Transformer abnormal overheating identification method and device

Abstract

Embodiments of the present disclosure provide a transformer abnormal overheating identification method and device. The method comprises: acquiring multiple infrared images of a transformer under different operating conditions, wherein the operating conditions include normal operating conditions and multiple abnormal overheating operating conditions; calculating an abnormal feature image that fuses features of the multiple abnormal overheating operating conditions according to the multiple infrared images of the transformer under different operating conditions; processing a target infrared image using the abnormal feature image to calculate a local entropy image of the target infrared image; wherein the target infrared image is an infrared image of the transformer that needs to be identified for abnormal overheating; splicing the target infrared image and the local entropy image to obtain a spliced image, and identifying the spliced image for abnormal overheating. In this way, the abnormal overheating area in the transformer infrared image can be automatically and quickly detected and identified, and the transformer operation and maintenance efficiency and the abnormal identification accuracy are significantly improved.

Description

Technical Field

[0001] This disclosure relates to the field of power equipment testing technology, and in particular to a method and apparatus for identifying abnormal overheating of transformers. Background Technology

[0002] Infrared inspection is a crucial part of substation inspection. Infrared images can promptly detect localized overheating areas in transformers, identifying defects such as poor contact, overheating oil, and insulation aging, thus enabling early warning and preventing defects from escalating into major accidents. However, traditional infrared inspection requires maintenance personnel to conduct on-site inspections with handheld infrared detectors, consuming significant manpower. Furthermore, visual judgment is often subjective and heavily reliant on the experience of maintenance personnel, hindering accurate defect identification. Summary of the Invention

[0003] In a first aspect, embodiments of this disclosure provide a method for identifying abnormal overheating in a transformer, the method comprising:

[0004] Multiple infrared images of the transformer under different operating conditions were acquired. The operating conditions included normal operating conditions and various abnormal overheating operating conditions.

[0005] Based on multiple infrared images of the transformer under different operating conditions, an abnormal feature image is calculated and fused with the characteristics of various abnormal overheating operating conditions.

[0006] The target infrared image is processed using anomaly feature images to calculate the local entropy image of the target infrared image; where the target infrared image is the infrared image of the transformer that needs to be identified for abnormal overheating.

[0007] The target infrared image and local entropy image are stitched together to obtain a stitched image, and abnormal overheating is identified in the stitched image.

[0008] Among some possible implementations of the first aspect, abnormal overheating operating conditions include: overheating operating conditions of bushings and risers, overheating operating conditions of transformer body, overheating operating conditions of radiators, overheating operating conditions of on-load tap changers, and overheating operating conditions of terminals.

[0009] In some possible implementations of the first aspect, multiple infrared images of the transformer under different operating conditions are acquired, including:

[0010] Multiple raw infrared images of the transformer under different operating conditions were acquired using an infrared imager. All raw infrared images were then subjected to size unification and median filtering for noise reduction, resulting in multiple infrared images of the transformer under different operating conditions.

[0011] In some possible implementations of the first aspect, based on multiple infrared images of the transformer under different operating conditions, an abnormal feature image is calculated that fuses characteristics of various abnormal overheating operating conditions, including:

[0012] Convert multiple infrared images of the transformer under different operating conditions into grayscale images;

[0013] For any abnormal overheating operating condition, firstly, its multiple grayscale images are matched one-to-one with the multiple grayscale images of the normal operating condition to obtain multiple grayscale image pairs. Secondly, the grayscale image difference of each grayscale image pair is calculated to obtain multiple grayscale difference images. Then, the multiple grayscale difference images are binarized to obtain multiple binarized images. Finally, the average of the multiple binarized images is calculated to obtain an average image.

[0014] The average images of multiple abnormal overheating operating conditions are summed to obtain an abnormal feature image that integrates the characteristics of multiple abnormal overheating operating conditions.

[0015] In some possible implementations of the first aspect, the target infrared image is processed using anomaly feature images to calculate a local entropy image of the target infrared image, including:

[0016] The abnormal feature image is normalized to obtain a normalized image;

[0017] The target infrared image is processed using a normalized image to calculate the local entropy image of the target infrared image.

[0018] In some possible implementations of the first aspect, the target infrared image is processed using a normalized image to calculate a local entropy image of the target infrared image, including:

[0019] Convert the infrared image of the target into a grayscale image of the target;

[0020] The normalized image and the target grayscale image are fused to obtain a fused image;

[0021] The entropy value of each pixel neighborhood in the fused image is calculated using a sliding window to obtain a local entropy image.

[0022] Among the possible implementations of the first aspect, abnormal overheating detection of stitched images includes:

[0023] The K-nearest neighbor algorithm is used to identify abnormal overheating in stitched images.

[0024] Secondly, embodiments of this disclosure provide a transformer abnormal overheating identification device, the device comprising:

[0025] The acquisition module is used to acquire multiple infrared images of the transformer under different operating conditions, including normal operating conditions and various abnormal overheating operating conditions.

[0026] The calculation module is used to calculate and fuse multiple abnormal overheating operating conditions characteristics into an abnormal feature image based on multiple infrared images of the transformer under different operating conditions.

[0027] The processing module is used to process the target infrared image using abnormal feature images and calculate the local entropy image of the target infrared image; wherein, the target infrared image is the infrared image of the transformer that needs to be identified for abnormal overheating.

[0028] The identification module is used to stitch together the target infrared image and the local entropy image to obtain a stitched image, and to identify abnormal overheating in the stitched image.

[0029] Thirdly, embodiments of this disclosure provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0030] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0031] In this embodiment, an abnormal feature image can be calculated by fusing multiple infrared images of the transformer under normal operating conditions and various abnormal overheating operating conditions. Then, the abnormal feature image is used to process the target infrared image, i.e., the transformer infrared image that needs to be identified for abnormal overheating, to calculate the local entropy image of the target infrared image. The target infrared image and the local entropy image are then stitched together to obtain a stitched image, and abnormal overheating is identified on the stitched image. This can automatically and quickly detect and identify abnormal overheating areas in the transformer infrared image, significantly improving the transformer operation and maintenance efficiency and the accuracy of abnormal identification.

[0032] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0033] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0034] Figure 1 A flowchart of a transformer abnormal overheating identification method provided by an embodiment of the present disclosure is shown;

[0035] Figure 2 A structural diagram of a transformer abnormal overheating identification device provided in an embodiment of this disclosure is shown;

[0036] Figure 3 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0038] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0039] To address the problems in the background art, embodiments of this disclosure provide a method, apparatus, device, and storage medium for identifying abnormal overheating in transformers. Based on multiple infrared images of the transformer under normal operating conditions and various abnormal overheating operating conditions, an abnormal feature image is calculated and fused with characteristics of multiple abnormal overheating operating conditions. This abnormal feature image is then used to process the target infrared image (i.e., the transformer infrared image requiring abnormal overheating identification), calculating the local entropy image of the target infrared image. The target infrared image and the local entropy image are then stitched together to obtain a stitched image, which is then used for abnormal overheating identification. This method can automatically and quickly detect and identify abnormal overheating areas in transformer infrared images, significantly improving transformer operation and maintenance efficiency and anomaly identification accuracy.

[0040] The following detailed description, with reference to the accompanying drawings and specific embodiments, illustrates a transformer overheating identification method, apparatus, device, and storage medium provided by the present disclosure.

[0041] Figure 1 A flowchart of a transformer abnormal overheating identification method provided by an embodiment of this disclosure is shown, such as... Figure 1 As shown, the transformer abnormal overheating identification method 100 may include the following steps:

[0042] S110 acquires multiple infrared images of the transformer under different operating conditions.

[0043] In some embodiments, an infrared imager can be used to acquire multiple raw infrared images of the transformer under different operating conditions. All raw infrared images are then subjected to size unification and median filtering for noise reduction to obtain multiple infrared images of the transformer under different operating conditions. These operating conditions include: normal operating conditions and various abnormal overheating operating conditions. Further, abnormal overheating operating conditions include: bushing and riser overheating, transformer body overheating, radiator overheating, on-load tap changer overheating, and terminal block overheating.

[0044] S120 calculates and fuses multiple abnormal overheating operating conditions characteristics into an abnormal feature image based on multiple infrared images of the transformer under different operating conditions.

[0045] In some embodiments, multiple infrared images of the transformer under different operating conditions can be converted into grayscale images. For any abnormal overheating operating condition, firstly, multiple grayscale images belonging to that condition are mapped one-to-one with multiple grayscale images under normal operating conditions to obtain multiple grayscale image pairs. Secondly, the grayscale image difference of each grayscale image pair is calculated to obtain multiple grayscale difference images. Then, the multiple grayscale difference images are binarized to obtain multiple binarized images. Next, the multiple binarized images are averaged to obtain an average image. The average images of multiple abnormal overheating operating conditions are summed to obtain an abnormal feature image that integrates the characteristics of multiple abnormal overheating operating conditions.

[0046] S130: Process the target infrared image using the abnormal feature image to calculate the local entropy image of the target infrared image.

[0047] In some embodiments, the abnormal feature image can be normalized to obtain a normalized image. This normalized image is then used to process the target infrared image, calculating its local entropy. For example, the target infrared image can be converted into a target grayscale image of the same size as the normalized image. The normalized image and the target grayscale image are then fused to obtain a fused image. A sliding window is used to calculate the entropy value of each pixel's neighborhood in the fused image, resulting in a local entropy image. Here, the target infrared image is the infrared image of the transformer for which abnormal overheating identification is required.

[0048] S140: The target infrared image and the local entropy image are stitched together to obtain a stitched image, and abnormal overheating is identified in the stitched image.

[0049] In some embodiments, the target grayscale image converted from the target infrared image can be stitched together with the local entropy image to form a 2-channel image, guiding the subsequent classification algorithm to focus on hotspots and fault points. Then, the K-Nearest Neighbor (KNN) algorithm is used to classify the 2-channel image to achieve abnormal overheating identification and output the identification results.

[0050] To facilitate further understanding, the transformer abnormal overheating identification method 100 provided in this disclosure will be described in detail below with reference to a specific embodiment.

[0051] (1) Multiple original infrared images of the transformer under various operating conditions were acquired using an infrared imager, including normal operation condition N, bushing and riser overheating condition B, transformer body overheating condition W, radiator overheating condition S, on-load tap changer overheating condition O, and terminal overheating condition J. All original infrared images were then resized (to 640×640) and subjected to median filtering for noise reduction, resulting in multiple infrared images of the transformer under different operating conditions. Here, 50 infrared images are obtained for each operating condition.

[0052] (2) Convert 50 infrared images of the transformer under different operating conditions into grayscale images.

[0053] (3) For any abnormal overheating operation condition, first, the 50 grayscale images under it are matched one-to-one with the 50 grayscale images under normal operation condition to obtain 50 grayscale image pairs. Then, the grayscale image difference of the 50 grayscale image pairs is calculated to obtain 50 grayscale difference images. Then, the 50 grayscale difference images are binarized to obtain 50 binarized images. Finally, the 50 binarized images are averaged to obtain the average image.

[0054] The calculation of grayscale image differences under five abnormal overheating operating conditions can be represented by the following formula:

[0055] D1(x,y)=|I N (x,y)-I B (x,y)|,D2(x,y=|I N (x,y)-I W (x,y)|……D5(x,y=|I N (x,y)-I J (x,y)| (1)

[0056] Taking the overheated operation of the bushing and riser as an example, D1(x,y)=|I N (x,y)-I B (x,y)| represents the calculation of the grayscale image difference between the bushing and riser under overheating operation conditions, obtaining the grayscale difference image of the bushing and riser under overheating operation conditions, and D1(x,y) represents the grayscale difference image of the bushing and riser under overheating operation conditions. N (x,y) represents the grayscale image under normal operating conditions in a grayscale image pair. B (x,y) represents the grayscale image of the bushing and riser under overheating operation conditions, where (x,y) represents the pixel coordinates. It is understood that other abnormal overheating operation conditions are similar to those of the bushing and riser, and will not be elaborated upon here.

[0057] Binarizing the grayscale difference images under five abnormal overheating operating conditions can highlight local overheated areas (buoys, radiators, tap changers, etc.) in the images. The specific process is shown in the following formula:

[0058]

[0059] Among them, D′ i (x,y) represents the binarized image under the i-th abnormal overheating operating condition, D i (x,y) represents the grayscale difference image under the i-th abnormal overheating operating condition. This represents the optimal binarization threshold under the i-th abnormal overheating operating condition.

[0060] Averaging the binarized images under five abnormal overheating operating conditions can reduce the randomness that may appear in a single image. The specific process is shown in the following formula:

[0061]

[0062] Among them, Avg i (x,y) represents the average image under the i-th abnormal overheating operating condition, D′ i (x,y) represents the binarized image under the i-th abnormal overheating operating condition, with a total of 50 images.

[0063] (4) Sum the average images under multiple abnormal overheating operating conditions to obtain an abnormal feature image that integrates the characteristics of multiple abnormal overheating operating conditions. The specific process is shown in the following formula:

[0064]

[0065] Where Y(x,y) represents the anomaly feature image, Avg i (x,y) represents the average image under the i-th abnormal overheating operating condition.

[0066] (5) Normalize the abnormal feature image to obtain a normalized image, where the value of each pixel is between 0 and 1. The specific process is shown in the following formula:

[0067]

[0068] Where F(x,y) represents the normalized image, and max(Y(x,y)) represents the maximum pixel value in the anomalous feature image Y(x,y);

[0069] (6) Convert the target infrared image into a target grayscale image, and fuse the normalized image and the target grayscale image to obtain a fused image, where all negative numbers are assigned a value of 0. The specific process is shown in the following formula:

[0070] H = X + F - 1(6)

[0071] Where H represents the fused image, X represents the target grayscale image, and F represents the normalized image.

[0072] (7) Calculate the entropy value of each pixel neighborhood in the fused image using a sliding window, thereby calculating the local entropy value of the fused image and obtaining the local entropy image. The specific process is shown in the following formula:

[0073] L(x,y)=-∑p k (x,y)log2p k (x,y) (7)

[0074] Where L(x,y) represents the local entropy image, p k (x,y) represents the probability that the gray level is k within a window centered at pixel (x,y) in the fused image.

[0075] (8) The target grayscale image and the local entropy image are stitched together to form a 2-channel image, which guides the focus of subsequent classification algorithms on hot spots and fault points. Then, the K-Nearest Neighbor (KNN) algorithm is used to classify the 2-channel image to achieve abnormal overheating identification and output the identification results.

[0076] In summary, this disclosure achieves at least the following technical effects:

[0077] By adopting a multi-source anomaly feature fusion mechanism, the limitations of traditional single-condition detection are overcome, and the ability to characterize complex thermal defects is enhanced.

[0078] Local entropy analysis enhances the ability to extract abrupt changes in temperature distribution features, significantly improving the accuracy of temperature gradient identification for subtle anomalies.

[0079] Dual-channel feature fusion technology enables the collaborative analysis of texture features and temperature field. While reducing environmental noise interference, it also makes the detection results more robust and generalizable, ultimately achieving the dual technical effect of reducing the false negative rate and false positive rate.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0081] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0082] Figure 2 A structural diagram of a transformer abnormal overheating identification device provided in an embodiment of this disclosure is shown, as follows: Figure 2 As shown, the transformer abnormal overheating identification device 200 may include:

[0083] The acquisition module 210 is used to acquire multiple infrared images of the transformer under different operating conditions, including normal operating conditions and various abnormal overheating operating conditions.

[0084] The calculation module 220 is used to calculate an abnormal feature image that integrates the characteristics of multiple abnormal overheating operating conditions based on multiple infrared images of the transformer under different operating conditions.

[0085] The processing module 230 is used to process the target infrared image using the abnormal feature image and calculate the local entropy image of the target infrared image; wherein the target infrared image is the infrared image of the transformer that needs to be identified for abnormal overheating.

[0086] The recognition module 240 is used to stitch together the target infrared image and the local entropy image to obtain a stitched image, and to identify abnormal overheating in the stitched image.

[0087] Understandable Figure 2 Each module / unit in the transformer abnormal overheating identification device 200 shown has the ability to realize Figure 1 The functions of each step in the transformer abnormal overheating identification method 100 shown are explained, and their corresponding technical effects are achieved. For the sake of brevity, they will not be elaborated here.

[0088] Figure 3 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0089] like Figure 3 As shown, the electronic device 300 may include a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0090] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0091] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer program product, including a computer program tangibly contained in a computer-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0092] The various embodiments described above can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), payload programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0095] It should be noted that this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute method 100 and achieve the corresponding technical effects achieved by the embodiments of this disclosure in executing the method. For the sake of brevity, these will not be elaborated here.

[0096] In addition, this disclosure also provides a computer program product including a computer program that implements method 100 when executed by a processor.

[0097] To provide interaction with a user, the embodiments described above can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] The embodiments described above can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0099] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0100] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying abnormal overheating in a transformer, characterized in that, The method includes: Multiple infrared images of the transformer under different operating conditions are acquired, including normal operating conditions and various abnormal overheating operating conditions. Based on multiple infrared images of the transformer under different operating conditions, an abnormal feature image is calculated and fused with the characteristics of various abnormal overheating operating conditions. The abnormal feature image is used to process the target infrared image to calculate the local entropy image of the target infrared image; wherein, the target infrared image is the infrared image of a transformer that needs to be identified for abnormal overheating. The target infrared image and the local entropy image are stitched together to obtain a stitched image, and abnormal overheating is identified in the stitched image. The process of calculating and fusing multiple infrared images of the transformer under different operating conditions to obtain an abnormal feature image that integrates various abnormal overheating operating conditions includes: Convert multiple infrared images of the transformer under different operating conditions into grayscale images; For any abnormal overheating operating condition, firstly, its multiple grayscale images are matched one-to-one with the multiple grayscale images of the normal operating condition to obtain multiple grayscale image pairs. Secondly, the grayscale image difference of each grayscale image pair is calculated to obtain multiple grayscale difference images. Then, the multiple grayscale difference images are binarized to obtain multiple binarized images. Finally, the average of the multiple binarized images is calculated to obtain an average image. The average images of multiple abnormal overheating operating conditions are summed to obtain an abnormal feature image that integrates the characteristics of multiple abnormal overheating operating conditions; The step of processing the target infrared image using the abnormal feature image to calculate the local entropy image of the target infrared image includes: The abnormal feature image is normalized to obtain a normalized image; The target infrared image is processed using the normalized image to calculate the local entropy image of the target infrared image; The step of processing the target infrared image using the normalized image to calculate the local entropy image of the target infrared image includes: Convert the target infrared image into a target grayscale image; The normalized image and the target grayscale image are fused to obtain a fused image; The entropy value of each pixel neighborhood in the fused image is calculated using a sliding window to obtain a local entropy image.

2. The method according to claim 1, characterized in that, The abnormal overheating operating conditions include: overheating of the bushing and riser seat, overheating of the transformer body, overheating of the radiator, overheating of the on-load tap changer, and overheating of the terminal block.

3. The method according to claim 1, characterized in that, The acquisition of multiple infrared images of the transformer under different operating conditions includes: Multiple raw infrared images of the transformer under different operating conditions were acquired using an infrared imager. All raw infrared images were then subjected to size unification and median filtering for noise reduction, resulting in multiple infrared images of the transformer under different operating conditions.

4. The method according to claim 1, characterized in that, The step of identifying abnormal overheating in the stitched image includes: The K-nearest neighbor algorithm is used to identify abnormal overheating in the stitched image.

5. A transformer abnormal overheating identification device, characterized in that, The apparatus is used to perform the method according to any one of claims 1-4, comprising: The acquisition module is used to acquire multiple infrared images of the transformer under different operating conditions, wherein the operating conditions include: normal operating conditions and various abnormal overheating operating conditions; The calculation module is used to calculate and fuse multiple abnormal overheating operating conditions characteristics into an abnormal feature image based on multiple infrared images of the transformer under different operating conditions. The processing module is used to process the target infrared image using the abnormal feature image and calculate the local entropy image of the target infrared image; wherein the target infrared image is the infrared image of a transformer that needs to be identified for abnormal overheating. The identification module is used to stitch together the target infrared image and the local entropy image to obtain a stitched image, and to identify abnormal overheating in the stitched image.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images