CM-type on-load tap changer switching circuit electrical fault diagnosis system and method

Abstract

This invention provides an electrical fault diagnosis system and method for a CM-type on-load tap changer switching circuit. The electrical fault diagnosis system for the CM-type on-load tap changer switching circuit includes: a CM-type on-load tap changer; a waveform acquisition device connected in series with the CM-type on-load tap changer for acquiring the current waveform and corresponding time information generated by the CM-type on-load tap changer during the switching circuit; and a fault diagnosis device connected to the waveform acquisition device for performing fault diagnosis of the CM-type on-load tap changer based on the acquired current waveform and corresponding time information. The fault diagnosis device has a fault diagnosis model built based on the CatBoost algorithm, used to determine fault diagnosis information based on the input current waveform and corresponding time information.

Description

Technical Field

[0001] This invention relates to the field of electrical testing technology for on-load tap changer switching circuits, and particularly to an electrical fault diagnosis system and method for a CM-type on-load tap changer switching circuit. Background Technology

[0002] Currently, the industry uses switching process characteristic tests to determine the status of switching switches. This involves connecting a constant current source to the on-load tap changer and recording waveforms at high speed to test characteristics such as switching time, transition resistance connection timing, and three-phase asynchrony, in order to determine issues like mechanism jamming, contact fatigue, and timing disorder. However, this testing process heavily relies on the testing personnel's experience, and different personnel will inevitably produce different results, leading to uncontrollable testing procedures and outcomes, and a lack of intelligent diagnostic tools. Summary of the Invention

[0003] To address the aforementioned technical problems, embodiments of the present invention provide a CM-type on-load tap changer switching circuit electrical fault diagnosis system, comprising: A waveform acquisition device is connected in series with the CM type on-load tap changer under test to acquire the current waveform and corresponding time information generated by the CM type on-load tap changer during the switching circuit. The fault diagnosis device is connected to the waveform acquisition unit and is used to perform fault diagnosis of the CM type on-load tap changer based on the acquired current waveform and corresponding time information. The fault diagnosis device has a fault diagnosis model built based on the CatBoost algorithm, which is used to determine fault diagnosis information based on the input current waveform and the corresponding time information.

[0004] In one embodiment, the waveform acquisition device is a DC transition waveform acquisition device.

[0005] In one embodiment, the CM-type on-load tap changer includes a tap selector, a switching switch, and an output terminal connected in sequence, and the waveform acquisition device is connected in series between the tap selector and the output terminal.

[0006] Another embodiment of the present invention also provides a method for diagnosing electrical faults in a CM-type on-load tap changer switching circuit, applied to an electrical fault diagnosis system for a CM-type on-load tap changer switching circuit as described above, the method comprising: Collect the current waveform and corresponding timing information generated by the CM type on-load tap changer during the switching circuit; The current waveform and corresponding time information are processed by calling a fault diagnosis model pre-built based on the CatBoost algorithm to obtain the corresponding fault diagnosis information. Based on the fault diagnosis information, visualized fault diagnosis data is generated for users to view.

[0007] In one embodiment, the method further includes: Obtain historical current waveforms and corresponding historical time information generated by multiple CM-type on-load tap changers during switching circuits in a historical period; Determine the fault diagnosis label of the historical current waveform, wherein the fault diagnosis label indicates whether the historical current waveform has a fault and the type of fault; Training data is generated based on historical current waveforms with the aforementioned fault diagnosis tags and corresponding historical time information. An initial fault diagnosis model was constructed based on the CatBoost algorithm; The initial fault diagnosis model is trained using the training data to obtain the fault diagnosis model.

[0008] In one embodiment, the fault diagnosis tag for determining the historical current waveform includes: Determine the fault type of the historical current waveform; A fault code is generated based on the fault type; The fault diagnosis label is generated based on the fault code.

[0009] In one embodiment, the method further includes: During the training of the initial fault diagnosis model using the training data, the parameters of the initial fault diagnosis model are adjusted by combining information sharing and collaborative algorithms.

[0010] In one embodiment, the parameter adjustment of the initial fault diagnosis model using a combination of information sharing and collaborative algorithms includes: The parameters of the initial fault diagnosis model are adjusted using the PSO algorithm.

[0011] In one embodiment, the method further includes: Both the collected current waveforms and historical current waveforms were subjected to wavelet denoising processing.

[0012] In one embodiment, generating visualized fault diagnosis data for user viewing based on the fault diagnosis information includes: Based on the fault codes in the fault diagnosis information, the corresponding fault type is determined, and matching text data is generated based on the fault type. Alternatively, the fault location and corresponding fault information are highlighted in conjunction with the linear architecture diagram of the electrical fault diagnosis system for the CM type on-load tap changer switching circuit.

[0013] Based on the solutions of the above embodiments of this application, the electrical fault diagnosis method for the switching circuit of the CM type on-load tap changer proposed in this embodiment can improve the observability of the circuit switching process and achieve "full-process transparency". Moreover, by configuring a fault diagnosis model to judge the test switching time, bridging duration, contact bounce, three-phase asynchrony, and transition resistance waveform, it can automatically identify waveform anomalies, such as lack of bridging, open circuit resistance, and waveform distortion, thereby determining whether the CM type on-load tap changer has a fault and what kind of fault it has. The above process replaces manual interpretation, reduces misjudgment, and can be applied in batches.

[0014] Other features and advantages of this application will be set forth in the following description. The objectives and other advantages of this application can be realized and obtained through the structures particularly pointed out in the written description and drawings.

[0015] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the electrical fault diagnosis system for the CM type on-load tap changer switching circuit in an embodiment of the present invention.

[0018] Figure 2 This is a flowchart illustrating the electrical fault diagnosis method for the switching circuit of a CM-type on-load tap changer in an embodiment of the present invention.

[0019] Figure 3 This is a flowchart illustrating an electrical fault diagnosis method for a CM-type on-load tap changer switching circuit according to another embodiment of the present invention. Detailed Implementation

[0020] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.

[0021] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope of this disclosure will be apparent to those skilled in the art.

[0022] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0023] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0024] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0025] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0026] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely to serve as the basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.

[0027] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0028] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0029] like Figure 1 As shown, this embodiment of the invention provides an electrical fault diagnosis system for a CM-type on-load tap changer switching circuit, comprising: A waveform acquisition device is connected in series with the CM type on-load tap changer under test to acquire the current waveform and corresponding time information generated by the CM type on-load tap changer during the switching circuit. The fault diagnosis device is connected to the waveform acquisition unit and is used to perform fault diagnosis of the CM type on-load tap changer based on the acquired current waveform and corresponding time information. The fault diagnosis device has a fault diagnosis model built based on the CatBoost algorithm, which is used to determine fault diagnosis information based on the input current waveform and the corresponding time information.

[0030] In this embodiment, the waveform acquisition device is a DC transition waveform acquisition device. The CM-type on-load tap changer includes a main winding and a tap winding. The tap winding obtains electrical energy through an external polarity selector. It also includes a tap selector, a switching switch, and an output terminal connected in sequence. The tap selector is also connected to the tap winding. The waveform acquisition device is connected in series between the tap selector and the output terminal.

[0031] In another embodiment, such as Figure 2 As shown, the present invention also provides a method for diagnosing electrical faults in a CM-type on-load tap changer switching circuit, which is applied to the electrical fault diagnosis system for a CM-type on-load tap changer switching circuit as described above. The method includes: S1: Collect the current waveform and corresponding time information generated by the CM type on-load tap changer during the switching circuit; S2: Call the fault diagnosis model pre-built based on the CatBoost algorithm to process the current waveform and the corresponding time information to obtain the corresponding fault diagnosis information; S3: Generate visualized fault diagnosis data for users to view based on the fault diagnosis information.

[0032] In this embodiment, the above scheme can be applied to the fault diagnosis equipment in the electrical fault diagnosis system of the CM-type on-load tap changer switching circuit. In such a system, the system receives the current waveform and corresponding time information generated by the CM-type on-load tap changer during the switching circuit. Then, it calls a pre-built fault diagnosis model based on the CatBoost algorithm to process the received current waveform and corresponding time information, i.e., performs fault diagnosis based on the waveform to obtain the corresponding fault diagnosis information. After obtaining the fault diagnosis information output by the fault diagnosis model, the system cannot yet present it to the user. The system needs to process the fault diagnosis information, change its format and structure, and obtain visualized fault diagnosis data that can be viewed by the user.

[0033] Based on the above, it can be seen that the electrical fault diagnosis method for the switching circuit of the CM-type on-load tap changer proposed in this embodiment can improve the observability of the circuit switching process and achieve "full-process transparency". Furthermore, by configuring a fault diagnosis model to judge the test switching time, bridging duration, contact bounce, three-phase asynchrony, and transition resistance waveform, it effectively achieves automatic identification of waveform anomalies, such as missing bridging, open circuit resistance, and waveform distortion, thereby determining whether the CM-type on-load tap changer has a fault and what kind of fault it has. This process can completely replace manual interpretation, reduce misjudgments, and enable batch application.

[0034] In one embodiment, the method further includes: S4: Obtain the historical current waveforms and corresponding historical time information generated by multiple CM-type on-load tap changers during the switching circuit period in history; S5: Determine the fault diagnosis label of the historical current waveform, wherein the fault diagnosis label indicates whether the historical current waveform has a fault and the type of fault; S6: Training data is generated based on the historical current waveforms with the fault diagnosis tags and the corresponding historical time information; S7: Construct an initial fault diagnosis model based on the CatBoost algorithm; S8: Use the training data to train the initial fault diagnosis model to obtain the fault diagnosis model.

[0035] The above embodiments disclose a method for constructing a fault diagnosis model, including obtaining historical current waveforms and corresponding historical time information generated by multiple CM-type on-load tap changers during switching circuits over a historical period, i.e., obtaining a large amount of historical current waveform data. Then, the historical current waveform data can be manually labeled to determine whether the historical current waveforms have faults and what kind of faults they have, such as the fault type, i.e., determining matching fault diagnosis labels. Alternatively, other methods can be used to determine fault diagnosis labels, such as determining them based on historical diagnostic data. After obtaining the historical current waveforms with fault diagnosis labels and their corresponding historical time information, training data and detection data are formed based on this. Then, an initial fault diagnosis model is constructed based on the CatBoost algorithm, and this initial fault diagnosis model is trained using the training data to obtain the fault diagnosis model. Afterwards, the trained fault diagnosis model is tested using test data. Once the test is passed, the obtained fault diagnosis model can be put into use.

[0036] Furthermore, as shown in Figure 3, the fault diagnosis tag for determining the historical current waveform includes: S501: Determine the fault type of the historical current waveform; S502: Generate a fault code based on the fault type; S503: Generate the fault diagnosis label based on the fault code.

[0037] In this embodiment, when determining the fault diagnosis label, the fault type of the historical current waveform is identified. For example, based on the identified waveform anomalies, it is determined whether there are phenomena such as missing bridging, open circuit, waveform distortion, three-phase asynchrony, or abnormal transition resistance waveform. Simultaneously, historical time information is combined to judge the test switching time and bridging duration, and then it is determined whether there are faults of the following types, such as, but not limited to, R1 large, R1 small, R2 large, R2 small, abnormal switching duration, and abnormal bridging duration. Then, a corresponding fault code is configured for each fault type. Finally, a fault diagnosis label is generated based on the fault code. The result output by the fault diagnosis model is the content of this fault diagnosis label; that is, the fault diagnosis model outputs the fault code.

[0038] Specifically, in combination with, for example Figure 1 The CM-type on-load tap changer shown employs a switching mode combining transition resistance current limiting and fast mechanical switching. During switching, transition resistors R1 and R2 are first connected to bridge the old and new taps, limiting circulating current. Then, the main contacts are switched, and finally, transition resistors R1 and R2 are disconnected. In practical applications, based on the on-load tap changer field test guidelines and power transformer tap changer operation and maintenance guidelines, the following regulations are made regarding adjusting the resistance values ​​of R1 and R2, the contact resistance at positions 1-4, and the spring force of the energy storage spring: the deviation of transition resistors R1 and R2 from their factory values ​​must not exceed 10% of their original resistance; the switching time t is 50-70 ms; and the bridging time t1 is 2-7 ms. These regulations will also serve as reference rules for fault diagnosis.

[0039] As described above, the fault types involved in this embodiment are: R1 large, R1 small, R2 large, R2 small, abnormal switching time, and abnormal bridging time. These faults also include single faults and multi-dimensional faults; that is, the CM-type on-load tap changer may have a single fault or multiple faults simultaneously. For example, this embodiment involves 6 types of single faults, 13 types of two-dimensional composite faults, 12 types of three-dimensional composite faults, and 4 types of four-dimensional composite faults, totaling 35 fault categories. During model training, 10,000 samples can be extracted to prepare training and testing data.

[0040] Among them, the fault codes involved in a single fault include: 100000, 010000, 001000, 000100, 000010, 000001; Two-dimensional faults involve the following fault codes: 101000, 100100, 100001, 100010, 011000, 010100, 010010, 010001, 001010, 001001, 000110, 000101, 000011; The fault codes involved in three-dimensional faults include: 101010, 101001, 100110, 100101, 011010, 011001, 010110, 010101, 100011, 010011, 001011, 000111; The fault codes involved in four-dimensional faults include: 101011, 100111, 011011, 010111.

[0041] In another embodiment, the method further includes: S9: During the training of the initial fault diagnosis model using the training data, the parameters of the initial fault diagnosis model are adjusted by combining information sharing and collaborative algorithms.

[0042] By configuring this type of algorithm to adjust the model's parameters, the accuracy of parameter adjustment can be improved. Through continuous iterative updates, the model gradually approaches the optimal solution, which means that the optimal parameters are finally determined.

[0043] In this embodiment, the parameter adjustment of the initial fault diagnosis model by combining information sharing and collaborative algorithms includes: S901: The parameters of the initial fault diagnosis model are adjusted by combining the PSO algorithm.

[0044] The core idea of ​​the PSO algorithm is information sharing and collaboration to meet the needs of model parameter adjustment. Of course, other similar algorithms can also be used, and there are no specific limitations.

[0045] To optimize the data input to the fault diagnosis model, the method further includes: S10: Wavelet denoising processing is performed on the collected current waveform and historical current waveform.

[0046] Denoising can effectively reduce interference information on the fault diagnosis model and improve its diagnostic accuracy.

[0047] Furthermore, the step of generating visualized fault diagnosis data for user viewing based on the fault diagnosis information includes: S301: Determine the corresponding fault type based on the fault code in the fault diagnosis information, and generate matching text data based on the fault type, or highlight the fault location and corresponding fault information in conjunction with the linear architecture diagram of the electrical fault diagnosis system for the CM type on-load tap changer switching circuit.

[0048] For example, the system will determine the corresponding text data based on the fault codes output by the model, such as R1 being too large, R2 being too small, or abnormal switching time. Alternatively, it can be combined with the linear architecture diagram of the CM-type on-load tap changer switching circuit electrical fault diagnosis system, such as... Figure 1 The electrical structure diagram shown is used to highlight the fault area and mark the fault type, such as marking R1 being too large, R2 being too small, or abnormal switching time.

[0049] Another embodiment of the present invention provides an electrical fault diagnosis device for a CM-type on-load tap changer switching circuit, applied in the electrical fault diagnosis system for a CM-type on-load tap changer switching circuit as described above, the device comprising: The acquisition module is used to acquire the current waveform and corresponding time information generated by the CM type on-load tap changer during the switching circuit. The calling module is used to call the fault diagnosis model pre-built based on the CatBoost algorithm to process the current waveform and the corresponding time information to obtain the corresponding fault diagnosis information; The generation module is used to generate visualized fault diagnosis data for users to view based on the fault diagnosis information.

[0050] In one embodiment, the device further includes: The acquisition module is used to obtain the historical current waveforms and corresponding historical time information generated by multiple CM-type on-load tap changers during the switching circuit period in a historical period. A determination module is used to determine the fault diagnosis label of the historical current waveform, wherein the fault diagnosis label indicates whether the historical current waveform has a fault and the fault type; A generation module is used to generate training data based on historical current waveforms with the fault diagnosis tags and corresponding historical time information. The building block is used to construct an initial fault diagnosis model based on the CatBoost algorithm; The training module is used to train the initial fault diagnosis model using the training data to obtain the fault diagnosis model.

[0051] In one embodiment, the fault diagnosis tag for determining the historical current waveform includes: Determine the fault type of the historical current waveform; A fault code is generated based on the fault type; The fault diagnosis label is generated based on the fault code.

[0052] In one embodiment, the device further includes: An adjustment module is used to adjust the parameters of the initial fault diagnosis model by combining information sharing and collaborative algorithms during the training of the initial fault diagnosis model using the training data.

[0053] In one embodiment, the parameter adjustment of the initial fault diagnosis model using a combination of information sharing and collaborative algorithms includes: The parameters of the initial fault diagnosis model are adjusted using the PSO algorithm.

[0054] In one embodiment, the device further includes: The denoising module is used to perform wavelet denoising processing on the acquired current waveform and historical current waveform.

[0055] In one embodiment, generating visualized fault diagnosis data for user viewing based on the fault diagnosis information includes: Based on the fault codes in the fault diagnosis information, the corresponding fault type is determined, and matching text data is generated based on the fault type. Alternatively, the fault location and corresponding fault information are highlighted in conjunction with the linear architecture diagram of the electrical fault diagnosis system for the CM type on-load tap changer switching circuit.

[0056] Another embodiment of the present invention also provides a fault diagnosis device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the electrical fault diagnosis method for the CM type on-load tap changer switching circuit as described above.

[0057] Furthermore, one embodiment of the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the electrical fault diagnosis method for the switching circuit of a CM-type on-load tap changer as described above. It should be understood that the various solutions in this embodiment have the corresponding technical effects in the above-described method embodiments, and will not be repeated here.

[0058] Furthermore, embodiments of the present invention also provide a computer program product, which is tangibly stored on a computer-readable medium and includes computer-readable instructions that, when executed, cause at least one processor to perform an electrical fault diagnosis method for a CM-type on-load tap changer switching circuit, as described in the embodiments above.

[0059] It should be noted that the computer storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access storage medium (RAM), a read-only storage medium (ROM), an erasable programmable read-only storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only storage medium (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, system, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.

[0060] Furthermore, those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0061] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0062] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

Claims

1. A CM-type on-load tap changer switching circuit electrical fault diagnostic system, characterized by, include: A waveform acquisition device is connected in series with the CM type on-load tap changer under test to acquire the current waveform and corresponding time information generated by the CM type on-load tap changer during the switching circuit. The fault diagnosis device is connected to the waveform acquisition unit and is used to perform fault diagnosis of the CM type on-load tap changer based on the acquired current waveform and corresponding time information. The fault diagnosis device has a fault diagnosis model built based on the CatBoost algorithm, which is used to determine fault diagnosis information based on the input current waveform and the corresponding time information.

2. The CM-type on-load tap changer switching circuit electrical fault diagnostic system of claim 1, wherein, The waveform acquisition device is a DC transition waveform acquisition device.

3. The CM-type on-load tap changer switching circuit electrical fault diagnostic system of claim 1, wherein, The CM type on-load tap changer includes a tap selector, a switching switch and an output terminal connected in sequence, and the waveform acquisition device is connected in series between the tap selector and the output terminal.

4. A method for diagnosing electrical faults in a CM-type on-load tap changer switching circuit, applied in any one of claims 1-3, the method comprising: Collect the current waveform and corresponding time information generated by the CM-type on-load tap changer during the switching circuit; The current waveform and corresponding time information are processed by calling a fault diagnosis model pre-built based on the CatBoost algorithm to obtain the corresponding fault diagnosis information. Based on the fault diagnosis information, visualized fault diagnosis data is generated for users to view.

5. The CM-type on-load tap changer switching circuit electrical fault diagnostic method of claim 4, wherein, The method further includes: Obtain historical current waveforms and corresponding historical time information generated by multiple CM-type on-load tap changers during switching circuits in a historical period; Determine the fault diagnosis label of the historical current waveform, wherein the fault diagnosis label indicates whether the historical current waveform has a fault and the type of fault; Training data is generated based on historical current waveforms with the aforementioned fault diagnosis tags and corresponding historical time information. An initial fault diagnosis model was constructed based on the CatBoost algorithm; The initial fault diagnosis model is trained using the training data to obtain the fault diagnosis model.

6. The CM-type on-load tap changer switching circuit electrical fault diagnostic method of claim 5, wherein, The fault diagnosis tag for determining the historical current waveform includes: Determine the fault type of the historical current waveform; A fault code is generated based on the fault type; The fault diagnosis label is generated based on the fault code.

7. The CM-type on-load tap changer switching circuit electrical fault diagnostic method of claim 5, wherein, The method further includes: During the training of the initial fault diagnosis model using the training data, the parameters of the initial fault diagnosis model are adjusted by combining information sharing and collaborative algorithms.

8. The CM-type on-load tap changer switching circuit electrical fault diagnostic method of claim 7, wherein, The parameter adjustment of the initial fault diagnosis model by combining information sharing and collaborative algorithms includes: The parameters of the initial fault diagnosis model are adjusted using the PSO algorithm.

9. The electrical fault diagnosis method for the switching circuit of a CM-type on-load tap changer according to claim 5, characterized in that, The method further includes: Both the collected current waveforms and historical current waveforms were subjected to wavelet denoising processing.

10. The electrical fault diagnosis method for the switching circuit of a CM-type on-load tap changer according to claim 6, characterized in that, The process of generating visualized fault diagnosis data for user viewing based on the fault diagnosis information includes: Based on the fault codes in the fault diagnosis information, the corresponding fault type is determined, and matching text data is generated based on the fault type. Alternatively, the fault location and corresponding fault information are highlighted in conjunction with the linear architecture diagram of the electrical fault diagnosis system for the CM type on-load tap changer switching circuit.

Images