Application method and system of electrical equipment fire monitoring system in mountain photovoltaic power station

Abstract

The present invention relates to the field of remote monitoring, and discloses a method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station, including: defining nodes to be monitored of electrical equipment, configuring monitoring equipment of the nodes to be monitored using a fire monitoring and management system for electrical equipment corresponding to the mountain photovoltaic power station, configuring an edge lightweight visual analysis model at the nodes to be monitored, and configuring a high-precision visual analysis model at a data processing center in the fire monitoring and management system for electrical equipment; using the edge lightweight visual analysis model to analyze potential smoke pixel blocks and potential flame pixel blocks of electrical equipment, analyzing the fire coefficient of electrical equipment, using a high-precision visual analysis model to analyze the fire status of electrical equipment, using a fire module in the fire monitoring and management system for electrical equipment to construct a fire fighting strategy for electrical equipment, and executing the fire elimination of electrical equipment corresponding to the mountain photovoltaic power station through the fire fighting strategy. The present invention can improve the fire fighting efficiency of electrical equipment in a photovoltaic power station.

Description

Technical Field

[0001] The invention relates to an application method and system of an electrical equipment fire monitoring system in a mountain photovoltaic power station, belonging to the field of remote monitoring. Background Art

[0002] The application of electrical equipment fire monitoring system in mountain photovoltaic power stations refers to the process of using a series of high-tech monitoring and management technologies to conduct real-time monitoring of the operating status of electrical equipment in mountain photovoltaic power stations, promptly discover and deal with potential fire risks, and ensure the safe and stable operation of the power station, effectively improving the safety management level of the power station and reducing the risk of fire.

[0003] The application of electrical equipment fire monitoring systems in mountain photovoltaic power plants usually relies on fixed cameras and temperature sensors for monitoring, and transmits data to the central control system for analysis through a wired network. Once an abnormality is detected, an alarm is triggered. This method cannot perform fast edge real-time analysis of monitoring data to identify potential fire pixel blocks, making it impossible to detect fire hazards in a timely manner, resulting in poor fire protection efficiency of electrical equipment in mountain photovoltaic power plants. Summary of the invention

[0004] The present invention provides an application method and system of an electrical equipment fire monitoring system in a mountain photovoltaic power station, the main purpose of which is to improve the fire protection efficiency of electrical equipment in the mountain photovoltaic power station.

[0005] To achieve the above-mentioned purpose, the present invention provides an application method of an electrical equipment fire monitoring system in a mountain photovoltaic power station, comprising:

[0006] Obtaining a power station scene structure of a mountain photovoltaic power station, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, defining the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configuring the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera;

[0007] Analyze the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment, and calculate the necessary monitoring coefficient of the monitoring blind area. When the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, configure an edge lightweight visual analysis model at the node to be monitored, and configure a high-precision visual analysis model in the data processing center of the electrical equipment fire monitoring and management system;

[0008] Using the infrared thermal imager and the high-definition camera to collect infrared thermal imaging data and image data of the electrical equipment, extracting smoke visual features and flame visual features of the image data, analyzing potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculating the equipment hot spots of the electrical equipment based on the infrared thermal imaging data;

[0009] The fire coefficient of the electrical equipment is analyzed by using the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the equipment hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by using the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level.

[0010] According to the fire status, a fire fighting strategy for the electrical equipment is constructed using the fire fighting module in the electrical equipment fire monitoring and management system, and the fire fighting strategy is used to eliminate the fire in the electrical equipment corresponding to the mountain photovoltaic power station.

[0011] Optionally, defining the nodes to be monitored of the electrical equipment through the electrical equipment distribution includes:

[0012] identifying functional characteristics of the electrical equipment;

[0013] Analyzing the fire risk factor of the electrical equipment through the functional characteristics;

[0014] Dividing the monitoring area of ​​the electrical equipment according to the functional characteristics and the distribution of the electrical equipment;

[0015] Calculating a monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics;

[0016] The nodes to be monitored of the electrical equipment are defined by the monitoring priority coefficient and the electrical equipment distribution.

[0017] Optionally, the calculating the monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics includes:

[0018] Defining equipment characteristic indicators of the functional characteristics, wherein the equipment characteristic indicators include equipment criticality index, equipment failure rate index, equipment maintenance difficulty index and equipment environmental sensitivity index;

[0019] Determine the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, and equipment environmental sensitivity index weight of the equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, and equipment environmental sensitivity index;

[0020] According to the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, equipment environmental sensitivity index weight, equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, equipment environmental sensitivity index and fire risk coefficient, the monitoring priority coefficient of the monitoring area is calculated using the following formula:

[0021]

[0022] in, Indicates the monitoring priority coefficient of the monitoring area. Indicates the weight of the corresponding functional characteristics of the monitoring area in the monitoring priority. Indicates the equipment criticality index of the equipment in the monitoring area. Indicates the criticality index weight of the equipment in the monitoring area. Indicates the equipment failure rate index of the monitored area, Indicates the equipment failure rate index weight of the monitoring area, Indicates the equipment maintenance difficulty index of the monitoring area, Indicates the equipment maintenance difficulty index weight of the monitoring area, Indicates the device environment sensitivity index of the monitored area. Indicates the weight of the equipment environment sensitivity index in the monitoring area. Indicates the weight of the fire risk factor corresponding to the monitoring area in the monitoring priority. Represents the fire risk factor of the monitored area, represents the probability of fire occurrence in the monitored area, Indicates the fire consequence severity coefficient of the monitored area, Represents the fire risk calculation function.

[0023] Optionally, the analyzing the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring device includes:

[0024] Constructing a device layout diagram of the monitoring device;

[0025] Identifying effective adjustment parameters of the monitoring device, and calculating an effective monitoring range of the monitoring device based on the effective adjustment parameters;

[0026] Analyze the environmental characteristics of the mountain photovoltaic power station;

[0027] Defining a monitoring impact factor of the monitoring device according to the environmental characteristics;

[0028] Marking a monitoring effective area map of the monitoring equipment on the equipment layout map according to the effective monitoring range, the environmental characteristics and the monitoring influencing factors;

[0029] Based on the monitoring effective area map, a monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment is determined.

[0030] Optionally, the calculating the necessary monitoring coefficient of the monitoring blind area includes:

[0031] Identify the blind area functional characteristics, blind area structural characteristics and monitoring targets of the monitoring blind area;

[0032] Analyzing the blind spot risk level of the monitoring blind spot through the blind spot functional characteristics and the monitoring target, and defining the blind spot risk impact coefficient of the blind spot risk level;

[0033] Determining a blind spot monitoring complexity coefficient and a blind spot monitoring size of the monitoring blind spot based on the blind spot structural characteristics;

[0034] A blind spot risk level score, a blind spot risk impact coefficient score, a blind spot monitoring complexity coefficient score, and a blind spot monitoring size score that define the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, and the blind spot monitoring size;

[0035] The necessary monitoring coefficient of the monitoring blind spot is calculated using the following formula through the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, the blind spot monitoring size, the blind spot risk level score, the blind spot risk impact coefficient score, the blind spot monitoring complexity coefficient score and the blind spot monitoring size score:

[0036]

[0037] in, Indicates the necessary monitoring coefficient of the monitoring blind area, Indicates the blind spot risk level of the monitoring blind spot. Indicates the blind spot risk level score of the monitoring blind spot. Indicates the blind spot risk impact coefficient of the monitoring blind spot, Indicates the blind spot risk impact coefficient score of the monitoring blind spot, The blind spot monitoring complexity coefficient represents the blind spot monitoring area. Indicates the blind spot monitoring complexity coefficient score of the monitoring blind spot, Indicates the size of the blind area monitoring. Indicates the blind spot monitoring size score of the monitoring blind spot.

[0038] Optionally, configuring an edge lightweight visual analysis model at the node to be monitored includes:

[0039] Defining lightweight visual analysis requirements of the nodes to be monitored;

[0040] According to the lightweight visual analysis requirements, a lightweight network architecture of the nodes to be monitored is constructed;

[0041] Collecting historical monitoring data of the node to be monitored, and performing data enhancement on the historical monitoring data to obtain enhanced historical monitoring data;

[0042] Using the enhanced historical monitoring data to train the lightweight network architecture, to obtain a trained lightweight network model;

[0043] Performing model compression on the trained lightweight network model to obtain a compressed lightweight network model, wherein the model compression includes model weight pruning and model quantization;

[0044] Calculating a lightweight model performance of the compressed lightweight network model;

[0045] When the performance of the lightweight model meets a preset model performance threshold, the compressed lightweight network model is configured on the node to be monitored to obtain the edge lightweight visual analysis model.

[0046] Optionally, extracting smoke visual features and flame visual features from the image data includes:

[0047] Performing image preprocessing on the image data to obtain a processed electrical equipment image;

[0048] Calculating a color histogram of the processed electrical device image;

[0049] Defining a color moment of the processed electrical device image according to the color histogram, and extracting smoke color features and flame color features of the processed electrical device image through the color moment;

[0050] Constructing a gray level co-occurrence matrix of the processed electrical equipment image;

[0051] capturing smoke texture features of the processed electrical equipment image according to the gray level co-occurrence matrix;

[0052] Extracting the smoke contour and the flame contour of the processed electrical device image, and determining the smoke shape feature and the flame shape feature of the processed electrical device image through the smoke contour;

[0053] marking the smoke motion pattern of the processed electrical device image;

[0054] Determining the smoke movement characteristics of the processed electrical equipment image through the smoke movement pattern;

[0055] Analyzing the flame frequency components of the processed electrical equipment image, and defining the flame frequency characteristics of the processed electrical equipment image according to the flame frequency components;

[0056] Determining smoke visual features of the processed electrical device image based on the smoke color features, the smoke texture features, the smoke shape features, and the smoke operation features;

[0057] The flame visual feature of the processed electrical device image is determined according to the flame color feature, the flame shape feature and the flame frequency feature.

[0058] Optionally, marking the smoke motion pattern of the processed electrical device image includes:

[0059] Selecting the continuous frame images of the processed electrical equipment image;

[0060] Constructing an optical flow field of the continuous frame images;

[0061] Calculating the smoke movement direction and smoke movement amplitude of the processed electrical equipment image through the optical flow field;

[0062] The smoke movement direction standard deviation and the smoke movement amplitude standard deviation of the smoke movement direction and the smoke movement amplitude are calculated using the following formula:

[0063]

[0064] in, represents the standard deviation of the smoke movement direction, represents the standard deviation of smoke motion amplitude, Indicates the number of processed electrical equipment images, Indicates The direction of smoke movement in electrical equipment images is processed. Indicates the average value of smoke movement direction for processing electrical equipment images, Indicates The smoke motion amplitude of the electrical equipment image is processed. represents the average value of the smoke motion amplitude of the first processed electrical equipment image;

[0065] The smoke movement pattern of the processed electrical device image is analyzed according to the smoke movement direction, the smoke movement amplitude, the smoke movement direction standard deviation and the smoke movement amplitude standard deviation.

[0066] Optionally, analyzing the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot includes:

[0067] Analyzing the smoke area and smoke density of the electrical equipment through the potential smoke pixel block;

[0068] Calculating the smoke coefficient of the electrical equipment based on the smoke area and the smoke density;

[0069] Analyzing the flame area, flame temperature and flame dynamic parameters of the electrical equipment according to the potential flame pixel block and the equipment hotspot;

[0070] Calculating a flame coefficient of the electrical device based on the flame area, flame temperature and flame dynamic parameters;

[0071] Analyzing the hotspot temperature, hotspot coordinates and hotspot distribution of the device hotspot, and calculating the hotspot coefficient of the electrical device based on the hotspot temperature, hotspot coordinates and hotspot distribution;

[0072] The fire coefficient of the electrical equipment is calculated by using the smoke coefficient, the flame coefficient and the hot spot coefficient.

[0073] In order to solve the above problems, the present invention also provides an application system of an electrical equipment fire monitoring system in a mountain photovoltaic power station, the system comprising:

[0074] A monitoring equipment configuration module is used to obtain a power station scene structure of a mountain photovoltaic power station, determine the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, define the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configure the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera;

[0075] A visual analysis model configuration module is used to analyze the monitoring blind area of ​​the monitoring equipment on the mountain photovoltaic power station and calculate the necessary monitoring coefficient of the monitoring blind area. When the necessary monitoring coefficient is lower than a preset necessary monitoring threshold, an edge lightweight visual analysis model is configured at the node to be monitored, and a high-precision visual analysis model is configured in the data processing center of the electrical equipment fire monitoring and management system;

[0076] A potential fire analysis module, used to collect infrared thermal imaging data and image data of the electrical equipment using the infrared thermal imager and the high-definition camera, extract smoke visual features and flame visual features of the image data, analyze potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features and use the edge lightweight visual analysis model, and calculate the equipment hot spots of the electrical equipment based on the infrared thermal imaging data;

[0077] A fire status analysis module, used to analyze the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot, and when the fire coefficient meets the preset fire threshold, send the smoke pixel block, the potential flame pixel block and the equipment hotspot to the data processing center in the electrical equipment fire monitoring and management system, and use the high-precision visual analysis model to analyze the fire status of the electrical equipment, wherein the fire status includes the fire location, fire type and fire level;

[0078] A fire fighting strategy construction module is used to construct a fire fighting strategy for the electrical equipment based on the fire status and the fire fighting module in the electrical equipment fire monitoring and management system, and to eliminate the fire of the electrical equipment corresponding to the mountain photovoltaic power station through the fire fighting strategy.

[0079] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0080] at least one processor; and,

[0081] a memory communicatively connected to the at least one processor; wherein,

[0082] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the above-mentioned application method of the electrical equipment fire monitoring system in a mountain photovoltaic power station.

[0083] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method of applying the electrical equipment fire monitoring system in a mountain photovoltaic power station.

[0084] Compared with the problems described in the background technology, the present invention obtains the power station scene structure of the mountain photovoltaic power station. According to the power station scene structure, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station is the basis for designing a fire monitoring system. It helps to reasonably plan the location and type of monitoring points to ensure that the monitoring system can effectively cover all key areas and timely discover and deal with potential fire risks. Furthermore, the present invention defines the nodes to be monitored in the mountain photovoltaic power station through the electrical equipment distribution to ensure that the electrical equipment fire monitoring system of the mountain photovoltaic power station effectively covers all key areas and timely discovers and deals with potential fire risks. Furthermore, the present invention utilizes the fire monitoring management system configuration of the electrical equipment corresponding to the mountain photovoltaic power station The monitoring equipment of the node to be monitored, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera, which can collect fire data from two monitoring devices, thereby improving the reliability of the subsequent fire analysis of electrical equipment. Next, the present invention analyzes the monitoring equipment and optimizes the blind spots of the mountain photovoltaic power station, thereby improving the reliability and effectiveness of the entire fire monitoring system. In detail, when the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, the edge lightweight visual analysis model is configured at the node to be monitored to realize timely processing of node collected data, thereby improving data processing efficiency, thereby increasing the speed of fire processing. Furthermore, the present invention is in the electrical equipment fire monitoring and management system The data processing center is equipped with a high-precision visual analysis model to further determine the possible fire analysis results. The layered fire analysis not only improves the reliability of the fire analysis, but also improves the operation effect of the entire system. Furthermore, the present invention is based on the smoke visual features and flame visual features, and uses the edge lightweight visual analysis model to analyze the potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment. It relies on efficient algorithms and models to ensure real-time monitoring and rapid response, thereby improving the efficiency of fire analysis of electrical equipment. The present invention calculates the equipment hotspots of the electrical equipment based on the infrared thermal imaging data and effectively uses the infrared thermal imaging data to monitor the operating status of the electrical equipment, discover abnormal hotspots in time, and prevent equipment Overheating and potential fire risks. Optionally, the present invention analyzes the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot, and can perform fire analysis through multi-dimensional fire data to improve the accuracy of fire analysis. Furthermore, when the fire coefficient meets the preset fire threshold, the present invention sends the smoke pixel block, the potential flame pixel block and the equipment hotspot to the data processing center in the electrical equipment fire monitoring and management system, and uses the high-precision visual analysis model to analyze the fire status of the electrical equipment, wherein the fire status includes the fire location, fire type and fire level, and the fire information can be further determined through the high-precision visual analysis model.This provides a basis for later firefighting measures. Finally, the present invention uses the fire status and the firefighting module in the electrical equipment fire monitoring and management system to construct the firefighting strategy for the electrical equipment, which can effectively deal with fire incidents of electrical equipment and minimize losses and impacts. Therefore, the present invention can improve the firefighting efficiency of electrical equipment in photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 A flow chart of a method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station provided by an embodiment of the present invention;

[0086] Figure 2 A functional module diagram of an application system of an electrical equipment fire monitoring system in a mountain photovoltaic power station provided by an embodiment of the present invention;

[0087] Figure 3 A schematic diagram of the structure of electronic equipment of an application system of an electrical equipment fire monitoring system in a mountain photovoltaic power station provided by an embodiment of the present invention;

[0088] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0089] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0090] The embodiment of the present application provides a method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station. The execution subject of the method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0091] Embodiment 1:

[0092] Reference Figure 1 FIG. 1 is a flow chart of a method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station according to an embodiment of the present invention. In this embodiment, the method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station includes:

[0093] S1. Obtain a power station scene structure of a mountain photovoltaic power station, determine the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, define the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and use the fire protection monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station to configure the monitoring equipment of the nodes to be monitored, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera.

[0094] The present invention obtains the power station scene structure of the mountain photovoltaic power station. According to the power station scene structure, determining the electrical equipment distribution of the corresponding electrical equipment of the mountain photovoltaic power station is the basis for designing a fire monitoring system. It helps to rationally plan the location and type of monitoring points, ensure that the monitoring system can effectively cover all key areas, and promptly discover and deal with potential fire risks.

[0095] It should be explained that the power station scene structure refers to the overall layout and terrain features of the mountain photovoltaic power station, including the geographical location of the power station, terrain undulations, building facility layout, arrangement of photovoltaic panel arrays, road network, vegetation coverage and other structures; the electrical equipment distribution refers to the types, locations, connection relationships and functional areas of all electrical equipment in the power station.

[0096] The present invention defines the nodes to be monitored of the mountain photovoltaic power station through the distribution of the electrical equipment, which can ensure that the electrical equipment fire monitoring system of the mountain photovoltaic power station effectively covers all key areas and timely discovers and handles potential fire risks.

[0097] In detail, defining the nodes to be monitored of the electrical equipment through the distribution of the electrical equipment includes:

[0098] identifying functional characteristics of the electrical equipment;

[0099] Analyzing the fire risk factor of the electrical equipment through the functional characteristics;

[0100] Dividing the monitoring area of ​​the electrical equipment according to the functional characteristics and the distribution of the electrical equipment;

[0101] Calculating a monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics;

[0102] The nodes to be monitored of the electrical equipment are defined by the monitoring priority coefficient and the electrical equipment distribution.

[0103] Among them, the functional characteristics refer to the operating characteristics, uses, performance parameters, operating environment requirements, maintenance requirements and other attributes of electrical equipment. For example, the functional characteristics may be whether the equipment is a high-power device, whether it operates in a high temperature or flammable environment, whether it is a critical path device, etc. The fire risk factor refers to the ability to assess the possibility of fire in electrical equipment and the severity of its potential impact. The monitoring area refers to a specific monitoring area divided according to the distribution, functional characteristics and fire risk factor of electrical equipment. Each monitoring area contains a group of related electrical equipment. The monitoring priority factor refers to an indicator used to determine the monitoring priority of the monitoring area. The node to be monitored refers to the specific location or equipment in the monitoring area where monitoring equipment (such as infrared thermal imagers, high-definition cameras, etc.) needs to be installed, which is determined according to the functional characteristics, fire risk factor and monitoring priority factor of the electrical equipment.

[0104] Furthermore, the calculating of the monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics includes:

[0105] Defining equipment characteristic indicators of the functional characteristics, wherein the equipment characteristic indicators include equipment criticality index, equipment failure rate index, equipment maintenance difficulty index and equipment environmental sensitivity index;

[0106] Determine the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, and equipment environmental sensitivity index weight of the equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, and equipment environmental sensitivity index;

[0107] According to the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, equipment environmental sensitivity index weight, equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, equipment environmental sensitivity index and fire risk coefficient, the monitoring priority coefficient of the monitoring area is calculated using the following formula:

[0108]

[0109] in, Indicates the monitoring priority coefficient of the monitoring area. Indicates the weight of the corresponding functional characteristics of the monitoring area in the monitoring priority. Indicates the equipment criticality index of the equipment in the monitoring area. Indicates the criticality index weight of the equipment in the monitoring area. Indicates the equipment failure rate index of the monitored area, Indicates the equipment failure rate index weight of the monitoring area, Indicates the equipment maintenance difficulty index of the monitoring area, Indicates the equipment maintenance difficulty index weight of the monitoring area, Indicates the device environment sensitivity index of the monitored area. Indicates the weight of the equipment environment sensitivity index in the monitoring area. Indicates the weight of the fire risk factor corresponding to the monitoring area in the monitoring priority. Represents the fire risk factor of the monitored area, represents the probability of fire occurrence in the monitored area, Indicates the fire consequence severity coefficient of the monitored area, Represents the fire risk calculation function.

[0110] Among them, the equipment criticality index refers to an indicator that measures the importance or criticality of equipment in system operation, the equipment failure rate index refers to an indicator that measures the probability of equipment failure within a certain period of time, the equipment maintenance difficulty index refers to an indicator that measures the difficulty of equipment maintenance and repair, the equipment environmental sensitivity index refers to an indicator that measures the sensitivity of equipment to changes in the surrounding environment (such as temperature, humidity, pollution, etc.), the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight and equipment environmental sensitivity index weight refer to the weights of the equipment criticality index, equipment failure rate index, equipment maintenance difficulty index and equipment environmental sensitivity index in calculating the monitoring priority, the fire occurrence probability refers to the possibility of a fire occurring in a monitored area within a certain period of time, the fire consequence severity coefficient refers to an indicator that measures the losses or impacts that may be caused after a fire occurs, and the fire risk calculation function refers to the multiplication operation used to calculate the fire risk coefficient.

[0111] The present invention utilizes the mountain photovoltaic power station corresponding to the electrical equipment fire monitoring and management system to configure the monitoring equipment of the node to be monitored, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera, which can collect fire data from two monitoring devices, thereby improving the reliability of the subsequent electrical equipment fire analysis. The infrared thermal imager refers to an instrument that obtains a thermal image of the surface temperature distribution of an object by detecting the infrared radiation emitted by the object, and the high-definition camera refers to a video monitoring device that can capture high-resolution images and videos.

[0112] S2. Analyze the monitoring blind spots of the mountain photovoltaic power station by the monitoring equipment, and calculate the necessary monitoring coefficient of the monitoring blind spots. When the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, configure an edge lightweight visual analysis model at the node to be monitored, and configure a high-precision visual analysis model in the data processing center of the electrical equipment fire monitoring and management system.

[0113] The present invention analyzes the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment and optimizes the blind area in a targeted manner, thereby improving the reliability and effectiveness of the entire fire monitoring system.

[0114] In detail, the analyzing the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring device includes:

[0115] Constructing a device layout diagram of the monitoring device;

[0116] Identifying effective adjustment parameters of the monitoring device, and calculating an effective monitoring range of the monitoring device based on the effective adjustment parameters;

[0117] Analyze the environmental characteristics of the mountain photovoltaic power station;

[0118] Defining a monitoring impact factor of the monitoring device according to the environmental characteristics;

[0119] Marking a monitoring effective area map of the monitoring equipment on the equipment layout map according to the effective monitoring range, the environmental characteristics and the monitoring influencing factors;

[0120] Based on the monitoring effective area map, a monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment is determined.

[0121] Among them, the equipment layout diagram refers to a display diagram showing the specific location, direction and configuration of the monitoring equipment in the mountain photovoltaic power station, the effective adjustment parameters refer to the parameters that can be adjusted on the monitoring equipment, and these parameters directly affect the monitoring capabilities of the equipment. Including but not limited to focal length, field of view angle, rotation range, magnification, resolution, etc., the effective monitoring range refers to the area that the equipment can actually cover and effectively monitor after considering the effective adjustment parameters and environmental factors of the equipment, the environmental characteristics refer to the surrounding environment that affects the monitoring equipment, the monitoring influencing factors refer to the surrounding environmental factors that affect the performance of the monitoring equipment, including factors such as terrain undulations, building layout, vegetation coverage, climate conditions (such as rain, fog, light changes), temperature changes, etc., the monitoring effective area map refers to the area map drawn on the equipment layout map according to the effective monitoring range and environmental characteristics of each monitoring equipment, and the monitoring blind area refers to the area not covered by any monitoring equipment on the monitoring effective area map.

[0122] Optionally, the effective monitoring range of the monitoring device is calculated by using the effective adjustment parameters. The effective adjustment parameters may be used to determine the field of view of the monitoring device and to perform calculations in combination with trigonometric functions.

[0123] Optionally, the monitoring effective area map of the monitoring equipment marked on the equipment layout diagram can be drawn by 3DMAX software based on the effective monitoring range, the environmental characteristics and the monitoring influencing factors.

[0124] The present invention calculates the necessary monitoring coefficient of the monitoring blind area to improve the monitoring coverage of the electrical equipment of the mountain photovoltaic power station, thereby improving the reliability of the monitoring data.

[0125] In detail, the calculation of the necessary monitoring coefficient of the monitoring blind area includes:

[0126] Identify the blind area functional characteristics, blind area structural characteristics and monitoring targets of the monitoring blind area;

[0127] Analyzing the blind spot risk level of the monitoring blind spot through the blind spot functional characteristics and the monitoring target, and defining the blind spot risk impact coefficient of the blind spot risk level;

[0128] Determining a blind spot monitoring complexity coefficient and a blind spot monitoring size of the monitoring blind spot based on the blind spot structural characteristics;

[0129] A blind spot risk level score, a blind spot risk impact coefficient score, a blind spot monitoring complexity coefficient score, and a blind spot monitoring size score that define the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, and the blind spot monitoring size;

[0130] The necessary monitoring coefficient of the monitoring blind spot is calculated using the following formula through the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, the blind spot monitoring size, the blind spot risk level score, the blind spot risk impact coefficient score, the blind spot monitoring complexity coefficient score and the blind spot monitoring size score:

[0131]

[0132] in, Indicates the necessary monitoring coefficient of the monitoring blind area, Indicates the blind spot risk level of the monitoring blind spot. Indicates the blind spot risk level score of the monitoring blind spot. Indicates the blind spot risk impact coefficient of the monitoring blind spot, Indicates the blind spot risk impact coefficient score of the monitoring blind spot, The blind spot monitoring complexity coefficient represents the blind spot monitoring area. Indicates the blind spot monitoring complexity coefficient score of the monitoring blind spot, Indicates the size of the blind area monitoring. Indicates the blind spot monitoring size score of the monitoring blind spot.

[0133] Among them, the blind spot functional characteristics refer to the description of the purpose and function of the monitoring blind spot, such as whether it is a densely populated area, a transportation hub, a place where property is concentrated, etc. The blind spot structural characteristics refer to the description of the physical structure of the monitoring blind spot, including the terrain, building layout, obstacles and other characteristics. The monitoring target refers to the specific object or target that needs to be monitored in the monitoring blind spot, such as personnel, vehicles, important facilities and other targets. The blind spot risk level refers to the level divided according to the risks that the blind spot may face (such as crime, accidents, disasters, etc.). The blind spot risk impact coefficient refers to the degree of influence of the quantified blind spot risk level on the overall monitoring effect. The blind spot monitoring complexity coefficient refers to the description of the complexity of the monitoring blind spot, including the complexity of the monitoring environment and the difficulty of installing the monitoring equipment. The blind spot monitoring size refers to the area or volume size of the monitoring blind spot. The blind spot risk level score refers to the quantitative score of the blind spot risk level. The blind spot risk impact coefficient score refers to the quantitative score of the blind spot risk impact coefficient. The blind spot monitoring complexity coefficient score refers to the quantitative score of the blind spot monitoring complexity coefficient. The blind spot monitoring size score refers to the quantitative score of the blind spot monitoring size. The monitoring necessity coefficient refers to an indicator used to indicate the urgency and importance of monitoring the blind spot.

[0134] Optionally, analyzing the blind spot risk level of the monitoring blind spot through the blind spot functional characteristics and the monitoring target is performed by evaluating the monitoring blind spot risk type through the blind spot functional characteristics and the monitoring target.

[0135] In the present invention, when the necessary monitoring coefficient is lower than a preset necessary monitoring threshold, configuring an edge lightweight visual analysis model at the node to be monitored can realize timely processing of node collected data, improve data processing efficiency, and thus increase the sorting speed of fire handling.

[0136] In detail, configuring the edge lightweight visual analysis model at the node to be monitored includes:

[0137] Defining lightweight visual analysis requirements of the nodes to be monitored;

[0138] According to the lightweight visual analysis requirements, a lightweight network architecture of the nodes to be monitored is constructed;

[0139] Collecting historical monitoring data of the node to be monitored, and performing data enhancement on the historical monitoring data to obtain enhanced historical monitoring data;

[0140] Using the enhanced historical monitoring data to train the lightweight network architecture, to obtain a trained lightweight network model;

[0141] Performing model compression on the trained lightweight network model to obtain a compressed lightweight network model, wherein the model compression includes model weight pruning and model quantization;

[0142] Calculating a lightweight model performance of the compressed lightweight network model;

[0143] When the performance of the lightweight model meets a preset model performance threshold, the compressed lightweight network model is configured on the node to be monitored to obtain the edge lightweight visual analysis model.

[0144] Among them, the lightweight visual analysis requirement refers to a detailed description of the specific visual analysis tasks that need to be performed on the monitored node, including detection objects (such as smoke, flames, personnel, etc.), environmental conditions, and performance indicators (such as accuracy, response time, resource consumption, etc.); the lightweight network architecture refers to a neural network structure designed to run on resource-constrained devices; the historical monitoring data refers to image or video data collected from the monitored node in the past period of time; the enhanced historical monitoring data refers to historical monitoring data processed by data enhancement technology to improve the generalization ability and robustness of the model; the training of lightweight network model refers to training the lightweight network architecture using historical monitoring data to learn the model after the task of detecting specific objects or events; the compressed lightweight network model refers to the compressed lightweight network architecture processed by model compression technology The technology reduces the size and computational complexity of lightweight network models so that they can run more efficiently on edge devices. The model weight pruning refers to removing connections with smaller weights in the neural network to reduce the number of parameters and the amount of computation of the model. The model quantization refers to converting the weights and activations of the model from floating point numbers to low-precision integers to reduce the size of the model and accelerate the inference process. The lightweight model performance refers to the performance of the lightweight network model on specific tasks. The compressed lightweight network model refers to a model that reduces the size of the neural network model, reduces its computational complexity, and reduces its memory and storage requirements through a series of technical means. The model performance threshold is the minimum performance standard set to ensure the effectiveness of the model in practical applications. The edge lightweight visual analysis model refers to a lightweight visual analysis model running on an edge device.

[0145] Optionally, the performing data enhancement on the historical monitoring data to obtain enhanced historical monitoring data includes performing operations such as image horizontal flipping, image vertical flipping, rotation, and scaling on the historical monitoring data.

[0146] Optionally, the present invention configures a high-precision visual analysis model in the data processing center of the electrical equipment fire monitoring and management system to further determine the possible fire analysis results. The layered fire analysis not only improves the reliability of the fire analysis, but also improves the operation effect of the entire system. Among them, the high-precision visual analysis model refers to an advanced machine learning or deep learning model, which can accurately identify and classify specific objects, events or abnormal situations in images or videos in complex monitoring scenes. In detail, the high-precision visual analysis model needs to centrally analyze the analysis results of the lightweight visual analysis model of possible fires. The high-precision visual analysis model is obtained by training the ResNet neural network structure.

[0147] S3. Collect infrared thermal imaging data and image data of the electrical equipment using the infrared thermal imager and high-definition camera, extract smoke visual features and flame visual features of the image data, analyze potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculate the equipment hotspot of the electrical equipment based on the infrared thermal imaging data.

[0148] It should be explained that the infrared thermal imaging data refers to the thermal radiation images of electrical equipment captured by infrared thermal imagers. These data show the distribution of the surface temperature of the equipment and are usually presented in the form of a thermal spectrum, where each pixel represents a temperature value. The image data refers to the visible light photos or videos of electrical equipment collected by high-definition cameras. These data provide details of the appearance of the equipment, including color, shape, texture and layout.

[0149] The smoke visual features and flame visual features extracted from the image data of the present invention can be used as a basis for fire identification.

[0150] In detail, the extracting of smoke visual features and flame visual features of the image data includes:

[0151] Performing image preprocessing on the image data to obtain a processed electrical equipment image;

[0152] Calculating a color histogram of the processed electrical device image;

[0153] Defining a color moment of the processed electrical device image according to the color histogram, and extracting smoke color features and flame color features of the processed electrical device image through the color moment;

[0154] Constructing a gray level co-occurrence matrix of the processed electrical equipment image;

[0155] capturing smoke texture features of the processed electrical equipment image according to the gray level co-occurrence matrix;

[0156] Extracting the smoke contour and the flame contour of the processed electrical device image, and determining the smoke shape feature and the flame shape feature of the processed electrical device image through the smoke contour;

[0157] marking the smoke motion pattern of the processed electrical device image;

[0158] Determining the smoke movement characteristics of the processed electrical equipment image through the smoke movement pattern;

[0159] Analyzing the flame frequency components of the processed electrical equipment image, and defining the flame frequency characteristics of the processed electrical equipment image according to the flame frequency components;

[0160] Determining smoke visual features of the processed electrical device image based on the smoke color features, the smoke texture features, the smoke shape features, and the smoke operation features;

[0161] The flame visual feature of the processed electrical device image is determined according to the flame color feature, the flame shape feature and the flame frequency feature.

[0162] Among them, the processed electrical equipment image refers to an electrical equipment image that has undergone a series of image preprocessing operations, and these preprocessing operations include denoising, enhancement, segmentation and other operations; the color histogram refers to a statistical chart showing the number of pixels of each color (or grayscale level) in the image; the color moment includes parameters such as the mean, standard deviation and skewness of the color; the smoke color feature refers to a feature related to the smoke color extracted from the processed electrical equipment image; the flame color feature refers to a feature related to the flame color extracted from the processed electrical equipment image; the grayscale co-occurrence matrix refers to a matrix that describes the image texture; the smoke texture feature refers to information describing the smoke texture characteristics extracted from the grayscale co-occurrence matrix, such as contrast, energy, entropy and correlation; the smoke contour refers to a contour line formed by the smoke edge extracted from the image by an edge detection algorithm; the flame contour refers to a contour line formed by the flame edge extracted from the image by an edge detection algorithm; the smoke shape feature refers to a feature extracted from the smoke The features extracted from the fog contour, such as area, perimeter, circularity, compactness, etc., are used to describe the shape characteristics of the smoke. The flame shape features refer to the features extracted from the flame contour, which are used to describe the shape characteristics of the flame, such as sharp angles, ripples, etc. The smoke motion pattern refers to the smoke motion characteristics described by analyzing the changes in smoke position in consecutive frames. The smoke operation features refer to the features extracted from the smoke motion pattern, such as movement speed, direction and dynamic changes. The flame frequency component refers to the frequency feature in the flame image extracted by Fourier transform or other frequency domain analysis methods. The flame frequency feature refers to the feature defined from the flame frequency component, which is used to describe the frequency domain characteristics of the flame. The smoke visual feature refers to the comprehensive feature combining the smoke color feature, the smoke texture feature, the smoke shape feature and the smoke operation feature, which is used to characterize the visual attributes of the smoke. The flame visual feature refers to the comprehensive feature combining the flame color feature, the flame shape feature and the flame frequency feature, which is used to characterize the visual attributes of the flame.

[0163] Further, the marking of the smoke motion pattern of the processed electrical device image includes:

[0164] Selecting the continuous frame images of the processed electrical equipment image;

[0165] Constructing an optical flow field of the continuous frame images;

[0166] Calculating the smoke movement direction and smoke movement amplitude of the processed electrical equipment image through the optical flow field;

[0167] The smoke movement direction standard deviation and the smoke movement amplitude standard deviation of the smoke movement direction and the smoke movement amplitude are calculated using the following formula:

[0168]

[0169] in, represents the standard deviation of the smoke movement direction, represents the standard deviation of smoke motion amplitude, Indicates the number of processed electrical equipment images, Indicates The direction of smoke movement in electrical equipment images is processed. Indicates the average value of smoke movement direction for processing electrical equipment images, Indicates The smoke motion amplitude of the electrical equipment image is processed. represents the average value of the smoke motion amplitude of the first processed electrical equipment image;

[0170] The smoke movement pattern of the processed electrical device image is analyzed according to the smoke movement direction, the smoke movement amplitude, the smoke movement direction standard deviation and the smoke movement amplitude standard deviation.

[0171] Among them, the continuous frame image refers to a series of continuous image frames, which are extracted from the video, the optical flow field refers to a vector field, each vector represents the movement direction and speed of each pixel in the image between continuous frames, the smoke movement direction refers to the direction of movement of smoke particles in the continuous frame images, the smoke movement amplitude refers to the distance or speed of movement of smoke particles in the continuous frame images, the smoke movement direction standard deviation refers to the measure of the variability of the smoke movement direction, and the smoke movement amplitude standard deviation refers to the measure of the variability of the smoke movement amplitude.

[0172] Optionally, the smoke movement direction and smoke movement amplitude calculated by using the optical flow field for processing the electrical device image can be determined by a vector of the optical flow field.

[0173] The present invention is based on the smoke visual features and flame visual features, and utilizes the edge lightweight visual analysis model to analyze the potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment. The method relies on efficient algorithms and models to ensure real-time monitoring and rapid response, thereby improving the efficiency of fire analysis of electrical equipment. The potential smoke pixel blocks refer to pixel blocks where smoke may exist, and the potential flame pixel blocks refer to pixel blocks where flame may exist. In detail, the edge lightweight visual analysis model is utilized to analyze the potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment. The edge lightweight visual analysis model is used to analyze the probability that smoke and flame may exist in each pixel block of the electrical equipment. When the probability is greater than the preset smoke threshold and flame threshold, the pixel block is marked as a potential smoke pixel block and a potential flame pixel block.

[0174] The present invention calculates the equipment hot spots of the electrical equipment based on the infrared thermal imaging data, effectively utilizes the infrared thermal imaging data to monitor the operating status of the electrical equipment, promptly discovers abnormal hot spots, and prevents equipment overheating and potential fire risks.

[0175] In detail, the calculating of the device hotspot of the electrical device based on the infrared thermal imaging data includes:

[0176] Preprocessing the infrared thermal imaging data to obtain preprocessed infrared thermal imaging data;

[0177] Calculating an imaging data effectiveness coefficient of the preprocessed infrared thermal imaging data;

[0178] When the imaging data validity coefficient meets the preset imaging data validity threshold, classifying the pre-processed infrared thermal imaging data to obtain classified thermal imaging data;

[0179] identifying a class temperature sequence of the classified thermal imaging data;

[0180] An equipment hot spot of the electrical equipment is determined according to the category temperature sequence.

[0181] Among them, the pre-processed infrared thermal imaging data refers to the infrared thermal imaging data after a series of processing steps, which may include image correction, denoising, filtering, temperature calibration and other steps; the imaging data effectiveness coefficient refers to an indicator used to quantify the quality or reliability of infrared thermal imaging data; the imaging data effectiveness threshold refers to a threshold used to determine whether the imaging data is sufficiently effective for further analysis; the classified thermal imaging data refers to the classification of the pre-processed infrared thermal imaging data into different categories according to certain standards (such as temperature range, thermal characteristics, etc.); the category temperature sequence refers to a sequence obtained by sorting the temperature values ​​in the classified thermal imaging data; the device hotspot refers to a point or area identified in the infrared thermal imaging data whose temperature is significantly higher than that of the surrounding area.

[0182] S4. Analyze the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, send the smoke pixel block, the potential flame pixel block and the equipment hotspot to the data processing center in the electrical equipment fire monitoring and management system, and use the high-precision visual analysis model to analyze the fire status of the electrical equipment, wherein the fire status includes the fire location, fire type and fire level.

[0183] The present invention analyzes the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot, and can perform fire analysis through multi-dimensional fire data, thereby improving the accuracy of fire analysis.

[0184] In detail, the analyzing the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot includes:

[0185] Analyzing the smoke area and smoke density of the electrical equipment through the potential smoke pixel block;

[0186] Calculating the smoke coefficient of the electrical equipment based on the smoke area and the smoke density;

[0187] Analyzing the flame area, flame temperature and flame dynamic parameters of the electrical equipment according to the potential flame pixel block and the equipment hotspot;

[0188] Calculating a flame coefficient of the electrical device based on the flame area, flame temperature and flame dynamic parameters;

[0189] Analyzing the hotspot temperature, hotspot coordinates and hotspot distribution of the device hotspot, and calculating the hotspot coefficient of the electrical device based on the hotspot temperature, hotspot coordinates and hotspot distribution;

[0190] The fire coefficient of the electrical equipment is calculated by using the smoke coefficient, the flame coefficient and the hot spot coefficient.

[0191] Among them, the smoke area refers to the total area covered by the smoke pixel blocks identified in the image, and the smoke density refers to the concentration of smoke in a specific area. It can be calculated as the ratio of the smoke area to the total area of ​​the area. The smoke coefficient is used to indicate the severity or risk level of the smoke. The flame area refers to the total area covered by the flame pixel blocks identified in the image. This is usually obtained by calculating the sum of all pixels marked as flames. The flame temperature refers to the average or maximum temperature in the flame area. This can be obtained through temperature readings in infrared thermal imaging data. The flame dynamic parameters refer to parameters that describe the behavior of the flame, such as the swing, jump, and spread speed of the flame. These parameters can be calculated by analyzing the flame movement in continuous frame images. The flame coefficient refers to an indicator used to indicate the severity or risk level of the flame. The hotspot temperature refers to the temperature of a specific hotspot area on the equipment. The hotspot coordinates refer to the specific location of the hotspot in the image, usually expressed in the form of pixel coordinates. The hotspot distribution refers to the description of the distribution of hotspots on the equipment, including the number, location, size, etc. of hotspots. The hotspot coefficient refers to an indicator used to indicate the severity or risk level of the hotspot of the equipment. The fire coefficient refers to an indicator used to assess the fire risk of electrical equipment.

[0192] Optionally, the smoke coefficient, the flame coefficient and the hot spot coefficient are calculated by a weighted algorithm of corresponding parameters.

[0193] In the present invention, when the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the device hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level, and the fire information can be further determined by the high-precision visual analysis model to provide a basis for later fire fighting measures. Among them, the fire threshold refers to an indicator used to determine whether the fire coefficient has reached a level that requires action, and the data processing center refers to a centralized computing and storage facility, which usually includes a server and corresponding software for receiving, processing and analyzing data from electrical equipment. In the fire monitoring and management system, the data processing center is responsible for analyzing the incoming smoke, flame and hotspot data, the fire location refers to the exact or approximate location where the fire occurs, usually expressed in coordinates or relative positions (such as specific parts or areas of the equipment), the fire type refers to a classification that describes the characteristics of the fire, such as electrical fire, oil fire, solid material fire, etc., and the fire level refers to the classification of fires according to the severity and potential destructive power of the fire, which is usually divided into several levels, such as small fire, medium fire, large fire, etc.

[0194] S5. Based on the fire status, a fire fighting module in the electrical equipment fire monitoring and management system is used to construct a fire fighting strategy for the electrical equipment, and the fire fighting strategy is used to eliminate the fire of the electrical equipment corresponding to the mountain photovoltaic power station.

[0195] The present invention uses the fire state and the fire fighting module in the electrical equipment fire monitoring and management system to construct the fire fighting strategy of the electrical equipment, which can effectively deal with the fire incident of the electrical equipment and minimize the loss and impact. Among them, the fire fighting strategy includes determining the fire response level, selecting the fire extinguishing method, formulating an evacuation plan, starting the fire fighting facilities and coordinating external support. In detail, the fire response level is determined: according to the fire level, the corresponding fire response level is determined, such as a small fire may only require local fire fighting, while a large fire may require full evacuation and external fire fighting support; select the fire fighting method: select the appropriate fire fighting method according to the type of fire, such as water, foam, dry powder, carbon dioxide, etc.; formulate an evacuation plan: if necessary, formulate a personnel evacuation plan, including evacuation routes, assembly points and evacuation commands; start fire fighting facilities: automatically or manually start internal fire fighting facilities, such as sprinkler systems, fire extinguishers, smoke and fire doors, etc.; coordinate external support: if internal resources are insufficient to deal with the fire, immediately contact the external fire department and other emergency service agencies. The fire fighting module refers to a preset module that constructs different fire fighting strategies according to different fire states. Finally, the present invention can realize efficient monitoring of fires in the electrical equipment corresponding to the mountain photovoltaic power station by executing the fire fighting strategy to eliminate fires in the electrical equipment corresponding to the mountain photovoltaic power station.

[0196] Compared with the problems described in the background technology, the present invention obtains the power station scene structure of the mountain photovoltaic power station. According to the power station scene structure, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station is the basis for designing a fire monitoring system. It helps to reasonably plan the location and type of monitoring points to ensure that the monitoring system can effectively cover all key areas and timely discover and deal with potential fire risks. Furthermore, the present invention defines the nodes to be monitored in the mountain photovoltaic power station through the electrical equipment distribution to ensure that the electrical equipment fire monitoring system of the mountain photovoltaic power station effectively covers all key areas and timely discovers and deals with potential fire risks. Furthermore, the present invention utilizes the fire monitoring management system configuration of the electrical equipment corresponding to the mountain photovoltaic power station The monitoring equipment of the node to be monitored, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera, which can collect fire data from two monitoring devices, thereby improving the reliability of the subsequent fire analysis of electrical equipment. Next, the present invention analyzes the monitoring equipment and optimizes the blind spots of the mountain photovoltaic power station, thereby improving the reliability and effectiveness of the entire fire monitoring system. In detail, when the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, the edge lightweight visual analysis model is configured at the node to be monitored to realize timely processing of node collected data, thereby improving data processing efficiency, thereby increasing the speed of fire processing. Furthermore, the present invention is in the electrical equipment fire monitoring and management system The data processing center is equipped with a high-precision visual analysis model to further determine the possible fire analysis results. The layered fire analysis not only improves the reliability of the fire analysis, but also improves the operation effect of the entire system. Furthermore, the present invention is based on the smoke visual features and flame visual features, and uses the edge lightweight visual analysis model to analyze the potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment. It relies on efficient algorithms and models to ensure real-time monitoring and rapid response, thereby improving the efficiency of fire analysis of electrical equipment. The present invention calculates the equipment hotspots of the electrical equipment based on the infrared thermal imaging data and effectively uses the infrared thermal imaging data to monitor the operating status of the electrical equipment, discover abnormal hotspots in time, and prevent equipment Overheating and potential fire risks. Optionally, the present invention analyzes the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot, and can perform fire analysis through multi-dimensional fire data to improve the accuracy of fire analysis. Furthermore, when the fire coefficient meets the preset fire threshold, the present invention sends the smoke pixel block, the potential flame pixel block and the equipment hotspot to the data processing center in the electrical equipment fire monitoring and management system, and uses the high-precision visual analysis model to analyze the fire status of the electrical equipment, wherein the fire status includes the fire location, fire type and fire level, and the fire information can be further determined through the high-precision visual analysis model.This provides a basis for later firefighting measures. Finally, the present invention uses the fire status and the firefighting module in the electrical equipment fire monitoring and management system to construct the firefighting strategy for the electrical equipment, which can effectively deal with fire incidents of electrical equipment and minimize losses and impacts. Therefore, the present invention can improve the firefighting efficiency of electrical equipment in photovoltaic power stations.

[0197] Embodiment 2:

[0198] like Figure 2 , which is a functional module diagram of an application system of an electrical equipment fire monitoring system in a mountain photovoltaic power station provided by an embodiment of the present invention.

[0199] The application system 200 of the fire monitoring system for electrical equipment in mountain photovoltaic power stations of the present invention can be installed in electronic equipment. According to the functions to be implemented, the application system 200 of the fire monitoring system for electrical equipment in mountain photovoltaic power stations can include a monitoring equipment configuration module 201, a visual analysis model configuration module 202, a potential fire analysis module 203, a fire state analysis module 204 and a fire fighting strategy construction module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0200] In this embodiment, the functions of each module / unit are as follows:

[0201] The monitoring equipment configuration module 201 is used to obtain the power station scene structure of the mountain photovoltaic power station, determine the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, define the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configure the monitoring equipment of the nodes to be monitored using the fire monitoring management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera;

[0202] The visual analysis model configuration module 202 is used to analyze the monitoring blind area of ​​the monitoring equipment on the mountain photovoltaic power station and calculate the monitoring necessary coefficient of the monitoring blind area. When the monitoring necessary coefficient is lower than the preset monitoring necessary threshold, an edge lightweight visual analysis model is configured at the node to be monitored, and a high-precision visual analysis model is configured in the data processing center of the electrical equipment fire monitoring and management system;

[0203] The potential fire analysis module 203 is used to collect infrared thermal imaging data and image data of the electrical equipment using the infrared thermal imager and the high-definition camera, extract smoke visual features and flame visual features of the image data, analyze potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculate the equipment hot spots of the electrical equipment based on the infrared thermal imaging data;

[0204] The fire status analysis module 204 is used to analyze the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the equipment hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by using the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level;

[0205] The fire fighting strategy construction module 205 is used to construct a fire fighting strategy for the electrical equipment according to the fire state using the fire fighting module in the electrical equipment fire monitoring and management system, and to execute fire elimination of the electrical equipment corresponding to the mountain photovoltaic power station through the fire fighting strategy.

[0206] In detail, the modules described in the application system 200 of the electrical equipment fire monitoring system in the mountain photovoltaic power station described in the embodiment of the present invention adopt the same technical means as the application method of the electrical equipment fire monitoring system in the mountain photovoltaic power station described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0207] An embodiment of the present invention provides an electronic device for implementing a method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station.

[0208] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a method program for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station.

[0209] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory (for example, executing the application program of the fire monitoring system of electrical equipment in a mountain photovoltaic power station, etc.), and calling the data stored in the memory.

[0210] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory can not only be used to store application software and various types of data installed in the electronic device, such as the code of the application program in the mountain photovoltaic power station based on the electrical equipment fire monitoring system, but also can be used to temporarily store data that has been output or is to be output.

[0211] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0212] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0213] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0214] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0215] The application program of the fire monitoring system for electrical equipment in a mountain photovoltaic power station stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0216] Obtaining a power station scene structure of a mountain photovoltaic power station, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, defining the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configuring the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera;

[0217] Analyze the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment, and calculate the necessary monitoring coefficient of the monitoring blind area. When the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, configure an edge lightweight visual analysis model at the node to be monitored, and configure a high-precision visual analysis model in the data processing center of the electrical equipment fire monitoring and management system;

[0218] Using the infrared thermal imager and the high-definition camera to collect infrared thermal imaging data and image data of the electrical equipment, extracting smoke visual features and flame visual features of the image data, analyzing potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculating the equipment hot spots of the electrical equipment based on the infrared thermal imaging data;

[0219] The fire coefficient of the electrical equipment is analyzed by using the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the equipment hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by using the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level.

[0220] According to the fire status, a fire fighting strategy for the electrical equipment is constructed using the fire fighting module in the electrical equipment fire monitoring and management system, and the fire fighting strategy is used to eliminate the fire in the electrical equipment corresponding to the mountain photovoltaic power station.

[0221] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0222] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0223] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0224] Obtaining a power station scene structure of a mountain photovoltaic power station, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, defining the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configuring the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera;

[0225] Analyze the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment, and calculate the necessary monitoring coefficient of the monitoring blind area. When the necessary monitoring coefficient is lower than the preset necessary monitoring threshold, configure an edge lightweight visual analysis model at the node to be monitored, and configure a high-precision visual analysis model in the data processing center of the electrical equipment fire monitoring and management system;

[0226] Using the infrared thermal imager and the high-definition camera to collect infrared thermal imaging data and image data of the electrical equipment, extracting smoke visual features and flame visual features of the image data, analyzing potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculating the equipment hot spots of the electrical equipment based on the infrared thermal imaging data;

[0227] The fire coefficient of the electrical equipment is analyzed by using the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the equipment hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by using the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level.

[0228] According to the fire status, a fire fighting strategy for the electrical equipment is constructed using the fire fighting module in the electrical equipment fire monitoring and management system, and the fire fighting strategy is used to eliminate the fire in the electrical equipment corresponding to the mountain photovoltaic power station.

[0229] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0230] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0231] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0232] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0233] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0234] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0235] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for applying an electrical equipment fire monitoring system in a mountain photovoltaic power station, characterized in that: The method comprises: Obtaining a power station scene structure of a mountain photovoltaic power station, determining the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, defining the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configuring the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera; Analyze the monitoring blind spot of the mountain photovoltaic power station by the monitoring equipment, and calculate the monitoring necessity coefficient of the monitoring blind spot, wherein the monitoring necessity coefficient refers to an indicator used to indicate the urgency and importance of monitoring the monitoring blind spot, and the monitoring necessity coefficient is calculated according to the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, equipment environmental sensitivity index weight, equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, equipment environmental sensitivity index and fire risk coefficient. When the monitoring necessity coefficient is lower than the preset monitoring necessity threshold, configure an edge lightweight visual analysis model at the node to be monitored, and configure a high-precision visual analysis model at the data processing center in the electrical equipment fire monitoring and management system; Using the infrared thermal imager and the high-definition camera to collect infrared thermal imaging data and image data of the electrical equipment, extracting smoke visual features and flame visual features of the image data, analyzing potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features using the edge lightweight visual analysis model, and calculating the equipment hot spots of the electrical equipment based on the infrared thermal imaging data; The fire coefficient of the electrical equipment is analyzed by using the potential smoke pixel block, the potential flame pixel block and the equipment hotspot. When the fire coefficient meets the preset fire threshold, the smoke pixel block, the potential flame pixel block and the equipment hotspot are sent to the data processing center in the electrical equipment fire monitoring and management system, and the fire status of the electrical equipment is analyzed by using the high-precision visual analysis model, wherein the fire status includes the fire location, fire type and fire level. According to the fire status, a fire fighting strategy for the electrical equipment is constructed using the fire fighting module in the electrical equipment fire monitoring and management system, and the fire fighting strategy is used to eliminate the fire in the electrical equipment corresponding to the mountain photovoltaic power station.

2. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station according to claim 1 is characterized in that: Defining nodes to be monitored of the electrical equipment through the electrical equipment distribution includes: identifying functional characteristics of the electrical equipment; Analyzing the fire risk factor of the electrical equipment through the functional characteristics; Dividing the monitoring area of ​​the electrical equipment according to the functional characteristics and the distribution of the electrical equipment; Calculating a monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics; The nodes to be monitored of the electrical equipment are defined by the monitoring priority coefficient and the electrical equipment distribution.

3. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 2 is characterized in that: The calculating the monitoring priority coefficient of the monitoring area based on the fire risk coefficient and the functional characteristics includes: Defining equipment characteristic indicators of the functional characteristics, wherein the equipment characteristic indicators include equipment criticality index, equipment failure rate index, equipment maintenance difficulty index and equipment environmental sensitivity index; Determine the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, and equipment environmental sensitivity index weight of the equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, and equipment environmental sensitivity index; According to the equipment criticality index weight, equipment failure rate index weight, equipment maintenance difficulty index weight, equipment environmental sensitivity index weight, equipment criticality index, equipment failure rate index, equipment maintenance difficulty index, equipment environmental sensitivity index and fire risk coefficient, the monitoring priority coefficient of the monitoring area is calculated using the following formula: in, Indicates the monitoring priority coefficient of the monitoring area. Indicates the weight of the corresponding functional characteristics of the monitoring area in the monitoring priority. Indicates the equipment criticality index of the equipment in the monitoring area. Indicates the criticality index weight of the equipment in the monitoring area. Indicates the equipment failure rate index of the monitored area, Indicates the equipment failure rate index weight of the monitoring area, Indicates the equipment maintenance difficulty index of the monitored area, Indicates the equipment maintenance difficulty index weight of the monitoring area, Indicates the device environment sensitivity index of the monitored area. Indicates the weight of the equipment environment sensitivity index in the monitoring area. Indicates the weight of the fire risk factor corresponding to the monitoring area in the monitoring priority. Represents the fire risk factor of the monitored area, represents the probability of fire occurrence in the monitored area, Indicates the fire consequence severity coefficient of the monitored area, Represents the fire risk calculation function.

4. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 3 is characterized in that: The analyzing the monitoring blind area of ​​the mountain photovoltaic power station by the monitoring device includes: Constructing a device layout diagram of the monitoring device; Identifying effective adjustment parameters of the monitoring device, and calculating an effective monitoring range of the monitoring device based on the effective adjustment parameters; Analyze the environmental characteristics of the mountain photovoltaic power station; Defining a monitoring impact factor of the monitoring device according to the environmental characteristics; Marking a monitoring effective area map of the monitoring equipment on the equipment layout map according to the effective monitoring range, the environmental characteristics and the monitoring influencing factors; Based on the monitoring effective area map, a monitoring blind area of ​​the mountain photovoltaic power station by the monitoring equipment is determined.

5. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 4 is characterized in that: The calculating of the necessary monitoring coefficient of the monitoring blind area includes: Identify the blind area functional characteristics, blind area structural characteristics and monitoring targets of the monitoring blind area; Analyzing the blind spot risk level of the monitoring blind spot through the blind spot functional characteristics and the monitoring target, and defining the blind spot risk impact coefficient of the blind spot risk level; Determining a blind spot monitoring complexity coefficient and a blind spot monitoring size of the monitoring blind spot based on the blind spot structural characteristics; A blind spot risk level score, a blind spot risk impact coefficient score, a blind spot monitoring complexity coefficient score, and a blind spot monitoring size score that define the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, and the blind spot monitoring size; The necessary monitoring coefficient of the monitoring blind spot is calculated using the following formula through the blind spot risk level, the blind spot risk impact coefficient, the blind spot monitoring complexity coefficient, the blind spot monitoring size, the blind spot risk level score, the blind spot risk impact coefficient score, the blind spot monitoring complexity coefficient score and the blind spot monitoring size score: in, Indicates the necessary monitoring coefficient of the monitoring blind area, Indicates the blind spot risk level of the monitoring blind spot. Indicates the blind spot risk level score of the monitoring blind spot. Indicates the blind spot risk impact coefficient of the monitoring blind spot, Indicates the blind spot risk impact coefficient score of the monitoring blind spot, The blind spot monitoring complexity coefficient represents the blind spot monitoring area. Indicates the blind spot monitoring complexity coefficient score of the monitoring blind spot, Indicates the size of the blind area monitoring. Indicates the blind spot monitoring size score of the monitoring blind spot.

6. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 5 is characterized in that: Configuring the edge lightweight visual analysis model at the node to be monitored includes: Defining lightweight visual analysis requirements of the nodes to be monitored; According to the lightweight visual analysis requirements, a lightweight network architecture of the nodes to be monitored is constructed; Collecting historical monitoring data of the node to be monitored, and performing data enhancement on the historical monitoring data to obtain enhanced historical monitoring data; Using the enhanced historical monitoring data to train the lightweight network architecture, to obtain a trained lightweight network model; Performing model compression on the trained lightweight network model to obtain a compressed lightweight network model, wherein the model compression includes model weight pruning and model quantization; Calculating a lightweight model performance of the compressed lightweight network model; When the performance of the lightweight model meets a preset model performance threshold, the compressed lightweight network model is configured on the node to be monitored to obtain the edge lightweight visual analysis model.

7. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 6 is characterized in that: The step of extracting smoke visual features and flame visual features from the image data comprises: Performing image preprocessing on the image data to obtain a processed electrical equipment image; Calculating a color histogram of the processed electrical device image; Defining a color moment of the processed electrical device image according to the color histogram, and extracting smoke color features and flame color features of the processed electrical device image through the color moment; Constructing a gray level co-occurrence matrix of the processed electrical equipment image; capturing smoke texture features of the processed electrical equipment image according to the gray level co-occurrence matrix; Extracting the smoke contour and the flame contour of the processed electrical device image, and determining the smoke shape feature and the flame shape feature of the processed electrical device image through the smoke contour; marking the smoke motion pattern of the processed electrical device image; Determining the smoke movement characteristics of the processed electrical equipment image through the smoke movement pattern; Analyzing the flame frequency components of the processed electrical equipment image, and defining the flame frequency characteristics of the processed electrical equipment image according to the flame frequency components; Determining smoke visual features of the processed electrical device image based on the smoke color features, the smoke texture features, the smoke shape features, and the smoke operation features; The flame visual feature of the processed electrical device image is determined according to the flame color feature, the flame shape feature and the flame frequency feature.

8. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 7 is characterized in that: The marking of the smoke motion pattern of the processed electrical device image includes: Selecting the continuous frame images of the processed electrical equipment image; Constructing an optical flow field of the continuous frame images; Calculating the smoke movement direction and smoke movement amplitude of the processed electrical equipment image through the optical flow field; The smoke movement direction standard deviation and the smoke movement amplitude standard deviation of the smoke movement direction and the smoke movement amplitude are calculated using the following formula: in, represents the standard deviation of the smoke movement direction, represents the standard deviation of smoke motion amplitude, Indicates the number of processed electrical equipment images, Indicates The direction of smoke movement in electrical equipment images is processed. Indicates the average value of smoke movement direction for processing electrical equipment images, Indicates The smoke motion amplitude of the electrical equipment image is processed. represents the average value of the smoke motion amplitude of the first processed electrical equipment image; The smoke movement pattern of the processed electrical device image is analyzed according to the smoke movement direction, the smoke movement amplitude, the smoke movement direction standard deviation and the smoke movement amplitude standard deviation.

9. The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station as claimed in claim 8, characterized in that: The analyzing the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot includes: Analyzing the smoke area and smoke density of the electrical equipment through the potential smoke pixel block; Calculating the smoke coefficient of the electrical equipment based on the smoke area and the smoke density; Analyzing the flame area, flame temperature and flame dynamic parameters of the electrical equipment according to the potential flame pixel block and the equipment hotspot; Calculating a flame coefficient of the electrical device based on the flame area, flame temperature and flame dynamic parameters; Analyzing the hotspot temperature, hotspot coordinates and hotspot distribution of the device hotspot, and calculating the hotspot coefficient of the electrical device based on the hotspot temperature, hotspot coordinates and hotspot distribution; The fire coefficient of the electrical equipment is calculated by using the smoke coefficient, the flame coefficient and the hot spot coefficient.

10. An electrical equipment fire monitoring system applied in a mountain photovoltaic power station, characterized in that: The method for applying the electrical equipment fire monitoring system in a mountain photovoltaic power station according to any one of claims 1 to 9 is used to implement the method, wherein the system comprises: A monitoring equipment configuration module is used to obtain a power station scene structure of a mountain photovoltaic power station, determine the electrical equipment distribution of the electrical equipment corresponding to the mountain photovoltaic power station according to the power station scene structure, define the nodes to be monitored of the electrical equipment through the electrical equipment distribution, and configure the monitoring equipment of the nodes to be monitored using the fire monitoring and management system of the electrical equipment corresponding to the mountain photovoltaic power station, wherein the monitoring equipment includes an infrared thermal imager and a high-definition camera; A visual analysis model configuration module is used to analyze the monitoring blind area of ​​the monitoring equipment on the mountain photovoltaic power station and calculate the necessary monitoring coefficient of the monitoring blind area. When the necessary monitoring coefficient is lower than a preset necessary monitoring threshold, an edge lightweight visual analysis model is configured at the node to be monitored, and a high-precision visual analysis model is configured in the data processing center of the electrical equipment fire monitoring and management system; A potential fire analysis module, used to collect infrared thermal imaging data and image data of the electrical equipment using the infrared thermal imager and the high-definition camera, extract smoke visual features and flame visual features of the image data, analyze potential smoke pixel blocks and potential flame pixel blocks of the electrical equipment based on the smoke visual features and flame visual features and use the edge lightweight visual analysis model, and calculate the equipment hot spots of the electrical equipment based on the infrared thermal imaging data; A fire status analysis module, used to analyze the fire coefficient of the electrical equipment through the potential smoke pixel block, the potential flame pixel block and the equipment hotspot, and when the fire coefficient meets the preset fire threshold, send the smoke pixel block, the potential flame pixel block and the equipment hotspot to the data processing center in the electrical equipment fire monitoring and management system, and use the high-precision visual analysis model to analyze the fire status of the electrical equipment, wherein the fire status includes the fire location, fire type and fire level; A fire fighting strategy construction module is used to construct a fire fighting strategy for the electrical equipment based on the fire status and the fire fighting module in the electrical equipment fire monitoring and management system, and to eliminate the fire of the electrical equipment corresponding to the mountain photovoltaic power station through the fire fighting strategy.

Images