Transformer insulation defect diagnosis method and device under electromechanical combined action and computing equipment

Abstract

The invention relates to the technical field of transformers, in particular to the technical field of transformers, and particularly relates to a transformer insulation defect diagnosis method and device under the electromechanical joint effect and computing equipment. The method comprises the steps that a vibration signal and a discharge signal of partial discharge of a to-be-detected transformer are acquired; performing correlation analysis according to the vibration signal and the discharge signal; if it is determined that the discharge signal is related to the vibration signal, performing defect diagnosis on the to-be-detected transformer based on a preset partial discharge database; and if it is determined that the discharge signal is irrelevant to the vibration signal, performing defect diagnosis on the to-be-detected transformer based on the discharge signal. According to the transformer insulation defect diagnosis scheme under the mechanical-electrical combined action, more comprehensive information is provided by combining the vibration signal and the discharge signal, the diagnosis accuracy and reliability are improved, and the technical blank of diagnosis under the mechanical-electrical combined action is filled.

Description

Technical Field

[0001] The present application relates to the technical field of transformers, and in particular to a method, device and computing equipment for diagnosing transformer insulation defects under the combined action of electromechanics and electricity. Background Art

[0002] Power transformers are the "core" of the power grid. Once a fault occurs, it will cause huge economic losses, and in serious cases, it may cause the local power grid to be paralyzed. The transformer is a typical mechanical and electrical synergistic system. It will produce mechanical vibration during normal operation. The vibration has a destructive effect on the oil-paper insulation, causing insulation degradation and even developing into serious accidents.

[0003] At present, most of the research on partial discharge of transformers is based on the electrical stress they are subjected to. Since the actual transformer insulation degradation process is affected by the synergistic effect of electromechanics and electricity, it is difficult to fully obtain its insulation status through a single test. The oil-paper insulation of the transformer undergoes partial discharge, and mechanical stress has a significant impact on the partial discharge of the oil-paper insulation. The transformer insulation defect diagnosis technology considering the combined effect of electromechanics needs further in-depth research.

[0004] Therefore, there is an urgent need for a transformer insulation defect diagnosis scheme under the combined electromechanical action to diagnose the insulation defects of the transformer under the combined electromechanical working condition and improve the operation, maintenance and fault diagnosis level of the transformer. Summary of the invention

[0005] In view of this, it is necessary to provide a transformer insulation defect diagnosis scheme under the combined action of electromechanics, aiming to achieve accurate diagnosis of the transformer insulation status through comprehensive analysis of partial discharge tests and vibration signals, and prevent accidents caused by insulation degradation.

[0006] A transformer insulation defect diagnosis method under electromechanical combined action, comprising:

[0007] Obtaining vibration signals and discharge signals of partial discharge of the transformer to be tested;

[0008] Performing correlation analysis based on the vibration signal and the discharge signal;

[0009] If it is determined that the discharge signal is related to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on a preset partial discharge database;

[0010] If it is determined that the discharge signal is unrelated to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on the discharge signal.

[0011] Preferably, the vibration signal and the discharge signal of the partial discharge of the transformer to be tested are obtained, and then the method further includes:

[0012] Preprocessing the vibration signal and the discharge signal;

[0013] Fusing the preprocessed vibration signal and the discharge signal to construct a first fusion feature matrix;

[0014] Extracting key feature parameters from the first fused feature matrix;

[0015] A preliminary defect diagnosis is performed on the transformer to be tested according to the key characteristic parameters.

[0016] Preferably, if it is determined that the discharge signal is related to the vibration signal, defect diagnosis of the transformer to be tested is performed based on a preset partial discharge database, including:

[0017] Performing correlation analysis based on the vibration signal and the discharge signal in the first fusion feature matrix to determine a feature set related to the discharge signal;

[0018] Fusing the feature set related to the discharge signal to obtain a second fused feature matrix;

[0019] The second fused feature matrix is ​​compared with the feature matrix in a preset partial discharge database to determine the sample with the highest similarity to the preset partial discharge database, and defect diagnosis is performed on the transformer to be tested.

[0020] Preferably, performing correlation analysis based on the vibration signal and the discharge signal in the first fusion feature matrix to determine a feature set related to the discharge signal includes:

[0021] The mRMR algorithm is used to screen out a feature set related to the discharge signal from the first fused feature matrix.

[0022] Preferably, if it is determined that the discharge signal is unrelated to the vibration signal, performing defect diagnosis on the transformer to be tested based on the discharge signal includes:

[0023] extracting a discharge signal feature of the discharge signal, and determining a PRPD spectrum of the discharge signal;

[0024] Defect diagnosis is performed based on the discharge signal characteristics and the PRPD spectrum.

[0025] Preferably, the method further includes: constructing the preset partial discharge database:

[0026] Obtain partial discharge signals of sample transformers with different defects;

[0027] Extracting a sample vibration signal and a sample discharge signal of the defective sample transformer according to the partial discharge signal;

[0028] Performing correlation analysis on the sample vibration signal and the sample discharge signal to obtain defect classification results corresponding to different defects;

[0029] The preset partial discharge database is established according to the defect division result.

[0030] Preferably, preprocessing the vibration signal and the discharge signal includes:

[0031] The vibration signal and the discharge signal are subjected to de-averaging, whitening and filtering.

[0032] Preferably, it also includes:

[0033] Acquiring the ultrasonic signal of the transformer under test synchronously when acquiring the discharge signal of the transformer under test;

[0034] determining a correlation coefficient between the ultrasonic signal and the electrical signal;

[0035] Based on the correlation coefficient, the electrical signal is obtained from the ultrasonic signal.

[0036] The present application also provides a transformer insulation defect diagnosis device under the combined action of electromechanics, comprising:

[0037] A data acquisition module, used to acquire a vibration signal and a discharge signal of a partial discharge of the transformer to be tested;

[0038] An analysis module, used for performing correlation analysis based on the vibration signal and the discharge signal;

[0039] A diagnosis module, configured to perform defect diagnosis on the transformer to be tested based on a preset partial discharge database when it is determined that the discharge signal is related to the vibration signal;

[0040] The diagnosis module is further configured to perform defect diagnosis on the transformer to be tested based on the discharge signal if it is determined that the discharge signal is unrelated to the vibration signal.

[0041] The present application also provides a computing device, including: a processor, and a memory, on which program instructions are stored. When the program instructions are executed by the processor, the processor executes the transformer insulation defect diagnosis method under the combined electromechanical action as described above.

[0042] Compared with the prior art, the beneficial effect of the present application is that the above-mentioned transformer insulation defect diagnosis scheme under the combined action of mechanical and electrical elements provides more comprehensive information by combining vibration signals and discharge signals, improves the accuracy and reliability of diagnosis, and fills the technical gap in diagnosis under the combined action of mechanical and electrical elements. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a transformer insulation defect diagnosis method under the combined electromechanical action provided in this application.

[0044] Figure 2 It is a flowchart of the process of establishing a preset partial discharge database provided by this application.

[0045] Figure 3 It is a structural schematic diagram of the transformer insulation defect diagnosis device 300 under the combined electromechanical action provided in the present application.

[0046] Figure 4 It is a structural schematic diagram of a computing device 900 provided in this application. DETAILED DESCRIPTION

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] See also Figure 1 , Figure 1 The figure is a flow chart of a transformer insulation defect diagnosis method under the combined action of electromechanics provided in the present application. The transformer insulation defect diagnosis method under the combined action of electromechanics comprises the following steps:

[0049] S101: Acquire a vibration signal and a discharge signal of a partial discharge of a transformer to be tested.

[0050] In this embodiment, multiple vibration sensors are used. The vibration sensors are attached to the surface of the transformer through coupling agents and magnets to achieve good signal collection effects. The vibration sensors are respectively attached to the high, middle and low parts of the front and side of the transformer to obtain more comprehensive vibration signals, which helps to more accurately reflect the vibration conditions inside the transformer.

[0051] For the measurement of vibration signals, a result parameter is required to reflect the severity of the vibration, such as using the effective value as the criterion for judging the vibration condition. The effective value formula is expressed as:

[0052]

[0053] Where X represents the vibration signal, T represents the signal period, N represents the number of sampling points in a complete period, and Δt represents the time interval between sampling points.

[0054] Furthermore, this embodiment uses an ultrasonic sensor to measure the partial discharge signal, and its detection frequency band can effectively avoid electromagnetic interference, thereby improving the accuracy of detection. In addition, the ultrasonic sensor can also determine the spatial position of the discharge point. Specifically, the ultrasonic signal and the electrical signal can be collected in advance at the same time to determine the correlation coefficient between the ultrasonic signal and the electrical signal; based on the correlation coefficient, the electrical signal is obtained (expressed) through the ultrasonic signal. Among them, the ultrasonic sensor can be set on the oil tank wall of the transformer, and the partial discharge in the transformer can be qualitatively measured by the measured ultrasonic signal.

[0055] Furthermore, the vibration signal and discharge signal of the partial discharge of the transformer to be tested are obtained, which usually contain a large number of original signals, which may contain noise, outliers and trend items. The vibration signal and the discharge signal can be preprocessed, including de-averaging, whitening and filtering, to eliminate noise and outliers and ensure the accuracy and reliability of the data.

[0056] Furthermore, the pre-processed vibration signal and the discharge signal are fused to construct a first fusion feature matrix. According to the key feature parameters in the first fusion feature matrix, some obvious faults can be quickly eliminated, reducing the complexity of subsequent analysis. Specifically, when constructing the first fusion feature matrix, a preliminary feature selection can be performed first to select the most representative feature parameters, i.e., key feature parameters. For example, extract the RMS, mean, variance, kurtosis, and skewness time domain features of the vibration signal, extract the apparent discharge amount and discharge repetition rate in the local discharge signal, extract the effective value, peak value, 50Hz component, and 100Hz component parameters of the ultrasonic signal, obtain the PRPD spectrum and the ultrasonic signal phase-amplitude scatter plot, etc.

[0057] Then, the extracted characteristic parameters are standardized, such as normalization or standardization, to ensure the comparability between different characteristics and eliminate dimensional differences. Finally, a preliminary defect diagnosis is performed on the transformer to be tested based on the key characteristic parameters to identify whether there are obvious mechanical or electrical faults. The analysis process can be based on existing specification data and engineering experience.

[0058] In addition, by comparing the first fusion feature matrix in different time periods, the operation trend of the transformer can be analyzed and potential problems can be discovered in time.

[0059] S102: performing correlation analysis based on the vibration signal and the discharge signal.

[0060] The ultrasonic signal (i.e., discharge signal) and the transformer box vibration signal when partial discharge occurs are collected synchronously to analyze the correlation between the two. This includes the correlation between time domain features and frequency domain features:

[0061] For time domain features, the time domain features of ultrasonic signals include effective value and peak value. The effective value of ultrasonic signals reflects the overall strength of the signal, and the peak value reflects the maximum amplitude of the ultrasonic signal. The 50Hz component and the 100Hz component are harmonic components related to the power frequency voltage in the ultrasonic signal. The time domain features of vibration signals include effective value of vibration signals, average value of vibration signals, variance of vibration signals, kurtosis of vibration signals, skewness of vibration signals, etc.

[0062] For frequency domain features, including spectrum distribution, frequency band energy, etc., Fourier transform can be used to extract the spectrum distribution of ultrasonic signals and vibration signals, and frequency band energy can be obtained by calculating the energy distribution in different frequency bands. In addition, wavelet transform can be used to extract time-frequency domain features and further refine feature parameters.

[0063] Then the correlation coefficient between the ultrasonic signal and the vibration signal is calculated to evaluate the linear relationship between them. The correlation between the discharge signal and the vibration signal can be calculated using methods such as the Pearson correlation coefficient, the Spearman rank correlation coefficient, or the Kendall rank correlation coefficient. In addition, the cross-spectral density of the ultrasonic signal and the vibration signal is calculated to evaluate their correlation at different frequencies, and the time delay between the ultrasonic signal and the vibration signal is calculated to evaluate their relationship in the time domain.

[0064] Finally, the correlation between the vibration signal and the discharge signal is comprehensively judged, for example:

[0065] Correlation coefficient: Set a correlation threshold. If the correlation coefficient is greater than the correlation threshold (for example, the correlation threshold is 0.7), it is considered that the ultrasonic signal is correlated with the vibration signal. Otherwise, it is considered that the ultrasonic signal is unrelated to the vibration signal.

[0066] Cross-spectral density: If the cross-spectral density is high in certain frequency bands, it is considered that the ultrasonic signal and the vibration signal are correlated at these frequencies.

[0067] Time Delay: If the calculated time delay is reasonable (eg, within the expected range), the ultrasonic signal is considered to be correlated with the vibration signal.

[0068] S103: If it is determined that the discharge signal is related to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on a preset partial discharge database.

[0069] Based on the vibration signal and the discharge signal in the first fused feature matrix, correlation analysis is performed to determine a feature set related to the discharge signal; the feature set related to the discharge signal is fused to obtain a second fused feature matrix; the second fused feature matrix is ​​compared with the feature matrix in a preset partial discharge database to determine the sample with the highest similarity with the preset partial discharge database, and defect diagnosis is performed on the transformer to be tested.

[0070] Further, performing correlation analysis based on the vibration signal and the discharge signal in the first fusion feature matrix to determine a feature set related to the discharge signal includes:

[0071] Based on the characteristic parameter combination of the ultrasonic signal and the vibration signal in the first fusion characteristic matrix, the mRMR algorithm is used to screen the features, which can be time domain features, frequency domain features, time-frequency domain features, etc., so that these features have the maximum correlation with the target variable (such as the defect type of the transformer) and the features have the minimum redundancy. For example, the following steps are included:

[0072] Calculate the correlation between features and target variables: Use correlation coefficients (such as Pearson correlation coefficient, mutual information, etc.) to calculate the correlation between each feature and the target variable.

[0073] Calculate redundancy between features: Use correlation coefficient or mutual information to calculate the redundancy between each feature and other features.

[0074] Feature selection: Select the features that have the greatest correlation with the target variable and the least redundancy with other features.

[0075] Then, the mRMR algorithm is used to filter out the feature set most relevant to the transformer acoustic signal from the feature set, thereby improving the accuracy and efficiency of subsequent analysis.

[0076] Furthermore, based on the feature set that is most relevant to the transformer acoustic signal, multiple feature combinations in the feature set can be fused to obtain a second fused feature matrix. The second fused feature matrix is ​​compared with the feature matrix in the preset partial discharge database to find the most similar samples. To find the most similar samples, methods such as Euclidean distance and cosine similarity can be used. According to the severity of similar samples in the database, the severity of the defects of the transformer to be tested is evaluated.

[0077] A detailed diagnostic report can also be generated, including the defect type, severity, possible causes and recommended preventive measures. According to the diagnostic results, corresponding preventive measures are proposed, such as strengthening maintenance, replacing parts, adjusting operating parameters, etc., to prevent accidents caused by insulation deterioration of the transformer.

[0078] Furthermore, establishing a preset partial discharge database may include:

[0079] Obtain partial discharge signals of sample transformers with different defects; extract sample vibration signals and sample discharge signals of the defective sample transformer based on the partial discharge signals; perform correlation analysis based on the sample vibration signals and the sample discharge signals to obtain defect division results corresponding to different defects; and establish the preset partial discharge database based on the defect division results.

[0080] like Figure 2 The flowchart of the process of establishing the preset partial discharge database is shown in FIG. Specifically, the process of establishing the preset partial discharge database is as follows:

[0081] N1: Obtaining partial discharge test data of defective sample transformer

[0082] Partial discharge test: Partial discharge test is carried out on transformer samples containing different defects, applying power frequency voltage.

[0083] Vibration signal acquisition: Vibration sensors are arranged on the surface of the transformer box to measure the generated vibration signals.

[0084] Ultrasonic signal acquisition: Use ultrasonic sensors to collect ultrasonic signals generated by local discharge.

[0085] Data recording: Record all collected vibration signals and partial discharge signals to ensure data integrity and accuracy.

[0086] N2: Based on the experimental data, the partial discharge signal characteristics of the defective sample transformer are obtained

[0087] Vibration signal feature extraction: Extract the time domain features of the vibration signal, including RMS (root mean square), mean, variance, kurtosis, skewness, etc.

[0088] Partial discharge signal feature extraction: Extract characteristic parameters of partial discharge signals, such as apparent discharge amount, discharge repetition rate, effective value of ultrasonic signal, peak value, 50Hz component, 100Hz component, etc.

[0089] PRPD spectrum: Generate a phase-resolved partial discharge spectrum (PRPD spectrum) of partial discharge to analyze the phase distribution and amplitude characteristics of the discharge.

[0090] Ultrasonic signal phase-amplitude scatter plot: Generate a phase-amplitude scatter plot of the ultrasonic signal for further analysis of the spatiotemporal characteristics of the discharge.

[0091] N3: Feature Parameter Extraction and Analysis

[0092] Data fusion: The vibration signal and the partial discharge signal data are fused to construct the basic first fusion feature matrix A.

[0093] Feature extraction: Further feature extraction is performed on the fused data, including time domain features, frequency domain features, and time-frequency domain features.

[0094] Time domain features: such as RMS, mean, variance, kurtosis, skewness, etc.

[0095] Frequency domain features: such as spectrum analysis, power spectral density, etc.

[0096] Time-frequency domain features: Wavelet packet decomposition is used to decompose the signal into components of different frequencies and time scales, and the energy percentage of the last layer of sub-bands is extracted as features.

[0097] N4: Correlation feature analysis

[0098] Synchronous measurement of partial discharge and vibration signals: Synchronously collect the ultrasonic signal when partial discharge occurs and the vibration signal of the transformer box, and analyze the correlation between the two.

[0099] Wavelet packet decomposition: Use wavelet packet decomposition to decompose the signal into components of different frequencies and time scales, and extract time-frequency domain features.

[0100] mRMR algorithm: The mRMR (maximum relevance minimum redundancy) algorithm is used to screen out the feature set most relevant to the transformer acoustic signal, construct the second fusion feature matrix B, and calculate the correlation coefficient R between the fusion feature matrices in different operating periods.

[0101] N5: Determine the defect type and severity

[0102] Partial discharge type classification:

[0103] Suspension discharge: The phases are mainly between 70°~130° and 260°~300°, and the number of discharges decreases as the phase increases.

[0104] Tip discharge: The phases are mainly between 50°~120° and 200°~270°, and the number of discharges is concentrated around 70°.

[0105] Air-gap discharge: The phase is mainly between 40°~130° and 230°~320°, and the PRPD spectrum is hump-shaped.

[0106] Surface discharge: There are two different agglomeration distributions in the PRPD spectrum. The discharge occurs at the peak positions of the positive and negative half cycles and is relatively symmetrical.

[0107] Severity assessment: The severity of the discharge was assessed based on the PRPD spectrum and ultrasound signal characteristics.

[0108] N6: Complete the establishment of the preset partial discharge database.

[0109] The obtained partial discharge type and severity evaluation related results are stored to obtain a preset partial discharge database.

[0110] S104: If it is determined that the discharge signal is unrelated to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on the discharge signal.

[0111] Extracting the discharge signal characteristics of the discharge signal and determining the PRPD spectrum of the discharge signal; and performing defect diagnosis based on the discharge signal characteristics and the PRPD spectrum.

[0112] Among them, the PRPD spectrum and ultrasonic signal characteristics are collectively referred to as partial discharge characteristics. These characteristic parameters are key information extracted from the partial discharge signal and are used to diagnose the insulation status of the transformer. The partial discharge characteristic parameters include but are not limited to the apparent discharge amount, discharge repetition rate, effective value of the ultrasonic signal, peak value, 50Hz component, 100Hz component, etc.

[0113] Afterwards, the partial discharge defects inside the transformer, such as suspended discharge, tip discharge, air gap discharge, etc., can be identified and located by analyzing the partial discharge characteristics.

[0114] When evaluating the health status of transformer insulation, predict potential failure risks. Based on the diagnosis results, take corresponding preventive measures to prevent transformer accidents caused by insulation degradation. It can comprehensively and accurately evaluate the insulation status of the transformer and improve the safe operation level of the transformer.

[0115] Furthermore, for the defect severity evaluation of steps S103-S104, the development process of partial discharge can also be divided into a slight stage, a moderate stage and a severe stage. The difference in adjacent partial discharge pulse amplitudes, the ratio of the maximum discharge pulse amplitudes, the adjacent discharge time interval, the discharge amplitude, the number of discharges and the ultrasonic equivalent root mean square bandwidth are extracted as discharge severity evaluation parameters. There are differences in the development process of different defects. A large number of evaluation parameters are obtained by conducting discharge tests on defects of different severity, and the changes in the evaluation parameters of different defects within the same time interval are obtained. The development of the defects is evaluated, and the division of the development stage of the defect partial discharge and the evaluation of the development process are completed.

[0116] The transformer insulation defect diagnosis method under the electromechanical joint action provided in this embodiment comprehensively considers the electromechanical joint action, realizes the determination of the insulation defect type and severity, and improves the accuracy and reliability of transformer insulation defect diagnosis. At the same time, it can also analyze the process of transformer insulation degradation, which can effectively prevent the further degradation of transformer insulation.

[0117] Based on the same inventive concept, the present application also provides a transformer insulation defect diagnosis device 300 under the combined action of electromechanics, such as Figure 3 The schematic diagram of the structure of the transformer insulation defect diagnosis device 300 under the combined action of electromechanics shown in FIG. 1 includes:

[0118] The data acquisition module 301 is used to acquire the vibration signal and discharge signal of the partial discharge of the transformer to be tested;

[0119] An analysis module 302, configured to perform correlation analysis based on the vibration signal and the discharge signal;

[0120] A diagnosis module 303, configured to perform defect diagnosis on the transformer to be tested based on a preset partial discharge database when it is determined that the discharge signal is related to the vibration signal;

[0121] The diagnosis module 303 is further configured to perform defect diagnosis on the transformer to be tested based on the discharge signal if it is determined that the discharge signal is unrelated to the vibration signal.

[0122] The transformer insulation defect diagnosis device 300 under the electromechanical combined action provided in this embodiment can be used to execute the transformer insulation defect diagnosis method under the electromechanical combined action provided in steps S101 to S104 and any optional embodiments thereof, which will not be described in detail.

[0123] Based on the same inventive concept, the present application also provides a computing device 900, Figure 4 900 is a schematic structural diagram of a computing device provided by the present application. The computing device can execute the optional embodiments of the experimental method based on the above transformer oil-paper insulation electromechanical combined action experimental system. The computing device can be a terminal or a chip or chip system inside the terminal. Figure 4 As shown, the computing device 900 includes: a processor 910 , a memory 920 , and a communication interface 930 .

[0124] It should be understood that Figure 4 The communication interface 930 in the computing device 900 shown may be used to communicate with other devices, and may specifically include one or more transceiver circuits or interface circuits.

[0125] The processor 910 may be connected to a memory 920. The memory 920 may be used to store the program code and data. Therefore, the memory 920 may be a storage unit inside the processor 910, or an external storage unit independent of the processor 910, or a component including a storage unit inside the processor 910 and an external storage unit independent of the processor 910.

[0126] Optionally, the computing device 900 may further include a bus. The memory 920 and the communication interface 930 may be connected to the processor 910 via the bus. The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 A line without an arrow is used to represent the bus, but this does not mean that there is only one bus or one type of bus.

[0127] It should be understood that in the embodiment of the present application, the processor 910 may adopt a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Alternatively, the processor 910 may adopt one or more integrated circuits to execute relevant programs to implement the technical solutions provided in the embodiment of the present application.

[0128] The memory 920 may include a read-only memory and a random access memory, and provides instructions and data to the processor 910. A portion of the processor 910 may also include a nonvolatile random access memory. For example, the processor 910 may also store information on the device type.

[0129] When the computing device 900 is running, the processor 910 executes the computer-executable instructions in the memory 920 to perform any operation step of the above method and any optional embodiment thereof.

[0130] It should be understood that the computing device 900 according to the embodiment of the present application may correspond to the corresponding subject in the method according to each embodiment of the present application, and the above-mentioned and other operations and / or functions of each module in the computing device 900 are respectively to implement the steps of the present method, and can be implemented by electronic hardware, or computer software, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application. For example, the devices described in the above embodiments, or the units or modules contained in the devices, can be implemented by processes or software modules, wherein the software modules can be units obtained by splitting according to functional logic. Technical personnel in the relevant field can clearly understand that the corresponding processes of the various methods of the examples are not repeated here for the sake of brevity.

[0131] A person of ordinary skill in the art may appreciate that, in combination with the units and components of the various examples described in the embodiments disclosed herein, for the sake of convenience and brevity of description, the specific working processes of the systems, devices, and units described above may refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0132] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0136] In addition, the words "first, second, third, etc." or module A, module B, module C and other similar terms in the specification and claims are only used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that the specific order or sequence can be interchanged where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0137] In the above description, the numbers representing the steps, such as S110, S120, etc., do not necessarily mean that the steps will be executed in this manner. If permitted, the order of the steps can be interchanged or they can be executed simultaneously.

[0138] The term "comprising" as used in the description and claims should not be interpreted as being limited to what is listed thereafter; it does not exclude other elements or steps. Therefore, it should be interpreted as specifying the presence of the features, integers, steps or components mentioned, but does not exclude the presence or addition of one or more other features, integers, steps or components and groups thereof. Therefore, the expression "a device comprising means A and B" should not be limited to a device consisting of components A and B only.

[0139] References to "one embodiment" or "an embodiment" in this specification mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present application. Therefore, the phrases "in one embodiment" or "in an embodiment" appearing in various places in this specification do not necessarily refer to the same embodiment, but may refer to the same embodiment. In addition, in one or more embodiments, the particular features, structures, or characteristics can be combined in any appropriate manner, as would be apparent to one of ordinary skill in the art from this disclosure.

[0140] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present application, all of which belong to the scope of protection of the present application.

Claims

1. A transformer insulation defect diagnosis method under the combined action of electromechanics, characterized in that: include: Obtaining vibration signals and discharge signals of partial discharge of the transformer to be tested; Performing correlation analysis based on the vibration signal and the discharge signal; If it is determined that the discharge signal is related to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on a preset partial discharge database; If it is determined that the discharge signal is unrelated to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on the discharge signal.

2. The method according to claim 1, characterized in that Obtaining the vibration signal and discharge signal of the partial discharge of the transformer to be tested, and then also including: Preprocessing the vibration signal and the discharge signal; Fusing the preprocessed vibration signal and the discharge signal to construct a first fusion feature matrix; Extracting key feature parameters from the first fused feature matrix; A preliminary defect diagnosis is performed on the transformer to be tested according to the key characteristic parameters.

3. The method according to claim 2, characterized in that If it is determined that the discharge signal is related to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on a preset partial discharge database, including: Performing correlation analysis based on the vibration signal and the discharge signal in the first fusion feature matrix to determine a feature set related to the discharge signal; Fusing the feature set related to the discharge signal to obtain a second fused feature matrix; The second fused feature matrix is ​​compared with the feature matrix in a preset partial discharge database to determine the sample with the highest similarity to the preset partial discharge database, and defect diagnosis is performed on the transformer to be tested.

4. The method according to claim 3, characterized in that Performing correlation analysis based on the vibration signal and the discharge signal in the first fusion feature matrix to determine a feature set related to the discharge signal includes: The mRMR algorithm is used to screen out a feature set related to the discharge signal from the first fused feature matrix.

5. The method according to claim 1, characterized in that: If it is determined that the discharge signal is irrelevant to the vibration signal, a defect diagnosis is performed on the transformer to be tested based on the discharge signal, including: extracting a discharge signal feature of the discharge signal, and determining a PRPD spectrum of the discharge signal; Defect diagnosis is performed based on the discharge signal characteristics and the PRPD spectrum.

6. The method according to claim 1, characterized in that Also includes: Constructing the preset partial discharge database: Obtain partial discharge signals of sample transformers with different defects; Extracting a sample vibration signal and a sample discharge signal of the defective sample transformer according to the partial discharge signal; Performing correlation analysis on the sample vibration signal and the sample discharge signal to obtain defect classification results corresponding to different defects; The preset partial discharge database is established according to the defect division result.

7. The method according to claim 2, characterized in that: Preprocessing the vibration signal and the discharge signal includes: The vibration signal and the discharge signal are subjected to de-averaging, whitening and filtering.

8. The method according to claim 1, characterized in that: Also includes: Acquiring the ultrasonic signal of the transformer under test synchronously when acquiring the discharge signal of the transformer under test; determining a correlation coefficient between the ultrasonic signal and the electrical signal; Based on the correlation coefficient, the electrical signal is obtained from the ultrasonic signal.

9. A transformer insulation defect diagnosis device under the combined action of electromechanics, characterized in that: include: A data acquisition module, used to acquire a vibration signal and a discharge signal of a partial discharge of the transformer to be tested; An analysis module, used for performing correlation analysis based on the vibration signal and the discharge signal; A diagnosis module, configured to perform defect diagnosis on the transformer to be tested based on a preset partial discharge database when it is determined that the discharge signal is related to the vibration signal; The diagnosis module is further configured to perform defect diagnosis on the transformer to be tested based on the discharge signal if it is determined that the discharge signal is unrelated to the vibration signal.

10. A computing device, characterized in that include: processor, and A memory having program instructions stored thereon, wherein when the program instructions are executed by the processor, the processor executes the transformer insulation defect diagnosis method under the electromechanical combined action as described in any one of claims 1 to 8.

Images