Multi-source data monitoring processing method and system of GIS equipment

Abstract

The invention discloses a multi-source data monitoring processing method and system for GIS equipment. The method comprises the steps that environmental influence data corresponding to the insulation characteristic of target GIS equipment and density data and pressure data of internal gas of the target GIS equipment in the operation process are obtained in real time; inputting the environmental influence data, the density data and the pressure data into a pre-constructed insulation monitoring model to obtain an insulation prediction result of the target GIS equipment, and correspondingly generating a fault processing signal according to the insulation prediction result; executing a contact fault monitoring mode and a high temperature fault monitoring mode in response to the fault processing signal; in the contact fault monitoring mode, obtaining a contact fault result of the target GIS equipment; in the high-temperature fault monitoring mode, determining a high-temperature region fault result of the target GIS equipment; and executing a corresponding GIS equipment fault processing strategy based on the obtained contact fault result and / or the high-temperature area fault result. According to the method provided by the invention, the recognition precision of the GIS equipment fault is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a multi-source data monitoring and processing method and system for GIS devices. Background Art

[0002] With the continuous expansion of the scale of the power system, gas-insulated switchgear (GIS) has become the core equipment of modern substations due to its characteristics such as compact structure and high reliability. However, GIS devices operate in complex environments such as high voltage and strong electromagnetic fields for a long time, and are vulnerable to multiple faults such as mechanical wear, insulation deterioration, and partial discharge.

[0003] Traditional monitoring means only analyze the density data of GIS devices detected to determine whether a fault occurs. This monitoring method is difficult to accurately determine the fault location of GIS devices, and still requires maintenance personnel to further analyze, resulting in poor overall monitoring effects and greatly reduced maintenance efficiency.

[0004] Therefore, how to accurately monitor the fault location of GIS devices to improve the maintenance efficiency has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] The present invention provides a multi-source data monitoring and processing method and system for GIS devices to solve the technical problem of how to accurately monitor the fault location of GIS devices, thereby improving the maintenance efficiency of GIS devices.

[0006] To solve the above technical problem, an embodiment of the present invention provides a multi-source data monitoring and processing method for GIS devices, including: Real-time obtaining environmental impact data corresponding to the insulation characteristics of a target GIS device, as well as density data and pressure data of the internal gas of the target GIS device during operation; Inputting the environmental impact data, the density data, and the pressure data into a pre-constructed insulation monitoring model to obtain an insulation prediction result of the target GIS device, and generating a fault handling signal according to the insulation prediction result; Responding to the fault handling signal, executing a contact fault monitoring mode and a high-temperature fault monitoring mode; In the contact fault monitoring mode, based on the corner detection algorithm, locating the contact feature points of the circuit breaker of the target GIS device in the acquired image dataset, determining the trajectory information of the contact feature points under selected typical working conditions based on the optical flow method, and performing intelligent recognition on the trajectory information to obtain the contact fault result of the target GIS device; In the high-temperature fault monitoring mode, identify the abnormal high-temperature area of the GIS device based on the real-time acquired infrared image dataset, compare the abnormal high-temperature area based on the partial discharge signal detection data within the abnormal high-temperature area, and determine the high-temperature area fault result of the target GIS device based on the comparison result; Based on the obtained contact fault result and / or the high-temperature area fault result, execute the corresponding GIS device fault handling strategy.

[0007] As one of the preferred solutions, the environmental impact data includes: temperature data and humidity data; Before inputting the environmental impact data, the density data, and the pressure data into the pre-constructed insulation monitoring model, it further includes: Obtain the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the gas inside the target GIS device; Perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data based on the interpolation processing algorithm to obtain multi-source monitoring data; Construct an initial insulation monitoring model based on the random forest algorithm, and input the multi-source monitoring data into the initial insulation monitoring model for training to obtain a trained insulation monitoring model.

[0008] As one of the preferred solutions, the insulation prediction result includes the material aging rate and the internal gas insulation strength of the target GIS device; The corresponding generation of the fault handling signal according to the insulation prediction result includes: Compare the material aging rate with a preset aging rate threshold. If the material aging rate is greater than the aging rate threshold, generate the fault handling signal; Or compare the internal gas insulation strength with a preset insulation strength threshold. If the internal gas insulation strength is less than the insulation strength threshold, generate the fault handling signal.

[0009] As one of the preferred solutions, the positioning and acquisition of the contact characteristic points of the circuit breaker of the target GIS device in the image dataset obtained according to the corner detection algorithm includes: Perform grayscale conversion, filtering, and edge detection processing on the image dataset in sequence to obtain an image dataset to be extracted, and the image dataset to be extracted includes several consecutive frames of images to be extracted; Calculate the autocorrelation matrix of each pixel point in the image to be extracted, and calculate the corner response function value according to the eigenvalues of the autocorrelation matrix; Pixels with corner response function values greater than a preset threshold are taken as corner points to construct a corner point dataset. According to the obtained position characteristics and shape characteristics of the contacts of the circuit breaker, the corner points belonging to the contacts of the circuit breaker in the corner point dataset are selected as the contact feature points.

[0010] As one of the preferred solutions, the trajectory information includes moving speed and moving time; The method for determining the trajectory information of the contact feature points under selected typical working conditions based on the optical flow method includes: Obtain the coordinate positions of the contact feature points in each frame of the image dataset to be extracted; Based on the coordinate positions of the adjacent frames of the images to be extracted, calculate the displacement data of the feature points between adjacent frames; Obtain the time interval data between adjacent frames, and calculate the moving speed and moving time of the contact feature points according to the displacement data and the time interval data.

[0011] As one of the preferred solutions, the method for performing intelligent recognition on the trajectory information to obtain the contact fault result of the target GIS device includes: If the moving time is greater than a preset time threshold, it is determined that the circuit breaker of the target GIS device fails; Or if the moving speed is less than a preset speed threshold, it is determined that the circuit breaker of the target GIS device fails.

[0012] As one of the preferred solutions, the method for identifying the abnormal high-temperature area of the GIS device according to the real-time obtained infrared image dataset includes: Perform image enhancement and noise removal processing on the infrared image dataset in sequence to obtain the image to be identified; Perform binarization processing on the image to be identified based on a pre-selected binarization threshold to obtain a binarized image, and identify the abnormal high-temperature area of the target GIS device according to the binarized image.

[0013] As one of the preferred solutions, the method for comparing the abnormal high-temperature area based on the partial discharge signal detection data in the abnormal high-temperature area and determining the high-temperature area fault result of the target GIS device based on the comparison result includes: Obtain the partial discharge signal of the target GIS device based on a partial discharge acquisition device, and perform filtering processing on the partial discharge signal; Synchronize the time of the filtered partial discharge signal with the infrared image data generated based on the high-temperature area. Perform correlation analysis on the infrared image data and the partial discharge signal after time synchronization, determine the fault type according to the analysis result, and generate a high-temperature area fault result corresponding to the fault type.

[0014] As one of the preferred solutions, the execution of the corresponding GIS device fault handling strategy further includes: Establish a fault type - handling measure mapping knowledge base; Perform fuzzy logic comprehensive evaluation on the contact fault result and the high-temperature area fault result according to the fault type - handling measure mapping knowledge base, and calculate the fault confidence level; When the fault confidence level exceeds a preset first confidence threshold, execute the GIS device fault handling strategy generated based on the fault type - handling measure mapping knowledge base.

[0015] Another embodiment of the present invention provides a multi-source data monitoring and processing system for GIS devices, including: An acquisition module, configured to acquire in real time environmental impact data corresponding to the insulation characteristics of a target GIS device, as well as density data and pressure data of the internal gas of the target GIS device during operation; An insulation monitoring module, configured to input the environmental impact data, the density data, and the pressure data into a pre-constructed insulation monitoring model to obtain an insulation prediction result of the target GIS device, and generate a fault handling signal according to the insulation prediction result; A response module, configured to execute a contact fault monitoring mode and a high-temperature fault monitoring mode in response to the fault handling signal; A first identification module, configured to, in the contact fault monitoring mode, locate the contact feature points of the circuit breaker of the target GIS device in the acquired image dataset according to the corner detection algorithm, determine the trajectory information of the contact feature points under selected typical working conditions based on the optical flow method, and perform intelligent identification on the trajectory information to obtain the contact fault result of the target GIS device; A second identification module, configured to, in the high-temperature fault monitoring mode, identify the abnormal high-temperature area of the GIS device according to the acquired infrared image dataset in real time, compare the abnormal high-temperature area based on the partial discharge signal detection data in the abnormal high-temperature area, and determine the high-temperature area fault result of the target GIS device based on the comparison result; An execution module, configured to execute the corresponding GIS device fault handling strategy based on the obtained contact fault result and / or the high-temperature area fault result.

[0016] As one of the preferred solutions, the environmental impact data includes: temperature data and humidity data; The insulation monitoring module is further configured to: Obtain the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the gas inside the target GIS device; Perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data based on the interpolation processing algorithm to obtain multi-source monitoring data; Construct an initial insulation monitoring model based on the random forest algorithm, and input the multi-source monitoring data into the initial insulation monitoring model for training to obtain a trained insulation monitoring model.

[0017] As one of the preferred solutions, the insulation prediction result includes the material aging speed and the internal gas insulation strength of the target GIS device; The insulation monitoring module is further configured to: Compare the material aging speed with a preset aging speed threshold. If the material aging speed is greater than the aging speed threshold, generate the fault handling signal; Or compare the internal gas insulation strength with a preset insulation strength threshold. If the internal gas insulation strength is less than the insulation strength threshold, generate the fault handling signal.

[0018] As one of the preferred solutions, the first recognition module is further configured to: Perform gray conversion, filtering, and edge detection processing on the image data set in sequence to obtain a to-be-extracted image data set, and the to-be-extracted image data set includes to-be-extracted images of several consecutive frames; Calculate the autocorrelation matrix of each pixel point in the to-be-extracted image, and calculate the corner response function value according to the eigenvalues of the autocorrelation matrix; Take the pixel points with the corner response function value greater than the preset threshold as corners to construct a corner data set, and filter out the corners belonging to the breaker contact in the corner data set as the contact feature points according to the position characteristics and shape characteristics of the contact of the breaker obtained.

[0019] As one of the preferred solutions, the trajectory information includes the moving speed and the moving time; The first recognition module is further configured to: Obtain the coordinate positions of the contact feature points in each frame of the to-be-extracted image in the image data set; Calculate the displacement data of the feature points between adjacent frames based on the coordinate positions of the to-be-extracted images of adjacent frames; Obtain the time interval data between adjacent frames, and calculate the moving speed and moving time of the contact feature points according to the displacement data and the time interval data.

[0020] As one of the preferred solutions, the first recognition module is further configured to: If the moving time is greater than a preset time threshold, determine that there is a circuit breaker fault in the target GIS device; Or if the moving speed is less than a preset speed threshold, determine that there is a circuit breaker fault in the target GIS device.

[0021] As one of the preferred solutions, the second recognition module is further configured to: Perform image enhancement and noise removal processing on the infrared image dataset in sequence to obtain an image to be recognized; Perform binarization processing on the image to be recognized based on a pre-selected binarization threshold to obtain a binarized image, and recognize the abnormal high-temperature area of the target GIS device according to the binarized image.

[0022] As one of the preferred solutions, the second recognition module is further configured to: Acquire the partial discharge signal of the target GIS device based on a partial discharge acquisition device, and perform filtering processing on the partial discharge signal; Synchronize the time of the filtered partial discharge signal with the infrared image data generated based on the high-temperature area; Perform correlation analysis on the infrared image data and the partial discharge signal after time synchronization, and determine the fault type according to the analysis result, and generate a high-temperature area fault result corresponding to the fault type.

[0023] As one of the preferred solutions, the execution module is further configured to: Establish a fault type - treatment measure mapping knowledge base; Perform fuzzy logic comprehensive evaluation on the contact fault result and the high-temperature area fault result according to the fault type - treatment measure mapping knowledge base, and calculate the fault confidence level; When the fault confidence level exceeds a preset first confidence threshold, execute the GIS device fault treatment strategy generated based on the fault type - treatment measure mapping knowledge base.

[0024] Another embodiment of the present invention provides a multi-source data monitoring and processing device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned multi-source data monitoring and processing method is implemented.

[0025] Another embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the device where the computer-readable storage medium is located executes the computer program, the above-mentioned multi-source data monitoring and processing method is implemented.

[0026] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: (1) The present invention processes and analyzes multi-source data based on a pre-constructed insulation monitoring model, generates insulation prediction results and fault handling signals based on the data, and then executes corresponding fault monitoring modes and handling strategies, avoiding the subjectivity and uncertainty of human judgment, and making fault diagnosis and handling more scientific and accurate.

[0027] (2) The present invention provides accurate fault information and handling basis for operation and maintenance personnel, helps operation and maintenance personnel formulate and implement operation and maintenance plans targeted, reasonably arrange maintenance resources and time, avoids blind inspection and over-maintenance, improves the efficiency and quality of operation and maintenance work, and realizes the transformation from traditional regular maintenance to state-based intelligent maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic flow chart of a method for monitoring and processing multi-source data of a GIS device in one embodiment of the present invention; Figure 2 is a schematic diagram of a system for monitoring and processing multi-source data of a GIS device in one embodiment of the present invention; Figure 3 is a schematic diagram of a device for monitoring and processing multi-source data of a GIS device in one embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0030] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0031] In the description of this application, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0032] In the description of this application, it should be noted that unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as those commonly understood by those skilled in the technical field to which this invention belongs. The terms used in the specification of this invention are only for the purpose of describing specific embodiments, and are not intended to limit this invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0033] An embodiment of the present invention provides a multi-source data monitoring and processing method for a GIS device. Specifically, please refer to Figure 1 , Figure 1 which shows a schematic flow chart of the multi-source data monitoring and processing method for a GIS device in one of the embodiments of the present invention, and it includes steps S1 - S6: S1: Real-time obtain the environmental impact data corresponding to the insulation characteristics of the target GIS device, as well as the density data and pressure data of the internal gas during the operation of the target GIS device; Real-time collect a variety of data related to the insulation characteristics of the target GIS (Gas-Insulated Switchgear) device. Among them, the environmental impact data plays an important role in the insulation performance of the device. For example, changes in temperature and humidity will affect the performance of insulation materials. At the same time, the density data and pressure data of the internal gas during the operation of the device are also obtained in real time, because GIS devices usually use insulating gases (such as sulfur hexafluoride) to achieve functions such as electrical insulation and arc extinguishing, and the density and pressure of the gas are directly related to its insulation performance. For example, when the gas pressure drops to a certain extent, it may lead to a decline in insulation performance and increase the risk of equipment failure.

[0034] Preferably, in an embodiment of the present invention, the environmental impact data includes: temperature data and humidity data; Before inputting environmental impact data, density data, and pressure data into a pre-built insulation monitoring model, it further includes: Obtain the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the gas inside the target GIS device; Based on the interpolation processing algorithm, perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data to obtain multi-source monitoring data; Based on the interpolation processing algorithm, perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data to obtain multi-source monitoring data; Construct an initial insulation monitoring model based on the random forest algorithm, and input the multi-source monitoring data into the initial insulation monitoring model for training to obtain a trained insulation monitoring model.

[0035] Among them, since the obtained historical environmental impact data, historical density data, and historical pressure data may come from different monitoring devices or systems, their acquisition time intervals and start times may not be consistent. If these data are directly used, it may lead to chaos in the time dimension of the data, unable to accurately reflect the correlation between the data, and thus affect the accuracy of the insulation monitoring model. Therefore, time alignment processing is required. Perform time alignment on the above three types of historical data through the interpolation processing algorithm. The basic principle of the interpolation algorithm is to construct a function between the known data points to estimate the values of the unknown points.

[0036] In an embodiment of the present invention, the data in the temperature sensor data set and the humidity sensor data set are preprocessed and then constitute a first parameter group , where represents the first parameter group corresponding to the th first sensor group within the preset time period , represents the temperature data set of the temperature sensor within the preset time period in the th first sensor group, represents the humidity data set of the humidity sensor within the preset time period in the th first sensor group.

[0037] Use sliding window one to start from and Select multiple temperature data and humidity data from it to form a temperature time series and a humidity time series; move the sliding window one to obtain multiple temperature time series and humidity time series. Extract multiple temperature feature values and humidity feature values from each temperature data series and humidity data series to form a temperature feature set and a humidity feature set. Secondly, the gas density and pressure of the insulating gas SF6 inside the GIS device are also key factors determining its insulation performance. The monitoring model predicts the current insulation characteristics of the device based on the real-time density, pressure data of the SF6 gas inside the GIS device, and the temperature data, humidity data, and dust concentration data of the external environment. Obtain the aging parameters of the insulating material used by the GIS from the database, and use the temperature feature set, humidity feature set, bulk density data of SF6, pressure data, and insulating material aging parameters to form a training sample set; use the training sample set to train the initial insulation monitoring model, and after meeting the performance requirements, deploy it.

[0038] That is, the environmental impact data, internal gas pressure, and density data are combined to form multi-source data, which can improve the accuracy of predicting the insulation of GIS equipment.

[0039] S2: Input the environmental impact data, density data, and pressure data into the pre-constructed insulation monitoring model to obtain the insulation prediction result of the target GIS device, and generate a fault handling signal according to the insulation prediction result; Specifically, input the real-time obtained environmental impact data (such as temperature, humidity), internal gas density data, and pressure data during the operation of the target GIS device into the pre-constructed insulation monitoring model. After the operation and analysis of the model, obtain the insulation prediction result of the target GIS device, which specifically includes two key indicators: the material aging speed and the internal gas insulation strength. The material aging speed reflects the speed of aging of the insulating material in the GIS device as it changes with time and operating conditions. For example, in harsh environments such as high temperature and high humidity, the aging speed of the insulating material may increase. The internal gas insulation strength directly reflects the current insulation ability of the gas used for insulation inside the device (such as sulfur hexafluoride, etc.). These two indicators reflect the insulation performance status of the GIS device from different aspects and provide a basis for subsequent judgment of whether there are potential faults in the device.

[0040] Preferably, in an embodiment of the present invention, the insulation prediction result includes the material aging speed and the internal gas insulation strength of the target GIS device; Generating a fault handling signal according to the insulation prediction result includes: Compare the material aging speed with a preset aging speed threshold. If the material aging speed is greater than the aging speed threshold, generate a fault handling signal; Or compare the internal gas insulation strength with a preset insulation strength threshold. If the internal gas insulation strength is less than the insulation strength threshold, a fault handling signal is generated.

[0041] S3: In response to the fault handling signal, execute the contact fault monitoring mode and the high-temperature fault monitoring mode; When the system receives the fault handling signal, it means that the insulation prediction result of the GIS device shows potential risks, which may affect the normal operation of the device. At this time, the system will quickly trigger a preset response program, allocate corresponding computing resources and data channels to ensure that the contact fault monitoring mode and the high-temperature fault monitoring mode can be started quickly and stably. At the same time, the system will transmit key information related to the fault handling signal, such as the insulation prediction indicators (material aging speed, internal gas insulation strength, etc.) of the trigger signal, to the subsequent monitoring module for comprehensive analysis during the monitoring process.

[0042] S4: In the contact fault monitoring mode, based on the corner detection algorithm, locate the contact feature points of the circuit breaker of the target GIS device in the acquired image dataset, determine the trajectory information of the contact feature points under the selected typical working conditions based on the optical flow method, and perform intelligent recognition on the trajectory information to obtain the contact fault result of the target GIS device; Preferably, in an embodiment of the present invention, locating the contact feature points of the circuit breaker of the target GIS device in the acquired image dataset according to the corner detection algorithm includes: Perform gray conversion, filtering, and edge detection processing on the image dataset in sequence to obtain an image dataset to be extracted, and the image dataset to be extracted includes several consecutive frames of images to be extracted; Calculate the autocorrelation matrix of each pixel point in the image to be extracted, and calculate the corner response function value according to the eigenvalues of the autocorrelation matrix; Take the pixel points with the corner response function value greater than the preset threshold as corners to construct a corner dataset, and filter out the corners belonging to the circuit breaker contacts in the corner dataset as contact feature points according to the position characteristics and shape characteristics of the acquired circuit breaker contacts.

[0043] Specifically, the original image dataset may be a color image, which contains rich color information. However, when performing corner detection, color information is not necessary and will instead increase the computational complexity. Therefore, the color image is first converted into a grayscale image. In the grayscale image, each pixel point has only one brightness value, which simplifies the data representation of the image. The image after gray conversion may contain noise, and the noise will interfere with the accuracy of subsequent corner detection. Therefore, it is necessary to perform filtering processing on the grayscale image.

[0044] The filtered image is then subjected to edge detection. The purpose of edge detection is to find the regions in the image where the gray - level values change drastically, and these regions often correspond to the edges of objects. For example, the Canny edge - detection algorithm smooths the image through Gaussian filtering, then calculates the gradient magnitude and direction of the image, followed by non - maximum suppression to remove possible false edges, and finally determines the edges in the image through double - threshold detection and edge linking.

[0045] For each pixel point in the image to be extracted, calculate its autocorrelation matrix. The autocorrelation matrix describes the gray - level change of the pixel point in different directions. Assume that taking a small neighborhood window centered on a certain pixel point, within this window, by calculating the gray - level changes of the pixel point in the horizontal and vertical directions, the autocorrelation matrix is constructed. For example, for a two - dimensional image, the autocorrelation matrix is usually a 2x2 matrix, and its elements are related to the gradients of the pixel points in the horizontal and vertical directions within the window.

[0046] After obtaining the autocorrelation matrix, calculate the eigenvalues of this matrix. The eigenvalues reflect the degree of gray - level change of the pixel point in different directions. Then, calculate the corner response function value based on these eigenvalues. Common corner response functions (such as the response function in the Harris corner - detection algorithm) will comprehensively consider the magnitude relationship between the two eigenvalues. For example, when both eigenvalues are large and close, it indicates that the gray - level change of the pixel point is obvious in all directions, and it is very likely to be a corner point; when one eigenvalue is very large and the other is very small, it indicates that the gray - level change of the pixel point is drastic in a certain direction and may be an edge point; when both eigenvalues are very small, it indicates that the gray - level change of the pixel point is not obvious and it is a point in a flat area. In this way, a corner response function value is calculated for each pixel point to measure the possibility that the pixel point is a corner point.

[0047] The pixel points with corner response function values greater than the preset threshold are regarded as corner points, and these corner points form a corner - point data set. The setting of the preset threshold needs to be adjusted according to the actual situation, and it determines the sensitivity of corner detection. If the threshold is set too high, some real corner points may be missed; if the threshold is set too low, too many false corner points may be detected.

[0048] According to the obtained position characteristics and shape characteristics of the circuit - breaker contact, select the corner points belonging to the circuit - breaker contact from the corner - point data set as contact feature points. Circuit - breaker contacts usually have specific positions and shapes. For example, their positions in the image are relatively fixed, and the shapes may be regular geometric shapes (such as circles, rectangles, etc.). By analyzing and matching these characteristics, the corner points related to the contact can be accurately selected from a large number of corner points, laying a foundation for analyzing the motion trajectory of the contact based on these feature points.

[0049] Preferably, in an embodiment of the present invention, the trajectory information includes the moving speed and the moving time; Based on the optical flow method, determining the trajectory information of the contact characteristic points under selected typical working conditions, including: Obtaining the coordinate positions of the contact characteristic points in each frame of the image to be extracted in the image dataset; Calculating the displacement data of the characteristic points between adjacent frames based on the coordinate positions of the images to be extracted in adjacent frames; Obtaining the time interval data between adjacent frames, and calculating the moving speed and moving time of the contact characteristic points according to the displacement data and the time interval data.

[0050] Specifically, in each frame of the image to be extracted in the image dataset, the coordinate position of the contact characteristic point obtained by the previous positioning is used to obtain its coordinate position in this frame of the image. The coordinate system in the image usually takes the upper left corner as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis. By recording the (x, y) coordinate values of each contact characteristic point in each frame of the image, basic data is provided for subsequent calculation of its motion trajectory.

[0051] Based on the coordinate positions of the contact characteristic points in the images to be extracted in adjacent frames, calculate the displacement data of the characteristic points between adjacent frames. Suppose the coordinate of a certain contact characteristic point in the nth frame of the image is (x1, y1), and the coordinate of this characteristic point in the (n + 1)th frame of the image is (x2, y2), then the displacement of this characteristic point between these two frames in the x direction is Δx = x2 - x1, and in the y direction is Δy = y2 - y1. By calculating the displacements of all contact characteristic points between adjacent frames, displacement data is obtained, which reflects the motion change of the contact characteristic points between adjacent frames.

[0052] In addition to the image data, it is also necessary to obtain the time interval data between adjacent frames. This usually depends on the frame rate of the image acquisition device. For example, if the frame rate is 25 frames per second, then the time interval between adjacent frames is 1 / 25 second. Calculate the moving speed and moving time of the contact characteristic points according to the displacement data and the time interval data. The moving speed can be calculated by the ratio of the displacement to the time interval. For example, the moving speed x in the x direction is x = Δx / Δt, and the moving speed y in the y direction is y = Δy / Δt. The actual moving speed of the characteristic point can be obtained by combining the speeds in the two directions. The moving time is the time elapsed from the start of monitoring to the current frame, which can be calculated by the product of the number of frames and the time interval. For example, after N frames of images, and the time interval for each frame is Δt, then the moving time T = N * Δt. Through these calculations, the trajectory information of the contact characteristic points under selected typical working conditions, including the moving speed and the moving time, is obtained, so as to obtain the closing time and closing speed of the circuit breaker contact.

[0053] Preferably, in an embodiment of the present invention, intelligent identification of the trajectory information is performed to obtain the contact fault result of the target GIS device, including: If the moving time is greater than a preset time threshold, it is determined that the circuit breaker of the target GIS device has a fault; Or if the moving speed is less than a preset speed threshold, it is determined that the circuit breaker of the target GIS device has a fault.

[0054] Compare the calculated moving time of the contact characteristic point with the preset time threshold. The preset time threshold is set according to the normal operation characteristics and experience of the GIS device circuit breaker. It represents the longest time allowed for the contact to complete one action (such as closing or opening) under normal circumstances. If the moving time of the contact characteristic point is greater than this preset time threshold, it indicates that the action time of the contact is too long, and there may be mechanical failures, poor contacts, etc., resulting in the contact being unable to complete the normal action in time. At this time, it is determined that the circuit breaker of the target GIS device has a fault. Compare the moving speed of the contact characteristic point with the preset speed threshold. The preset speed threshold is also set based on the normal operation parameters of the device. It reflects the speed range of the contact during the action under normal circumstances. If the moving speed of the contact characteristic point is less than the preset speed threshold, it indicates that the action speed of the contact is too slow, which may be caused by contact wear, jamming, etc., and will also affect the normal operation of the circuit breaker. At this time, it is determined that the circuit breaker of the target GIS device has a fault. By judging these two key parameters of moving speed and moving time, it is possible to intelligently identify whether there is a fault in the contact, so as to obtain the contact fault result of the target GIS device.

[0055] S5: In the high-temperature fault monitoring mode, identify the abnormal high-temperature area of the GIS device according to the real-time acquired infrared image dataset, compare the abnormal high-temperature area based on the partial discharge signal detection data in the abnormal high-temperature area, and determine the high-temperature area fault result of the target GIS device based on the comparison result; Preferably, in an embodiment of the present invention, identifying the abnormal high-temperature area of the GIS device according to the real-time acquired infrared image dataset includes: Perform image enhancement and noise removal processing on the infrared image dataset in sequence to obtain the image to be identified; Perform binarization processing on the image to be identified based on a pre-selected binarization threshold to obtain a binarized image, and identify the abnormal high-temperature area of the target GIS device according to the binarized image.

[0056] The real-time acquired infrared image dataset may have problems such as low contrast and unclear details due to environmental factors, equipment performance, etc. The purpose of image enhancement is to improve the visual effect of the image through certain algorithms and highlight the useful information in the image. For example, the histogram equalization method can be adopted. This method redistributes the number of pixels at each gray level in the image, making the gray level distribution of the image more uniform, thereby enhancing the contrast of the image. For infrared images, this helps to more clearly display the differences between different temperature regions. In addition, an image enhancement algorithm based on wavelet transform can also be used. It can analyze the image at different scales, enhance the detailed information of the image, and make the boundaries of high-temperature regions more obvious.

[0057] Perform binarization processing on the preprocessed image to be recognized based on a preselected binarization threshold. The purpose of binarization processing is to divide the pixel points in the image into two categories, usually represented by 0 and 1, corresponding to different regions in the image. In the scenario of identifying abnormally high-temperature regions, pixel points above the binarization threshold can be considered to belong to the abnormally high-temperature region, while pixel points below the threshold belong to the normal temperature region. The selection of the binarization threshold is very crucial and needs to be reasonably set according to the temperature range during the normal operation of the GIS device and historical data. For example, if it is known that the highest temperature during the normal operation of the GIS device is T1, considering a certain safety margin, the binarization threshold is set to T2 (T2>T1). After binarization processing, the region with a temperature higher than T2 will be marked as 1, forming a binarized image.

[0058] According to the regions in the binarized image where the pixel value is 1, the abnormally high-temperature regions of the target GIS device can be identified. In the binarized image, these regions with pixel value 1 form continuous blocks or irregular shapes. Through image analysis algorithms, such as the connected component labeling algorithm, these abnormally high-temperature regions can be marked and extracted, thereby determining information such as the location, shape, and size of the abnormally high-temperature regions.

[0059] Preferably, in an embodiment of the present invention, compare the abnormally high-temperature regions based on the partial discharge signal detection data within the abnormally high-temperature regions, and determine the high-temperature region fault result of the target GIS device based on the comparison result, including: Obtain the partial discharge signal of the target GIS device based on the partial discharge acquisition device, and perform filtering processing on the partial discharge signal; Synchronize the time of the filtered partial discharge signal with the infrared image data generated based on the high-temperature region; Perform correlation analysis on the infrared image data and the partial discharge signal after time synchronization, and judge the fault type according to the analysis result to generate a high-temperature region fault result corresponding to the fault type.

[0060] Specifically, a partial discharge acquisition device is used to obtain the partial discharge signals of the target GIS equipment. Partial discharge refers to the discharge phenomenon that occurs in a local area inside the GIS equipment due to insulation defects or other reasons. This kind of discharge will generate various physical signals such as electricity, sound, and light. The partial discharge acquisition device can detect these signals to obtain relevant information about partial discharge, such as the intensity and frequency of the discharge.

[0061] Time synchronization is performed on the filtered partial discharge signals and the infrared image data generated based on the high-temperature area. During the actual monitoring process, due to reasons such as equipment asynchronization and data transmission delay in the infrared image acquisition and partial discharge signal acquisition, there may be a time deviation between the two. The purpose of time synchronization is to ensure that the partial discharge signals and the corresponding infrared image data can be accurately matched for effective correlation analysis. Time synchronization can be achieved by setting a synchronous clock signal in the acquisition system or using the timestamp information in the data for time calibration. For example, when acquiring infrared images and partial discharge signals, record the acquisition time of each data point simultaneously, and then use an algorithm to match and adjust the time information of the two data sets so that the partial discharge signals at the same moment correspond to the corresponding infrared image data.

[0062] Correlation analysis is performed on the infrared image data and partial discharge signals after time synchronization. This step is mainly to find the internal connection between the two to judge the type of fault. For example, if a strong partial discharge signal is detected during the time period corresponding to a certain abnormally high-temperature area, and the characteristics of the partial discharge signal (such as discharge amplitude, frequency, etc.) are consistent with the partial discharge characteristics caused by insulation aging, then it can be preliminarily judged that the fault in this high-temperature area may be caused by insulation aging. By establishing a correlation model between the partial discharge signals and infrared image characteristics corresponding to different fault types, the acquired data is analyzed and matched to determine the type of fault.

[0063] According to the results of the correlation analysis, judge the type of fault and generate a high-temperature area fault result corresponding to the type of fault. The fault result should not only clarify the type of fault but also include an assessment of the severity of the fault.

[0064] S6: Based on the obtained contact fault result and / or high-temperature area fault result, execute the corresponding GIS equipment fault handling strategy.

[0065] Among them, the contact fault results include but are not limited to contact overheating, contact wear, and contact welding, and the high-temperature area fault results include but are not limited to insulation performance degradation, component damage, and partial discharge.

[0066] In an embodiment of the present invention, once overheating of the contact is detected, the load current of the device should be reduced first to prevent the overheating situation from deteriorating further. Specifically, the operation mode of the power grid can be adjusted to transfer some loads to other devices. At the same time, professional technicians should be arranged to perform power-off maintenance on the device as soon as possible to check the contact condition of the contact, such as whether the contact pressure spring is normal, whether there is dirt or burn on the contact surface, etc. When contact wear is found, different measures should be taken according to the degree of wear. If the wear degree is relatively light, the contact surface can be polished to remove burrs and oxides on the surface to improve the contact performance of the contact. At the same time, adjust the pressure and stroke of the contact to ensure good contact during the opening and closing process of the contact. If the contact is severely worn, such as the remaining thickness is less than 1 / 2 of the original thickness, a new contact must be replaced. Once contact welding occurs and the device cannot break the circuit normally, power must be cut off immediately for treatment. First, remove the welded contact and analyze the cause of the welding, such as whether the contact capacity is improperly selected, the operating frequency is too high, or the contact spring is damaged, etc. Take corresponding measures according to different reasons, such as replacing the contact with a suitable capacity, reducing the operating frequency, or replacing the contact spring, etc.

[0067] When a decrease in insulation performance due to high temperature is detected, the operating temperature of the device should be reduced first. Measures such as strengthening ventilation and heat dissipation and installing cooling devices can be taken. At the same time, conduct a comprehensive inspection of the insulation performance of the device, such as performing insulation resistance tests and dielectric loss tests, etc., to evaluate the degree of decrease in insulation performance. For component damage caused by high temperature, such as aging and deformation of seals and loosening of connectors, etc., the damaged components need to be replaced in time. When replacing the seal, choose high-temperature resistant and aging-resistant high-quality sealing materials and ensure the installation quality of the seal to prevent gas leakage. When partial discharge phenomena are detected in the high-temperature area, first monitor and analyze the partial discharge signals to determine the location and severity of the discharge. Then, take corresponding treatment measures according to the discharge situation.

[0068] Preferably, in an embodiment of the present invention, implementing the corresponding GIS device fault handling strategy further includes: Establish a fault type - treatment measure mapping knowledge base; Conduct a fuzzy logic comprehensive evaluation of the contact fault result and the high-temperature area fault result according to the fault type - treatment measure mapping knowledge base, and calculate the fault confidence level; When the fault confidence level exceeds the preset first confidence level threshold, execute the GIS device fault handling strategy generated based on the fault type - treatment measure mapping knowledge base.

[0069] Fuzzy logic comprehensive evaluation is an effective method for dealing with uncertainty problems. First, for the contact fault results and high-temperature area fault results, relevant knowledge and rules are extracted from the fault type - treatment measure mapping knowledge base. These rules usually exist in the form of fuzzy conditional statements, such as "If the contact wear degree is severe and the temperature in the high-temperature area exceeds a certain threshold, then the fault possibility is very high." Then, based on these rules and combined with actual fault data, such as the specific degree of contact wear and the temperature value in the high-temperature area, a fuzzy inference algorithm is used for comprehensive evaluation. During the evaluation process, the influence of multiple factors is considered, including the frequency of fault occurrence, the severity of the fault, etc., and finally a fault confidence level is calculated. The fault confidence level is a value between 0 and 1, which represents the credibility of the fault judgment. For example, a fault confidence level of 0.8 means there is an 80% certainty that the device has the corresponding fault.

[0070] The preset first confidence threshold is a key decision-making basis, which is determined according to factors such as the importance of the device, the operating environment, and the acceptable risk level. When the calculated fault confidence level exceeds this first confidence threshold, it indicates that the possibility of the device having a fault is very high. At this time, the system will immediately execute the GIS device fault handling strategy generated based on the fault type - treatment measure mapping knowledge base. For example, if the fault type is judged to be contact adhesion and the fault confidence level reaches the preset threshold, then the system will issue instructions according to the treatment measures for contact adhesion faults in the knowledge base, arranging maintenance personnel to perform operations such as contact replacement or repair to quickly restore the normal operation of the device and reduce the impact of the fault on the entire system.

[0071] Another embodiment of the present invention provides a multi-source data monitoring and processing method for GIS devices. Specifically, please refer to Figure 2 , Figure 2 which shows a schematic diagram of a multi-source data monitoring and processing system for a GIS device in one of the embodiments of the present invention, and it includes: An acquisition module 11, which is used to acquire in real time the environmental impact data corresponding to the insulation characteristics of the target GIS device, as well as the density data and pressure data of the internal gas during the operation of the target GIS device; An insulation monitoring module 12, which is used to input the environmental impact data, density data, and pressure data into a pre-constructed insulation monitoring model to obtain the insulation prediction result of the target GIS device, and generate a fault handling signal according to the insulation prediction result; A response module 13, which is used to execute the contact fault monitoring mode and the high-temperature fault monitoring mode in response to the fault handling signal; The first recognition module 14 is used to locate the contact feature points of the circuit breaker of the target GIS device in the acquired image dataset according to the corner detection algorithm in the contact fault monitoring mode, determine the trajectory information of the contact feature points under the selected typical working conditions based on the optical flow method, and perform intelligent recognition on the trajectory information to obtain the contact fault result of the target GIS device; The second recognition module 15 is used to identify the abnormal high-temperature area of the GIS device according to the real-time acquired infrared image dataset in the high-temperature fault monitoring mode, compare the abnormal high-temperature area based on the partial discharge signal detection data in the abnormal high-temperature area, and determine the high-temperature area fault result of the target GIS device based on the comparison result; The execution module 16 is used to execute the corresponding GIS device fault handling strategy based on the obtained contact fault result and / or high-temperature area fault result.

[0072] Preferably, in an embodiment of the present invention, the environmental impact data includes: temperature data and humidity data; The insulation monitoring module is further used for: Obtain the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the gas inside the target GIS device; Perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data based on the interpolation processing algorithm to obtain multi-source monitoring data; Construct an initial insulation monitoring model based on the random forest algorithm, and input the multi-source monitoring data into the initial insulation monitoring model for training to obtain a trained insulation monitoring model.

[0073] Preferably, in an embodiment of the present invention, the insulation prediction result includes the material aging speed and the internal gas insulation strength of the target GIS device; The insulation monitoring module is further used for: Compare the material aging speed with a preset aging speed threshold. If the material aging speed is greater than the aging speed threshold, generate the fault handling signal; Or compare the internal gas insulation strength with a preset insulation strength threshold. If the internal gas insulation strength is less than the insulation strength threshold, generate the fault handling signal.

[0074] Preferably, in an embodiment of the present invention, the first recognition module is further used for: Perform gray conversion, filtering, and edge detection processing on the image dataset in sequence to obtain a to-be-extracted image dataset, and the to-be-extracted image dataset includes to-be-extracted images of several consecutive frames; Calculate the autocorrelation matrix of each pixel point in the image to be extracted, and calculate the corner response function value according to the eigenvalues of the autocorrelation matrix; Take the pixel points with the corner response function value greater than the preset threshold as corners to construct a corner data set, and filter out the corners belonging to the breaker contacts in the corner data set as the contact feature points according to the position characteristics and shape characteristics of the breaker contacts obtained.

[0075] Preferably, in an embodiment of the present invention, the trajectory information includes moving speed and moving time; The first recognition module is further configured to: Obtain the coordinate positions of the contact feature points in each frame of the image to be extracted in the image data set; Calculate the displacement data of the feature points between adjacent frames based on the coordinate positions of the adjacent frames of the image to be extracted; Obtain the time interval data between adjacent frames, and calculate the moving speed and moving time of the contact feature points according to the displacement data and the time interval data.

[0076] Preferably, in an embodiment of the present invention, the first recognition module is further configured to: If the moving time is greater than the preset time threshold, it is determined that the breaker of the target GIS device fails; Or if the moving speed is less than the preset speed threshold, it is determined that the breaker of the target GIS device fails.

[0077] Preferably, in an embodiment of the present invention, the second recognition module is further configured to: Perform image enhancement and noise removal processing on the infrared image data set in sequence to obtain an image to be recognized; Perform binarization processing on the image to be recognized based on a pre-selected binarization threshold to obtain a binarized image, and identify the abnormal high-temperature area of the target GIS device according to the binarized image.

[0078] Preferably, in an embodiment of the present invention, the second recognition module is further configured to: Obtain the partial discharge signal of the target GIS device based on the partial discharge acquisition device, and perform filtering processing on the partial discharge signal; Synchronize the time of the filtered partial discharge signal with the infrared image data generated based on the high-temperature area; Perform correlation analysis on the infrared image data and the partial discharge signal after time synchronization, and judge the fault type according to the analysis result to generate a high-temperature area fault result corresponding to the fault type.

[0079] Preferably, in an embodiment of the present invention, the execution module is further configured to: Establish a fault type - handling measure mapping knowledge base; Perform fuzzy logic comprehensive evaluation on the contact fault result and the high - temperature area fault result according to the fault type - handling measure mapping knowledge base, and calculate the fault confidence level; When the fault confidence level exceeds a preset first confidence threshold, execute the GIS device fault handling strategy generated based on the fault type - handling measure mapping knowledge base.

[0080] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: (1) The present invention processes and analyzes multi - source data based on a pre - constructed insulation monitoring model, generates insulation prediction results and fault handling signals based on data, and then executes corresponding fault monitoring modes and handling strategies, avoiding the subjectivity and uncertainty of human judgment, and making fault diagnosis and handling more scientific and accurate.

[0081] (2) The present invention provides accurate fault information and handling basis for operation and maintenance personnel, helps operation and maintenance personnel formulate and implement operation and maintenance plans targeted, reasonably arrange maintenance resources and time, avoids blind patrol and over - maintenance, improves the efficiency and quality of operation and maintenance work, and realizes the transformation from traditional regular maintenance to state - based intelligent maintenance.

[0082] Another embodiment of the present invention provides a multi - source data monitoring and processing device for GIS equipment. Refer to Figure 3 , which is a structural block diagram of the multi - source data monitoring and processing device provided by the embodiments of the present invention. The multi - source data monitoring and processing device provided by the embodiments of the present invention includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps in the embodiments of the multi - source data monitoring and processing method for GIS equipment as described above, such as Figure 1 the steps S1 - S6 described in ; or when the processor 21 executes the computer program, it implements the functions of each module in the above - mentioned device embodiments, such as the acquisition module 11.

[0083] Exemplarily, the computer program can be divided into one or more modules. The one or more modules are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the multi - source data monitoring and processing device. For example, the computer program can be divided into an acquisition module 11, an insulation monitoring module 12, a response module 13, etc.

[0084] The multi-source data monitoring and processing device may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art can understand that the schematic diagram is only an example of the multi-source data monitoring and processing device, and does not constitute a limitation on the multi-source data monitoring and processing device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the multi-source data monitoring and processing device may also include input / output devices, network access devices, buses, etc.

[0085] The processor 21 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor 21 is the control center of the multi-source data monitoring and processing device, and connects various parts of the entire multi-source data monitoring and processing device through various interfaces and lines.

[0086] The memory 22 can be used to store the computer programs and / or modules. The processor 21 realizes various functions of the multi-source data monitoring and processing device by running or executing the computer programs and / or modules stored in the memory 22, and by calling the data stored in the memory 22. The memory 22 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0087] Among them, if the modules integrated in the multi-source data monitoring and processing device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0088] Those of ordinary skill in the art can understand that to implement all or part of the processes in the above-mentioned embodiment methods, it can be completed by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. Among them, the storage medium can be a magnetic disk, optical disc, read-only memory (ROM, Read-Only Memory), or random access memory (RAM), etc.

[0089] Correspondingly, an embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the steps in the multi-source data monitoring and processing method of the GIS device in the above-mentioned embodiment, for example Figure 1 the steps S1 to S6 described above.

[0090] The above-mentioned embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. A multi-source data monitoring and processing method for GIS equipment, characterized in that, Including: Obtaining in real time the environmental impact data corresponding to the insulation characteristics of the target GIS device, as well as the density data and pressure data of the internal gas of the target GIS device during operation; Inputting the environmental impact data, the density data, and the pressure data into a pre-constructed insulation monitoring model to obtain the insulation prediction result of the target GIS device, and generating a fault handling signal corresponding to the insulation prediction result; In response to the fault handling signal, executing a contact fault monitoring mode and a high-temperature fault monitoring mode; In the contact fault monitoring mode, based on the corner detection algorithm, locate the contact characteristic points of the circuit breaker of the target GIS device in the acquired image dataset, determine the trajectory information of the contact characteristic points under the selected typical working conditions based on the optical flow method, and perform intelligent recognition on the trajectory information to obtain the contact fault result of the target GIS device; In the high-temperature fault monitoring mode, identify the abnormally high-temperature area of the GIS device according to the real-time acquired infrared image dataset, compare the abnormally high-temperature area based on the partial discharge signal detection data in the abnormally high-temperature area, and determine the high-temperature area fault result of the target GIS device based on the comparison result; Based on the obtained contact fault result and / or the high-temperature area fault result, execute the corresponding GIS device fault handling strategy.

2. The multi-source data monitoring and processing method for GIS devices according to claim 1, wherein, The environmental impact data includes: temperature data and humidity data; Before inputting the environmental impact data, the density data, and the pressure data into a pre-constructed insulation monitoring model, it further includes: Obtaining the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the internal gas of the target GIS device; Performing time alignment processing on the historical environmental impact data, historical density data, and historical pressure data based on the interpolation processing algorithm to obtain multi-source monitoring data; Constructing an initial insulation monitoring model based on the random forest algorithm, inputting the multi-source monitoring data into the initial insulation monitoring model for training, and obtaining a trained insulation monitoring model.

3. The multi-source data monitoring and processing method of the GIS device according to claim 1, characterized in that, The insulation prediction result includes the material aging speed and the internal gas insulation strength of the target GIS device; The generating a fault handling signal corresponding to the insulation prediction result includes: Comparing the material aging speed with a preset aging speed threshold, if the material aging speed is greater than the aging speed threshold, generating the fault handling signal; Or comparing the internal gas insulation strength with a preset insulation strength threshold, if the internal gas insulation strength is less than the insulation strength threshold, generating the fault handling signal.

4. The multi-source data monitoring and processing method for GIS devices according to claim 1, characterized in that, The locating the contact characteristic points of the circuit breaker of the target GIS device in the acquired image dataset based on the corner detection algorithm includes: Successively performing gray-scale conversion, filtering, and edge detection processing on the image dataset to obtain a to-be-extracted image dataset, and the to-be-extracted image dataset includes to-be-extracted images of several consecutive frames; Calculating the autocorrelation matrix of each pixel point in the to-be-extracted image, and calculating the corner response function value according to the eigenvalues of the autocorrelation matrix; Pixels with corner response function values greater than a preset threshold are regarded as corner points to construct a corner point dataset. According to the obtained position characteristics and shape characteristics of the contacts of the circuit breaker, corner points belonging to the contacts of the circuit breaker in the corner point dataset are screened out as the contact feature points.

5. The multi-source data monitoring and processing method of the GIS device according to claim 1, characterized in that, The trajectory information includes moving speed and moving time; Determining the trajectory information of the contact feature points under selected typical working conditions based on the optical flow method includes: Obtaining the coordinate positions of the contact feature points in each frame of the image dataset to be extracted; Calculating the displacement data of the feature points between adjacent frames based on the coordinate positions of the adjacent frames of the image to be extracted; Obtaining the time interval data between adjacent frames, and calculating the moving speed and moving time of the contact feature points according to the displacement data and the time interval data.

6. The multi-source data monitoring and processing method of the GIS device according to claim 5, characterized in that, Intelligently identifying the trajectory information to obtain the contact fault result of the target GIS device includes: If the moving time is greater than a preset time threshold, it is determined that the circuit breaker of the target GIS device fails; Or if the moving speed is less than a preset speed threshold, it is determined that the circuit breaker of the target GIS device fails.

7. The multi-source data monitoring and processing method of the GIS device according to claim 1, characterized in that Identifying the abnormal high-temperature area of the GIS device according to the real-time obtained infrared image dataset includes: Successively performing image enhancement and noise removal processing on the infrared image dataset to obtain an image to be identified; Performing binarization processing on the image to be identified based on a pre-selected binarization threshold to obtain a binarized image, and identifying the abnormal high-temperature area of the target GIS device according to the binarized image.

8. The multi-source data monitoring and processing method of the GIS device according to claim 7, characterized in that Comparing the abnormal high-temperature area based on the partial discharge signal detection data in the abnormal high-temperature area, and determining the high-temperature area fault result of the target GIS device based on the comparison result includes: Obtaining the partial discharge signal of the target GIS device based on a partial discharge acquisition device, and filtering the partial discharge signal; Synchronizing the filtered partial discharge signal with the infrared image data generated based on the high-temperature area in time; Performing correlation analysis on the infrared image data and the partial discharge signal after time synchronization, judging the fault type according to the analysis result, and generating a high-temperature area fault result corresponding to the fault type.

9. The multi-source data monitoring and processing method for a GIS device according to claim 1, characterized in that Executing the corresponding GIS device fault handling strategy further includes: Establishing a fault type - treatment measure mapping knowledge base; Performing fuzzy logic comprehensive evaluation on the contact fault result and the high-temperature area fault result according to the fault type - treatment measure mapping knowledge base, and calculating the fault confidence level; When the fault confidence level exceeds a preset first confidence threshold, execute the GIS device fault handling strategy generated based on the fault type - treatment measure mapping knowledge base.

10. A multi-source data monitoring and processing system for a GIS device, characterized in that, Including: An acquisition module for real-time acquiring environmental impact data corresponding to the insulation characteristics of the target GIS device, as well as density data and pressure data of the internal gas during the operation of the target GIS device; An insulation monitoring module, configured to input the environmental impact data, the density data, and the pressure data into a pre-constructed insulation monitoring model to obtain an insulation prediction result of the target GIS device, and generate a fault handling signal according to the insulation prediction result; A response module, configured to execute a contact fault monitoring mode and a high-temperature fault monitoring mode in response to the fault handling signal; A first identification module, configured to, in the contact fault monitoring mode, locate the contact feature points of the circuit breaker of the target GIS device in the image data set obtained by corner detection algorithm, determine the trajectory information of the contact feature points under a selected typical working condition based on the optical flow method, and perform intelligent identification on the trajectory information to obtain a contact fault result of the target GIS device; A second identification module, configured to, in the high-temperature fault monitoring mode, identify an abnormally high-temperature area of the GIS device according to the real-time obtained infrared image data set, compare the abnormally high-temperature area based on the partial discharge signal detection data in the abnormally high-temperature area, and determine a high-temperature area fault result of the target GIS device based on the comparison result; An execution module, configured to execute a corresponding GIS device fault handling strategy based on the obtained contact fault result and / or the high-temperature area fault result.

11. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The environmental impact data includes: temperature data and humidity data; The insulation monitoring module is further configured to: Obtain the historical environmental impact data of the GIS device, as well as the historical density data and historical pressure data of the gas inside the target GIS device; Perform time alignment processing on the historical environmental impact data, historical density data, and historical pressure data based on an interpolation processing algorithm to obtain multi-source monitoring data; Construct an initial insulation monitoring model based on a random forest algorithm, input the multi-source monitoring data into the initial insulation monitoring model for training, and obtain a trained insulation monitoring model.

12. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The insulation prediction result includes the material aging speed and the internal gas insulation strength of the target GIS device; The insulation monitoring module is further configured to: Compare the material aging speed with a preset aging speed threshold, and if the material aging speed is greater than the aging speed threshold, generate the fault handling signal; Or compare the internal gas insulation strength with a preset insulation strength threshold, and if the internal gas insulation strength is less than the insulation strength threshold, generate the fault handling signal.

13. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The first identification module is further configured to: Perform gray conversion, filtering, and edge detection processing on the image data set in sequence to obtain an image data set to be extracted, where the image data set to be extracted includes a plurality of consecutive frames of images to be extracted; Calculate the autocorrelation matrix of each pixel point in the image to be extracted, and calculate the corner response function value according to the eigenvalues of the autocorrelation matrix; Use the pixel points with the corner response function value greater than a preset threshold as corners to construct a corner data set, and filter out the corners belonging to the circuit breaker contact in the corner data set as the contact feature points according to the position features and shape features of the obtained circuit breaker contact.

14. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The trajectory information includes the moving speed and moving time; The first recognition module is further configured to: Obtain the coordinate positions of the contact feature points in each frame of the image to be extracted in the image dataset; Calculate the displacement data of the feature points between adjacent frames based on the coordinate positions of the adjacent frames of the image to be extracted; Obtain the time interval data between adjacent frames, and calculate the moving speed and moving time of the contact feature points according to the displacement data and the time interval data.

15. The multi-source data monitoring and processing system of the GIS device according to claim 14, characterized in that, The first recognition module is further configured to: If the moving time is greater than a preset time threshold, determine that the circuit breaker of the target GIS device fails; Or if the moving speed is less than a preset speed threshold, determine that the circuit breaker of the target GIS device fails.

16. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The second recognition module is further configured to: Perform image enhancement and noise removal processing on the infrared image dataset in sequence to obtain an image to be recognized; Perform binarization processing on the image to be recognized based on a pre-selected binarization threshold to obtain a binarized image, and identify the abnormally high temperature area of the target GIS device according to the binarized image.

17. The multi-source data monitoring and processing system of the GIS device according to claim 16, characterized in that, The second recognition module is further configured to: Obtain the partial discharge signal of the target GIS device based on the partial discharge acquisition device, and perform filtering processing on the partial discharge signal; Synchronize the time of the filtered partial discharge signal with the infrared image data generated based on the high temperature area; Perform correlation analysis on the infrared image data and the partial discharge signal after time synchronization, and determine the fault type according to the analysis result, and generate a high temperature area fault result corresponding to the fault type.

18. The multi-source data monitoring and processing system of the GIS device according to claim 10, characterized in that, The execution module is further configured to: Establish a fault type - treatment measure mapping knowledge base; Perform fuzzy logic comprehensive evaluation on the contact fault result and the high temperature area fault result according to the fault type - treatment measure mapping knowledge base, and calculate the fault confidence level; When the fault confidence level exceeds a preset first confidence threshold, execute the GIS device fault treatment strategy generated based on the fault type - treatment measure mapping knowledge base.

19. A multi-source data monitoring and processing device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the multi-source data monitoring and processing method according to any one of claims 1 to 9.

20. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the device where the computer-readable storage medium is located executes the computer program, it implements the multi-source data monitoring and processing method according to any one of claims 1 to 9.

Images