CN114966477A - Transformer voiceprint analysis method and system - Google Patents
Transformer voiceprint analysis method and system Download PDFInfo
- Publication number
- CN114966477A CN114966477A CN202210514966.1A CN202210514966A CN114966477A CN 114966477 A CN114966477 A CN 114966477A CN 202210514966 A CN202210514966 A CN 202210514966A CN 114966477 A CN114966477 A CN 114966477A
- Authority
- CN
- China
- Prior art keywords
- transformer
- signal
- voiceprint
- acoustic signal
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/62—Testing of transformers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
- G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
- Y04S40/126—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wireless data transmission
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention belongs to the technical field of transformer voiceprint analysis, and particularly relates to a transformer voiceprint analysis method which comprises the following steps: arranging optical fiber microphones on two sides of a transformer oil tank to collect acoustic signals from two directions; transmitting the collected acoustic signals to monitoring service equipment through a wireless network; framing the acoustic signals, and applying a Hamming window to each framed signal after framing; respectively extracting frequency spectrum and energy characteristic vectors of the acoustic signals by using a fast Fourier transform and wavelet decomposition algorithm; and combining the obtained frequency spectrum and energy eigenvector distribution characteristics, obtaining the change rule of the acoustic signal under each operation condition according to the characteristics of the transformer under different operation conditions, and diagnosing whether the transformer winding and the transformer iron core are in a normal state. The invention preprocesses the collected signals, namely, frames the sound signals to ensure the continuity between two adjacent frames of signals, applies Hamming window to each frame of signal after the framing treatment and then transforms, increases the continuity of two ends of the signal and reduces the distortion phenomenon caused by Fourier transform.
Description
Technical Field
The invention relates to the technical field of transformer voiceprint analysis, in particular to a transformer voiceprint analysis method and system.
Background
The transformer state real-time monitoring is one of key points of transformer operation and maintenance work, along with the development and construction of power equipment in China, more and more transformer substations adopt the inspection robot to carry out transformer state real-time monitoring, however, the inspection robot adopted by the transformer substations mostly carries out transformer state real-time monitoring through video data and image data, the monitoring result has errors usually because the data is too single, although the current transformer substation inspection robot basically configures a pickup to collect transformer operation voiceprint data, but because the research degree of the power industry on voiceprint analysis is lower, an effective voiceprint analysis method is not formed at present, and the transformer operation voiceprint data cannot be fully utilized.
Therefore, a transformer voiceprint analysis method and system are provided to solve the above problems.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a transformer voiceprint analysis method and system.
In order to achieve the purpose, the invention adopts the following technical scheme:
a transformer voiceprint analysis method comprises the following steps:
s1, arranging the optical fiber microphones on two sides of the transformer oil tank to collect acoustic signals from two directions;
s2, transmitting the collected acoustic signals to monitoring service equipment through a wireless network;
s3, framing the acoustic signals, and applying a Hamming window to each framed signal after framing;
s4, respectively extracting frequency spectrum and energy characteristic vectors of the acoustic signals by using fast Fourier transform and wavelet decomposition algorithms;
and S5, combining the frequency spectrum and energy eigenvector distribution characteristics obtained in the step S4, obtaining the change rule of the acoustic signal under each operation condition according to the characteristics of the transformer under different operation conditions, and diagnosing whether the transformer winding and the transformer iron core are in a normal state.
In the transformer voiceprint analysis method, in the step S3, when framing the acoustic signal, continuity between two adjacent frames of signals is ensured, there is an overlap between the two frames, and a framing relationship of the overlapped signals is represented as:
M-n-Lb/[ L (1-b) ], wherein: m is the frame number; n is the noise signal length; l is the frame length; b is the overlap ratio.
In the transformer voiceprint analysis method, after the voice signal is subjected to framing processing, a hamming window is applied to each framing signal, continuity of two ends of the signal is increased, and a distortion phenomenon caused by fourier transform in step S4 is reduced, wherein the hamming window formula is as follows:
In the transformer voiceprint analysis method, in step S4, 5-layer decomposition and reconstruction are performed on the acoustic signal by using a wavelet function, where the decomposition method is as follows:
(1) the first layer of decomposition divides the signal into a low frequency part a1, a high frequency part b1, and then retains b 1; continuously decomposing a1 to obtain a low-frequency part a2 and a high-frequency part b2, and reserving b 2; continuing to decompose a2, repeating the steps, taking b 1-b 5 after decomposition, extracting frequency band signals from low frequency to high frequency from the first layer to the fifth layer for characteristic analysis, and naming five high and low frequency coefficients obtained by wavelet decomposition as X k (t) (k ═ 1, 2, … 5), reconstructing the wavelet decomposition coefficients, using S k (t) represents X k (t) the total signal s (t) is then: s (t) ═ S 1 (t)+S 2 (t)+…+S 5 (t)；
(2) The total energy, S, of the signal in each frequency band is determined k Energy E corresponding to (t) k (wherein k is 1, 2, … 5) then:
(3) characteristic amount: constructing a feature vector by taking energy as an element, and expressing by Z: z ═ E 1 ，E 2 ，…E 5 ]And normalizing the feature vector Z to obtain:
wherein
And obtaining the energy characteristic vectors of the sound signals of the transformer under different operating conditions through the above formula, and obtaining the change rule of the sound signals under each operating condition.
Specifically, a total energy value E of the acoustic signal data is calculated k Total energy value E k All frequency domain voiceprint data values obtained by performing Fourier transform on the sound signal data in each acquisition period are respectively squared and then accumulated and summed, and then the energy value of the higher harmonic voiceprint data with the frequency of integral multiple of 100Hz is calculated, namely the frequency domain voiceprint data values with the frequency of integral multiple of 100 in the frequency domain voiceprint data obtained by performing Fourier transform are respectively squared and then accumulated and summed to obtain the energy value E of the higher harmonic voiceprint data k >100, respectively; if the specific gravity of the high-order harmonic energy exceeds the set initial threshold value by 20%, diagnosing that the transformer winding is in a loose fault state, otherwise, diagnosing that the transformer winding is in a normal state.
More specifically, an energy distribution matrix D in an acquisition period is constructed by using frequency domain acoustic signal data obtained by Fourier transform of acoustic signal data, wherein the D matrix is a 3N M matrix, and each row of the matrix corresponds to M frequency domain voiceprint data acquired by one sensor in the acquisition period; then, carrying out data preprocessing on the energy distribution matrix D, namely calculating the mean value of all values in the matrix, and then subtracting the mean value from all values in the matrix; then, calculating a covariance matrix C for the preprocessed energy distribution matrix D; and then obtaining a dimension position vector V of the first 3 important eigenvectors of the covariance matrix C through singular value decomposition, if the dimension position vector V is not equal to the historical reference value of the important dimension position vector, diagnosing that the transformer iron core is in a fault state, and otherwise, diagnosing that the transformer iron core is in a normal state.
In the transformer voiceprint analysis method, the acoustic signal is a relatively stable low-frequency signal, a pulse-shaped high-frequency unstable noise signal is mixed in the acoustic signal, the noise signal is overcome by adopting a layered denoising method, and the calculation formula is as follows:
A transformer voiceprint analysis system comprises an optical fiber voiceprint transmission device and monitoring service equipment:
the optical fiber sound transmission device comprises a sound acquisition module and a data transmission module, wherein the sound acquisition module is used for acquiring sound signals of the working of the transformer in real time; the data sending module is used for transmitting the acoustic signal to the monitoring service equipment through a wireless network;
the monitoring service equipment comprises a data receiving module, an acoustic signal preprocessing module, an acoustic signal function analysis module and an acoustic signal characteristic comparison module, wherein the data receiving module is used for receiving acoustic signals; the acoustic signal preprocessing module is used for performing framing and windowing preprocessing operations on the received acoustic signals; the sound signal function analysis module respectively extracts the frequency spectrum and the energy characteristic vector of sound by utilizing a fast Fourier transform and wavelet decomposition algorithm; and the acoustic signal characteristic comparison module is used for analyzing the characteristics of the transformer under different operating conditions and obtaining the change rule of the acoustic signal under each operating condition by combining the frequency spectrum and the energy characteristic vector distribution characteristics.
In the transformer voiceprint analysis system, the monitoring service device is further provided with a voiceprint signal denoising module, and the voiceprint signal denoising module is used for denoising the received voiceprint signal.
In the transformer voiceprint analysis system, a data storage module used for storing the acoustic signals is arranged in the monitoring service device, an acoustic signal sample database is arranged in the data storage module, and the acoustic signal characteristic comparison module is also used for comparing and analyzing the data storage module with the acoustic signal sample database to obtain the detection structure.
Compared with the prior art, the transformer voiceprint analysis method and system have the advantages that:
1. the invention carries out preprocessing on the collected signals, namely, frames are divided on the sound signals to ensure the continuity between two adjacent frames of signals, and after the framing processing, a Hamming window is applied to each frame signal and then the conversion operation is carried out, thereby increasing the continuity of two ends of the signals and reducing the distortion phenomenon caused by Fourier transform.
2. The invention carries out noise elimination processing on the noise in the acoustic signal to ensure the quality of acoustic signal analysis, and carries out multilayer decomposition and reconstruction on the acoustic signal through Fourier transform and wavelet function to correspondingly calculate the voiceprint value so as to be helpful for judging the use state of the transformer winding.
Drawings
FIG. 1 is a schematic diagram of the steps of a transformer voiceprint analysis method and system according to the present invention;
fig. 2 is a system structure block diagram of a transformer voiceprint analysis method and system provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example (b):
referring to fig. 1-2, the present embodiment provides a transformer voiceprint analysis method, including the following steps:
s1, arranging the optical fiber microphones on two sides of the transformer oil tank to collect acoustic signals from two directions;
s2, transmitting the collected acoustic signals to monitoring service equipment through a wireless network;
s3, framing the acoustic signals, and applying a Hamming window to each framed signal after framing;
s4, respectively extracting frequency spectrum and energy characteristic vectors of the acoustic signals by using fast Fourier transform and wavelet decomposition algorithms;
and S5, combining the frequency spectrum and the energy characteristic vector distribution characteristics obtained in the step S4, and obtaining the change rule of the acoustic signal under each operation condition according to the characteristics of the transformer under different operation conditions.
In step S3, when framing the acoustic signal, continuity between two adjacent frames of signals is ensured, there is an overlap between the two frames, and the relationship of the overlapped signal framing is represented as:
M-n-Lb/[ L (1-b) ], wherein: m is the frame number; n is the noise signal length; l is the frame length; b is the overlapping rate, 20-30 ms is usually taken as one frame in voiceprint recognition, and the frame length can be increased appropriately to obtain higher accuracy, in the embodiment, the frame length is taken as 100ms, and the overlapping rate is taken as 40%.
After the sound signal is subjected to framing processing, a Hamming window is applied to each framing signal for retransformation, the continuity of two ends of the signal is increased, and the distortion phenomenon caused by Fourier transform in the step S4 is reduced, wherein the Hamming window formula is as follows:
In step S4, 5-layer decomposition and reconstruction are performed on the acoustic signal by using a wavelet function, where the decomposition method is as follows:
(1) the first layer of decomposition divides the signal into a low frequency part a1, a high frequency part b1, and then retains b 1; continuously decomposing a1 to obtain a low-frequency part a2 and a high-frequency part b2, and reserving b 2; continuing to decompose a2, and repeating the above steps, taking b 1-b 5 after decomposition, specifically, the frequency ranges (unit: Hz) contained in each frequency band of b 1-b 5 are (12.5 k-25.5 k), (6.5 k-12.5 k), (3.5 k-6.5 k), (1.6 k-3.2 k) and (900-1500), extracting frequency band signals from low frequency to high frequency from the first layer to the fifth layer for feature analysis, and naming five high and low frequency coefficients obtained by wavelet decomposition as X and low frequency coefficients k (t) (k ═ 1, 2, … 5), reconstructing the wavelet decomposition coefficients, using S k (t) represents X k (t) the total signal s (t) is then: s (t) ═ S 1 (t)+S 2 (t)+…+S 5 (t)；
(2) The total energy, S, of the signal in each frequency band is determined k Energy E corresponding to (t) k (wherein k is 1, 2, … 5) then:
(3) characteristic amount: constructing a feature vector by taking energy as an element, and expressing by Z: z ═ E 1 ，E 2 ，…E 5 ]And normalizing the feature vector Z to obtain:
wherein
And obtaining the energy characteristic vectors of the sound signals of the transformer under different operating conditions through the above formula, and obtaining the change rule of the sound signals under each operating condition.
Specifically, a total energy value E of the acoustic signal data is calculated k Total energy value E k All frequency domain voiceprint data values obtained by performing Fourier transform on the acoustic signal data in each acquisition period are respectively squared and then accumulated and summed, and then the energy value of the higher harmonic voiceprint data with the frequency of integral multiple of 100Hz is calculated, namely, the frequency domain voiceprint data values with the frequency of integral multiple of 100 in the frequency domain voiceprint data obtained by the Fourier transform are respectively squared and then accumulated and summed to obtain the energy value E of the higher harmonic voiceprint data k >100, respectively; if the specific gravity of the high-order harmonic energy exceeds the set initial threshold value by 20%, diagnosing that the transformer winding is in a loose fault state, otherwise, diagnosing that the transformer winding is in a normal state;
more specifically, an energy distribution matrix D in an acquisition period is constructed by using frequency domain acoustic signal data obtained by Fourier transform of acoustic signal data, wherein the D matrix is a 3N M matrix, and each row of the matrix corresponds to M frequency domain voiceprint data acquired by one sensor in the acquisition period; then, carrying out data preprocessing on the energy distribution matrix D, namely calculating the mean value of all values in the matrix, and then subtracting the mean value from all values in the matrix; then, calculating a covariance matrix C for the preprocessed energy distribution matrix D; and then obtaining a dimension position vector V of the first 3 important eigenvectors of the covariance matrix C through singular value decomposition, if the dimension position vector V is not equal to the historical reference value of the important dimension position vector, diagnosing that the transformer iron core is in a fault state, and otherwise, diagnosing that the transformer iron core is in a normal state.
Furthermore, the acoustic signal is comparatively steady low frequency signal, can be mingled with the unstable noise signal of pulse form high frequency in the acoustic signal, and noise signal adopts the mode of layering noise elimination to overcome, and its computational formula is:
Referring to fig. 1-2, a transformer voiceprint analysis system comprising: the optical fiber sound transmission device comprises a sound acquisition module and a data transmission module, wherein the sound acquisition module is used for acquiring sound signals of the working of the transformer in real time; the data sending module is used for transmitting the acoustic signal to the monitoring service equipment through a wireless network; the monitoring service equipment comprises a data receiving module, an acoustic signal preprocessing module, an acoustic signal function analysis module and an acoustic signal characteristic comparison module, wherein the data receiving module is used for receiving acoustic signals; the acoustic signal preprocessing module is used for performing framing and windowing preprocessing operations on the received acoustic signals; the sound signal function analysis module respectively extracts the frequency spectrum and the energy characteristic vector of sound by utilizing a fast Fourier transform and wavelet decomposition algorithm; and the acoustic signal characteristic comparison module is used for analyzing the characteristics of the transformer under different operating conditions and obtaining the change rule of the acoustic signal under each operating condition by combining the frequency spectrum and the energy characteristic vector distribution characteristics.
The monitoring service equipment is further internally provided with a data storage module for storing the acoustic signals, the data storage module is internally provided with an acoustic signal sample database, and the acoustic signal characteristic comparison module is also used for comparing and analyzing the acoustic signal sample database to obtain a detection structure.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention and the equivalent alternatives or modifications according to the technical solution and the inventive concept of the present invention within the technical scope of the present invention.
Claims (10)
1. A transformer voiceprint analysis method is characterized by comprising the following steps:
s1, arranging the optical fiber microphones on two sides of the transformer oil tank to collect acoustic signals from two directions;
s2, transmitting the collected acoustic signals to monitoring service equipment through a wireless network;
s3, framing the acoustic signals, and applying a Hamming window to each framed signal after framing;
s4, respectively extracting frequency spectrum and energy characteristic vectors of the acoustic signals by using fast Fourier transform and wavelet decomposition algorithms;
and S5, combining the frequency spectrum and energy eigenvector distribution characteristics obtained in the step S4, obtaining the change rule of the acoustic signal under each operation condition according to the characteristics of the transformer under different operation conditions, and diagnosing whether the transformer winding and the transformer iron core are in a normal state.
2. The transformer voiceprint analysis method according to claim 1, wherein in step S3, when framing the acoustic signal, continuity between two adjacent frames is ensured, there is an overlap between the two frames, and the relationship between the overlapped frames is expressed as: M-n-Lb/[ L (1-b) ], wherein: m is the frame number; n is the noise signal length; l is the frame length; b is the overlap ratio.
3. The transformer voiceprint analysis method according to claim 1, wherein in step S3, a hamming window is applied to each framed signal after the framing processing of the acoustic signal, so as to increase the continuity of both ends of the signal and reduce the distortion caused by the fourier transform in step S4, and the hamming window formula is:
wherein A is the Hamming window length.
4. The transformer voiceprint analysis method according to claim 1, wherein in step S4, 5-layer decomposition and reconstruction are performed on the acoustic signal by using wavelet function, and the decomposition method is as follows:
(1) the first layer of decomposition divides the signal into a low frequency part a1, a high frequency part b1, and then retains b 1; continuously decomposing the a1 to obtain a low-frequency part a2 and a high-frequency part b2, and reserving b 2; continuing to decompose a2, repeating the steps, taking b 1-b 5 after decomposition, extracting frequency band signals from low frequency to high frequency from the first layer to the fifth layer for characteristic analysis, and naming five high and low frequency coefficients obtained by wavelet decomposition as X k (t) (k ═ 1, 2, … 5), reconstructing the wavelet decomposition coefficients, using S k (t) represents X k (t) the total signal s (t) is then: s (t) ═ S 1 (t)+S 2 (t)+…+S 5 (t)；
(2) The total energy, S, of the signal in each frequency band is determined k Energy E corresponding to (t) k (wherein k is 1, 2, … 5) then:
(3) characteristic amount: constructing a feature vector by taking energy as an element, and expressing by Z: z ═ E 1 ，E 2 ，…E 5 ]And normalizing the feature vector Z to obtain:
wherein
The energy characteristic vectors of the sound signals of the transformer under different operating conditions are obtained through the above formula, and the sound signals under each operating condition are obtainedThe change rule of the numbers.
5. The transformer voiceprint analysis method according to claim 1, wherein the acoustic signal is a relatively stable low-frequency signal, a pulse-shaped high-frequency unstable noise signal is mixed in the acoustic signal, the noise signal is overcome by adopting a layered noise elimination mode, and a calculation formula is as follows:
where N is the preset noise power, J is the maximum scale taken and is taken as constant 2, and a is the maximum extremum amplitude.
6. The transformer voiceprint analysis method according to claim 1, wherein the method for diagnosing the winding state of the transformer in step S5 is as follows: calculating a total energy value E of acoustic signal data k Total energy value E k All frequency domain voiceprint data values obtained by performing Fourier transform on the sound signal data in each acquisition period are respectively squared and then accumulated and summed, and then the energy value of the higher harmonic voiceprint data with the frequency of integral multiple of 100Hz is calculated, namely the frequency domain voiceprint data values with the frequency of integral multiple of 100 in the frequency domain voiceprint data obtained by performing Fourier transform are respectively squared and then accumulated and summed to obtain the energy value E of the higher harmonic voiceprint data k >100, respectively; if the specific gravity of the high-order harmonic energy exceeds the set initial threshold value by 20%, diagnosing that the transformer winding is in a loose fault state, otherwise, diagnosing that the transformer winding is in a normal state.
7. The transformer voiceprint analysis method according to claim 1, wherein the method for analyzing the state of the transformer core in step S5 is as follows: constructing an energy distribution matrix D in an acquisition period from frequency domain acoustic signal data obtained by Fourier transform, wherein the matrix D is a 3N M matrix, and each row of the matrix corresponds to M frequency domain voiceprint data acquired by one sensor in the acquisition period; then, carrying out data preprocessing on the energy distribution matrix D, namely calculating the mean value of all values in the matrix, and then subtracting the mean value from all values in the matrix; then, calculating a covariance matrix C for the preprocessed energy distribution matrix D; and then obtaining a dimension position vector V of the first 3 important eigenvectors of the covariance matrix C through singular value decomposition, if the dimension position vector V is not equal to the historical reference value of the important dimension position vector, diagnosing that the transformer iron core is in a fault state, and otherwise, diagnosing that the transformer iron core is in a normal state.
8. The transformer voiceprint analysis system is characterized by comprising an optical fiber voiceprint transmission device and monitoring service equipment:
the optical fiber sound transmission device comprises a sound acquisition module and a data transmission module, wherein the sound acquisition module is used for acquiring sound signals of the working of the transformer in real time; the data sending module is used for transmitting the acoustic signal to the monitoring service equipment through a wireless network;
the monitoring service equipment comprises a data receiving module, an acoustic signal preprocessing module, an acoustic signal function analysis module and an acoustic signal characteristic comparison module, wherein the data receiving module is used for receiving acoustic signals; the acoustic signal preprocessing module is used for performing framing and windowing preprocessing operations on the received acoustic signals; the sound signal function analysis module respectively extracts the frequency spectrum and the energy characteristic vector of sound by utilizing a fast Fourier transform and wavelet decomposition algorithm; and the acoustic signal characteristic comparison module is used for analyzing the characteristics of the transformer under different operating conditions and obtaining the change rule of the acoustic signal under each operating condition by combining the frequency spectrum and the energy characteristic vector distribution characteristics.
9. The transformer voiceprint analysis system according to claim 6, wherein a voiceprint signal denoising module is further arranged in the monitoring service device, and the voiceprint signal denoising module is used for denoising the received voiceprint signal.
10. The transformer voiceprint analysis system according to claim 6, wherein a data storage module for storing the acoustic signal is arranged in the monitoring service device, a sample database of the acoustic signal is arranged in the data storage module, and the acoustic signal characteristic comparison module is further configured to compare and analyze the acoustic signal characteristic with the sample database of the acoustic signal to obtain the detection structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210514966.1A CN114966477A (en) | 2022-05-11 | 2022-05-11 | Transformer voiceprint analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210514966.1A CN114966477A (en) | 2022-05-11 | 2022-05-11 | Transformer voiceprint analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114966477A true CN114966477A (en) | 2022-08-30 |
Family
ID=82981101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210514966.1A Pending CN114966477A (en) | 2022-05-11 | 2022-05-11 | Transformer voiceprint analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114966477A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115656341A (en) * | 2022-11-03 | 2023-01-31 | 江苏光微半导体有限公司 | Quantum sound wave sensor based on MEMS technology and array voiceprint system |
-
2022
- 2022-05-11 CN CN202210514966.1A patent/CN114966477A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115656341A (en) * | 2022-11-03 | 2023-01-31 | 江苏光微半导体有限公司 | Quantum sound wave sensor based on MEMS technology and array voiceprint system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740523B (en) | Power transformer fault diagnosis method based on acoustic features and neural network | |
| CN102426835B (en) | Method for identifying local discharge signals of switchboard based on support vector machine model | |
| Gokhale | ECG Signal De-noising using Discrete Wavelet Transform for removal of 50Hz PLI noise | |
| CN109507510A (en) | A kind of transformer fault diagnosis system | |
| CN114966477A (en) | Transformer voiceprint analysis method and system | |
| CN115376526A (en) | Power equipment fault detection method and system based on voiceprint recognition | |
| CN110426569A (en) | A kind of transformer acoustical signal noise reduction process method | |
| CN111912519A (en) | Transformer fault diagnosis method and device based on voiceprint frequency spectrum separation | |
| CN113257249A (en) | Power equipment fault diagnosis method, device and equipment based on voiceprint recognition | |
| CN114217149A (en) | Transformer acoustic fingerprint uninterrupted power detection and state early warning method | |
| CN115618213A (en) | Charger voltage disturbance analysis method, system, equipment and storage medium | |
| Geng et al. | Mechanical fault diagnosis of power transformer by GFCC time-frequency map of acoustic signal and convolutional neural network | |
| CN113866570A (en) | Voiceprint-based partial discharge monitoring method | |
| Kording et al. | Learning of sparse auditory receptive fields | |
| CN115389888B (en) | Partial discharge real-time monitoring system based on high-voltage cable | |
| Biswas et al. | Noise removing from ECG signal using FIR filter with windowing techniques | |
| CN111743535A (en) | Electroencephalogram abnormity monitoring method and system based on graph model | |
| CN114157023B (en) | Distribution transformer early warning information acquisition method | |
| CN109712639A (en) | A kind of audio collecting system and method based on wavelet filter | |
| CN115468751A (en) | Method and device for sound collection and defect identification of transformer | |
| WO2023060542A1 (en) | Bearing fault detection method and storage medium | |
| CN114295195A (en) | Method and system for judging abnormity of optical fiber sensing vibration signal based on feature extraction | |
| CN112274159B (en) | Compression domain electrocardiosignal quality assessment method based on improved band-pass filter | |
| CN110412366B (en) | Dynamic time algorithm-based transformer live-line detection method | |
| CN111932493A (en) | Power distribution network partial discharge ultrasonic detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |