CN117746903A - Voiceprint monitoring and diagnosing method based on wind power failure knowledge base - Google Patents
Voiceprint monitoring and diagnosing method based on wind power failure knowledge base Download PDFInfo
- Publication number
- CN117746903A CN117746903A CN202311773639.9A CN202311773639A CN117746903A CN 117746903 A CN117746903 A CN 117746903A CN 202311773639 A CN202311773639 A CN 202311773639A CN 117746903 A CN117746903 A CN 117746903A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- wind power
- knowledge base
- monitoring
- method based
- 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 34
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 230000005540 biological transmission Effects 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 238000000926 separation method Methods 0.000 claims abstract description 4
- 230000001629 suppression Effects 0.000 claims abstract description 4
- 238000003745 diagnosis Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 5
- 238000012552 review Methods 0.000 claims description 5
- 238000010977 unit operation Methods 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000010248 power generation Methods 0.000 abstract description 4
- 230000033228 biological regulation Effects 0.000 abstract description 2
- 230000002035 prolonged effect Effects 0.000 abstract description 2
- 230000001105 regulatory effect Effects 0.000 abstract description 2
- 238000009434 installation Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base, which belongs to the technical field of wind power equipment monitoring and comprises the following steps: voiceprint acquisition terminals are arranged at the bottom of a tower barrel of the wind power generator and in a cabin, voiceprint detection terminals arranged in the cabin are used for voiceprint detection of transmission chain equipment, voiceprint detection terminals arranged at the bottom of the tower barrel are used for blade damage detection, the microphones electrically connected with the voiceprint detection modules are used for acquiring the sound of the equipment during operation, the collected sound is filtered through the noise suppression algorithm, the sound source enhancement algorithm and the blind source separation algorithm of the voiceprint filtering module, the prediction result is fed back to the cloud server and operation and maintenance personnel to realize remote monitoring and control, and meanwhile, the fan is regulated and controlled through the control system, such as the fan rotating speed regulation, the fan start and stop control and the like, so that the fan is ensured to work in an optimal running state, the service life of the fan is prolonged, and the power generation efficiency is improved.
Description
Technical Field
The invention relates to the technical field of wind power equipment monitoring, in particular to a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base.
Background
With the rapid development of new energy industry in China, the wind power generation scale is increasingly enlarged, 3.5 hundred million kilowatts are broken through by the wind power installation in China by the end of 2022, and the number of wind power generation sets reaches 16 ten thousand. In addition, according to the planning, by 2025, the domestic wind power installation can reach 6 hundred million kilowatts, and the number of wind turbine generators can break through 22 ten thousand.
When the existing wind power fails, the failure point is difficult to detect, and is not easy to detect, and when the failure point is detected, workers are required to enter for maintenance, so that the efficiency is affected, and meanwhile, reasonable evaluation and maintenance advice cannot be given for the failure point.
Therefore, the invention provides a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base.
Disclosure of Invention
The present invention has been made in view of the above and/or problems occurring in the prior art of voiceprint monitoring and diagnosing methods based on a wind power failure knowledge base.
Therefore, the invention aims to provide a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base, which can solve the above-mentioned existing problems.
In order to solve the technical problems, according to one aspect of the present invention, the following technical solutions are provided:
a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base comprises the following steps: the method comprises the following steps: the method comprises the steps that voiceprint acquisition terminals are arranged at the bottom of a tower barrel of a wind power generator and in a cabin, voiceprint detection terminals arranged in the cabin are used for voiceprint detection of transmission chain equipment, the voiceprint detection terminals arranged at the bottom of the tower barrel are used for blade damage detection, sound generated during equipment operation is acquired through microphones electrically connected with each voiceprint detection module, the acquired sound is filtered through a noise suppression algorithm, a sound source enhancement algorithm and a blind source separation algorithm of a voiceprint filtering module, noise is reduced, the noise is transmitted to a sink control cabinet through a signal acquisition module, and the collected voiceprint characteristics of each motor are stored in a voiceprint characteristic library through the sink control cabinet.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: deep learning algorithms, such as Convolutional Neural Networks (CNNs), long and short time memory networks (LSTMs) and the like, are adopted to model and train voiceprint features, and fan fault diagnosis and prediction models are constructed.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: the established voiceprint recognition model is deployed on a cloud server, fault diagnosis and prediction service is provided through an API interface, and when the voiceprint recognition model is used, characterization parameter data in the running process of a unit are collected, transmitted and stored, and collected voiceprints are compared with voiceprints in a voiceprint feature library in real time.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: and analyzing and evaluating the state of each item of data based on the constructed algorithm model, so as to detect and early warn the health state of the unit operation.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: when a fault occurs, fault judgment and operation adjustment suggestions based on root cause analysis and diagnosis of each item of data are given.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: and the early warning data, the fault type predicted by the algorithm construction model and the processing advice are transmitted to the cloud end, so that the early warning data is convenient for staff to review and reference, and meanwhile, the early warning record is stored by the storage module.
As a preferable scheme of the voiceprint monitoring and diagnosing method based on the wind power failure knowledge base, the invention comprises the following steps: the voiceprint detection terminals arranged at the bottom of the tower cylinder are used for detecting blade damage, four voiceprint detection modules are uniformly distributed around the bottom of the tower cylinder, the voiceprint acquisition array is ensured to be positioned right below the windward side of the impeller and perpendicular to the rotating plane of the blade, and the voiceprint acquisition array is fixedly arranged in a stand column or cylinder wall bracket mode.
As a preferable scheme of the voiceprint detection and diagnosis method based on the wind power failure knowledge base, the invention comprises the following steps: the voiceprint detection module is two meters away from the ground level, four points are equally distributed around the voiceprint detection module for installation and fixation, whistle is collected when the blade runs, and damage conditions of the blade are detected and analyzed.
Compared with the prior art:
1. the prediction result is fed back to the cloud server and operation and maintenance personnel to realize remote monitoring and control, and meanwhile, the fan is regulated and controlled through the control system, such as the fan rotating speed regulation, the fan start and stop control and the like, so that the fan is ensured to work in an optimal running state, the service life of the fan is prolonged, and the power generation efficiency is improved;
2. the collected data and the prediction result are visually displayed, real-time operation state monitoring, fault diagnosis and prediction are provided, operation and maintenance personnel can conveniently know the operation state of the fan in time, corresponding measures are taken for maintenance and repair, basic data are provided for subsequent data analysis and optimization, and the cost of data processing can be remarkably reduced.
Drawings
FIG. 1 is a network topology of a fan detection system of the present invention;
FIG. 2 is a block diagram of the inside of the voiceprint acquisition terminal of the present invention;
FIG. 3 is a flow chart of voiceprint acquisition contrast of the present invention;
FIG. 4 is a flow chart of voiceprint detection in accordance with the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
Embodiment one:
the invention provides a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base, which has the advantages of convenient use and improved detection efficiency, and referring to fig. 1-4, comprises the following steps: the method comprises the steps that voiceprint acquisition terminals are arranged at the bottom of a tower barrel of a wind power generator and in a cabin, voiceprint detection terminals arranged in the cabin are used for voiceprint detection of transmission chain equipment, the voiceprint detection terminals arranged at the bottom of the tower barrel are used for blade damage detection, sound generated during equipment operation is acquired through microphones electrically connected with each voiceprint detection module, the acquired sound is filtered through a noise suppression algorithm, a sound source enhancement algorithm and a blind source separation algorithm of a voiceprint filtering module, noise is reduced, the noise is transmitted to a sink control cabinet through a signal acquisition module, and the collected voiceprint characteristics of each motor are stored in a voiceprint characteristic library through the sink control cabinet.
Deep learning algorithms, such as Convolutional Neural Networks (CNNs), long and short time memory networks (LSTMs) and the like, are adopted to model and train voiceprint features, and fan fault diagnosis and prediction models are constructed.
The established voiceprint recognition model is deployed on a cloud server, fault diagnosis and prediction service is provided through an API interface, and when the voiceprint recognition model is used, characterization parameter data in the running process of a unit are collected, transmitted and stored, and collected voiceprints are compared with voiceprints in a voiceprint feature library in real time.
And analyzing and evaluating the state of each item of data based on the constructed algorithm model, so as to detect and early warn the health state of the unit operation.
When a fault occurs, fault judgment and operation adjustment suggestions based on root cause analysis and diagnosis of each item of data are given.
And the early warning data, the fault type predicted by the algorithm construction model and the processing advice are transmitted to the cloud end, so that the early warning data is convenient for staff to review and reference, and meanwhile, the early warning record is stored by the storage module.
When the system is specifically used, a person skilled in the art firstly obtains voiceprint characteristics of each motor during normal operation through a voiceprint acquisition terminal, stores the voiceprint characteristics in a voiceprint characteristic library, models and trains the voiceprint characteristics by adopting a deep learning algorithm such as a convolutional neural network, a long-short-term memory network and the like, and builds a fan fault diagnosis and prediction model, namely sets a preset interval for the floating of a voiceprint curve of the normal operation;
when the system is used, the collected voiceprints are compared with the stored data in the voiceprint feature library in real time, and the analysis and the state evaluation are carried out on each item of data through the constructed algorithm model, so that the health state of the unit operation is detected and early-warned.
When a fault occurs, fault judgment and operation adjustment suggestions based on root cause analysis and diagnosis of each item of data are given.
And the early warning data, the fault type predicted by the algorithm construction model and the processing advice are transmitted to the cloud end, so that the early warning data is convenient for staff to review and reference, and meanwhile, the early warning record is stored by the storage module.
Embodiment two:
the invention provides a voiceprint monitoring and diagnosing method based on a wind power failure knowledge base, referring to fig. 1-4, voiceprint detection terminals arranged at the bottom of a tower cylinder are used for detecting blade damage, four voiceprint detection modules are uniformly distributed around the bottom of the tower cylinder, a voiceprint acquisition array is ensured to be positioned right below the windward side of an impeller and vertical to a blade rotation plane, and the voiceprint acquisition array is fixedly arranged in a stand column or cylinder wall bracket mode.
The voiceprint detection module is two meters away from the ground level, four points are equally distributed around the voiceprint detection module for installation and fixation, whistle is collected when the blade runs, and damage conditions of the blade are detected and analyzed.
When the system is specifically used, a person skilled in the art firstly obtains voiceprint characteristics of each motor during normal operation through a voiceprint acquisition terminal, stores the voiceprint characteristics in a voiceprint characteristic library, models and trains the voiceprint characteristics by adopting a deep learning algorithm such as a convolutional neural network, a long-short-term memory network and the like, and builds a fan fault diagnosis and prediction model, namely sets a preset interval for the floating of a voiceprint curve of the normal operation;
when the system is used, the collected voiceprints are compared with the stored data in the voiceprint feature library in real time, and the analysis and the state evaluation are carried out on each item of data through the constructed algorithm model, so that the health state of the unit operation is detected and early-warned.
When a fault occurs, fault judgment and operation adjustment suggestions based on root cause analysis and diagnosis of each item of data are given.
And the early warning data, the fault type predicted by the algorithm construction model and the processing advice are transmitted to the cloud end, so that the early warning data is convenient for staff to review and reference, and meanwhile, the early warning record is stored by the storage module.
Although the invention has been described hereinabove with reference to embodiments, various modifications thereof may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the features of the disclosed embodiments may be combined with each other in any manner as long as there is no structural conflict, and the exhaustive description of these combinations is not given in this specification merely for the sake of omitting the descriptions and saving resources. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (8)
1. A voiceprint monitoring and diagnosing method based on a wind power failure knowledge base is characterized by comprising the following steps of: the method comprises the following steps: the method comprises the steps that voiceprint acquisition terminals are arranged at the bottom of a tower barrel of a wind power generator and in a cabin, voiceprint detection terminals arranged in the cabin are used for voiceprint detection of transmission chain equipment, the voiceprint detection terminals arranged at the bottom of the tower barrel are used for blade damage detection, sound generated during equipment operation is acquired through microphones electrically connected with each voiceprint detection module, the acquired sound is filtered through a noise suppression algorithm, a sound source enhancement algorithm and a blind source separation algorithm of a voiceprint filtering module, noise is reduced, the noise is transmitted to a sink control cabinet through a signal acquisition module, and the collected voiceprint characteristics of each motor are stored in a voiceprint characteristic library through the sink control cabinet.
2. The voiceprint monitoring and diagnosing method based on the wind power failure knowledge base according to claim 1, wherein a deep learning algorithm, such as a Convolutional Neural Network (CNN), a long-short-time memory network (LSTM) and the like, is adopted to model and train voiceprint characteristics, and a fan failure diagnosis and prediction model is constructed.
3. The voiceprint monitoring and diagnosing method based on the wind power failure knowledge base according to claim 2, wherein the established voiceprint recognition model is deployed on a cloud server, failure diagnosis and prediction services are provided through an API interface, and when the method is used, characterization parameter data in the running process of a unit are collected, transmitted and stored, and collected voiceprints are compared with voiceprints in a voiceprint feature library in real time.
4. The voiceprint monitoring and diagnosing method based on the wind power failure knowledge base according to claim 3, wherein the health state of the unit operation is detected and early-warned by analyzing and evaluating various data based on a constructed algorithm model.
5. The voiceprint monitoring and diagnosing method based on a wind power failure knowledge base according to claim 4, wherein when a failure occurs, failure judgment and operation adjustment advice based on root cause analysis and diagnosis of respective data are given.
6. The voiceprint monitoring and diagnosing method based on the wind power failure knowledge base according to claim 5, wherein the early warning data, the failure type predicted by the algorithm construction model and the processing advice are transmitted to the cloud end, so that the staff can conveniently review and refer to the data, and meanwhile, the early warning records are stored through the storage module.
7. The voiceprint monitoring and diagnosing method based on the wind power failure knowledge base according to claim 1, wherein the voiceprint detection terminals arranged at the bottom of the tower are used for detecting blade damage, four voiceprint detection modules are uniformly distributed around the bottom of the tower, the voiceprint acquisition array is ensured to be positioned right below the windward side of the impeller and perpendicular to the rotation plane of the blade, and the voiceprint acquisition array is fixedly arranged in a stand column or cylinder wall bracket mode.
8. The voiceprint detection and diagnosis method based on the wind power failure knowledge base according to claim 7, wherein the voiceprint detection module is two meters away from the ground horizontally, four points are equally divided around to install and fix, whistles during operation of the blade are collected, and damage conditions of the blade are detected and analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311773639.9A CN117746903A (en) | 2023-12-22 | 2023-12-22 | Voiceprint monitoring and diagnosing method based on wind power failure knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311773639.9A CN117746903A (en) | 2023-12-22 | 2023-12-22 | Voiceprint monitoring and diagnosing method based on wind power failure knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117746903A true CN117746903A (en) | 2024-03-22 |
Family
ID=90254324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311773639.9A Pending CN117746903A (en) | 2023-12-22 | 2023-12-22 | Voiceprint monitoring and diagnosing method based on wind power failure knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117746903A (en) |
-
2023
- 2023-12-22 CN CN202311773639.9A patent/CN117746903A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110469462B (en) | Wind turbine generator system intelligent state monitoring system based on multiple templates | |
| Cui et al. | An anomaly detection approach based on machine learning and scada data for condition monitoring of wind turbines | |
| CN103343728A (en) | Wind generating set remote on-line multi-mode health state monitoring and fault diagnosis system | |
| CN102434387A (en) | Draught fan detection and diagnosis system | |
| CN109209783A (en) | A kind of method and device of the lightning damage based on noise measuring blade | |
| CN112324629A (en) | Wind power blade early damage monitoring system and method based on vibration and sound | |
| CN110940518B (en) | Aerospace transmission mechanism analysis method based on fault data | |
| CN112067701B (en) | Fan blade remote auscultation method based on acoustic diagnosis | |
| CN202676203U (en) | Large-size pumping station state monitoring and diagnosing and energy efficiency management device | |
| CN104564542B (en) | A kind of fault diagnosis system and its diagnostic method based on big data technology | |
| CN111509847A (en) | Intelligent detection system and method for power grid unit state | |
| CN103674538A (en) | Multi-fault mode identification method and device of swashplate of helicopter | |
| CN111927717B (en) | System and method for online monitoring noise of transmission chain of fan engine room | |
| CN113551765A (en) | Sound spectrum analysis and diagnosis method for equipment fault | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN102288911B (en) | System and method for monitoring and diagnosing thermal generator set | |
| CN113898537A (en) | Remote intelligent inspection system for wind power plant | |
| CN117746903A (en) | Voiceprint monitoring and diagnosing method based on wind power failure knowledge base | |
| CN106525214A (en) | Wind-driven generator vibration detecting system | |
| CN116840631A (en) | Transformer partial discharge monitoring and positioning method based on joint diagnosis model | |
| CN112378605B (en) | Wind turbine generator blade fault identification method based on EMD decomposition self-learning | |
| CN115163426A (en) | Draught fan fault detection method and system based on AI auscultation and draught fan safety system | |
| CN114593023A (en) | Wind turbine generator blade crack monitoring system and method | |
| CN111400959B (en) | Blade fault diagnosis method and device for wind generating set | |
| CN113218653A (en) | Offshore wind power gear box monitoring method and device based on low-frequency disturbance elimination |
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 |