Circuit breaker vibration signal processing method and device, equipment and storage medium

By correcting Laplace Gaussian filter and information entropy processing, the signal characteristics of the circuit breaker vibration signal are extracted, and the problems of nonlinearity and noise influence of the circuit breaker vibration signal are solved, and the abnormal state of the circuit breaker is accurately identified.

CN119066581APending Publication Date: 2024-12-03GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411156954.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The nonlinearity and transient nature of the circuit breaker vibration signal lead to poor accuracy of data feature extraction, and environmental noise and signal irregularities affect the effective identification of fault patterns.

Method used

The modified Laplace Gaussian filter is used to filter the vibration data, and the LoG filter is generated through the first and second order derivatives, and normalized to make the taps sums of them to zero, enhancing the clarity of signal characteristic transitions, combined with Information entropy determines the dimension and performs square processing to extract signal characteristics.

Benefits of technology

Effectively distinguishing background noise and signal characteristics, improve the accuracy of identification of circuit breaker abnormal state and fault mode, and reduce the impact of environmental noise and signal irregularity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066581A_ABST
    Figure CN119066581A_ABST
Patent Text Reader

Abstract

The invention discloses a circuit breaker vibration signal processing method, device and equipment and a storage medium, and the method comprises the steps: inputting the vibration data of a circuit breaker into a corrected Laplace Gaussian filter, reinforcing the transition between background noise and signal characteristics in the vibration data, and outputting the filtered vibration data; performing square processing on the filtered vibration data, extracting signal features corresponding to the vibration data, and then identifying the abnormal state of the circuit breaker according to the extracted signal features; wherein the generation of the modified Laplacian Gaussian filter comprises the following steps: respectively carrying out first-order derivation and second-order derivation on a Gaussian filter to obtain a corresponding LoG filter; and carrying out normalization processing on the LoG filter, and enabling the sum of taps of the LoG filter to be zero to obtain a corrected Laplacian Gaussian filter. According to the invention, filtering processing of environment noise of vibration data and effective distinguishing of signal features can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electrical equipment fault diagnosis, and in particular to a method, device, equipment and storage medium for processing a circuit breaker vibration signal. Background Art

[0002] In order to ensure the normal operation of various types of power equipment and meet the safety and stability of power transmission, it is necessary to deeply process and analyze the vibration signals of mechanical equipment or structures such as circuit breakers. However, at this stage, how to extract key characteristic parameters that can reflect the state or performance of mechanical equipment from the collected circuit breaker vibration signals is a major difficulty in the field of fault diagnosis. Because the circuit breaker vibration signal has strong nonlinearity and transient properties, the accuracy of the mechanism action parameter extraction is affected by the sensor installation position and some key parameters in the algorithm, resulting in poor stability of the data feature extraction results, and environmental noise, signal irregularity or randomness seriously affect the effective identification of abnormal states or fault modes of circuit breakers. Summary of the invention

[0003] The present invention provides a method, device, equipment and storage medium for processing vibration signals of a circuit breaker to solve the technical problem that environmental noise, irregularity or randomness of signals seriously affect the effective identification of abnormal states or fault modes of circuit breaker.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for processing a vibration signal of a circuit breaker, comprising:

[0005] Obtain vibration data of circuit breakers;

[0006] Inputting the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter strengthens the transition between background noise and signal features in the vibration data, and outputs the filtered vibration data;

[0007] Square the filtered vibration data, extract signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features;

[0008] The generation of the modified Laplace Gaussian filter includes:

[0009] Taking a first-order derivative of a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter;

[0010] Performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as a corresponding LoG filter;

[0011] The LoG filter is normalized and the sum of the taps of the LoG filter is made zero to obtain the modified Laplace Gaussian filter.

[0012] As a preferred solution, before the extracted vibration data is input into a preset modified Laplace Gaussian filter, the method further includes:

[0013] extracting information entropy of the vibration data;

[0014] According to the extracted information entropy, determining whether the dimension of the vibration data is greater than a preset threshold;

[0015] When the dimension of the vibration data is greater than the preset threshold, the vibration data is input into the modified Laplace Gaussian filter, and when the dimension of the vibration data is not greater than the preset threshold, the corresponding signal features of the vibration data are directly extracted.

[0016] As a preferred solution, before extracting the information entropy of the vibration data, the method further includes:

[0017] The vibration data is preprocessed; wherein the preprocessing includes: data filtering, data noise reduction and data cleaning.

[0018] As a preferred solution, the information entropy of the vibration data is extracted by the following formula:

[0019]

[0020] Wherein, H(x) is the information entropy of the vibration data, i=1,2,3,…n; p(x i ) is the probability of occurrence of each discrete point in the vibration data, x is the vibration random variable, is the energy sum of the frequency band signal, χ i is the amplitude corresponding to the discrete points of the frequency band signal.

[0021] As a preferred solution, the modified Laplace Gaussian filter is:

[0022]

[0023] Wherein, G(n) is the 2-Gaussian filter, G′(n) is the first-order derivative of the Gaussian filter, G″(n) is the LoG filter, LoG ~ is the normalized LoG filter, MLoG is the modified Laplace Gaussian filter, σ is the standard deviation of the Gaussian filter, n is the Gaussian index, and C is the number of taps of the modified Laplace Gaussian filter.

[0024] As a preferred solution, the vibration data after square processing is:

[0025]

[0026] Among them, X n (i) is the length set of vibration data, W(i) is the vibration data of length w in X n (i) The average value taken over the set, X 2 (i) is the square signal after filtering using the modified Laplace Gaussian filter, and w is the length of the vibration data.

[0027] On the basis of the above-mentioned embodiment, another embodiment of the present invention provides a circuit breaker vibration signal processing device, comprising: a vibration data acquisition module, a Gaussian filter module and a signal feature extraction module;

[0028] The vibration data acquisition module is used to acquire vibration data of the circuit breaker;

[0029] The Gaussian filter module is used to input the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter can strengthen the transition between the background noise and the signal characteristics in the vibration data, and output the filtered vibration data; wherein the generation of the modified Laplace Gaussian filter includes: performing a first-order derivative on a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter; performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as the corresponding LoG filter; normalizing the LoG filter, and making the sum of the taps of the LoG filter zero, to obtain the modified Laplace Gaussian filter;

[0030] The signal feature extraction module is used to perform square processing on the filtered vibration data, extract the signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features.

[0031] As a preferred solution, the circuit breaker vibration signal processing device further includes: an information entropy extraction module;

[0032] The information entropy extraction module is used to extract the information entropy of the vibration data; based on the extracted information entropy, determine whether the dimension of the vibration data is greater than a preset threshold; when the dimension of the vibration data is greater than the preset threshold, input the vibration data into the modified Laplace Gaussian filter, and when the dimension of the vibration data is not greater than the preset threshold, directly extract the corresponding signal features of the vibration data.

[0033] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the method for processing the circuit breaker vibration signal described in the above invention embodiment is implemented.

[0034] Based on the above embodiment, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the circuit breaker vibration signal processing method described in the above invention embodiment.

[0035] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0036] The present invention provides a method for processing vibration signals of a circuit breaker, wherein vibration data of the circuit breaker is input into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter strengthens the transition between background noise and signal features in the vibration data, and outputs filtered vibration data; then the filtered vibration data is squared, and signal features corresponding to the vibration data are extracted from the squared vibration data, and then the abnormal state of the circuit breaker is identified according to the extracted signal features;

[0037] The modified Laplace Gaussian filter is obtained by taking the first-order derivative and the second-order derivative of a preset Gaussian filter, respectively, to obtain the corresponding LoG filter, and then normalizing the LoG filter, and making the sum of the taps of the LoG filter zero. Using the modified Laplace Gaussian filter of the present invention to filter the vibration data of the circuit breaker can make the transition between the background noise and the signal of the vibration data clearer and sharper, and further realize the filtering of the environmental noise of the vibration data and the effective distinction of the signal characteristics. Then, the abnormal state of the circuit breaker is identified according to the extracted signal characteristics, and the abnormal state or fault mode of the circuit breaker can be effectively identified under the influence of environmental noise, irregularity or randomness of the signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of a method for processing a circuit breaker vibration signal provided by an embodiment of the present invention;

[0039] Figure 2 It is the overall flow chart of vibration data processing;

[0040] Figure 3 It is a schematic diagram of sensor placement and data sampling;

[0041] Figure 4 It is a comparison chart of information entropy extraction at different sensor locations;

[0042] Figure 5 This is a comparison chart of information entropy extraction under different working conditions;

[0043] Figure 6 It is a structural schematic diagram of a circuit breaker vibration signal processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0046] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0047] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0049] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0050] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0051] Embodiment 1

[0052] Please refer to Figure 1 , is a flow chart of a method for processing a circuit breaker vibration signal provided by an embodiment of the present invention, comprising the following specific steps:

[0053] S1. Obtain vibration data of the circuit breaker;

[0054] Preferably, before extracting the information entropy of the vibration data, the method further includes: preprocessing the vibration data; wherein the preprocessing includes: data filtering, data noise reduction and data cleaning.

[0055] For details, please refer to Figure 2 , is the overall flow chart of vibration data processing. First, vibration sensors are placed at different positions of the circuit breaker to be tested, and then the sensor vibration data is extracted using the acquisition system. The data of the opening or closing conditions, the opening and closing data of normal conditions and abnormal conditions can be collected. The sensor sensitivity is controlled at 0.5mV / m·s -2 , range is 10000m·s -2 , the sampling frequency is controlled to 15000Hz or above, and the voltage range of the acquisition equipment is 10V.

[0056] Furthermore, the collected vibration data is filtered, denoised, and cleaned. The specific method can select appropriate digital filtering, wavelet transform, adaptive filtering, and other methods according to the characteristics of the signal and processing requirements.

[0057] S2, inputting the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter strengthens the transition between the background noise and the signal characteristics in the vibration data, and outputs the filtered vibration data;

[0058] The generation of the modified Laplace Gaussian filter includes:

[0059] Taking a first-order derivative of a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter;

[0060] Performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as a corresponding LoG filter;

[0061] Normalizing the LoG filter and making the sum of the taps of the LoG filter zero, thereby obtaining the modified Laplace Gaussian filter;

[0062] Preferably, before the extracted vibration data is input into a preset modified Laplace Gaussian filter, it also includes: extracting the information entropy of the vibration data; judging whether the dimension of the vibration data is greater than a preset threshold value based on the extracted information entropy; when the dimension of the vibration data is greater than the preset threshold value, inputting the vibration data into the modified Laplace Gaussian filter, and when the dimension of the vibration data is not greater than the preset threshold value, directly extracting the corresponding signal features of the vibration data.

[0063] Preferably, the information entropy of the vibration data is extracted by the following formula:

[0064]

[0065] Wherein, H(x) is the information entropy of the vibration data, i=1,2,3,…n; p(x i ) is the probability of occurrence of each discrete point in the vibration data, x is the vibration random variable, is the energy sum of the frequency band signal, χ i is the amplitude corresponding to the discrete points of the frequency band signal.

[0066] Preferably, the modified Laplace-Gaussian filter is:

[0067]

[0068] Wherein, G(n) is the Gaussian filter, G′(n) is the first-order derivative of the Gaussian filter, G″(n) is the LoG filter, LoG ~ is the normalized LoG filter, MLoG is the modified Laplace Gaussian filter, σ is the standard deviation of the Gaussian filter, n is the Gaussian index, and C is the number of taps of the modified Laplace Gaussian filter.

[0069] Furthermore, the corresponding information entropy is calculated and extracted based on the preprocessed vibration data. Extracting information entropy is the first step before fault mode identification. When the equipment fails, its operating state will become complex and disordered, resulting in an increase in information entropy. By monitoring the change in information entropy, the equipment failure can be discovered in time. If the information entropy is not extracted, too much vibration point data will make the algorithm too complex and difficult to process.

[0070] The information entropy is calculated using the Shannon information entropy extraction method, which can be calculated using the following formula (1):

[0071]

[0072] Where i = 1, 2, 3, ... n; p(x i ) represents the probability of each discrete point appearing, x represents the vibration random variable, H(x) represents the information entropy extracted from the group of vibration signals, p(x i ) is calculated as:

[0073]

[0074] In the formula, is the energy sum of the frequency band signal, χ i is the amplitude corresponding to the discrete points of the frequency band signal.

[0075] Furthermore, when the data dimension is low, the traditional feature extraction module may be efficient enough to process the data and extract key features. At this time, using more complex processing modules (such as MLoG filters) may introduce unnecessary computational complexity and time. Therefore, choosing the right processing module according to the data dimension can improve processing efficiency.

[0076] For high-dimensional data, traditional feature extraction methods are difficult to fully capture the complexity and internal structure of the data. At this time, using filters specially designed to process high-dimensional data is more helpful to extract representative and discriminative features, making these features more valuable in subsequent analysis or model training.

[0077] On the other hand, in high-dimensional space, the sparsity of data increases, which may lead to the so-called "curse of dimensionality". The distribution of data will become very complex, and traditional statistical methods and machine learning algorithms will find it difficult to work effectively. By using appropriate filters to reduce the dimension or transform the features of high-dimensional data, the impact of the curse of dimensionality can be mitigated and the performance of the algorithm can be improved. Therefore, based on the extracted information entropy, it is first determined whether the dimension of the vibration data is greater than a preset threshold. When the dimension of the vibration data is greater than the preset threshold, the vibration data is input into the modified Laplace Gaussian filter. When the dimension of the vibration data is not greater than the preset threshold, the vibration data is directly input into the modified Laplace Gaussian filter. Figure 2The feature comparison module in extracts the corresponding signal features of the vibration data.

[0078] Feature comparison: Find the difference or similarity between the current feature and the reference feature based on distance metrics (such as Euclidean distance, Manhattan distance, etc.), similarity metrics (such as cosine similarity, Pearson correlation coefficient, etc.), or other comparison methods.

[0079] Discrimination judgment: Evaluate whether the difference between the current feature and the reference feature is significant, that is, whether it reaches a certain preset threshold or standard. If the difference is significant, it is considered that the current data has sufficient uniqueness or novelty and needs further processing or attention; if the difference is not significant, enter the MLoG on the right to extract information.

[0080] Historical data coverage: For features that are judged to have sufficient discrimination, the module will check whether these features have been covered by historical data. The purpose of this step is to ensure that the system can continue to learn and update, and avoid repeated processing of known information. If the current feature is not covered by historical data, it will be added to the historical database for future comparison and reference; if it has been covered, the location of the possible fault or the next change of the equipment will be inferred based on the previous vibration historical data such as certain types of faults or defects.

[0081] Furthermore, the Laplace Gaussian (LoG) filter is used to detect edge features in the information entropy image. The edge feature can be defined as a sudden change in the vibration signal, that is, a mutation from the circuit breaker background noise to the action signal P-. Therefore, by smoothing the background noise to detect the mutation of the action signal, the arrival time of P- can be made clearer. The coefficients of the LoG filter can be obtained by determining the second-order derivative of the Gaussian filter. Equation (3) gives a one-dimensional Gaussian filter:

[0082]

[0083] In the formula, σ represents the standard deviation of the Gaussian filter, n represents the Gaussian index, and its first-order derivative is shown in formula (4):

[0084]

[0085] The LoG filter is the second-order derivative of the Gaussian filter. Therefore, the formula of the LoG filter obtained by deriving equation (4) is as shown in equation (5):

[0086]

[0087] The scaling factor before the exponent is mainly to ensure that the area under the Gaussian integral is 1. Therefore, the normalized LoG filter can be obtained by dividing equation (5) by the exponential sum shown in equation (6):

[0088]

[0089] When the coefficients of the filter tend to zero, this filter can be used as a high-pass FIR filter. One of the characteristics of a high-pass FIR filter is that it has no response at zero frequency. Therefore, the formula of the LoG filter is modified so that the sum of the taps is zero, as shown in equation (7). The final formula of the LoG filter is named the modified Laplace of Gaussian filter (MLoG), which makes the transition between the background noise and the signal clearer and sharper.

[0090]

[0091] In formula (7), C represents the number of taps of the MLoG filter (filter order). When processing vibration signals with little difference, the order of MLoG can be selected as 10 and the order of σ is 2.5.

[0092] S3. Square the filtered vibration data, extract signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features.

[0093] Preferably, the vibration data after square processing is:

[0094]

[0095] Among them, X n (i) is the length set of vibration data, W(i) is the vibration data of length w in X n (i) The average value taken over the set, X 2 (i) is the square signal after filtering using the modified Laplace Gaussian filter, and w is the length of the vibration data.

[0096] The MLoG filter is used to filter the vibration signal. Further, the filtered signal is squared to maximize the difference between the vibration signals. Assume that the length of the vibration data is X. n (i), different data can be represented as X1(i), X2(i)…X n (i) Calculate the average value of samples with a length of w on the set and perform smoothing, as shown in formula (8).

[0097]

[0098] In formula (8), X n (i) represents the square signal after filtering using the MLoG filter, and w represents the length of the vibration data. After analysis, it is found that the filtering effect is best when there are 8 samples in each set.

[0099] Then, the signal features corresponding to the vibration data can be extracted from the vibration data after the square processing, and the abnormal state of the circuit breaker can be identified according to the extracted signal features.

[0100] The effect of the above signal feature extraction is described below with a specific embodiment:

[0101] For the collection of vibration signals of horizontal circuit breakers, the selection of sensor placement is crucial. The structure of horizontal circuit breakers is relatively complex, and its vibration characteristics may vary from part to part. Therefore, when selecting the placement location, it should be ensured that the sensor can cover key parts that may produce significant vibration, such as the outer box on the contact side, the operating mechanism, etc.

[0102] Please refer to Figure 3 , is a schematic diagram of sensor layout and data sampling, as shown in Figure 3 The sensor positions are arranged as shown in (a) for signal collection. The data sampling waveform after the opening action is shown in (b). Since the sensors are densely distributed, it is difficult to distinguish the signal characteristics collected by each other. Therefore, the MLoG method is used for filtering processing to achieve effective distinction of signal characteristics.

[0103] like Figure 3 As shown, sensors 4, 5, and 6 are distributed on both sides of the horizontal circuit breaker, especially 5 and 6 are completely symmetrical, and the measured data are highly similar. Please refer to Figure 4 , which is a comparison chart of information entropy extraction at different sensor locations. After traditional filtering and information extraction, the effect is as follows Figure 4 (a) The results show that the traditional extraction method can effectively distinguish the difference between the data information measured by sensor 4 and sensors 5 and 6, but it is difficult to distinguish the difference between the information of sensors 5 and 6. Therefore, the MLoG method is used to improve the traditional method and obtain Figure 4 The information entropy extraction result shown in (b) can effectively distinguish the signal features measured by sensors 5 and 6.

[0104] This method is used to extract the vibration signal characteristics under different working conditions. The results are as follows: Figure 5 shown. Figure 5 In (a), only some data features are clearly distinguished. However, after MLoG extracts information entropy, the opening and closing information in the entire data chain shows multiple peak and trough features in different time sequences, which is more helpful for the deep learning algorithm to identify different working conditions.

[0105] The present invention aims to solve the problem that some data features are not obvious or difficult to distinguish when multiple sensors collect vibration signals. It combines the two technologies of traditional feature extraction method of sensor data and information entropy analysis to achieve filtering processing of environmental noise and effective distinction of signal features. At the same time, applying this method to analyze vibration signals can quantify the sparsity and uncertainty of vibration signals. When the pulse impact in the vibration signal is submerged by noise, the information entropy is larger, and vice versa. By comparing the current signal features with the characteristic patterns in normal state or known fault state, abnormal state or potential fault can be identified, and early warning or location can be given.

[0106] Embodiment 2

[0107] Please refer to Figure 6 , is a schematic diagram of the structure of a circuit breaker vibration signal processing device provided by an embodiment of the present invention, the device comprising: a vibration data acquisition module, a Gaussian filter module and a signal feature extraction module;

[0108] The vibration data acquisition module is used to acquire vibration data of the circuit breaker;

[0109] The Gaussian filter module is used to input the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter can strengthen the transition between the background noise and the signal characteristics in the vibration data, and output the filtered vibration data; wherein the generation of the modified Laplace Gaussian filter includes: performing a first-order derivative on a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter; performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as the corresponding LoG filter; normalizing the LoG filter, and making the sum of the taps of the LoG filter zero, to obtain the modified Laplace Gaussian filter;

[0110] The signal feature extraction module is used to perform square processing on the filtered vibration data, extract the signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features.

[0111] Preferably, the circuit breaker vibration signal processing device further includes: an information entropy extraction module;

[0112] The information entropy extraction module is used to extract the information entropy of the vibration data; based on the extracted information entropy, determine whether the dimension of the vibration data is greater than a preset threshold; when the dimension of the vibration data is greater than the preset threshold, input the vibration data into the modified Laplace Gaussian filter, and when the dimension of the vibration data is not greater than the preset threshold, directly extract the corresponding signal features of the vibration data.

[0113] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0114] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0115] Embodiment 3

[0116] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for processing a circuit breaker vibration signal as described in the above embodiment of the invention when executing the computer program.

[0117] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0118] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0119] Embodiment 4

[0120] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the circuit breaker vibration signal processing method described in the above-mentioned embodiment of the invention.

[0121] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0122] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0123] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for processing a circuit breaker vibration signal, characterized in that: include: Obtain vibration data of circuit breakers; Inputting the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter strengthens the transition between background noise and signal features in the vibration data, and outputs the filtered vibration data; Square the filtered vibration data, extract signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features; The generation of the modified Laplace Gaussian filter includes: Taking a first-order derivative of a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter; Performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as a corresponding LoG filter; The LoG filter is normalized and the sum of the taps of the LoG filter is made zero to obtain the modified Laplace Gaussian filter.

2. The method for processing a circuit breaker vibration signal according to claim 1, characterized in that: Before the extracted vibration data is input into a preset modified Laplace Gaussian filter, the method further includes: extracting information entropy of the vibration data; According to the extracted information entropy, determining whether the dimension of the vibration data is greater than a preset threshold; When the dimension of the vibration data is greater than the preset threshold, the vibration data is input into the modified Laplace Gaussian filter, and when the dimension of the vibration data is not greater than the preset threshold, the corresponding signal features of the vibration data are directly extracted.

3. The method for processing a circuit breaker vibration signal according to claim 2, characterized in that: Before extracting the information entropy of the vibration data, the method further includes: The vibration data is preprocessed; wherein the preprocessing includes: data filtering, data noise reduction and data cleaning.

4. The method for processing a circuit breaker vibration signal according to claim 3, characterized in that: The information entropy of the vibration data is extracted by the following formula: Wherein, H(x) is the information entropy of the vibration data, i=1,2,3,…n; p(x i ) is the probability of occurrence of each discrete point in the vibration data, x is the vibration random variable, is the energy sum of the frequency band signal, χ i is the amplitude corresponding to the discrete points of the frequency band signal.

5. The method for processing a circuit breaker vibration signal as claimed in claim 4, characterized in that: The modified Laplace Gaussian filter is: Wherein, G(n) is the Gaussian filter, G′(n) is the first-order derivative of the Gaussian filter, G″(n) is the LoG filter, LoG ~ is the normalized LoG filter, MLoG is the modified Laplace Gaussian filter, σ is the standard deviation of the Gaussian filter, n is the Gaussian index, and C is the number of taps of the modified Laplace Gaussian filter.

6. The method for processing a circuit breaker vibration signal according to claim 5, characterized in that: The vibration data after the square processing is: Among them, X n (i) is the length set of vibration data, W(i) is the vibration data of length w in X n (i) The average value taken over the set, X 2 (i) is the square signal after filtering using the modified Laplace Gaussian filter, and w is the length of the vibration data.

7. A circuit breaker vibration signal processing device, characterized in that: include: Vibration data acquisition module, Gaussian filtering module and signal feature extraction module; The vibration data acquisition module is used to acquire vibration data of the circuit breaker; The Gaussian filter module is used to input the extracted vibration data into a preset modified Laplace Gaussian filter, so that the modified Laplace Gaussian filter can strengthen the transition between the background noise and the signal characteristics in the vibration data, and output the filtered vibration data; wherein the generation of the modified Laplace Gaussian filter includes: performing a first-order derivative on a preset Gaussian filter to obtain a first-order derivative of the Gaussian filter; performing a second-order derivative on the first-order derivative to obtain a second-order derivative of the Gaussian filter, and using the second-order derivative as the corresponding LoG filter; normalizing the LoG filter, and making the sum of the taps of the LoG filter zero, to obtain the modified Laplace Gaussian filter; The signal feature extraction module is used to perform square processing on the filtered vibration data, extract signal features corresponding to the vibration data from the squared vibration data, and then identify the abnormal state of the circuit breaker according to the extracted signal features.

8. The circuit breaker vibration signal processing device according to claim 7, characterized in that: Also includes: Information entropy extraction module; The information entropy extraction module is used to extract the information entropy of the vibration data; According to the extracted information entropy, it is determined whether the dimension of the vibration data is greater than a preset threshold; when the dimension of the vibration data is greater than the preset threshold, the vibration data is input into the modified Laplace Gaussian filter; when the dimension of the vibration data is not greater than the preset threshold, the corresponding signal features of the vibration data are directly extracted.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for processing a circuit breaker vibration signal according to any one of claims 1 to 6 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the method for processing a circuit breaker vibration signal according to any one of claims 1 to 6.

Citation Information

Cited By

  • Method and apparatus for processing vibration signals of circuit breaker, device, and storage medium

    WO2026040295A1