An active safety warning method for non-stop operation process based on artificial intelligence

Abstract

The present invention relates to an artificial intelligence-based active safety warning method for non-stop power operations, and relates to the field of power technology. The method primarily comprises: obtaining environmental data, monitoring data, original line operation data, and temporary bypass operation data during non-stop power operations on distribution network lines; determining a power operation risk coefficient based on the environmental data, original line operation data, and temporary bypass operation data; extracting video frames from the monitoring data, and determining a target video frame from the extracted video frames based on the operation risk level determined by the power operation risk coefficient; determining a worker's operation data, protective data, and construction equipment operation data based on the target video frame; calculating the worker's operation risk value based on the worker's operation data, protective data, construction equipment operation data, and the power operation risk coefficient; and issuing a safety warning if the worker's operation risk value is greater than a preset value.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an active safety early warning method for a non-stop operation process based on artificial intelligence. Background Art

[0002] With the continuous development of economic construction, urban construction has put forward stricter requirements for uninterrupted power supply and voltage fluctuation. Industrial progress, the development of automation, the improvement of people's living standards, and the popularization of household appliances have made improving power supply reliability a key task for the current power sector. Even interrupting power supply for maintenance on distribution line equipment has become unacceptable. This requires the vigorous implementation of live-line maintenance and repair work to replace power outage maintenance to improve power supply reliability. In this situation, the implementation of non-stop maintenance work on distribution network lines is imperative. This can timely address defects, improve the stability of equipment and power grids, ensure continuous power supply to users, and enhance economic and social benefits.

[0003] Currently, risk assessment for non-stop power system operations is based on human experience, which is highly subjective and rarely involves quantitative analysis. This results in poor scientificity and accuracy in the assessment. Therefore, a safety early warning method for non-stop power system operations is urgently needed to ensure the safe conduct of operations. Summary of the Invention

[0004] The present invention aims to provide an artificial intelligence-based active safety warning method for non-power-off operation processes to address the deficiencies in the prior art. The technical problems to be solved by the present invention are achieved through the following technical solutions.

[0005] An embodiment of the present invention provides an artificial intelligence-based active safety early warning method for a non-power-off operation process, the method comprising:

[0006] Obtaining environmental data, monitoring data, original line operation data, and temporary bypass operation data during the uninterrupted operation of the distribution network line; the monitoring data includes the uninterrupted operation process of the workers and construction equipment;

[0007] determining a power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data;

[0008] Determining an operation risk level based on the power operation risk coefficient;

[0009] extracting video frames from the monitoring data, and determining target video frames based on the operation risk level and the video frames;

[0010] Determining the operation data, protection data of the worker and the operation data of the construction equipment according to the target video frame;

[0011] Calculating the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient;

[0012] If the worker's operational risk value is greater than a preset value, a safety warning is issued.

[0013] In an optional embodiment, determining the power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data includes:

[0014] Determining the power supply line by comparing the original line operation data and the temporary bypass operation data;

[0015] If the power supply line is the original line, determining the power operation risk coefficient based on the original line operation data and the environmental data;

[0016] If the power supply line is a temporary bypass, the power operation risk coefficient is determined based on the temporary bypass operation data and the environmental data.

[0017] In an optional embodiment, determining the power operation risk coefficient based on the original line operation data and the environmental data includes:

[0018] Obtaining voltage data, current data, and temperature data from the original line operation data;

[0019] Determine the risk levels corresponding to the voltage data, the current data, the temperature data, and the environmental data respectively according to a preset mapping table;

[0020] The power operation risk coefficient is obtained by performing a weighted calculation on all risk levels.

[0021] In an optional embodiment, the method further includes:

[0022] Converting the voltage data, current data, temperature data and the environmental data in the original line operation data into a eigenvector matrix;

[0023] Inputting the characteristic vector matrix into the power operation risk prediction model to predict the power operation risk coefficient;

[0024] The power operation risk coefficient obtained by weighted calculation is compared with the power operation risk coefficient predicted by the power operation risk prediction model, and the maximum value of the comparison results is taken as the final power operation risk coefficient.

[0025] In an optional embodiment, determining the power operation risk coefficient based on the temporary bypass operation data and the environmental data includes:

[0026] Acquiring voltage data, current data, and temperature data from the temporary bypass operation data;

[0027] Converting the voltage data, current data, temperature data and the environmental data in the temporary bypass operation data into a eigenvector matrix;

[0028] The characteristic vector matrix is ​​input into the power operation risk prediction model to predict the power operation risk coefficient.

[0029] In an optional embodiment, determining the target video frame based on the operation risk level and the video frame includes:

[0030] Determine the operation risk level according to the interval range of the power operation risk coefficient;

[0031] A target video frame is determined from the video frames using the identification keyword corresponding to the operation risk level.

[0032] In an optional embodiment, determining the target video frame from the video frames using the identification keyword corresponding to the operation risk level includes:

[0033] Determine the target to be identified by using the identification keywords corresponding to the operation risk level;

[0034] A video frame containing the target to be identified is determined from the video frames, and the video frame containing the target to be identified is determined as a target video frame.

[0035] In an optional embodiment, determining the worker's operation data, protection data, and operation data of the construction equipment according to the target video frame includes:

[0036] If the target to be identified in the target video frame is a person, determining the operation data and protection data of the staff member according to the time sequence of the target video frame;

[0037] If the target to be identified in the target video frame is a construction machine, the operation data of the construction machine is determined according to the time sequence of the target video frame.

[0038] In an optional embodiment, the calculating of the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient includes:

[0039] Determine the personnel operation score and personnel protection score corresponding to the personnel operation data and protection data respectively through the personnel operation rule table;

[0040] Determine the equipment operation score corresponding to the operation of the construction equipment according to the construction equipment operation rule table;

[0041] The worker's operation risk value is calculated based on the personnel operation score, the personnel protection score, the equipment operation score, and the power operation risk coefficient.

[0042] An embodiment of the present invention provides an active safety warning device for a non-stop operation process based on artificial intelligence, the device comprising:

[0043] An acquisition module is used to obtain environmental data, monitoring data, original line operation data, and temporary bypass operation data during the uninterrupted operation of the distribution network line; the monitoring data includes the uninterrupted operation process of the workers and construction equipment;

[0044] a determination module, configured to determine a power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data;

[0045] The determination module is further configured to determine an operation risk level based on the power operation risk coefficient;

[0046] The determination module is further configured to extract video frames from the monitoring data and determine target video frames based on the operation risk level and the video frames;

[0047] The determination module is further configured to determine the worker's operation data, protection data, and operation data of the construction equipment based on the target video frame;

[0048] a calculation module, configured to calculate the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient;

[0049] The early warning module is used to issue a safety warning if the operator's operation risk value is greater than a preset value.

[0050] The embodiments of the present invention include the following advantages:

[0051] An embodiment of the present invention provides an artificial intelligence-based active safety warning method and device for non-stop power supply operation processes. The method first obtains environmental data, monitoring data, original line operation data, and temporary bypass operation data during the non-stop power supply operation of a distribution network line; the monitoring data includes the non-stop power supply operation process of workers and construction equipment; then, a power supply operation risk coefficient is determined based on the environmental data, original line operation data, and temporary bypass operation data; video frames are extracted from the monitoring data, and a target video frame is determined from the extracted video frames based on the operation risk level determined by the power supply operation risk coefficient; the worker's operation data, protective data, and construction equipment operation data are determined based on the target video frame; the worker's operation risk value is calculated based on the worker's operation data, protective data, construction equipment operation data, and the power supply operation risk coefficient; and a safety warning is issued if the worker's operation risk value is greater than a preset value. Compared to safety assessment and warning for non-stop power supply operations based on human experience, this embodiment calculates the worker's operation risk value based on the acquired data and issues a safety warning when the worker's operation risk value is greater than a preset value. Thus, this embodiment implements intelligent safety warning for non-stop power supply operations, thereby improving the worker's operation safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of an active safety warning method for a non-stop operation process based on artificial intelligence provided by an embodiment of the present invention;

[0053] Figure 2 This is a flow chart for determining a risk factor of an electric power operation provided by an embodiment of the present invention;

[0054] Figure 3 This is a structural diagram of an active safety warning device for non-power-off operation processes based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0056] Embodiment 1:

[0057] See also Figure 1 , an embodiment of the present invention provides an artificial intelligence-based active safety warning method for non-stop operation processes, the method specifically comprising S101-S107:

[0058] S101, obtaining environmental data, monitoring data, original line operation data and temporary bypass operation data during the non-stop operation of the distribution network line.

[0059] Since extreme weather such as thunderstorms and strong winds may affect the safety of non-stop power operations; environmental pollutants around the lines, such as salt spray and chemicals, may also cause corrosion or other damage to equipment; therefore, this embodiment needs to obtain environmental data during the non-stop power operation of the distribution network lines, thereby determining the impact of the current environment on the non-stop power operation.

[0060] The monitoring data in this embodiment is video footage of workers and construction equipment captured by video cameras. Temporary bypass is primarily used to bypass faulty or repaired sections of a line during overhaul or maintenance, maintaining continuous power supply to users. By setting up a temporary bypass to replace the section requiring repair, continuous power supply to users is maintained.

[0061] The line operation data and temporary bypass operation data include voltage data, current data, temperature data, and equipment status, etc., which are not specifically limited in this embodiment.

[0062] S102: Determine the power operation risk factor based on environmental data, original line operation data, and temporary bypass operation data.

[0063] In this embodiment, the risk factor for power operations can be used to indicate the risk associated with currently ongoing, uninterrupted power operations. A higher risk factor corresponds to a greater risk, while a lower risk factor corresponds to a lower risk. Both the original line operation data and the temporary bypass operation data include voltage data, current data, and temperature data. Voltage data includes real-time voltage values ​​and voltage fluctuation values. By continuously monitoring the line's real-time voltage level, it is possible to determine whether overvoltage or undervoltage conditions exist, which is fundamental to assessing the safety of uninterrupted power operations. Analyzing the voltage fluctuation pattern and frequency helps identify abnormal conditions that may lead to equipment failure or safety incidents. Current data includes load current values ​​and short-circuit current values. Monitoring the load current in the line ensures it remains within a safe range, avoiding safety issues caused by overloads and detecting short-circuit events. This is crucial for preventing circuit damage and ensuring worker safety. Temperature data includes conductor temperature and joint temperature. Conductor temperature directly affects its electrical resistance and mechanical strength. High temperatures can cause conductors to melt or break. Joints are common hotspots, and monitoring the temperature of these areas can help prevent fires or equipment failures caused by overheating.

[0064] Example 2:

[0065] like Figure 2 As shown, in an optional embodiment provided in the present application, determining the power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data includes:

[0066] S1021: Determine a power supply line by comparing the original line operation data and the temporary bypass operation data.

[0067] The power supply line can be determined by comparing the voltage, current, and temperature of the lines. Specifically, a safer line can be selected as the power supply line based on these three parameters. Specifically, this embodiment can perform a weighted calculation of the voltage, current, and temperature to obtain line scores corresponding to the original line and the temporary bypass line, and then determine the power supply line based on the line scores.

[0068] More specifically, this embodiment can determine the scores corresponding to the specific values ​​of voltage, current, and temperature. For example, the safety scores corresponding to the numerical ranges of voltage, current, and temperature can be determined based on a safety score mapping table. The determined safety scores are then weighted to calculate the line score, and the line with the highest score is ultimately determined as the power supply line. Thus, this embodiment can ensure the safety of line transportation and the safety of maintenance personnel.

[0069] S1022: If the power supply line is the original line, determine the power operation risk coefficient based on the original line operation data and the environmental data.

[0070] Specifically, the determination of the power operation risk coefficient based on the original line operation data and the environmental data includes: obtaining the voltage data, current data, and temperature data in the original line operation data; determining the risk levels corresponding to the voltage data, current data, temperature data, and environmental data respectively according to a preset mapping table; and performing a weighted calculation on all risk levels to obtain the power operation risk coefficient. The preset mapping table stores risk levels corresponding to different voltage ranges, current ranges, and temperature ranges. This embodiment searches the preset mapping table for the numerical ranges corresponding to the voltage data, current data, and temperature data, and then determines the risk level of loss or gain based on the corresponding numerical ranges. The risk level can be specifically represented by a number, such as a higher numerical value represents a higher risk level, and a lower numerical value represents a lower risk level.

[0071] Furthermore, this embodiment can also convert the voltage data, current data, temperature data and environmental data in the original line operation data into a characteristic vector matrix; input the characteristic vector matrix into the power operation risk prediction model to predict the power operation risk coefficient; compare the power operation risk coefficient obtained by weighted calculation with the power operation risk coefficient predicted by the power operation risk prediction model, and take the maximum value in the comparison result as the final power operation risk coefficient.

[0072] In this embodiment, the power operation risk coefficient is determined in two ways, namely, the power operation risk prediction model and the power operation risk coefficient obtained by the previous weighted calculation, and then the power operation risk coefficients determined by the two ways are compared, and the maximum value of the comparison results is taken as the final power operation risk coefficient, thereby ensuring the safety of the non-stop operation process.

[0073] Among them, the power operation risk prediction model is trained based on a large amount of sample data. The sample data is line sample data, which includes voltage data, current data, temperature data and environmental data. The sample line data is then converted into a eigenvector matrix, and the eigenvector matrix is ​​input into the power operation risk prediction model to obtain the power operation risk prediction coefficient. The loss value is then calculated using the power operation risk prediction coefficient and the power operation risk coefficient label. When the loss value is less than a certain value, the training of the power operation risk prediction model is completed.

[0074] In this embodiment, before converting the sample line data into a feature vector matrix, the sample line data needs to be preprocessed, such as performing data cleaning on the sample line data to remove errors, duplications, and incomplete records in the data set to ensure the accuracy and reliability of the data; data integration and data conversion include operations such as formatting and normalization, which are not specifically limited in this embodiment.

[0075] It should be noted that the power operation risk prediction model in this embodiment is trained by combining two types of models, namely, the classification model and the regression model are trained together to obtain the power operation risk prediction model, wherein the loss function calculation formula of the power operation risk prediction model is as follows:

[0076]

[0077]

[0078]

[0079] in, is the loss function of the classification model, is the loss function of the regression model, n is the number of sample line data, γ is the loss weight; p i is the predicted label of the i-th sample line data, is the actual label of the i-th sample line data, t i is the predicted label of the i-th sample line data, is the actual label of the i-th sample line data, and σ is the weight value for controlling smoothing.

[0080] S1023: If the power supply line is a temporary bypass, determine the power operation risk coefficient based on the temporary bypass operation data and the environmental data.

[0081] Specifically, determining the power operation risk coefficient based on the temporary bypass operation data and the environmental data includes: obtaining the voltage data, current data, and temperature data in the temporary bypass operation data; converting the voltage data, current data, temperature data and the environmental data in the temporary bypass operation data into a eigenvector matrix; inputting the eigenvector matrix into the power operation risk prediction model to predict the power operation risk coefficient.

[0082] It should be noted that the power operation risk prediction model in this embodiment is the same as the power operation risk prediction model in step S1022, that is, after the voltage data, current data, temperature data and environmental data in the temporary bypass operation data are converted into a characteristic line matrix, the characteristic vector matrix is ​​input into the power operation prediction model to obtain the power operation risk coefficient.

[0083] Furthermore, this embodiment can also perform linear fitting based on the sample data to obtain a linear fitting formula, and then determine the power operation risk coefficient based on the linear fitting formula. Specifically, the linear fitting formula in this embodiment is:

[0084] y=ax1 2 +bx2 3 +cx3

[0085] Where y is the obtained power operation risk coefficient, x1 is the voltage data, x2 is the current data, x3 is the temperature data, and a, b, and c are constant coefficients.

[0086] S103: Determine the operation risk level based on the power operation risk coefficient.

[0087] S104: extracting video frames from the monitoring data, and determining target video frames based on the operation risk level and the video frames.

[0088] In this embodiment, after extracting the video frame from the monitoring data, it is necessary to determine the corresponding operation risk level based on the power operation risk coefficient, and then determine the target video frame from the extracted video frame based on the content that needs to be monitored corresponding to the operation risk level, so that in the subsequent steps, the dangers that may occur during the non-stop operation can be warned based on the target video frame. Therefore, this embodiment can increase the amount of calculation required for the safety warning, thereby improving the efficiency of the safety warning.

[0089] It should be noted that in this embodiment, different monitoring objects are set for different operation risk levels. The higher the operation risk level, the more monitoring objects are required, thereby achieving monitoring from multiple aspects to ensure the safety of non-stop operations.

[0090] In an optional embodiment provided in the present application, determining the target video frame based on the operation risk level and the video frame includes:

[0091] S1031, determining the operation risk level according to the interval range of the power operation risk coefficient.

[0092] Specifically, this embodiment can determine the operation risk level corresponding to the power operation risk coefficient using a risk level table. This risk level table includes operation risk levels corresponding to various intervals. After obtaining the power operation risk coefficient, the risk level table is searched to determine the interval within which the power operation risk coefficient falls. The corresponding operation risk level is then determined based on this interval.

[0093] S1032: Determine a target video frame from the video frames using the identification keyword corresponding to the operation risk level.

[0094] Furthermore, the risk level table in this embodiment also includes identification keywords corresponding to each operation risk level. For example, the identification keywords can be operators, construction equipment, protective equipment, operating tools, foreign objects on the line, etc., which are not specifically limited in this embodiment. In this embodiment, after obtaining the corresponding identification keywords, the target video frame is determined from the extracted video frames based on the identification keywords. Specifically, this embodiment can identify the video frame based on image recognition technology or a neural network model to determine whether it contains the items corresponding to the identification keywords. If so, the video frame is determined as the target video frame.

[0095] In order to determine the target video frame for the neural network model, this embodiment needs to be trained with sample data and corresponding identification labels, that is, first it is necessary to obtain sample data and its identification labels, and then train to obtain the neural network model. It should be noted that since the camera equipment is easily shaken by environmental factors and the drone shooting angle problem leads to poor image viewing angle, the rotation and flipping methods are used to solve this problem. If the viewing angle is not good, a suitable rotation angle is selected. If the viewing angle is suitable, it can also be set to 5° to expand the data set. In order to solve the problems of low clarity and changes caused by natural factors such as rainy days and light intensity, the color space transformation method is used, that is, by randomly changing the saturation and transparency of the photo, the influence is eliminated to a certain extent and the image diversity is increased. Each sample is processed by the image enhancement method to generate a new image, and added to the initial data set. The final data set is obtained after screening.

[0096] S105 , determining the worker's operation data, protection data, and operation data of the construction equipment according to the target video frame.

[0097] Among them, the staff's operation data is used to describe the staff's workflow or work steps during the non-stop operation; the staff's protection data is used to describe whether the tools worn or used by the staff during the non-stop operation are properly protected; the construction equipment's operation data is used to describe the workflow or work steps during the non-stop operation during the construction period.

[0098] In an optional embodiment provided in the present application, the operation data, protection data of the staff and the operation data of the construction equipment are determined based on the target video frame, including: if the target to be identified in the target video frame is a person, the operation data and protection data of the staff are determined according to the time sequence of the target video frame; if the target to be identified in the target video frame is a construction equipment, the operation data of the construction equipment is determined according to the time sequence of the target video frame.

[0099] S106, calculating the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient.

[0100] Specifically, the operation risk value of the staff is calculated based on the operation data, protection data, operation data of the construction equipment and the power operation risk coefficient of the staff, including: determining the personnel operation score and personnel protection score corresponding to the operation data and protection data of the staff through the staff operation rule table; determining the equipment operation score corresponding to the operation of the construction equipment according to the construction equipment operation rule table; calculating the operation risk value of the staff based on the personnel operation score, the personnel protection score, the equipment operation score and the power operation risk coefficient.

[0101] S107: If the worker's operation risk value is greater than a preset value, a safety warning is issued.

[0102] The preset values ​​are set based on actual needs or experience.

[0103] This embodiment provides an artificial intelligence-based active safety warning method for non-stop power supply operation processes. The method first obtains environmental data, monitoring data, original line operation data, and temporary bypass operation data during the non-stop power supply operation of the distribution network line; the monitoring data includes the non-stop power supply operation process of the workers and construction equipment; then, the power supply operation risk coefficient is determined based on the environmental data, original line operation data, and temporary bypass operation data; video frames are extracted from the monitoring data, and target video frames are determined from the extracted video frames based on the operation risk level determined by the power supply operation risk coefficient; the worker's operation data, protective data, and construction equipment operation data are determined based on the target video frames; the worker's operation risk value is calculated based on the worker's operation data, protective data, construction equipment operation data, and the power supply operation risk coefficient; and a safety warning is issued if the worker's operation risk value is greater than a preset value. Compared with safety assessment and warning for non-stop power supply operations based on human experience, this embodiment calculates the worker's operation risk value through the acquired data and issues a safety warning when the worker's operation risk value is greater than the preset value. Thus, this embodiment realizes intelligent safety warning for non-stop power supply operations, thereby improving the worker's operation safety.

[0104] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0105] Example 3:

[0106] In one embodiment, an active safety warning device for non-stop operation process based on artificial intelligence is provided. Figure 3 As shown, the functional modules of the active safety warning device for non-stop operation based on artificial intelligence are described in detail as follows:

[0107] An acquisition module 31 is configured to acquire environmental data, monitoring data, original line operation data, and temporary bypass operation data during the uninterrupted operation of the distribution network line; the monitoring data includes the uninterrupted operation process of the workers and construction equipment;

[0108] a determination module 32, configured to determine a power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data;

[0109] The determination module 32 is further configured to determine an operation risk level based on the power operation risk coefficient;

[0110] The determination module 32 is further configured to extract video frames from the monitoring data and determine target video frames based on the operation risk level and the video frames;

[0111] The determination module 32 is further configured to determine the worker's operation data, protection data, and operation data of the construction equipment according to the target video frame;

[0112] A calculation module 33 is configured to calculate the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient;

[0113] The early warning module 34 is used to issue a safety early warning if the worker's operation risk value is greater than a preset value.

[0114] In an optional embodiment, the determination module 32 is specifically configured to:

[0115] Determining the power supply line by comparing the original line operation data and the temporary bypass operation data;

[0116] If the power supply line is the original line, determining the power operation risk coefficient based on the original line operation data and the environmental data;

[0117] If the power supply line is a temporary bypass, the power operation risk coefficient is determined based on the temporary bypass operation data and the environmental data.

[0118] In an optional embodiment, the determination module 32 is specifically configured to:

[0119] Obtaining voltage data, current data, and temperature data from the original line operation data;

[0120] Determine the risk levels corresponding to the voltage data, the current data, the temperature data, and the environmental data respectively according to a preset mapping table;

[0121] The power operation risk coefficient is obtained by performing a weighted calculation on all risk levels.

[0122] In an optional embodiment, the apparatus further includes a prediction module 35, configured to:

[0123] Converting the voltage data, current data, temperature data and the environmental data in the original line operation data into a eigenvector matrix;

[0124] Inputting the characteristic vector matrix into the power operation risk prediction model to predict the power operation risk coefficient;

[0125] The power operation risk coefficient obtained by weighted calculation is compared with the power operation risk coefficient predicted by the power operation risk prediction model, and the maximum value of the comparison results is taken as the final power operation risk coefficient.

[0126] In an optional embodiment, the determination module 32 is further configured to:

[0127] Acquiring voltage data, current data, and temperature data from the temporary bypass operation data;

[0128] Converting the voltage data, current data, temperature data and the environmental data in the temporary bypass operation data into a eigenvector matrix;

[0129] The characteristic vector matrix is ​​input into the power operation risk prediction model to predict the power operation risk coefficient.

[0130] In an optional embodiment, the determination module 32 is specifically configured to:

[0131] Determine the operation risk level according to the interval range of the power operation risk coefficient;

[0132] A target video frame is determined from the video frames using the identification keyword corresponding to the operation risk level.

[0133] In an optional embodiment, the determination module 32 is specifically configured to:

[0134] Determine the target to be identified by using the identification keywords corresponding to the operation risk level;

[0135] A video frame containing the target to be identified is determined from the video frames, and the video frame containing the target to be identified is determined as a target video frame.

[0136] In an optional embodiment, the determination module 32 is specifically configured to:

[0137] If the target to be identified in the target video frame is a person, determining the operation data and protection data of the staff member according to the time sequence of the target video frame;

[0138] If the target to be identified in the target video frame is a construction machine, the operation data of the construction machine is determined according to the time sequence of the target video frame.

[0139] In an optional embodiment, the calculation module 33 is specifically configured to:

[0140] Determine the personnel operation score and personnel protection score corresponding to the personnel operation data and protection data respectively through the personnel operation rule table;

[0141] Determine the equipment operation score corresponding to the operation of the construction equipment according to the construction equipment operation rule table;

[0142] The worker's operation risk value is calculated based on the personnel operation score, the personnel protection score, the equipment operation score, and the power operation risk coefficient.

[0143] It should be noted that the above detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0144] Regarding the specific limitations of an active safety warning device for an uninterrupted power operation process based on artificial intelligence, please refer to the limitations of the active safety warning method for an uninterrupted power operation process based on artificial intelligence above, and will not be repeated here. Each module in the above-mentioned device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0145] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0146] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. An artificial intelligence-based active safety warning method for non-stop operation, characterized in that: The method comprises: Acquire environmental data, monitoring data, original line operation data, and temporary bypass operation data during the uninterrupted operation of the distribution network line; the monitoring data includes the uninterrupted operation process of the workers and construction equipment; determining a power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data; Determining an operation risk level based on the power operation risk coefficient; extracting video frames from the monitoring data, and determining target video frames based on the operation risk level and the video frames; Determining the operation data, protection data of the worker and the operation data of the construction equipment according to the target video frame; Calculating the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient; If the worker's operational risk value is greater than a preset value, a safety warning is issued; The determining of the power operation risk coefficient according to the environmental data, the original line operation data, and the temporary bypass operation data includes: Determining the power supply line by comparing the original line operation data and the temporary bypass operation data; If the power supply line is the original line, determining the power operation risk coefficient based on the original line operation data and the environmental data; If the power supply line is a temporary bypass, determining the power operation risk coefficient based on the temporary bypass operation data and the environmental data; The determining of the power operation risk coefficient according to the original line operation data and the environmental data includes: Obtaining voltage data, current data, and temperature data from the original line operation data; Determine the risk levels corresponding to the voltage data, the current data, the temperature data, and the environmental data respectively according to a preset mapping table; Performing weighted calculation on all risk levels to obtain the power operation risk coefficient; Converting the voltage data, current data, temperature data and the environmental data in the original line operation data into a eigenvector matrix; Inputting the characteristic vector matrix into the power operation risk prediction model to predict the power operation risk coefficient; The power operation risk coefficient obtained by weighted calculation is compared with the power operation risk coefficient predicted by the power operation risk prediction model, and the maximum value of the comparison results is taken as the final power operation risk coefficient.

2. The method according to claim 1, characterized in that The determining of the power operation risk coefficient according to the temporary bypass operation data and the environmental data includes: Acquiring voltage data, current data, and temperature data from the temporary bypass operation data; Converting the voltage data, current data, temperature data and the environmental data in the temporary bypass operation data into a eigenvector matrix; The characteristic vector matrix is ​​input into the power operation risk prediction model to predict the power operation risk coefficient.

3. The method according to any one of claims 1-2, characterized in that The determining of the target video frame based on the operation risk level and the video frame includes: Determine the operation risk level according to the interval range of the power operation risk coefficient; A target video frame is determined from the video frames using the identification keyword corresponding to the operation risk level.

4. The method according to claim 3, characterized in that The step of determining a target video frame from the video frames using the identification keyword corresponding to the operation risk level includes: Determine the target to be identified by using the identification keywords corresponding to the operation risk level; A video frame containing the target to be identified is determined from the video frames, and the video frame containing the target to be identified is determined as a target video frame.

5. The method according to claim 4, characterized in that The determining of the worker's operation data, protection data, and operation data of the construction equipment according to the target video frame includes: If the target to be identified in the target video frame is a person, determining the operation data and protection data of the staff member according to the time sequence of the target video frame; If the target to be identified in the target video frame is a construction machine, the operation data of the construction machine is determined according to the time sequence of the target video frame.

6. The method according to claim 5, characterized in that The calculating of the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient includes: Determine the personnel operation score and personnel protection score corresponding to the personnel operation data and protection data respectively through the personnel operation rule table; Determine the equipment operation score corresponding to the operation of the construction equipment according to the construction equipment operation rule table; The worker's operation risk value is calculated based on the personnel operation score, the personnel protection score, the equipment operation score, and the power operation risk coefficient.

7. An active safety warning device for non-stop operation based on artificial intelligence, characterized in that: The device comprises: An acquisition module is used to obtain environmental data, monitoring data, original line operation data, and temporary bypass operation data during the uninterrupted operation of the distribution network line; the monitoring data includes the uninterrupted operation process of the workers and construction equipment; a determination module, configured to determine a power operation risk coefficient based on the environmental data, the original line operation data, and the temporary bypass operation data; The determination module is further configured to determine an operation risk level based on the power operation risk coefficient; The determination module is further configured to extract video frames from the monitoring data and determine target video frames based on the operation risk level and the video frames; The determination module is further configured to determine the worker's operation data, protection data, and operation data of the construction equipment based on the target video frame; a calculation module, configured to calculate the worker's operation risk value based on the worker's operation data, protection data, operation data of the construction equipment, and the power operation risk coefficient; An early warning module is used to issue a safety warning if the worker's operation risk value is greater than a preset value; The determining of the power operation risk coefficient according to the environmental data, the original line operation data, and the temporary bypass operation data includes: Determining the power supply line by comparing the original line operation data and the temporary bypass operation data; If the power supply line is the original line, determining the power operation risk coefficient based on the original line operation data and the environmental data; If the power supply line is a temporary bypass, determining the power operation risk coefficient based on the temporary bypass operation data and the environmental data; The determining of the power operation risk coefficient according to the original line operation data and the environmental data includes: Obtaining voltage data, current data, and temperature data from the original line operation data; Determine the risk levels corresponding to the voltage data, the current data, the temperature data, and the environmental data respectively according to a preset mapping table; Performing weighted calculation on all risk levels to obtain the power operation risk coefficient; Converting the voltage data, current data, temperature data and the environmental data in the original line operation data into a eigenvector matrix; Inputting the characteristic vector matrix into the power operation risk prediction model to predict the power operation risk coefficient; The power operation risk coefficient obtained by weighted calculation is compared with the power operation risk coefficient predicted by the power operation risk prediction model, and the maximum value of the comparison results is taken as the final power operation risk coefficient.

Images