Disconnecting switch fault diagnosis method and system, computer equipment and medium

Abstract

The invention belongs to the technical field of isolation switch fault detection, and particularly relates to an isolation switch fault diagnosis method and system, computer equipment and a medium. The method comprises the following steps: S1, acquiring a visible light image and an infrared image of a to-be-detected isolating switch; s2, preprocessing the obtained visible light image and infrared image; the preprocessing comprises a visible light image and an infrared image; converting the visible light image into an IHS image through IHS conversion; s3, converting the pre-processed visible light image into an IHS image through IHS conversion; taking the temperature data of the preprocessed infrared image as a brightness component of the infrared image; replacing the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image; and S4, performing fault diagnosis on the disconnecting switch according to the fused image. According to the invention, the technical problem of low fault diagnosis accuracy of the disconnecting switch in the prior art is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of isolating switch fault detection, and in particular relates to an isolating switch fault diagnosis method, system, computer equipment and medium. Background Art

[0002] With the development of electronic information technology, communication technology, materials and processes, online monitoring plays an increasingly important role in the normal operation and fault diagnosis of power equipment. However, in the process of developing and replacing manual maintenance and inspection, online monitoring technology needs to solve and improve many problems in actual operation, such as measurement errors caused by sensor and environmental interference, communication stability, and timeliness of data and control. An inappropriate monitoring system will not only lead to invalid data, affect the normal judgment of observers, but also cause abnormal operation of the equipment under test, and in severe cases, cause equipment damage or power transmission and distribution failures. Therefore, it is of great engineering significance to develop digital twin technology and design online monitoring systems with stable operation, valid and reliable data, and economical and environmentally friendly operation.

[0003] GIS (Gas Insulated Switchgear) is a gas-insulated metal-enclosed switchgear that integrates the primary equipment in the substation, such as busbars, circuit breakers, disconnectors, grounding switches, load switches, voltage transformers, current transformers, and lightning arresters, into a sealed cavity after optimized design to form a whole. The advantages of GIS equipment are that it occupies a small area, has high operating reliability and safety, and has a long maintenance cycle. Therefore, it has developed rapidly in my country since the 1970s and has been widely used in the field of power systems. However, due to its small size and small heat dissipation area, it is difficult to detect and repair. Once a fault occurs inside the GIS equipment, its fully enclosed structure makes it difficult to locate and repair the fault. The contacts of GIS equipment often have mechanical failures at the connection due to the influence of manufacturing process, working environment, etc., resulting in increased contact resistance at the contact, abnormal heating of the contact, and inducing thermal failure. It can be seen that thermal failures, especially thermal failures at the connection of contacts, are also one of the main causes of failure of GIS disconnectors.

[0004] The Chinese invention patent application with announcement number CN106650788A and application publication date 2017.05.10 discloses a disconnector fault detection method, which collects visible light images and infrared images of the disconnector in all directions, fuses the target contour information in the infrared image and the background information in the visible light image, and then uses the edge detection method to extract the edge features in the fused image, and performs fault identification based on the extracted edge features. However, when performing image fusion, the above technical solution fuses the target contour information in the infrared image and the background information in the visible light image, so that the final fused image may or may not have the color contrast information of the target to be detected, resulting in a low accuracy rate of the final fault diagnosis. Summary of the invention

[0005] The purpose of the present invention is to provide a disconnector fault diagnosis method, system, computer equipment and medium to solve the technical problem of low disconnector fault diagnosis accuracy in the prior art.

[0006] In order to solve the above technical problems, the present invention provides a technical solution of a disconnector fault diagnosis method: a disconnector fault diagnosis method, the method comprising:

[0007] S1. Acquire a visible light image and an infrared image of the disconnector to be detected;

[0008] S2, preprocessing the acquired visible light image and infrared image; the preprocessing includes image registration of the visible light image and the infrared image;

[0009] S3, converting the preprocessed visible light image into an IHS image through IHS transformation;

[0010] The temperature data of the preprocessed infrared image is used as the brightness component of the infrared image;

[0011] Replacing the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image;

[0012] S4. Perform fault diagnosis of the isolating switch based on the fused image.

[0013] The beneficial effect of the above technical solution is that the technical solution of the isolating switch fault diagnosis method of the present invention belongs to an improved invention. The present invention adopts an image fusion method based on IHS transformation for visible light images and infrared images, which better reflects the color contrast effect in the image, and realizes a comprehensive diagnosis of the isolating switch based on the fused isolating switch image, thereby improving the accuracy and reliability of the diagnosis. Visible light imaging and infrared imaging technology can be used to obtain rich information about the isolating switch, enhance the ability of fault diagnosis, and by fusing multiple feature parameters, the generated comprehensive image is more comprehensive and intuitive, which helps to quickly judge the working status of the isolating switch. The entire system has high real-time performance and flexibility, can adapt to different working environments and diagnostic requirements, and provides strong technical support for the intelligent diagnosis of isolating switches. The present invention solves the technical problem of low accuracy in isolating switch fault diagnosis in the prior art.

[0014] Furthermore, in S4, fault diagnosis of the disconnector is performed according to the RGB image of the fused image; the RGB image of the fused image is obtained by performing an IHS inverse transformation on the fused image in S3.

[0015] Furthermore, all pixels of the visible light image and the infrared image are transformed into the same plane space through a transformation matrix between the visible light image and the infrared image, thereby achieving image registration.

[0016] Furthermore, the transformation matrix is ​​obtained in the following manner: first, feature points are extracted from the visible light image and the infrared image respectively; then, feature points are matched to obtain the correspondence between each pixel point between the visible light image and the infrared image; finally, the transformation matrix is ​​obtained according to the correspondence.

[0017] Furthermore, the ORB algorithm is used to extract feature points from visible light images and infrared images.

[0018] Furthermore, the preprocessing also includes at least one of image interpolation, image denoising, image enhancement and image correction;

[0019] The image interpolation is used to generate a high-resolution image based on a low-resolution image; the image denoising is used to filter out interference information introduced during the image acquisition process; the image enhancement is used to improve the contrast and clarity of the image; and the image correction is used to eliminate geometric distortion and uneven lighting in the image.

[0020] Furthermore, the image interpolation adopts a bilinear interpolation method.

[0021] Furthermore, the image denoising is any one of Gaussian filtering, mean filtering and median filtering.

[0022] Furthermore, the method for performing fault diagnosis of the isolating switch according to the fused image in S4 is: extracting at least one of edge features, texture features and morphological features in the fused image, and performing fault diagnosis of the isolating switch according to the extracted features.

[0023] The present invention also provides a technical solution for a computer device: a computer device, comprising a processor, wherein the processor is used to execute a computer program to implement the steps of the isolating switch fault diagnosis method as described above.

[0024] The present invention also provides a technical solution of a computer-readable storage medium: a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program therein, and the computer program is used to be executed by a processor to implement the steps of the disconnector fault diagnosis method as described above.

[0025] The present invention also provides a technical solution of an isolating switch fault diagnosis system: an isolating switch fault diagnosis system, comprising a collection module and a processing module;

[0026] The acquisition module is used to acquire visible light images and infrared images of the disconnector to be tested in real time, and send the acquired images to the processing module;

[0027] The processing module is used to pre-process the image sent by the acquisition module, and then convert the pre-processed visible light image into an IHS image through IHS transformation; use the temperature data of the pre-processed infrared image as the brightness component of the infrared image; replace the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image; and perform fault diagnosis of the disconnector according to the fused image;

[0028] The preprocessing includes performing image registration on the visible light image and the infrared image.

[0029] The beneficial effect of the above technical solution is that the technical solution of the isolating switch fault diagnosis system of the present invention belongs to an improved invention. The present invention adopts an image fusion method based on IHS transformation for visible light images and infrared images, which better reflects the color contrast effect in the image, and realizes a comprehensive diagnosis of the isolating switch based on the fused isolating switch image, thereby improving the accuracy and reliability of the diagnosis. The use of visible light imaging and infrared imaging technology can obtain rich information about the isolating switch and enhance the ability of fault diagnosis. By fusing multiple feature parameters, the generated comprehensive image is more comprehensive and intuitive, which helps to quickly judge the working status of the isolating switch. The entire system has high real-time performance and flexibility, can adapt to different working environments and diagnostic requirements, and provides strong technical support for the intelligent diagnosis of isolating switches. The present invention solves the technical problem of low accuracy of isolating switch fault diagnosis in the prior art.

[0030] Furthermore, the acquisition module includes a visible light sensor, an infrared temperature sensor and a controller; the controller is used to receive image data acquired by the visible light sensor and the infrared temperature sensor, and send the image data to the processing module.

[0031] Furthermore, the priorities of the running tasks of the controller are from high to low: server task, infrared acquisition task, and image uploading task; the server task is used to process the access request of the processing module, complete the communication connection between the controller and the processing module, and also to complete the visible light image acquisition and upload it to the processing module; the infrared acquisition task is used to control the infrared temperature sensor to complete the infrared image acquisition; the image uploading task is used to upload the acquired image data to the processing module. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a structural schematic diagram of an embodiment of a method for diagnosing a fault of an isolating switch of the present invention;

[0033] Figure 2 is the original visible light image in the embodiment of the disconnector fault diagnosis method of the present invention;

[0034] Figure 3 is the original infrared image in the embodiment of the disconnector fault diagnosis method of the present invention;

[0035] Figure 4 is a registered visible light image in an embodiment of the disconnector fault diagnosis method of the present invention;

[0036] Figure 5 is an interpolated infrared temperature image in the embodiment of the disconnector fault diagnosis method of the present invention;

[0037] Figure 6 The original infrared image in the wavelet transform in the embodiment of the disconnector fault diagnosis method of the present invention;

[0038] Figure 7 The original visible light image in the wavelet transform in the embodiment of the disconnector fault diagnosis method of the present invention;

[0039] Figure 8 The fused image in the wavelet transform in the embodiment of the disconnector fault diagnosis method of the present invention;

[0040] Fig. 9 is the original infrared image in the IHS transformation in the embodiment of the disconnector fault diagnosis method of the present invention;

[0041] Fig.10 is the original visible light image in the IHS transformation in the embodiment of the disconnector fault diagnosis method of the present invention;

[0042] Fig.11 is the infrared image after registration in the IHS transformation in the embodiment of the disconnector fault diagnosis method of the present invention;

[0043] Fig.12 is a fused image in the IHS transformation in the embodiment of the disconnector fault diagnosis method of the present invention;

[0044] Fig.13 This is a fused image in an embodiment of the disconnector fault diagnosis method of the present invention. DETAILED DESCRIPTION

[0045] The present invention adopts an image fusion method based on IHS transformation for visible light images and infrared images, which better reflects the color contrast effect in the image, and realizes comprehensive diagnosis of the isolating switch based on the fused isolating switch image, thereby improving the accuracy and reliability of the diagnosis. The present invention solves the technical problem of low accuracy of isolating switch fault diagnosis in the prior art.

[0046] Isolating switch fault diagnosis method embodiment:

[0047] A method for diagnosing a fault of an isolating switch, such as Figure 1 As shown, the method includes:

[0048] S1. Obtain a visible light image and an infrared image of the disconnector to be inspected.

[0049] The visible light image and infrared image of the disconnector are obtained by the visible light sensor and the infrared sensor, and then the obtained visible light image and infrared image are preprocessed. The original visible light image and infrared image are as follows Figures 2-3 shown.

[0050] S2. Preprocess the acquired visible light image and infrared image.

[0051] Specifically, in this embodiment, the preprocessing includes image registration, image interpolation, image denoising, image enhancement and image correction.

[0052] Among them, image registration is used to make the points in the visible light image and the infrared image corresponding to the same position in space correspond one to one. Specifically, in this embodiment, the ORB algorithm is used to extract feature points from the infrared temperature image and the visible light image in the image fusion sample set. After completing the feature point matching, the pixel point correspondence between the two images is obtained, and then the transformation matrix between the two needs to be calculated. After obtaining the transformation matrix, all pixels of the two images can be transformed to the same plane space to achieve image registration. The visible light image after image registration is as follows Figure 4 As shown in the figure, the infrared image after image registration is as follows Fig.11 shown.

[0053] Image denoising is used to filter out interference information introduced during the image acquisition process. In actual application, according to the noise conditions on site, it is determined through testing to use any one of the filtering methods of Gaussian filtering, mean filtering and median filtering. The selection of the specific filtering method can refer to the existing technology, and this embodiment will not be described in detail.

[0054] Image interpolation is used to generate a high-resolution image from a low-resolution image. In this embodiment, bilinear interpolation is used to generate a high-resolution image from a low-resolution image. The infrared image after interpolation is as follows: Figure 5 shown.

[0055] Image enhancement is used to enhance images to improve the contrast and clarity of images. Image correction is used to correct images to eliminate geometric distortion and uneven lighting in images.

[0056] S3, converting the preprocessed visible light image into an IHS image through IHS transformation. Using the temperature data of the preprocessed infrared image as the brightness component of the infrared image; replacing the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image.

[0057] IHS is a color representation system similar to RGB, where I stands for intensity, H stands for hue, and S stands for saturation. For visible light images, RGB images can be converted to IHS images through matrix transformation. For temperature images, the temperature data of each pixel in the temperature matrix can be standardized to brightness data. The three channels of RGB images store the color information of red, green, and blue. The visible light RGB image needs to be transformed into an IHS image through the IHS matrix. The original infrared image and visible light image in the IHS transformation are as follows: Figures 9-10 shown.

[0058] The temperature image can represent the brightness of the image according to the temperature data, so the temperature data can represent the I component of the temperature image. The I component of the visible light image can be replaced by the I component of the temperature image to achieve image fusion. The fused image is converted to the commonly used RGB color model. The RGB image after inverse transformation is the fused image, such as Figures 12-13 shown.

[0059] Wavelet transform is also a common image fusion method. In this embodiment, a Harr-based wavelet decomposition is performed on the visible light image and the infrared image. The fusion rule adopts the weighted average method. The original infrared image, the original visible light image, and the fused image in the wavelet transform are respectively as follows: Figures 6 to 8 shown.

[0060] As for the selection of the number of wavelet decomposition layers, the larger the number of wavelet decomposition layers, the richer the fusion details. However, when the number of decomposition layers increases to a certain extent, the unit pixel points of the approximate part are reduced, resulting in unclear images and jagged edges, which reduces the quality of image fusion and causes color anomalies in the fusion of colorful images. As for the selection of wavelet transform function, since there is no universal wavelet transform function, it is necessary to determine the wavelet transform function through experiments for different infrared temperature and visible light images, which reduces the degree of automation of the monitoring system.

[0061] Compared with image fusion based on wavelet transform, image fusion based on IHS transform can better reflect the color contrast effect and image edge clarity. Therefore, on the basis of ensuring the image registration effect, the image fusion algorithm based on IHS transform is selected to improve the efficiency and accuracy of subsequent fault identification and diagnosis.

[0062] S4. Perform fault diagnosis of the isolating switch based on the fused image.

[0063] Specifically, the method for diagnosing the fault of the isolating switch based on the image can refer to the existing technology. For example, CN106650788A uses the edge detection method to detect the edge of the isolating switch in the fused image of the isolating switch in four directions to obtain the coordinates of the edge point; the coordinates of the edge point are compared with the template image to determine whether the isolating switch has a fault.

[0064] Alternatively, edge features, texture features or morphological features are extracted based on the fused image, and disconnector fault diagnosis or disconnector operation status assessment is performed based on the extracted features.

[0065] Disconnector fault diagnosis system implementation example:

[0066] A disconnector fault diagnosis system, such as Figure 1 As shown, it includes an acquisition module and a processing module (i.e., a host computer); the acquisition module is used to acquire visible light images and infrared images of the disconnector to be tested in real time, and send the acquired images to the processing module.

[0067] The processing module is used to preprocess the image sent by the acquisition module, and then convert the preprocessed visible light image into an IHS image through IHS transformation; use the temperature data of the preprocessed infrared image as the brightness component of the infrared image; replace the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image; and also to perform fault diagnosis of the disconnector according to the fused image.

[0068] Specifically, in this embodiment, the preprocessing includes image registration, image interpolation, image denoising, image enhancement and image correction.

[0069] Among them, image registration is used to make the points in the visible light image and the infrared image corresponding to the same position in space correspond one to one. Specifically, in this embodiment, the ORB algorithm is used to extract feature points from the infrared temperature image and the visible light image in the image fusion sample set. After completing the feature point matching, the pixel point correspondence between the two images is obtained, and then the transformation matrix between the two needs to be calculated. After obtaining the transformation matrix, all pixels of the two images can be transformed to the same plane space to achieve image registration. The visible light image after image registration is as follows Figure 4 As shown in Figure 2, the infrared image after image registration is as follows: Fig.11 shown.

[0070] Image denoising is used to filter out interference information introduced during the image acquisition process. In actual application, according to the noise conditions on site, it is determined through testing to use any one of the filtering methods of Gaussian filtering, mean filtering and median filtering. The selection of the specific filtering method can refer to the existing technology, and this embodiment will not be described in detail.

[0071] Image interpolation is used to generate a high-resolution image from a low-resolution image. In this embodiment, bilinear interpolation is used to generate a high-resolution image from a low-resolution image. The infrared image after interpolation is as follows: Figure 5 shown.

[0072] Image enhancement is used to enhance images to improve the contrast and clarity of images. Image correction is used to correct images to eliminate geometric distortion and uneven lighting in images.

[0073] In this embodiment, an infrared temperature camera and a visible light camera are used to collect infrared temperature images and visible light images, and the collected data are uploaded to a host computer through a microprocessor (i.e., a controller). The host computer fuses the infrared image and the visible light image according to an image fusion algorithm (i.e., an image fusion algorithm based on IHS transformation), thereby realizing non-contact, real-time online monitoring of the isolating switch.

[0074] In this embodiment, the image acquisition module includes an infrared temperature camera (i.e., an infrared sensor), a visible light camera (i.e., a visible light sensor), and a microprocessor (i.e., a controller), which are used to respectively acquire an infrared image and a visible light image of the isolating switch. The infrared sensor and the visible light sensor are respectively aimed at the isolating switch to acquire images of different bands, and are transmitted to the image preprocessing module in the host computer for preprocessing.

[0075] In this embodiment, the visible light sensor is controlled by the SCCB (Serial Camera Control Bus) bus and is compatible with I 2C (Inter-Intergrated Circuit) interface. The infrared temperature sensor communication interface uses I 2 C compatible digital interface, SDA (Serial Data Line) and (Serial clock) SCL signal lines are connected to the I 2 The microprocessor has its own DCMI (Digital camera Interface), which accepts high-speed data streams in different formats from the two cameras, and connects the data pin of the visible light sensor 2 to the DCMI pin of the microprocessor chip to realize the transmission of video data.

[0076] In this embodiment, the running tasks are divided into TCP server tasks (i.e., server tasks), infrared acquisition tasks, and data sending tasks according to the priority from high to low. The TCP server task determines whether there is an access request from the client to realize the connection between the acquisition system server and the host computer client. After the connection is completed, it is detected whether there is a data query instruction from the host computer. When data upload is required, the image acquisition and sending flags are set (i.e., the image acquisition flag and the image sending flag are both set to 1) to ensure the real-time performance of image acquisition (i.e., visible light acquisition) and sending; the infrared acquisition task will make a real-time judgment on the image acquisition flag. When the image acquisition flag is set to 1, the infrared temperature image is acquired by controlling the infrared sensor MLX90640, and the flag is cleared after the data acquisition is completed. The data sending task controls the data transmission by judging the status of the sending flag and the acquisition flag. Specifically, it is judged whether the sending flag is set to 1 and the acquisition flag is 0. If so, the collected data is sent, and the sending flag is cleared after the data is sent.

[0077] After the data is uploaded, the host computer will process the images collected by the sensor. First, bilinear interpolation is performed on the collected infrared temperature image to obtain an infrared temperature image with improved resolution. Secondly, feature-based image registration is performed on the visible light image and the infrared image to obtain the registered visible light image. Finally, the infrared temperature image after image preprocessing and the visible light image are fused based on the IHS transformation to achieve image fusion.

[0078] Computer equipment example:

[0079] A computer device includes a processor, the processor is used to execute a computer program to implement the steps of the isolating switch fault diagnosis method described above. The specific isolating switch fault diagnosis method has been described in detail in the above isolating switch fault diagnosis method embodiment, and will not be repeated here.

[0080] Computer readable storage medium embodiment:

[0081] A computer-readable storage medium having a computer program stored therein, the computer program being executed by a processor to implement the steps of the isolating switch fault diagnosis method as described above. The specific isolating switch fault diagnosis method has been described in sufficient detail in the above isolating switch fault diagnosis method embodiment, and will not be repeated here.

[0082] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments without creative work, or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for diagnosing a disconnector fault, characterized in that: The method includes: S1. Acquire a visible light image and an infrared image of the disconnector to be detected; S2, preprocessing the acquired visible light image and infrared image; the preprocessing includes image registration of the visible light image and the infrared image; S3, converting the preprocessed visible light image into an IHS image through IHS transformation; The temperature data of the preprocessed infrared image is used as the brightness component of the infrared image; Replacing the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image; S4. Perform fault diagnosis of the isolating switch based on the fused image.

2. The isolating switch fault diagnosis method according to claim 1, characterized in that: In S4, fault diagnosis of the disconnector is performed according to the RGB image of the fused image; the RGB image of the fused image is obtained by performing an IHS inverse transformation on the fused image in S3.

3. The isolating switch fault diagnosis method according to claim 1, characterized in that: All pixels of the visible light image and the infrared image are transformed to the same plane space through the transformation matrix between the visible light image and the infrared image to achieve image registration.

4. The isolating switch fault diagnosis method according to claim 3, characterized in that: The transformation matrix is ​​obtained in the following manner: first, feature points are extracted from the visible light image and the infrared image respectively; then, feature points are matched to obtain the correspondence between each pixel point between the visible light image and the infrared image; finally, the transformation matrix is ​​obtained according to the correspondence.

5. The isolating switch fault diagnosis method according to claim 4, characterized in that: The ORB algorithm is used to extract feature points from visible light images and infrared images.

6. The disconnector fault diagnosis method according to any one of claims 1 to 5, characterized in that: The preprocessing also includes at least one of image interpolation, image denoising, image enhancement and image correction; The image interpolation is used to generate a high-resolution image based on a low-resolution image; the image denoising is used to filter out interference information introduced during the image acquisition process; the image enhancement is used to improve the contrast and clarity of the image; and the image correction is used to eliminate geometric distortion and uneven lighting in the image.

7. The isolating switch fault diagnosis method according to claim 6, characterized in that: The image interpolation adopts bilinear interpolation method.

8. The isolating switch fault diagnosis method according to claim 6, characterized in that: The image denoising is any one of Gaussian filtering, mean filtering and median filtering.

9. The isolating switch fault diagnosis method according to claim 1 or 2, characterized in that: The method for performing fault diagnosis of the disconnector according to the fused image in S4 is: extracting at least one of edge features, texture features and morphological features in the fused image, and performing fault diagnosis of the disconnector according to the extracted features.

10. A computer device comprising a processor, characterized in that: The processor is used to execute a computer program to implement the steps of the disconnector fault diagnosis method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program therein, and the computer program is used to be executed by a processor to implement the steps of the disconnector fault diagnosis method according to any one of claims 1 to 9.

12. A disconnector fault diagnosis system, characterized in that: It includes an acquisition module and a processing module; The acquisition module is used to acquire visible light images and infrared images of the disconnector to be tested in real time, and send the acquired images to the processing module; The processing module is used to pre-process the image sent by the acquisition module, and then convert the pre-processed visible light image into an IHS image through IHS transformation; use the temperature data of the pre-processed infrared image as the brightness component of the infrared image; and replace the brightness component in the IHS image with the brightness component of the infrared image to obtain a fused image; It is also used to perform fault diagnosis of disconnectors based on fused images; The preprocessing includes performing image registration on the visible light image and the infrared image.

13. The disconnector fault diagnosis system according to claim 12, characterized in that: The acquisition module includes a visible light sensor, an infrared temperature sensor and a controller; the controller is used to receive image data acquired by the visible light sensor and the infrared temperature sensor, and send the image data to the processing module.

14. The isolating switch fault diagnosis system according to claim 13, characterized in that: The priorities of the running tasks of the controller are from high to low: server task, infrared acquisition task, and image uploading task; the server task is used to process the access request of the processing module, complete the communication connection between the controller and the processing module, and also to complete the visible light image acquisition and upload it to the processing module; the infrared acquisition task is used to control the infrared temperature sensor to complete the infrared image acquisition; the image uploading task is used to upload the acquired image data to the processing module.

Images