Method and system for identifying potential safety hazards of power distribution room of thermal power plant

Abstract

The invention belongs to the technical field of safety. The invention provides a thermal power plant distribution room potential safety hazard identification method and system. The method comprises the steps that a high-definition camera shoots high-definition video data of a power distribution room of a thermal power plant, and equipment operation data of an operator and equipment attribute data and state data of operated equipment are extracted; if it is determined that the equipment is in a completely normal state according to the equipment state data of the power distribution room of the thermal power plant, performing matching analysis on the equipment operation data, the equipment attribute data and the state data according to a preset rule to obtain a first potential safety hazard value; if the equipment is in an incomplete normal state, inputting the equipment operation data, the equipment attribute data and the state data into a potential safety hazard prediction model to obtain a predicted second potential safety hazard value; and deciding whether to output potential safety hazard alarm information according to the first potential safety hazard value or the second potential safety hazard value. Accurate identification of the potential safety hazard of the personnel operation behavior of the power distribution room of the thermal power plant is realized.

Description

Technical Field

[0001] The present invention relates to the field of safety technology, and in particular to a method and system for identifying safety hazards in a power distribution room of a thermal power plant. Background Art

[0002] The power distribution room of a thermal power plant is an important part of the power system. Its main functions and effects include: Power supply and distribution: The power distribution room introduces electric energy from the transmission line into the building or equipment, and distributes and controls it through the distribution device to meet the needs of different electrical equipment. It is equipped with transformers, switch cabinets, circuit breakers and other equipment, which can distribute electric energy to different circuits and electrical equipment.

[0003] Safety protection: The power distribution room plays an important role in safety protection in the process of power supply and distribution of electric energy. It is equipped with overload protection device and short circuit protection device, which can monitor and protect the current and voltage in the circuit. Once an overload or short circuit occurs, the power supply will be cut off in time to avoid equipment damage and personal safety accidents.

[0004] Troubleshooting: The power distribution room has the function of troubleshooting. It can monitor and detect the operating status of the equipment, find faults in time and take corresponding measures to eliminate them, ensuring the reliability and stability of power supply.

[0005] Maintenance and management: The equipment in the power distribution room needs regular inspection and maintenance to ensure its normal operation and safety and reliability. Maintenance work includes cleaning, inspection and lubrication of the equipment, as well as regular inspection and testing of the equipment.

[0006] Energy saving and environmental protection: The distribution room can optimize the power supply and distribution plan, rationally utilize electrical energy, reduce energy waste and consumption, improve energy utilization, and reduce energy consumption and environmental pollution.

[0007] The equipment composition in the distribution room is relatively complex, including incoming line cabinets, metering cabinets, PT cabinets, outgoing line cabinets, communication cabinets, isolation cabinets, etc. In order to improve power safety, it is necessary to monitor and identify safety hazards in the distribution room of thermal power plants, especially to monitor whether the operating behaviors of operators are compliant. The existing methods for identifying safety hazards in the distribution room of thermal power plants are all based on the set identification rules to conduct compliance analysis on the operating behaviors of operators. However, the operators' operations on the equipment in the distribution room may be routine operations, such as electrical operations on power lines, switches, sockets, etc.; they may also be maintenance operations, such as maintenance of circuit breakers. Routine operating behaviors and maintenance operating behaviors have certain similarities in many cases, which can easily cause the safety hazard identification system to make incorrect judgments, leading to unnecessary alarms. This technical problem needs to be solved urgently. Summary of the invention

[0008] In this regard, the present invention provides a method, system, electronic equipment, computer storage medium and computer program product for identifying safety hazards in a power distribution room of a thermal power plant to solve the above-mentioned technical problems.

[0009] The present invention discloses a method for identifying potential safety hazards in a power distribution room of a thermal power plant, the method comprising the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

[0010] In some embodiments, the extracting of the device operation data corresponding to the operator and the device attribute data and status data corresponding to the operated device from the high-definition video data includes: Identify operators and electrical equipment from the high-definition video data, and determine device attribute data of each of the electrical equipment by feature comparison; Tracking the hand movements of each operator to obtain hand movement characteristics, and obtaining the device operation data according to the hand movement characteristics analysis; The color tracking and the component position tracking are performed on the working components of each of the electrical devices, and the status data is determined based on the tracking results.

[0011] In some embodiments, the acquiring of equipment status data of a power distribution room of a thermal power plant and determining, according to the equipment status data, whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state includes: Acquire equipment status history data of a power distribution room of a thermal power plant, wherein the equipment status history data includes fault history data and maintenance history data, calculate a maintenance ratio based on the fault history data and the maintenance history data, and determine a threshold value of the number of equipment abnormalities based on the maintenance ratio; The equipment status data of the power distribution room of the thermal power plant is obtained, and the number of equipment abnormalities is determined based on the equipment status data. If the number of equipment abnormalities is lower than the equipment abnormality threshold, it is determined that the equipment in the power distribution room of the thermal power plant is in a completely normal state; otherwise, it is determined that the equipment in the power distribution room of the thermal power plant is in an incompletely normal state.

[0012] In some embodiments, matching and analyzing the device operation data with the device attribute data and the status data according to a preset rule to obtain a first safety hazard value includes: Perform matching calculation according to the device operation data, the device attribute data, the status data and the operation matching table; If the matching calculation is empty, the first safety hazard value is determined to be a first value; if the matching calculation is not empty, the first safety hazard value is set to a second value; wherein the first value is higher than the second value.

[0013] In some embodiments, inputting the device operation data, the device attribute data, and the status data into a safety hazard prediction model to obtain a predicted second safety hazard value includes: Determine a number of associated device status data according to the device attribute data, input the device operation data, the device attribute data, the status data and the associated device status data into a safety hazard prediction model, and obtain a third safety hazard value predicted by the safety hazard prediction model; Identify maintenance-type clothing on the high-definition video data, and if the maintenance-type clothing is identified, determine an adjustment coefficient according to the identification number of the maintenance-type clothing, and use the adjustment coefficient to correct the third safety hazard value to the second safety hazard value; wherein the adjustment coefficient is less than 1; If the maintenance-type clothing is not identified, the third safety hazard value is determined as the second safety hazard value.

[0014] In some embodiments, the safety hazard prediction model is constructed based on a multimodal knowledge graph and a deep learning algorithm.

[0015] The present invention also discloses a system for identifying safety hazards in a power distribution room of a thermal power plant. The system comprises a processing module and a storage module. The processing module executes a program code stored in the storage module to implement the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

[0016] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0017] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0018] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0019] The solution of the present invention analyzes whether there are abnormal conditions in all the equipment in the power distribution room of the thermal power plant, and analyzes whether there is a possibility of maintenance operation by the operator. If there is no possibility of maintenance operation, the conventional method is used to identify the safety hazard; if there is a possibility of maintenance operation, a safety hazard prediction model with stronger analysis ability is used to distinguish between conventional operation and maintenance operation, and then predict the corresponding safety hazard value. Therefore, the present invention not only ensures the accuracy of the safety hazard identification result by distinguishing between conventional operation and maintenance operation, but also effectively improves the efficiency of safety hazard identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of a method for identifying safety hazards in a power distribution room of a thermal power plant disclosed in an embodiment of the present invention; Figure 2 It is a schematic diagram of a process for extracting operator data and operated device data from high-definition video data disclosed in an embodiment of the present invention; Figure 3 It is a flow chart of analyzing whether the equipment in the power distribution room of a thermal power plant is in a completely normal state or an incompletely normal state according to an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a safety hazard identification system for a power distribution room in a thermal power plant disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0023] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0024] like Figure 1 As shown, an embodiment of the present invention discloses a method for identifying safety hazards in a power distribution room of a thermal power plant, the method comprising the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

[0025] In order to solve the problem that it is difficult to distinguish between routine operation behavior and maintenance operation behavior, which easily leads to misidentification of the operation behavior of operators in the power distribution room of the thermal power plant, and there are safety hazards, and then the wrong alarm information is issued, the present invention designs the above technical solution. In the above technical solution, at least one high-definition camera is configured in the power distribution room of the thermal power plant. The high-definition camera can shoot high-definition video data of the equipment and personnel in the power distribution room of the thermal power plant, and extract the equipment operation data of the operator on the equipment, as well as the equipment attribute data and status data of the operated equipment. At the same time, the equipment status data of the power distribution room of the thermal power plant is also obtained. The equipment status data can be directly obtained from the equipment monitoring system. The equipment monitoring system stores the working status of all equipment in the power distribution room of the thermal power plant, including abnormal status; according to these equipment status data, it can be determined that the power distribution room of the thermal power plant is in a completely normal state or an incompletely normal state of the equipment, wherein the completely normal state of the equipment refers to the working status of the equipment in the power distribution room of the thermal power plant "all" is normal, and when the working status of some equipment is abnormal, it corresponds to the incompletely normal state of the equipment. Therefore, when the equipment is in a completely normal state, the operator does not need to perform maintenance operations on the equipment. At this time, the equipment operation data can be matched and analyzed with the equipment attribute data and status data according to the preset rules to obtain the first safety hazard value; when the equipment is not in a completely normal state, the operator may need to perform maintenance operations on the equipment, and the equipment operation data, equipment attribute data, and status data are input into the pre-established safety hazard prediction model, and the model predicts whether the operator's operation behavior is a routine operation behavior or a maintenance operation behavior, and the corresponding prediction is used to obtain the second safety hazard value of the power distribution room of the thermal power plant. Finally, when the first safety hazard value or the second safety hazard value obtained above exceeds the specified threshold, the safety hazard alarm information can be output, for example, the alarm information can be output to the personnel in the power distribution room of the thermal power plant to remind them of the existence of safety hazards, and the alarm information can also be sent to the relevant management personnel at the same time.

[0026] The solution of the present invention analyzes whether there are abnormal conditions in all the equipment in the power distribution room of the thermal power plant, and analyzes whether there is a possibility of maintenance operation by the operator. If there is no possibility of maintenance operation, the conventional method is used to identify the safety hazard; if there is a possibility of maintenance operation, a safety hazard prediction model with stronger analysis ability is used to distinguish between conventional operation and maintenance operation, and then predict the corresponding safety hazard value. Therefore, the present invention not only ensures the accuracy of the safety hazard identification result by distinguishing between conventional operation and maintenance operation, but also effectively improves the efficiency of safety hazard identification.

[0027] In some embodiments, Figure 2As shown, the device operation data corresponding to the operator and the device attribute data and status data corresponding to the operated device are extracted from the high-definition video data, including: Identify operators and electrical equipment from the high-definition video data, and determine device attribute data of each of the electrical equipment by feature comparison; Tracking the hand movements of each operator to obtain hand movement characteristics, and obtaining the device operation data according to the hand movement characteristics analysis; The color tracking and the component position tracking are performed on the working components of each of the electrical devices, and the status data is determined based on the tracking results.

[0028] In the embodiment of the present invention, the safety hazard of the present invention is mainly aimed at improper operation of electrical equipment by operators, so the operators and electrical equipment are first identified in the high-definition video data. At the same time, since each electrical equipment has different appearance features, such as color, texture, structure, etc., the device attribute data of each electrical equipment, such as switch cabinets, circuit breakers, etc., can be determined by feature comparison.

[0029] Then, by performing subsequent continuous status tracking of the operators and electrical equipment, the above-mentioned equipment operation data and status data can be determined. Specifically, the hand movements of each operator are tracked to obtain hand movement characteristics. Different action sequences represent different operation types, such as plug-in and unplug operations, press operations, pull-down operations, and close operations, so the corresponding equipment operation data can be determined by analyzing the hand movement characteristics of the operator. In addition, color tracking and component position tracking are performed on each electrical equipment. The tracking results obtained will include, for example, the color change of the indicator light (green to red, green to yellow, etc.), the position of the operating lever (closed, pulled down, etc.), etc. Since different color changes and position changes of the operating lever represent different states, the state data of the electrical equipment at this time (disconnected, connected, etc.) can be determined accordingly.

[0030] In some embodiments, Figure 3 As shown, the step of obtaining the equipment status data of the power distribution room of the thermal power plant and determining whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data includes: Acquire equipment status history data of a power distribution room of a thermal power plant, wherein the equipment status history data includes fault history data and maintenance history data, calculate a maintenance ratio based on the fault history data and the maintenance history data, and determine a threshold value of the number of equipment abnormalities based on the maintenance ratio; The equipment status data of the power distribution room of the thermal power plant is obtained, and the number of equipment abnormalities is determined based on the equipment status data. If the number of equipment abnormalities is lower than the equipment abnormality threshold, it is determined that the equipment in the power distribution room of the thermal power plant is in a completely normal state; otherwise, it is determined that the equipment in the power distribution room of the thermal power plant is in an incompletely normal state.

[0031] In the embodiment of the present invention, since the abnormalities of some equipment in the power distribution room of the thermal power plant do not need to be handled by the operator, these equipment can eliminate the abnormal situation by self-adjustment, or the abnormal situation of some equipment is not really "abnormal", but is caused by the abnormal sensitivity set too high due to actual needs. Therefore, as long as there is an abnormality in one device, it is determined that the power distribution room of the thermal power plant is in an equipment not completely normal state, which is not reasonable enough. In this regard, the present invention further obtains the equipment status history data of the power distribution room of the thermal power plant, and the equipment status history data includes the fault history data and maintenance history data of all equipment. The fault history data refers to the abnormal signal reported to the equipment monitoring system when each device is abnormal, and the maintenance history data refers to the targeted maintenance behavior taken by the operator for the corresponding abnormal signal. The corresponding maintenance record can be manually reported by the operator, or it can be identified and recorded by the above-mentioned high-definition camera. According to the fault history data and maintenance history data, the maintenance ratio can be calculated, and the maintenance ratio = the number of maintenance records / the number of fault records. According to the maintenance ratio obtained above, the threshold value of the number of equipment abnormalities can be determined. On this basis, the current number of equipment abnormalities can be calculated according to the equipment status data obtained from the equipment monitoring system. When the number of equipment abnormalities is lower than the threshold value of the number of equipment abnormalities obtained above, it is determined that the equipment in the distribution room of the thermal power plant is in a completely normal state; otherwise, it is determined that the equipment in the distribution room of the thermal power plant is in an incompletely normal state.

[0032] Therefore, the present invention determines the appropriate equipment abnormality number threshold by analyzing the maintenance ratio of operators in the distribution room for equipment abnormalities, and makes a more reasonable judgment on the normal status of the equipment in the distribution room based on the equipment abnormality number threshold, which is conducive to reducing the number of times the safety hazard prediction model is used to conduct in-depth analysis of safety hazards, thereby improving the efficiency of safety hazard analysis.

[0033] It should be noted that the functional relationship between the equipment anomaly number threshold and the maintenance ratio should be negatively correlated, that is, the higher the maintenance ratio, the smaller the equipment anomaly number threshold is set, and the easier it is to identify the thermal power plant distribution room as having equipment in an incompletely normal state; the lower the maintenance ratio, the larger the equipment anomaly number threshold is set, and the easier it is to identify the thermal power plant distribution room as having equipment in a completely normal state.

[0034] In some embodiments, matching and analyzing the device operation data with the device attribute data and the status data according to a preset rule to obtain a first safety hazard value includes: Perform matching calculation according to the device operation data, the device attribute data, the status data and the operation matching table; If the matching calculation is empty, the first safety hazard value is determined to be a first value; if the matching calculation is not empty, the first safety hazard value is set to a second value; wherein the first value is higher than the second value.

[0035] In the embodiment of the present invention, an operation matching table is preset, which contains a plurality of sets of comparison relationships of compliant operations for device operation data and status data of each device, that is, each set of comparison relationships is used to indicate that a specific operation on a specific device is compliant. For example, when the status data of a device changes from green to red, it indicates that an abnormal alarm has occurred in the device, and at this time, the operator's pull-down disconnection operation of the operating handle is compliant.

[0036] The measured equipment operation data, equipment attribute data, and status data are matched and calculated with the operation matching table. If no matching result is obtained, it means that the operation behavior of the operator is not compliant. At this time, the first safety hazard value is determined to be a high value, that is, the first value. Correspondingly, when the matching result is not empty, it means that the operation behavior of the operator is a compliant operation recorded in the operation matching table. At this time, the first safety hazard value is set to a low value, the second value.

[0037] In addition, a specific device may have multiple corresponding compliance operations in the same state, for example, in case of an abnormality, you can take "press the emergency stop button", "turn off the power", "switch to backup equipment", etc., so there may be multiple matching calculation results. At this time, the appropriate second value can be determined according to the number of these matching results, for example, the second value = the third value * (1-n / N), where the third value is the preset safety hazard value, n is the number of matching results, and N is the total number of matching entries corresponding to the corresponding type of device in the operation matching table (that is, the number of compliance operations configured for the device in the operation matching table).

[0038] In some embodiments, inputting the device operation data, the device attribute data, and the status data into a safety hazard prediction model to obtain a predicted second safety hazard value includes: Determine a number of associated device status data according to the device attribute data, input the device operation data, the device attribute data, the status data and the associated device status data into a safety hazard prediction model, and obtain a third safety hazard value predicted by the safety hazard prediction model; Identify maintenance-type clothing on the high-definition video data, and if the maintenance-type clothing is identified, determine an adjustment coefficient according to the identification number of the maintenance-type clothing, and use the adjustment coefficient to correct the third safety hazard value to the second safety hazard value; wherein the adjustment coefficient is less than 1; If the maintenance-type clothing is not identified, the third safety hazard value is determined as the second safety hazard value.

[0039] In the embodiment of the present invention, the pre-built safety hazard prediction model of the present invention can perform in-depth analysis on the equipment operation data, equipment attribute data, and status data to obtain the predicted third safety hazard value. However, whether there are professional maintenance personnel in the power distribution room of the thermal power plant will also affect the judgment of whether the operator is performing routine operation behavior or maintenance operation behavior, thereby causing the third safety hazard value obtained by subsequent prediction to be inaccurate.

[0040] In response to the above technical problems, the present invention further identifies maintenance-type clothing from high-definition video data. Maintenance-type clothing is a preset clothing type for professional maintenance personnel in the power distribution room of the thermal power plant, including color, texture, specific characters, etc. If maintenance-type clothing is identified, it is determined that there are professional maintenance personnel in the power distribution room, and the probability of determining that the operating behavior of the operator is a maintenance operation can be increased. Therefore, an adjustment coefficient is determined based on the number of identifications of maintenance-type clothing (the two are negatively correlated), and the third safety hazard value obtained above is corrected to the second safety hazard value using the adjustment coefficient; wherein the adjustment coefficient is less than 1. If maintenance-type clothing is not identified, it is determined that there are no professional maintenance personnel in the power distribution room, and the third safety hazard value obtained above is directly determined as the second safety hazard value.

[0041] In addition, in addition to equipment operation data, equipment attribute data, and status data, the input data of the safety hazard prediction model also includes the status data of several associated devices associated with the target device that the operator is operating. The association here refers to electrical connectivity, that is, the device that is in electrical connectivity with the target device is the associated device. Using the status data of these associated devices as a reference will help the safety hazard prediction model to make a more accurate analysis of the operator's compliance with the device operation data of the target device. For example, when the yellow light of the target device is on, it is found that the working status of the associated devices of the target device is completely normal. At this time, the operator's behavior of "pressing the emergency stop button" on the target device may be unreasonable, and there are certain safety hazards.

[0042] It should be noted that the safety hazard prediction model can also first distinguish between routine operation behavior and maintenance operation behavior. If it is distinguished as maintenance operation behavior, the third safety hazard value is set to a low value. If it is distinguished as routine operation behavior, the third safety hazard value can be determined by comparing with the operation matching table as described above. The present invention does not make specific limitations on this.

[0043] In some embodiments, the safety hazard prediction model is constructed based on a multimodal knowledge graph and a deep learning algorithm.

[0044] In an embodiment of the present invention, in order to improve the ability to distinguish and identify routine operation behaviors and maintenance operation behaviors, the present invention constructs the above-mentioned safety hazard prediction model based on multimodal knowledge graph and deep learning algorithm. The model uses the improved Faster RCNN (Faster RCNN) to extract feature vectors from device operation data, device attribute data, status data, and associated device status data, and then uses cosine similarity to perform feature correspondence mapping, maps these feature vectors to entities, attributes, and relationship vectors in the knowledge graph, and generates recognition results of routine operation behaviors or maintenance operation behaviors through semantic matching reasoning, thereby generating corresponding safety hazard values.

[0045] like Figure 4 As shown, an embodiment of the present invention further discloses a system for identifying safety hazards in a power distribution room of a thermal power plant, the system comprising a processing module and a storage module, the processing module executes a program code stored in the storage module to implement the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

[0046] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0047] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0048] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0049] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for identifying safety hazards in a power distribution room of a thermal power plant, characterized in that , the method comprises the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

2. A method for identifying potential safety hazards in a power distribution room of a thermal power plant according to claim 1, characterized in that: Extracting device operation data corresponding to the operator and device attribute data and status data corresponding to the operated device from the high-definition video data includes: Identify operators and electrical equipment from the high-definition video data, and determine device attribute data of each of the electrical equipment by feature comparison; Tracking the hand movements of each operator to obtain hand movement characteristics, and obtaining the device operation data according to the hand movement characteristics analysis; The color tracking and the component position tracking are performed on the working components of each of the electrical devices, and the status data is determined based on the tracking results.

3. A method for identifying potential safety hazards in a power distribution room of a thermal power plant according to claim 2, characterized in that: Acquiring equipment status data of a power distribution room of a thermal power plant, and determining whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data, including: Acquire equipment status history data of a power distribution room of a thermal power plant, wherein the equipment status history data includes fault history data and maintenance history data, calculate a maintenance ratio based on the fault history data and the maintenance history data, and determine a threshold value of the number of equipment abnormalities based on the maintenance ratio; The equipment status data of the power distribution room of the thermal power plant is obtained, and the number of equipment abnormalities is determined based on the equipment status data. If the number of equipment abnormalities is lower than the equipment abnormality threshold, it is determined that the equipment in the power distribution room of the thermal power plant is in a completely normal state; otherwise, it is determined that the equipment in the power distribution room of the thermal power plant is in an incompletely normal state.

4. A method for identifying safety hazards in a power distribution room of a thermal power plant according to claim 3, characterized in that: Matching and analyzing the device operation data with the device attribute data and the status data according to a preset rule to obtain a first safety hazard value includes: Perform matching calculation according to the device operation data, the device attribute data, the status data and the operation matching table; If the matching calculation is empty, the first safety hazard value is determined to be a first value; if the matching calculation is not empty, the first safety hazard value is set to a second value; wherein the first value is higher than the second value.

5. A method for identifying safety hazards in a power distribution room of a thermal power plant according to claim 3, characterized in that: Inputting the device operation data, the device attribute data, and the status data into a safety hazard prediction model to obtain a predicted second safety hazard value, including: Determine a number of associated device status data according to the device attribute data, input the device operation data, the device attribute data, the status data and the associated device status data into a safety hazard prediction model, and obtain a third safety hazard value predicted by the safety hazard prediction model; Identify maintenance-type clothing on the high-definition video data, and if the maintenance-type clothing is identified, determine an adjustment coefficient according to the identification number of the maintenance-type clothing, and use the adjustment coefficient to correct the third safety hazard value to the second safety hazard value; wherein the adjustment coefficient is less than 1; If the maintenance-type clothing is not identified, the third safety hazard value is determined as the second safety hazard value.

6. A method for identifying safety hazards in a power distribution room of a thermal power plant according to claim 5, characterized in that: The safety hazard prediction model is constructed based on a multimodal knowledge graph and a deep learning algorithm.

7. A system for identifying safety hazards in a power distribution room of a thermal power plant, the system comprising a processing module and a storage module, characterized in that: The processing module executes the program code stored in the storage module to implement the following steps: Controlling a high-definition camera to capture high-definition video data of a power distribution room of a thermal power plant, and extracting equipment operation data corresponding to an operator, as well as equipment attribute data and status data corresponding to an operated equipment from the high-definition video data; Acquire equipment status data of a power distribution room of a thermal power plant, and determine whether the equipment in the power distribution room of the thermal power plant is in a completely normal state or in an incompletely normal state according to the equipment status data; If the equipment in the power distribution room of the thermal power plant is in a completely normal state, matching and analyzing the equipment operation data with the equipment attribute data and the status data is performed according to a preset rule to obtain a first safety hazard value; If the equipment in the power distribution room of the thermal power plant is not completely normal, the equipment operation data, the equipment attribute data, and the status data are input into a safety hazard prediction model to obtain a predicted second safety hazard value; A decision is made whether to output safety hazard alarm information according to the first safety hazard value or the second safety hazard value.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images