CN112435686A - Power equipment fault voice recognition method based on data enhancement - Google Patents
Power equipment fault voice recognition method based on data enhancement Download PDFInfo
- Publication number
- CN112435686A CN112435686A CN202011304659.8A CN202011304659A CN112435686A CN 112435686 A CN112435686 A CN 112435686A CN 202011304659 A CN202011304659 A CN 202011304659A CN 112435686 A CN112435686 A CN 112435686A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- feature vector
- fault
- data enhancement
- audio samples
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000013598 vector Substances 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000009432 framing Methods 0.000 claims abstract description 7
- 238000005516 engineering process Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 19
- 230000005236 sound signal Effects 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000037433 frameshift Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a data enhancement-based power equipment fault voice recognition method, which comprises the following steps of: firstly, collecting audio samples of common power equipment faults and marking the audio samples; then, performing framing and windowing on the audio sample through preprocessing operation; then extracting a Mel cepstrum coefficient from the preprocessed audio sample as a feature vector; then, performing data enhancement on the extracted feature vector by using a mix up technology to construct a new feature vector; and finally, inputting the enhanced training set into a ResNet network for judgment, and identifying fault sounds of different power equipment. The electric power equipment fault voice recognition method based on data enhancement can effectively solve the problem of insufficient training data in an actual electric power equipment fault voice recognition system, and improves the generalization capability of the model. When the fault voice of the power equipment is identified, the method can obtain better identification effect.
Description
Technical Field
The invention relates to the technical field of signal processing and deep learning, in particular to a power equipment fault voice identification method based on data enhancement.
Background
The power equipment plays an important role in each production link of power generation, power transmission, power distribution and the like of a power system, and any one key power equipment in the power system fails to cause operation instability and even production interruption, so that huge economic loss is caused, catastrophic consequences are brought, and life and personal safety of people are threatened. Therefore, the development of a practical power equipment fault detection system is very important, the significance is that the limitation of preventive maintenance is broken, the risk analysis capability is improved, and a user of the detection system can see the detection parameter information of the equipment, the fault result obtained by parameter processing and analysis and the early warning report at any time. Maintenance personnel can timely obtain equipment fault early warning information to check and solve problems, reliability of power equipment is enhanced, and unplanned downtime of key equipment is greatly reduced.
In addition to signals that are traditionally and widely used for detection, as the capability of sound collection and processing technology improves, the concept of sound for detection of electric power equipment is also proposed by some scholars. The sound is the radiation energy of mechanical waves of the electrical equipment from vibration to a sound transmission medium, and the sound signal contains a large amount of vibration information and is an important index for analyzing the running state of the equipment. When the equipment normally runs, the sound emitted by the equipment is different corresponding to different states of mutual movement of the machine body, the firmware, the parts and the parts, and the sound generated by the power equipment is changed when the running state is changed. At present, the audio data amount of power equipment faults is increased, but audio samples with accurate labels are few, and a more diversified sample database needs to be constructed on limited samples with labels, so that the generalization capability of the classifier is improved. In order to solve the problem that the number of labeled power equipment fault sound samples is insufficient, a data enhancement method needs to be adopted, the diversity of training samples is enriched, and therefore the generalization capability of the model is improved. When the fault voice of the power equipment is identified, the method can obtain better identification effect.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for recognizing the fault sound of the power equipment based on data enhancement.
The invention is realized by the following technical scheme.
A power equipment fault voice recognition method based on data enhancement comprises the following steps:
collecting audio samples of common power equipment faults by using a sound sensor, marking, and then dividing a training set and a testing set according to a proportion;
respectively carrying out frame division and windowing preprocessing operations on the training set and the test set audio samples;
extracting a characteristic vector from the preprocessed audio sample;
performing data enhancement on the extracted feature vector to construct a new feature vector;
and inputting the enhanced feature vector set into a ResNet network for judgment, and identifying fault sounds of different power equipment.
Further, the collecting common power equipment fault audio samples by using the sound sensor, labeling, and then dividing the training set and the testing set according to the proportion includes:
collecting audio samples of common power equipment faults by using a sound sensor: under different fault conditions of the power equipment, recording audio samples of corresponding fault conditions, wherein the sampling rate is 44100Hz, and the frequency range is 20-20000 Hz.
Dividing a training set and a testing set according to a proportion: and (4) marking the marked audio samples according to the following steps: the scale of 1 is randomly divided into a training set and a test set.
Further, the pre-processing operations of framing and windowing the training set and the test set audio samples respectively include:
framing: the audio samples are sliced into 25ms segments with a frame shift of 10 ms.
Windowing: windowing is performed on each frame of audio signal using a hamming window.
Further, the extracting the feature vector from the preprocessed audio sample includes:
and extracting 20-dimensional Mel cepstrum coefficients from each preprocessed frame of audio signal to serve as a feature vector of one frame, and averaging the 20-dimensional Mel cepstrum coefficients of the adjacent 10 frames of audio signals to form a new feature vector.
Further, the data enhancement of the extracted feature vector and the construction of a new feature vector include:
and performing data enhancement on the extracted feature vector by using a mix up technology to construct a new feature vector.
Further, the inputting the enhanced feature vector set into a ResNet network for decision, and identifying fault sounds of different power devices includes:
a ResNet network architecture is built, an activation function of network training adopts a tanh function, and the training process of the network is to obtain the minimum value through a loss function combining back propagation and gradient descent. And after training and debugging the network structure parameters to be optimal, repeating the steps of preprocessing and feature extraction on the test set sample, inputting the feature vector into a ResNet network to obtain the corresponding probability of each fault sound, and taking the fault with the highest probability as the recognition result of the audio sample.
Due to the adoption of the technical scheme, the invention has at least one of the following beneficial effects:
the ResNet network is applied to the electric power equipment fault sound recognition, an acoustic-based electric power equipment fault diagnosis model can be effectively established, and the recognition effect is better compared with the traditional support vector machine, random forest and other shallow classifiers.
The invention enhances the data of the available limited fault audio samples, enriches the diversity of the samples and improves the generalization capability of the classifier. In addition, the data enhancement also mines potential features among fault audio data, and the recognition effect is more excellent.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for recognizing a fault sound of an electrical device based on data enhancement according to the present invention.
Detailed Description
The following examples illustrate the invention in detail: the embodiment is implemented on the premise of the technical scheme of the invention, and a detailed implementation mode and a specific operation process are given. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Examples
A method for recognizing a fault sound of power equipment based on data enhancement can effectively solve the problem of insufficient training data in an actual power equipment fault sound recognition system and improve the generalization capability of a model. When the fault voice of the power equipment is identified, the method can obtain better identification effect.
As shown in fig. 1, the method comprises the steps of:
step 1, collecting audio samples of common power equipment faults by using a sound sensor, marking the audio samples, and then dividing a training set and a testing set according to a proportion.
In this embodiment, the step specifically includes the following steps:
step 1.1, recording audio samples of corresponding fault conditions through a non-contact sound acquisition system under different fault conditions of the power equipment, wherein the sampling rate is 44100Hz, and the frequency range is 20-20000 Hz.
Step 1.2, dividing a training set and a testing set according to a proportion: and (3) marking different fault audio samples by adopting numbers of 0-9, and randomly dividing the marked samples into a training set and a testing set according to the ratio of 4: 1.
Step 2, respectively carrying out frame division and windowing pretreatment operations on the audio samples of the training set and the test set;
in this embodiment, the step specifically includes the following steps:
step 2.1, framing: a plurality of sampling points are grouped into an observation unit, which is called a sub-frame. The covered time is about as. An overlap region is provided between two adjacent frames, the overlap region includes a plurality of sampling points, and the covered time is about bs.
In the embodiment, the number of sampling points is 400; the covered time is 0.025 s; the overlap region contains 160 sampling points covering 0.01 s.
And 2.2, windowing each frame of audio signal by using a Hamming window. The Hamming window function is expressed as:
in the formula, N represents the frame length, alpha is a window function parameter and is generally 0.46;
step 3, extracting feature vectors from the preprocessed audio samples, and specifically comprising the following steps:
and 3.1, performing fast Fourier transform on each frame signal subjected to framing and windowing to obtain a frequency spectrum of each frame, and performing modular squaring on the frequency spectrum of the sound signal (sound sample) to obtain a power spectrum of the sound signal.
Setting sound signal Xa(k) The DFT of (1) is:
where k denotes the kth frequency of the fourier transform, x (N) denotes an input speech signal, and N denotes the number of points of the fourier transform.
Step 3.2, passing the energy spectrum through a group of Mel-scale triangular filter banks, wherein the frequency response H of the triangular filter banksm(k) Comprises the following steps:
Step 3.3, calculating the logarithmic energy s (m) output by each filter bank, wherein the form is as follows:
step 3.4, obtaining the MFCC coefficient C (n) through Discrete Cosine Transform (DCT) in the form of:
step 3.5, averaging 20-dimensional Mel cepstrum coefficients of adjacent 10 frames of signals to form a new feature vector:
in the formula xiA 20-dimensional mel-frequency cepstral coefficient feature vector representing the ith frame, i 1, 2.
And 4, performing data enhancement on the extracted feature vector to construct a new feature vector, and specifically comprising the following steps of:
and performing data enhancement on the extracted feature vector by using a mix up technology to construct a new feature vector:
y=λyi+(1-λyj) (7)
in the formula (x)i,yi) And (x)j,yj) Are two samples, x, randomly drawn from the training dataiAnd xjFeature vector, y, representing a sampleiAnd yjIs the label corresponding to the sample.Representing the new training sample that is generated,the feature vector representing the new sample, y representing the corresponding new label; and lambda belongs to [0.1 ∈ ]]。
Step 5, inputting the enhanced feature vector set into a ResNet network for judgment, and identifying fault sounds of different power equipment, specifically comprising the following steps:
step 5.1, building a ResNet network architecture, wherein an activation function of network training adopts a Relu function:
the training process of the network is to obtain the minimum value through combining the back propagation and the gradient descent and is a loss function. Specific training methods references: he K, Zhang X, Ren S, et al. deep reactive Learning for Image Recognition [ J ]. 2015.
And 5.2, after training and debugging the network structure parameters to be optimal, repeating the steps of preprocessing and feature extraction on the test set sample, inputting the feature vector into the network to obtain the corresponding probability of each fault sound, and taking the fault with the highest probability as the recognition result of the audio sample so as to judge whether the equipment has faults and give the fault type.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.
Claims (6)
1. A method for recognizing fault sounds of power equipment based on data enhancement is characterized by comprising the following steps:
the method comprises the following steps of collecting audio samples of common power equipment faults by using a sound sensor, marking the audio samples, and then according to n: 1, dividing a training set and a test set in proportion;
respectively carrying out frame division and windowing preprocessing operations on the training set and the test set audio samples;
extracting a characteristic vector from the preprocessed audio sample;
performing data enhancement on the extracted feature vector to construct a new feature vector;
and inputting the new feature vector set into a ResNet network for judgment, and identifying fault sounds of different power equipment.
2. The method for recognizing the fault sound of the power equipment based on the data enhancement is characterized in that a sound sensor is used for collecting audio samples of common fault sound of the power equipment, the audio samples are labeled, and then a training set and a testing set are divided according to the proportion, and the method comprises the following steps of:
collecting audio samples of common power equipment faults by using a sound sensor: under different fault conditions of the power equipment, recording audio samples of corresponding fault conditions, wherein the sampling rate is 44100Hz, and the frequency range is 20-20000 Hz.
Dividing a training set and a testing set according to a proportion: and (4) marking the marked audio samples according to the following steps: the scale of 1 is randomly divided into a training set and a test set.
3. The method for voice recognition of power equipment failure based on data enhancement as claimed in claim 1, wherein the pre-processing operations of framing and windowing the training set and test set audio samples respectively comprise:
framing: the audio samples are sliced into 25ms segments with a frame shift of 10 ms.
Windowing: windowing each frame of audio signal with a hamming window.
4. The method for recognizing the fault sound of the power equipment based on the data enhancement is characterized in that the step of extracting the feature vector from the preprocessed audio sample comprises the following steps:
and extracting 20-dimensional Mel cepstrum coefficients from each preprocessed frame of audio signal to serve as a feature vector of one frame, averaging the 20-dimensional Mel cepstrum coefficients of adjacent N frames of audio signals to form a new feature vector, wherein N is generally 5-15.
5. The method for recognizing the fault voice of the power equipment based on the data enhancement is characterized in that the data enhancement of the extracted feature vector to construct a new feature vector comprises the following steps:
and performing data enhancement on the extracted feature vector by using a mix up technology to construct a new feature vector.
6. The method for recognizing the fault sound of the electric power equipment based on the data enhancement as claimed in claim 1, wherein the step of inputting the enhanced feature vector set into a ResNet network for decision to recognize the fault sound of different electric power equipment comprises the following steps:
a ResNet network architecture is built, an activation function of network training adopts a tanh function, and the training process of the network is to obtain the minimum value through a loss function combining back propagation and gradient descent. And after training and debugging the network structure parameters to be optimal, repeating the steps of preprocessing and feature extraction on the test set sample, inputting the feature vector into a ResNet network to obtain the corresponding probability of each fault sound, and taking the fault with the highest probability as the recognition result of the audio sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011304659.8A CN112435686A (en) | 2020-11-19 | 2020-11-19 | Power equipment fault voice recognition method based on data enhancement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011304659.8A CN112435686A (en) | 2020-11-19 | 2020-11-19 | Power equipment fault voice recognition method based on data enhancement |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112435686A true CN112435686A (en) | 2021-03-02 |
Family
ID=74694508
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011304659.8A Pending CN112435686A (en) | 2020-11-19 | 2020-11-19 | Power equipment fault voice recognition method based on data enhancement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112435686A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113033490A (en) * | 2021-04-23 | 2021-06-25 | 山东省计算中心(国家超级计算济南中心) | Industrial equipment general fault detection method and system based on sound signals |
CN113314144A (en) * | 2021-05-19 | 2021-08-27 | 中国南方电网有限责任公司超高压输电公司广州局 | Voice recognition and power equipment fault early warning method, system, terminal and medium |
CN113327629A (en) * | 2021-05-06 | 2021-08-31 | 上海交通大学 | Power equipment sound diagnosis method and system |
CN113551765A (en) * | 2021-08-17 | 2021-10-26 | 中冶北方(大连)工程技术有限公司 | Sound spectrum analysis and diagnosis method for equipment fault |
CN113553465A (en) * | 2021-06-15 | 2021-10-26 | 深圳供电局有限公司 | Sound data storage method and device, computer equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109599126A (en) * | 2018-12-29 | 2019-04-09 | 广州丰石科技有限公司 | A kind of sound fault recognition method based on mel energy spectrum and convolutional neural networks |
CN109978034A (en) * | 2019-03-18 | 2019-07-05 | 华南理工大学 | A kind of sound scenery identification method based on data enhancing |
CN110808068A (en) * | 2019-11-11 | 2020-02-18 | 北京软通智城科技有限公司 | Sound detection method, device, equipment and storage medium |
CN110930995A (en) * | 2019-11-26 | 2020-03-27 | 中国南方电网有限责任公司 | Voice recognition model applied to power industry |
CN110940539A (en) * | 2019-12-03 | 2020-03-31 | 桂林理工大学 | Machine equipment fault diagnosis method based on artificial experience and voice recognition |
-
2020
- 2020-11-19 CN CN202011304659.8A patent/CN112435686A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109599126A (en) * | 2018-12-29 | 2019-04-09 | 广州丰石科技有限公司 | A kind of sound fault recognition method based on mel energy spectrum and convolutional neural networks |
CN109978034A (en) * | 2019-03-18 | 2019-07-05 | 华南理工大学 | A kind of sound scenery identification method based on data enhancing |
CN110808068A (en) * | 2019-11-11 | 2020-02-18 | 北京软通智城科技有限公司 | Sound detection method, device, equipment and storage medium |
CN110930995A (en) * | 2019-11-26 | 2020-03-27 | 中国南方电网有限责任公司 | Voice recognition model applied to power industry |
CN110940539A (en) * | 2019-12-03 | 2020-03-31 | 桂林理工大学 | Machine equipment fault diagnosis method based on artificial experience and voice recognition |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113033490A (en) * | 2021-04-23 | 2021-06-25 | 山东省计算中心(国家超级计算济南中心) | Industrial equipment general fault detection method and system based on sound signals |
CN113033490B (en) * | 2021-04-23 | 2023-09-19 | 山东省计算中心(国家超级计算济南中心) | Industrial equipment general fault detection method and system based on sound signals |
CN113327629A (en) * | 2021-05-06 | 2021-08-31 | 上海交通大学 | Power equipment sound diagnosis method and system |
CN113314144A (en) * | 2021-05-19 | 2021-08-27 | 中国南方电网有限责任公司超高压输电公司广州局 | Voice recognition and power equipment fault early warning method, system, terminal and medium |
CN113553465A (en) * | 2021-06-15 | 2021-10-26 | 深圳供电局有限公司 | Sound data storage method and device, computer equipment and storage medium |
CN113553465B (en) * | 2021-06-15 | 2023-12-19 | 深圳供电局有限公司 | Sound data warehousing method, device, computer equipment and storage medium |
CN113551765A (en) * | 2021-08-17 | 2021-10-26 | 中冶北方(大连)工程技术有限公司 | Sound spectrum analysis and diagnosis method for equipment fault |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112435686A (en) | Power equipment fault voice recognition method based on data enhancement | |
CN108831485A (en) | Method for distinguishing speek person based on sound spectrograph statistical nature | |
CN101923855A (en) | Test-irrelevant voice print identifying system | |
CN111724770B (en) | Audio keyword identification method for generating confrontation network based on deep convolution | |
CN106941005A (en) | A kind of vocal cords method for detecting abnormality based on speech acoustics feature | |
CN105895078A (en) | Speech recognition method used for dynamically selecting speech model and device | |
CN109192222A (en) | A kind of sound abnormality detecting system based on deep learning | |
CN113566948A (en) | Fault audio recognition and diagnosis method for robot coal pulverizer | |
CN102201237B (en) | Emotional speaker identification method based on reliability detection of fuzzy support vector machine | |
CN109785857A (en) | Abnormal sound event recognition method based on MFCC+MP fusion feature | |
CN105244038A (en) | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM | |
CN110070895A (en) | A kind of mixed sound event detecting method based on supervision variation encoder Factor Decomposition | |
CN105810212A (en) | Train whistle recognizing method for complex noise environment | |
Kim et al. | Hierarchical approach for abnormal acoustic event classification in an elevator | |
CN105810191A (en) | Prosodic information-combined Chinese dialect identification method | |
CN110085216A (en) | A kind of vagitus detection method and device | |
Gong et al. | Vocalsound: A dataset for improving human vocal sounds recognition | |
CN112599134A (en) | Transformer sound event detection method based on voiceprint recognition | |
CN110570870A (en) | Text-independent voiceprint recognition method, device and equipment | |
CN110782902A (en) | Audio data determination method, apparatus, device and medium | |
CN114373452A (en) | Voice abnormity identification and evaluation method and system based on deep learning | |
CN115101076B (en) | Speaker clustering method based on multi-scale channel separation convolution feature extraction | |
CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
CN114352486A (en) | Wind turbine generator blade audio fault detection method based on classification | |
CN116778956A (en) | Transformer acoustic feature extraction and fault identification method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210302 |