Transformer Fault Prediction Method, Device, Terminal and Storage Medium
By constructing and splitting multi-dimensional tensors, the correlation of different dimensions of the transformer is extracted, and the problem of low accuracy in transformer failure prediction in the prior art is solved, and more accurate failure prediction is achieved.
Patent Information
- Application Number
- CN202411242505.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2025-05-30
- Estimated Expiration
- 2044-09-05
AI Technical Summary
The existing transformer fault prediction methods have problems of insufficient accuracy and poor universality, and it is difficult to fully reflect the real operating status of the transformer.
By acquiring multiple monitoring data at different locations and acquisition times of the target transformer, a multi-dimensional tensor is constructed, and segmented it according to time, space and feature dimensions, the correlation of slice data is extracted, and the fault prediction results are obtained using a fully connected network.
This method can integrate a variety of monitoring data and fully extract the correlation between different dimensions of the transformer, thereby improving the accuracy of fault prediction.
Smart Images
Figure CN119202591B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fault prediction, and in particular, to a transformer fault prediction method, device, terminal and storage medium. Background Art
[0002] As a key device in the power system, the operating state of a power transformer directly affects the safety and stability of the power grid. However, transformer faults often involve complex factors in multiple aspects such as electromagnetics, mechanics, and chemistry, and traditional single monitoring means are difficult to comprehensively reflect its true operating state. Existing fault prediction methods, such as the IEC three-ratio method, infrared detection method, etc., although each has its own advantages, all have limitations, such as insufficient accuracy and poor universality. Therefore, it is particularly important to develop a new method that can integrate multiple monitoring data and improve the accuracy of fault prediction. Summary of the Invention
[0003] Embodiments of the present invention provide a transformer fault prediction method, device, terminal and storage medium to solve the problems that current transformer fault prediction methods all have limitations and the accuracy of fault prediction is not high.
[0004] In a first aspect, embodiments of the present invention provide a transformer fault prediction method, including:
[0005] Obtain a variety of target monitoring data at different acquisition times at different positions of the target transformer;
[0006] Using each of the target monitoring data as a feature dimension of the target transformer, construct a multi-dimensional tensor from the variety of target monitoring data according to the time dimension, space dimension and feature dimension;
[0007] Slice the multi-dimensional tensor according to the time dimension, space dimension and feature dimension respectively to obtain the space dimension and feature dimension slice data, time dimension and feature dimension slice data, and time dimension and space dimension slice data of the target transformer;
[0008] Extract the correlations of the space dimension and feature dimension slice data, the time dimension and feature dimension slice data, and the time dimension and space dimension slice data respectively, and obtain the fault prediction result of the target transformer according to the extraction results.
[0009] In a possible implementation manner, extracting the correlations of the space dimension and feature dimension slice data, the time dimension and feature dimension slice data, and the time dimension and space dimension slice data respectively, and obtaining the fault prediction result of the target transformer according to the extraction results includes:
[0010] Extract the correlation of the space dimension and feature dimension slice data, denoted as the first correlation;
[0011] Extract the correlation of the slice data in the time dimension and the feature dimension, denoted as the second correlation;
[0012] Extract the correlation of the slice data in the time dimension and the spatial dimension, denoted as the third correlation;
[0013] Input the first correlation, the second correlation, and the third correlation into a fully connected network to obtain the fault prediction result of the target transformer.
[0014] In a possible implementation manner, extracting the correlation of the slice data in the spatial dimension and the feature dimension, denoted as the first correlation, includes:
[0015] Extract the correlation of the slice data in the spatial dimension and the feature dimension based on a graph convolutional network, denoted as the first correlation.
[0016] In a possible implementation manner, extracting the correlation of the slice data in the time dimension and the feature dimension, denoted as the second correlation, includes:
[0017] Extract the correlation of the slice data in the time dimension and the feature dimension based on a gated recurrent unit, denoted as the second correlation.
[0018] In a possible implementation manner, extracting the correlation of the slice data in the time dimension and the spatial dimension, denoted as the third correlation, includes:
[0019] Extract the correlation of the slice data in the time dimension and the spatial dimension based on a spatio-temporal graph convolutional network, denoted as the third correlation.
[0020] In a possible implementation manner, after obtaining multiple pieces of target monitoring data at different acquisition times at different positions of the target transformer, it further includes:
[0021] Perform data cleaning processing and data standardization processing on each piece of the target monitoring data to obtain the preprocessed target monitoring data;
[0022] Construct a multi-dimensional tensor from multiple pieces of the target monitoring data according to the time dimension, the spatial dimension, and the feature dimension, including:
[0023] Construct a multi-dimensional tensor from multiple pieces of the preprocessed target monitoring data according to the time dimension, the spatial dimension, and the feature dimension.
[0024] In a second aspect, an embodiment of the present invention provides a transformer fault prediction device, including:
[0025] An acquisition module, configured to acquire multiple pieces of target monitoring data at different acquisition times at different positions of the target transformer;
[0026] The first processing module is configured to use each of the target monitoring data as a feature dimension of the target transformer, and construct a multi-dimensional tensor from the multiple target monitoring data according to the time dimension, the space dimension, and the feature dimension;
[0027] The second processing module is configured to slice the multi-dimensional tensor according to the time dimension, the space dimension, and the feature dimension respectively, to obtain the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension of the target transformer;
[0028] The prediction module is configured to extract the correlations of the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension respectively, and obtain a fault prediction result of the target transformer according to the extraction results.
[0029] In a possible implementation manner, the prediction module is specifically configured to:
[0030] Extract the correlation of the slice data of the space dimension and the feature dimension, denoted as the first correlation;
[0031] Extract the correlation of the slice data of the time dimension and the feature dimension, denoted as the second correlation;
[0032] Extract the correlation of the slice data of the time dimension and the space dimension, denoted as the third correlation;
[0033] Input the first correlation, the second correlation, and the third correlation into a fully connected network to obtain a fault prediction result of the target transformer.
[0034] In a third aspect, an embodiment of the present invention provides a terminal, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method according to the first aspect or any possible implementation manner of the first aspect above.
[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method according to the first aspect or any possible implementation manner of the first aspect above are implemented.
[0036] An embodiment of the present invention provides a transformer fault prediction method, device, terminal, and storage medium. First, a variety of target monitoring data at different acquisition times at different positions of a target transformer are obtained. Then, each type of target monitoring data is used as a feature dimension of the target transformer, and the multiple types of target monitoring data are used to construct a multi-dimensional tensor according to the time dimension, space dimension, and feature dimension. Then, the multi-dimensional tensor is sliced according to the time dimension, space dimension, and feature dimension respectively to obtain the sliced data of the space dimension and feature dimension, the sliced data of the time dimension and feature dimension, and the sliced data of the time dimension and space dimension of the target transformer. Furthermore, the correlations of the sliced data of the space dimension and feature dimension, the sliced data of the time dimension and feature dimension, and the sliced data of the time dimension and space dimension are respectively extracted, and a fault prediction result of the target transformer is obtained according to the extraction result. Thus, when obtaining the fault prediction result of the target transformer, multiple types of target monitoring data of the target transformer can be integrated, and the correlations between multiple types of target monitoring information of the target transformer in each dimension can be fully extracted, thereby improving the accuracy of transformer fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0038] Figure 1 is a flowchart of the implementation of the transformer fault prediction method provided by the embodiment of the present invention;
[0039] Figure 2 is a technical roadmap of the transformer fault prediction method provided by the embodiment of the present invention;
[0040] Figure 3 is a schematic diagram of slicing the multi-dimensional tensor according to the time dimension, space dimension, and feature dimension respectively provided by the embodiment of the present invention;
[0041] Figure 4 is a schematic diagram of the structure of the transformer fault prediction device provided by the embodiment of the present invention;
[0042] Figure 5 is a schematic diagram of the terminal provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0043] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.
[0044] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments with reference to the accompanying drawings.
[0045] Refer to Figure 1 and Figure 2 , which shows the implementation flowchart of the transformer fault prediction method provided by the embodiments of the present invention, and is described in detail as follows:
[0046] In step 101, various target monitoring data at different acquisition times at different positions of the target transformer are obtained.
[0047] In this embodiment, in order to improve the accuracy of transformer fault prediction, various monitoring data of the transformer are considered comprehensively. Therefore, when it is necessary to perform fault prediction on the target transformer, various monitoring data at different acquisition times at different positions of the target transformer are obtained, which are denoted as various target monitoring data.
[0048] Exemplarily, the various monitoring data of the transformer obtained may include oil temperature, dissolved gas content in oil (such as key gases like hydrogen H 2 , methane CH 4 , ethane C 2 H 6 , etc.), current, voltage, etc. Various sensors can be respectively arranged at different positions of the transformer to collect multi-dimensional state monitoring data of the transformer over a period of history.
[0049] Exemplarily, assuming that 5 monitoring points are set on the transformer, an oil temperature sensor, a gas content detection sensor, a current sensor, a voltage sensor, etc. can be arranged at each monitoring point of the transformer, so as to facilitate subsequent fault prediction by comprehensively considering various monitoring data at each acquisition time at each position of the transformer.
[0050] In one embodiment, after obtaining various target monitoring data at different acquisition times at different positions of the target transformer, it may further include:
[0051] Performing data cleaning processing and data standardization processing on each type of target monitoring data to obtain preprocessed target monitoring data.
[0052] In this embodiment, after obtaining various monitoring data (i.e., various target monitoring data of the target transformer), data cleaning and data standardization processing are performed, which can eliminate noise and outliers in various target monitoring data, and thus facilitate more accurate subsequent fault prediction.
[0053] In step 102, each type of target monitoring data is used as a feature dimension of the target transformer, and multiple target monitoring data are constructed into a multi-dimensional tensor according to the time dimension, space dimension, and feature dimension.
[0054] In one embodiment, constructing a multi-dimensional tensor from multiple target monitoring data according to the time dimension, space dimension, and feature dimension may be constructing a multi-dimensional tensor from multiple preprocessed target monitoring data according to the time dimension, space dimension, and feature dimension.
[0055] In this embodiment, considering that when performing fault prediction on a transformer currently, even if multiple monitoring data are considered, the correlation between different monitoring data is often ignored, or the correlation between different monitoring data cannot be fully extracted, resulting in the fault prediction result of the transformer being difficult to meet the expectation.
[0056] Therefore, in this embodiment, after obtaining multiple target monitoring data at different acquisition times at different positions of the target transformer, a dynamic tensor fusion network is constructed to facilitate subsequent full extraction of the correlation between different monitoring data of the transformer in different dimensions.
[0057] Among them, when constructing the dynamic tensor fusion network, considering that for the corresponding transformer, different types of monitoring data such as oil temperature, dissolved gas content in oil, current, and voltage respectively correspond to a feature dimension of the transformer, while the oil temperature, dissolved gas content in oil, current, voltage, etc. at different positions respectively correspond to a space dimension of the transformer, and the oil temperature, dissolved gas content in oil, current, voltage, etc. at different acquisition times respectively correspond to a time dimension of the transformer. Therefore, multiple target monitoring data can be constructed into a multi-dimensional tensor according to the time dimension, space dimension, and feature dimension.
[0058] For example, if the state of the target transformer is characterized by four types of monitoring data: oil temperature, dissolved gas content in oil, current, and voltage, and 5 monitoring points are set on the target transformer, and sensor data is collected every 15 seconds, then the target transformer has 4 feature dimensions, 5 space dimensions, and a time dimension every 15 seconds. Therefore, the sensor data collected at different acquisition times at different positions of the target transformer can be numbered according to the feature dimension, space dimension, and time dimension respectively to form a multi-dimensional tensor of the target transformer.
[0059] In step 103, the multi-dimensional tensor is sliced according to the time dimension, the spatial dimension, and the feature dimension respectively to obtain the sliced data of the spatial dimension and the feature dimension of the target transformer, the sliced data of the time dimension and the feature dimension, and the sliced data of the time dimension and the spatial dimension.
[0060] In this embodiment, in order to fully extract the correlation between different dimensions of the transformer, after constructing the multi-dimensional tensor, it can be sliced along the time dimension, the spatial dimension, and the feature dimension respectively.
[0061] As Figure 2 and Figure 3 shown in (a), (b), and (c) of , χ represents the multi-dimensional tensor, T represents the time dimension, N represents the spatial dimension, and C represents the feature dimension. Slicing the multi-dimensional tensor χ along the time dimension T, the sliced data of the spatial dimension and the feature dimension N×C is obtained. Slicing the multi-dimensional tensor χ along the spatial dimension N, the sliced data of the time dimension and the feature dimension T×C is obtained. Slicing the multi-dimensional tensor χ along the feature dimension C, the sliced data of the time dimension and the spatial dimension N×T is obtained.
[0062] In step 104, the correlations of the sliced data of the spatial dimension and the feature dimension, the sliced data of the time dimension and the feature dimension, and the sliced data of the time dimension and the spatial dimension are extracted respectively, and the fault prediction result of the target transformer is obtained according to the extraction result.
[0063] Exemplarily, extracting the correlations of the sliced data of the spatial dimension and the feature dimension, the sliced data of the time dimension and the feature dimension, and the sliced data of the time dimension and the spatial dimension respectively, and obtaining the fault prediction result of the target transformer according to the extraction result may include:
[0064] Extracting the correlation of the sliced data of the spatial dimension and the feature dimension, denoted as the first correlation.
[0065] Extracting the correlation of the sliced data of the time dimension and the feature dimension, denoted as the second correlation.
[0066] Extracting the correlation of the sliced data of the time dimension and the spatial dimension, denoted as the third correlation.
[0067] Inputting the first correlation, the second correlation, and the third correlation into a fully connected network to obtain the fault prediction result of the target transformer.
[0068] Exemplarily, the correlation of the sliced data of the spatial dimension and the feature dimension can be extracted based on a graph convolutional network, denoted as the first correlation. The correlation of the sliced data of the time dimension and the feature dimension can be extracted based on a gated recurrent unit, denoted as the second correlation. The correlation of the sliced data of the time dimension and the spatial dimension can be extracted based on a spatio-temporal graph convolutional network, denoted as the third correlation.
[0069] In this embodiment, after obtaining the spatial dimension and feature dimension slice data, the temporal dimension and feature dimension slice data, and the temporal dimension and spatial dimension slice data, considering that there are correlations between every two dimensions and the correlation features are different, different networks can be used to extract the correlations between every two dimensions according to the characteristics of every two dimensions. For example, the graph convolutional network is used to extract the correlation between the spatial dimension-feature dimension slice data, the gated recurrent unit is used to extract the correlation between the temporal dimension-feature dimension slice data, and the spatio-temporal graph convolutional network is used to extract the correlation between the temporal dimension-spatial dimension slice data. Then, the correlation features of the three types of slices are input into a fully connected network for fault prediction. Thus, after fully extracting the correlations between the information of each dimension of the transformer, fault prediction is performed to improve the accuracy of the transformer's fault prediction.
[0070] Exemplarily, before inputting the correlation features of the three types of slices into the fully connected network for fault prediction, various monitoring data of the faulty transformer can be obtained, a multi-dimensional tensor can be constructed, sliced, the correlation can be extracted, and input into the fully connected network according to steps 101 to 104, so as to determine a fault threshold. Then, when the correlation features of the three types of slices are input into the fully connected network, the correlations of the various target monitoring data of the target transformer in different dimensions can be compared with the correlations of the various monitoring data of the faulty transformer in different dimensions, so as to obtain the fault prediction result of the target transformer.
[0071] In the embodiment of the present invention, various target monitoring data at different acquisition times at different positions of the target transformer are first obtained, and then each target monitoring data is used as a feature dimension of the target transformer, and the various target monitoring data are used to construct a multi-dimensional tensor according to the temporal dimension, spatial dimension, and feature dimension; then the multi-dimensional tensor is sliced according to the temporal dimension, spatial dimension, and feature dimension respectively to obtain the spatial dimension and feature dimension slice data, the temporal dimension and feature dimension slice data, and the temporal dimension and spatial dimension slice data of the target transformer; and then the correlations of the spatial dimension and feature dimension slice data, the temporal dimension and feature dimension slice data, and the temporal dimension and spatial dimension slice data are extracted respectively, and the fault prediction result of the target transformer is obtained according to the extraction result. Thus, when obtaining the fault prediction result of the target transformer, various target monitoring data of the target transformer can be integrated, and the correlations between the various target monitoring information of the target transformer in each dimension can be fully extracted, thereby improving the accuracy of the transformer fault prediction.
[0072] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
[0073] The following is an apparatus embodiment of the present invention. For details not described in detail herein, reference may be made to the corresponding method embodiment above.
[0074] Figure 4 The structural schematic diagram of the transformer fault prediction apparatus provided by the embodiment of the present invention is shown. For the sake of convenience of description, only the parts related to the embodiment of the present invention are shown and are described in detail as follows:
[0075] As Figure 4 shown, the transformer fault prediction apparatus includes: an acquisition module 41, a first processing module 42, a second processing module 43, and a prediction module 44.
[0076] The acquisition module 41 is configured to acquire a variety of target monitoring data at different acquisition times at different positions of the target transformer.
[0077] The first processing module 42 is configured to use each type of target monitoring data as a feature dimension of the target transformer, and construct a multi-dimensional tensor from the variety of target monitoring data according to the time dimension, the space dimension, and the feature dimension.
[0078] The second processing module 43 is configured to slice the multi-dimensional tensor according to the time dimension, the space dimension, and the feature dimension respectively, to obtain the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension of the target transformer.
[0079] The prediction module 44 is configured to extract the correlations of the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension respectively, and obtain the fault prediction result of the target transformer according to the extraction results.
[0080] In the embodiment of the present invention, first, a variety of target monitoring data at different acquisition times at different positions of the target transformer are acquired, and then each type of target monitoring data is used as a feature dimension of the target transformer, and a multi-dimensional tensor is constructed from the variety of target monitoring data according to the time dimension, the space dimension, and the feature dimension; then the multi-dimensional tensor is sliced according to the time dimension, the space dimension, and the feature dimension respectively, to obtain the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension of the target transformer; furthermore, the correlations of the slice data of the space dimension and the feature dimension, the slice data of the time dimension and the feature dimension, and the slice data of the time dimension and the space dimension are extracted respectively, and the fault prediction result of the target transformer is obtained according to the extraction results. Thus, when obtaining the fault prediction result of the target transformer, a variety of target monitoring data of the target transformer can be integrated, and the correlations between various target monitoring information of the target transformer in each dimension can be fully extracted, thereby improving the accuracy of transformer fault prediction.
[0081] In a possible implementation, the prediction module 44 is specifically configured to:
[0082] Extract the correlation between the spatial dimension and the feature dimension slice data, denoted as the first correlation.
[0083] Extract the correlation between the time dimension and the feature dimension slice data, denoted as the second correlation.
[0084] Extract the correlation between the time dimension and the spatial dimension slice data, denoted as the third correlation.
[0085] Input the first correlation, the second correlation, and the third correlation into a fully connected network to obtain the fault prediction result of the target transformer.
[0086] In a possible implementation, the prediction module 44 is specifically configured to: Based on a graph convolutional network, extract the correlation between the spatial dimension and the feature dimension slice data, denoted as the first correlation.
[0087] In a possible implementation, the prediction module 44 is specifically configured to: Based on a gated recurrent unit, extract the correlation between the time dimension and the feature dimension slice data, denoted as the second correlation.
[0088] In a possible implementation, the prediction module 44 is specifically configured to: Based on a spatio-temporal graph convolutional network, extract the correlation between the time dimension and the spatial dimension slice data, denoted as the third correlation.
[0089] In a possible implementation, the acquisition module 41 can also be used to perform data cleaning processing and data standardization processing on each type of target monitoring data to obtain the preprocessed target monitoring data; the first processing module 42 is specifically configured to: Construct a multi-dimensional tensor from multiple preprocessed target monitoring data according to the time dimension, the spatial dimension, and the feature dimension.
[0090] Figure 5 It is a schematic diagram of the terminal provided by the embodiment of the present invention. As Figure 5 shown, the terminal 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above-mentioned various embodiments of the transformer fault prediction method are implemented, such as Figure 1 the steps 101 to 104 shown. Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as Figure 4 the functions of the modules 41 to 44 shown.
[0091] Exemplarily, the computer program 52 can be divided into one or more modules / units. One or more modules / units are stored in the memory 51 and executed by the processor 50 to implement the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 52 in the terminal 5. For example, the computer program 52 can be divided into Figure 4 the modules 41 to 44 shown in the figure.
[0092] The terminal 5 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art can understand that Figure 5 this is merely an example of the terminal 5 and does not constitute a limitation on the terminal 5. It may include more or fewer components than shown in the figure, or combine certain components, or have different components. For example, the terminal may further include input / output devices, network access devices, a bus, etc.
[0093] The so-called processor 50 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.
[0094] The memory 51 may be an internal storage unit of the terminal 5, such as the hard disk or memory of the terminal 5. The memory 51 may also be an external storage device of the terminal 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 5. Further, the memory 51 may also include both the internal storage unit and the external storage device of the terminal 5. The memory 51 is used to store computer programs and other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.
[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.
[0096] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0097] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
[0098] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are only illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.
[0099] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0100] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
[0101] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various embodiments of the transformer fault prediction method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.
[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A transformer fault prediction method, characterized in that: include: Acquire multiple target monitoring data at different locations of the target transformer at different collection times; Taking each target monitoring data as a feature dimension of the target transformer, constructing a multidimensional tensor of the multiple target monitoring data according to the time dimension, space dimension and feature dimension; The multidimensional tensor is divided according to the time dimension to obtain slice data consisting of the spatial dimension and the feature dimension of the target transformer, which is recorded as the first slice data; The multidimensional tensor is divided according to the spatial dimension to obtain slice data consisting of the time dimension and the feature dimension of the target transformer, which is recorded as the second slice data; The multidimensional tensor is divided according to the feature dimension to obtain slice data consisting of the time dimension and the space dimension of the target transformer, which is recorded as the third slice data; Extracting the correlation between the spatial dimension and the feature dimension of the first slice data, recorded as the first correlation; Extracting the correlation between the time dimension and the feature dimension of the second slice data, recorded as the second correlation; Extracting the correlation between the time dimension and the space dimension of the third slice data, recorded as the third correlation; The first correlation, the second correlation and the third correlation are input into a fully connected network, the output result of the fully connected network is compared with the fault threshold, and the fault prediction result of the target transformer is obtained according to the comparison result, wherein the fault threshold is a fault threshold determined by the output result obtained by constructing a multidimensional tensor based on a variety of monitoring data at different locations and different collection times of the faulty transformer, slicing, extracting correlations and inputting them into the fully connected network.
2. The transformer fault prediction method according to claim 1, characterized in that: Extracting the correlation between the spatial dimension and the feature dimension of the first slice data, recorded as the first correlation, includes: The correlation between the spatial dimension and the feature dimension of the first slice data is extracted based on the graph convolutional network and recorded as the first correlation.
3. The transformer fault prediction method according to claim 1, characterized in that: Extracting the correlation between the time dimension and the feature dimension of the second slice data, recorded as the second correlation, includes: The correlation between the time dimension and the feature dimension of the second slice data is extracted based on the gated recurrent unit and recorded as the second correlation.
4. The transformer fault prediction method according to claim 1, characterized in that: Extracting the correlation between the time dimension and the space dimension of the third slice data, recorded as the third correlation, includes: The correlation between the time dimension and the space dimension of the third slice data is extracted based on the spatiotemporal graph convolutional network, which is recorded as the third correlation.
5. The transformer fault prediction method according to claim 1, characterized in that: After obtaining a variety of target monitoring data at different locations of the target transformer at different acquisition times, it also includes: Performing data cleaning and data standardization on each of the target monitoring data to obtain pre-processed target monitoring data; The target monitoring data are constructed into a multidimensional tensor according to the time dimension, space dimension and feature dimension, including: A variety of pre-processed target monitoring data are constructed into multi-dimensional tensors according to the time dimension, space dimension and feature dimension.
6. A transformer fault prediction device, characterized in that: include: An acquisition module, used to acquire a variety of target monitoring data at different locations of a target transformer at different acquisition times; A first processing module is used to use each of the target monitoring data as a feature dimension of the target transformer, and construct a multidimensional tensor of the multiple target monitoring data according to the time dimension, space dimension and feature dimension; The second processing module is used to divide the multidimensional tensor according to the time dimension to obtain slice data composed of the space dimension and feature dimension of the target transformer, which is recorded as the first slice data; divide the multidimensional tensor according to the space dimension to obtain slice data composed of the time dimension and feature dimension of the target transformer, which is recorded as the second slice data; divide the multidimensional tensor according to the feature dimension to obtain slice data composed of the time dimension and space dimension of the target transformer, which is recorded as the third slice data; A prediction module is used to extract the correlation between the spatial dimension and the feature dimension of the first slice data, which is recorded as the first correlation; extract the correlation between the time dimension and the feature dimension of the second slice data, which is recorded as the second correlation; extract the correlation between the time dimension and the spatial dimension of the third slice data, which is recorded as the third correlation; input the first correlation, the second correlation and the third correlation into a fully connected network, compare the output result of the fully connected network with the fault threshold, and obtain the fault prediction result of the target transformer according to the comparison result, wherein the fault threshold is determined by the output result obtained after constructing a multi-dimensional tensor based on multiple monitoring data at different locations and different collection times of the faulty transformer, slicing, extracting correlations and inputting them into the fully connected network.
7. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 5.
8. A computer-readable storage medium storing 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 5 are implemented.
Citation Information
Patent Citations
Battery fault prediction model training method and device, and prediction method and device
CN118395370A
KR20240033432A