Transformer short circuit type discrimination method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to the technical field of transformer operation maintenance, and provides a transformer short circuit type discrimination method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a voltage time-domain signal and a current time-domain signal at a port of a target transformer; according to the voltage time-domain signal and the current time-domain signal, voltage spectrum characteristics and current spectrum characteristics are obtained; and obtaining the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-constructed transformer short-circuit discrimination model. The method can improve the discrimination precision of the short circuit type of the transformer.

Description

Technical Field

[0001] The present application relates to the technical field of transformer operation and maintenance, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for determining the short-circuit type of a transformer. Background Art

[0002] Transformers are key equipment in power systems and are widely used for voltage conversion and transmission and distribution of electric energy. The operating environment of transformers is complex and the load fluctuates greatly, so transformer short-circuit failures often occur. Short-circuit failures not only affect the operating status of the transformer itself, but may also cause serious power grid failures. Therefore, quickly and accurately identifying the type of transformer short-circuit is of great significance to the safety and reliability of the power system.

[0003] At present, the short-circuit type of transformer can be determined by analyzing the electrical characteristic quantity. However, the existing transformer short-circuit determination method mainly relies on the mutation of a single electrical characteristic quantity, and the determination accuracy is low. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining the short-circuit type of a transformer in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for determining the short-circuit type of a transformer, comprising:

[0006] Acquire voltage time domain signal and current time domain signal at the target transformer port;

[0007] Obtaining voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal;

[0008] The short-circuit type of the target transformer is obtained according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-constructed transformer short-circuit discrimination model.

[0009] In one embodiment, the step of obtaining a voltage time domain signal and a current time domain signal at a target transformer port includes:

[0010] Obtain voltage and current recording data at the target transformer port;

[0011] Performing data format conversion on the voltage recording data and the current recording data to obtain an initial voltage time domain signal and an initial current time domain signal;

[0012] The initial voltage time-domain signal and the initial current time-domain signal are subjected to denoising and normalization processing to obtain a voltage time-domain signal and a current time-domain signal.

[0013] In one embodiment, obtaining voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal includes:

[0014] Obtaining a voltage waveform diagram and a current waveform diagram according to the voltage time domain signal and the current time domain signal;

[0015] Performing time-frequency domain conversion on the voltage waveform diagram and the current waveform diagram to obtain a voltage frequency domain diagram and a current frequency domain diagram;

[0016] Voltage spectrum characteristics and current spectrum characteristics are obtained according to the frequency components and harmonic characteristics of the voltage frequency domain diagram and the current frequency domain diagram.

[0017] In one embodiment, before obtaining the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-built transformer short-circuit discrimination model, the method further includes:

[0018] Acquire a simulated short-circuit feature training set; each simulated short-circuit feature sample in the simulated short-circuit feature training set has a corresponding simulated short-circuit type; the simulated short-circuit feature samples include voltage spectrum feature simulation samples and current spectrum feature simulation samples;

[0019] The simulated short-circuit feature samples are used as input and the simulated short-circuit types are used as labels to train a deep learning model to obtain a transformer short-circuit discrimination model.

[0020] In one embodiment, the step of obtaining a simulation short circuit feature training set includes:

[0021] Obtain the short-circuit test simulation results of the transformer model;

[0022] According to the short-circuit test simulation results, voltage time-domain simulation signals and current time-domain simulation signals of various simulated short-circuit types at the transformer model port are obtained;

[0023] According to the voltage time-domain simulation signals and the current time-domain simulation signals of various simulated short-circuit types, voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types are obtained;

[0024] A simulated short-circuit feature training set is obtained based on the voltage spectrum feature simulation samples and current spectrum feature simulation samples of the various simulated short-circuit types.

[0025] In one embodiment, the simulated short-circuit feature sample is used as input, the simulated short-circuit type is used as a label, and a deep learning model is trained to obtain a transformer short-circuit discrimination model, including:

[0026] Taking the simulated short-circuit feature sample as input and the simulated short-circuit type as a label, a deep learning model is trained to obtain an initial transformer short-circuit discrimination model;

[0027] Acquire a real short-circuit feature training set; each real short-circuit feature sample in the real short-circuit feature training set has a corresponding real short-circuit type; the real short-circuit feature samples include real voltage spectrum feature samples and real current spectrum feature samples;

[0028] The initial transformer short-circuit discrimination model is trained with the real short-circuit feature sample as input and the real short-circuit type as a label to obtain a transformer short-circuit discrimination model.

[0029] In a second aspect, the present application also provides a device for determining the short-circuit type of a transformer, comprising:

[0030] A time domain signal acquisition module, used to acquire a voltage time domain signal and a current time domain signal at a target transformer port;

[0031] A spectrum feature acquisition module, used to obtain voltage spectrum features and current spectrum features according to the voltage time domain signal and the current time domain signal;

[0032] The short-circuit type acquisition module is used to obtain the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-built transformer short-circuit discrimination model.

[0033] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the above method.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to execute the above method.

[0035] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and the computer program is executed by a processor to execute the above method.

[0036] The above-mentioned transformer short-circuit type discrimination method, device, computer equipment, computer-readable storage medium and computer program product obtain the voltage time domain signal and current time domain signal at the target transformer port; obtain the voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal; obtain the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and the pre-constructed transformer short-circuit discrimination model. The present application obtains the short-circuit type of the target transformer based on the two electrical characteristic quantities of the voltage spectrum characteristics and the current spectrum characteristics; by discriminating the short-circuit type of the transformer through multiple electrical characteristic quantities, the discrimination accuracy of the transformer short-circuit type can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 An application environment diagram of a method for determining a transformer short-circuit type in one embodiment;

[0039] Figure 2 A schematic flow chart of a method for determining a transformer short-circuit type in one embodiment;

[0040] Figure 3 A schematic diagram of a process for obtaining a voltage time domain signal and a current time domain signal in one embodiment;

[0041] Figure 4 is a structural block diagram of a device for determining the short-circuit type of a transformer in one embodiment;

[0042] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The present application embodiment provides a method for determining the type of transformer short circuit, and the present embodiment can be executed by a computer device, such as Figure 1As shown, the computer device can obtain the voltage time domain signal and the current time domain signal at the target transformer port, and then obtain the short circuit type of the target transformer. It can be understood that the computer device can be implemented by a server, a terminal, or an interactive system between a terminal and a server. In this embodiment, the method includes Figure 2 The steps shown are:

[0045] Step S201, obtaining a voltage time domain signal and a current time domain signal at a target transformer port.

[0046] The transformer for which short circuit (fault) type identification is to be performed may be referred to as a target transformer.

[0047] The voltage time domain signal and current time domain signal at the port of the target transformer can be obtained when the transformer is in operation.

[0048] Step S202: obtaining voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal.

[0049] The voltage time domain signal and the current time domain signal can be analyzed and processed to obtain the voltage spectrum characteristics and the current spectrum characteristics.

[0050] Step S203, obtaining the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and the pre-built transformer short-circuit discrimination model.

[0051] The voltage spectrum characteristics and current spectrum characteristics of the transformer are different for different transformer short-circuit types. The voltage spectrum characteristics and current spectrum characteristics of the transformer have obvious indication of the short-circuit type and can effectively distinguish different short-circuit types. Therefore, the voltage spectrum characteristics and current spectrum characteristics of the transformer can be used as the basis for distinguishing the short-circuit type of the transformer. Based on the voltage spectrum characteristics and current spectrum characteristics of the transformer, a feature library can be established for each common short-circuit type to record the spectrum characteristics corresponding to different short-circuit types.

[0052] The transformer short-circuit discrimination model can extract deep features from the voltage spectrum features and current spectrum features to predict the transformer short-circuit type. The transformer short-circuit discrimination model is essentially a multi-classifier used to distinguish different transformer short-circuit types.

[0053] The voltage spectrum features and current spectrum features can be input into the pre-built transformer short-circuit identification model to quickly identify the short-circuit type of the target transformer. The short-circuit types of transformers generally include winding short circuit, turn-to-turn short circuit, ground short circuit and phase-to-phase short circuit.

[0054] In the above-mentioned method for distinguishing the short-circuit type of the transformer, the short-circuit type of the target transformer is obtained based on the two electrical characteristic quantities of the voltage spectrum characteristic and the current spectrum characteristic; by distinguishing the short-circuit type of the transformer through multiple electrical characteristic quantities, the distinction accuracy of the short-circuit type of the transformer can be improved. In addition, the present application distinguishes the short-circuit type of the transformer through multiple electrical characteristic quantities, and can realize online distinction of the short-circuit type of the transformer under complex working conditions, which can improve the adaptability of distinguishing sudden faults of the transformer.

[0055] In one embodiment, the voltage time domain signal and the current time domain signal at the target transformer port are obtained. The specific steps are as follows: Figure 3 As shown: Step S301, obtaining the voltage recording data and the current recording data at the target transformer port; Step S302, performing data format conversion on the voltage recording data and the current recording data to obtain an initial voltage time domain signal and an initial current time domain signal; Step S303, performing denoising and normalization processing on the initial voltage time domain signal and the initial current time domain signal to obtain a voltage time domain signal and a current time domain signal.

[0056] The voltage recording data and current recording data at the transformer port may usually be stored as specific binary files. The data cannot be directly analyzed. Therefore, it is necessary to convert the voltage recording data and the current recording data into a common processable format to obtain the initial voltage time domain signal and the initial current time domain signal.

[0057] The process of recording data acquisition may be accompanied by noise and interference, so it is necessary to denoise the initial voltage time domain signal and the initial current time domain signal. The filtering method can be used to denoise the initial voltage time domain signal and the initial current time domain signal, remove high-frequency interference, and retain the effective signal.

[0058] The denoised initial voltage time-domain signal and the initial current time-domain signal may be normalized so that the initial voltage time-domain signal and the initial current time-domain signal have the same dimension and are distributed in the same numerical range.

[0059] In this embodiment, the voltage recording data and the current recording data at the target transformer port are normalized to obtain a voltage time domain signal and a current time domain signal, thereby improving the accuracy of determining the short circuit type of the transformer.

[0060] In one of the embodiments, voltage spectrum characteristics and current spectrum characteristics are obtained according to voltage time domain signals and current time domain signals, and the specific steps are as follows: according to the voltage time domain signals and current time domain signals, a voltage waveform diagram and a current waveform diagram are obtained; the voltage waveform diagram and the current waveform diagram are converted into time-frequency domain to obtain a voltage frequency domain diagram and a current frequency domain diagram; according to the frequency components and harmonic characteristics of the voltage frequency domain diagram and the current frequency domain diagram, the voltage spectrum characteristics and the current spectrum characteristics are obtained.

[0061] The voltage waveform and the current waveform can be obtained based on the voltage time domain signal and the current time domain signal. The voltage waveform and the current waveform can be subjected to Fast Fourier Transform (FFT) to complete the time-frequency domain conversion of the voltage waveform and the current waveform to obtain the voltage frequency domain and the current frequency domain. The voltage spectrum characteristics and the current spectrum characteristics can be obtained based on the frequency components and harmonic characteristics of the voltage frequency domain and the current frequency domain, where different types of short circuits will produce different transient waveforms, and the transient waveforms have harmonic characteristics of different components.

[0062] In this embodiment, the voltage time domain signal and the current time domain signal are converted into the time-frequency domain to obtain the voltage spectrum characteristics and the current spectrum characteristics according to the frequency components and harmonic characteristics of the voltage frequency domain diagram and the current frequency domain diagram, so as to prepare data for the determination of the transformer short circuit type.

[0063] In one of the embodiments, before obtaining the short-circuit type of the target transformer based on the voltage spectrum characteristics, the current spectrum characteristics and the pre-built transformer short-circuit discrimination model, the method provided by the present application also includes: obtaining a simulated short-circuit feature training set; each simulated short-circuit feature sample in the simulated short-circuit feature training set has a corresponding simulated short-circuit type; the simulated short-circuit feature samples include voltage spectrum feature simulation samples and current spectrum feature simulation samples; using the simulated short-circuit feature samples as input and the simulated short-circuit type as a label, the deep learning model is trained to obtain a transformer short-circuit discrimination model.

[0064] The transformer model can be used to carry out various types of short-circuit tests to obtain a simulated short-circuit feature training set, wherein each simulated short-circuit feature sample in the simulated short-circuit feature training set has a corresponding simulated short-circuit type, and the simulated short-circuit feature samples include voltage spectrum feature simulation samples and current spectrum feature simulation samples.

[0065] The simulated short-circuit feature samples can be input into the deep learning model in sequence. The deep learning model automatically extracts the deep features in the simulated short-circuit feature samples through a multi-layer neural network to obtain the predicted short-circuit type corresponding to the simulated short-circuit feature samples.

[0066] The prediction accuracy of the deep learning model can be determined based on the labels and predicted short-circuit types corresponding to each simulated short-circuit feature sample; when the prediction accuracy of the deep learning model is greater than the first accuracy threshold, a transformer short-circuit discrimination model is obtained based on the deep learning model.

[0067] In this embodiment, the deep learning model is trained based on the simulated short-circuit feature training set to obtain a transformer short-circuit discrimination model to quickly discriminate the short-circuit type of the transformer. The response speed of the transformer short-circuit type discrimination is improved through deep learning technology.

[0068] In one of the embodiments, a simulated short-circuit feature training set is obtained, and the specific steps are as follows: obtain the short-circuit test simulation results of the transformer model; obtain the voltage time-domain simulation signal and the current time-domain simulation signal of various simulated short-circuit types at the transformer model port based on the short-circuit test simulation results; obtain the voltage spectrum feature simulation samples and the current spectrum feature simulation samples of various simulated short-circuit types based on the voltage time-domain simulation signals and the current time-domain simulation signals of various simulated short-circuit types; obtain the simulated short-circuit feature training set based on the voltage spectrum feature simulation samples and the current spectrum feature simulation samples of various simulated short-circuit types.

[0069] According to the actual parameters of the transformer, a transformer model can be established in the COMSOL multi-physics simulation software, where the transformer model can also be called a transformer finite element model. The transformer model consists of three parts: the core, the winding and the oil tank. The core structure is designed in the form of stacked silicon steel sheets; the winding is divided into multiple cake units based on the same number of turns per cake, and the windings of various voltage levels are formed according to the actual connection structure of the winding; the oil tank is simplified to a rectangular structure.

[0070] The transformer model can be used to carry out various types of short-circuit tests to obtain short-circuit test simulation results, which include voltage time-domain simulation signals and current time-domain simulation signals of various simulated short-circuit types.

[0071] Voltage waveforms and current waveforms of various simulated short-circuit types can be obtained based on voltage time-domain simulation signals and current time-domain simulation signals of various simulated short-circuit types; voltage waveforms and current waveforms of various simulated short-circuit types are converted into time-frequency domain to obtain voltage frequency domain graphs and current frequency domain graphs of various simulated short-circuit types; and voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types can be obtained based on frequency components and harmonic characteristics of voltage frequency domain graphs and current frequency domain graphs of various simulated short-circuit types.

[0072] The voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types can be assigned corresponding simulated short-circuit type labels to obtain a simulated short-circuit feature training set.

[0073] In this embodiment, based on the short-circuit test simulation results, voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types are obtained, and based on the voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types, a simulated short-circuit feature training set is obtained, enriching the training data of the transformer short-circuit discrimination model.

[0074] In one of the embodiments, a deep learning model is trained with simulated short-circuit feature samples as input and simulated short-circuit types as labels to obtain a transformer short-circuit discrimination model. The specific steps are as follows: a deep learning model is trained with simulated short-circuit feature samples as input and simulated short-circuit types as labels to obtain an initial transformer short-circuit discrimination model; a real short-circuit feature training set is obtained; each real short-circuit feature sample in the real short-circuit feature training set has a corresponding real short-circuit type; the real short-circuit feature samples include real samples of voltage spectrum features and real samples of current spectrum features; the initial transformer short-circuit discrimination model is trained with real short-circuit feature samples as input and real short-circuit types as labels to obtain a transformer short-circuit discrimination model.

[0075] The simulated short-circuit feature samples can be input into the deep learning model in sequence, and the deep learning model automatically extracts the deep features in the simulated short-circuit feature samples through a multi-layer neural network to obtain the predicted short-circuit type corresponding to the simulated short-circuit feature samples. The prediction accuracy of the deep learning model can be determined based on the labels and predicted short-circuit types corresponding to each simulated short-circuit feature sample; when the prediction accuracy of the deep learning model is greater than the first accuracy threshold, the deep learning model at this time is used as the initial transformer short-circuit discrimination model.

[0076] The initial transformer short-circuit discrimination model can be further trained based on the real short-circuit feature training set. The real short-circuit feature samples can be input into the initial transformer short-circuit discrimination model in sequence to obtain the predicted short-circuit type corresponding to the real short-circuit feature samples. The prediction accuracy of the initial transformer short-circuit discrimination model can be determined based on the labels and predicted short-circuit types corresponding to each real short-circuit feature sample; when the prediction accuracy of the initial transformer short-circuit discrimination model is greater than the second accuracy threshold, the initial transformer short-circuit discrimination model at this time is used as the transformer short-circuit discrimination model.

[0077] After the transformer short-circuit identification model is trained, the trained transformer short-circuit identification model can be deployed to the online monitoring system to realize real-time automatic identification of the transformer short-circuit type.

[0078] The transformer short-circuit discrimination model can be embedded in the real-time monitoring platform of the power system. The voltage spectrum characteristics and current spectrum characteristics are input into the transformer short-circuit discrimination model in real time through the acquisition system, and the transformer short-circuit discrimination model calculates and discriminates the voltage spectrum characteristics and current spectrum characteristics in real time. Once a short-circuit fault is detected, the power system will immediately call the transformer short-circuit discrimination model for discrimination and output the short-circuit type. If the detection result is abnormal, the power system will further trigger the alarm mechanism. In addition, during the online operation of the transformer short-circuit discrimination model, the transformer short-circuit discrimination model can be continuously optimized according to the actual short-circuit data, and the discrimination ability of new or unknown short-circuit types can be improved through incremental learning or retraining.

[0079] In this embodiment, after the deep learning model is trained according to the simulated short-circuit feature training set to obtain the initial transformer short-circuit discrimination model, the initial transformer short-circuit discrimination model can be further trained according to the real short-circuit feature training set to improve the discrimination accuracy of the transformer short-circuit discrimination model.

[0080] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0081] Based on the same inventive concept, the embodiment of the present application also provides a device for determining the type of transformer short circuit for implementing the above-mentioned method for determining the type of transformer short circuit. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more devices for determining the type of transformer short circuit provided below can refer to the limitations of the method for determining the type of transformer short circuit above, and will not be repeated here.

[0082] In an exemplary embodiment, Figure 4 As shown, a device for determining the short-circuit type of a transformer is provided, wherein:

[0083] A time domain signal acquisition module 401 is used to acquire a voltage time domain signal and a current time domain signal at a target transformer port;

[0084] A spectrum feature acquisition module 402, configured to obtain a voltage spectrum feature and a current spectrum feature according to the voltage time domain signal and the current time domain signal;

[0085] The short-circuit type acquisition module 403 is used to obtain the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-built transformer short-circuit identification model.

[0086] In one of the embodiments, the time domain signal acquisition module 401 is also used to: obtain voltage recording data and current recording data at the target transformer port; perform data format conversion on the voltage recording data and the current recording data to obtain an initial voltage time domain signal and an initial current time domain signal; perform denoising and normalization on the initial voltage time domain signal and the initial current time domain signal to obtain a voltage time domain signal and a current time domain signal.

[0087] In one embodiment, the spectrum feature acquisition module 402 is also used to: obtain a voltage waveform diagram and a current waveform diagram based on the voltage time domain signal and the current time domain signal; perform time-frequency domain conversion on the voltage waveform diagram and the current waveform diagram to obtain a voltage frequency domain diagram and a current frequency domain diagram; obtain voltage spectrum features and current spectrum features based on the frequency components and harmonic characteristics of the voltage frequency domain diagram and the current frequency domain diagram.

[0088] In one of the embodiments, the device method also includes a model training module, which is used to: obtain a simulated short-circuit feature training set; each simulated short-circuit feature sample in the simulated short-circuit feature training set has a corresponding simulated short-circuit type; the simulated short-circuit feature samples include voltage spectrum feature simulation samples and current spectrum feature simulation samples; with the simulated short-circuit feature samples as input and the simulated short-circuit type as a label, the deep learning model is trained to obtain a transformer short-circuit discrimination model.

[0089] In one of the embodiments, the model training module is also used to: obtain the short-circuit test simulation results of the transformer model; obtain the voltage time-domain simulation signal and the current time-domain simulation signal of various simulated short-circuit types at the transformer model port based on the short-circuit test simulation results; obtain the voltage spectrum feature simulation samples and the current spectrum feature simulation samples of various simulated short-circuit types based on the voltage time-domain simulation signals and the current time-domain simulation signals of various simulated short-circuit types; obtain the simulated short-circuit feature training set based on the voltage spectrum feature simulation samples and the current spectrum feature simulation samples of the various simulated short-circuit types.

[0090] In one of the embodiments, the model training module is also used to: use the simulated short-circuit feature samples as input and the simulated short-circuit type as a label to train the deep learning model to obtain an initial transformer short-circuit discrimination model; obtain a real short-circuit feature training set; each real short-circuit feature sample in the real short-circuit feature training set has a corresponding real short-circuit type; the real short-circuit feature samples include real samples of voltage spectrum features and real samples of current spectrum features; use the real short-circuit feature samples as input and the real short-circuit type as a label to train the initial transformer short-circuit discrimination model to obtain a transformer short-circuit discrimination model.

[0091] Each module in the above transformer short circuit type determination device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0092] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of an embodiment of a method for distinguishing the short-circuit type of a transformer. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for distinguishing the short-circuit type of a transformer is implemented.

[0093] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0095] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0096] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0098] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0100] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining the short-circuit type of a transformer, characterized in that: The method comprises: Acquire voltage time domain signal and current time domain signal at the target transformer port; Obtaining voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal; The short-circuit type of the target transformer is obtained according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-constructed transformer short-circuit discrimination model.

2. The method according to claim 1, characterized in that: The step of obtaining a voltage time domain signal and a current time domain signal at a target transformer port includes: Obtain voltage and current recording data at the target transformer port; Performing data format conversion on the voltage recording data and the current recording data to obtain an initial voltage time domain signal and an initial current time domain signal; The initial voltage time-domain signal and the initial current time-domain signal are subjected to denoising and normalization processing to obtain a voltage time-domain signal and a current time-domain signal.

3. The method according to claim 1, characterized in that The step of obtaining voltage spectrum characteristics and current spectrum characteristics according to the voltage time domain signal and the current time domain signal includes: Obtaining a voltage waveform diagram and a current waveform diagram according to the voltage time domain signal and the current time domain signal; Performing time-frequency domain conversion on the voltage waveform diagram and the current waveform diagram to obtain a voltage frequency domain diagram and a current frequency domain diagram; Voltage spectrum characteristics and current spectrum characteristics are obtained according to the frequency components and harmonic characteristics of the voltage frequency domain diagram and the current frequency domain diagram.

4. The method according to claim 1, characterized in that Before obtaining the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-built transformer short-circuit discrimination model, the method further includes: Acquire a simulated short-circuit feature training set; each simulated short-circuit feature sample in the simulated short-circuit feature training set has a corresponding simulated short-circuit type; the simulated short-circuit feature samples include voltage spectrum feature simulation samples and current spectrum feature simulation samples; The simulated short-circuit feature samples are used as input and the simulated short-circuit types are used as labels to train a deep learning model to obtain a transformer short-circuit discrimination model.

5. The method according to claim 4, characterized in that The step of obtaining a simulation short circuit feature training set comprises: Obtain the short-circuit test simulation results of the transformer model; According to the short-circuit test simulation results, voltage time-domain simulation signals and current time-domain simulation signals of various simulated short-circuit types at the transformer model port are obtained; According to the voltage time-domain simulation signals and the current time-domain simulation signals of various simulated short-circuit types, voltage spectrum feature simulation samples and current spectrum feature simulation samples of various simulated short-circuit types are obtained; A simulated short-circuit feature training set is obtained based on the voltage spectrum feature simulation samples and current spectrum feature simulation samples of the various simulated short-circuit types.

6. The method according to claim 4, characterized in that The method uses the simulated short-circuit feature sample as input and the simulated short-circuit type as a label to train the deep learning model to obtain a transformer short-circuit discrimination model, including: Taking the simulated short-circuit feature sample as input and the simulated short-circuit type as a label, a deep learning model is trained to obtain an initial transformer short-circuit discrimination model; Acquire a real short-circuit feature training set; each real short-circuit feature sample in the real short-circuit feature training set has a corresponding real short-circuit type; the real short-circuit feature samples include real voltage spectrum feature samples and real current spectrum feature samples; The initial transformer short-circuit discrimination model is trained with the real short-circuit feature sample as input and the real short-circuit type as a label to obtain a transformer short-circuit discrimination model.

7. A device for determining the short-circuit type of a transformer, characterized in that: The device comprises: A time domain signal acquisition module, used to acquire a voltage time domain signal and a current time domain signal at a target transformer port; A spectrum feature acquisition module, used to obtain voltage spectrum features and current spectrum features according to the voltage time domain signal and the current time domain signal; The short-circuit type acquisition module is used to obtain the short-circuit type of the target transformer according to the voltage spectrum characteristics, the current spectrum characteristics and a pre-built transformer short-circuit discrimination model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images