A high-voltage circuit breaker vibration signal feature extraction method

Abstract

The application provides a high-voltage circuit breaker vibration signal feature extraction method, which comprises the following steps: obtaining a vibration signal when a high-voltage circuit breaker operates, and filtering the vibration signal; extracting a first operation time parameter from the filtered vibration signal; obtaining an electric parameter information when the high-voltage circuit breaker operates, and extracting a second operation time parameter from the electric parameter; correcting the first operation time parameter according to the second operation time parameter; dividing an operation cycle of the high-voltage circuit breaker into three time periods by using the corrected first operation time parameter, calculating a signal energy entropy corresponding to each time period, and combining the energy entropy of each signal to obtain a feature vector; and identifying a fault of the high-voltage circuit breaker by using a classification algorithm according to the obtained feature vector. The time parameter extracted from the electric parameter is used as a reference adjustment, the signal deviation of the vibration signal caused by the vibration noise of the circuit breaker is eliminated, and the precision of feature extraction is improved.

Description

Technical Field

[0001] This invention belongs to the field of high-voltage circuit breaker fault diagnosis technology, specifically relating to a method for extracting vibration signal features of high-voltage circuit breakers. Background Technology

[0002] As crucial high-voltage equipment in power systems, high-voltage circuit breakers play a vital role in control and protection, and their operational status directly impacts the safety and stability of the lines they operate on. When a short-circuit fault occurs, the high-voltage circuit breaker quickly interrupts the massive short-circuit current to protect the entire power system from damage. However, high-voltage circuit breakers are diverse in type, quantity, and structure, and are susceptible to failure due to factors such as their own quality and external operating conditions, leading to a decline in the reliability of the entire power system.

[0003] Currently, most fault diagnosis of high-voltage circuit breakers is based on electrical parameters. However, mechanical faults of high-voltage circuit breakers cannot be directly diagnosed through electrical parameters. It is necessary to train and fit the corresponding relationship through a large amount of sample data. Therefore, it is necessary to diagnose mechanical faults of high-voltage circuit breakers through vibration signals.

[0004] However, since the high-voltage circuit breaker is located in the high-altitude environment of the transmission line, in addition to the vibration generated by its own operation, the vibration sources in the external environment will also cause a lot of noise in the vibration signal. Therefore, it is necessary to design a method for noise reduction of vibration signal to make feature extraction more accurate. Summary of the Invention

[0005] In view of this, the present invention aims to provide a method for extracting vibration signal features of high-voltage circuit breakers to solve the problems existing in the prior art.

[0006] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0007] A method for extracting vibration signal features from a high-voltage circuit breaker includes the following steps:

[0008] Step S1: Obtain the vibration signal when the high-voltage circuit breaker operates, and filter the vibration signal;

[0009] Step S2: Extract the first action time parameter from the filtered vibration signal. The first action time parameter includes the first start time and the first end time.

[0010] Step S3: Obtain electrical parameter information when the high-voltage circuit breaker operates, and extract the second operating time parameter from the electrical parameters. The second operating time parameter includes the second start time and the second end time.

[0011] Step S4: Correct the first action time parameter in step S2 according to the second action time parameter in step S3;

[0012] Step S5: Divide the operating cycle of the high-voltage circuit breaker into three time periods using the corrected first operating time, calculate the signal energy entropy corresponding to each time period, and combine the energy entropy of each signal as a feature vector.

[0013] Step S6: Based on the feature vector obtained in step S5, use a classification algorithm to identify faults in the high-voltage circuit breaker.

[0014] Furthermore, in step S1, the filtering method is to detect the vibration signal in the external environment of the high-voltage circuit breaker and use a subtractor to remove external vibration noise.

[0015] Furthermore, in step S2, the method for extracting the first action time parameter includes the following steps:

[0016] Step S201: Set the window function to frame the vibration signal. Signal framing is used to decompose the vibration signal into multiple overlapping frame signals.

[0017] Step S202: Calculate the Teager energy and quadratic energy of each frame of signal;

[0018] Step S203: Set the motion parameters and motion threshold values. The times corresponding to the waveform intersections of the motion parameters and motion threshold values ​​are the first motion time and the second motion time, respectively, in sequence.

[0019] Furthermore, in step S201, the framing expression of the vibration signal is:

[0020] yi(n)=w(n)*x((i-1)*inc+n)

[0021] Where w(n) is the window function, yi(n) is the i-th frame signal obtained by framing, n = 1, 2, ..., L, i = 1, 2, ..., fn, inc is the sliding distance of the window function each time, and L is the length of each frame signal, that is, the length of the window function.

[0022] Furthermore, in step S202, the formula for calculating the Teager energy is:

[0023]

[0024] Furthermore, in step S203, the formula for calculating the motion parameters is:

[0025]

[0026] In the formula, STTEOi is the short-time Teager energy of the i-th frame signal, STSEOi is the short-time quadratic energy of the i-th frame signal, and a is the correction parameter;

[0027] Furthermore, in step S203, the formula for calculating the action threshold is:

[0028] T = b × mean(IP)

[0029] In the formula, b is the threshold coefficient.

[0030] Furthermore, in step S3, the electrical parameters include one or more of the following: coil current, contact current, and coil magnetic field.

[0031] Furthermore, in step S4, the correction is implemented using the KNN algorithm, specifically including:

[0032] Compare the Euclidean distance between the first action time parameter and the second action time parameter. If the Euclidean distance is less than or equal to a distance threshold, the average of the first action time parameter and the second action time parameter is selected as the new first action time parameter. If the Euclidean distance is greater than the threshold, feature vectors are extracted according to the first action time parameter and the second action time parameter respectively. The angle difference and length difference of the corresponding feature vectors are compared. If they are not less than the corresponding threshold, the feature vector extracted by the first action time parameter is used. Otherwise, the average of the first action time parameter and the second action time parameter is used as the new first action time parameter.

[0033] In summary, this invention provides a method for extracting vibration signal features from high-voltage circuit breakers. The method involves acquiring the vibration signal of the high-voltage circuit breaker during operation and filtering the signal; extracting a first action time parameter from the filtered vibration signal; acquiring the electrical parameter information of the high-voltage circuit breaker during operation and extracting a second action time parameter from the electrical parameters; correcting the first action time parameter based on the second action time parameter; dividing the operation cycle of the high-voltage circuit breaker into three time periods using the corrected first action time; calculating the signal energy entropy corresponding to each time period; combining the energy entropies of each signal period as a feature vector; and using a classification algorithm to identify faults in the high-voltage circuit breaker based on the obtained feature vector. This invention eliminates signal deviations caused by the vibration noise of the circuit breaker itself by using the time parameter extracted from the electrical parameters as a reference adjustment, thus improving the accuracy of feature extraction. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1This is a flowchart illustrating a method for extracting vibration signal features from a high-voltage circuit breaker, as provided in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0037] As crucial high-voltage equipment in power systems, high-voltage circuit breakers play a vital role in control and protection, and their operational status directly impacts the safety and stability of the lines they operate on. When a short-circuit fault occurs, the high-voltage circuit breaker quickly interrupts the massive short-circuit current to protect the entire power system from damage. However, high-voltage circuit breakers are diverse in type, quantity, and structure, and are susceptible to failure due to factors such as their own quality and external operating conditions, leading to a decline in the reliability of the entire power system.

[0038] Currently, most fault diagnosis of high-voltage circuit breakers is based on electrical parameters. However, mechanical faults of high-voltage circuit breakers cannot be directly diagnosed through electrical parameters. It is necessary to train and fit the corresponding relationship through a large amount of sample data. Therefore, it is necessary to diagnose mechanical faults of high-voltage circuit breakers through vibration signals.

[0039] However, since the high-voltage circuit breaker is located in the high-altitude environment of the transmission line, in addition to the vibration generated by its own operation, the vibration sources in the external environment will also cause a lot of noise in the vibration signal. Therefore, it is necessary to design a method for noise reduction of vibration signal to make feature extraction more accurate.

[0040] Based on this, the present invention provides a method for extracting vibration signal features of high-voltage circuit breakers.

[0041] The following is a detailed description of an embodiment of the vibration signal feature extraction method for high-voltage circuit breakers according to the present invention.

[0042] Please see Figure 1 This embodiment provides a method for extracting vibration signal features from a high-voltage circuit breaker, including the following steps:

[0043] Step S1: Obtain the vibration signal when the high-voltage circuit breaker operates, and filter the vibration signal;

[0044] Step S2: Extract the first action time parameter from the filtered vibration signal. The first action time parameter includes the first start time and the first end time.

[0045] Step S3: Obtain electrical parameter information when the high-voltage circuit breaker operates, and extract the second operating time parameter from the electrical parameters. The second operating time parameter includes the second start time and the second end time.

[0046] Step S4: Correct the first action time parameter in step S2 according to the second action time parameter in step S3;

[0047] Step S5: Divide the operating cycle of the high-voltage circuit breaker into three time periods using the corrected first operating time, calculate the signal energy entropy corresponding to each time period, and combine the energy entropy of each signal as a feature vector.

[0048] Step S6: Based on the feature vector obtained in step S5, use a classification algorithm to identify faults in the high-voltage circuit breaker.

[0049] This embodiment provides a method for extracting vibration signal features from a high-voltage circuit breaker. The method involves acquiring the vibration signal of the high-voltage circuit breaker during operation and filtering the signal; extracting a first action time parameter from the filtered vibration signal; acquiring the electrical parameter information of the high-voltage circuit breaker during operation and extracting a second action time parameter from the electrical parameters; correcting the first action time parameter based on the second action time parameter; dividing the operation cycle of the high-voltage circuit breaker into three time periods using the corrected first action time; calculating the signal energy entropy corresponding to each time period; combining the energy entropies of each signal period as a feature vector; and using a classification algorithm to identify faults in the high-voltage circuit breaker based on the obtained feature vector. This invention eliminates signal deviations caused by the vibration noise of the circuit breaker itself by using the time parameter extracted from the electrical parameters as a reference adjustment, thus improving the accuracy of feature extraction.

[0050] In an optional embodiment, in step S1, the filtering method can detect vibration signals in the external environment of the high-voltage circuit breaker and use a subtractor to remove external vibration noise.

[0051] In an optional embodiment, step S2, the method for extracting the first action time parameter includes the following steps:

[0052] Step S201: Set the window function to frame the vibration signal. Signal framing is used to decompose the vibration signal into multiple overlapping frame signals.

[0053] Step S202: Calculate the Teager energy and quadratic energy of each frame of signal;

[0054] Step S203: Set the motion parameters and motion threshold values. The times corresponding to the waveform intersections of the motion parameters and motion threshold values ​​are the first motion time and the second motion time, respectively, in sequence.

[0055] In an optional embodiment, in step S201, the framing expression of the vibration signal is:

[0056] yi(n)=w(n)*x((i-1)*inc+n)

[0057] Where w(n) is the window function, yi(n) is the i-th frame signal obtained by framing, n = 1, 2, ..., L, i = 1, 2, ..., fn, inc is the sliding distance of the window function each time, and L is the length of each frame signal, that is, the length of the window function.

[0058] In an optional embodiment, in step S202, the formula for calculating the Teager energy is:

[0059]

[0060] In an optional embodiment, in step S203, the formula for calculating the action threshold is:

[0061] T = b × mean(IP)

[0062] In the formula, b is the threshold coefficient.

[0063] In an optional embodiment, in step S3, the electrical parameters include one or more of the coil current, contact current, and coil magnetic field.

[0064] In an optional embodiment, in step S4, the correction is implemented using the KNN algorithm, specifically including:

[0065] Compare the Euclidean distance between the first action time parameter and the second action time parameter. If the Euclidean distance is less than or equal to a distance threshold, the average of the first action time parameter and the second action time parameter is selected as the new first action time parameter. If the Euclidean distance is greater than the threshold, feature vectors are extracted according to the first action time parameter and the second action time parameter respectively. The angle difference and length difference of the corresponding feature vectors are compared. If they are not less than the corresponding threshold, the feature vector extracted by the first action time parameter is used. Otherwise, the average of the first action time parameter and the second action time parameter is used as the new first action time parameter.

[0066] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting vibration signal features from a high-voltage circuit breaker, characterized in that, Includes the following steps: Step S1: Obtain the vibration signal when the high-voltage circuit breaker operates, and filter the vibration signal; Step S2: Extract the first action time parameter from the filtered vibration signal. The first action time parameter includes the first start time and the first end time. Step S3: Obtain electrical parameter information when the high-voltage circuit breaker operates, and extract the second operating time parameter from the electrical parameters. The second operating time parameter includes the second start time and the second end time. Step S4: Correct the first action time parameter in step S2 according to the second action time parameter in step S3; Step S5: Divide the operating cycle of the high-voltage circuit breaker into three time periods using the corrected first operating time, calculate the signal energy entropy corresponding to each time period, and combine the energy entropy of each signal as a feature vector. Step S6: Based on the feature vector obtained in step S5, use a classification algorithm to identify faults in the high-voltage circuit breaker. In step S4, the correction method is implemented using the KNN algorithm, specifically including: Compare the Euclidean distance between the first action time parameter and the second action time parameter. If the Euclidean distance is less than or equal to a distance threshold, the average of the first action time parameter and the second action time parameter is selected as the new first action time parameter. If the Euclidean distance is greater than the threshold, feature vectors are extracted according to the first action time parameter and the second action time parameter respectively. The angle difference and length difference of the corresponding feature vectors are compared. If they are not less than the corresponding threshold, the feature vector extracted by the first action time parameter is used. Otherwise, the average of the first action time parameter and the second action time parameter is used as the new first action time parameter.

2. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 1, characterized in that: In step S1, the filtering method is to detect the vibration signal in the external environment of the high-voltage circuit breaker and use a subtractor to remove external vibration noise.

3. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 1, characterized in that: In step S2, the method for extracting the first action time parameter includes the following steps: Step S201: Set the window function to frame the vibration signal. Signal framing is used to decompose the vibration signal into multiple overlapping frame signals. Step S202: Calculate the Teager energy and quadratic energy of each frame of signal; Step S203: Set action parameters and action threshold values. The time corresponding to the waveform intersection of the action parameters and action threshold values ​​are, in order, the first action time and the second action time.

4. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 3, characterized in that: In step S201, the framing expression of the vibration signal is: ； Where w(n) is the window function, yi(n) is the i-th frame signal obtained by framing, n=1,2,...,L, i=1,2,...,fn, inc is the sliding distance of the window function each time, and L is the length of each frame signal, that is, the length of the window function.

5. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 3, characterized in that: In step S202, the formula for calculating the Teager energy is: 。 6. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 3, characterized in that: In step S203, the formula for calculating the action parameters is: ； In the formula, Let be the short-time Teager energy of the i-th frame signal. Let be the short-time quadratic energy of the i-th frame signal, and 'a' be the correction parameter.

7. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 6, characterized in that: In step S203, the formula for calculating the action threshold is: ； In the formula, b is the threshold coefficient.

8. The method for extracting vibration signal features of a high-voltage circuit breaker according to claim 1, characterized in that: In step S3, the electrical parameters include one or more of the following: coil current, contact current, and coil magnetic field.

Images