Fault identification method, device and equipment for transformer bushing and medium

Abstract

The embodiment of the invention discloses a fault identification method and device for a transformer bushing, equipment and a medium, and relates to the technical field of transformers. The method comprises the following steps: constructing a target kernel function based on an original kernel function and a target symmetric positive semidefinite matrix; based on a target kernel function, mapping a plurality of complete sleeve data and missing sleeve data to a regeneration kernel Hilbert space, and according to the similarity between a missing value and other data points, complementing the missing value to obtain complemented data of the to-be-detected sleeve of the transformer; and performing fault identification on the to-be-detected bushing of the transformer based on the complementation data to obtain a fault identification result. According to the technical scheme, the missing bushing data is mapped to the regeneration kernel Hilbert space through the matrix capable of reflecting the characteristics of the transformer bushing, then data completion is carried out in the regeneration kernel Hilbert space, fault recognition is carried out based on the completion data, and the fault recognition result of the to-be-detected bushing of the transformer can be accurately determined.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a transformer bushing fault identification method, device, equipment and medium. Background Art

[0002] At present, when fault identification is performed on transformer bushings, one method is to collect sound during the use of the bushing and identify the bushing fault based on the sound information. The other method is to identify the fault through an artificial intelligence model.

[0003] However, both the technical solutions based on sound collection and the technical solutions based on artificial intelligence rely on complete and large amounts of data. If the data is missing, it is impossible to identify the fault of the transformer bushing. Summary of the invention

[0004] The present invention provides a transformer bushing fault identification method, device, equipment and medium, which can accurately identify the transformer bushing fault based on the completed data after completing the bushing data.

[0005] According to one aspect of the present invention, a transformer bushing fault identification method is provided, the method comprising:

[0006] The target kernel function is constructed based on the original kernel function and the target symmetric semi-positive definite matrix; the target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing.

[0007] Based on the target kernel function, multiple complete bushing data and missing bushing data are mapped to the regenerated kernel Hilbert space, and the missing values ​​are completed according to the similarity between the missing values ​​and other data points to obtain the completed data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data;

[0008] Based on the supplemented data, fault identification is performed on the bushing to be inspected of the transformer to obtain a fault identification result.

[0009] According to another aspect of the present invention, a transformer bushing fault identification device is provided, comprising:

[0010] The target kernel function construction module is used to construct the target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix; the target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing

[0011] A completion data determination module is used to map multiple complete bushing data and missing bushing data to a regenerating kernel Hilbert space based on a target kernel function, and to complete the missing values ​​according to the similarity between the missing values ​​and other data points, so as to obtain the completion data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data;

[0012] The fault identification module is used to perform fault identification on the bushing to be detected of the transformer based on the supplemented data to obtain a fault identification result.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the transformer bushing fault identification method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the transformer bushing fault identification method according to any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present application includes: constructing a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix; mapping multiple complete bushing data and missing bushing data to the regenerated kernel Hilbert space based on the target kernel function, and completing the missing values ​​according to the similarity between the missing values ​​and other data points to obtain the completed data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; based on the completed data, the bushing to be detected of the transformer is fault identified to obtain a fault identification result. The technical solution maps the missing bushing data to the regenerated kernel Hilbert space through a matrix that can reflect the characteristics of the transformer bushing, and then determines the data points similar to the missing values ​​in the regenerated kernel Hilbert space, and after the data is completed, fault identification is performed based on the completed data, so that the fault identification result of the bushing to be detected of the transformer can be accurately determined.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a transformer bushing fault identification method provided according to Embodiment 1 of the present application;

[0022] Figure 2 is a flow chart of a transformer bushing fault identification method provided according to Embodiment 2 of the present application;

[0023] Figure 3 It is a structural schematic diagram of a transformer bushing fault identification device provided according to Embodiment 3 of the present application;

[0024] Figure 4 It is a structural schematic diagram of an electronic device for implementing a transformer bushing fault identification method according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1 A flowchart of a transformer bushing fault identification method is provided for the first embodiment of the present application. The present embodiment of the present application is applicable to the case of transformer bushing fault identification. The method can be executed by a transformer bushing fault identification device. The transformer bushing fault identification device can be implemented in the form of hardware and / or software. The transformer bushing fault identification device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S110, constructing a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix.

[0030] The original kernel function may be selected according to the data type of the transformer bushing, and the original kernel function includes but is not limited to: a linear kernel function, a polynomial kernel function, a radial basis kernel function, a Laplace kernel function, etc. The target symmetric semi-positive definite matrix may be obtained by iterating the initial symmetric semi-positive definite matrix, and the target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing.

[0031] Specifically, after the original kernel function and the target symmetric semi-positive definite matrix are determined, the target kernel function is constructed based on the original kernel function and the target symmetric semi-positive definite matrix, so that the target kernel function is symmetric positive definite.

[0032] S120, mapping multiple complete bushing data and missing bushing data to the regenerating kernel Hilbert space based on the target kernel function, and completing the missing values ​​according to the similarity between the missing values ​​and other data points to obtain the completed data of the bushing to be detected of the transformer.

[0033] The complete bushing data may include: manufacturer, voltage level, dielectric loss factor, bushing thickness, dielectric constant, no-load current, etc. One transformer device corresponds to a set of complete bushing data, and multiple complete bushing data are multiple sets of complete bushing data corresponding to multiple transformer devices.

[0034] The missing bushing data is data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; for example, the complete bushing data includes: factory manufacturer, voltage level, dielectric loss factor, bushing thickness, dielectric constant, and no-load current; the missing bushing data includes: factory manufacturer, voltage level, dielectric loss factor, dielectric constant, and no-load current; in this case, the bushing thickness is the missing value.

[0035] Specifically, after mapping multiple complete bushing data and missing bushing data to the regenerated kernel Hilbert space based on the target kernel function, the similarity between each transformer device can be determined in the regenerated kernel Hilbert space. The similarity reflects the similarity between the missing value and other data points (i.e., the data in the complete bushing data). The missing value can be completed according to data similar to the missing value, and then the completed missing value and missing bushing data can be determined as the completed data of the bushing to be detected of the transformer.

[0036] S130, performing fault identification on the bushing to be inspected of the transformer based on the supplemented data to obtain a fault identification result.

[0037] Specifically, after the supplemented data is obtained, the supplemented data can be processed based on the pre-trained fault identification model to obtain a fault identification result. In one case, the fault identification result includes two cases: faulty and non-faulty. In another case, in the fault identification result, if the bushing to be detected of the transformer is faulty, the fault type is also included. Obviously, the fault identification model can be selected according to the actual situation, and the embodiment of the present application does not limit this.

[0038] In an embodiment of the present application, optionally, fault identification is performed on the bushing to be detected of the transformer based on the completed data to obtain a fault identification result, including: inputting the completed data and normal transformer bushing data into a pre-trained double-tower model; if the output result of the double-tower model is greater than a similarity threshold, it is determined that the bushing to be detected of the transformer is not faulty; otherwise, it is determined that the bushing to be detected of the transformer is faulty.

[0039] Specifically, the pre-trained dual-tower model is used to identify the similarity between the completed data and the normal transformer bushing data. If the output result of the dual-tower model is greater than the similarity threshold, the bushing to be detected is similar to the normal bushing, and it can be determined that the bushing to be detected of the transformer is not faulty; otherwise, it is determined that the bushing to be detected of the transformer is faulty.

[0040] The scheme is configured in this way, and it is possible to quickly determine whether the bushing to be inspected is similar to a normal transformer bushing through the double-tower model, and then determine whether the bushing to be inspected has a fault.

[0041] In an embodiment of the present application, optionally, fault identification is performed on the bushing to be detected of the transformer based on the completed data to obtain a fault identification result, including: inputting the completed data and the faulty transformer bushing data into a pre-trained dual-tower model; if the output result of the dual-tower model is greater than a similarity threshold, determining that the fault type of the bushing to be detected of the transformer is a target fault type; the target fault type is the fault type reflected by the faulty transformer bushing data; otherwise, determining that the bushing to be detected of the transformer does not have a target fault.

[0042] Specifically, the double-tower model may be input with completion data and faulty transformer bushing data for multiple times, with the fault type of the faulty transformer bushing data input each time being different. Thus, the fault type of the transformer bushing to be detected may be confirmed one by one according to the output results of the double-tower model.

[0043] For example, during the training of the dual-tower model, all transformer bushing feature information is sent to the dual-tower model, and one feature information is input to the left tower and the right tower respectively. If both transformer bushings are in normal state, the output value after the cosine function should be close to 1; if the left tower inputs normal transformer bushing data and the right tower inputs abnormal transformer bushing data, the output value after the cosine function should be close to 0; if the left tower inputs abnormal heat dissipation data and the right tower inputs abnormal insulation data, and the two abnormal conditions are different, the output value after the cosine function should be close to 0. The dual-tower model is trained according to the above conditions, and finally a trained model is obtained for subsequent rapid detection of abnormal equipment.

[0044] The technical solution of the embodiment of the present application includes: constructing a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix; mapping multiple complete bushing data and missing bushing data to the regenerated kernel Hilbert space based on the target kernel function, and completing the missing values ​​according to the similarity between the missing values ​​and other data points to obtain the completed data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; based on the completed data, the bushing to be detected of the transformer is fault identified to obtain a fault identification result. The technical solution maps the missing bushing data to the regenerated kernel Hilbert space through a matrix that can reflect the characteristics of the transformer bushing, and then determines the data points similar to the missing values ​​in the regenerated kernel Hilbert space, and after the data is completed, fault identification is performed based on the completed data, so that the fault identification result of the bushing to be detected of the transformer can be accurately determined.

[0045] Embodiment 2

[0046] Figure 2 This is a flow chart of a transformer bushing fault identification method provided in Embodiment 2 of the present application. The embodiment of the present application is optimized based on the above embodiment.

[0047] like Figure 2 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0048] S210, constructing a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix.

[0049] The target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing.

[0050] In an embodiment of the present application, optionally, constructing a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix includes: the target kernel function is determined according to the following formula:

[0051]

[0052] in, is the target kernel function, k b (x, y) is the original kernel function, η is a constant greater than 0, for The transposed matrix of x is the source domain data set, β(,) is a binary function, x1 is the data in the source domain data set, M is the target symmetric semi-positive definite matrix, y is the target domain dataset.

[0053] For example, M∈R H×H , that is, the target symmetric semi-positive definite matrix is ​​full of real numbers, H is the number of data in the data set, the source domain data set is the complete casing data, and the target domain data set is the missing casing data. β(,) can be a kernel function.

[0054] Furthermore, the following proves For any finite number of data z1,…,z N ,have

[0055]

[0056] here

[0057]

[0058] Because k b is the kernel function, so K b is a symmetric positive definite matrix, and because M is a symmetric semi-positive definite matrix, ΦT MΦ∈R N×N is also a symmetric semi-positive definite matrix, so, is a symmetric positive definite matrix.

[0059] Furthermore, the mean difference between the source domain data and the target domain data can be calculated to determine the objective function used by the target symmetric semi-positive definite matrix according to the mean difference:

[0060] because is symmetric positive definite, so, is a kernel function that can be used to generate a RKHS, and It is the reproducing core of this RKHS (for a RKHS, the reproducing core is unique).

[0061] The data with similar problems but without any missing information are regarded as source domain data, and the data with similar problems but with any missing information are regarded as target domain data.

[0062] Source domain data X s and target domain data X t After transformation to RKHS, it becomes and Their maximum mean difference is:

[0063]

[0064] This mean difference can be expressed as:

[0065]

[0066] here

[0067]

[0068]

[0069]

[0070]

[0071] Furthermore, we adopt the sample dependence and learnable kernel function we proposed, and we have

[0072]

[0073]

[0074] Finally there is

[0075]

[0076]

[0077] here

[0078]

[0079] The maximum mean difference then becomes:

[0080]

[0081] In an embodiment of the present application, optionally, the process of determining the target symmetric semi-positive definite matrix includes: iteratively optimizing the initial symmetric semi-positive definite matrix based on Riemann manifold, during the iteration process, the objective function is the mean difference between the source domain data and the target domain data, and the iteration goal is to make the objective function as small as possible; if it is determined that the iteration has ended, the final matrix is ​​determined as the target symmetric semi-positive definite matrix.

[0082] In the embodiment of the present application, optionally, the objective function is:

[0083]

[0084] in, Ns is the number of source domain data points, Nt is the number of target domain data points, Φ is the mapping value of source domain data or target domain data in the reproducing kernel Hilbert space, M is a symmetric semi-positive definite matrix, and μ is a constant.

[0085] Exemplarily, the objective function is: T Φ T MΦΓ+μM 2 , the iteration goal is to minimize the objective function as much as possible. The restriction is: M T =M and M is greater than or equal to 0.

[0086] This scheme is set up so that the target kernel function can reflect the characteristic information of the transformer bushing, so that the similarity can be determined more accurately in the regenerated kernel Hilbert space.

[0087] S220 , mapping the plurality of complete casing data and the missing casing data to the reproducing kernel Hilbert space based on the target kernel function, and determining a first number of data points in the complete casing data that satisfy a similarity condition with the missing value.

[0088] The first number may be 10. Specifically, among the similarities between each data point and the missing value, the top 10 data points are selected in descending order of similarity, and the missing value in the completed data is determined according to the average value of the top 10 data points.

[0089] S230, determining an average value of the first number of data points as the missing value in the supplemented data.

[0090] S240, performing fault identification on the bushing to be inspected of the transformer based on the supplemented data to obtain a fault identification result.

[0091] The technical solution of the embodiment of the present application determines the objective function through the maximum mean difference, and then iteratively optimizes the initial symmetric semi-positive definite matrix based on the Riemann manifold. The iterative goal is to minimize the objective function as much as possible, and obtain the target symmetric semi-positive definite matrix, and then determine the target kernel function. When calculating the similarity in the regenerating kernel Hilbert space, since the target kernel function reflects the characteristics of the transformer bushing, the similarity calculation is more accurate, and the subsequent data completion process can be completed according to the data points with better similarity, and finally a more accurate fault identification result is obtained.

[0092] Embodiment 3

[0093] Figure 3 This is a schematic diagram of the structure of a transformer bushing fault identification device provided in the third embodiment of the present application. The device can execute the transformer bushing fault identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 3 As shown, the device comprises:

[0094] The target kernel function construction module 310 is used to construct the target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix; the target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing.

[0095] The completion data determination module 320 is used to map multiple complete bushing data and missing bushing data to the regenerated kernel Hilbert space based on the target kernel function, and to complete the missing value according to the similarity between the missing value and other data points, so as to obtain the completion data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data;

[0096] The fault identification module 330 is used to perform fault identification on the bushing to be inspected of the transformer based on the supplemented data to obtain a fault identification result.

[0097] The technical solution of the embodiment of the present application includes: a target kernel function construction module 310, which is used to construct a target kernel function based on the original kernel function and a target symmetric semi-positive definite matrix; the target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing; a completion data determination module 320, which is used to map multiple complete bushing data and missing bushing data to the regenerated kernel Hilbert space based on the target kernel function, and to complete the missing values ​​according to the similarity between the missing values ​​and other data points, so as to obtain the completed data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; a fault identification module 330, which is used to perform fault identification on the bushing to be detected of the transformer based on the completed data, and obtain a fault identification result. The technical solution maps the missing bushing data to the regenerated kernel Hilbert space through a matrix that can reflect the characteristics of the transformer bushing, and then determines the data points similar to the missing values ​​in the regenerated kernel Hilbert space, and performs fault identification based on the completed data after the data is completed, so as to accurately determine the fault identification result of the bushing to be detected of the transformer.

[0098] Optionally, the target kernel function construction module 310 includes:

[0099] The target kernel function determination unit is used to determine the target kernel function according to the following formula:

[0100]

[0101] in, is the target kernel function, k b (x, y) is the original kernel function, η is a constant greater than 0, for The transposed matrix of x is the source domain data set, β(,) is a binary function, x1 is the data in the source domain data set, M is the target symmetric semi-positive definite matrix, y is the target domain dataset.

[0102] Optionally, the device further comprises: a target symmetric semi-positive definite matrix determination module, comprising:

[0103] An objective function determination unit is used to iteratively optimize the initial symmetric semi-positive definite matrix based on the Riemann manifold. During the iteration process, the objective function is the mean difference between the source domain data and the target domain data, and the iteration goal is to minimize the objective function.

[0104] The target symmetric semi-positive definite matrix determining unit is used to determine the finally obtained matrix as the target symmetric semi-positive definite matrix if it is determined that the iteration has ended.

[0105] Optionally, the objective function is:

[0106]

[0107] in, Ns is the number of source domain data points, Nt is the number of target domain data points, Φ is the mapping value of source domain data or target domain data in the reproducing kernel Hilbert space, M is a symmetric semi-positive definite matrix, and μ is a constant.

[0108] Optionally, the completion data determination module 320 includes:

[0109] A first number of data point determination unit, used to determine a first number of data points that meet a similarity condition with the missing value in the complete casing data;

[0110] The supplementary data determining unit is used to determine the average value of the first number of data points as the missing value in the supplementary data.

[0111] Optionally, the fault identification module 330 is specifically configured to:

[0112] Input the completed data and normal transformer bushing data into the pre-trained dual-tower model;

[0113] If the output result of the double-tower model is greater than the similarity threshold, it is determined that the bushing to be tested of the transformer has no fault;

[0114] Otherwise, it is determined that the bushing to be inspected of the transformer is faulty.

[0115] Optionally, the fault identification module 330 is specifically configured to:

[0116] Input the completed data and the faulty transformer bushing data into the pre-trained dual-tower model;

[0117] If the output result of the double-tower model is greater than the similarity threshold, the fault type of the transformer bushing to be detected is determined to be the target fault type; the target fault type is the fault type reflected by the faulty transformer bushing data;

[0118] Otherwise, it is determined that the bushing to be inspected of the transformer does not have a target fault.

[0119] A transformer bushing fault identification device provided in an embodiment of the present application can execute a transformer bushing fault identification method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0120] Embodiment 4

[0121] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0122] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0123] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a fault identification method for a transformer bushing.

[0125] In some embodiments, the transformer bushing fault identification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the transformer bushing fault identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the transformer bushing fault identification method in any other appropriate manner (e.g., by means of firmware).

[0126] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0128] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0131] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0132] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0133] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A transformer bushing fault identification method, characterized in that: include: Construct a target kernel function based on the original kernel function and the target symmetric semi-positive definite matrix; The target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing; Based on the target kernel function, multiple complete bushing data and missing bushing data are mapped to the regenerated kernel Hilbert space, and the missing values ​​are completed according to the similarity between the missing values ​​and other data points to obtain the completed data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; Based on the supplemented data, fault identification is performed on the bushing to be inspected of the transformer to obtain a fault identification result.

2. The method according to claim 1, characterized in that The target kernel function is constructed based on the original kernel function and the target symmetric semi-positive definite matrix, including: The target kernel function is determined according to the following formula: in, is the target kernel function, k b (x, y) is the original kernel function, η is a constant greater than 0, for The transposed matrix of x is the source domain data set, β(,) is a binary function, x1 is the data in the source domain data set, M is the target symmetric semi-positive definite matrix, y is the target domain dataset.

3. The method according to claim 2, characterized in that The process of determining the target symmetric semi-positive definite matrix includes: The initial symmetric semi-positive definite matrix is ​​iteratively optimized based on Riemann manifold. During the iteration process, the objective function is the mean difference between the source domain data and the target domain data, and the iteration goal is to minimize the objective function. If it is determined that the iteration has ended, the final matrix is ​​determined as the target symmetric semi-positive definite matrix.

4. The method according to claim 3, characterized in that The objective function is: in, N s is the number of source domain data points, N t is the number of target domain data points, Φ is the mapping value of source domain data or target domain data in the reproducing kernel Hilbert space, M is a symmetric semi-positive definite matrix, and μ is a constant.

5. The method according to claim 1, characterized in that According to the similarity between the missing value and other data points, the missing value is completed to obtain the completed data of the bushing to be tested of the transformer, including: Determining a first number of data points in the complete casing data that satisfy a similarity condition with the missing value; The mean of the first number of data points is determined to fill in the missing values ​​in the data.

6. The method according to claim 1, characterized in that Based on the supplemented data, fault identification is performed on the bushing to be detected of the transformer to obtain a fault identification result, including: Input the completed data and normal transformer bushing data into the pre-trained dual-tower model; If the output result of the double-tower model is greater than the similarity threshold, it is determined that the bushing to be tested of the transformer has no fault; Otherwise, it is determined that the bushing to be inspected of the transformer is faulty.

7. The method according to claim 1, characterized in that Based on the supplemented data, fault identification is performed on the bushing to be detected of the transformer to obtain a fault identification result, including: Input the completed data and the faulty transformer bushing data into the pre-trained dual-tower model; If the output result of the double-tower model is greater than the similarity threshold, the fault type of the transformer bushing to be detected is determined to be the target fault type; the target fault type is the fault type reflected by the faulty transformer bushing data; Otherwise, it is determined that the bushing to be inspected of the transformer does not have a target fault.

8. A transformer bushing fault identification device, characterized in that: include: A target kernel function construction module is used to construct a target kernel function based on the original kernel function and a target symmetric semi-positive definite matrix; The target symmetric semi-positive definite matrix is ​​a matrix that can reflect the characteristics of the transformer bushing A completion data determination module is used to map multiple complete bushing data and missing bushing data to a regenerating kernel Hilbert space based on a target kernel function, and to complete the missing values ​​according to the similarity between the missing values ​​and other data points, so as to obtain the completion data of the bushing to be detected of the transformer; the missing bushing data is the data of the bushing to be detected of the transformer, and the amount of data in the missing bushing data is less than the amount of data in the complete bushing data; The fault identification module is used to perform fault identification on the bushing to be detected of the transformer based on the supplemented data to obtain a fault identification result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the transformer bushing fault identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the transformer bushing fault identification method according to any one of claims 1 to 7 when executed.

Images