Substation transformer gap generation risk detection method, device, equipment and medium

Abstract

The present invention discloses a method, device, equipment and medium for detecting the risk of gap generation in transformers in substations. The method includes constructing a gap detection model based on the spectral response differences of the reflectivity change spectrum of the base sealing ring and the edge position of the metal contact surface of the transformer in substations under different elastic deformation characteristics under multispectral imaging, dividing the gap generation area and performing risk judgment according to the change speed of the reflectivity change spectrum, and training the gap detection model based on the reflectivity characteristics of the leakage oil sample image and the ultraviolet fluorescence reaction of the leakage oil sample under ultraviolet light. The present invention establishes a correlation between reflectivity characteristics and material properties, and uses the reflectivity changes in the multispectral fusion image, the leakage oil distribution characteristics and the ultraviolet fluorescence reaction under ultraviolet light source to detect the risk of gap generation, thereby improving the accuracy and efficiency of the transformer sealing ring status assessment and providing strong support for preventing sealing failure.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer substation detection, and in particular to a method, device, equipment and medium for detecting the risk of transformer gap generation in a transformer substation. Background Art

[0002] In the supplementary inspection of substation blind spots, the detection of transformer base sealing ring is a key link, especially the study of the spectral reflection law of the edge of the rubber ring and the metal contact surface.

[0003] Because the rubber ring will deform due to elasticity during long-term operation, a tiny gap will be generated at the edge where the rubber ring contacts the metal. This gap will lead to a decrease in sealing performance, which in turn causes oil leakage. In the existing technology, it is often necessary to wait until a more obvious oil leakage occurs in the transformer before it can be detected through inspection technology. If the transformer with quality problems cannot be discovered and replaced in time during the supplementary inspection of the blind spot of the substation, it will threaten the safe operation of the substation.

[0004] Therefore, how to improve the detection accuracy of transformer gap in substation to avoid transformer oil leakage is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present invention provides a transformer substation transformer gap generation risk detection method, device, equipment and medium, so as to realize the detection of transformer substation transformer gap generation risk, thereby avoiding transformer oil leakage.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for detecting the risk of transformer gap generation in a substation, comprising:

[0007] Obtaining first reflectivity characteristics of different regions at the edge of a base sealing ring and a metal contact surface of a transformer in a substation under multispectral imaging, and obtaining a first reflectivity change map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of the different regions;

[0008] Building a gap detection model based on the spectral response differences of the first reflectivity change map under different elastic deformation characteristics of the base sealing ring;

[0009] According to the reflectivity characteristic change speed of the first reflectivity change map, a region with a change speed greater than a preset speed is divided into a gap generation region, a second reflectivity characteristic of the gap generation region under multispectral imaging is obtained, and a gap generation risk is pre-assessed based on the second reflectivity characteristic to obtain a first risk detection result;

[0010] Acquire a transformer oil leakage sample dataset, illuminate the oil leakage sample images in the oil leakage sample dataset using an ultraviolet simulated light source, and obtain ultraviolet fluorescence reaction features;

[0011] performing gap detection training on the gap detection model according to the third reflectivity feature of the oil leakage sample image in the oil leakage sample dataset under multispectral imaging, the ultraviolet fluorescence reaction feature, and the second reflectivity feature;

[0012] During the actual operation of the substation, the real-time collected transformer image data is input into the trained gap detection model to obtain a second risk detection result. The gap generation risk of the target transformer is detected and evaluated based on the first risk detection result and the second risk detection result.

[0013] Furthermore, the step of obtaining first reflectivity characteristics of different regions at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and obtaining a first reflectivity change map of the base sealing ring and the metal contact surface according to the first reflectivity characteristics of the different regions, includes:

[0014] Acquire spectral images of different areas at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and extract first spectral reflectance data from the spectral images;

[0015] Preprocessing the first spectral reflectance data using a Gaussian filter, and extracting a first reflectance feature from the preprocessed first spectral reflectance data;

[0016] A reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features at adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of reflectivity change within a unit distance.

[0017] Furthermore, the step of constructing a gap detection model based on the spectral response differences of the first reflectivity change map under different elastic deformation characteristics of the base sealing ring includes:

[0018] Obtaining a sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor;

[0019] extracting, based on the elastic deformation data sample set, several elastic deformation features of the base sealing ring when a gap exists in the mutual inductor;

[0020] A mapping relationship between the elastic deformation characteristics and the gap generation conditions is determined according to each of the elastic deformation characteristics and the corresponding first reflectivity change map, and a gap detection model is constructed according to the mapping relationship.

[0021] Furthermore, dividing an area having a change speed greater than a preset speed as a gap generation area according to the reflectivity characteristic change speed of the first reflectivity change map, and obtaining a second reflectivity characteristic of the gap generation area under multispectral imaging includes:

[0022] Extracting reflectivity jump data with a reflectivity feature change speed greater than a preset speed from the first reflectivity change map, segmenting the reflectivity jump data using a maximum inter-class variance method to obtain candidate gap regions with a sudden reflectivity feature change;

[0023] The division boundary of each gap candidate region is adjusted according to the region area, edge direction and spectral intensity of the gap candidate region to obtain a gap generation region and acquire a second reflectivity feature of the gap generation region under multispectral imaging.

[0024] Furthermore, the generating risk based on the second reflectivity characteristic gap is pre-evaluated to obtain a first risk detection result, including:

[0025] Calculating a change rate of a second reflectivity characteristic of the gap generation region within the region to obtain a second reflectivity change spectrum within the gap generation region;

[0026] The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map. If there is a point in the gap generation area where the change rate of the second reflectivity characteristics is greater than the preset reflectivity change threshold, it is judged that there is a gap generation risk in the gap generation area corresponding to the point.

[0027] Furthermore, the reflectivity change threshold is a multi-level reflectivity change threshold;

[0028] If there is a point in the gap generation area where the change rate value of the second reflectivity feature is greater than a preset reflectivity change threshold, then determining that the gap generation area corresponding to the point has a gap generation risk includes:

[0029] If there is a point in the gap generation area where the change rate value of the second reflectivity characteristic is greater than the preset reflectivity change threshold, the gap generation area is divided into gap generation risk levels according to the change rate value and the multi-level reflectivity change threshold.

[0030] Furthermore, the method includes obtaining a mutual inductor oil leakage sample dataset, irradiating the oil leakage sample images in the oil leakage sample dataset with an ultraviolet simulated light source, and obtaining ultraviolet fluorescence reaction features; and performing gap detection training on the gap detection model based on the third reflectivity feature of the oil leakage sample images in the oil leakage sample dataset under multispectral imaging, the ultraviolet fluorescence reaction feature, and the second reflectivity feature, including:

[0031] Acquire a transformer oil leakage sample data set, and obtain an oil leakage spectrum of each oil leakage sample image in the oil leakage sample data set under multispectral imaging;

[0032] Extracting the leakage oil distribution characteristics from the leakage oil spectrum, and determining the leakage oil region boundary in the leakage oil spectrum according to the leakage oil distribution characteristics;

[0033] The oil leakage diffusion rate data is calculated based on the boundaries of the oil leakage area of ​​at least two consecutive frames by using the optical flow method, and the oil leakage diffusion trend prediction curve is established based on the oil leakage diffusion rate data;

[0034] Obtaining a surface image of the base sealing ring corresponding to the spectrum of the leaked oil, and identifying elastic deformation information of the base sealing ring in the surface image using an edge detection algorithm;

[0035] Using an ultraviolet simulated light source to illuminate the oil leakage sample image in the oil leakage sample dataset to obtain an ultraviolet fluorescence reaction feature;

[0036] The third reflectivity feature of the leakage oil spectrum under multispectral imaging is obtained, and the gap detection model is trained for gap detection based on the third reflectivity feature, the ultraviolet fluorescence reaction feature, the second reflectivity feature, the leakage oil diffusion trend prediction curve and the elastic deformation information.

[0037] Another embodiment of the present invention provides a device for detecting a transformer gap risk in a substation, comprising:

[0038] a feature extraction module configured to obtain first reflectivity characteristics of different regions at the edge of a base sealing ring and a metal contact surface of a transformer in a substation under multispectral imaging, and to obtain a first reflectivity variation map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of the different regions;

[0039] a model building module, configured to build a gap detection model according to spectral response differences of the first reflectivity change map under different elastic deformation characteristics of the base sealing ring;

[0040] a region division module, configured to divide, based on the reflectivity characteristic change speed of the first reflectivity change map, a region having a change speed greater than a preset speed as a gap generation region, obtain a second reflectivity characteristic of the gap generation region under multispectral imaging, and pre-evaluate the gap generation risk based on the second reflectivity characteristic to obtain a first risk detection result;

[0041] An ultraviolet reaction module is used to obtain a mutual inductor oil leakage sample data set, and use an ultraviolet simulated light source to illuminate the oil leakage sample images in the oil leakage sample data set to obtain ultraviolet fluorescence reaction features;

[0042] a model training module, configured to perform gap detection training on the gap detection model based on the third reflectivity feature of the oil leakage sample image in the oil leakage sample dataset under multispectral imaging, the ultraviolet fluorescence reaction feature, and the second reflectivity feature;

[0043] The risk detection module is used to input the real-time collected transformer image data into the trained gap detection model during the actual substation operation to obtain a second risk detection result, and to detect and evaluate the gap generation risk of the target transformer based on the first risk detection result and the second risk detection result.

[0044] Furthermore, the feature extraction module is used to:

[0045] Acquire spectral images of different areas at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and extract first spectral reflectance data from the spectral images;

[0046] Preprocessing the first spectral reflectance data using a Gaussian filter, and extracting a first reflectance feature from the preprocessed first spectral reflectance data;

[0047] A reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features at adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of reflectivity change within a unit distance.

[0048] Furthermore, the model building module is used to:

[0049] Obtaining a sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor;

[0050] extracting, based on the elastic deformation data sample set, several elastic deformation features of the base sealing ring when a gap exists in the mutual inductor;

[0051] A mapping relationship between the elastic deformation characteristics and the gap generation conditions is determined according to each of the elastic deformation characteristics and the corresponding first reflectivity change map, and a gap detection model is constructed according to the mapping relationship.

[0052] Furthermore, the region division module is used to:

[0053] Extracting reflectivity jump data with a reflectivity feature change speed greater than a preset speed from the first reflectivity change map, segmenting the reflectivity jump data using a maximum inter-class variance method to obtain candidate gap regions with a sudden reflectivity feature change;

[0054] The division boundary of each gap candidate region is adjusted according to the region area, edge direction and spectral intensity of the gap candidate region to obtain a gap generation region and acquire a second reflectivity feature of the gap generation region under multispectral imaging.

[0055] Furthermore, the device also includes a risk judgment module:

[0056] Calculating a change rate of a second reflectivity characteristic of the gap generation region within the region to obtain a second reflectivity change spectrum within the gap generation region;

[0057] The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map. If there is a point in the gap generation area where the change rate of the second reflectivity characteristics is greater than the preset reflectivity change threshold, it is judged that there is a gap generation risk in the gap generation area corresponding to the point.

[0058] Furthermore, the reflectivity change threshold is a multi-level reflectivity change threshold;

[0059] The risk judgment module is also used to:

[0060] If there is a point in the gap generation area where the change rate value of the second reflectivity feature is greater than a preset reflectivity change threshold, then determining that the gap generation area corresponding to the point has a gap generation risk includes:

[0061] If there is a point in the gap generation area where the change rate value of the second reflectivity characteristic is greater than the preset reflectivity change threshold, the gap generation area is divided into gap generation risk levels according to the change rate value and the multi-level reflectivity change threshold.

[0062] Furthermore, the model training module is used to:

[0063] Acquire a transformer oil leakage sample data set, and obtain an oil leakage spectrum of each oil leakage sample image in the oil leakage sample data set under multispectral imaging;

[0064] Extracting the leakage oil distribution characteristics from the leakage oil spectrum, and determining the leakage oil region boundary in the leakage oil spectrum according to the leakage oil distribution characteristics;

[0065] The oil leakage diffusion rate data is calculated based on the boundaries of the oil leakage area of ​​at least two consecutive frames by using the optical flow method, and the oil leakage diffusion trend prediction curve is established based on the oil leakage diffusion rate data;

[0066] Obtaining a surface image of the base sealing ring corresponding to the spectrum of the leaked oil, and identifying elastic deformation information of the base sealing ring in the surface image using an edge detection algorithm;

[0067] Using an ultraviolet simulated light source to illuminate the oil leakage sample image in the oil leakage sample dataset to obtain an ultraviolet fluorescence reaction feature;

[0068] The third reflectivity feature of the leakage oil spectrum under multispectral imaging is obtained, and the gap detection model is trained for gap detection based on the third reflectivity feature, the ultraviolet fluorescence reaction feature, the second reflectivity feature, the leakage oil diffusion trend prediction curve and the elastic deformation information.

[0069] Yet another embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the above-described method for detecting risk of transformer gap generation in a substation when executing the computer program.

[0070] Yet another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the substation transformer gap generation risk detection method as described above is implemented.

[0071] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0072] By acquiring multispectral image data of the edge of the mutual inductor base sealing ring and the metal contact surface, the spectral reflection law of the rubber ring and the metal contact surface is analyzed, and the correlation between the reflectivity characteristics and the material properties is established; using these data, a gap detection model is constructed, and by analyzing the reflectivity changes and leakage oil distribution characteristics in the multispectral fusion image, an accurate assessment of the base sealing ring status is achieved; the present invention integrates multispectral data of visible light, infrared light and ultraviolet light bands, classifies the image features, and finally outputs the gap generation risk level judgment result, which improves the accuracy and efficiency of the mutual inductor sealing ring status assessment and provides strong support for preventing sealing failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A flowchart of the steps of a method for detecting transformer gap generation risk in a substation provided by an embodiment of the present invention;

[0074] Figure 2 A structural block diagram of a device for detecting gap generation risk of transformers in substations provided by an embodiment of the present invention;

[0075] Figure 3 A structural diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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 ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0077] In the description of this application, the terms "first," "second," "third," etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first," "second," "third," etc. may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0078] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" 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 a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more 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.

[0079] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the art. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. Those skilled in the art will understand the specific meanings of the above terms in this application in specific circumstances.

[0080] An embodiment of the present invention provides a method for detecting the risk of transformer gap generation in a substation. For details, see Figure 1 , Figure 1 The flowchart shows a method for detecting a transformer gap generation risk in a transformer substation according to one embodiment of the present invention, including steps S11 to S16:

[0081] Step S11, obtaining first reflectivity characteristics of different regions at the edge position of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and obtaining a first reflectivity change map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of different regions.

[0082] Multispectral imaging technology can capture spectral information in different bands. This spectral information reflects the reflection, transmission, and absorption characteristics of substances at different wavelengths. For power equipment such as transformers in substations, the material, state (such as oxidation, corrosion, contamination, etc.), and contact conditions of the base sealing ring and the metal contact surface will be reflected in the spectral image.

[0083] Due to the different spectral reflectance characteristics at the edge of the rubber ring and metal contact surface, the reflection spectrum changes when a gap is created. This change manifests as a difference in reflection intensity in a localized area in multispectral imaging. However, due to the material differences between the rubber ring and the metal surface, the spectral reflectance patterns are complex. Multispectral fusion can collaboratively process spectral data from different bands to extract the reflectance characteristics of the edge of the rubber ring and metal contact surface. When the elastic deformation of the sealing ring causes a gap, the spectral reflectance characteristics of the gap area will differ significantly from those of the normal contact area.

[0084] A multispectral image of the edge of the base seal ring and metal contact surface of a transformer in a substation is acquired, and the first spectral reflectance data is extracted from the spectral image. Compared to traditional visible light imaging, multispectral imaging provides richer information, facilitating more accurate identification and analysis of device status. Multispectral imaging is unaffected by lighting conditions and operates stably in a variety of environments, improving detection reliability and applicability. Spectral reflectance data describes the ratio of reflected light intensity to incident light intensity at different wavelengths, directly reflecting the material's reflective properties.

[0085] The first spectral reflectance data is preprocessed using a Gaussian filter to remove noise and outliers in the data, making the data smoother and more reliable, and the first reflectance feature is extracted from the preprocessed first spectral reflectance data.

[0086] The reflectivity difference calculation method reflects the degree of change of reflectivity within a unit distance by calculating the difference in reflectivity between adjacent positions. The reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features of adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of change of reflectivity within a unit distance, which can intuitively reflect the change of reflectivity in space.

[0087] Step S12: constructing a gap detection model according to the spectral response differences of the first reflectivity variation map under different elastic deformation characteristics of the base sealing ring.

[0088] Ensuring the sealing performance of instrument transformers (especially current transformers) is crucial for their inspection and maintenance. The sealing performance directly impacts the transformer's operational stability and service life. The base seal ring, a key component of the transformer's sealing structure, has an elastic deformation that indirectly reflects the transformer's sealing status and the presence of gaps. Therefore, in-depth research on the elastic deformation of the base seal ring is necessary to develop an effective gap detection model.

[0089] A sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor is obtained, and several elastic deformation features of the base sealing ring when a gap exists in the mutual inductor are extracted according to the sample set of elastic deformation data.

[0090] By determining the mapping relationship between the elastic deformation characteristics and the gap generation conditions according to each elastic deformation characteristic and the corresponding first reflectivity change map and constructing a gap detection model based on the mapping relationship, a quantitative evaluation of the mutual inductor sealing performance can be achieved, thereby improving the accuracy and reliability of the detection.

[0091] Step S13: According to the reflectivity characteristic change speed of the first reflectivity change map, the area with a change speed greater than the preset speed is divided into a gap generation area, the second reflectivity characteristic of the gap generation area under multispectral imaging is obtained, and the gap generation risk is pre-evaluated based on the second reflectivity characteristic to obtain a first risk detection result.

[0092] After obtaining the second reflectivity feature of the area where the reflectivity change rate is greater than the preset rate, the risk of gap formation can be pre-evaluated based on the second reflectivity feature to obtain the first risk detection result. In actual applications, this preliminary detection step can be used to estimate the risk of gap formation. The specific process is as follows:

[0093] Under normal circumstances, the reflectivity difference between adjacent areas will remain within a small range. Therefore, when the reflectivity characteristics change suddenly, it means that there may be a gap in the nearby area. The specific judgment method is as follows:

[0094] Reflectivity jump data is extracted from the first reflectivity change map, and the reflectivity jump data is segmented using the maximum inter-class variance method. This can preliminarily identify areas with large reflectivity feature changes and obtain gap candidate areas with sudden reflectivity feature changes.

[0095] The boundaries of each gap candidate region are adjusted based on their area, edge orientation, and spectral intensity to determine the gap formation region. The second reflectivity characteristics of the gap formation region under multispectral imaging are then obtained. After the gap formation regions are determined, the second reflectivity characteristics of these regions under multispectral imaging are further obtained. These second reflectivity characteristics are then used to further filter out gap formation risk areas within the gap candidate regions.

[0096] The second reflectivity change spectrum of the gap generation area is obtained according to the change trend of the continuous points of the second reflectivity characteristic in the gap generation area; if there are points in the second reflectivity change spectrum whose second reflectivity change value is greater than the reflectivity change threshold, it is determined that there is a gap generation risk in the corresponding gap generation area.

[0097] After obtaining the second reflectivity characteristics of the gap candidate area, it is necessary to further accurately judge the area, specifically: calculate the change rate of the second reflectivity characteristics of the gap generation area within the area, and obtain the second reflectivity change spectrum in the gap generation area. According to the second reflectivity change spectrum, areas where the reflectivity characteristics may change significantly due to gap generation can be discovered in time, thereby identifying the risk of gap generation.

[0098] The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map, and multi-level reflectivity change thresholds are divided according to different gap generation risk levels. If there are one or more points in the gap generation area whose corresponding reflectivity change values ​​in the second reflectivity change map are greater than the reflectivity change threshold, it is judged that there is a gap generation risk in the corresponding gap generation area, and the corresponding gap generation risk level is determined based on the actual reflectivity change value and the corresponding multi-level reflectivity change threshold.

[0099] This method can quickly analyze and detect the risk of gap generation. It is suitable for simple scenarios and helps inspectors to conduct preliminary screening of transformers and areas that may cause gaps. In practical applications, it helps inspectors quickly understand the situation.

[0100] The second reflectivity feature is also used in subsequent processing steps to combine with a series of infrared reaction data and other data to perform further and more accurate refined modeling and detection.

[0101] Multi-level reflectivity change thresholds are defined based on experimental data, experience, or industry standards. These thresholds reflect the range of possible reflectivity changes under different risk levels. Using these thresholds, we can more finely categorize the risk levels of gap formation areas, providing a more accurate basis for subsequent treatment measures. This allows for a refined and differentiated classification of gap formation risks, laying the foundation for subsequent gap formation risk control.

[0102] Step S14: obtaining a transformer oil leakage sample data set, and irradiating the oil leakage sample images in the oil leakage sample data set with an ultraviolet simulated light source to obtain ultraviolet fluorescence reaction features.

[0103] In order to train the gap detection model, a large amount of oil leakage sample data is required as input. A transformer oil leakage sample dataset is obtained. These datasets contain various oil leakage situations to ensure the generalization ability of the model.

[0104] The oil leakage spectrum of each oil leakage sample image in the oil leakage sample dataset under multispectral imaging is obtained, and the oil leakage distribution characteristics in the oil leakage spectrum are extracted. The oil leakage will show specific reflectivity characteristics under multispectral imaging. These characteristics can help identify the distribution area of ​​the oil leakage. The boundaries of the oil leakage area in the oil leakage spectrum are determined based on the oil leakage distribution characteristics. Clarifying the boundaries of the oil leakage area helps to more accurately calculate the diffusion rate of the oil leakage and predict its diffusion trend.

[0105] An ultraviolet light source is used to illuminate the leaked oil sample images in the leaked oil sample dataset to obtain ultraviolet fluorescence reaction characteristics. Insulating oils such as transformer oil will produce a fluorescent reaction under ultraviolet light, making the leaked oil more obvious in the image and forming a sharp contrast with the surrounding background, making it easier to detect.

[0106] Understanding the diffusion rate of leaked oil is crucial for assessing its potential risks and formulating emergency response measures. Therefore, this embodiment uses the optical flow method to calculate the diffusion rate data of leaked oil based on at least two frames of leaked oil boundaries, and establishes a leakage oil diffusion trend prediction curve based on the leakage oil diffusion rate data to intuitively understand the diffusion trend and potential risks of leaked oil.

[0107] The surface image of the base sealing ring corresponding to the spectrum of the leaked oil is obtained, and the elastic deformation information of the base sealing ring in the surface image is identified using an edge detection algorithm.

[0108] Step S15 , performing gap detection training on the gap detection model according to the third reflectivity feature of the oil leakage sample image in the oil leakage sample dataset under multispectral imaging, the ultraviolet fluorescence reaction feature, and the second reflectivity feature.

[0109] The third reflectivity feature of the oil leakage spectrum under multispectral imaging is obtained. The gap detection model is trained based on the third reflectivity feature, ultraviolet fluorescence reaction feature, second reflectivity feature, oil leakage diffusion trend prediction curve and elastic deformation information.

[0110] The third reflectivity characteristics, ultraviolet fluorescence reaction characteristics, oil leakage diffusion trend prediction curve and elastic deformation information data are cleaned and preprocessed to remove abnormal values ​​and missing values ​​where the data jumps, so as to ensure the quality of the data.

[0111] The processed data is divided into training set, validation set and test set. During the division process, it is necessary to ensure that the samples in each data set are representative and evenly distributed.

[0112] Preferably, in order to improve the local perception of the model during the gap detection process, the base model used to construct the gap detection model in this embodiment is a convolutional neural network model, and the processed third reflectivity feature, ultraviolet fluorescence reaction feature, leakage oil diffusion trend prediction curve and elastic deformation information are fused to obtain a high-dimensional feature vector as the input of the gap detection model. During the fusion process, the third reflectivity feature, ultraviolet fluorescence reaction feature, leakage oil diffusion trend prediction curve and elastic deformation information can be weighted according to the importance and actual situation of each feature according to the feature selection method, such as the feature selection method based on information gain, etc., which will not be elaborated here.

[0113] The mean square error function is used as the loss function of the gap detection model. The average value of the square difference between the predicted value and the true value of the gap detection model is calculated according to the output of each round of the model.

[0114] During the training process, the stochastic gradient descent method is used to calculate the gradient of the loss function with respect to the gap detection model parameters to minimize the loss function, and the model parameters are updated through back propagation.

[0115] Repeat the above steps until the loss value of the gap detection model on the training set converges to below the preset deviation value, which means that the deviation between the detection result of the gap detection model for the gap in the image and the true result is less than the acceptable deviation range. The training effect meets the standard, and the model training is ended. The model at this time is used as the optimized trained model to perform subsequent detection tasks.

[0116] Preferably, during the training process, at the end of each round of iteration, the model is verified using a validation set, and the above-mentioned preset deviation value is updated according to the detection accuracy at the end of each round. Specific verification indicators include accuracy, F1 score, etc.

[0117] The introduction of the oil leakage sample data set in this step is to obtain the third reflectivity characteristics of the base sealing ring corresponding to different degrees of oil leakage from mild to severe, so as to predict the reflectivity characteristics of the base sealing ring where a gap is about to appear and oil leakage will occur, so as to detect the problematic mutual inductor during the period when there is a risk of gap generation to avoid the occurrence of oil leakage.

[0118] The ultraviolet fluorescence reaction can excite the fluorescent substances in the leaked oil, causing it to emit visible light under ultraviolet light. Even a trace amount of leaked oil can be detected, significantly improving the sensitivity of detection. Detecting leaked oil through ultraviolet fluorescence reaction can further verify whether there is a leakage risk in the gap generation area, avoiding misjudgment or missed judgment. Combining multispectral imaging and ultraviolet fluorescence reaction, data on gap generation risk and oil leakage risk can be obtained at the same time, providing a more reliable basis for the detection results.

[0119] Step S16: During the actual operation of the substation, the real-time collected transformer image data is input into the trained gap detection model to obtain a second risk detection result, and the gap generation risk of the target transformer is detected and evaluated based on the first risk detection result and the second risk detection result.

[0120] The transformer image data acquired in real time includes image data of different directions and lighting conditions in different areas of the base sealing ring and the edge of the metal contact surface of the transformer in the target substation.

[0121] The collected mutual inductor image data is input into the gap detection model for detection to obtain a more accurate and refined second risk detection result.

[0122] Based on the preliminary first risk detection result obtained in the pre-evaluation in step S13 and the second risk detection result generated by the gap detection model, the detection and evaluation of the gap generation risk of the target mutual inductor is jointly achieved.

[0123] The method for detecting gap generation risk of transformers in substations of the present invention obtains multispectral image data of the edge of the transformer base sealing ring and the metal contact surface, analyzes the spectral reflection law of the rubber ring and the metal contact surface, and establishes a correlation between reflectivity characteristics and material properties; using these data, a gap detection model is constructed, and by analyzing the reflectivity changes and leakage oil distribution characteristics in the multispectral fusion image, an accurate assessment of the status of the base sealing ring is achieved; the present invention integrates multispectral data of visible light, infrared light and ultraviolet light bands, classifies and processes the image features, and finally outputs a gap generation risk level judgment result, thereby improving the accuracy and efficiency of transformer sealing ring status assessment and providing strong support for preventing sealing failure.

[0124] The embodiment of the present invention further provides a transformer substation gap generation risk detection device, which is used to execute the transformer substation gap generation risk detection method as described above. Figure 2 This is a structural block diagram of a device for detecting a transformer gap generation risk in a substation according to an embodiment of the present invention. The device includes:

[0125] A feature extraction module 21 is configured to obtain first reflectivity characteristics of different regions at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and obtain a first reflectivity change map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of the different regions;

[0126] A model building module 22 is configured to build a gap detection model based on the spectral response differences of the first reflectivity change map under different elastic deformation characteristics of the base sealing ring;

[0127] a region division module 23 for dividing, based on the reflectivity characteristic change rate of the first reflectivity change map, a region having a change rate greater than a preset rate as a gap generation region, obtaining a second reflectivity characteristic of the gap generation region under multispectral imaging, and performing a preliminary assessment of the gap generation risk based on the second reflectivity characteristic to obtain a first risk detection result;

[0128] The ultraviolet reaction module 24 is used to obtain a mutual inductor oil leakage sample data set, and use an ultraviolet simulated light source to illuminate the oil leakage sample images in the oil leakage sample data set to obtain ultraviolet fluorescence reaction characteristics;

[0129] a model training module 25 for performing gap detection training on the gap detection model according to the third reflectivity feature of the oil leakage sample image in the oil leakage sample dataset under multispectral imaging, the ultraviolet fluorescence reaction feature, and the second reflectivity feature;

[0130] The risk detection module 26 is used to input the real-time collected transformer image data into the trained gap detection model during the actual substation operation to obtain a second risk detection result, and to detect and evaluate the gap generation risk of the target transformer based on the first risk detection result and the second risk detection result.

[0131] Wherein, the feature extraction module is used to:

[0132] Acquire spectral images of different areas at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and extract first spectral reflectance data from the spectral images;

[0133] Preprocessing the first spectral reflectance data using a Gaussian filter, and extracting a first reflectance feature from the preprocessed first spectral reflectance data;

[0134] A reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features at adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of reflectivity change within a unit distance.

[0135] The model building module is used to:

[0136] Obtaining a sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor;

[0137] extracting, based on the elastic deformation data sample set, several elastic deformation features of the base sealing ring when a gap exists in the mutual inductor;

[0138] A mapping relationship between the elastic deformation characteristics and the gap generation conditions is determined according to each of the elastic deformation characteristics and the corresponding first reflectivity change map, and a gap detection model is constructed according to the mapping relationship.

[0139] The area division module is used for:

[0140] Extracting reflectivity jump data with a reflectivity feature change speed greater than a preset speed from the first reflectivity change map, segmenting the reflectivity jump data using a maximum inter-class variance method to obtain candidate gap regions with a sudden reflectivity feature change;

[0141] The division boundary of each gap candidate region is adjusted according to the region area, edge direction and spectral intensity of the gap candidate region to obtain a gap generation region and acquire a second reflectivity feature of the gap generation region under multispectral imaging.

[0142] The device also includes a risk judgment module:

[0143] Calculating a change rate of a second reflectivity characteristic of the gap generation region within the region to obtain a second reflectivity change spectrum within the gap generation region;

[0144] The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map. If there is a point in the gap generation area where the change rate of the second reflectivity characteristics is greater than the preset reflectivity change threshold, it is judged that there is a gap generation risk in the gap generation area corresponding to the point.

[0145] The reflectivity change threshold is a multi-level reflectivity change threshold;

[0146] The risk judgment module is also used to:

[0147] If there is a point in the gap generation area where the change rate value of the second reflectivity feature is greater than a preset reflectivity change threshold, then determining that the gap generation area corresponding to the point has a gap generation risk includes:

[0148] If there is a point in the gap generation area where the change rate value of the second reflectivity characteristic is greater than the preset reflectivity change threshold, the gap generation area is divided into gap generation risk levels according to the change rate value and the multi-level reflectivity change threshold.

[0149] The model training module is used to:

[0150] Acquire a transformer oil leakage sample data set, and obtain an oil leakage spectrum of each oil leakage sample image in the oil leakage sample data set under multispectral imaging;

[0151] Extracting the leakage oil distribution characteristics from the leakage oil spectrum, and determining the leakage oil region boundary in the leakage oil spectrum according to the leakage oil distribution characteristics;

[0152] The oil leakage diffusion rate data is calculated based on the boundaries of the oil leakage area of ​​at least two consecutive frames by using the optical flow method, and the oil leakage diffusion trend prediction curve is established based on the oil leakage diffusion rate data;

[0153] Obtaining a surface image of the base sealing ring corresponding to the spectrum of the leaked oil, and identifying elastic deformation information of the base sealing ring in the surface image using an edge detection algorithm;

[0154] Using an ultraviolet simulated light source to illuminate the oil leakage sample image in the oil leakage sample dataset to obtain an ultraviolet fluorescence reaction feature;

[0155] The third reflectivity feature of the leakage oil spectrum under multispectral imaging is obtained, and the gap detection model is trained for gap detection based on the third reflectivity feature, the ultraviolet fluorescence reaction feature, the second reflectivity feature, the leakage oil diffusion trend prediction curve and the elastic deformation information.

[0156] The technical features and technical effects of the device proposed in the embodiment of the present invention are the same as those of the method proposed in the embodiment of the present invention and are not described in detail here. Each module in the above-mentioned device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to the above modules.

[0157] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the substation transformer gap generation risk detection method as described above.

[0158] An embodiment of the present invention further provides a computer device, Figure 3 This is a structural block diagram of a preferred embodiment of a computer device provided by the present invention, wherein the computer device 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 above-mentioned substation transformer gap generation risk detection method.

[0159] Preferably, the computer program can be divided into one or more modules / units (e.g., computer program 1, computer program 2, ...). These one or more modules / units are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units 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 computer device.

[0160] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) 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 be any conventional processor. The processor is the control center of the computer device, and various parts of the computer device are connected using various interfaces and lines.

[0161] The memory primarily includes a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function, and the data storage area can store related data. Furthermore, the memory can be a high-speed random access memory or a non-volatile memory, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, or a Flash Card. Alternatively, the memory can be other volatile solid-state storage devices.

[0162] It should be noted that the above-mentioned computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 3 The structural block diagram is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or some components may be combined, or different components may be included.

[0163] In summary, the method, apparatus, device, and medium for detecting transformer gap generation risk in a substation provided by the embodiments of the present invention have the following beneficial effects compared to the prior art:

[0164] By acquiring multispectral image data of the edge of the mutual inductor base sealing ring and the metal contact surface, the spectral reflection law of the rubber ring and the metal contact surface is analyzed, and the correlation between the reflectivity characteristics and the material properties is established; using these data, a gap detection model is constructed, and by analyzing the reflectivity changes and leakage oil distribution characteristics in the multispectral fusion image, an accurate assessment of the base sealing ring status is achieved; the present invention integrates multispectral data of visible light, infrared light and ultraviolet light bands, classifies the image features, and finally outputs the gap generation risk level judgment result, which improves the accuracy and efficiency of the mutual inductor sealing ring status assessment and provides strong support for preventing sealing failure.

[0165] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for detecting gap generation risk of transformers in substations, characterized in that: include: Obtaining first reflectivity characteristics of different regions at the edge of a base sealing ring and a metal contact surface of a transformer in a substation under multispectral imaging, and obtaining a first reflectivity change map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of the different regions; Constructing a gap detection model based on the spectral response differences of the first reflectivity change spectrum under different elastic deformation characteristics of the base sealing ring; specifically, the method comprises: obtaining a sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor; extracting a plurality of elastic deformation characteristics of the base sealing ring when a gap exists in the mutual inductor based on the sample set of elastic deformation data; determining a mapping relationship between the elastic deformation characteristic and the gap generation condition based on each of the elastic deformation characteristics and the corresponding first reflectivity change spectrum, and constructing a gap detection model based on the mapping relationship; According to the reflectivity characteristic change speed of the first reflectivity change map, a region with a change speed greater than a preset speed is divided into a gap generation region, a second reflectivity characteristic of the gap generation region under multispectral imaging is obtained, and a gap generation risk is pre-evaluated based on the second reflectivity characteristic to obtain a first risk detection result; Acquire a transformer oil leakage sample dataset, illuminate the oil leakage sample images in the oil leakage sample dataset using an ultraviolet simulated light source, and obtain ultraviolet fluorescence reaction features; The gap detection model is trained for gap detection according to the third reflectivity feature, the ultraviolet fluorescence reaction feature and the second reflectivity feature of the leakage oil sample image in the leakage oil sample data set under multispectral imaging; specifically comprising: obtaining a mutual inductor leakage oil sample data set, obtaining a leakage oil spectrum of each leakage oil sample image in the leakage oil sample data set under multispectral imaging; extracting leakage oil distribution features in the leakage oil spectrum, and determining the leakage oil area boundary in the leakage oil spectrum according to the leakage oil distribution features; calculating leakage oil diffusion velocity data according to the leakage oil area boundary of at least two consecutive frames using the optical flow method, and determining the leakage oil diffusion velocity data according to the leakage oil diffusion velocity data. The leakage oil diffusion trend prediction curve is established based on the diffusion velocity data; a surface image of the base sealing ring corresponding to the leakage oil spectrum is obtained, and the elastic deformation information of the base sealing ring in the surface image is identified using an edge detection algorithm; the leakage oil sample image in the leakage oil sample data set is irradiated with an ultraviolet simulated light source to obtain an ultraviolet fluorescence reaction feature; the third reflectivity feature of the leakage oil spectrum under multispectral imaging is obtained, and the gap detection model is trained for gap detection based on the third reflectivity feature, the ultraviolet fluorescence reaction feature, the second reflectivity feature, the leakage oil diffusion trend prediction curve, and the elastic deformation information; During the actual operation of the substation, the real-time collected transformer image data is input into the trained gap detection model to obtain a second risk detection result. The gap generation risk of the target transformer is detected and evaluated based on the first risk detection result and the second risk detection result.

2. The method for detecting the risk of transformer gap generation in a transformer substation according to claim 1, wherein: The step of obtaining first reflectivity characteristics of different regions at the edge of a base sealing ring and a metal contact surface of a transformer in a substation under multispectral imaging, and obtaining a first reflectivity change map of the base sealing ring and the metal contact surface according to the first reflectivity characteristics of the different regions, includes: Acquire spectral images of different areas at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and extract first spectral reflectance data from the spectral images; Preprocessing the first spectral reflectance data using a Gaussian filter, and extracting a first reflectance feature from the preprocessed first spectral reflectance data; A reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features at adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of reflectivity change within a unit distance.

3. The method for detecting the risk of transformer gap generation in a transformer substation according to claim 1, wherein: The step of dividing an area having a change speed greater than a preset speed as a gap generation area according to the reflectivity characteristic change speed of the first reflectivity change map, and obtaining a second reflectivity characteristic of the gap generation area under multispectral imaging includes: Extracting reflectivity jump data with a reflectivity feature change speed greater than a preset speed from the first reflectivity change map, segmenting the reflectivity jump data using a maximum inter-class variance method to obtain candidate gap regions with a sudden reflectivity feature change; The division boundary of each gap candidate region is adjusted according to the region area, edge direction and spectral intensity of the gap candidate region to obtain a gap generation region and acquire a second reflectivity feature of the gap generation region under multispectral imaging.

4. The method for detecting the risk of transformer gap generation in a transformer substation according to claim 1, wherein: The pre-evaluating the gap generation risk according to the second reflectivity feature to obtain a first risk detection result includes: Calculating a change rate of a second reflectivity characteristic of the gap generation region within the region to obtain a second reflectivity change spectrum within the gap generation region; The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map. If there is a point in the gap generation area where the change rate of the second reflectivity characteristics is greater than the preset reflectivity change threshold, it is judged that there is a gap generation risk in the gap generation area corresponding to the point.

5. The method for detecting the risk of transformer gap generation in a transformer substation according to claim 4, wherein: The reflectivity change threshold is a multi-level reflectivity change threshold; If there is a point in the gap generation area where the change rate value of the second reflectivity feature is greater than a preset reflectivity change threshold, then determining that the gap generation area corresponding to the point has a gap generation risk includes: If there is a point in the gap generation area where the change rate value of the second reflectivity characteristic is greater than the preset reflectivity change threshold, the gap generation area is divided into gap generation risk levels according to the change rate value and the multi-level reflectivity change threshold.

6. A transformer gap generation risk detection device for a substation, characterized in that: include: a feature extraction module configured to obtain first reflectivity characteristics of different regions at the edge of a base sealing ring and a metal contact surface of a transformer in a substation under multispectral imaging, and to obtain a first reflectivity variation map of the base sealing ring and the metal contact surface based on the first reflectivity characteristics of the different regions; A model construction module is configured to construct a gap detection model based on the spectral response differences of the first reflectivity change map under different elastic deformation characteristics of the base sealing ring. The model construction module specifically comprises: obtaining a sample set of elastic deformation data of the base sealing ring when a gap exists in the mutual inductor; extracting a plurality of elastic deformation characteristics of the base sealing ring when a gap exists in the mutual inductor based on the sample set of elastic deformation data; determining a mapping relationship between the elastic deformation characteristic and the gap generation condition based on each of the elastic deformation characteristics and the corresponding first reflectivity change map, and constructing a gap detection model based on the mapping relationship; a region division module, configured to divide, based on the reflectivity characteristic change speed of the first reflectivity change map, a region having a change speed greater than a preset speed as a gap generation region, obtain a second reflectivity characteristic of the gap generation region under multispectral imaging, and pre-evaluate the gap generation risk based on the second reflectivity characteristic to obtain a first risk detection result; An ultraviolet reaction module is used to obtain a mutual inductor oil leakage sample data set, and use an ultraviolet simulated light source to illuminate the oil leakage sample images in the oil leakage sample data set to obtain ultraviolet fluorescence reaction features; The model training module is used to perform gap detection training on the gap detection model according to the third reflectivity feature, the ultraviolet fluorescence reaction feature and the second reflectivity feature of the leakage oil sample image in the leakage oil sample data set under multispectral imaging; specifically comprising: obtaining a mutual inductor leakage oil sample data set, obtaining a leakage oil spectrum of each leakage oil sample image in the leakage oil sample data set under multispectral imaging; extracting leakage oil distribution features in the leakage oil spectrum, and determining the leakage oil area boundary in the leakage oil spectrum according to the leakage oil distribution features; calculating the leakage oil diffusion velocity data using the optical flow method based on the leakage oil area boundary of at least two consecutive frames, and obtaining the leakage oil diffusion velocity data according to the leakage oil diffusion velocity data. The leakage oil diffusion velocity data is used to establish a leakage oil diffusion trend prediction curve; a surface image of the base sealing ring corresponding to the leakage oil spectrum is obtained, and the elastic deformation information of the base sealing ring in the surface image is identified using an edge detection algorithm; the leakage oil sample image in the leakage oil sample data set is irradiated with an ultraviolet simulated light source to obtain an ultraviolet fluorescence reaction feature; a third reflectivity feature of the leakage oil spectrum under multispectral imaging is obtained, and the gap detection model is trained for gap detection based on the third reflectivity feature, the ultraviolet fluorescence reaction feature, the second reflectivity feature, the leakage oil diffusion trend prediction curve, and the elastic deformation information; The risk detection module is used to input the real-time collected transformer image data into the trained gap detection model during the actual substation operation to obtain a second risk detection result, and to detect and evaluate the gap generation risk of the target transformer based on the first risk detection result and the second risk detection result.

7. The substation transformer gap generation risk detection device according to claim 6, characterized in that: The feature extraction module is used to: Acquire spectral images of different areas at the edge of the base sealing ring and the metal contact surface of the transformer in the substation under multispectral imaging, and extract first spectral reflectance data from the spectral images; Preprocessing the first spectral reflectance data using a Gaussian filter, and extracting a first reflectance feature from the preprocessed first spectral reflectance data; A reflectivity difference calculation method is used to perform difference calculation on the first reflectivity features at adjacent positions in the image to obtain a first reflectivity change map reflecting the degree of reflectivity change within a unit distance.

8. The transformer transformer gap generation risk detection device according to claim 6, characterized in that: The area division module is used for: Extracting reflectivity jump data with a reflectivity feature change speed greater than a preset speed from the first reflectivity change map, segmenting the reflectivity jump data using a maximum inter-class variance method to obtain candidate gap regions with a sudden reflectivity feature change; The division boundary of each gap candidate region is adjusted according to the region area, edge direction and spectral intensity of the gap candidate region to obtain a gap generation region and acquire a second reflectivity feature of the gap generation region under multispectral imaging.

9. The substation transformer gap generation risk detection device according to claim 6, characterized in that: The device also includes a risk judgment module: Calculating a change rate of a second reflectivity characteristic of the gap generation region within the region to obtain a second reflectivity change spectrum within the gap generation region; The second reflectivity characteristics of the gap generation area are screened according to the second reflectivity change map. If there is a point in the gap generation area where the change rate of the second reflectivity characteristics is greater than the preset reflectivity change threshold, it is judged that there is a gap generation risk in the gap generation area corresponding to the point.

10. The transformer substation mutual inductor gap generation risk detection device according to claim 9, characterized in that: The reflectivity change threshold is a multi-level reflectivity change threshold; The risk judgment module is also used to: If there is a point in the gap generation area where the change rate value of the second reflectivity feature is greater than a preset reflectivity change threshold, then determining that the gap generation area corresponding to the point has a gap generation risk includes: If there is a point in the gap generation area where the change rate value of the second reflectivity characteristic is greater than the preset reflectivity change threshold, the gap generation area is divided into gap generation risk levels according to the change rate value and the multi-level reflectivity change threshold.

11. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for detecting the risk of transformer gap generation in a substation according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the substation transformer gap generation risk detection method according to any one of claims 1 to 5 is implemented.

Images