Casing thermal diagnosis method, device and electronic equipment
By obtaining and analyzing the map of the transformer casing, extracting features and calculating temperature difference information, and using convolutional layer branches and conditional random fields for diagnosis, the problem of inefficient casing thermal fault diagnosis in the existing technology is solved, achieving efficient and accurate fault detection.
Patent Information
- Application Number
- CN202210874006.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-20
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-07-20
AI Technical Summary
The prior art is difficult to diagnose thermal failure of transformer casing in a timely and effective manner, resulting in inefficiency, wasting manpower, material resources and financial resources, and the inability to grasp the status of the equipment in real time.
By obtaining the casing map, extracting features, determining candidate maps, analyzing the temperature difference information of the airspace and time domains, performing thermal diagnosis, and using convolutional layer branches and conditional random fields to perform feature fusion and identification, the accurate diagnosis of the casing is achieved.
It improves the accuracy and efficiency of casing thermal fault diagnosis, can grasp the equipment status in real time, reduce manual inspections, and promptly detect faults.
Smart Images

Figure CN115266819B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of transformers, and in particular to a bushing thermal diagnosis method, device and electronic equipment. Background Art
[0002] During operation, the transformer is subjected to electrical, thermal and mechanical stresses at the same time. In addition, it is also affected by external environmental factors, which may cause heating failures. As the main accessory, the bushing, especially the working nature of the valve-side bushing, makes the bushing thermal failures frequent, which is much higher than the body, cooler, and control cabinet. The statistics of the CIGRE A2.37 working group's report on the causes of transformer failures in 2015 show that as the voltage level increases, the proportion of transformer failures caused by bushings gradually increases. When the voltage level is 500kV and above, the proportion reaches 27.8%. Bushing oil leakage, poor grounding of the end screen, poor wiring, insulation damage, and sealing failure can all cause overheating. Furthermore, once a fault occurs, it will directly cause the transformer to stop operating, and in severe cases, it may even cause fire and explosion. Therefore, how to effectively diagnose bushing thermal faults has important practical value.
[0003] At present, the most commonly used technology for overheating fault diagnosis of substation equipment in most substations is to conduct offline inspections manually using handheld devices, and determine the bushing thermal fault through manual offline inspections.
[0004] The above method is inefficient, wastes a lot of manpower, material resources and financial resources, and cannot grasp the equipment status in real time, so it is impossible to effectively diagnose the casing thermal fault in time. Summary of the invention
[0005] In view of this, the embodiments of the present invention provide a bushing thermal diagnosis method, device and electronic equipment, aiming to solve the problem that bushing thermal faults cannot be effectively diagnosed in time.
[0006] According to a first aspect, an embodiment of the present invention provides a casing thermal diagnosis method, comprising:
[0007] Obtain a bushing atlas to be processed, wherein the bushing atlas to be processed includes atlases corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing;
[0008] Extract features from the casing map to be processed, and determine a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features;
[0009] Perform data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map respectively to determine the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing;
[0010] According to the air domain temperature difference information and the time domain temperature difference information, thermal diagnosis is performed on the A phase bushing, the B phase bushing and the C phase bushing.
[0011] The bushing thermal diagnosis method provided by the embodiment of the present invention obtains the bushing spectrum to be processed, then extracts features of the bushing spectrum to be processed, and determines the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum from the bushing spectrum to be processed according to the extracted features, thereby ensuring the accuracy of the determined candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum. Data analysis is performed on the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the airspace temperature difference information and the time domain temperature difference information corresponding to the determined A-phase bushing, the B-phase bushing, and the C-phase bushing. Then, according to the airspace temperature difference information and the time domain temperature difference information, the A-phase bushing, the B-phase bushing, and the C-phase bushing are thermally diagnosed, thereby ensuring the accuracy of the thermal diagnosis of the A-phase bushing, the B-phase bushing, and the C-phase bushing. The above method does not require manual use of handheld devices for offline inspections, thereby not only ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, but also improving the efficiency of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, and ensuring real-time grasp of the equipment status, so that the bushing thermal fault can be effectively diagnosed in time.
[0012] In combination with the first aspect, in the first embodiment of the first aspect, feature extraction is performed on the casing map to be processed, and candidate A-phase casing map, candidate B-phase casing map and candidate C-phase casing map are determined from the casing map to be processed according to the extracted features, including:
[0013] Based on the two convolutional layer branches in the casing recognition model, convolution processing is performed on the casing map to be processed to generate the first feature and the second feature;
[0014] Fusing the first feature and the second feature to generate a fused feature;
[0015] The fused features are identified, and a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map are determined from the casing maps to be processed.
[0016] The bushing thermal diagnosis method provided by the embodiment of the present invention performs convolution processing on the bushing map to be processed based on the two convolution layer branches in the bushing recognition model, respectively, to generate the first feature and the second feature, thereby ensuring the accuracy of the generated first feature and the second feature. The first feature and the second feature are fused to generate a fusion feature, thereby ensuring the accuracy of the generated fusion feature. Then, the fusion feature is identified, and the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map are determined from the bushing map to be processed, thereby ensuring the accuracy of the determined candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map.
[0017] In combination with the first implementation of the first aspect, in the second implementation of the first aspect, convolution processing is performed on the casing map to be processed based on two convolution layer branches in the casing recognition model to generate the first feature and the second feature, including:
[0018] Based on the first convolutional layer branch in the casing recognition model, the casing map to be processed is first amplified and then convolved to generate a first feature;
[0019] Based on the second convolutional layer branch in the casing recognition model, the casing map to be processed is first reduced and then convolved in a loop to generate the second feature.
[0020] The casing thermal diagnosis method provided by the embodiment of the present invention first amplifies the casing map to be processed and then performs convolution cycle processing based on the first convolution layer branch in the casing recognition model to generate a first feature, thereby ensuring the accuracy of the generated first feature. The second convolution layer branch in the casing recognition model first reduces the casing map to be processed and then performs convolution cycle processing to generate a second feature, thereby ensuring the accuracy of the generated second feature.
[0021] In combination with the first embodiment of the first aspect, in the third embodiment of the first aspect, the fusion feature is identified, and a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map are determined from the casing map to be processed, including:
[0022] Perform convolution processing on the fused features based on the conditional random field to generate the target features;
[0023] The target features are identified, and a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map are determined from the casing maps to be processed.
[0024] The bushing thermal diagnosis method provided by the embodiment of the present invention performs convolution processing on the fused features based on the conditional random field to generate the target features, thereby ensuring the accuracy of the generated target features. The target features are identified, and the candidate A-phase bushing maps, the candidate B-phase bushing maps, and the candidate C-phase bushing maps are determined from the bushing maps to be processed, thereby ensuring the accuracy of determining the candidate A-phase bushing maps, the candidate B-phase bushing maps, and the candidate C-phase bushing maps.
[0025] In combination with the first aspect, in a fourth implementation of the first aspect, data analysis is performed on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map, respectively, to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, including:
[0026] Based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each bushing map, the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map are aligned to obtain the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map;
[0027] The target A phase bushing map, the target B phase bushing map and the target C phase bushing map are respectively segmented into sub-regions to obtain the sub-regions corresponding to the target A phase bushing map, the target B phase bushing map and the target C phase bushing map;
[0028] Obtain target area temperatures corresponding to each sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map;
[0029] Based on the relationship between the temperatures of each target area, the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing are calculated.
[0030] The bushing thermal diagnosis method provided by the embodiment of the present invention performs position alignment on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each bushing map, and obtains the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map, thereby ensuring the accuracy of the obtained target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map, and can ensure the accuracy of data analysis on the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map. Then, the target A phase bushing map, the target B phase bushing map and the target C phase bushing map are respectively divided into sub-regions to obtain the sub-regions corresponding to the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, so as to ensure the accuracy of the sub-regions corresponding to the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, and facilitate the study of the temperature information of the target A phase bushing map, the target B phase bushing map and the target C phase bushing map. In addition, the electronic device obtains the target area temperature corresponding to each sub-region in the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, and calculates the airspace temperature difference information and the time domain temperature difference information corresponding to the A phase bushing, the B phase bushing and the C phase bushing based on the relationship between the temperatures of each target area, thereby ensuring the accuracy of the calculated airspace temperature difference information and the time domain temperature difference information corresponding to the A phase bushing, the B phase bushing and the C phase bushing.
[0031] In combination with the fourth implementation of the first aspect, in the fifth implementation of the first aspect, based on the relationship between the temperatures of the target areas, the airspace temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing is calculated, including:
[0032] For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, the maximum target area temperature and the minimum target area temperature are determined from the target area temperatures corresponding to the sub-areas corresponding to the respective bushing maps;
[0033] The temperature field distribution of the A-phase bushing, the B-phase bushing and the C-phase bushing is calculated by subtracting the minimum target area temperature from the maximum target area temperature.
[0034] The target area temperatures of the corresponding sub-areas in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map are respectively compared to obtain the target area temperature differences corresponding to the corresponding sub-areas;
[0035] Determine the maximum target area temperature difference from the target area temperature differences as the temperature difference field distribution corresponding to the A phase bushing, the B phase bushing and the C phase bushing;
[0036] Based on the relationship between its own temperature field distribution and the temperature difference field distribution, the spatial temperature difference information is calculated.
[0037] The bushing thermal diagnosis method provided by the embodiment of the present invention determines the maximum target area temperature and the minimum target area temperature from the target area temperature corresponding to the sub-area corresponding to each bushing map for the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, and respectively subtracts the minimum target area temperature from the maximum target area temperature to calculate the corresponding self-temperature field distribution of the A phase bushing, the B phase bushing, and the C phase bushing, thereby ensuring the accuracy of the calculated self-temperature field distribution of the A phase bushing, the B phase bushing, and the C phase bushing. Then, the electronic device compares the target area temperature of each corresponding sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, respectively, and obtains the target area temperature difference corresponding to each corresponding sub-area, thereby ensuring the accuracy of the obtained target area temperature difference corresponding to each corresponding sub-area. The maximum target area temperature difference is determined from the target area temperature difference as the temperature difference field distribution corresponding to the A-phase casing, the B-phase casing and the C-phase casing, thereby ensuring the accuracy of the obtained temperature difference field distribution corresponding to the A-phase casing, the B-phase casing and the C-phase casing. Based on the relationship between the own temperature field distribution and the temperature difference field distribution, the airspace temperature difference information is calculated, thereby ensuring the accuracy of the calculated airspace temperature difference information.
[0038] In combination with the fourth implementation of the first aspect, in the sixth implementation of the first aspect, based on the relationship between the temperatures of the target areas, the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing is calculated, including:
[0039] For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively obtain a preset number of historical regional temperatures corresponding to each sub-region;
[0040] Compare the target area temperature corresponding to each sub-area with each historical area temperature to obtain a preset number of historical temperature differences corresponding to each sub-area;
[0041] A preset number of historical temperature differences corresponding to each sub-region are averaged to obtain an average historical temperature difference corresponding to each sub-region;
[0042] The maximum average historical temperature difference is determined from the average historical temperature differences corresponding to each sub-area as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0043] The bushing thermal diagnosis method provided by the embodiment of the present invention obtains the preset number of historical regional temperatures corresponding to each sub-region for the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively, and compares the target regional temperature corresponding to each sub-region with each historical regional temperature, respectively, to obtain the preset number of historical temperature differences corresponding to each sub-region, thereby ensuring the accuracy of the preset number of historical temperature differences corresponding to each sub-region. The preset number of historical temperature differences corresponding to each sub-region are averaged to obtain the average historical temperature difference corresponding to each sub-region, thereby ensuring the accuracy of the average historical temperature difference corresponding to each sub-region. The maximum average historical temperature difference is determined from the average historical temperature differences corresponding to each sub-region as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the determined time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0044] In combination with the first aspect, in a seventh implementation manner of the first aspect, thermal diagnosis is performed on the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the airspace temperature difference information and the time domain temperature difference information, including:
[0045] For the A-phase bushing, the B-phase bushing, and the C-phase bushing, obtain the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information;
[0046] Compare the airspace temperature difference information with the airspace temperature threshold, and compare the time domain temperature difference information with the time domain temperature difference information;
[0047] When the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A phase bushing or / and the B phase bushing or / and the C phase bushing is heated.
[0048] The bushing thermal diagnosis method provided in the embodiment of the present invention obtains, for the A-phase bushing, the B-phase bushing and the C-phase bushing, the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information, compares the airspace temperature difference information with the airspace temperature threshold, and compares the time domain temperature difference information with the time domain temperature difference information. When the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A-phase bushing or / and the B-phase bushing or / and the C-phase bushing is heated, thereby ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0049] According to a second aspect, an embodiment of the present invention further provides a casing thermal diagnosis device, comprising:
[0050] An acquisition module is used to acquire a to-be-processed bushing atlas, wherein the to-be-processed bushing atlas includes atlases corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing;
[0051] A feature extraction module is used to extract features from the casing map to be processed, and determine a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features;
[0052] A determination module is used to perform data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing;
[0053] The diagnosis module is used to perform thermal diagnosis on the A-phase bushing, the B-phase bushing and the C-phase bushing according to the airspace temperature difference information and the time domain temperature difference information.
[0054] The bushing thermal diagnosis device provided by the embodiment of the present invention obtains the bushing spectrum to be processed, and then extracts features of the bushing spectrum to be processed, and determines the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum from the bushing spectrum to be processed according to the extracted features, thereby ensuring the accuracy of the determined candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum. Data analysis is performed on the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the determined airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing. Then, according to the airspace temperature difference information and the time domain temperature difference information, thermal diagnosis is performed on the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing, and the C-phase bushing. The above device does not require manual use of handheld devices for offline inspection, thereby not only ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, but also improving the efficiency of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, and ensuring real-time grasp of the equipment status, so that the bushing thermal fault can be effectively diagnosed in time.
[0055] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the casing thermal diagnosis method in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.
[0056] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the casing thermal diagnosis method in the first aspect or any one of the embodiments of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0058] Figure 1 is a flow chart of a casing thermal diagnosis method provided by an embodiment of the present invention;
[0059] Figure 2 is a flow chart of a casing thermal diagnosis method provided by another embodiment of the present invention;
[0060] Figure 3 It is a schematic diagram of extracting features from a casing map to be processed in a casing thermal diagnosis method provided by another embodiment of the present invention;
[0061] Figure 4 is a flow chart of a casing thermal diagnosis method provided by another embodiment of the present invention;
[0062] Figure 5 is a schematic diagram of target registration of three-phase bushings in a bushing thermal diagnosis method provided by another embodiment of the present invention;
[0063] Figure 6 It is a schematic diagram of calculating the time domain temperature difference information and the space domain temperature difference information in the casing thermal diagnosis method provided by another embodiment of the present invention;
[0064] Figure 7 This is a functional module diagram of a casing thermal diagnosis device provided by an embodiment of the present invention;
[0065] Figure 8 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0067] It should be noted that the execution subject of the casing thermal diagnosis method provided in the embodiment of the present application may be a casing thermal diagnosis device, and the casing thermal diagnosis device may be implemented as part or all of a computer device through software, hardware, or a combination of software and hardware, wherein the computer device may be a server or a terminal, wherein the server in the embodiment of the present application may be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, and other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.
[0068] In one embodiment of the present application, Figure 1 As shown, a casing thermal diagnosis method is provided, and the method is applied to electronic equipment as an example for explanation, comprising the following steps:
[0069] S11, obtaining a casing map to be processed.
[0070] The bushing atlas to be processed includes the atlases corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0071] Specifically, the data acquisition device can collect data on the bushing of the transformer in real time, and collect the bushing map to be processed corresponding to the bushing of the transformer. The electronic device can obtain the bushing map to be processed corresponding to the bushing of the transformer collected by the data acquisition device based on the connection with the data acquisition device.
[0072] The data acquisition device may be an infrared thermal imager or other data acquisition devices. When the data acquisition device is an infrared thermal imager, the infrared thermal imager may acquire infrared thermal image spectra corresponding to the transformer bushing.
[0073] S12, extracting features from the casing map to be processed, and determining a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features.
[0074] Specifically, the electronic device can extract features of the bushing map to be processed based on the deep learning model, and then identify the bushing map to be processed according to the extracted features, and determine the candidate A phase bushing map, the candidate B phase bushing map and the candidate C phase bushing map from the bushing map to be processed.
[0075] This step will be described in detail below.
[0076] S13, respectively performing data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map to determine the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0077] In an optional embodiment, the electronic device can perform atlas image recognition on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map, respectively, obtain temperature information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, perform data analysis on the temperature information, and determine the spatial temperature difference information and time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0078] This step will be described in detail below.
[0079] S14. Perform thermal diagnosis on the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the air-domain temperature difference information and the time-domain temperature difference information.
[0080] In an optional embodiment, after obtaining the airspace temperature difference information and time domain temperature difference information corresponding to the A phase bushing, the B phase bushing and the C phase bushing, the electronic device can respectively compare the airspace temperature difference information and the time domain temperature difference information with the preset airspace temperature threshold and the preset time domain temperature threshold, and perform thermal diagnosis on the A phase bushing, the B phase bushing and the C phase bushing according to the comparison results.
[0081] This step will be described in detail below.
[0082] The bushing thermal diagnosis method provided by the embodiment of the present invention obtains the bushing spectrum to be processed, then extracts features of the bushing spectrum to be processed, and determines the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum from the bushing spectrum to be processed according to the extracted features, thereby ensuring the accuracy of the determined candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum. Data analysis is performed on the candidate A-phase bushing spectrum, the candidate B-phase bushing spectrum, and the candidate C-phase bushing spectrum respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the airspace temperature difference information and the time domain temperature difference information corresponding to the determined A-phase bushing, the B-phase bushing, and the C-phase bushing. Then, according to the airspace temperature difference information and the time domain temperature difference information, the A-phase bushing, the B-phase bushing, and the C-phase bushing are thermally diagnosed, thereby ensuring the accuracy of the thermal diagnosis of the A-phase bushing, the B-phase bushing, and the C-phase bushing. The above method does not require manual use of handheld devices for offline inspections, thereby not only ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, but also improving the efficiency of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing, and ensuring real-time grasp of the equipment status, so that the bushing thermal fault can be effectively diagnosed in time.
[0083] In one embodiment of the present application, Figure 2As shown, a casing thermal diagnosis method is provided, and the method is applied to electronic equipment as an example for explanation, comprising the following steps:
[0084] S21, obtaining a casing map to be processed.
[0085] The bushing atlas to be processed includes the atlases corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0086] For more information about this step, see Figure 1 The introduction of S11 will not be elaborated here.
[0087] S22, extracting features from the casing map to be processed, and determining a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features.
[0088] In an optional embodiment of the present application, the above S22 "extracting features from the casing map to be processed, and determining candidate A-phase casing maps, candidate B-phase casing maps, and candidate C-phase casing maps from the casing map to be processed according to the extracted features" may include the following steps:
[0089] S221. Based on the two convolutional layer branches in the casing recognition model, convolution processing is performed on the casing map to be processed to generate a first feature and a second feature.
[0090] In an optional implementation of the present application, the electronic device may utilize two convolutional layer branches in the casing recognition model to perform up-sampling convolution processing and down-sampling convolution processing on the casing map to be processed, respectively, to generate a first feature and a second feature.
[0091] The casing recognition model may be a model based on manual features, such as a DPM (Deformable Parts Model) improved, or a convolutional neural network model improved, wherein the neural network model may be a YOLO (You Only Look Once) detector, an R-CNN (Region-based Convolutional Neural Networks) model, an SSD (Single Shot MultiBox) detector, and a Mask R-CNN (Mask Region-based Convolutional Neural Networks) model, etc. The embodiment of the present application does not specifically limit the casing recognition model.
[0092] In an optional implementation of the present application, the above S221 "performing convolution processing on the casing map to be processed based on the two convolution layer branches in the casing recognition model to generate the first feature and the second feature" may include the following steps:
[0093] (1) Based on the first convolutional layer branch in the casing recognition model, the casing map to be processed is first amplified and then convolved to generate the first feature.
[0094] (2) Based on the second convolutional layer branch in the casing recognition model, the casing map to be processed is first reduced and then convolved in a loop to generate a second feature.
[0095] Specifically, the electronic device can enlarge the sleeve map to be processed based on the first convolution layer branch in the sleeve recognition model and then perform convolution loop processing to generate a first feature; and reduce the sleeve map to be processed based on the second convolution layer branch in the sleeve recognition model and then perform convolution loop processing to generate a second feature.
[0096] S222: Fuse the first feature and the second feature to generate a fused feature.
[0097] In an optional implementation, after acquiring the first feature and the second feature, the electronic device may add the first feature and the second feature to generate a fusion feature.
[0098] In another optional implementation, after acquiring the first feature and the second feature, the electronic device may concatenate the first feature and the second feature to generate a fusion feature.
[0099] S223, identifying the fusion features, and determining a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing maps to be processed.
[0100] In an optional implementation of the present application, the above S223 "identifying the fusion feature and determining the candidate A-phase casing map, the candidate B-phase casing map and the candidate C-phase casing map from the casing maps to be processed" may include the following steps:
[0101] (1) Perform convolution processing on the fused features based on the conditional random field to generate the target features.
[0102] (2) Identify the target features and determine the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map from the casing maps to be processed.
[0103] Specifically, after acquiring the fused features, the electronic device can perform convolution processing on the fused features based on the conditional random field to generate target features. The electronic device identifies the target features, and according to the result of identifying the target features, determines the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map from the casing maps to be processed.
[0104] like Figure 3 As shown, the electronic device can input the to-be-processed casing map into the casing recognition model. The first convolutional layer branch in the casing recognition model, that is, Figure 2 The convolutional layer branch in the middle and upper part first amplifies the casing image to be processed and then performs convolution cycle processing to generate the first feature. Figure 2 The convolution layer branch in the middle and lower part performs a convolution cycle on the casing map to be processed by first reducing it and then performing a convolution cycle to generate a second feature. After generating the first feature and the second feature, the electronic device performs a fusion process on the first feature and the second feature to generate a fusion feature. Then, the fusion feature is convolved based on the conditional random field to generate a target feature. The electronic device identifies the target feature and determines the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map from the casing map to be processed based on the result of identifying the target feature.
[0105] S23, respectively performing data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map to determine the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0106] For more information about this step, see Figure 1 The introduction of S13 will not be elaborated here.
[0107] S24. Perform thermal diagnosis on the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the air-domain temperature difference information and the time-domain temperature difference information.
[0108] For more information about this step, see Figure 1 The introduction of S14 will not be elaborated here.
[0109] The bushing thermal diagnosis method provided by the embodiment of the present invention first enlarges the bushing map to be processed based on the first convolution layer branch in the bushing recognition model and then performs convolution cycle processing to generate the first feature, thereby ensuring the accuracy of the generated first feature. Based on the second convolution layer branch in the bushing recognition model, the bushing map to be processed is first reduced and then convolution cycle processing is performed to generate the second feature, thereby ensuring the accuracy of the generated second feature. The first feature and the second feature are fused to generate a fused feature, thereby ensuring the accuracy of the generated fused feature. Then, the fused feature is convoluted based on the conditional random field to generate a target feature, thereby ensuring the accuracy of the generated target feature. The target feature is identified, and the candidate A phase bushing map, the candidate B phase bushing map, and the candidate C phase bushing map are determined from the bushing map to be processed, thereby ensuring the accuracy of determining the candidate A phase bushing map, the candidate B phase bushing map, and the candidate C phase bushing map.
[0110] In one embodiment of the present application, Figure 4 As shown, a casing thermal diagnosis method is provided, and the method is applied to electronic equipment as an example for explanation, comprising the following steps:
[0111] S31, obtaining a bushing atlas to be processed, wherein the bushing atlas to be processed includes atlases corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0112] For more information about this step, see Figure 2 The introduction of S21 will not be elaborated here.
[0113] S32, extracting features from the casing map to be processed, and determining a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features.
[0114] For more information about this step, see Figure 2 The introduction of S22 will not be elaborated here.
[0115] S33, respectively performing data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map to determine the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0116] In an optional implementation of the present application, the above S33 "perform data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing" may include the following steps:
[0117] S331. Based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each bushing map, position alignment is performed on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map to obtain the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map.
[0118] Specifically, after the electronic device obtains the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map, it can, based on the position information of the A-phase bushing, the B-phase bushing, and the C-phase bushing in each bushing map, use a preset image registration method to positionally align the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map with the corresponding historical A-phase bushing map, the historical B-phase bushing map, and the historical C-phase bushing map, respectively. It can also use a preset image registration method to positionally configure the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map, so as to obtain the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map.
[0119] Among them, the preset image registration method can be any one of an image registration method based on grayscale information, a registration method based on a transform domain, an image registration method based on a feature, and an image registration method based on a registration network.
[0120] Image registration methods based on grayscale information generally do not require complex pre-processing of images, but use some statistical information of the grayscale of the image itself to measure the similarity of images. The main feature is that it is simple to implement, but the scope of application is narrow. It cannot be directly used to correct nonlinear deformation of images, and it often requires a huge amount of calculation in the search process of the optimal transformation. After decades of development, people have proposed many image registration methods based on grayscale information, which can be roughly divided into three categories: cross-correlation method (also known as template matching method), sequential similarity detection matching method, and mutual information method.
[0121] The image registration method based on transform domain can be the Fourier transform method, which has the following main advantages: image translation, rotation, affine and other transformations are all reflected accordingly in the Fourier transform domain; the method using transform domain may also achieve a certain degree of robustness against noise; because the Fourier transform has a mature and fast algorithm and is easy to implement in hardware, it has unique advantages in algorithm implementation.
[0122] The common point of feature-based image registration methods is that the image to be registered must be preprocessed first, that is, the process of image segmentation and feature extraction, and then the extracted features are used to complete the matching between the features of the two images, and the registration mapping relationship between the images is established through the matching relationship of the features. Since there are many kinds of features that can be used in the image, a variety of feature-based methods have been generated. Commonly used image features include: feature points (including corner points, high curvature points, etc.), straight line segments, edges, contours, closed areas, feature structures, and statistical features such as moment invariants, center of gravity, etc.
[0123] The construction and training of the target registration network in the image registration method based on the registration network include: using the AffNet registration network to predict a pair of affine transformations; finally, the corresponding transformation is performed through the spatial transformer to obtain the registration of the target in shape. The registration loss uses the HardNegC loss function, that is, the descriptor is obtained through the descriptor network (HardNet network), and the n×n descriptor distance matrix is calculated as the registration distance.
[0124] Among them, a registration network based on affine transformation is proposed to achieve the registration between any segmented bushing positions. For example, the registration results between three-phase bushings are shown in the attached figure. Figure 5 Such target registration can provide data basis and accuracy guarantee for the subsequent automatic temperature difference information calculation.
[0125] S332, respectively perform sub-region segmentation on the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map to obtain sub-regions corresponding to the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map.
[0126] Specifically, after position alignment is performed on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map to obtain the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, the electronic device can perform sub-region segmentation on the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map according to the map sizes of the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively, to obtain the sub-regions corresponding to the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map.
[0127] Exemplarily, the electronic device can divide the target A phase bushing map, the target B phase bushing map and the target C phase bushing map into four sub-areas according to the map sizes of the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, respectively, and record them as A1, A2, A3, A4; B1, B2, B3, B4; C1, C2, C3, C4.
[0128] S333, obtaining the target area temperature corresponding to each sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map.
[0129] Specifically, the electronic device can analyze the spectrum pixel points corresponding to each sub-region respectively to obtain the pixel temperature corresponding to each pixel point in each sub-region. Then, for each sub-region, the electronic device calculates the maximum pixel temperature value among the pixel temperatures corresponding to each pixel point in the sub-region, and uses the maximum pixel temperature value as the target region temperature corresponding to the sub-region.
[0130] For example, taking the A1 sub-region as an example, assuming that the A1 sub-region includes 4 pixels, and the pixel temperatures corresponding to each pixel are 30°C, 31°C, 28°C, and 29°C, respectively, the electronic device determines that the maximum pixel temperature value is 31°C from the 4 pixel temperatures, and therefore uses 31°C as the target region temperature corresponding to the A1 sub-region. The electronic device obtains the target region temperatures corresponding to other sub-regions in the same manner as the A1 sub-region.
[0131] S334. Based on the relationship between the temperatures of the target areas, calculate the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0132] In an optional implementation of the present application, the above S334 "calculating the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing based on the relationship between the temperatures of each target area" may include the following steps:
[0133] (1) For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, the maximum target area temperature and the minimum target area temperature are determined from the target area temperatures corresponding to the sub-areas corresponding to the respective bushing maps.
[0134] Specifically, for the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, after obtaining the target area temperature corresponding to each sub-area, the electronic device can respectively obtain the maximum target area temperature and the minimum target area temperature in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map.
[0135] Exemplarily, taking the target A phase bushing map as an example, the electronic device can obtain the target area temperatures corresponding to the A1 sub-area, A2 sub-area, A3 sub-area, and A4 sub-area in the target A phase bushing map, and then determine the maximum target area temperature and the minimum target area temperature from the target area temperatures corresponding to the A1 sub-area, A2 sub-area, A3 sub-area, and A4 sub-area. According to this method, the electronic device can sequentially obtain the maximum target area temperature and the minimum target area temperature in the target B phase bushing map and the target C phase bushing map.
[0136] (2) The temperature field distribution of the A-phase bushing, the B-phase bushing, and the C-phase bushing is calculated by subtracting the minimum target area temperature from the maximum target area temperature.
[0137] Specifically, for the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, the electronic device uses the maximum target area temperature minus the minimum target area temperature to calculate the corresponding own temperature field distribution of the A phase bushing, the B phase bushing and the C phase bushing.
[0138] For example, the target A-phase bushing map is used as an example to illustrate that after determining the maximum target area temperature and the minimum target area temperature from the target area temperatures corresponding to the A1 sub-area, the A2 sub-area, the A3 sub-area, and the A4 sub-area, the maximum target area temperature is subtracted from the minimum target area temperature to calculate the corresponding temperature field distribution of the A-phase bushing. The electronic device calculates the corresponding temperature field distribution of the B-phase bushing and the C-phase bushing in the same way as it calculates the corresponding temperature field distribution of the A-phase bushing.
[0139] (3) The target area temperatures of the corresponding sub-areas in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map are compared to obtain the target area temperature differences corresponding to the corresponding sub-areas.
[0140] Specifically, after the electronic device calculates the target area temperature corresponding to each sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, it can compare the target area temperatures of each corresponding sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map to obtain the target area temperature difference corresponding to each corresponding sub-area.
[0141] Exemplarily, assuming that the A1 sub-region, the B1 sub-region, and the C1 sub-region correspond to each other, the A2 sub-region, the B2 sub-region, and the C2 sub-region correspond to each other, the A3 sub-region, the B3 sub-region, and the C3 sub-region correspond to each other, and the A4 sub-region, the B4 sub-region, and the C4 sub-region correspond to each other, then the electronic device can respectively calculate the temperature difference between the A1 sub-region, the B1 sub-region, and the C1 sub-region, the temperature difference between the A2 sub-region, the B2 sub-region, and the C2 sub-region, the temperature difference between the A3 sub-region, the B3 sub-region, and the C3 sub-region, and the temperature difference between the A4 sub-region, the B4 sub-region, and the C4 sub-region, thereby obtaining the target area temperature difference corresponding to each corresponding sub-region.
[0142] (4) Determine the maximum target area temperature difference from the target area temperature differences as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0143] Specifically, after calculating the target area temperature differences corresponding to the corresponding sub-areas, the electronic device can determine the maximum target area temperature difference from the target area temperature differences as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0144] Exemplarily, the electronic device compares the temperature differences between the A1 sub-region, the B1 sub-region, and the C1 sub-region, the temperature differences between the A2 sub-region, the B2 sub-region, and the C2 sub-region, the temperature differences between the A3 sub-region, the B3 sub-region, and the C3 sub-region, and the temperature differences between the A4 sub-region, the B4 sub-region, and the C4 sub-region, to obtain the target area temperature differences corresponding to each corresponding sub-region, and then determines the maximum target area temperature difference from the target area temperature differences as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0145] (5) Based on the relationship between its own temperature field distribution and the temperature difference field distribution, the spatial temperature difference information is calculated.
[0146] In an optional implementation of the present application, the electronic device may add its own temperature field distribution and the temperature difference field distribution to calculate the airspace temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0147] In an optional implementation of the present application, the electronic device can multiply its own temperature field distribution and temperature difference field distribution by corresponding weight coefficients respectively, and then add them together to calculate the airspace temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0148] (6) For the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, a preset number of historical regional temperatures corresponding to each sub-region are obtained respectively.
[0149] Specifically, the electronic device can respectively obtain a preset number of historical regional temperatures corresponding to each sub-region in the target A phase bushing map, a preset number of historical regional temperatures corresponding to each sub-region in the target B phase bushing map, and a preset number of historical regional temperatures corresponding to each sub-region in the target C phase bushing map.
[0150] Among them, the preset number can be 10, 15, or 20, 25. The embodiment of the present application does not specifically limit the preset number.
[0151] Exemplarily, taking the A1 sub-region in the target A-phase bushing map as an example, the electronic device can obtain 15 historical region temperatures corresponding to the A1 sub-region.
[0152] (7) The target area temperature corresponding to each sub-area is compared with each historical area temperature to obtain a preset number of historical temperature differences corresponding to each sub-area.
[0153] Specifically, for each sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, the electronic device can compare the target area temperature corresponding to each sub-area with each historical area temperature to obtain a preset number of historical temperature differences corresponding to each sub-area.
[0154] Exemplarily, taking the A1 sub-region in the target A phase bushing map as an example, the electronic device can compare the target region temperature corresponding to the A1 sub-region with the 15 historical region temperatures respectively, and calculate the 15 historical temperature differences corresponding to the A1 sub-region. According to this method, the electronic device can obtain a preset number of historical temperature differences corresponding to the A2 sub-region, A3 sub-region, and A4 sub-region in the target A phase bushing map; a preset number of historical temperature differences corresponding to the B1 sub-region, B2 sub-region, B3 sub-region, and B4 sub-region in the target B phase bushing map; and a preset number of historical temperature differences corresponding to the C1 sub-region, C2 sub-region, C3 sub-region, and B4 sub-region in the target C phase bushing map.
[0155] (8) A preset number of historical temperature differences corresponding to each sub-region are averaged to obtain an average historical temperature difference corresponding to each sub-region.
[0156] Specifically, for each sub-area in the target A phase bushing map, the target B phase bushing map, and the target C phase bushing map, after the electronic device calculates a preset number of historical temperature differences corresponding to each sub-area, the electronic device can average the preset number of historical temperature differences corresponding to each sub-area to obtain an average historical temperature difference corresponding to each sub-area.
[0157] For example, taking the A1 sub-region in the target A-phase bushing map as an example, after the electronic device calculates and obtains 15 historical temperature differences corresponding to the A1 sub-region, the electronic device can average the 15 historical temperature differences to obtain the average historical temperature difference corresponding to the A1 sub-region. The electronic device calculates the average historical temperature difference corresponding to other sub-regions in the same way as the average historical temperature difference corresponding to the A1 sub-region.
[0158] (9) Determine the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-area as the time domain temperature difference information corresponding to the A phase bushing, the B phase bushing, and the C phase bushing.
[0159] Specifically, after calculating the average historical temperature difference corresponding to each sub-area, the electronic device determines the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-area in the target A phase bushing map, as the time domain temperature difference information corresponding to the A phase bushing; the electronic device determines the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-area in the target B phase bushing map, as the time domain temperature difference information corresponding to the B phase bushing; the electronic device determines the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-area in the target C phase bushing map, as the time domain temperature difference information corresponding to the C phase bushing.
[0160] For example, Figure 6 As shown, it is a schematic diagram of calculating the air-domain temperature difference information and the time-domain temperature difference information of the electronic device.
[0161] S34. Perform thermal diagnosis on the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the air-domain temperature difference information and the time-domain temperature difference information.
[0162] In an optional implementation manner of the present application, the above S34 "performing thermal diagnosis on the A-phase bushing, the B-phase bushing and the C-phase bushing according to the airspace temperature difference information and the time domain temperature difference information" may include the following steps:
[0163] S341. For the A-phase bushing, the B-phase bushing and the C-phase bushing, obtain the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information.
[0164] Optionally, for the A-phase bushing, the B-phase bushing, and the C-phase bushing, the electronic device may receive the airspace temperature difference information input by the user and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information.
[0165] Optionally, for the A-phase bushing, the B-phase bushing and the C-phase bushing, the electronic device may also receive airspace temperature difference information sent by other devices and airspace temperature thresholds and time domain temperature thresholds corresponding to the time domain temperature difference information.
[0166] S342: Compare the airspace temperature difference information with the airspace temperature threshold, and compare the time domain temperature difference information with the time domain temperature difference information.
[0167] Specifically, after obtaining the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information, the electronic device can compare the airspace temperature difference information with the airspace temperature threshold and compare the time domain temperature difference information with the time domain temperature difference information.
[0168] S343. When the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A phase bushing or / and the B phase bushing or / and the C phase bushing is heated.
[0169] Specifically, when the airspace temperature corresponding to the A-phase bushing is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A-phase bushing and / or the B-phase bushing and / or the C-phase bushing are heated.
[0170] The bushing thermal diagnosis method provided by the embodiment of the present invention performs position alignment on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each bushing map, and obtains the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map, thereby ensuring the accuracy of the obtained target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map, and can ensure the accuracy of data analysis on the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map. Then, the target A phase bushing map, the target B phase bushing map and the target C phase bushing map are respectively segmented into sub-regions to obtain the sub-regions corresponding to the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, thereby ensuring the accuracy of the sub-regions corresponding to the target A phase bushing map, the target B phase bushing map and the target C phase bushing map, and facilitating the study of the temperature information of the target A phase bushing map, the target B phase bushing map and the target C phase bushing map.
[0171] The electronic device obtains the target area temperature corresponding to each sub-area in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, and determines the maximum target area temperature and the minimum target area temperature from the target area temperature corresponding to the sub-area corresponding to each bushing map for the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, and respectively subtracts the minimum target area temperature from the maximum target area temperature to calculate the corresponding self-temperature field distribution of the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the calculated self-temperature field distribution of the A-phase bushing, the B-phase bushing, and the C-phase bushing. Then, the electronic device compares the target area temperature of each corresponding sub-area in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively, and obtains the target area temperature difference corresponding to each corresponding sub-area, thereby ensuring the accuracy of the obtained target area temperature difference corresponding to each corresponding sub-area. The maximum target area temperature difference is determined from the target area temperature difference as the temperature difference field distribution corresponding to the A-phase casing, the B-phase casing and the C-phase casing, thereby ensuring the accuracy of the obtained temperature difference field distribution corresponding to the A-phase casing, the B-phase casing and the C-phase casing. Based on the relationship between the own temperature field distribution and the temperature difference field distribution, the airspace temperature difference information is calculated, thereby ensuring the accuracy of the calculated airspace temperature difference information.
[0172] For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively obtain the preset number of historical regional temperatures corresponding to each sub-region, respectively compare the target regional temperature corresponding to each sub-region with each historical regional temperature, respectively, and obtain the preset number of historical temperature differences corresponding to each sub-region, thereby ensuring the accuracy of the preset number of historical temperature differences corresponding to each sub-region. Average the preset number of historical temperature differences corresponding to each sub-region to obtain the average historical temperature difference corresponding to each sub-region, thereby ensuring the accuracy of the average historical temperature difference corresponding to each sub-region. Determine the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-region as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the determined time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0173] For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, the electronic device obtains the preset number of historical regional temperatures corresponding to each sub-region, respectively, and compares the target regional temperature corresponding to each sub-region with each historical regional temperature, respectively, to obtain the preset number of historical temperature differences corresponding to each sub-region, thereby ensuring the accuracy of the preset number of historical temperature differences corresponding to each sub-region. The preset number of historical temperature differences corresponding to each sub-region are averaged to obtain the average historical temperature difference corresponding to each sub-region, thereby ensuring the accuracy of the average historical temperature difference corresponding to each sub-region. The maximum average historical temperature difference is determined from the average historical temperature differences corresponding to each sub-region as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing, thereby ensuring the accuracy of the determined time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0174] For the A-phase bushing, the B-phase bushing and the C-phase bushing, the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information are obtained, the airspace temperature difference information is compared with the airspace temperature threshold, and the time domain temperature difference information is compared with the time domain temperature difference information. When the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A-phase bushing and / or the B-phase bushing and / or the C-phase bushing are heated, thereby ensuring the accuracy of thermal diagnosis of the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0175] It should be understood that although Figure 1 , Figure 2 as well as Figure 4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 , Figure 2 as well as Figure 4 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.
[0176] like Figure 7 As shown, this embodiment provides a casing thermal diagnosis device, including:
[0177] An acquisition module 41 is used to acquire a bushing map to be processed, wherein the bushing map to be processed includes maps corresponding to the bushing of phase A, the bushing of phase B and the bushing of phase C;
[0178] A feature extraction module 42 is used to extract features from the casing map to be processed, and determine a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features;
[0179] A determination module 43 is used to perform data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing;
[0180] The diagnosis module 44 is used to perform thermal diagnosis on the A-phase bushing, the B-phase bushing and the C-phase bushing according to the spatial temperature difference information and the temporal temperature difference information.
[0181] In one embodiment of the present application, the feature extraction module 42 is specifically used to perform convolution processing on the casing map to be processed based on the two convolution layer branches in the casing recognition model to generate a first feature and a second feature; fuse the first feature and the second feature to generate a fused feature; identify the fused feature, and determine a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed.
[0182] In one embodiment of the present application, the feature extraction module 42 is specifically used to first enlarge the casing map to be processed and then perform convolution loop processing based on the first convolution layer branch in the casing recognition model to generate a first feature; and first reduce the casing map to be processed and then perform convolution loop processing based on the second convolution layer branch in the casing recognition model to generate a second feature.
[0183] In one embodiment of the present application, the feature extraction module 42 is specifically used to perform convolution processing on the fused features based on the conditional random field to generate target features; identify the target features, and determine the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map from the casing maps to be processed.
[0184] In one embodiment of the present application, the above-mentioned determination module 43 is specifically used to perform position alignment on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each bushing map to obtain the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map; perform sub-region segmentation on the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map respectively to obtain the sub-regions corresponding to the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map; obtain the target area temperature corresponding to each sub-region in the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map; based on the relationship between the temperatures of each target area, calculate the spatial temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
[0185] In one embodiment of the present application, the above-mentioned determination module 43 is specifically used to determine the maximum target area temperature and the minimum target area temperature from the target area temperatures corresponding to the sub-areas corresponding to each bushing map for the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map; respectively use the maximum target area temperature to subtract the minimum target area temperature to calculate the corresponding self-temperature field distribution of the A-phase bushing, the B-phase bushing, and the C-phase bushing; respectively compare the target area temperatures of each corresponding sub-area in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map to obtain the target area temperature difference corresponding to each corresponding sub-area; determine the maximum target area temperature difference from the target area temperature difference as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing; calculate the spatial temperature difference information based on the relationship between the self-temperature field distribution and the temperature difference field distribution.
[0186] In one embodiment of the present application, the above-mentioned determination module 43 is specifically used to obtain a preset number of historical regional temperatures corresponding to each sub-region for the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map; respectively compare the target regional temperature corresponding to each sub-region with each historical regional temperature to obtain a preset number of historical temperature differences corresponding to each sub-region; average the preset number of historical temperature differences corresponding to each sub-region to obtain an average historical temperature difference corresponding to each sub-region; determine the maximum average historical temperature difference from the average historical temperature differences corresponding to each sub-region as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing.
[0187] In one embodiment of the present application, the above-mentioned diagnostic module 44 is specifically used to obtain the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information for the A phase bushing, the B phase bushing and the C phase bushing; compare the airspace temperature difference information with the airspace temperature threshold, and compare the time domain temperature difference information with the time domain temperature difference information; when the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A phase bushing or / and the B phase bushing or / and the C phase bushing is hot.
[0188] For the specific limitations and beneficial effects of the casing thermal diagnosis device, please refer to the limitations of the casing thermal diagnosis method above, which will not be repeated here. Each module in the above casing thermal diagnosis device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0189] The embodiment of the present invention also provides an electronic device having the above Figure 7 The casing thermal diagnostic device is shown.
[0190] like Figure 8 As shown, Figure 8 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, a memory 54, and at least one communication bus 52. The communication bus 52 is used to realize the connection and communication between these components. The communication interface 53 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 53 may also include a standard wired interface and a wireless interface. The memory 54 may be a high-speed RAM memory (Random Access Memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 54 may optionally be at least one storage device located away from the aforementioned processor 51. The processor 51 may be combined with Figure 7 In the described device, the memory 54 stores an application program, and the processor 51 calls the program code stored in the memory 54 to execute any of the above method steps.
[0191] The communication bus 52 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 52 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0192] Among them, the memory 54 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 54 may also include a combination of the above types of memory.
[0193] The processor 51 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.
[0194] The processor 51 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.
[0195] Optionally, the memory 54 is also used to store program instructions. The processor 51 can call the program instructions to implement the present application Figure 1 , Figure 3 as well as Figure 4 The casing thermal diagnosis method shown in the embodiment.
[0196] The embodiment of the present invention further provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the casing thermal diagnosis method in any of the above method embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.
[0197] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A casing thermal diagnosis method, It is characterized in that include: Obtaining a bushing atlas to be processed, wherein the bushing atlas to be processed includes atlases corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing; Extracting features from the casing map to be processed, and determining a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features; Performing data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map, and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing, and the C-phase bushing; Performing thermal diagnosis on the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the air-domain temperature difference information and the time-domain temperature difference information; The data analysis of the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map is performed respectively to determine the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing, including: Based on the position information of the A-phase bushing, the B-phase bushing and the C-phase bushing in each of the bushing maps, position registration is performed on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map to obtain a target A-phase bushing map, a target B-phase bushing map and a target C-phase bushing map; Respectively performing sub-region segmentation on the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map to obtain sub-regions corresponding to the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map; Obtaining the target area temperature corresponding to each of the sub-areas in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map; Based on the relationship between the temperatures of the target areas, the spatial temperature difference information and the temporal temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing are calculated; Wherein, the calculating of the airspace temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing based on the relationship between the temperatures of the target areas includes: For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, determine the maximum target area temperature and the minimum target area temperature from the target area temperatures corresponding to the sub-areas corresponding to the respective bushing maps; The temperature field distributions of the A-phase bushing, the B-phase bushing, and the C-phase bushing are calculated by subtracting the minimum target area temperature from the maximum target area temperature; Respectively comparing the target area temperatures of the corresponding sub-areas in the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map to obtain target area temperature differences corresponding to the corresponding sub-areas; Determine the maximum target area temperature difference from the target area temperature differences as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing; The spatial temperature difference information is calculated based on the relationship between the own temperature field distribution and the temperature difference field distribution.
2. The method according to claim 1, It is characterized in that The extracting features of the casing map to be processed and determining a candidate A-phase casing map, a candidate B-phase casing map and a candidate C-phase casing map from the casing map to be processed according to the extracted features include: Based on two convolutional layer branches in the casing recognition model, convolution processing is performed on the casing map to be processed to generate a first feature and a second feature; fusing the first feature and the second feature to generate a fused feature; The fusion feature is identified, and the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map are determined from the casing maps to be processed.
3. The method according to claim 2, It is characterized in that The two convolutional layer branches in the casing recognition model respectively perform convolution processing on the casing map to be processed to generate a first feature and a second feature, including: Based on the first convolutional layer branch in the casing recognition model, the casing map to be processed is first amplified and then convolved to generate the first feature; Based on the second convolutional layer branch in the casing recognition model, the casing map to be processed is subjected to a reduction-first and then convolution cycle process to generate the second feature.
4. The method according to claim 2, It is characterized in that The step of identifying the fusion feature and determining the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map from the casing map to be processed includes: Performing convolution processing on the fused features based on a conditional random field to generate target features; The target feature is identified, and the candidate A-phase casing map, the candidate B-phase casing map, and the candidate C-phase casing map are determined from the casing maps to be processed.
5. The method according to claim 1, It is characterized in that The calculating, based on the relationship between the temperatures of the target areas, the time domain temperature difference information corresponding to the A phase bushing, the B phase bushing and the C phase bushing includes: For the target A-phase bushing map, the target B-phase bushing map, and the target C-phase bushing map, respectively obtain a preset number of historical regional temperatures corresponding to each of the sub-regions; Compare the target area temperature corresponding to each of the sub-areas with the historical area temperature to obtain a preset number of historical temperature differences corresponding to each of the sub-areas; Averaging a preset number of historical temperature differences corresponding to each of the sub-regions to obtain an average historical temperature difference corresponding to each of the sub-regions; The maximum average historical temperature difference is determined from the average historical temperature differences corresponding to the sub-areas as the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing.
6. The method according to claim 1, It is characterized in that The thermal diagnosis of the A-phase bushing, the B-phase bushing, and the C-phase bushing according to the air-domain temperature difference information and the time-domain temperature difference information includes: For the A-phase bushing, the B-phase bushing, and the C-phase bushing, obtaining the airspace temperature difference information and the airspace temperature threshold and the time domain temperature threshold corresponding to the time domain temperature difference information; Comparing the airspace temperature difference information with the airspace temperature threshold, and comparing the time domain temperature difference information with the time domain temperature difference information; When the airspace temperature is greater than the airspace temperature threshold or / and the time domain temperature is greater than the time domain temperature threshold, it is determined that the A-phase bushing or / and the B-phase bushing or / and the C-phase bushing is heated.
7. A casing thermal diagnostic device, It is characterized in that include: An acquisition module is used to acquire a map of the bushing to be processed, wherein the map of the bushing to be processed includes maps corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing; A feature extraction module is used to extract features from the casing map to be processed, and determine a candidate A-phase casing map, a candidate B-phase casing map, and a candidate C-phase casing map from the casing map to be processed according to the extracted features; A determination module is used to perform data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing; wherein, the data analysis on the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map respectively to determine the airspace temperature difference information and time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing includes: based on the position of the A-phase bushing, the B-phase bushing and the C-phase bushing in each of the bushing maps Based on the location information, the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map are aligned to obtain the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map; the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map are segmented into sub-regions to obtain the sub-regions corresponding to the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map; the target region temperature corresponding to each of the sub-regions in the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map is obtained; based on the location information, the candidate A-phase bushing map, the candidate B-phase bushing map and the candidate C-phase bushing map are aligned to obtain the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map ... Based on the relationship between the temperatures of each target area, the airspace temperature difference information and the time domain temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing are calculated; wherein, based on the relationship between the temperatures of each target area, the airspace temperature difference information corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing is calculated, including: for the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map, the maximum target area temperature and the minimum target area temperature are determined from the target area temperatures corresponding to the sub-areas corresponding to each bushing map; the maximum target area temperature is subtracted from the minimum target area temperature; the maximum target area temperature is respectively The temperature of the small target area is calculated to obtain the corresponding self-temperature field distribution of the A-phase bushing, the B-phase bushing and the C-phase bushing; the target area temperature of each corresponding sub-area in the target A-phase bushing map, the target B-phase bushing map and the target C-phase bushing map is compared to obtain the target area temperature difference corresponding to each corresponding sub-area; the maximum target area temperature difference is determined from the target area temperature difference as the temperature difference field distribution corresponding to the A-phase bushing, the B-phase bushing and the C-phase bushing; based on the relationship between the self-temperature field distribution and the temperature difference field distribution, the airspace temperature difference information is calculated; The diagnosis module is used to perform thermal diagnosis on the A-phase bushing, the B-phase bushing and the C-phase bushing according to the airspace temperature difference information and the time domain temperature difference information.
8. An electronic device, It is characterized in that The invention comprises a memory and a processor, wherein the memory stores computer instructions, and the processor executes the casing thermal diagnosis method according to any one of claims 1 to 6 by executing the computer instructions.
