A High-Voltage Switch Intelligent Voiceprint Monitoring, Diagnosis and Analysis System

Abstract

The present invention relates to the technical field of power equipment fault diagnosis, and particularly relates to a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system. The present invention obtains an information quantity index according to the amplitude change trend of the component signals in the current signal segment and the power difference at different frequencies, obtains an amplitude growth index according to the difference in the matching situation of the component signals with the same frequency in the adjacent audio signal segments and the current signal segment respectively, and obtains a spectral distribution diffusion index according to the spectral change degree of the component signals with the same frequency in different audio signal segments; then combines the information quantity index, the amplitude growth index and the spectral distribution diffusion index to select the effective component signals of the current signal segment, reconstructs them to obtain the current effective signal segment, and uses it to diagnose the working state of the high-voltage switch in the current time. The present invention increases the proportion of abnormal working sounds of the high-voltage switch in the current signal segment and improves the accuracy of diagnosing the working state of the high-voltage switch.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment fault diagnosis, and particularly relates to a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis system. Background Art

[0002] The high-voltage switch, also known as the high-voltage circuit breaker, is one of the most important electrical appliances in the high-voltage power supply system; the high-voltage switch can not only cut off and connect the no-load current and load current in the high-voltage circuit under normal conditions, but also cooperate with the protection device and the automatic device when a system fault occurs to quickly cut off the fault power supply and ensure the safe operation of the system.

[0003] At present, the high-voltage switches in China's power system are basically in a state of regular maintenance. Condition-based maintenance is a preventive operation based on the operating state of the high-voltage circuit breaker. By online monitoring the state diagnosis of the high-voltage switch and determining the maintenance plan, the fault prediction and health management of the high-voltage switch can be realized.

[0004] The existing method analyzes the audio during the closing or opening operation of the high-voltage switch to determine the working state of the high-voltage switch. The audio during the working process of the high-voltage switch usually contains the sound information when the high-voltage switch works, the abnormal sound of the high-voltage switch and the surrounding environmental noise. Among them, the abnormal sound of the high-voltage switch is an important factor for judging the working state of the high-voltage switch; if the influence of the environmental noise on the audio is higher than the influence of the abnormal sound of the high-voltage switch on the audio, the accuracy of diagnosing the working state of the high-voltage switch is low. Summary of the Invention

[0005] In order to solve the technical problem that the abnormal sound of the high-voltage switch has a small influence on the audio during its working process, resulting in a low accuracy of diagnosing the working state of the high-voltage switch, the purpose of the present invention is to provide a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis system, and the specific technical solution adopted is as follows:

[0006] The present invention proposes a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis system, and the system includes:

[0007] A data acquisition module, configured to obtain a sequence of audio signal segments when the high-voltage switch works continuously, and record the last audio signal segment in the sequence as the current signal segment;

[0008] An information amount analysis module, configured to decompose each audio signal segment to obtain component signals of different frequencies; according to the amplitude change trend and the power difference of different frequencies of each component signal of the current signal segment, obtain the information amount index of each component signal of the current signal segment;

[0009] An amplitude growth analysis module, which is used to match the component signals with the same frequency in the current signal segment and the remaining audio signal segments in the audio signal segment sequence, and obtain the amplitude growth index of each component signal of the current signal segment according to the difference in the matching conditions of the component signals with the same frequency between two adjacent audio signal segments and the current signal segment;

[0010] A spectrum analysis module, which is used to obtain the spectrum distribution diffusion index of each component signal of the current signal segment according to the degree of spectrum change of the component signals with the same frequency in the audio signal segments in the audio signal segment sequence;

[0011] A voiceprint diagnosis module, which is used to adjust the information quantity index according to the amplitude growth index and the spectrum distribution diffusion index, reconstruct the effective component signals screened from the component signals of the current signal segment by using the adjusted information quantity index to obtain the current effective signal segment; and diagnose the working state of the high-voltage switch in the current time based on the current effective signal segment.

[0012] Further, the obtaining of the information quantity index of each component signal of the current signal segment includes:

[0013] For each component signal of the current signal segment, obtain the envelope of the component signal, and the envelope includes: an upper envelope and a lower envelope; obtain the mean value of the absolute values of the differences in amplitudes of all adjacent two data points on each envelope of the component signal, and record it as the local amplitude change degree of the corresponding envelope; take the mean value of the local amplitude change degrees of all envelopes of the component signal as the comprehensive amplitude change degree of the component signal;

[0014] Perform Fourier transform on the component signal to obtain spectrum data, and record the frequency corresponding to the maximum power in the spectrum data as the main frequency of the component signal; in the spectrum data, the frequency segments formed by continuous data points with power greater than the preset power threshold, and record the frequency corresponding to the maximum power on each frequency segment as the analysis frequency of the component signal;

[0015] Take the product of the absolute value of the difference between each analysis frequency and the main frequency of the component signal and the power of each analysis frequency as the local distribution generality of each analysis frequency of the component signal; take the sum of the local distribution generalities of all analysis frequencies of the component signal as the frequency distribution generality of the component signal;

[0016] Obtain the information quantity index of the component signal according to the comprehensive amplitude change degree and the frequency distribution generality.

[0017] Further, the obtaining of the amplitude growth index of each component signal of the current signal segment includes:

[0018] Arrange the component signals of the same frequency in all audio signal segments in the audio signal segment sequence in sequence to obtain a component signal sequence for each frequency; for each component signal sequence, respectively record the last component signal in the component signal sequence as the current component signal, and the remaining component signals as target component signals;

[0019] According to the matching situation of the data points on the envelope line between the current component signal and each target component signal, obtain the envelope analysis index of the current component signal and each target component signal;

[0020] Obtain the mean value of the differences between the envelope analysis indexes of the remaining target component signals except the first target component signal and its adjacent previous target component signal and the current component signal as the amplitude growth index of the current component signal.

[0021] Furthermore, the obtaining of the envelope analysis index of the current component signal and each target component signal includes:

[0022] Arrange the data points on each envelope line of each component signal in sequence to obtain an analysis sequence corresponding to the component signal; the analysis sequence includes: an upper analysis sequence and a lower analysis sequence;

[0023] For each target component signal, match the upper analysis sequence of the current component signal and the target component signal, and select the matching data points of each data point in the upper analysis sequence of the current component signal from the upper analysis sequence of the target component signal;

[0024] Obtain the mean value of the time intervals corresponding to the data points in the upper analysis sequence of the current component signal and their matching data points, and record it as the time difference index; obtain the mean value of the absolute values of the differences between the amplitudes of the data points in the upper analysis sequence of the current component signal and their matching data points, and record it as the amplitude difference index;

[0025] According to the time difference index and the amplitude difference index, obtain the local analysis index of the upper analysis sequence of the current component signal and the target component signal; the time difference index and the local analysis index are negatively correlated, and the amplitude difference index and the local analysis index are positively correlated;

[0026] Take the mean value of the local analysis indexes of the upper analysis sequence and the lower analysis sequence of the current component signal and the target component signal as the envelope analysis index of the current component signal and the target component signal.

[0027] Furthermore, the obtaining of the spectrum distribution diffusion index of each component signal of the current signal segment includes:

[0028] Subtract the spectral data of each of the target component signals from the spectral data of the current component signal to obtain the difference spectral data of each target component signal; arrange the difference spectral data of all target component signals in sequence to obtain a difference spectral sequence;

[0029] Normalize the mean of the correlation coefficients of two adjacent difference spectral data in the difference frequency sequence to obtain the spectral change consistency value of the current component signal;

[0030] Obtain the mean of the powers of all data points of each difference spectral data, denoted as the first mean power of the corresponding difference frequency data; normalize the mean of the first mean powers of all difference spectral data in the difference frequency sequence to obtain the second mean power of the current component signal;

[0031] Obtain a spectral distribution diffusion index according to the second mean power and the spectral change consistency value; both the second mean power and the spectral change consistency value are positively correlated with the spectral distribution diffusion index.

[0032] Further, the method for obtaining the current effective signal segment includes:

[0033] Obtain the abnormal information amount coefficient of each component signal of the current signal segment according to the amplitude growth index and the spectral distribution diffusion index; use the abnormal information amount coefficient to weight the information amount index to obtain the effective information index of each component signal of the current signal segment;

[0034] For the effective information indexes of all component signals of the current signal segment, use the component signals corresponding to the largest preset number of the effective information indexes as effective component signals; reconstruct all effective component signals of the current signal segment to obtain the current effective signal segment.

[0035] Further, the diagnosis of the working state of the high-voltage switch based on the current effective signal segment includes:

[0036] Extract features from the current effective signal segment to obtain a feature vector, denoted as the current diagnosis vector;

[0037] Obtain the cosine similarity between the current diagnosis vector and a preset normal feature vector. If the cosine similarity is greater than the preset normal threshold, the working state of the high-voltage switch in the current operation is normal; if the cosine similarity is less than or equal to the preset normal threshold, the working state of the high-voltage switch in the current operation is abnormal.

[0038] Further, the method for decomposing each audio signal segment is the EMD algorithm.

[0039] Further, the method for matching the upper analysis sequence of the current component signal and the target component signal is the DTW algorithm.

[0040] Further, the method for extracting features from the current valid signal segment is the MFCC algorithm.

[0041] The present invention has the following beneficial effects:

[0042] In the embodiment of the present invention, the working abnormal sound of the high-voltage switch and the strong noise in the ambient noise will cause large changes in the audio signal segment during the operation of the high-voltage switch, which are mainly reflected in the changes in the signal amplitude and signal frequency of the audio signal segment. Then, the information amount index is obtained according to the amplitude change trend of the component signal and the power difference of different frequencies; when the high-voltage switch is abnormal, the proportion of abnormal sound in the audio signal segment will gradually increase, resulting in an increasing trend in the frequency and amplitude of the component signals of the same frequency in the audio signal segment sequence of the audio signal segment, and the distribution of the voice signal in the frequency domain range will gradually spread with the increase of the abnormal sound content. According to the above two features, the amplitude growth index and the spectrum distribution diffusion index are obtained in sequence, and both can reflect the abnormal sound content of the high-voltage switch in the component signals of the current signal segment; then, the effective component signals are screened according to the information amount index adjusted by using the amplitude growth index and the spectrum distribution diffusion index. The abnormal sound of the high-voltage switch working in the effective component signals is clearer and has a larger proportion. Based on the effective component signals, reconstruction is carried out to obtain clearer abnormal sound audio data, that is, the current valid signal segment, on the premise of reducing the ambient noise in the audio signal segment, thereby improving the accuracy of the abnormal diagnosis of the working state of the high-voltage switch. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is the system structure diagram of a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis system provided by an embodiment of the present invention;

[0045] Figure 2 2]It is the system structure diagram of a method for obtaining an amplitude growth index provided by an embodiment of the present invention;

[0046] Figure 3 It is the computer device schematic diagram of a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0047] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system proposed according to the present invention, including its specific implementation manner, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0049] The following specifically describes the specific solution of a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system provided by the present invention in conjunction with the accompanying drawings.

[0050] Embodiment 1:

[0051] Please refer to Figure 1 , which shows a system block diagram of a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system provided by an embodiment of the present invention. The system includes: a data acquisition module 110, an information quantity analysis module 120, an amplitude growth analysis module 130, a spectrum analysis module 140, and a voiceprint diagnosis module 150.

[0052] The data acquisition module 110 is used to obtain the audio signal segment sequence when the high-voltage switch works continuously, and the last audio signal segment in the sequence is recorded as the current signal segment.

[0053] Specifically, a sound acquisition device is arranged near the high-voltage switch to be monitored. The arrangement method of the sound acquisition device is the microphone array technology. The sound acquisition device is started each time the high-voltage switch starts to work, and the sound generated by the high-voltage switch during each work process is collected by the sound acquisition device to obtain the audio signal segment of each work.

[0054] It should be noted that the sound acquisition device can be a microphone, or an acoustic sensor and a recording pen, etc.; the operation of the high-voltage switch refers to the closing and opening operations of the high-voltage switch; the duration of the audio signal segment of each work is equal to the duration of the closing or opening operation of the high-voltage switch each time; in this embodiment, the data acquisition frequency of the sound acquisition device is once every 0.1 seconds, and the implementer can set it according to specific circumstances.

[0055] The horizontal axis of the audio signal segment represents time, and the vertical axis represents the intensity or energy of the sound; the data points of the sound intensity at each moment during each operation of the high-voltage switch are curve-fitted to obtain the audio signal segment for each operation. Among them, the curve-fitting method is the least squares method, and both the least squares method and the microphone array technology are well-known technologies to those skilled in the art and will not be elaborated here.

[0056] Arrange the audio signal segments of the high-voltage switch in the current operation and the adjacent preset reference number of operations before it in the order of the working sequence of the high-voltage switch to obtain an audio signal segment sequence. The last audio signal segment in the audio signal segment sequence is the audio signal segment of the high-voltage switch in the current operation, denoted as the current signal segment.

[0057] It should be noted that in the embodiments of the present invention, the preset reference number takes an empirical value of 10, and the number of audio signal segments in the audio signal segment sequence is 11. The implementer can set it according to specific situations.

[0058] The information amount analysis module 120 is used to decompose each audio signal segment to obtain component signals of different frequencies; according to the amplitude change trend and the power difference of different frequencies of each component signal of the current signal segment, obtain the information amount index of each component signal of the current signal segment.

[0059] In this embodiment, the empirical mode decomposition (EMD) algorithm is selected to decompose each audio signal segment to obtain component signals of different frequencies. In other embodiments, signal decomposition methods such as the ensemble empirical mode decomposition (EEMD) algorithm and the variational mode decomposition (VMD) algorithm can also be selected. Among them, the EMD algorithm is a well-known technology to those skilled in the art and will not be elaborated here.

[0060] The audio signal segment usually contains the sound information during the operation of the high-voltage switch, the abnormal sound of the high-voltage switch and the environmental noise; the stronger noise in the abnormal sound of the high-voltage switch and the environmental noise will cause great changes in the sound signal during the operation of the high-voltage switch, mainly reflected in the changes of the signal amplitude and signal frequency of the audio signal segment. Therefore, according to the amplitude change trend and the power difference of different frequencies of the component signals of the current signal segment, obtain the information amount index of the component signals.

[0061] The first sub-unit: Obtain the comprehensive amplitude change degree of the component signal.

[0062] For each component signal of the current signal segment, the envelope of the component signal is obtained, and the envelope includes: an upper envelope and a lower envelope; the average of the absolute values of the differences between the amplitudes of all two adjacent data points on each envelope of the component signal is obtained, and recorded as the local amplitude variation of the corresponding envelope; the average of the local amplitude variation of all envelopes of the component signal is used as the comprehensive amplitude variation of the component signal.

[0063] The integrated amplitude variation shows the amplitude variation trend of the component signal. Since the data points on the component signal envelope are usually related to the main characteristics and mutation points of the signal and can carry more useful information, the greater the amplitude difference between adjacent data points on the component signal envelope, the more dramatic the component signal change and the greater the integrated amplitude variation.

[0064] It should be noted that the data point on each envelope line of the component signal refers to a local maximum point or a local minimum point in the component signal.

[0065] In a specific implementation of the embodiment of the present invention, the comprehensive amplitude variation of the component signal is expressed as follows:

[0066]

[0067] Where DA is the comprehensive amplitude variation of the component signal; A is the total number of envelopes of the component signal, which is equal to a constant 2 in this embodiment; N a is the total number of data points on the ath envelope of the component signal; F a,n is the amplitude of the nth data point on the ath envelope of the component signal; F a,n+1 is the amplitude of the n+1th data point on the ath envelope of the component signal;

[0068] is the local amplitude variation of the a-th envelope of the component signal; || is the absolute value function.

[0069] The second subunit: obtains the frequency distribution of the component signal.

[0070] Perform Fourier transform on the component signal to obtain spectrum data, record the frequency corresponding to the maximum power in the spectrum data as the main frequency of the component signal; in the spectrum data, a frequency segment is formed by continuous data points with power greater than a preset power threshold, and record the frequency corresponding to the maximum power in each frequency segment as the analysis frequency of the component signal; the product of the absolute value of the difference between each analysis frequency of the component signal and the main frequency and the power of each analysis frequency is used as the local distribution spread of each analysis frequency of the component signal; the cumulative sum of the local distribution spreads of all analysis frequencies of the component signal is used as the frequency distribution spread of the component signal. Among them, Fourier transform is a well-known technology for those skilled in the art and will not be described in detail here.

[0071] The data point with the maximum power in the frequency band represents the main local feature of the spectrum data. Selecting the relevant data of the data point with the maximum power in the frequency band for analysis is conducive to simplifying the analysis and highlighting the feature information.

[0072] Frequency distribution broadness indicates the power differences between different frequencies in a component signal. A larger difference between the analysis frequency and the primary frequency indicates that the component signal contains more frequency components. A higher power at the analysis frequency indicates that the analysis frequency component plays a more important role in the component signal. This indicates that the component signal contains multiple incoherent frequency components, making the component signal's spectrum more dispersed and the frequency distribution broadness is greater.

[0073] It should be noted that spectral data refers to a spectrogram, with the horizontal axis representing frequency and the vertical axis representing power. Spectral data is a curve obtained by least squares curve fitting using the power data points of the audio signal segment at each frequency. In this embodiment of the present invention, the preset power threshold is equal to one-tenth of the power of the component signal's dominant frequency; implementers may adjust this threshold based on their specific circumstances.

[0074] In a specific implementation of the embodiment of the present invention, the frequency distribution of the component signal is expressed as follows:

[0075]

[0076] Where SF is the frequency distribution of the component signal; B is the total number of analysis frequencies of the component signal; P b is the power of the bth analysis frequency of the component signal; F b is the bth analysis frequency of the component signal; F_main is the main frequency of the component signal; P b ×|F b -F_main| is the local distribution extensiveness of the b-th analysis frequency of the component signal; || is the absolute value function.

[0077] The third subunit: obtaining information content indicators of component signals.

[0078] A greater degree of integrated amplitude variation indicates a more dramatic change in the component signal, meaning the component signal contains more information, and thus, the information content of the analysis signal is richer. A greater frequency distribution variability indicates a more discrete distribution of the component signal's frequency components, indicating that the component signal can simultaneously transmit information at multiple frequencies, which means that the component signal itself has a stronger expressive power and richer information.

[0079] Therefore, both the comprehensive amplitude variation and the frequency distribution extensiveness are positively correlated with the information content index. In the embodiment of the present invention, the product of the comprehensive amplitude variation and the frequency distribution extensiveness of the component signal is normalized to obtain the information content index of the component signal.

[0080] In the embodiments of the present invention, the correlation relationship between the comprehensive amplitude change degree, the frequency distribution generality, and the information amount index can also be constructed through other basic mathematical operations, which will not be limited and elaborated herein.

[0081] It should be noted that in the embodiments of the present invention, the Norm function is used for normalization processing. In the embodiments of the present invention, other normalization methods can also be selected, such as function transformation, maximum-minimum normalization, etc. The normalization methods are not limited herein; the normalization methods used in other positions in this solution are the same as those used here.

[0082] According to the above method, the information amount index of each component signal of the current signal segment is obtained.

[0083] The amplitude growth analysis module 130 is used to match the component signals of the same frequency between the current signal segment and the remaining audio signal segments in the audio signal segment sequence, and obtain the amplitude growth index of each component signal of the current signal segment according to the difference in the matching conditions of the component signals of the same frequency between two adjacent audio signal segments and the current signal segment.

[0084] The normal sound during the operation of the high-voltage switch is usually similar in the audio signal segment. The jamming, stroke, vibration, etc. of the high-voltage switch during operation can all reflect the operating conditions of the high-voltage switch; when the high-voltage switch is abnormal, it will cause abnormal sounds during the operation of the high-voltage switch, and the proportion of abnormal sounds in the audio signal segments of multiple operations will gradually increase. Then, the audio characteristics of the audio signal segments in the audio signal segment sequence show a gradually increasing trend, and the more they can represent the abnormal sounds during the operation of the high-voltage switch.

[0085] The difference in the matching conditions of the component signals of the same frequency between two adjacent audio signal segments and the current signal segment presents the amplitude and frequency growth trends of the component signals of the same frequency between two adjacent audio signal segments, and then the amplitude growth index is obtained to measure the content of abnormal sounds of the high-voltage switch in the component signals of the current signal segment.

[0086] Please refer to Figure 2 , which shows the system structure diagram of a method for obtaining the amplitude growth index provided by an embodiment of the present invention. The system includes: a component definition unit 131, an envelope analysis unit 132, and an amplitude analysis unit 133.

[0087] The component definition unit 131: Sequentially arrange the component signals of the same frequency of all audio signal segments in the audio signal segment sequence to obtain a component signal sequence for each frequency; for each component signal sequence, respectively record the last component signal in the component signal sequence as the current component signal, and the remaining component signals as the target component signals.

[0088] Analyzing using the component signals of the same frequency in different audio signal segments can reduce noise interference, improve the resolution of the audio signal segments, and enhance the robustness of the analysis.

[0089] Envelope analysis unit 132: Obtain the envelope analysis metrics of the current component signal and each target component signal according to the matching situation of the data points on the envelope lines of the current component signal and each target component signal.

[0090] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the envelope analysis metrics includes: arranging the data points on each envelope line of each component signal in sequence to obtain the analysis sequence corresponding to the component signal; the analysis sequence includes: an upper analysis sequence and a lower analysis sequence; for each target component signal, match the current component signal with the upper analysis sequence of the target component signal, and select the matching data points of each data point in the upper analysis sequence of the current component signal from the upper analysis sequence of the target component signal; obtain the mean value of the time intervals corresponding to the data points in the upper analysis sequence of the current component signal and their matching data points, and denote it as the time difference metric; obtain the mean value of the absolute values of the differences between the amplitudes of the data points in the upper analysis sequence of the current component signal and their matching data points, and denote it as the amplitude difference metric; obtain the local analysis metric of the upper analysis sequence of the current component signal and the target component signal according to the time difference metric and the amplitude difference metric; the time difference metric and the local analysis metric are negatively correlated, and the amplitude difference metric and the local analysis metric are positively correlated; take the mean value of the local analysis metrics of the upper analysis sequence and the lower analysis sequence of the current component signal and the target component signal as the envelope analysis metric of the current component signal and the target component signal.

[0091] The envelope analysis metric presents the matching situation between the current component signal and the target component signal. The time difference metric reflects the similarity between the current component signal and the target component signal, and the amplitude difference metric reflects the amplitude change degree between the current component signal and the target component signal; if the matching distance between the current component signal and the target component signal remains unchanged, that is, the time difference metric is smaller, but the amplitude difference of the envelope line, that is, the amplitude difference metric is larger, it indicates that the similarity between the current component signal and the target component signal is stronger and the amplitude shows an increasing trend, then the proportion of abnormal sounds of the high-voltage switch in the current component signal is larger. Therefore, perform a negative correlation mapping on the time difference metric, and normalize the product of the mapping result and the amplitude difference metric to obtain the local analysis metric.

[0092] In this embodiment, an exponential function with the natural constant as the base is selected for negative correlation mapping. The specific method is: first take the opposite number of the time difference metric, and use this opposite number as the exponent of the exponential function with the natural constant as the base to achieve negative correlation mapping of the time difference metric; select the Norm function for normalization processing.

[0093] It should be noted that the data points on the envelope line of the component signal are arranged according to the time sequence to obtain an analysis sequence; the analysis sequence corresponding to the upper envelope line of the component signal is the upper analysis sequence, and the analysis sequence corresponding to the lower envelope line is the lower analysis sequence. In the embodiments of the present invention, the dynamic time warping (DTW) algorithm is used to match the upper analysis sequence of the current component signal and the target component signal. Among them, the DTW algorithm is a well-known technology to those skilled in the art and will not be elaborated here.

[0094] The method for obtaining the local analysis indexes of the upper analysis sequence and the lower analysis sequence of the current component signal and the target component signal is the same; that is, the upper analysis sequence is replaced with the lower analysis sequence, and other contents remain unchanged.

[0095] Amplitude analysis unit 133: Obtain the average value of the differences between the remaining target component signals except the first target component signal and its adjacent previous target component signal and the envelope analysis indexes of the current component signal, as the amplitude growth index of the current component signal.

[0096] The local analysis index only considers the relationship between a single target component signal and the current component signal, and cannot describe the amplitude and frequency growth trends of the component signals with the same frequency in the audio signal segment. In this embodiment, the above growth trends are presented by the differences between the adjacent target component signals and the envelope analysis indexes of the current component signal respectively.

[0097] If the differences between all the target component signals and their adjacent previous target component signals and the envelope analysis indexes of the current component signal are all greater than the constant 0 and the larger they are, then the amplitude and frequency of the component signals with the same frequency in the audio signal segment show a growth trend and the trend is more obvious.

[0098] In a specific implementation manner of the embodiments of the present invention, the amplitude growth index of the current component signal is expressed by the formula:

[0099]

[0100] In the formula, EA is the amplitude growth index of the current component signal; M is the total number of target component signals in the component signal sequence where the current component signal is located, that is, the difference between the total number of component signals in the component signal sequence where the current component signal is located and the constant 1; SAM M-m is the envelope analysis index of the current component signal and the M - m-th target component signal; SAM M-m-1 is the envelope analysis index of the current component signal and the M - m - 1-th target component signal.

[0101] It should be noted that the larger the amplitude growth index is, the more similar the component signals in the component signal sequence are, and the more obvious the increasing trend of the amplitude and frequency is, the higher the abnormal sound content of the high-voltage switch in the current component signal is; on the contrary, the weaker the similarity of the component signals in the component signal sequence is, the greater the possibility that the information in the current component signal is environmental noise.

[0102] Obtain the amplitude growth index of the component signals of each frequency in the current signal segment, and these amplitude growth indices are obtained in the same way as the amplitude growth index of the current component signal.

[0103] The spectrum analysis module 140 is used to obtain the spectrum distribution diffusion index of each component signal in the current signal segment according to the spectrum change degree of the component signals of the same frequency in the audio signal segment sequence.

[0104] Since the abnormal sound content of the high-voltage switch in the component signal sequence shows a gradually increasing trend, the distribution of the voice signal in the frequency domain will gradually spread as the abnormal sound content increases. Therefore, if the distribution of the audio signal segments of the high-voltage switch in adjacent operations shows a more obvious diffusion trend in the frequency domain, the abnormal sound content of the high-voltage operation in the component signals of the current signal segment is higher. According to the spectrum change degree of the component signals of the same frequency in the audio signal segment sequence, obtain the spectrum distribution diffusion index to measure the abnormal content of the high-voltage switch in the component signals of the current signal segment.

[0105] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the spectrum distribution diffusion index includes: subtracting the spectrum data of each target component signal from the spectrum data of the current component signal to obtain the difference spectrum data of each target component signal; arranging the difference spectrum data of all target component signals in sequence to obtain a difference spectrum sequence; normalizing the mean of the correlation coefficients of two adjacent difference spectrum data in the difference frequency sequence to obtain the spectrum change consistency value of the current component signal; obtaining the mean of the powers of all data points of each difference spectrum data, which is denoted as the first mean power of the corresponding difference frequency data; normalizing the mean of the first mean powers of all difference spectrum data in the difference frequency sequence to obtain the second mean power of the current component signal; obtaining the spectrum distribution diffusion index according to the second mean power and the spectrum change consistency value; both the second mean power and the spectrum change consistency value are positively correlated with the spectrum distribution diffusion index.

[0106] It should be noted that the power of each frequency of the difference spectrum data of the target component signal is equal to the difference between the powers of the same frequency in the spectrum data of the current component signal and the target component signal. The correlation coefficient in the embodiments of the present invention is the Pearson correlation coefficient; in other embodiments, the correlation coefficient can also be the Spearman correlation coefficient, the Kendall rank correlation coefficient, and the canonical correlation coefficient, etc.

[0107] The similarity index between two adjacent difference spectrum data in the difference frequency sequence reflects the similarity degree of the spectral change degree of some component signals in the component signal sequence, and the frequency change consistency value reflects the consistency of the overall spectral change degree of the component signals in the component signal sequence. When the abnormal sound ratio of the high-voltage switch gradually increases during multiple operations, the spectral difference changes of the high-voltage switch in the audio signal segment during multiple operations are more similar and the spectrum is more dispersed. Therefore, if the frequency change consistency value is larger and the spectrum of the current component signal is more dispersed, the spectral distribution diffusion index is larger.

[0108] In order to analyze the overall trend of the abnormal ratio of the high-voltage switch during multiple operations, considering the abnormal ratio of the high-voltage switch between every two adjacent operations during multiple operations, the mean value of the first average power of all difference spectrum data in the difference frequency sequence is obtained for analysis. If the second average power is larger, it indicates that the growth trend of the abnormal ratio of the high-voltage switch during multiple operations is more obvious, the frequency information change of the high-voltage switch in the audio segment during multiple operations is larger, the frequency information change is more extensive, and the spectral distribution range is larger, then the spectral distribution diffusion index is larger.

[0109] Therefore, the second average power has a positive correlation with the frequency change consistency value and the spectral distribution diffusion index. In the embodiment of the present invention, the product of the second average power of the current component signal and the frequency change consistency value is normalized to obtain the spectral distribution diffusion index of the current component signal. If the spectral distribution diffusion index is larger, the abnormal sound ratio of the high-voltage switch in the current component signal is larger. In this embodiment, the Norm function is selected for normalization processing.

[0110] In the embodiment of the present invention, the correlation relationship between the second average power, the frequency change consistency value, and the spectral distribution diffusion index can also be constructed through other basic mathematical operations, which will not be limited and elaborated here.

[0111] The method for obtaining the spectral distribution diffusion index of each component signal in the current signal segment is the same as the method for obtaining the spectral distribution diffusion index of the current component signal.

[0112] The voiceprint diagnosis module 150 is used to adjust the information quantity index according to the amplitude growth index and the spectral distribution diffusion index, reconstruct the effective component signals screened from the component signals of the current signal segment by using the adjusted information quantity index to obtain the current effective signal segment; and diagnose the working state of the high-voltage switch in the current operation based on the current effective signal segment.

[0113] Both the amplitude growth index and the spectral distribution diffusion index are used to measure the abnormal sound content of the high-voltage switch in the component signals of the current signal segment. By combining the two to adaptively adjust the information quantity index, the adjusted information quantity index can more accurately reflect the abnormal sound information in the component signals of the current signal segment.

[0114] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the effective information index includes: obtaining the abnormal information amount coefficient of each component signal of the current signal segment according to the amplitude growth index and the spectrum distribution diffusion index; using the abnormal information amount coefficient to perform a weighting process on the information amount index to obtain the effective information index of each component signal of the current signal segment.

[0115] According to the content of the amplitude growth analysis module 130 and the spectrum analysis module 140, it can be known that the higher the amplitude growth index and the spectrum distribution diffusion index are, the higher the content of abnormal sound of the high-voltage switch in the component signals of the current signal segment is. Therefore, the amplitude growth index, the spectrum distribution diffusion index and the abnormal information amount coefficient are positive correlation coefficients.

[0116] In a specific implementation manner of the embodiments of the present invention, the effective information index of each component signal of the current signal segment is expressed by the formula:

[0117] E i =Norm(EP i ×EA i )×X i

[0118] In the formula, E i is the effective information index of the i-th component signal of the current signal segment; EP i is the amplitude growth index of the i-th component signal of the current signal segment; EA i is the spectrum distribution diffusion index of the i-th component signal of the current signal segment; Norm(EP i ×EA i ) is the abnormal information amount coefficient of the i-th component signal of the current signal segment; X i is the information amount index of the i-th component signal of the current signal segment; Norm is a normalization function.

[0119] For the effective information indexes of all component signals of the current signal segment, the component signals corresponding to the largest preset number of effective information indexes are used as effective component signals; all effective component signals of the current signal segment are reconstructed to obtain the current effective signal segment. The abnormal sound information of the high-voltage switch working in the current effective signal segment is clearer and has a larger proportion.

[0120] It should be noted that in the embodiments of the present invention, the preset number is the ceiling result of one-tenth of the total number of audio signal segments in the audio signal segment sequence, and the implementer can set it according to the specific situation; in the embodiments of the present invention, the EMD algorithm is selected to reconstruct the effective component signals.

[0121] In this embodiment, the Mel-Frequency Cepstrum Coefficient (MFCC) algorithm is selected to extract features from the current valid signal segment, obtaining a feature vector, denoted as the current diagnosis vector; the cosine similarity between the current diagnosis vector and the preset normal feature vector is obtained. If the cosine similarity is greater than the preset normal threshold, the high-voltage switch is in a normal state during the current operation; if the cosine similarity is less than or equal to the preset normal threshold, the high-voltage switch is in an abnormal state during the current operation. Among them, the MACC algorithm is a well-known technology to those skilled in the art and will not be elaborated here.

[0122] If the cosine similarity between the current diagnosis vector and the preset normal feature vector is larger, it indicates that the audio of the high-voltage switch during the current operation is closer to the audio during normal operation, then the high-voltage switch is in a normal state during the current operation; on the contrary, it indicates that the difference between the audio of the high-voltage switch during the current operation and the audio during normal operation is larger, then the high-voltage switch is in an abnormal state during the current operation.

[0123] In a quiet environment, use a sound acquisition device to obtain the audio signal segment of a new high-voltage switch during its first operation, and use the MFCC algorithm to extract the feature vector of this audio signal segment, denoted as the preset normal feature vector. It should be noted that a quiet environment avoids the influence of environmental noise. The new high-voltage switch is of the same type as the high-voltage switch to be monitored. The new high-voltage switch is usually in a normal operating state during its first operation and there will be no abnormal working sounds. Since the value range of the cosine similarity is from -1 to 1, the preset normal threshold in this embodiment takes an empirical value of 0.3, and the implementer can set it according to specific circumstances.

[0124] Select the effective component signals for reconstruction to obtain clearer abnormal sound audio data on the premise of reducing the environmental noise in the audio signal segment, so that the feature vector transformed from the audio data can better reflect the abnormal sounds during the operation of the high-voltage switch, and the abnormal diagnosis of the working state of the high-voltage switch is more accurate.

[0125] So far, the present invention is completed.

[0126] Embodiment 2:

[0127] Figure 3 It is a schematic diagram of a computer device for a high-voltage switch intelligent voiceprint monitoring and diagnosis analysis device provided by an embodiment of the present invention. Exemplarily, as Figure 3 shown, the computer device includes: a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202. Among them, when the processor 202 executes the computer program 203, the computer device can execute any one of the high-voltage switch intelligent voiceprint monitoring and diagnosis analysis systems introduced above.

[0128] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor. Among them, an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system provided by an embodiment of the present application.

[0129] In this embodiment, the device can be divided into functional modules according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0130] It should be understood that the device provided in this embodiment is used to execute the above high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system, so the same effect as the above implementation method can be achieved.

[0131] In the case of adopting an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc.

[0132] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination that realizes computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0133] Embodiment 3:

[0134] This embodiment also provides a computer-readable storage medium, in which computer program code is stored. When the computer program code runs on a computer, the computer is enabled to execute the above related method steps to implement a high-voltage switch intelligent voiceprint monitoring and diagnostic analysis system provided by the above embodiment.

[0135] Among them, the device and the computer-readable storage medium provided in this embodiment are both used to execute the corresponding system provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding system provided above, and will not be elaborated here.

[0136] It should be noted that the above order of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0138] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A high-voltage switch intelligent voiceprint monitoring, diagnosis and analysis system, characterized in that The system includes: A data acquisition module, configured to obtain an audio signal segment sequence when a high-voltage switch operates continuously for multiple times, and record the last audio signal segment in the sequence as the current signal segment; An information quantity analysis module, configured to decompose each audio signal segment to obtain component signals of different frequencies; and obtain an information quantity index of each component signal of the current signal segment according to the amplitude change trend and power difference of each component signal of the current signal segment at different frequencies; An amplitude growth analysis module, configured to match the component signals of the same frequency of the current signal segment with those of the remaining audio signal segments in the audio signal segment sequence, and obtain an amplitude growth index of each component signal of the current signal segment according to the difference in the matching conditions of the component signals of the same frequency of two adjacent audio signal segments with those of the current signal segment respectively; A spectrum analysis module, configured to obtain a spectrum distribution diffusion index of each component signal of the current signal segment according to the degree of spectrum change of the component signals of the same frequency in the audio signal segment sequence; A voiceprint diagnosis module, configured to adjust the information quantity index according to the amplitude growth index and the spectrum distribution diffusion index, reconstruct the effective component signals screened from the component signals of the current signal segment by using the adjusted information quantity index to obtain the current effective signal segment; and diagnose the working state of the high-voltage switch in the current operation based on the current effective signal segment; The obtaining of the amplitude growth index of each component signal of the current signal segment includes: Sequentially arranging the component signals of the same frequency of all audio signal segments in the audio signal segment sequence to obtain a component signal sequence for each frequency; for each component signal sequence, respectively record the last component signal in the component signal sequence as the current component signal, and the remaining component signals as target component signals; Obtaining an envelope analysis index of the current component signal and each target component signal according to the matching condition of the data points on the envelope line of the current component signal and each target component signal; Obtaining the mean value of the differences between the envelope analysis indexes of the remaining target component signals except the first target component signal and its adjacent previous target component signal and the current component signal as the amplitude growth index of the current component signal; The obtaining of the spectrum distribution diffusion index of each component signal of the current signal segment includes: [[ID=−11]]Subtracting the spectrum data of each target component signal from the spectrum data of the current component signal to obtain the difference spectrum data of each target component signal; and sequentially arranging the difference spectrum data of all target component signals to obtain a difference spectrum sequence; Normalizing the mean value of the correlation coefficients of two adjacent difference spectrum data in the difference spectrum sequence to obtain a spectrum change consistency value of the current component signal; Obtaining the mean value of the powers of all data points of each difference spectrum data, and recording it as the first average power of the corresponding difference spectrum data; and normalizing the mean value of the first average powers of all difference spectrum data in the difference spectrum sequence to obtain the second average power of the current component signal; Obtain a spectrum distribution diffusion index according to the second average power and the spectrum change consistency value; both the second average power and the spectrum change consistency value are positively correlated with the spectrum distribution diffusion index.

2. The intelligent voiceprint monitoring, diagnosis and analysis system for high-voltage switch according to claim 1, wherein The obtaining of the information amount index of each component signal of the current signal segment includes: For each component signal of the current signal segment, obtain the envelope of the component signal, and the envelope includes: an upper envelope and a lower envelope; obtain the average value of the absolute values of the differences between the amplitudes of all adjacent two data points on each envelope of the component signal, and record it as the local amplitude change degree of the corresponding envelope; use the average value of the local amplitude change degrees of all envelopes of the component signal as the comprehensive amplitude change degree of the component signal. Perform a Fourier transform on the component signal to obtain spectrum data, and record the frequency corresponding to the maximum power in the spectrum data as the main frequency of the component signal; in the spectrum data, a frequency segment is formed by continuous data points with power greater than a preset power threshold, and record the frequency corresponding to the maximum power on each frequency segment as the analysis frequency of the component signal. Use the product of the absolute value of the difference between each analysis frequency and the main frequency of the component signal and the power of each analysis frequency as the local distribution generality of each analysis frequency of the component signal; use the sum of the local distribution generalities of all analysis frequencies of the component signal as the frequency distribution generality of the component signal. Obtain the information amount index of the component signal according to the comprehensive amplitude change degree and the frequency distribution generality.

3. A high-voltage switch intelligent voiceprint monitoring, diagnosing and analyzing system according to claim 1, characterized in that, The obtaining of the envelope analysis index of the current component signal and each target component signal includes: Arrange the data points on each envelope of each component signal in sequence to obtain the analysis sequence corresponding to the component signal; the analysis sequence includes: an upper analysis sequence and a lower analysis sequence. For each target component signal, match the upper analysis sequence of the current component signal and the target component signal, and select the matching data points of each data point in the upper analysis sequence of the current component signal from the upper analysis sequence of the target component signal. Obtain the average value of the time intervals corresponding to the data points in the upper analysis sequence of the current component signal and their matching data points, and record it as the time difference index; obtain the average value of the absolute values of the differences between the amplitudes of the data points in the upper analysis sequence of the current component signal and their matching data points, and record it as the amplitude difference index. Obtain the local analysis index of the upper analysis sequence of the current component signal and the target component signal according to the time difference index and the amplitude difference index; the time difference index is negatively correlated with the local analysis index, and the amplitude difference index is positively correlated with the local analysis index. Use the average value of the local analysis indexes of the upper analysis sequence and the lower analysis sequence of the current component signal and the target component signal as the envelope analysis index of the current component signal and the target component signal.

4. A high-voltage switch intelligent voiceprint monitoring, diagnosing and analyzing system according to claim 1, characterized in that, The method for obtaining the current effective signal segment includes: Obtain the abnormal information amount coefficient of each component signal of the current signal segment according to the amplitude growth index and the spectrum distribution diffusion index; use the abnormal information amount coefficient to perform weighted processing on the information amount index to obtain the effective information index of each component signal of the current signal segment. For the valid information indicators of all component signals in the current signal segment, the component signals corresponding to the largest preset number of the valid information indicators are used as valid component signals; all valid component signals in the current signal segment are reconstructed to obtain the current valid signal segment.

5. The intelligent voiceprint monitoring, diagnosis and analysis system for high-voltage switch according to claim 1, characterized in that, Diagnosing the working state of the high-voltage switch in the current time based on the current valid signal segment includes: Performing feature extraction on the current valid signal segment to obtain a feature vector, denoted as the current diagnosis vector; Obtaining the cosine similarity between the current diagnosis vector and a preset normal feature vector. If the cosine similarity is greater than the preset normal threshold, the working state of the high-voltage switch in the current time is normal; if the cosine similarity is less than or equal to the preset normal threshold, the working state of the high-voltage switch in the current time is abnormal.

6. The intelligent voiceprint monitoring, diagnosis and analysis system for high-voltage switch according to claim 1, characterized in that The method for decomposing each audio signal segment is the EMD algorithm.

7. The intelligent voiceprint monitoring, diagnosis and analysis system for high-voltage switch according to claim 3, characterized in that, The method for matching the upper analysis sequences of the current component signal and the target component signal is the DTW algorithm.

8. The intelligent voiceprint monitoring, diagnosis and analysis system for high-voltage switch according to claim 5, characterized in that, The method for performing feature extraction on the current valid signal segment is the MFCC algorithm.

Images