Power grid region risk assessment method and device under satellite perception and storage medium
Through the combination of satellite perception technology, Gaussian hybrid model and hierarchical fault tree model, the temperature and failure probability of power equipment are dynamically monitored, solving the problems of low efficiency and inaccuracy of traditional power grid risk assessment methods, and achieving efficient failure risk of power equipment Assessment and early warning.
Patent Information
- Application Number
- CN202411146418.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-22
AI Technical Summary
Traditional grid risk assessment methods are inefficient and blind, and cannot accurately assess the risk of power equipment failure, especially in large-scale power equipment inspections and failure probability assessments, where there are difficulties in handling inaccuracies and complex relationships.
Satellite perception technology is adopted to obtain the temperature spatiotemporal distribution data of power equipment through thermal infrared and visible band imaging processing, and combine the Gaussian hybrid model and the hierarchical fault tree model to dynamically monitor the temperature gradient and fault probability, and issue alarm information to warning for potential faults.
Accurate temperature monitoring and fault risk assessment of power equipment are achieved, the efficiency of power grid management is improved, maintenance costs and power outage risks are reduced, and comprehensive monitoring and management of the operating status of power equipment is provided.
Smart Images

Figure CN119005699A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information technology, and in particular to a method for risk assessment of a power grid area under satellite perception, a device for risk assessment of a power grid area under satellite perception, a computer-readable storage medium, and an electronic device. Background Art
[0002] In the power system, local overheating is one of the main causes of power equipment failure, which may cause serious power outages and accidents. Therefore, early detection of potential problems in power equipment is crucial to maintaining the stable operation of the power grid.
[0003] Traditional risk assessment methods often rely on manual inspections and empirical judgments, which have some problems. Manual inspections are inefficient. Traditional inspection methods require personnel to enter the site for inspection, which consumes a lot of time and human resources. For a wide range of power equipment, including substations, transmission lines, distribution equipment, etc., the inspection tasks are huge and cumbersome. Failure probability assessment is inaccurate. Traditional risk assessment methods often cannot accurately assess the failure probability of power equipment. The failure probability of power equipment is usually affected by multiple factors, and there may be complex correlations between these factors. Traditional methods often cannot effectively handle such complex correlations, resulting in inaccurate assessment results. The operating status of power equipment will change over time, such as aging, wear, etc. Traditional methods often cannot accurately consider the impact of changes in equipment status on the failure probability. This results in the inability to detect potential failure risks in advance, increasing the maintenance cost of power equipment and the risk of power outages. Summary of the invention
[0004] The main purpose of this application is to provide a power grid area risk assessment method under satellite perception, a power grid area risk assessment device under satellite perception, a computer-readable storage medium and an electronic device, so as to at least solve the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance.
[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for risk assessment of power grid area under satellite perception is provided, comprising: imaging a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, wherein the power equipment is arranged in the target area; dynamically monitoring and collecting the temperature gradient change of the surface area of the power equipment based on the temperature spatiotemporal distribution data to obtain temperature gradient data; imaging the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormality score of each surface area of the power equipment, and determining the temperature abnormality area of the power equipment based on the size of the predicted abnormality score and a preset score threshold; inputting the temperature abnormality area of the power equipment into a hierarchical fault tree model to obtain the failure probability of the power equipment, and issuing an alarm message when the failure probability exceeds the probability threshold.
[0006] Optionally, imaging processing is performed on the target area in a thermal infrared band to obtain a first satellite remote sensing image, and temperature spatiotemporal distribution data of the surface area of the power equipment is determined based on the first satellite remote sensing image, including: determining the optimal time window for satellite shooting based on satellite orbit parameters and the geographical location information of the target area, and acquiring the thermal infrared band satellite image within the time window; performing geometric correction and radiation calibration on the thermal infrared band satellite image to obtain the first satellite remote sensing image; extracting the pixel area of the power equipment in the first satellite remote sensing image, and calculating the radiation brightness of each pixel based on Planck's law, and converting the radiation brightness into surface temperature; and obtaining temperature spatiotemporal distribution data of different parts of the power equipment based on the surface temperature corresponding to each pixel.
[0007] Optionally, the temperature gradient changes in the surface area of the electric equipment are dynamically monitored and collected based on the temperature spatiotemporal distribution data to obtain temperature gradient data, including: predicting the heat load changes of the electric equipment based on the operating current of the electric equipment, and determining the sampling frequency of temperature monitoring; determining the sampling method of temperature monitoring based on the equipment type of the electric equipment; determining the heat source and heat dissipation path existing in the electric equipment based on the surface geometry and structural characteristics of the electric equipment, and determining the temperature sampling path based on the heat source and the heat dissipation path; dynamically monitoring and collecting the temperature gradient changes in the surface area of the electric equipment based on the temperature spatiotemporal distribution data, the sampling frequency of temperature monitoring, the sampling method of temperature monitoring and the temperature sampling path.
[0008] Optionally, imaging processing is performed on the target area in the visible light band to obtain a second satellite remote sensing image, and a thermal map of the power equipment is obtained based on the first satellite remote sensing image and the second satellite remote sensing image, including: geometric correction and denoising preprocessing are performed on the first satellite remote sensing image and the second satellite remote sensing image respectively to obtain a first processed image and a second processed image; the boundary contour of the power equipment in the first processed image is extracted using a Sobel operator to obtain a pixel area of the power equipment, and a graded color table is set according to the actual surface temperature range of the power equipment, and the first processed image is mapped and rendered to obtain a thermal infrared image; the name and number attribute data of the power equipment are obtained in combination with geographic information system data, and the spatial position coordinate information of the power equipment is marked on the second processed image to obtain a visible light image; based on the thermal infrared image and the visible light image, a temperature scale and a legend are added below the image to indicate the temperature values and meanings corresponding to different colors to form a thermal map of the power equipment, and the thermal map includes the spatial position, surface temperature distribution and identification information of the power equipment.
[0009] Optionally, the temperature spatiotemporal distribution data is input into a Gaussian mixture model to obtain a predicted abnormality score for each of the surface areas of the electrical equipment, and the temperature abnormality area of the electrical equipment is determined based on the size of the predicted abnormality score and a preset score threshold, including: obtaining historical temperature distribution data, and using the Bayesian information criterion to select optimal model parameters and the number of Gaussian distributions to construct an initial Gaussian model; inputting the historical temperature distribution data into the initial Gaussian model for training to obtain the Gaussian mixture model, wherein the historical temperature distribution data is a mixed distribution composed of several Gaussian distributions; inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormality score for each of the surface areas of the electrical equipment; when the predicted abnormality score is greater than the preset score threshold, the surface area is determined as the temperature abnormality area; when the predicted abnormality score is less than or equal to the preset score threshold, the surface area is determined as a non-temperature abnormality area.
[0010] Optionally, before inputting the abnormal temperature area of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, the method also includes: constructing a first-level subtree based on the historical local overheating causes and historical failure modes of the power equipment, taking different failure modes as sub-event nodes, and refining the subtree step by step for each failure mode, and the sub-event nodes include at least overload, short circuit and open circuit; according to the historical local overheating causes and historical failure modes of the power equipment, presetting the failure probability of basic event nodes; using the combination of Boolean algebra and logic gates to calculate the probability of upper-level events based on the probability and logical relationship of lower-level sub-events; according to the structure of the hierarchical fault tree model and the defined event probability, calculating the failure probability of the top event by transferring the probability from the bottom layer to the top, so as to construct the hierarchical fault tree model.
[0011] Optionally, after inputting the abnormal temperature area of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, and issuing an alarm message when the failure probability exceeds the probability threshold, the method also includes: determining the operating state of the power equipment, the operating state including: normal operating state, partial failure state of different levels and complete failure state; constructing a multi-state Markov model of the power equipment, and based on the multi-state Markov model, establishing a state transition probability matrix according to the operating state of the power equipment to obtain the state transition probability of the power equipment, the state transition probability matrix characterizes the probability of the power equipment transferring between different states; determining the time distribution of the power equipment in each operating state according to historical fault statistics, to obtain the state duration of the power equipment, the time distribution including exponential distribution or Weibull distribution; calculating the maintenance requirement probability of the power equipment in different operating states based on the state transition probability and the state duration, the maintenance requirement probability indicating the probability that the power equipment needs to be repaired in a certain state; evaluating the maintenance requirement index of the power equipment according to the maintenance requirement probability, the maintenance requirement index including the average life and reliability parameters of the power equipment.
[0012] According to another aspect of the present application, a power grid area risk assessment device under satellite perception is provided, comprising: a first processing unit, used to perform imaging processing on a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determine the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, wherein the power equipment is arranged in the target area; a collection unit, used to dynamically monitor and collect the temperature gradient change of the surface area of the power equipment based on the temperature spatiotemporal distribution data to obtain temperature gradient data; a second processing unit, used to perform imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtain a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; a determination unit, used to input the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the power equipment, and determine the temperature abnormal area of the power equipment based on the size of the predicted abnormal score and a preset score threshold; a third processing unit, used to input the temperature abnormal area of the power equipment into a hierarchical fault tree model to obtain the failure probability of the power equipment, and issue an alarm message when the failure probability exceeds the probability threshold.
[0013] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the power grid area risk assessment methods under satellite perception.
[0014] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the above-mentioned power grid area risk assessment methods under satellite perception.
[0015] Applying the technical solution of the present application, the above-mentioned power grid area risk assessment method under satellite perception first performs imaging processing on the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determines the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, and the power equipment is arranged in the target area; then, the temperature gradient change of the surface area of the power equipment is dynamically monitored and collected based on the temperature spatiotemporal distribution data to obtain temperature gradient data; then, the target area is imaged and processed in the visible light band to obtain a second satellite remote sensing image, and a thermal map of the power equipment is obtained based on the first satellite remote sensing image and the second satellite remote sensing image; the temperature spatiotemporal distribution data is input into a Gaussian mixture model to obtain the predicted abnormality score of each surface area of the power equipment, and the temperature abnormality area of the power equipment is determined based on the size of the predicted abnormality score and the preset score threshold; finally, the temperature abnormality area of the power equipment is input into a hierarchical fault tree model to obtain the failure probability of the power equipment, and when the failure probability exceeds the probability threshold, an alarm message is issued. This method can draw thermal infrared images of power equipment facilities, predict abnormal hot spots of power equipment, and assess the failure probability of power equipment due to local overheating. If the failure probability exceeds the limit, it will issue a temperature abnormality risk warning for the power equipment in the power grid area. In addition, it can also generate accurate power equipment temperature monitoring results, and provide corresponding failure probability assessment and maintenance demand prediction, to achieve comprehensive monitoring and management of the operating status of power equipment, solving the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0017] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for risk assessment of a power grid area under satellite perception provided in an embodiment of the present application is shown;
[0018] Figure 2 A schematic diagram of a flow chart of a method for risk assessment of a power grid area under satellite perception provided according to an embodiment of the present application is shown;
[0019] Figure 3 A schematic diagram of a power grid area risk assessment method under satellite perception provided according to an embodiment of the present application is shown;
[0020] Figure 4 A schematic flow chart of another method for risk assessment of a power grid area under satellite perception provided according to an embodiment of the present application is shown;
[0021] Figure 5 A structural block diagram of a power grid area risk assessment device under satellite perception provided according to an embodiment of the present application is shown.
[0022] The above drawings include the following reference numerals:
[0023] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION
[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0027] As introduced in the background technology, traditional risk assessment methods in the prior art often rely on manual inspections and empirical judgments, and there are some problems. The failure probability assessment is inaccurate, and the failure probability of power equipment cannot be accurately assessed. It is difficult to effectively handle this complex correlation, resulting in inaccurate assessment results, and it is impossible to accurately consider the impact of changes in equipment status on the failure probability. In order to solve the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance, the embodiments of the present application provide a power grid area risk assessment method under satellite perception, a power grid area risk assessment device under satellite perception, a computer-readable storage medium and an electronic device.
[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for assessing power grid area risk under satellite perception according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for risk assessment of power grid area under satellite perception in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0031] In this embodiment, a method for risk assessment of a power grid area under satellite perception running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0032] Figure 2 FIG. 1 is a flow chart of a method for assessing power grid area risk under satellite perception according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:
[0033] Step S201, imaging a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of a surface area of the power equipment according to the first satellite remote sensing image, wherein the power equipment is arranged in the target area;
[0034] Specifically, by analyzing the spatiotemporal distribution data of temperature on the surface of power equipment, abnormal conditions of power equipment can be discovered in a timely manner, providing a scientific basis for equipment maintenance and fault handling.
[0035] The method of imaging the target area in the thermal infrared band to obtain a first satellite remote sensing image and determining the temperature spatiotemporal distribution data of the surface area of the power equipment according to the first satellite remote sensing image comprises the following steps:
[0036] Step S301, determining the best time window for satellite photography based on satellite orbit parameters and the geographical location information of the target area, and acquiring a thermal infrared band satellite image within the time window;
[0037] Step S302, performing geometric correction and radiation calibration on the above-mentioned thermal infrared band satellite image to obtain the above-mentioned first satellite remote sensing image;
[0038] Step S303, extracting the pixel area of the electric power equipment in the first satellite remote sensing image, calculating the radiation brightness of each pixel according to Planck's law, and converting the radiation brightness into surface temperature;
[0039] Step S304: obtaining the spatiotemporal temperature distribution data of different parts of the electric power equipment according to the surface temperature corresponding to each of the pixels.
[0040] Specifically, if the thermal infrared band satellite image contains power equipment, the pixel area of the power equipment is extracted. According to Planck's law, the radiation brightness of each pixel is calculated and converted into surface temperature. According to the surface material characteristics of the power equipment, the temperature distribution map is corrected and mapped. The thermal map of the power equipment is drawn to reflect the temporal and spatial distribution of temperature, and the temporal and spatial distribution thermal map of temperature in different parts of the power equipment facilities is obtained. This method can eliminate image distortion and radiation noise.
[0041] If the distribution area of power equipment cannot be effectively segmented due to its dense distribution, the SIFT feature descriptor is set to extract the outline of the power equipment and identify different power equipment. If the obstruction affects the reading of the surface temperature of the power equipment, the temperature of the obscured area is estimated based on the surface temperature of the surrounding exposed power equipment. If some power equipment is facing a transitional or insufficient heating state, the missing temperature time period of the corresponding power equipment is recorded and the next thermal infrared image data is waited for.
[0042] In some examples, a substation is determined as the target area according to the grid planning information, and its location coordinates are (32.5°N, 118.8°E). The astronomical calendar is queried to determine that December 3rd 10:00 to 12:00 is the satellite orbit transit time window. The parameters of the satellite thermal imager are set to 8-14μm band and 2m resolution. The thermal infrared camera is turned on at 10:30 on December 3rd to image the target area. The original image obtained has geometric distortion, and the image is calibrated by the four-parameter method to eliminate the distortion. Then, based on the blackbody radiation law, the radiance of each pixel is converted into a temperature value. However, since the target area is too small and the proportion of power equipment in the image is small, it cannot be effectively segmented and identified. Therefore, the SIFT feature descriptor is used to match the contour shapes of different equipment, such as transformers, switch cabinets, etc., and the pixel area of each equipment is extracted. However, the equipment in the distant image is severely blocked, and the surface temperature cannot be fully read. According to the surface temperature of the surrounding exposed equipment, the temperature distribution of the blocked area is extrapolated and estimated. At the same time, DBSCAN cluster analysis is performed to detect and filter outlier temperature points with abnormal readings. Finally, a thermal map of the main equipment in the target area is drawn, and the working status of the equipment is judged by temperature changes. For example, a gradual increase in the temperature of a transformer may represent an overload operation; if high-temperature points are widely distributed on the surface of the switch cabinet, local component failure is predicted.
[0043] Step S202, dynamically monitoring and collecting the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data to obtain temperature gradient data;
[0044] Specifically, through dynamic monitoring, the temperature gradient changes in the surface area of the power equipment can be understood in a timely manner, which helps to detect abnormal situations in a timely manner and take corresponding measures, thereby improving the safety of the power equipment.
[0045] The temperature gradient change of the surface area of the above-mentioned power equipment is dynamically monitored and collected according to the above-mentioned temperature spatiotemporal distribution data to obtain the temperature gradient data, including the following steps:
[0046] Step S401, predicting the change of the heat load of the above-mentioned power equipment according to the operating current of the above-mentioned power equipment, and determining the sampling frequency of temperature monitoring;
[0047] Step S402, determining a sampling method for temperature monitoring according to the equipment type of the above-mentioned power equipment;
[0048] Step S403, determining the heat source and heat dissipation path existing in the power equipment according to the surface geometry and structural characteristics of the power equipment, and determining the temperature sampling path according to the heat source and the heat dissipation path;
[0049] Step S404: dynamically monitor and collect the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data, the above-mentioned temperature monitoring sampling frequency, the above-mentioned temperature monitoring sampling method and the above-mentioned temperature sampling path.
[0050] Specifically, the sampling frequency, method and sampling path of temperature monitoring can be determined through various data of the power equipment, and data can be collected according to the change of temperature gradient. This method can optimize the collection path and collect temperature gradient data more accurately.
[0051] Among them, the change of thermal load of the power equipment is predicted according to the operating current of the power equipment, and the sampling frequency of temperature monitoring is determined. If the power equipment is a transformer, a multi-channel infrared temperature measurement module is installed on the high-voltage side of the transformer to monitor the temperature of several sampling points on the surface. If the reflectivity of the material of the power equipment is lower than the preset reflectivity, a contact temperature probe is used. If some measuring points cannot completely cover the surface temperature distribution, the historical temperature gradient data is obtained and used as input to construct a Bayesian network model for probabilistic inference to obtain the probability distribution of the temperature distribution in the uncovered area. If there is heat accumulation in the local area of the power equipment and the temperature difference exceeds the preset temperature difference threshold, it is evaluated as an abnormal temperature gradient. According to the geometric shape and structural characteristics of the surface of the power equipment, the existing heat source and heat dissipation path are determined, the sampling path is optimized, and the above-mentioned temperature gradient data of the surface area of the power equipment are collected.
[0052] In some examples, the thermal load change of the equipment is predicted according to the equipment running current, and the sampling frequency of temperature monitoring is determined. There is a motor with a rated current of 10 amperes. Through historical data, the thermal load change law of the motor under different load conditions can be obtained. When the motor running current is 5 amperes, its thermal load is 50 degrees / hour; when the motor running current is 8 amperes, its thermal load is 80 degrees / hour. The thermal load change under different running currents can be predicted based on these data. The current running current of the motor is 7 amperes, and its thermal load can be estimated to be 70 degrees / hour by linear interpolation. Next, the sampling frequency of temperature monitoring needs to be determined. Real-time temperature monitoring of the motor is required to ensure its normal operation. According to experience, it is known that the temperature change of the motor is relatively slow and will not change drastically in a short time. Therefore, it is possible to choose to collect temperature data once an hour to meet the needs of real-time monitoring. If the equipment is a transformer and the reflectivity of the material is lower than the preset reflectivity, you can choose to install a multi-channel infrared temperature measurement module to monitor the temperature of several sampling points on the transformer surface. Four infrared temperature measurement modules are installed on the high-voltage side of the transformer to monitor the four sampling points on the transformer surface respectively. The temperature value of each sampling point can be expressed in the form of a numerical value. The temperature of sampling point 1 is 80 degrees Celsius, the temperature of sampling point 2 is 85 degrees Celsius, the temperature of sampling point 3 is 82 degrees Celsius, and the temperature of sampling point 4 is 78 degrees Celsius. If some measuring points cannot completely cover the surface temperature distribution, the historical temperature gradient data can be obtained and used as input to build a Bayesian network model for probabilistic inference to obtain a probability distribution prediction of the temperature distribution of the uncovered area. There is a plate with 5 measuring points on it to measure the temperature, but for some reason, it is impossible to measure at the center of the plate. The historical data can be used to infer the probability distribution prediction of the temperature distribution at the center through the Bayesian network model. According to the historical temperature gradient data, it can be obtained that the probability of the temperature at the center being 30 degrees Celsius is 80%, the probability of the temperature being 35 degrees Celsius is 15%, and the probability of the temperature being 40 degrees Celsius is 5%. If there is heat accumulation in the local area of the equipment and the temperature difference exceeds the preset temperature difference threshold, it can be evaluated as a temperature gradient anomaly. An electronic device has a component that has heat accumulation, causing its temperature to be 10 degrees Celsius higher than the surrounding environment. According to the preset temperature difference threshold of 5 degrees Celsius, the temperature gradient of the component can be evaluated as abnormal. Finally, by monitoring the temperature distribution on the surface of the device, the existing heat source and heat dissipation path can be determined based on the geometric shape and structural characteristics of the device surface, so as to optimize the sampling path and collect temperature gradient data on the surface area of the device. There is a radiator with many cooling fins on its surface. The heat dissipation path can be determined based on the geometric shape and structural characteristics of the cooling fins, and the temperature sampling path can be optimized to obtain temperature gradient data at various locations of the radiator. You can choose to collect a set of data in the center and on both sides of the cooling fins to obtain the gradient information of the radiator surface temperature.
[0053] Step S203, performing imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image;
[0054] Specifically, this method can realize remote monitoring and diagnosis of power equipment, reduce the workload and risk of manual inspections, and improve the management efficiency and reliability of power equipment.
[0055] The step of imaging the target area in the visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image, comprises the following steps:
[0056] Step S501, performing geometric correction and denoising preprocessing on the first satellite remote sensing image and the second satellite remote sensing image respectively to obtain a first processed image and a second processed image;
[0057] Step S502, using the Sobel operator to extract the boundary contour of the power equipment in the first processed image to obtain the pixel area of the power equipment, and setting a graded color table according to the actual surface temperature range of the power equipment, mapping and rendering the first processed image to obtain a thermal infrared image;
[0058] Step S503, combining the geographic information system data, obtaining the name and number attribute data of the power equipment, marking the spatial position coordinate information of the power equipment on the second processed image, and obtaining a visible light image;
[0059] Step S504, based on the thermal infrared image and the visible light image, a temperature scale and a legend are added below the image to indicate the temperature values and meanings corresponding to different colors, so as to form a thermal map of the power equipment. The thermal map includes the spatial position, surface temperature distribution and identification information of the power equipment.
[0060] Specifically, combining the first and second satellite remote sensing images can provide a more comprehensive understanding of the condition of the power equipment, including its appearance and thermal characteristics, which helps to detect problems in a timely manner and perform maintenance. The thermal map can intuitively display the heat distribution of the power equipment, help analyze the working status and performance of the equipment, and improve the efficiency and safety of equipment operation.
[0061] Among them, satellite remote sensing images in thermal infrared and visible light bands are obtained, and geometric correction and denoising preprocessing are performed on the satellite remote sensing images in thermal infrared and visible light bands respectively. On the thermal infrared image, the boundary contour of the power equipment target is extracted using the Sobel operator to obtain the pixel area of the power equipment. According to the actual surface temperature range of the power equipment, a graded color table is set to map and render the temperature distribution map of the power equipment. On the visible light image, the spatial position coordinate information of the power facility is plotted and fused with the thermal infrared image. Combined with the geographic information system data, the name and number attribute data of the power equipment are obtained, and the power equipment identification mark is drawn. A temperature scale and legend are added below the image to indicate the temperature values and meanings corresponding to different colors, forming a thermal infrared image thermogram of the power facility area, which includes the spatial position and surface temperature distribution and identification information of the power equipment. If the deviation between the power equipment mark and the actual position in the generated thermogram exceeds the preset deviation, the image geometric transformation parameters are recalibrated. If the boundary recognition of the power equipment in the thermogram is inaccurate and cannot be aligned with the temperature distribution, the Sobel operator is used to re-segment the target.
[0062] In some instances, a visible light image and a thermal infrared image of the same geographical location are obtained. The thermal infrared image is denoised, and a 5*5 Gaussian filter is used to smooth the image and eliminate isolated noise points. Then, the exponential edge detection operator is used to detect the edge contour of the rectangular device target in the image. Based on the morphological segmentation method, the device pixel area is determined and the target of interest is extracted. For the device surface temperature range of 20℃-100℃, a color mapping table of blue, white and red intervals is set, with blue below 20℃, white at 40℃, red at 60℃, and dark red above 100℃. According to this temperature-color mapping relationship, the device temperature pixels are converted and rendered into color values to generate a pseudo-color map of the temperature distribution. In addition, the name, number, category, etc. of each device are manually marked in the visible light image, and the image is fused with the thermal infrared image. Then the coordinate system is set, and a digital temperature scale and a color legend bar are added to the blank space of the image to complete the thermal map drawing of the power facility area. In the final thermal map, different equipment categories and specific numbers are visualized corresponding to their surface temperature distribution, and temperature anomalies are judged by color changes.
[0063] Step S204, inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each of the surface areas of the power equipment, and determining a temperature abnormal area of the power equipment according to a difference between the predicted abnormal score and a preset score threshold;
[0064] Specifically, the Gaussian mixture model is used to accurately predict the temperature abnormality area of the power equipment, which improves the accuracy and efficiency of fault detection. At the same time, the method can effectively identify and locate the abnormal area of the power equipment, helping maintenance personnel to quickly take corresponding measures. In addition, thermal infrared images of power equipment facilities are produced to predict the hot spot abnormal area of the power equipment and evaluate the failure probability of the power equipment due to local overheating.
[0065] The temperature spatiotemporal distribution data is input into a Gaussian mixture model to obtain the predicted abnormality score of each of the surface areas of the power equipment, and the temperature abnormality area of the power equipment is determined according to the difference between the predicted abnormality score and the preset score threshold, including the following steps:
[0066] Step S601, obtaining historical temperature distribution data, and using the Bayesian Information Criterion to select optimal model parameters and Gaussian distribution quantity, and constructing an initial Gaussian model;
[0067] Step S602, inputting the historical temperature distribution data into the initial Gaussian model for training to obtain the Gaussian mixture model, wherein the historical temperature distribution data is a mixture distribution composed of several Gaussian distributions;
[0068] Step S603, inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormality score of each of the surface areas of the power equipment;
[0069] Step S604, when the predicted abnormality score is greater than the preset score threshold, determining the surface area as the temperature abnormality area;
[0070] Step S605: when the predicted abnormality score is less than or equal to the preset score threshold, the surface area is determined as a non-temperature abnormality area.
[0071] Specifically, the trained Gaussian mixture model is used to predict the new temperature spatiotemporal distribution data, and for each area, the anomaly score of the area under each Gaussian distribution is calculated. This method can accurately predict the temperature anomaly area of power equipment, improve the accuracy and efficiency of fault detection, and help personnel take measures in advance.
[0072] Among them, the above temperature gradient data is obtained, and the above temperature gradient data is preprocessed to eliminate the unreadable areas. The temperature spatiotemporal distribution data is used as input and trained using the Gaussian mixture model. The temperature spatiotemporal distribution data is regarded as a mixed distribution composed of several Gaussian distributions. The Bayesian information criterion is used to select the optimal model parameters and the number of Gaussian distributions. According to the anomaly score, the area with an anomaly score higher than the preset anomaly score threshold is determined as the abnormal hot spot area of the power equipment.
[0073] In some instances, the temperature gradient data of power equipment is obtained, and temperature anomalies may indicate equipment failure or hot spots. First, the obtained temperature gradient data needs to be preprocessed. Among them, eliminating the unreadable area is an important step. If the sensor is damaged or cannot work, the corresponding temperature data is invalid. The preset threshold can be used to determine whether to exclude the temperature data of a certain area. Next, the temperature gradient data is used as input and trained using the Gaussian mixture model. The Gaussian mixture model is a probabilistic model in which the temperature gradient data is a mixture distribution composed of several Gaussian distributions. The Bayesian Information Criterion can be used to select the optimal model parameters and the number of Gaussian distributions. A Gaussian mixture model is selected, and the model parameters and the number of Gaussian distributions are obtained. Now, the trained Gaussian mixture model can be used to predict the new temperature spatiotemporal distribution data. For each area, the anomaly score of the area under each Gaussian distribution can be calculated. The anomaly score can be used to measure whether the temperature of the area is abnormal. There is a new temperature gradient data, which contains temperature information of multiple areas. The trained Gaussian mixture model can be used to calculate the anomaly score for each area. There are three Gaussian distributions, representing normal temperature, slightly abnormal temperature, and severely abnormal temperature. For a certain area, its anomaly score under these three Gaussian distributions can be calculated, and then the preset anomaly score threshold can be used to determine whether the area is an abnormal device hotspot area.
[0074] Before inputting the abnormal temperature region of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, the method further includes the following steps:
[0075] Step S701, constructing a first-level subtree according to the historical local overheating causes and historical failure modes of the above-mentioned power equipment, taking different failure modes as sub-event nodes, and refining the subtree level by level for each of the above-mentioned failure modes, wherein the above-mentioned sub-event nodes at least include overload, short circuit and open circuit;
[0076] Step S702, presetting the failure probability of the basic event node according to the historical local overheating causes and historical failure modes of the above-mentioned power equipment;
[0077] Step S703, using a combination of Boolean algebra and logic gates to calculate the probability of the upper-level event based on the probability and logical relationship of the lower-level sub-events;
[0078] Step S704 , according to the structure of the above-mentioned hierarchical fault tree model and the defined event probabilities, the fault probability of the top event is calculated by performing probability transfer from the bottom layer upwards to construct the above-mentioned hierarchical fault tree model.
[0079] Specifically, by constructing a hierarchical fault tree model, the historical failure modes and overheating causes of power equipment can be clearly displayed, helping analysts to better understand the potential failure mechanisms. By using a combination of Boolean algebra and logic gates, the probability of events at each layer can be accurately calculated.
[0080] Figure 3 A schematic diagram of a power grid area risk assessment method under satellite perception provided according to an embodiment of the present application is shown;
[0081] First, the event is defined as the failure of power equipment due to local overheating, and the system boundary is the involved power equipment and its related components. Then, a hierarchical fault model of the power equipment is constructed. The first-level subtree is constructed according to the causes of local overheating of the power equipment and the possible fault models. Different failure modes are used as sub-event nodes, including overload, short circuit and open circuit. The subtree is refined step by step until the required accuracy and detail are achieved. According to the failure probability of the basic event nodes in the historical fault statistical data trajectory, the probability of the upper-level event is calculated through the combination of Boolean algebra and logic gates. Starting from the lowest level, the probability is transferred upward to calculate the failure probability of the above-mentioned top event. According to the calculated potential failure probability of the top event, the probability of failure of the power equipment due to local overheating is estimated.
[0082] The top event is defined as the failure of the power equipment due to local overheating, and the system boundary is the involved power equipment and its related components, and a hierarchical fault tree model of the power equipment is constructed. According to the causes of local overheating of the power equipment and the possible failure modes, the first-level subtree is constructed, and different failure modes are used as sub-event nodes, including overload, short circuit and open circuit. For each failure mode, the subtree is refined step by step until the required accuracy and detail are achieved. According to the historical failure statistics, the failure probability of the basic event node is estimated. For the top event and the intermediate event nodes, the probability of the upper event is calculated according to the probability and logical relationship of the lower sub-events through the combination of Boolean algebra and logic gates. According to the structure of the above hierarchical fault tree model and the defined event probability, the failure probability of the above top event is calculated by transferring the probability from the bottom to the top. According to the calculated potential failure probability of the top event, the probability of failure of the power equipment due to local overheating is evaluated.
[0083] In some instances, a hierarchical fault tree model of power equipment is constructed to evaluate the probability of failure of power equipment due to local overheating. First, the top event is defined as the failure of power equipment due to local overheating. The system boundary is the power equipment involved and its related components. The first-level subtree can be constructed based on possible failure modes, including overload, short circuit and open circuit. Each failure mode is regarded as a sub-event node. Next, the subtree is refined step by step until the required accuracy and detail are achieved. For the overload sub-event node, various causes of overload can be considered, such as overcurrent, overload, etc. Based on historical failure statistics, the failure probability of the basic event node can be estimated. The failure probability of the overload event is 0.05, the failure probability of the short circuit event is 0.08, and the failure probability of the open circuit event is 0.03. Based on the combination of Boolean algebra and logic gates, the probability of the upper-level event can be calculated. The probability of overload and short circuit can be multiplied using AND gates to obtain the probability of causing local overheating. Assuming that overload and short circuit events occur independently, the probability of causing local overheating is 0.05*0.08=0.004. According to the structure of the hierarchical fault tree model and the defined event probability, the failure probability of the top event can be calculated by transferring the probability from the bottom layer to the top. If the circuit breaker event is the only cause of local overheating, the failure probability of the top event is 0.03. Based on the calculated potential failure probability of the top event, it can be assessed that the probability of failure of the power equipment due to local overheating is 0.03.
[0084] Step S205, inputting the temperature abnormality area of the above-mentioned power equipment into the hierarchical fault tree model to obtain the failure probability of the above-mentioned power equipment, and issuing an alarm message when the above-mentioned failure probability exceeds the probability threshold.
[0085] Specifically, the method can timely detect faults in power equipment, provide early warnings, avoid equipment damage or accidents, and thus ensure the safe operation of power equipment.
[0086] In some instances, based on the failure probability assessment results, if the failure probability of the target power equipment exceeds the major accident alarm threshold, the corresponding level of temperature abnormality alarm information is automatically generated. According to the failure probability, the power equipment risk ranking is compiled, the status data of maintenance feedback is obtained, and the failure probability assessment of the power equipment is updated in real time. If the latest status data verifies that the temperature is abnormal, the warning level is upgraded and risk isolation measures are taken. Failure probability assessment is implemented for relevant power equipment in the power grid area. Based on the failure probability assessment, it is determined whether the power equipment needs to be repaired in advance.
[0087] Among them, according to the risk assessment, the potential failure probability of a distribution transformer has reached 18.7%, exceeding the warning threshold of 15% for major accidents. The system automatically generates a high-level orange temperature abnormality warning. After seeing the warning, the on-duty personnel immediately checked the real-time operation data of the transformer and found that the load rate and oil temperature parameters showed a continuous upward trend, which preliminarily verified the temperature abnormality. According to the risk ranking list generated by the system, the transformer has the highest probability of failure, and the on-duty personnel arranged to go to the distribution station where the transformer is located for a detailed inspection first. The on-site inspection also found that the temperature at the electrical connection on the back of the transformer was significantly higher and needed to be dealt with immediately. So the backup transformer of the distribution station was immediately manually activated, and the original working transformer was withdrawn from operation through differential protection to complete the risk isolation. At the same time, the maintenance personnel were contacted to go to the site to check the cause of the transformer failure and handle it according to the regulations. In addition, the hot words of other transformers and switch cabinets in the same distribution station were checked and evaluated, and no abnormalities were found. However, it is recommended to appropriately reduce the heat resistance setting value of the transformer to prevent overheating from occurring again.
[0088] Wherein, after inputting the abnormal temperature area of the above-mentioned power equipment into the hierarchical fault tree model to obtain the failure probability of the above-mentioned power equipment, and issuing an alarm message when the above-mentioned failure probability exceeds the probability threshold, the above-mentioned method further includes the following steps:
[0089] Step S801, determining the operating state of the above-mentioned power equipment, the above-mentioned operating state includes: normal operating state, partial fault state of different levels and complete failure state;
[0090] Step S802, constructing a multi-state Markov model of the power equipment, and establishing a state transition probability matrix based on the multi-state Markov model according to the operating state of the power equipment to obtain the state transition probability of the power equipment, wherein the state transition probability matrix represents the probability of the power equipment transitioning between different states;
[0091] Step S803, determining the time distribution of the power equipment in each of the above operating states according to historical fault statistical data, and obtaining the state duration of the power equipment, wherein the time distribution includes exponential distribution or Weibull distribution;
[0092] Step S804, based on the state transition probability and the state duration, calculating the maintenance requirement probability of the electric power equipment in different operating states, the maintenance requirement probability indicating the probability that the electric power equipment needs maintenance in a certain state;
[0093] Step S805: evaluating the maintenance demand index of the power equipment according to the maintenance demand probability, wherein the maintenance demand index includes the average life and reliability parameter of the power equipment.
[0094] Specifically, the Gaussian mixture model is used to predict abnormal hot spots in power equipment with failure risks, and maintenance personnel are dispatched to the most dangerous power equipment for on-site inspection and verification on a priority basis. This method can reduce maintenance costs, effectively plan maintenance plans, and reduce maintenance costs and downtime.
[0095] Among them, the state of the power equipment is defined, including the normal operating state, the partial fault state of different levels and the complete failure state, and a multi-state Markov model of the power equipment is constructed. According to the definition of the power equipment state, a state transition probability matrix is established to describe the probability of the power equipment transferring between different states. According to the above historical fault statistics, the time distribution of the power equipment in each power equipment state is determined, and the above time distribution includes exponential distribution or Weibull distribution. Based on the state transition probability and state duration, the maintenance demand probability of the equipment in different states is calculated. The above maintenance demand probability represents the probability that the power equipment needs to be repaired in a certain state, which is calculated by accumulating the transition probability and the state duration. According to the above maintenance demand probability, the maintenance demand index of the power equipment is evaluated, and the above maintenance demand index includes the average life and reliability parameters. The different state transition probabilities are imported into the relevant nodes of the above hierarchical fault tree model to provide the above hierarchical fault tree model with the transition rules and state duration between the power equipment states, and the above hierarchical fault tree model provides the above multi-state Markov model with the failure probability and cause analysis.
[0096] In some instances, the states of power equipment can generally be divided into the following types: the normal operating state is that the power equipment can operate normally and provide the required power supply without any fault or failure. The partial fault state is that the power equipment may have different levels of partial faults, such as partial failure, performance degradation, etc. These faults may cause the function of the equipment to be affected to a certain extent, but the equipment can still continue to operate. The complete failure state is that the power equipment experiences a serious fault or complete failure and cannot continue to provide power supply, and needs to be repaired or replaced. According to the above definition, a multi-state Markov model of the power equipment can be constructed. The model can describe the probability of the power equipment transitioning between different states. There is a simple power equipment, including a normal operating state, a partial fault state, and a complete failure state. A 3x3 state transition probability matrix P can be defined, where P(i, j) represents the probability of the device transitioning from state i to state j. The probability of the power equipment transitioning to a partial fault state in the normal operating state is 0.001, and the probability of transitioning to a complete failure state is 0. In the partial failure state, the probability of transitioning to the normal operating state is 0.002, and the probability of transitioning to the complete failure state is 0.001. In the complete failure state, the probability of transferring to the normal operation state is 0, and the probability of transferring to the partial failure state is 0.003. Based on the historical failure statistics, the time distribution of the equipment in each state can be determined. The duration of the equipment in the normal operation state follows an exponential distribution with an average duration of 1000 hours; the duration in the partial failure state also follows an exponential distribution with an average duration of 500 hours; the duration in the complete failure state follows a Weibull distribution with a shape parameter of 2 and a scale parameter of 1000 hours. Based on the state transition probability and state duration, the maintenance demand probability of the equipment in different states can be calculated. The maintenance demand probability indicates the probability that the power equipment needs to be repaired in a certain state, which can be calculated by the cumulative transition probability and state duration. The maintenance demand probability of the equipment in the normal operation state is 0.001, which means that the equipment needs to be repaired once every 1000 hours on average in the normal operation state. The maintenance demand probability in the partial failure state is 0.002, which means that the equipment needs to be repaired once every 500 hours on average in the partial failure state. The maintenance demand probability in the complete failure state is 1, which means that the equipment needs to be repaired in the complete failure state. According to the probability of maintenance demand, the maintenance demand indicators of power equipment, such as average life and reliability parameters, can be evaluated. Average life indicates the average operating time of the equipment under different states, and reliability parameters indicate the reliability level of the equipment under different states. Importing the transition probabilities of different states into the relevant nodes of the hierarchical fault tree model can provide the hierarchical fault tree model with the transition rules and state duration between power equipment states.The hierarchical fault tree model can be used for reliability assessment and fault analysis based on the failure probability and cause analysis provided by the multi-state Markov model.
[0097] The grid area risk assessment method under the above-mentioned satellite perception of the present application firstly images the target area in the thermal infrared band to obtain the first satellite remote sensing image, and determines the temperature spatiotemporal distribution data of the surface area of the power equipment according to the first satellite remote sensing image, and the target area is provided with power equipment; then, the temperature gradient change of the surface area of the power equipment is dynamically monitored and collected according to the temperature spatiotemporal distribution data to obtain the temperature gradient data; then, the target area is imaged in the visible light band to obtain the second satellite remote sensing image, and the thermal map of the power equipment is obtained according to the first satellite remote sensing image and the second satellite remote sensing image; the temperature spatiotemporal distribution data is input into the Gaussian mixture model to obtain the predicted abnormal scores of each surface area of the power equipment, and the temperature abnormal area of the power equipment is determined according to the size of the predicted abnormal score and the preset score threshold; finally, the temperature abnormal area of the power equipment is input into the hierarchical fault tree model to obtain the failure probability of the power equipment, and when the failure probability exceeds the probability threshold, an alarm message is issued. The method can draw the thermal infrared map of the power equipment facilities, predict the abnormal hot spot area of the power equipment, and evaluate the failure probability of the power equipment due to local overheating. If the failure probability exceeds the limit, a temperature abnormal risk warning will be issued to the power equipment in the power grid area. In addition, it can also generate accurate temperature monitoring results for power equipment and provide corresponding failure probability assessment and maintenance demand forecasts, to achieve comprehensive monitoring and management of the operating status of power equipment, solving the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance.
[0098] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the power grid area risk assessment method under satellite perception of the present application will be described in detail below in combination with specific embodiments.
[0099] This embodiment relates to a specific method for assessing regional risk of a power grid under satellite perception, such as Figure 4 As shown, the following steps are included:
[0100] Step S1: Acquire a satellite remote sensing image in the thermal infrared band;
[0101] Step S2: non-destructively testing the temporal and spatial distribution data of the temperature of the power equipment and facilities by thermal infrared imaging technology;
[0102] Step S3: dynamically detect and collect temperature gradient changes on the surface area of the power equipment to obtain temperature gradient data;
[0103] Step S4: Draw a thermal diagram of the power equipment and facilities through Sobel operator and thermal map visualization;
[0104] Step S5: predicting abnormal hot spot areas of power equipment according to temperature threshold settings and Gaussian mixture models;
[0105] Step S6: constructing a hierarchical fault tree model of the power equipment to evaluate the failure probability of the power equipment due to local overheating;
[0106] Step S7: If the failure probability exceeds the limit, a temperature abnormality risk warning is issued to the power equipment in the power grid area;
[0107] Step S8: construct a multi-state Markov model of the power equipment to evaluate the maintenance demand of the power equipment.
[0108] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0109] The embodiment of the present application also provides a power grid area risk assessment device under satellite perception. It should be noted that the power grid area risk assessment device under satellite perception of the embodiment of the present application can be used to execute the power grid area risk assessment method under satellite perception provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0110] The following is an introduction to the power grid area risk assessment device under satellite perception provided in an embodiment of the present application.
[0111] Figure 5 Schematic diagram of a power grid area risk assessment device under satellite sensing according to an embodiment of the present application. Figure 5As shown, the device includes: a first processing unit 10, a collection unit 20, a second processing unit 30, a determination unit 40 and a third processing unit 50, the first processing unit 10 is used to perform imaging processing on the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determine the temperature spatiotemporal distribution data of the surface area of the power equipment according to the first satellite remote sensing image, and the power equipment is arranged in the target area; the collection unit 20 is used to dynamically monitor and collect the temperature gradient change of the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data; the second processing unit 30 is used to perform temperature spatiotemporal distribution processing on the target area in the visible light band The second satellite remote sensing image is obtained by imaging processing, and the thermal map of the above-mentioned power equipment is obtained according to the above-mentioned first satellite remote sensing image and the above-mentioned second satellite remote sensing image; the determination unit 40 is used to input the above-mentioned temperature spatiotemporal distribution data into the Gaussian mixture model, obtain the predicted abnormality score of each of the above-mentioned surface areas of the above-mentioned power equipment, and determine the temperature abnormality area of the above-mentioned power equipment according to the size of the above-mentioned predicted abnormality score and the preset score threshold; the third processing unit 50 is used to input the temperature abnormality area of the above-mentioned power equipment into the hierarchical fault tree model, obtain the failure probability of the above-mentioned power equipment, and issue an alarm message when the above-mentioned failure probability exceeds the probability threshold.
[0112] The above-mentioned power grid area risk assessment device under satellite perception of the present application includes: a first processing unit, a collection unit, a second processing unit, a determination unit and a third processing unit, the first processing unit is used to perform imaging processing on the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determine the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, and the target area is provided with power equipment; the collection unit is used to dynamically monitor and collect the temperature gradient change of the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data; the second processing unit is used to perform imaging processing on the target area in the visible light band to obtain a second satellite remote sensing image, and obtain a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; the determination unit is used to input the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the power equipment, and determine the temperature abnormal area of the power equipment according to the size of the predicted abnormal score and a preset score threshold; the third processing unit is used to input the temperature abnormal area of the power equipment into a hierarchical fault tree model to obtain the failure probability of the power equipment, and issue an alarm message when the failure probability exceeds the probability threshold. The device can draw thermal infrared images of power equipment facilities, predict abnormal hot spots of power equipment, and assess the probability of failure of power equipment due to local overheating. If the failure probability exceeds the limit, it will issue a temperature abnormality risk warning to the power equipment in the power grid area. In addition, it can also generate accurate power equipment temperature monitoring results, and provide corresponding failure probability assessment and maintenance demand forecasts, to achieve comprehensive monitoring and management of the operating status of power equipment, solving the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance.
[0113] In some examples, the first processing unit includes a first determination module, a first processing module, a first calculation module and a second processing module. The first determination module is used to determine the best time window for satellite shooting according to satellite orbit parameters and the geographical location information of the target area, and obtain the thermal infrared band satellite image within the time window; the first processing module is used to perform geometric correction and radiation calibration on the thermal infrared band satellite image to obtain the first satellite remote sensing image; the first calculation module is used to extract the pixel area of the power equipment in the first satellite remote sensing image, and calculate the radiation brightness of each pixel according to Planck's law, and convert the radiation brightness into surface temperature; the second processing module is used to obtain the temperature spatiotemporal distribution data of different parts of the power equipment according to the surface temperature corresponding to each of the above pixels. This method can eliminate image distortion and radiation noise.
[0114] In some examples, the acquisition unit includes a second determination module, a third determination module, a fourth determination module and a first acquisition module, wherein the second determination module is used to predict the change in the heat load of the above-mentioned power equipment according to the operating current of the above-mentioned power equipment, and determine the sampling frequency of temperature monitoring; the third determination module is used to determine the sampling method of temperature monitoring according to the equipment type of the above-mentioned power equipment; the fourth determination module is used to determine the heat source and heat dissipation path existing in the above-mentioned power equipment according to the surface geometry and structural characteristics of the above-mentioned power equipment, and determine the temperature sampling path according to the above-mentioned heat source and the above-mentioned heat dissipation path; the first acquisition module is used to dynamically monitor and collect the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data, the sampling frequency of the above-mentioned temperature monitoring, the sampling method of the above-mentioned temperature monitoring and the above-mentioned temperature sampling path. The sampling frequency, method and sampling path of temperature monitoring can be determined through various data of the power equipment, and the temperature gradient change can be collected according to the change in temperature. This method can optimize the collection path and collect temperature gradient data more accurately. The thermal map can intuitively display the heat distribution of the power equipment, which is helpful to analyze the working status and performance of the equipment and improve the efficiency and safety of the equipment operation.
[0115] In some examples, the second processing unit includes a second processing module, a third processing module, a first acquisition module and a fourth processing module. The second processing module is used to perform geometric correction and denoising preprocessing on the first satellite remote sensing image and the second satellite remote sensing image, respectively, to obtain a first processed image and a second processed image; the third processing module is used to extract the boundary contour of the power equipment in the first processed image using the Sobel operator to obtain the pixel area of the power equipment, and set a graded color table according to the actual surface temperature range of the power equipment, map and render the first processed image, and obtain a thermal infrared image; the first acquisition module is used to combine the geographic information system data to obtain the name and number attribute data of the power equipment, and mark the spatial position coordinate information of the power equipment on the second processed image to obtain a visible light image; the fourth processing module is used to add a temperature scale and a legend below the image according to the thermal infrared image and the visible light image, indicating the temperature values and meanings corresponding to different colors, and forming a thermal map of the power equipment, and the thermal map includes the spatial position, surface temperature distribution and identification information of the power equipment. The method can accurately predict the temperature abnormality area of the power equipment, improve the accuracy and efficiency of fault detection, and help personnel take measures in advance.
[0116] In some examples, the determination unit includes a second acquisition module, a first training module, a fifth processing module, a fifth determination module and a sixth determination module, wherein the second acquisition module is used to acquire historical temperature distribution data, and use the Bayesian information criterion to select the optimal model parameters and the number of Gaussian distributions to construct an initial Gaussian model; the first training module is used to input the above historical temperature distribution data into the above initial Gaussian model for training to obtain the above Gaussian mixture model, wherein the above historical temperature distribution data is a mixture distribution composed of several Gaussian distributions; the fifth processing module is used to input the above temperature spatiotemporal distribution data into the Gaussian mixture model to obtain the predicted abnormality score of each of the above surface areas of the above power equipment; the fifth determination module is used to determine the above surface area as the above temperature abnormality area when the above predicted abnormality score is greater than the above preset score threshold; the sixth determination module is used to determine the above surface area as the non-temperature abnormality area when the above predicted abnormality score is less than or equal to the above preset score threshold. The historical failure mode and overheating cause of the power equipment can be clearly displayed, helping analysts to better understand the potential failure mechanism, and the combination operation of Boolean algebra and logic gates can accurately calculate the probability of each layer event.
[0117] In some instances, the device further includes a first construction module, a sixth processing module, a second calculation module and a second construction module, wherein the first construction module is used to construct a first-level subtree according to the historical local overheating causes and historical failure modes of the power equipment before inputting the abnormal temperature area of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, and taking different failure modes as sub-event nodes, and for each of the above failure modes, the subtree is refined step by step, and the sub-event nodes include at least overload, short circuit and open circuit; the sixth processing module is used to preset the failure probability of the basic event node according to the historical local overheating causes and historical failure modes of the power equipment; the second calculation module is used to use a combination of Boolean algebra and logic gates to calculate the probability of the upper-level event according to the probability and logical relationship of the lower-level sub-events; the second construction module is used to calculate the failure probability of the top event by transferring the probability from the bottom layer to the top layer according to the structure of the hierarchical fault tree model and the defined event probability, so as to construct the hierarchical fault tree model. By constructing a hierarchical fault tree model, the historical failure modes and overheating causes of power equipment can be clearly displayed, helping analysts to better understand the potential failure mechanisms. By using a combination of Boolean algebra and logic gates, the probability of events at each layer can be accurately calculated.
[0118] In some instances, the device further includes a seventh determination module, a third construction module, an eighth determination module, a third calculation module and a first evaluation module, wherein the seventh determination module is used to input the temperature abnormality area of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, and when the failure probability exceeds the probability threshold, after issuing an alarm message, determine the operating state of the power equipment, wherein the operating state includes: normal operating state, partial failure state of different levels and complete failure state; the third construction module is used to construct a multi-state Markov model of the power equipment, and based on the multi-state Markov model, establish a state transition probability matrix according to the operating state of the power equipment to obtain the state transition probability of the power equipment, The state transition probability matrix represents the probability of the above-mentioned power equipment transferring between different states; the eighth determination module is used to determine the time distribution of the above-mentioned power equipment in each of the above-mentioned operating states according to historical fault statistical data, and obtain the state duration of the above-mentioned power equipment, and the above-mentioned time distribution includes exponential distribution or Weibull distribution; the third calculation module is used to calculate the maintenance demand probability of the above-mentioned power equipment in different operating states based on the above-mentioned state transition probability and the above-mentioned state duration, and the above-mentioned maintenance demand probability represents the probability that the power equipment needs to be repaired in a certain state; the first evaluation module is used to evaluate the maintenance demand index of the above-mentioned power equipment according to the above-mentioned maintenance demand probability, and the above-mentioned maintenance demand index includes the average life and reliability parameters of the above-mentioned power equipment. This method can reduce maintenance costs, can effectively plan maintenance plans, and reduce maintenance costs and downtime.
[0119] The above-mentioned power grid area risk assessment device under satellite perception includes a processor and a memory. The above-mentioned acquisition units, etc. are stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in any combination.
[0120] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the risk of power equipment failure in advance.
[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0122] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid area risk assessment method under the satellite perception.
[0123] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the power grid area risk assessment method under satellite perception when running.
[0124] Specifically, the power grid regional risk assessment method under satellite perception includes:
[0125] Step S201, imaging a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of a surface area of the power equipment according to the first satellite remote sensing image, wherein the power equipment is arranged in the target area;
[0126] Specifically, by analyzing the spatiotemporal distribution data of temperature on the surface of power equipment, abnormal conditions of power equipment can be discovered in a timely manner, providing a scientific basis for equipment maintenance and fault handling.
[0127] Step S202, dynamically monitoring and collecting the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data to obtain temperature gradient data;
[0128] Specifically, through dynamic monitoring, the temperature gradient changes in the surface area of the power equipment can be understood in a timely manner, which helps to detect abnormal situations in a timely manner and take corresponding measures, thereby improving the safety of the power equipment.
[0129] Step S203, performing imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image;
[0130] Specifically, this method can realize remote monitoring and diagnosis of power equipment, reduce the workload and risk of manual inspections, and improve the management efficiency and reliability of power equipment.
[0131] Step S204, inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each of the surface areas of the power equipment, and determining a temperature abnormal area of the power equipment according to a difference between the predicted abnormal score and a preset score threshold;
[0132] Specifically, the Gaussian mixture model is used to accurately predict the temperature anomaly area of the power equipment, improving the accuracy and efficiency of fault detection. At the same time, this method can effectively identify and locate the abnormal area of the power equipment, helping maintenance personnel to quickly take corresponding measures.
[0133] Step S205, inputting the temperature abnormality area of the above-mentioned power equipment into the hierarchical fault tree model to obtain the failure probability of the above-mentioned power equipment, and issuing an alarm message when the above-mentioned failure probability exceeds the probability threshold.
[0134] Specifically, the method can timely detect faults in power equipment, provide early warnings, avoid equipment damage or accidents, and thus ensure the safe operation of power equipment.
[0135] An embodiment of the present invention provides a device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:
[0136] Step S201, imaging a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of a surface area of the power equipment according to the first satellite remote sensing image, wherein the power equipment is arranged in the target area;
[0137] Specifically, by analyzing the spatiotemporal distribution data of temperature on the surface of power equipment, abnormal conditions of power equipment can be discovered in a timely manner, providing a scientific basis for equipment maintenance and fault handling.
[0138] Step S202, dynamically monitoring and collecting the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data to obtain temperature gradient data;
[0139] Specifically, through dynamic monitoring, the temperature gradient changes in the surface area of the power equipment can be understood in a timely manner, which helps to detect abnormal situations in a timely manner and take corresponding measures, thereby improving the safety of the power equipment.
[0140] Step S203, performing imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image;
[0141] Specifically, this method can realize remote monitoring and diagnosis of power equipment, reduce the workload and risk of manual inspections, and improve the management efficiency and reliability of power equipment.
[0142] Step S204, inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each of the surface areas of the power equipment, and determining a temperature abnormal area of the power equipment according to a difference between the predicted abnormal score and a preset score threshold;
[0143] Specifically, the Gaussian mixture model is used to accurately predict the temperature anomaly area of the power equipment, improving the accuracy and efficiency of fault detection. At the same time, this method can effectively identify and locate the abnormal area of the power equipment, helping maintenance personnel to quickly take corresponding measures.
[0144] Step S205, inputting the temperature abnormality area of the above-mentioned power equipment into the hierarchical fault tree model to obtain the failure probability of the above-mentioned power equipment, and issuing an alarm message when the above-mentioned failure probability exceeds the probability threshold.
[0145] Specifically, the method can timely detect faults in power equipment, provide early warnings, avoid equipment damage or accidents, and thus ensure the safe operation of power equipment.
[0146] The devices in this article can be servers, PCs, PADs, mobile phones, etc.
[0147] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with at least the following method steps: Step S201, imaging a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, wherein the power equipment is arranged in the target area;
[0148] Specifically, by analyzing the spatiotemporal distribution data of temperature on the surface of power equipment, abnormal conditions of power equipment can be discovered in a timely manner, providing a scientific basis for equipment maintenance and fault handling.
[0149] Step S202, dynamically monitoring and collecting the temperature gradient change of the surface area of the above-mentioned power equipment according to the above-mentioned temperature spatiotemporal distribution data to obtain temperature gradient data;
[0150] Specifically, through dynamic monitoring, the temperature gradient changes in the surface area of the power equipment can be understood in a timely manner, which helps to detect abnormal situations in a timely manner and take corresponding measures, thereby improving the safety of the power equipment.
[0151] Step S203, performing imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image;
[0152] Specifically, this method can realize remote monitoring and diagnosis of power equipment, reduce the workload and risk of manual inspections, and improve the management efficiency and reliability of power equipment.
[0153] Step S204, inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each of the surface areas of the power equipment, and determining a temperature abnormal area of the power equipment according to a difference between the predicted abnormal score and a preset score threshold;
[0154] Specifically, the Gaussian mixture model is used to accurately predict the temperature anomaly area of the power equipment, improving the accuracy and efficiency of fault detection. At the same time, this method can effectively identify and locate the abnormal area of the power equipment, helping maintenance personnel to quickly take corresponding measures.
[0155] Step S205, inputting the temperature abnormality area of the above-mentioned power equipment into the hierarchical fault tree model to obtain the failure probability of the above-mentioned power equipment, and issuing an alarm message when the above-mentioned failure probability exceeds the probability threshold.
[0156] Specifically, the method can timely detect faults in power equipment, provide early warnings, avoid equipment damage or accidents, and thus ensure the safe operation of power equipment.
[0157] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0158] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0159] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0160] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0162] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0163] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0164] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0165] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0166] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:
[0167] 1) The above-mentioned power grid area risk assessment method under satellite perception of the present application first images the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determines the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, and the power equipment is arranged in the target area; then, the temperature gradient change of the surface area of the power equipment is dynamically monitored and collected based on the temperature spatiotemporal distribution data to obtain temperature gradient data; then, the target area is imaged in the visible light band to obtain a second satellite remote sensing image, and a thermal map of the power equipment is obtained based on the first satellite remote sensing image and the second satellite remote sensing image; the temperature spatiotemporal distribution data is input into a Gaussian mixture model to obtain the predicted abnormality score of each surface area of the power equipment, and the temperature abnormality area of the power equipment is determined based on the size of the predicted abnormality score and the preset score threshold; finally, the temperature abnormality area of the power equipment is input into a hierarchical fault tree model to obtain the failure probability of the power equipment, and when the failure probability exceeds the probability threshold, an alarm message is issued. This method can draw thermal infrared images of power equipment facilities, predict abnormal hot spots of power equipment, and assess the failure probability of power equipment due to local overheating. If the failure probability exceeds the limit, it will issue a temperature abnormality risk warning for the power equipment in the power grid area. In addition, it can also generate accurate power equipment temperature monitoring results, and provide corresponding failure probability assessment and maintenance demand prediction, to achieve comprehensive monitoring and management of the operating status of power equipment, solving the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance.
[0168] 2) The power grid area risk assessment device under the above-mentioned satellite perception of the present application includes: a first processing unit, a collection unit, a second processing unit, a determination unit and a third processing unit. The first processing unit is used to perform imaging processing on the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determine the temperature spatiotemporal distribution data of the surface area of the power equipment based on the first satellite remote sensing image, and the target area is provided with power equipment; the collection unit is used to dynamically monitor and collect the temperature gradient change of the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data; the second processing unit is used to perform imaging processing on the target area in the visible light band to obtain a second satellite remote sensing image, and obtain a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; the determination unit is used to input the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the power equipment, and determine the temperature abnormal area of the power equipment according to the size of the predicted abnormal score and the preset score threshold; the third processing unit is used to input the temperature abnormal area of the power equipment into a hierarchical fault tree model to obtain the failure probability of the power equipment, and issue an alarm message when the failure probability exceeds the probability threshold. The device can draw thermal infrared images of power equipment facilities, predict abnormal hot spots of power equipment, and assess the probability of failure of power equipment due to local overheating. If the failure probability exceeds the limit, it will issue a temperature abnormality risk warning to the power equipment in the power grid area. In addition, it can also generate accurate power equipment temperature monitoring results, and provide corresponding failure probability assessment and maintenance demand forecasts, to achieve comprehensive monitoring and management of the operating status of power equipment, solving the problem that traditional inspection and monitoring methods are inefficient and blind, resulting in the inability to accurately assess the failure risk of power equipment in advance.
[0169] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A method for risk assessment of power grid area based on satellite perception. It is characterized in that include: Performing imaging processing on the target area in a thermal infrared band to obtain a first satellite remote sensing image, and determining the spatiotemporal distribution data of the temperature of the surface area of the electric power equipment according to the first satellite remote sensing image, wherein the electric power equipment is arranged in the target area; Dynamically monitor and collect temperature gradient changes on the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data; Performing imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtaining a thermal map of the electric power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; Inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the power equipment, and determining the temperature abnormal area of the power equipment according to the magnitude of the predicted abnormal score and a preset score threshold; The temperature abnormality area of the power equipment is input into a hierarchical fault tree model to obtain the failure probability of the power equipment, and when the failure probability exceeds a probability threshold, an alarm message is issued.
2. The method according to claim 1, It is characterized in that Performing imaging processing on the target area in the thermal infrared band to obtain a first satellite remote sensing image, and determining the temperature spatiotemporal distribution data of the surface area of the power equipment according to the first satellite remote sensing image, including: Determine the best time window for satellite photography based on satellite orbit parameters and geographic location information of the target area, and obtain thermal infrared band satellite images within the time window; Performing geometric correction and radiometric calibration on the thermal infrared band satellite image to obtain the first satellite remote sensing image; Extracting a pixel area of the electric power equipment in the first satellite remote sensing image, calculating the radiation brightness of each pixel according to Planck's law, and converting the radiation brightness into a surface temperature; According to the surface temperature corresponding to each pixel, the spatiotemporal distribution data of the temperature of different parts of the electric power equipment are obtained.
3. The method according to claim 1, It is characterized in that Dynamically monitoring and collecting the temperature gradient change of the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data, including: Predicting the change in the heat load of the power equipment according to the operating current of the power equipment, and determining the sampling frequency of temperature monitoring; Determining a sampling method for temperature monitoring according to the equipment type of the electric power equipment; Determine a heat source and a heat dissipation path in the power equipment according to the surface geometry and structural characteristics of the power equipment, and determine a temperature sampling path according to the heat source and the heat dissipation path; According to the temperature spatiotemporal distribution data, the temperature monitoring sampling frequency, the temperature monitoring sampling method and the temperature sampling path, the temperature gradient change in the surface area of the power equipment is dynamically monitored and collected.
4. The method according to claim 1, It is characterized in that The target area is imaged in a visible light band to obtain a second satellite remote sensing image, and a thermal map of the power equipment is obtained based on the first satellite remote sensing image and the second satellite remote sensing image, including: Performing geometric correction and denoising preprocessing on the first satellite remote sensing image and the second satellite remote sensing image respectively to obtain a first processed image and a second processed image; Using the Sobel operator to extract the boundary contour of the power equipment in the first processed image to obtain the pixel area of the power equipment, and setting a graded color table according to the actual surface temperature range of the power equipment, mapping and rendering the first processed image to obtain a thermal infrared image; In combination with geographic information system data, the name and number attribute data of the power equipment are obtained, and the spatial position coordinate information of the power equipment is marked on the second processed image to obtain a visible light image; According to the thermal infrared image and the visible light image, a temperature scale and a legend are added below the image to indicate the temperature values and meanings corresponding to different colors, so as to form a thermal map of the power equipment, which includes the spatial position, surface temperature distribution and identification information of the power equipment.
5. The method according to claim 1, It is characterized in that Inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the power equipment, and determining the temperature abnormal area of the power equipment according to the magnitude of the predicted abnormal score and a preset score threshold, including: Obtain historical temperature distribution data, and use the Bayesian information criterion to select the optimal model parameters and the number of Gaussian distributions to construct an initial Gaussian model; Inputting the historical temperature distribution data into the initial Gaussian model for training to obtain the Gaussian mixture model, wherein the historical temperature distribution data is a mixture distribution composed of several Gaussian distributions; Inputting the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormality score for each surface area of the power equipment; In a case where the predicted anomaly score is greater than the preset score threshold, determining the surface area as the temperature anomaly area; When the predicted abnormality score is less than or equal to the preset score threshold, the surface area is determined as a non-temperature abnormality area.
6. The method according to claim 1, It is characterized in that Before inputting the abnormal temperature region of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, the method further includes: According to the historical local overheating causes and historical failure modes of the power equipment, a first-level subtree is constructed, different failure modes are used as sub-event nodes, and for each failure mode, the subtree is refined step by step, and the sub-event nodes include at least overload, short circuit and open circuit; Presetting the failure probability of the basic event node according to the historical local overheating causes and historical failure modes of the power equipment; The combination of Boolean algebra and logic gates is used to calculate the probability of the upper-level event based on the probability and logical relationship of the lower-level sub-events; According to the structure of the hierarchical fault tree model and the defined event probabilities, the hierarchical fault tree model is constructed by calculating the failure probability of the top event through probability transfer from the bottom layer upwards.
7. The method according to claim 1, It is characterized in that After inputting the abnormal temperature region of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, and issuing an alarm message when the failure probability exceeds a probability threshold, the method further includes: Determine the operating state of the power equipment, the operating state including: normal operating state, partial failure state of different levels and complete failure state; Constructing a multi-state Markov model of the power device, and establishing a state transition probability matrix based on the multi-state Markov model according to the operating state of the power device to obtain the state transition probability of the power device, wherein the state transition probability matrix represents the probability of the power device transitioning between different states; Determine the time distribution of the power equipment in each of the operating states according to historical fault statistical data to obtain the state duration of the power equipment, wherein the time distribution includes exponential distribution or Weibull distribution; Based on the state transition probability and the state duration, calculating the maintenance requirement probability of the power equipment in different operating states, the maintenance requirement probability indicating the probability that the power equipment needs maintenance in a certain state; According to the maintenance requirement probability, a maintenance requirement index of the electric power equipment is evaluated, wherein the maintenance requirement index includes an average life span and a reliability parameter of the electric power equipment.
8. A satellite-based power grid regional risk assessment device. It is characterized in that include: A first processing unit is used to perform imaging processing on a target area in a thermal infrared band to obtain a first satellite remote sensing image, and determine the temperature spatiotemporal distribution data of a surface area of an electric power device according to the first satellite remote sensing image, wherein the electric power device is arranged in the target area; A collection unit, used to dynamically monitor and collect temperature gradient changes in the surface area of the power equipment according to the temperature spatiotemporal distribution data to obtain temperature gradient data; A second processing unit is used to perform imaging processing on the target area in a visible light band to obtain a second satellite remote sensing image, and obtain a thermal map of the power equipment based on the first satellite remote sensing image and the second satellite remote sensing image; A determination unit, configured to input the temperature spatiotemporal distribution data into a Gaussian mixture model to obtain a predicted abnormal score of each surface area of the electric equipment, and determine a temperature abnormal area of the electric equipment according to a difference between the predicted abnormal score and a preset score threshold; The third processing unit is used to input the temperature abnormality area of the power equipment into the hierarchical fault tree model to obtain the failure probability of the power equipment, and issue an alarm message when the failure probability exceeds a probability threshold.
9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid area risk assessment method under satellite perception as described in any one of claims 1 to 7.
10. An electronic device, It is characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the satellite-aware power grid area risk assessment method as described in any one of claims 1 to 7.
Citation Information
Cited By
Power equipment risk identification method and system
CN119322995A
Water heating pipeline maintenance detection method and system
CN119844713A
Substation equipment temperature measurement method and system based on visible light guidance
CN120043640A
Instant remote sensing satellite constellation system
CN121366364A
Low-voltage switch temperature abnormity early warning system and early warning method based on time sequence prediction
CN121878447A
