Method, system and equipment for identifying turn-to-turn discharge mode of power transformer winding

Abstract

The invention discloses a power transformer winding turn-to-turn discharge mode identification method, system, medium and equipment, and the method comprises the steps: collecting an electrical quantity signal and a non-electrical quantity signal during the discharge of a power transformer winding; performing signal preprocessing by using wavelet transform, and eliminating noise and electromagnetic interference mixed in the electrical quantity signal and the non-electrical quantity signal; fourier transform is utilized to generate a signal spectrogram, and time domain waveforms of each electrical quantity signal and each non-electrical quantity signal and characteristic parameters of the spectrogram are extracted; inputting all the extracted characteristic parameters into a turn-to-turn discharge mode recognition model, and judging whether turn-to-turn discharge occurs in the transformer winding or not; and according to an identification result of the turn-to-turn discharge mode identification model, if turn-to-turn discharge exists, triggering an early warning mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformers, and in particular to a method, system, medium and equipment for identifying inter-turn discharge patterns of power transformer windings. Background Art

[0002] As the core equipment of the power grid, power transformers play a vital role in the transmission and conversion of electric energy. Their safe and stable operation is directly related to the health and stability of the entire power system. However, during the long-term operation of the transformer, due to the influence of various factors such as material aging and insulation failure, local discharge is prone to occur in the transformer windings, especially in the inter-turn parts of the windings. Inter-turn discharge will not only cause the insulation performance of the transformer to gradually decline, but may also cause serious faults such as inter-turn short circuits, and even cause fires and explosions, seriously threatening the overall safety of the power system. According to relevant statistics, among the existing recorded power transformer winding fault accidents, inter-turn short circuit accidents caused by inter-turn discharge account for more than 50%. Therefore, it is very necessary to conduct timely and effective pattern recognition of inter-turn discharge before the inter-turn short circuit occurs.

[0003] At present, although there are many technical methods for the identification and monitoring of interturn discharge patterns of power transformer windings, there are still many shortcomings. Traditional methods mostly rely on manually set feature parameters for identification, which are subjective and prone to misjudgment. In addition, the feature parameters are often relatively simple and only rely on single physical signals for feature extraction. It is difficult to fully reflect the complex characteristics of interturn discharge, resulting in low recognition accuracy. In addition, traditional methods use real-time collected signals for model training and testing, and the timeliness of fault diagnosis is poor, which is not conducive to timely maintenance work. It is urgent to propose a new method for identifying interturn discharge patterns of power transformer windings to solve the contradiction between the requirements for fast speed and high accuracy of interturn discharge pattern recognition and the slow recognition speed and low accuracy of existing methods.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The present invention provides a method, system, medium and equipment for identifying the inter-turn discharge pattern of a power transformer winding, which solves the contradiction between the requirements for fast speed and high accuracy of inter-turn discharge pattern identification and the slow identification speed and low accuracy of existing methods, thereby improving the judgment speed and accuracy.

[0006] A method for identifying an inter-turn discharge pattern of a power transformer winding comprises:

[0007] Step 1: Collect electrical quantity signals and non-electrical quantity signals when the power transformer winding is discharged;

[0008] Step 2: Use wavelet transform to preprocess the signal to eliminate the noise and electromagnetic interference mixed in the electrical quantity signal and non-electrical quantity signal;

[0009] Step 3: Generate a signal spectrum diagram using Fourier transform, and extract characteristic parameters of the time domain waveform and spectrum diagram of each electrical quantity signal and non-electrical quantity signal;

[0010] Step 4: Input all the extracted characteristic parameters into the inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding;

[0011] Step 5: According to the identification result of the inter-turn discharge pattern recognition model, if inter-turn discharge exists, the early warning mechanism is triggered.

[0012] In the method for identifying the inter-turn discharge pattern of a power transformer winding, in step 2, wavelet transform is used to pre-process the electrical quantity signal and the non-electrical quantity signal, filter out the frequency band where the noise is located, retain the frequency band where the real discharge signal is located, and realize the separation of signal and noise.

[0013] In the method for identifying the inter-turn discharge pattern of a power transformer winding, the electrical quantity signals and non-electrical quantity signals include collecting the high-voltage side voltage signal, low-voltage side voltage signal, high-voltage side current signal, low-voltage side current signal, ultrasonic signal, and ultra-high frequency signal of the power transformer winding.

[0014] In the method for identifying the inter-turn discharge pattern of a power transformer winding, a voltage sensor is used to measure the high-voltage side voltage signal and the low-voltage side voltage signal; a current sensor is used to measure the high-voltage side current signal and the low-voltage side current signal; an ultrasonic sensor is used to measure the ultrasonic signal, and the ultrasonic sensor is equipped with an ultrasonic power amplifier; and a UHF sensor is used to measure the UHF signal.

[0015] In the method for identifying the interturn discharge pattern of a power transformer winding, in step 3, Fourier transform is used to generate a spectrum diagram of the de-noised electrical quantity signal and the non-electrical quantity signal, and characteristic parameters of the time domain waveforms and the spectrum diagram of the electrical quantity signal and the non-electrical quantity signal are extracted.

[0016] For the high-voltage side voltage signal, low-voltage side voltage signal, high-voltage side current signal, low-voltage side current signal and ultra-high frequency signal, seven characteristic parameters including maximum discharge amplitude, average discharge amplitude, discharge amplitude entropy, discharge amplitude standard deviation, average pulse repetition rate, skewness and steepness are extracted respectively. For the ultrasonic signal, four characteristic parameters including maximum amplitude, average amplitude, standard deviation of amplitude and mean square amplitude are extracted.

[0017] In the method for identifying the inter-turn discharge pattern of a power transformer winding, the inter-turn discharge pattern recognition model is trained in advance using sample signals of known inter-turn discharge patterns. The inter-turn discharge pattern recognition model uses a support vector machine algorithm as a pattern recognition mechanism, and the characteristic parameters are input into the inter-turn discharge pattern recognition model for pattern recognition. The model output is a recognition result of whether there is inter-turn discharge in the power transformer winding.

[0018] A power transformer winding interturn discharge pattern recognition and monitoring system includes:

[0019] The discharge signal processing module is used to collect the electrical quantity signals and non-electrical quantity signals of the power transformer winding during discharge in real time, and use wavelet transform to perform signal preprocessing to eliminate the noise and electromagnetic interference mixed in the signal.

[0020] The discharge pattern recognition module is used to generate a signal spectrum through Fourier transform, extract the relevant characteristic parameters of each signal time domain waveform and spectrum, and use the trained inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding.

[0021] The equipment status warning module is used to display the recognition results and trigger the alarm. If there is inter-turn discharge, the alarm mechanism is triggered.

[0022] In the system, the discharge mode recognition module includes a processor.

[0023] A computer storage medium includes computer instructions, which, when executed on a computer, cause the computer to execute the method described.

[0024] An electronic device, comprising:

[0025] A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0026] When the processor executes the program, the method described is implemented.

[0027] Compared with the prior art, the present invention has the following advantages: by collecting multiple types of signals during the discharge process and using a pre-trained turn-to-turn discharge pattern recognition model, the present invention can timely and accurately identify the turn-to-turn discharge of power transformer windings. By discovering potential problems early, it provides maintenance strategy support for operation and maintenance personnel to prevent the discharge from developing to a more serious stage, and is expected to be promoted in the field of turn-to-turn discharge pattern recognition and online monitoring of power transformer windings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the detailed description of the preferred specific embodiments below, various other advantages and benefits of the present invention will become clear to those of ordinary skill in the art. The drawings in the specification are only for the purpose of illustrating the preferred embodiments and are not considered to be limitations of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work. Moreover, the same reference numerals are used to represent the same components throughout the drawings.

[0029] In the attached picture:

[0030] Figure 1 It is a flow chart of a method for identifying inter-turn discharge patterns of power transformer windings;

[0031] Figure 2 It is a schematic diagram of the principle of the support vector machine algorithm used in the turn-to-turn discharge pattern recognition model of the present invention;

[0032] Figure 3 It is a schematic diagram of system module composition and functions.

[0033] The present invention is further explained below in conjunction with the accompanying drawings and embodiments. DETAILED DESCRIPTION

[0034] The specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the specific embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0035] It should be noted that certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that technicians may use different nouns to refer to the same component. This specification and claims do not use the difference in nouns as a way to distinguish components, but use the difference in the functions of the components as the criterion for distinction. As mentioned throughout the specification and claims, "including" or "comprising" is an open term, so it should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The scope of protection of the present invention shall be determined by the attached claims.

[0036] To facilitate understanding of the embodiments of the present invention, further explanation will be given below by taking specific embodiments as examples in conjunction with the accompanying drawings, and each of the accompanying drawings does not constitute a limitation on the embodiments of the present invention.

[0037] like Figures 1 to 3 As shown, the method for identifying the inter-turn discharge pattern of a power transformer winding includes the following steps:

[0038] Step 1: Collect electrical quantity signals and non-electrical quantity signals when the power transformer winding is discharged;

[0039] Step 2: Use wavelet transform to preprocess the signal to eliminate the noise and electromagnetic interference mixed in the electrical quantity signal and non-electrical quantity signal;

[0040] Step 3: Generate a signal spectrum diagram using Fourier transform, and extract characteristic parameters of the time domain waveform and spectrum diagram of each electrical quantity signal and non-electrical quantity signal;

[0041] Step 4: Input all the extracted characteristic parameters into the inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding;

[0042] Step 5: According to the identification result of the inter-turn discharge pattern recognition model, if inter-turn discharge exists, the early warning mechanism is triggered.

[0043] In a preferred implementation of the method for identifying the inter-turn discharge pattern of a power transformer winding, in step 2, wavelet transform is used to preprocess the electrical quantity signal and the non-electrical quantity signal, filter out the frequency band where the noise is located, retain the frequency band where the real discharge signal is located, and realize the separation of signal and noise.

[0044] In a preferred embodiment of the method for identifying inter-turn discharge patterns of power transformer windings, electrical quantity signals and non-electrical quantity signals include collecting high-voltage side voltage signals, low-voltage side voltage signals, high-voltage side current signals, low-voltage side current signals, ultrasonic signals, and ultra-high frequency signals of power transformer windings.

[0045] In a preferred implementation of the method for identifying the inter-turn discharge pattern of a power transformer winding, a voltage sensor is used to measure the high-voltage side voltage signal and the low-voltage side voltage signal; a current sensor is used to measure the high-voltage side current signal and the low-voltage side current signal; an ultrasonic sensor is used to measure the ultrasonic signal, and the ultrasonic sensor is equipped with an ultrasonic power amplifier; and a UHF sensor is used to measure the UHF signal.

[0046] In a preferred embodiment of the method for identifying the interturn discharge pattern of a power transformer winding, in step 3, Fourier transform is used to generate a spectrum diagram of the de-noised electrical quantity signal and the non-electrical quantity signal, and characteristic parameters of the time domain waveforms and spectrum diagrams of the electrical quantity signal and the non-electrical quantity signal are extracted.

[0047] For the high-voltage side voltage signal, low-voltage side voltage signal, high-voltage side current signal, low-voltage side current signal and ultra-high frequency signal, seven characteristic parameters including maximum discharge amplitude, average discharge amplitude, discharge amplitude entropy, discharge amplitude standard deviation, average pulse repetition rate, skewness and steepness are extracted respectively. For the ultrasonic signal, four characteristic parameters including maximum amplitude, average amplitude, standard deviation of amplitude and mean square amplitude are extracted.

[0048] In a preferred embodiment of the method for identifying the inter-turn discharge pattern of a power transformer winding, the inter-turn discharge pattern recognition model is trained in advance using sample signals of known inter-turn discharge patterns, the inter-turn discharge pattern recognition model uses a support vector machine algorithm as a pattern recognition mechanism, and the characteristic parameters are input into the inter-turn discharge pattern recognition model for pattern recognition, and the model output is a recognition result of whether there is inter-turn discharge in the winding of the power transformer.

[0049] A power transformer winding interturn discharge pattern recognition and monitoring system includes:

[0050] The discharge signal processing module is used to collect the electrical quantity signals and non-electrical quantity signals of the power transformer winding during discharge in real time, and use wavelet transform to perform signal preprocessing to eliminate the noise and electromagnetic interference mixed in the signal.

[0051] The discharge pattern recognition module is used to generate a signal spectrum through Fourier transform, extract the relevant characteristic parameters of each signal time domain waveform and spectrum, and use the trained inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding.

[0052] The equipment status warning module is used to display the recognition results and trigger the alarm. If there is inter-turn discharge, the alarm mechanism is triggered.

[0053] In a preferred embodiment of the system, the discharge pattern recognition module includes a processor.

[0054] A computer storage medium includes computer instructions, which, when executed on a computer, cause the computer to execute the method described.

[0055] An electronic device, comprising:

[0056] A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0057] When the processor executes the program, the method described is implemented.

[0058] In one embodiment, a method for identifying an inter-turn discharge pattern of a power transformer winding specifically includes:

[0059] Step 1: Collect electrical quantity signals and non-electrical quantity signals when the power transformer winding is discharged;

[0060] Step 2: Use wavelet transform to preprocess the signal to eliminate the noise and electromagnetic interference in the signal;

[0061] Step 3: Generate a signal spectrum using Fourier transform, and extract relevant characteristic parameters of each signal's time domain waveform and spectrum;

[0062] Step 4: Input all extracted characteristic parameters into the inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding;

[0063] Step 5: According to the model identification results, if there is inter-turn discharge, the early warning mechanism is triggered.

[0064] In a preferred embodiment of the method for identifying the inter-turn discharge pattern of a power transformer winding, the wavelet transform is used to transform the time domain signal The formula for decomposition is as follows:

[0065] , where is the wavelet function after scaling and translation, a is the scale parameter to control the scaling of the wavelet, b is the displacement parameter to control the translation of the wavelet, It represents the wavelet transform result under the scale parameter a and the displacement parameter b, and * represents the complex conjugate.

[0066] In a preferred implementation of the method for identifying the inter-turn discharge pattern of a power transformer winding, in step 3, a Fourier transform is used to generate a spectrum diagram of the denoised signal, and the signal time domain waveform and the spectrum diagram related characteristic parameters are extracted as the basis for pattern recognition. The maximum discharge amplitude is the maximum value of the discharge amplitude within a period of time, which can intuitively reflect the intensity of the discharge. The average discharge amplitude is the average value of the discharge amplitude within a period of time, reflecting the average level of the discharge amplitude in each period of time. The entropy value of the discharge amplitude reflects the degree of confusion of the discharge amplitude within a period of time, and its formula is as follows: , where is the probability distribution of the discharge amplitude, and n is the number of discharge intervals. The standard deviation of the discharge amplitude reflects the degree of dispersion of the discharge amplitude over a period of time. The average pulse repetition rate is the average number of discharges per unit time, reflecting the intensity of the discharge. The skewness characterizes the asymmetry of the data distribution, and its formula is as follows: , where n is the number of discharges in the statistical interval, is the amplitude of the ith discharge, is the average discharge amplitude in the interval, is the standard deviation of the discharge amplitude within the interval. The steepness characterizes the peak value of the data distribution curve at the mean value, reflecting the flatness of the data relative to the normal distribution. The formula is as follows: , where n is the number of discharges in the statistical interval, is the amplitude of the ith discharge, is the average discharge amplitude in the interval, is the standard deviation of the discharge amplitude within the interval.

[0067] In a preferred embodiment of the method for identifying the interturn discharge pattern of a power transformer winding, in step 4, the extracted signal characteristic parameters are used as inputs to the interturn discharge pattern recognition model, and the model's own algorithm is used to perform pattern recognition, and the model output is the recognition result, that is, whether there is interturn discharge in the power transformer winding. Preferably, the interturn discharge pattern recognition model is a model that has been trained in advance, which can ensure the accuracy and reliability of pattern recognition. Preferably, the interturn discharge pattern recognition model uses sample signals of known interturn discharge patterns to train the model in advance, and the trained model can directly perform discharge pattern recognition on the input characteristic parameters. Preferably, the interturn discharge pattern recognition model uses a support vector machine algorithm as a pattern recognition mechanism. Further, sample signals of known interturn discharge patterns are used as inputs of the support vector machine model, of which 80% are used as the training set of the model and 20% are used as the test set of the model. Sigmod is selected as the kernel function of the support vector machine, and the optimal search for the regularization parameter C is achieved through the Bayesian optimization and grid search methods. The model is trained multiple times using the training set and the classification accuracy is tested using the test set until the classification accuracy is greater than 90%. The feature parameters extracted in step 4 of the present invention are directly input into the trained turn-to-turn discharge pattern recognition model to achieve discharge recognition.

[0068] Figure 2 Shown is a schematic diagram of the support vector machine model, which divides the data set by finding the hyperplane that maximizes the geometric interval, thereby achieving classification and recognition effects.

[0069] Another embodiment of the present invention provides a power transformer winding inter-turn discharge pattern recognition and monitoring system, which includes a discharge signal processing module, a discharge pattern recognition module and an equipment status early warning module.

[0070] Specifically, the discharge signal processing module is used to collect electrical quantity signals and non-electrical quantity signals when the power transformer winding is discharged in real time, and use wavelet transform to perform signal preprocessing to eliminate noise and electromagnetic interference mixed in the signal. Specifically, the discharge mode recognition module is used to generate a signal spectrum through Fourier transform, extract relevant characteristic parameters of each signal time domain waveform and spectrum, and use the trained inter-turn discharge mode recognition model to determine whether the transformer winding has inter-turn discharge. Specifically, the equipment status warning module is used to display the recognition result and trigger the alarm. If there is inter-turn discharge, the alarm mechanism is immediately triggered to remind the operation and maintenance personnel to carry out equipment maintenance. The present invention can timely and accurately identify the inter-turn discharge of the power transformer winding by collecting multiple types of physical quantity signals during the discharge process and using the inter-turn discharge mode recognition model trained in advance. By discovering potential problems early, it provides maintenance strategy support for operation and maintenance personnel to avoid the development of discharge to a more serious stage, which is expected to be promoted in the field of inter-turn discharge mode recognition and online monitoring of power transformer windings.

[0071] Although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above specific embodiments and application fields, and the above specific embodiments are only illustrative and instructive, rather than restrictive. A person of ordinary skill in the art can also make many forms under the guidance of this specification and without departing from the scope of protection of the claims of the present invention, all of which belong to the protection of the present invention.

Claims

1. A method for identifying interturn discharge patterns of power transformer windings, characterized in that: The steps include: Step 1: Collect electrical quantity signals and non-electrical quantity signals when the power transformer winding is discharged; Step 2: Use wavelet transform to preprocess the signal to eliminate the noise and electromagnetic interference mixed in the electrical quantity signal and non-electrical quantity signal; Step 3: Generate a signal spectrum diagram using Fourier transform, and extract characteristic parameters of the time domain waveform and spectrum diagram of each electrical quantity signal and non-electrical quantity signal; Step 4: Input all the extracted characteristic parameters into the inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding; Step 5: According to the identification result of the inter-turn discharge pattern recognition model, if inter-turn discharge exists, the early warning mechanism is triggered.

2. A method for identifying interturn discharge patterns of power transformer windings according to claim 1, characterized in that: Preferably, in step 2, wavelet transform is used to pre-process the electrical quantity signal and the non-electrical quantity signal, the frequency band where the noise is located is filtered out, and the frequency band where the real discharge signal is located is retained, so as to achieve separation of signal and noise.

3. The method for identifying interturn discharge patterns of power transformer windings according to claim 1, characterized in that: The electrical quantity signals and non-electrical quantity signals include the collected power transformer winding high-voltage side voltage signal, low-voltage side voltage signal, high-voltage side current signal, low-voltage side current signal, ultrasonic signal, and ultra-high frequency signal.

4. A method for identifying interturn discharge patterns of power transformer windings according to claim 3, characterized in that: A voltage sensor is used to measure the high-voltage side voltage signal and the low-voltage side voltage signal; a current sensor is used to measure the high-voltage side current signal and the low-voltage side current signal; an ultrasonic sensor is used to measure the ultrasonic signal, and the ultrasonic sensor is equipped with an ultrasonic power amplifier; and a UHF sensor is used to measure the UHF signal.

5. The method for identifying interturn discharge patterns of power transformer windings according to claim 3, characterized in that: In step 3, Fourier transform is used to generate a spectrum of the denoised electrical quantity signal and the non-electrical quantity signal, and characteristic parameters of the time domain waveforms and spectrum of the electrical quantity signal and the non-electrical quantity signal are extracted. For the high-voltage side voltage signal, low-voltage side voltage signal, high-voltage side current signal, low-voltage side current signal and ultra-high frequency signal, seven characteristic parameters including maximum discharge amplitude, average discharge amplitude, discharge amplitude entropy, discharge amplitude standard deviation, average pulse repetition rate, skewness and steepness are extracted respectively. For the ultrasonic signal, four characteristic parameters including maximum amplitude, average amplitude, standard deviation of amplitude and mean square amplitude are extracted.

6. A power transformer winding interturn discharge pattern recognition and monitoring system, characterized in that: These include, The discharge signal processing module is used to collect the electrical quantity signals and non-electrical quantity signals of the power transformer winding during discharge in real time, and use wavelet transform to perform signal preprocessing to eliminate the noise and electromagnetic interference mixed in the signal. The discharge pattern recognition module is used to generate a signal spectrum through Fourier transform, extract the relevant characteristic parameters of each signal time domain waveform and spectrum, and use the trained inter-turn discharge pattern recognition model to determine whether inter-turn discharge occurs in the transformer winding. The equipment status warning module is used to display the recognition results and trigger the alarm. If there is inter-turn discharge, the alarm mechanism is triggered.

7. The system according to claim 6, characterized in that The discharge pattern recognition module includes a processor.

8. A computer storage medium, characterized in that The storage medium includes computer instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 5.

9. An electronic device, characterized in that: The electronic device comprises: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

Images