as a label sequence; and ensure that the lengths of all samples and the corresponding label sequences are equal. The purpose of doing this is to enable the model to extract the deep features of the anti-electric shock safety distance and time, making the model output more in line with the actual situation.

[0084] Secondly, take the samples encoded with the label sequence as the input to train the long short-term memory neural network model. Among them, take the root mean square loss function as the loss function of the neural network model, take the gradient descent method as the optimization algorithm of the neural network model, and take the trained model as the prediction model for the anti-electric shock safety distance. The training of the long short-term memory neural network model is a well-known technology, and the specific process will not be elaborated here.

[0085] Take the electric shock risk coefficient sequence FN(t) and the anti-electric shock safety distance prediction sequence DN(t) as the input of the prediction model for the anti-electric shock safety distance, and output the predicted anti-electric shock safety distance as the anti-electric shock safety distance for the t-th time period, denoted as d(t), and transmit it to the warning module.

[0086] Step 6: Based on the distance between the person and the power supply box and the anti-electric shock safety distance for the corresponding time period, determine whether to issue an alarm.

[0087] In the (t + 1)-th time period, if the human body perception and ranging module senses the presence of a person and the distance between the person and the power supply box is less than or equal to d(t), an alarm is triggered, and the real-time distance value of the person and the current anti-electric shock safety distance d(t) are displayed in real time in the early warning module, completing the anti-electric shock safety early warning and protection of the power supply box.

[0088] Based on the same concept as the method embodiment of the present application, an anti-electric shock early warning and protection device for a power supply box is provided, including:

[0089] A data acquisition module, configured to acquire the leakage current data, the in-box environment monitoring data, and the out-box humidity data of the power supply box in each time period; wherein, the in-box environment monitoring data includes the in-box temperature data and the in-box humidity data;

[0090] A data processing unit, configured to analyze the correlation degree between the in-box environment monitoring data and the leakage current data in a preset historical time period, and combine the change trend of the in-box environment monitoring data in each time period to obtain the first influence coefficient of the leakage current in each time period; combine the in-box environment monitoring data in each time period and a preset number of time periods before it, and combine a preset environment threshold to obtain the second influence coefficient of the leakage current in each time period, and obtain the comprehensive influence coefficient of the leakage current in each time period; obtain the out-box electric shock risk degree of the power supply box in each time period according to the change trend and data distribution of the out-box environment monitoring data in each time period; combine the distribution of the leakage current data in each time period, the leakage current comprehensive influence index, and the out-box electric shock risk degree to obtain the electric shock risk coefficient in each time period; and obtain the anti-electric shock safety distance in each time period according to the electric shock risk coefficients in continuous time periods and in combination with a neural network model;

[0091] An early warning module, configured to judge whether to issue an alarm according to the distance between the person and the power supply box and the anti-electric shock safety distance in the corresponding time period.

[0092] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to the embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the boxes may occur in a different order than that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes may also occur in a different order than that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. Each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0093] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. The anti-electric shock warning and protection method of the power supply box is characterized in that: The method comprises the following steps: Collect leakage current data, in-box environment monitoring data, and outside-box humidity data of the power box in each time period; among which, in-box environment monitoring data includes in-box temperature data and in-box humidity data; Analyze the correlation between the in-box environment monitoring data and the leakage current data in the preset historical time period, and combine the change trend of the in-box environment monitoring data in each time period to obtain the first influence coefficient of the leakage current in each time period; Combine the in-box environmental monitoring data of each time period with the preset number of time periods before it, and combine them with the preset environmental threshold to obtain the second influence coefficient of the leakage current in each time period, and obtain the comprehensive influence coefficient of the leakage current in each time period; According to the change trend and data distribution of the external environment monitoring data in each time period, the risk of electric shock outside the power box in each time period is obtained; the distribution of leakage current data in each time period, the leakage current comprehensive impact index and the risk of electric shock outside the box are combined to obtain the risk coefficient of electric shock in each time period; According to the electric shock risk coefficient of continuous time periods, combined with the neural network model, the anti-electric shock safety distance of each time period is obtained; Determine whether to sound an alarm based on the distance between the person and the power box and the safety distance against electric shock in the corresponding time period.

2. The anti-electric shock warning and protection method for a power supply box as claimed in claim 1, characterized in that: The first influence coefficient of the leakage current in each time period is obtained as follows: Extract the sequence of the box temperature data in the preset historical time period and record it as the historical box temperature sequence; adopt the same method as the historical box temperature sequence to obtain the historical box humidity sequence and the historical leakage current sequence according to the box humidity data in the preset historical time period and the leakage current data in the preset historical time period; The correlation degree analysis is performed on the historical temperature sequence in the box and the historical leakage current sequence to obtain the correlation degree W1 of the temperature data in the box to the leakage current data; the correlation degree analysis is performed on the historical humidity sequence in the box and the historical leakage current sequence to obtain the correlation degree W2 of the humidity data in the box to the leakage current data; All the temperature data in the box in each time period are decomposed by trend to obtain the trend item sequence; the elements in the first-order difference sequence of the trend item sequence and their position numbers are combined to obtain the adjacent temperature trends in each time period. ; Using the same acquisition method as the adjacent temperature trend, according to all the humidity data in the box in each time period, the adjacent humidity trend L3 of each time period is obtained; The first influence coefficient of leakage current in each time period is recorded as S1, and its formula is: .

3. The anti-electric shock warning and protection method for a power supply box as claimed in claim 2, characterized in that: The adjacent temperature trends in each time period are obtained, specifically, the result of fusing the normalized values ​​of the position numbers of all elements in the first-order difference sequence with the corresponding elements.

4. The anti-electric shock warning and protection method for a power supply box according to claim 1, characterized in that: The second influence coefficient of the leakage current in each time period is obtained, specifically: Record the sequence composed of all the in-box temperature data of each time period and a total of a preset number of time periods before as a recent in-box temperature sequence; obtain a negative correlation mapping of the difference between each data point in the recent in-box temperature sequence and a preset temperature threshold, and obtain a temperature suitability sequence; Using the same acquisition method as the temperature suitable sequence, the humidity suitable sequence is obtained according to all the humidity data in each time period and the previously preset number of time periods; According to the distribution of the mean values ​​of the elements at the same position in the temperature suitable sequence and the humidity suitable sequence, the second influence coefficient of the leakage current in each time period is obtained.

5. The anti-electric shock warning and protection method for a power supply box as claimed in claim 1, characterized in that: The comprehensive influence coefficient of the leakage current in each time period is specifically an average of a normalized value of the first influence coefficient of the leakage current and a normalized value of the second influence coefficient of the leakage current.

6. The anti-electric shock warning and protection method for a power supply box as claimed in claim 3, characterized in that: The process of obtaining the risk of electric shock outside the power box in each time period includes: Adopting the same acquisition method as the adjacent temperature trend, according to all the humidity data outside the box in each time period, the adjacent humidity trend outside the box in each time period is obtained; According to the humidity trends outside the adjacent boxes in each time period and the distribution of all humidity data outside the boxes in each time period, the risk of electric shock outside the box in each time period is obtained.

7. The anti-electric shock warning and protection method for a power supply box as claimed in claim 1, characterized in that: The electric shock risk coefficient obtained in each time period is specifically: The electric shock risk factor of the power box in the tth time period is recorded as F(t), and its formula is: , where a1 represents the maximum value of all leakage current data in the tth time period; a represents the preset leakage current safety threshold; S(t) represents the comprehensive influence coefficient of leakage current of the power box in the tth time period; f(t) represents the risk of electric shock outside the power box in the tth time period; exp() represents an exponential function with a natural constant as the base.

8. The anti-electric shock warning and protection method for a power supply box as claimed in claim 1, characterized in that: The step of obtaining the safety distance for preventing electric shock in each time period includes: The electric shock risk coefficients of the tth time period and the previous n consecutive time periods are combined into the electric shock risk coefficient sequence of the tth time period; the electric shock safety distances from the tn-1th time period to the t-1th time period are combined into the electric shock safety distance prediction sequence of the tth time period; the electric shock risk coefficient sequence of the tth time period and the electric shock safety distance prediction sequence are used as inputs of the long short-term memory neural network to obtain the electric shock safety distance of the tth time period; wherein n is a preset value.

9. The anti-electric shock warning and protection method for a power supply box as claimed in claim 1, characterized in that: The determination of whether to issue an alarm is specifically as follows: issuing an alarm when it is detected that the distance between the person and the power box is less than or equal to the safety distance for preventing electric shock in the corresponding time period.

10. The anti-electric shock warning and protection device of the power box is characterized by: include: The data acquisition module is used to collect leakage current data of the power box in each time period, the environment monitoring data inside the box, and the humidity data outside the box; wherein the environment monitoring data inside the box includes the temperature data inside the box and the humidity data inside the box; The data processing unit is used to analyze the correlation between the in-box environmental monitoring data and the leakage current data in the preset historical time period, and obtain the first leakage current influence coefficient of each time period in combination with the change trend of the in-box environmental monitoring data in each time period; combine each time period with the in-box environmental monitoring data of a preset number of time periods before it, and combine it with the preset environmental threshold, to obtain the second leakage current influence coefficient of each time period, and obtain the comprehensive leakage current influence coefficient of each time period; according to the change trend and data distribution of the external environmental monitoring data in each time period, obtain the external electric shock risk of the power box in each time period; comprehensively analyze the distribution of the leakage current data in each time period, the leakage current comprehensive influence index and the external electric shock risk, to obtain the electric shock risk coefficient of each time period; according to the electric shock risk coefficient of the continuous time period, combined with the neural network model, obtain the anti-electric shock safety distance of each time period; The early warning module is used to determine whether to issue an alarm based on the distance between the person and the power box and the anti-electric shock safety distance in the corresponding time period.

Images