Gas insulation equipment acoustic signal feature extraction method

Abstract

The invention discloses a gas insulation equipment acoustic signal feature extraction method, which comprises the following steps: carrying out noise reduction processing on a collected sound signal, and carrying out normalization processing on a mean value and a variance of the signal; performing time-frequency decomposition on the preprocessed sound signal by adopting short-time Fourier transform STFT and wavelet transform WT; comprehensively extracting the features of the sound signals by integrating the MFCC, the AWPC adaptive wavelet packet coefficient and the instantaneous frequency feature IF; carrying out feature fusion on the extracted voiceprint features, splicing MFCC, AWPC and IF features to form a high-dimensional feature vector, and carrying out dimensionality reduction by using a principal component analysis (PCA); and performing standardization processing on the dimensionality-reduced features, and further screening the features by using a correlation analysis method. Effective voiceprint features can be extracted from the sound signals generated by the defects of the gas insulation equipment, and the influence of noise on detection is reduced, so that the detection accuracy is improved.

Description

Technical Field

[0001] The invention relates to the technical field of gas insulation defect acoustic signal feature extraction, and in particular to a gas insulation equipment acoustic signal feature extraction method. Background Art

[0002] In the field of gas insulation defect detection, accurate extraction of soundprint signal features generated by partial discharge and mechanical vibration plays an extremely important role in determining the defect type. Traditional feature extraction methods, such as Mel Frequency Cepstrum Coefficients (MFCC), although they capture the frequency domain information of sound signals to a certain extent, still have certain limitations in processing noise, changes in sound signals and detailed features. In order to improve recognition accuracy and robustness, the present invention proposes a feature extraction method that integrates time-frequency and frequency domain information. Time-frequency analysis methods such as short-time Fourier transform (STFT) and wavelet transform (WT) can provide signal information at different scales and time resolutions. However, these methods are still difficult to fully explore all the features in the sound signal when used alone. Therefore, the present invention proposes a time-frequency domain feature fusion (STFF) algorithm, which combines MFCC, AWPC (adaptive wavelet packet coefficients) and instantaneous frequency features (IF) to comprehensively capture the subtle features and dynamic changes of the soundprint, thereby improving the accuracy and robustness of the voiceprint recognition system in the extraction of acoustic signal features of gas insulation equipment. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] According to a first aspect of the present invention, a method for extracting acoustic signal features of gas-insulated equipment is provided, which can extract effective voiceprint features from sound signals generated by defects in gas-insulated equipment and reduce the impact of noise on detection, thereby improving detection accuracy.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution, a method for extracting acoustic signal features of gas-insulated equipment, comprising:

[0006] The collected sound signal is denoised, and the mean and variance of the signal are normalized; the short-time Fourier transform STFT and wavelet transform WT are used to perform time-frequency decomposition on the preprocessed sound signal; the features of the sound signal are comprehensively extracted by integrating MFCC, AWPC adaptive wavelet packet coefficients and instantaneous frequency features IF; the extracted voiceprint features are fused, and the MFCC, AWPC and IF features are concatenated to form a high-dimensional feature vector, which is then reduced in dimension using principal component analysis PCA; the features after dimensionality reduction are standardized to improve the stability of the algorithm, and the correlation analysis method is used to further screen the features.

[0007] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment described in the present invention, the noise reduction process includes using the Wiener filter method to perform noise reduction on the sound signal, assuming that the observed signal x(t) satisfies the following relationship:

[0008] x(t)=s(t)+n(t)

[0009] Where s(t) is the detection signal and n(t) is the noise;

[0010] The output of the Wiener filter Through convolution we get:

[0011]

[0012] The goal of the Wiener filter is to minimize the mean square error E:

[0013]

[0014] In the frequency domain, assume that the power spectral densities of the signal and noise are S sx (f) and S n (f), the frequency response H(f) of the filter is calculated by the following formula:

[0015]

[0016] In the formula, S sx (f) is the cross power spectral density of the signal and the observed signal; S x (f) = S sx (f)+S n (f is the power spectral density of the observed signal.

[0017] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment of the present invention, the noise reduction process includes, if the power spectrum density of the signal s(t) and the noise n(t) is known, performing an inverse Fourier transform into the time domain to obtain a time domain filter h(t);

[0018] The mean of the filtered signal is calculated, and the mean of each frame signal is subtracted to ensure that the mean of the signal in each frame is zero, eliminate the influence of the DC component on the characteristics, and adjust the standard deviation of each frame signal to unity to scale the amplitude range of the signal.

[0019] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment described in the present invention, the time-frequency decomposition includes performing time-frequency decomposition on the preprocessed sound signal using short-time Fourier transform STFT and wavelet transform WT;

[0020] Short-time Fourier transform (STFT) is a method for analyzing the time-frequency characteristics of a signal by applying a time window to the signal and calculating the Fourier transform. For the preprocessed sound signal x[n], STFT is expressed as:

[0021]

[0022] Among them, w[m] is a window function, and the Hamming window is selected;

[0023]

[0024] Among them, m represents the time offset, ω represents the frequency variable, and the STFT result X(m,ω) is a complex number, which represents the signal component at the frequency ω at the time m.

[0025] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment described in the present invention, wherein: the comprehensive extraction of the features of the sound signal includes using adaptive wavelet packet decomposition to capture the time-frequency features of the signal, performing multi-level wavelet packet decomposition on the signal, recursively decomposing the frequency band of the signal, and decomposing each frequency band of the signal into low-frequency and high-frequency sub-bands at each level of decomposition, selecting the decomposition path that best represents the signal features, extracting wavelet packet coefficients as features from the selected optimal decomposition tree, and distributing the signal in time and frequency.

[0026] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment according to the present invention, the comprehensive extraction of the features of the sound signal includes extracting the instantaneous frequency features of the sound signal, performing Hilbert transform on the preprocessed signal x(t) to obtain its analytical signal z(t):

[0027]

[0028] in is the Hilbert transform of x(t);

[0029] The instantaneous frequency f(t) is the time derivative of the phase of the analytical signal z(t):

[0030]

[0031] The rate of change of the instantaneous frequency can provide dynamic information about the local frequency changes of the signal.

[0032] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment described in the present invention, the feature fusion of the extracted voiceprint features includes obtaining a comprehensive feature description of the sound signal by combining MFCC, AWPC and IF:

[0033] MFCC provides the static spectrum characteristics of the signal on the Mel frequency scale, which is suitable for describing the harmonic structure of the sound signal; AWPC provides the multi-resolution time-frequency characteristics of the signal, capturing the energy distribution and changes of the signal in different frequency bands; IF provides the dynamic change information of the instantaneous frequency of the signal, which is used to analyze non-stationary signals, including modulation and jitter characteristics in the sound;

[0034] The feature vectors of MFCC, AWPC and IF are connected, and the principal component analysis method is used for dimension reduction. The fused feature vectors are used in the machine learning model for classification and recognition.

[0035] As a preferred solution of the method for extracting acoustic signal features of gas-insulated equipment described in the present invention, wherein: the standardization of the features after dimensionality reduction includes standardizing the features after dimensionality reduction. A zero-mean unit variance standardization Z-Score is adopted, by adjusting the mean of the feature to 0 and the standard deviation to 1, so that the standardized features obey a standard normal distribution with a mean of 0 and a standard deviation of 1;

[0036] Given a feature vector x = [x1, x2, x3…x n ], the mean μ and standard deviation σ are:

[0037]

[0038] The eigenvector z after Z-Score standardization is [z1,z2,z3…z n ] is calculated as follows:

[0039]

[0040] Map feature data to the same scale to eliminate dimensional differences between different features;

[0041] The correlation analysis method is used to evaluate the correlation between the standardized features and the target variable. The Pearson correlation coefficient is used, and the value range is [-1,1]. When the correlation coefficient is close to 1, it indicates that there is a strong positive correlation between the two variables; when the correlation coefficient is close to -1, it indicates that there is a strong negative correlation; when the correlation coefficient is close to 0, it indicates that there is no linear correlation.

[0042] Given two variables X and Y, the formula for calculating the Pearson correlation coefficient r is:

[0043]

[0044] in and are the means of X and Y respectively.

[0045] According to a second aspect of the present invention, there is provided a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of a method for extracting acoustic signal features of gas-insulated equipment when executing the computer program.

[0046] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a method for extracting acoustic signal features of gas-insulated equipment.

[0047] Beneficial effects of the invention: The method of the invention proposes a method for extracting acoustic signal features of gas-insulated equipment based on time-frequency domain feature fusion (STFF). The method can extract effective voiceprint features from the sound signals generated by defects in gas-insulated equipment and reduce the impact of noise on detection, thereby improving the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 A schematic flow chart of a method for extracting acoustic signal features of gas-insulated equipment provided by an embodiment of the present invention.

[0050] Figure 2 A flowchart of MFCC feature parameter extraction of a method for extracting acoustic signal features of gas-insulated equipment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for extracting acoustic signal features of a gas-insulated device, comprising:

[0058] S1: Perform noise reduction processing on the collected sound signal and normalize the mean and variance of the signal.

[0059] S2: Short-time Fourier transform (STFT) and wavelet transform (WT) are used to perform time-frequency decomposition on the preprocessed sound signal.

[0060] S3: Comprehensively extract the characteristics of the sound signal by integrating MFCC, AWPC (adaptive wavelet packet coefficient) and instantaneous frequency characteristics (IF). Figure 2 .

[0061] S4: The extracted voiceprint features are fused, and the MFCC, AWPC and IF features are concatenated to form a high-dimensional feature vector. The principal component analysis (PCA) method is then used for dimensionality reduction to reduce the feature dimension and retain the most important information.

[0062] S5: Standardize the features after dimensionality reduction to improve the stability of the algorithm, and use correlation analysis to further screen the most recognizable features.

[0063] The specific method of step S1: is:

[0064] The Wiener filter method is used to reduce the noise of the sound signal. Assume that the observed signal x(t) satisfies the following relationship:

[0065] x(t)=s(t)+n(t) (1)

[0066] Where s(t) is the detection signal and n(t) is the noise.

[0067] The output of the Wiener filter Through convolution we get:

[0068]

[0069] The goal of the Wiener filter is to minimize the mean square error E:

[0070]

[0071] In the frequency domain, assume that the power spectral densities of the signal and noise are S sx (f) and S n (f), the frequency response H(f) of the filter can be calculated by the following formula:

[0072]

[0073] Where S sx (f) is the cross power spectral density of the signal and the observed signal; S x (f) = S sx (f)+S n (f) is the power spectral density of the observed signal.

[0074] If the power spectral density of the signal s(t) and the noise n(t) is known, the frequency domain response of the Wiener filter is equation (4). By inverse Fourier transforming it to the time domain, the time domain filter h(t) can be obtained.

[0075] Calculate the mean of the filtered signal and subtract the mean of each frame to ensure that the mean of the signal in each frame is zero. This can eliminate the influence of the DC component on the characteristics. Then adjust the standard deviation of each frame signal to unity to scale the amplitude range of the signal. This is to avoid instability of signal characteristics caused by changes in signal strength.

[0076] The specific method of step S2 is:

[0077] Short-time Fourier transform (STFT) and wavelet transform (WT) are used to perform time-frequency decomposition on the preprocessed sound signal.

[0078] Short-time Fourier transform (STFT) is a method to analyze the time-frequency characteristics of a signal by applying a time window to the signal and calculating the Fourier transform. For the preprocessed sound signal x[n], STFT can be expressed as:

[0079]

[0080] Among them, w[m] is a window function, and the Hamming window is selected.

[0081]

[0082] m represents the time offset, ω represents the frequency variable. The result of STFT X(m,ω) is a complex number, which represents the signal component at the frequency ω at the time m.

[0083] By choosing the right window length and overlap rate, STFT can achieve a good balance of resolution in time and frequency. The choice of window function and the setting of window length have a direct impact on frequency resolution and time resolution. Short windows provide better time resolution but poorer frequency resolution; long windows provide the opposite. Different window settings can be selected for different defect types to achieve the best extraction accuracy.

[0084] In order to further analyze the non-stationary characteristics of the sound signal, the present invention also uses wavelet transform (WT) to process and analyze the sound signal. Wavelet transform uses scaling and translation of wavelet basis functions to perform multi-resolution analysis on the signal, and can simultaneously provide detailed information of the signal at different time and frequency scales.

[0085] The specific method of step S3 is:

[0086] The three methods of MFCC, AWPC and IF are combined to comprehensively extract the features of the sound signal.

[0087] First, the features of the sound signal are extracted through MFCC. The steps of MFCC extraction are as follows: Figure 1 shown.

[0088] Secondly, adaptive wavelet packet decomposition is used to capture the time-frequency characteristics of the signal. Wavelet packet decomposition is an extended wavelet decomposition that can refine the frequency bands of the signal to a higher resolution. The signal is subjected to multi-level wavelet packet decomposition to recursively decompose the frequency bands of the signal. Each level of decomposition decomposes each frequency band of the signal into low-frequency and high-frequency sub-bands again. Wavelet packet decomposition is more flexible than traditional wavelet decomposition because it allows the decomposition of arbitrary frequency bands instead of fixed low and high frequencies. The decomposition path that best represents the signal characteristics is selected, which can reduce unnecessary calculations and retain the significant features of the signal. Wavelet packet coefficients are extracted as features from the selected optimal decomposition tree. According to the time and frequency distribution of the signal, AWPC can provide rich time-frequency features.

[0089] Finally, the instantaneous frequency characteristics of the sound signal are extracted, and the preprocessed signal x(t) is subjected to Hilbert transform to obtain its analytical signal z(t).

[0090]

[0091] in is the Hilbert transform of x(t).

[0092] The instantaneous frequency f(t) is the time derivative of the phase of the analytical signal z(t):

[0093]

[0094] The rate of change of instantaneous frequency can provide dynamic information about the local frequency changes of the signal and is an important tool for non-stationary signal analysis.

[0095] The specific method of step S4 is:

[0096] By combining MFCC, AWPC and IF, a comprehensive characterization of the sound signal can be obtained:

[0097] MFCC provides the static spectral characteristics of the signal on the Mel frequency scale, which is suitable for describing the harmonic structure of the sound signal.

[0098] AWPC provides multi-resolution time-frequency characteristics of the signal, which can capture the energy distribution and changes of the signal in different frequency bands, and is suitable for a variety of sound signal analysis.

[0099] IF provides dynamic change information of the signal's instantaneous frequency and is suitable for analyzing non-stationary signals, such as modulation and jitter in sound.

[0100] The feature vectors of MFCC, AWPC and IF are connected and the principal component analysis method is used for dimensionality reduction to reduce the feature dimension and retain the most important information. The fused feature vector can be used for classification and recognition in machine learning models.

[0101] The principal component analysis method mainly includes the following steps:

[0102] 1) Data Standardization

[0103] 2) Calculate the covariance matrix

[0104] 3) Calculate the eigenvalues ​​and eigenvectors of the covariance matrix

[0105] 4) Select the main eigenvectors

[0106] 5) Transform to new feature space

[0107] By projecting high-dimensional features into a low-dimensional subspace, PCA can reduce redundant information, improve computational efficiency, and enhance model performance.

[0108] The specific method of step S5 is:

[0109] Standardize the features after dimensionality reduction. Use zero mean unit variance standardization (Z-Score). Z-Score standardization is the most commonly used standardization method. By adjusting the mean of the feature to 0 and the standard deviation to 1, the standardized feature follows the standard normal distribution (mean is 0 and standard deviation is 1).

[0110] Given a feature vector x = [x1, x2, x3…x n ], whose mean μ and standard deviation σ are:

[0111]

[0112] The eigenvector z after Z-Score standardization is [z1,z2,z3…z n ] is calculated as follows:

[0113]

[0114] Mapping feature data to the same scale can eliminate the dimensional differences of different features, make the features have the same weight and importance, and improve the convergence speed and stability of the model.

[0115] After that, the standardized features are evaluated by correlation analysis to determine the correlation between the features and the target variable. The present invention uses the Pearson correlation coefficient, which ranges from -1 to 1. When the correlation coefficient is close to 1, it indicates that there is a strong positive correlation between the two variables; when the correlation coefficient is close to -1, it indicates that there is a strong negative correlation; when the correlation coefficient is close to 0, it indicates that there is no linear correlation.

[0116] Given two variables X and Y, the formula for calculating the Pearson correlation coefficient r is:

[0117]

[0118] in and are the means of X and Y respectively.

[0119] By selecting the strongest positively correlated feature quantity as the feature parameter of the extracted sound signal, the feature parameter extraction method proposed in the present invention can comprehensively capture the subtle features and dynamic changes of the voiceprint, thereby improving the accuracy and robustness of the voiceprint recognition system in the extraction of acoustic signal features of gas-insulated equipment.

[0120] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0122] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0126] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for extracting acoustic signal features of gas-insulated equipment, characterized in that: include, The collected sound signal is subjected to noise reduction processing, and the mean and variance of the signal are normalized; Using short-time Fourier transform STFT and wavelet transform WT to perform time-frequency decomposition on the noise-reduced sound signal; Comprehensively extract the features of the sound signal by combining MFCC, AWPC adaptive wavelet packet coefficients and instantaneous frequency features IF; The extracted voiceprint features are fused, and the MFCC, AWPC and IF features are concatenated to form a high-dimensional feature vector, which is then reduced using principal component analysis (PCA). The features after dimensionality reduction are standardized and the correlation analysis method is used to further screen the features.

2. The method for extracting acoustic signal characteristics of a gas-insulated device according to claim 1, characterized in that: The noise reduction process further includes using a Wiener filter method to perform noise reduction on the sound signal, assuming that the observed signal x(t) satisfies the following relationship: x(t)=s(t)+n(t) Where s(t) is the detection signal and n(t) is the noise; The output of the Wiener filter Through convolution we get: Where x(t) is the observed signal and h(t) represents the impulse response of the filter. The goal of the Wiener filter is to minimize the mean square error E: In the frequency domain, assume that the power spectral densities of the signal and noise are S sx (f) and S n (f), the frequency response H(f) of the filter is calculated by the following formula: Where S sx (f) is the cross power spectral density of the signal and the observed signal; S x (f) = S sx (f)+S n (f) is the power spectral density of the observed signal.

3. The method for extracting acoustic signal characteristics of a gas-insulated device according to claim 2, characterized in that: The noise reduction process further includes, if the power spectral density of the signal s(t) and the noise n(t) is known, performing an inverse Fourier transform into the time domain to obtain a time domain filter h(t); The mean of the filtered signal is calculated, and the mean of each frame signal is subtracted to ensure that the mean of the signal in each frame is zero, eliminate the influence of the DC component on the characteristics, and adjust the standard deviation of each frame signal to unity to scale the amplitude range of the signal.

4. The method for extracting acoustic signal characteristics of a gas-insulated device according to claim 3, characterized in that: The time-frequency decomposition includes using short-time Fourier transform STFT and wavelet transform WT to perform time-frequency decomposition on the pre-processed sound signal; Short-time Fourier transform (STFT) is a method for analyzing the time-frequency characteristics of a signal by applying a time window to the signal and calculating the Fourier transform. For the preprocessed sound signal x(n), STFT is expressed as: Among them, w(n) is a window function, and the Hamming window is selected; Among them, m represents the time offset, ω represents the frequency variable, N is a natural number, a is a constant. For the Hamming window, a is 0.

46. The result of STFT (X9m,ω) is a complex number, which represents the signal component at the frequency ω at the time m.

5. The method for extracting acoustic signal characteristics of gas-insulated equipment according to claim 4, characterized in that: The comprehensive extraction of the characteristics of the sound signal includes: using adaptive wavelet packet decomposition to capture the time-frequency characteristics of the signal, performing multi-level wavelet packet decomposition on the signal, recursively decomposing the frequency band of the signal, decomposing each frequency band of the signal into low-frequency and high-frequency sub-bands at each level of decomposition, selecting the decomposition path that best represents the signal characteristics, and extracting wavelet packet coefficients as features from the selected optimal decomposition tree.

6. The method for extracting acoustic signal characteristics of gas-insulated equipment according to claim 5, characterized in that: The comprehensive extraction of the characteristics of the sound signal further includes extracting the instantaneous frequency characteristics of the sound signal, performing Hilbert transform on the preprocessed signal x(t) to obtain its analytical signal z(t): in is the Hilbert transform of x(t), is the imaginary part; The instantaneous frequency f(t) is the time derivative of the phase of the analytical signal z(t): The rate of change of the instantaneous frequency can provide dynamic information about the local frequency changes of the signal.

7. The method for extracting acoustic signal characteristics of gas-insulated equipment according to claim 6, characterized in that: The feature fusion of the extracted voiceprint features includes obtaining a comprehensive feature description of the sound signal by combining MFCC, AWPC and IF: MFCC provides the static spectrum characteristics of the signal on the Mel frequency scale, which is suitable for describing the harmonic structure of the sound signal; AWPC provides the multi-resolution time-frequency characteristics of the signal, capturing the energy distribution and changes of the signal in different frequency bands; IF provides the dynamic change information of the instantaneous frequency of the signal, which is used to analyze non-stationary signals, including modulation and jitter characteristics in the sound; The feature vectors of MFCC, AWPC and IF are connected, and the principal component analysis method is used to reduce the dimension. The machine learning model is used to classify and identify the fused feature vectors.

8. The method for extracting acoustic signal characteristics of gas-insulated equipment according to claim 7, characterized in that: The standardization of the features after dimensionality reduction further includes: The Z-Score is standardized with zero mean and unit variance. By adjusting the mean of the feature to 0 and the standard deviation to 1, the standardized feature follows a standard normal distribution with a mean of 0 and a standard deviation of 1. Given a feature vector x = [x1, x2, x3…x n ], the mean μ and standard deviation σ are: Where n is the length of the feature vector, x i is the component corresponding to the eigenvector. The eigenvector z after Z-Score standardization is [z1,z2,z3…z n ] is calculated as follows: Map feature data to the same scale to eliminate dimensional differences between different features; The standardized features are used to evaluate the correlation between the features and the target variables through correlation analysis, using the Pearson correlation coefficient, which ranges from [-1,1]; When the correlation coefficient is close to 1, it indicates that there is a strong positive correlation between the two variables; when the correlation coefficient is close to -1, it indicates that there is a strong negative correlation; when the correlation coefficient is close to 0, it indicates that there is no linear correlation. Given two variables X and Y, the formula for calculating the Pearson correlation coefficient r is: in and are the means of X and Y respectively, X i and Y i are the values ​​of the i-th item of X and Y respectively, where i is a natural number.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images