CN111456915A - Fault diagnosis device and method for internal components of fan engine room - Google Patents
Fault diagnosis device and method for internal components of fan engine room Download PDFInfo
- Publication number
- CN111456915A CN111456915A CN202010234559.6A CN202010234559A CN111456915A CN 111456915 A CN111456915 A CN 111456915A CN 202010234559 A CN202010234559 A CN 202010234559A CN 111456915 A CN111456915 A CN 111456915A
- Authority
- CN
- China
- Prior art keywords
- component
- audio
- fault diagnosis
- fault
- original
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a fault diagnosis device and method for internal components of a fan engine room. Wherein the device includes: the system comprises at least one component audio acquisition module, at least one component audio acquisition module and a control module, wherein the component audio acquisition module corresponds to one component in a fan cabin respectively and is used for acquiring the original operation audio of the corresponding component; the noise audio acquisition module is arranged in the cabin and used for acquiring the environmental noise audio in the fan cabin; and the fault diagnosis module is used for respectively calculating the environmental noise component contained in the original operation audio frequency of each component, respectively calculating the actual operation audio frequency of each component, and carrying out fault diagnosis on the components according to the actual operation audio frequency, wherein the actual operation audio frequency is equal to the difference between the original operation audio frequency and the contained environmental noise component. The method and the device respectively collect the original operation audio frequency of the cabin component and the external environmental noise to obtain the actual operation audio frequency of the component with higher noise elimination quality, so that the fault diagnosis of the component is carried out, and the diagnosis accuracy is improved.
Description
Technical Field
The invention belongs to the field of fault diagnosis, and particularly relates to a fault diagnosis device and method for internal components of a fan engine room.
Background
Components inside a wind turbine nacelle are often prone to failure. The current failure diagnosis methods mainly include the following methods:
identifying the fault of the component by means of worker inspection, but the worker inspection consumes manpower and cannot feed back the health condition of the component in real time;
secondly, a vibration sensor is arranged on a fan cabin part, transmitted vibration signals are subjected to time-frequency spectrum analysis to identify faults, but the vibration sensor is high in cost and depends on expert experience to judge the faults;
and thirdly, an audio acquisition device is arranged in the fan cabin, the state of the fan cabin components is judged by utilizing the captured sound information, the noise generated in the fan cabin is larger due to the operation of various components, the judged fault result has larger error, and the accuracy is lower.
Disclosure of Invention
The invention aims to overcome the defect of inaccurate judgment caused by judging component faults through sound captured in a fan cabin in the prior art, and provides a fault diagnosis device and method for internal components of the fan cabin.
The invention solves the technical problems through the following technical scheme:
a fault diagnosis apparatus for internal components of a wind turbine nacelle, comprising:
the system comprises at least one component audio acquisition module, at least one component audio acquisition module and a control module, wherein each component audio acquisition module corresponds to one component in a fan cabin respectively, and the component audio acquisition modules are arranged on the corresponding components and used for acquiring the original operation audio of the corresponding components;
the noise audio acquisition module is arranged inside the fan cabin and used for acquiring environmental noise audio inside the fan cabin;
and the fault diagnosis module is used for respectively calculating the environmental noise component contained in the original operation audio of each component according to the environmental noise audio, respectively calculating the actual operation audio of each component, and carrying out fault diagnosis on the components according to the actual operation audio, wherein the actual operation audio is equal to the difference between the original operation audio and the contained environmental noise component.
Preferably, the fault diagnosis apparatus further includes:
and the audio preprocessing module is connected with each component audio acquisition module and used for receiving the original operation audio acquired by each component audio acquisition module to form mixed audio, splitting the mixed audio into the independent original operation audio of each component, and transmitting the split original operation audio to the fault diagnosis module.
Preferably, the diagnosing the fault of the component according to the actual operation audio specifically includes:
extracting at least one of frequency domain features, energy domain features and time domain features from the actual operating audio;
and inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model, wherein the fault diagnosis model comprises a fault judgment model for judging whether the component is in fault and/or a fault classification model for identifying the fault type of the component.
Preferably, the fault diagnosis apparatus further includes:
and the fault alarm module is used for sending out an alarm signal when the component is in fault.
Preferably, the ambient noise component is [ | original running audio waveform of component |/(| original running audio waveform of component | ambient noise audio waveform |) ] | ambient noise audio waveform.
Preferably, the component is at least one of a gearbox, a main shaft and a generator input.
A fault diagnosis method for internal components of a wind turbine cabin comprises the following steps:
acquiring original operation audio of at least one part in a fan cabin and environmental noise audio in the fan cabin;
respectively calculating the environmental noise components contained in the original operation audio of each component according to the environmental noise audio;
respectively calculating the actual operation audio frequency of each component, wherein the actual operation audio frequency is equal to the difference between the original operation audio frequency and the contained environmental noise component;
and carrying out fault diagnosis on the component according to the actual operation audio.
Preferably, the fault diagnosis method further includes:
when the original operation audios of all the components form mixed audio, splitting the mixed audio into the original operation audios of each component.
Preferably, the step of performing fault diagnosis of the component according to the actual operation audio specifically includes:
extracting at least one of frequency domain features, energy domain features and time domain features from the actual operating audio;
and inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model, wherein the fault diagnosis model comprises a fault judgment model for judging whether the component is in fault and/or a fault classification model for identifying the fault type of the component.
Preferably, the fault diagnosis method further includes:
an alarm signal is emitted when the component fails.
Preferably, the ambient noise component is [ | original running audio waveform of component |/(| original running audio waveform of component | ambient noise audio waveform |) ] | ambient noise audio waveform.
Preferably, the component is at least one of a gearbox, a main shaft and a generator input.
On the basis of the common knowledge in the field, the above preferred conditions can be combined randomly to obtain the preferred embodiments of the invention.
The positive progress effects of the invention are as follows: according to the fault diagnosis device and method for the components in the fan engine room, the component audio acquisition module arranged on the components and the noise audio acquisition module arranged in the fan engine room are used for respectively acquiring the original operation audio of the engine room components and the external environmental noise, and the actual operation audio of the components with high noise elimination quality is obtained after processing, so that the fault diagnosis of the components is performed, and the diagnosis accuracy is improved.
Drawings
Fig. 1 is a schematic block diagram of a fault diagnosis apparatus for internal components of a wind turbine nacelle according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for diagnosing a fault of an internal component of a wind turbine nacelle according to embodiment 2 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
Fig. 1 shows a failure diagnosis device for internal components of a wind turbine nacelle according to the present embodiment. The fault diagnosis apparatus includes at least one component audio acquisition module 101 (only three are schematically shown in fig. 1, but the present invention is not limited thereto), a noise audio acquisition module 102, and a fault diagnosis module 103.
Each component audio acquisition module 101 corresponds to a component inside the fan cabin, and the component audio acquisition modules 101 are arranged on the corresponding components and used for acquiring original operation audio of the corresponding components. The noise audio acquisition module 102 is disposed inside the fan cabin and configured to acquire an environmental noise audio inside the fan cabin. The fault diagnosis module 103 is configured to calculate an environmental noise component included in an original operating audio of each component according to the environmental noise audio, calculate an actual operating audio of each component, and perform fault diagnosis on the component according to the actual operating audio, where the actual operating audio is equal to a difference between the original operating audio and the included environmental noise component.
Wherein the components may be a gearbox, a main shaft and a generator input, respectively. The fault diagnosis device may correspondingly include a gear box component audio acquisition module disposed on the gear box, a main shaft component audio acquisition module disposed on the main shaft, and a generator input component audio acquisition module disposed on the generator input. The noise audio collection module 102 may be disposed inside the wind turbine nacelle at a location between the gearbox, the main shaft, and the generator input, such as on a nacelle stand. The component audio capture module 101 and the noise audio capture module 102 may include an array of microphones.
In this embodiment, each component audio collection module 101 may indirectly transmit the original operating audio to the fault diagnosis module 103. The indirect transmission mode may be that the component audio acquisition module 101 transmits the original operating audio to a certain intermediate module through a data line or a wired or wireless network, and then the intermediate module transmits the original operating audio to the fault diagnosis module 103 through the data line or the wired or wireless network. The intermediate module may be one module or a plurality of modules, and the intermediate module may have some function, such as preprocessing of the original running audio. The intermediate module may be the audio pre-processing module 104. The audio preprocessing module 104 is connected to each component audio acquisition module 101, and is further connected to the fault diagnosis module 103. The audio preprocessing module 104 is configured to receive an original operating audio acquired by each component audio acquisition module 101 to form a mixed audio, split the mixed audio into individual original operating audio of each component, and transmit the split original operating audio to the fault diagnosis module 103.
Of course, in other embodiments, each component audio acquisition module 101 may transmit raw operating audio directly to the fault diagnosis module 103. The direct transmission may be that the component audio collection module 101 transmits the original operating audio to the fault diagnosis module 103 through a data line or a wired or wireless network.
In order to report the fault in time and enable the technician to handle the fault in time, the fault diagnosis apparatus in this embodiment may further include a fault alarm module 105. The fault alarm module 105 is configured to issue an alarm signal when the component fails. The alarm signal may take various forms, such as a warning tone, a warning light, etc.
In this embodiment, the environmental noise component may be calculated by the following formula:
the ambient noise component [ | original running audio waveform of the component |/(| original running audio waveform of the component | ambient noise audio waveform |) ] | ambient noise audio waveform.
The calculation formula of the actual operating audio of the component can thus be derived:
the actual operating audio of the component is the component's original operating audio waveform- [ | the component's original operating audio waveform environmental noise audio waveform |/(| the component's original operating audio waveform | environmental noise audio waveform |) ] | the environmental noise audio waveform.
The fault diagnosis module 103 may implement fault diagnosis of the component according to the actual operating audio by using a machine learning algorithm, and specifically includes:
extracting at least one of a frequency domain feature, an energy domain feature and a time domain feature from the actual running audio, wherein the time domain feature may comprise at least one of volume, volume change and zero point passing rate; the frequency domain features may include at least one of a center frequency, a bandwidth, a threshold frequency, and a spectral transition, and the energy domain features may include MFCC features; (ii) a
And inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model.
The failure diagnosis model may be a failure determination model for determining whether the component is failed. And when the frequency domain characteristic, the energy domain characteristic and the time domain characteristic are input into the fault judgment model, the output of the fault judgment model is whether the component has a fault or not.
The fault diagnosis model may also be a fault classification model for identifying a fault type of the component. When the frequency domain features, the energy domain features and the time domain features are input into the fault classification model, the output of the fault classification model is which type of fault occurs in the component.
The fault judgment model and the fault classification model may be constructed based on a clustering algorithm and a classification algorithm, for example, by using a large amount of pre-collected component fault data, an abnormal condition is detected by using a clustering algorithm such as KNN (proximity algorithm), GARCH (generalized autoregressive conditional variance model), etc., and an outlier detection algorithm such as SOM (self-organizing (competitive) neural network), etc.; when the data label and the rule space are accurate, classification algorithms such as SVM (support vector machine) and the like can be used for classifying normal and abnormal data. The fault types identifiable by the fault classification model may include gear cracking, bearing wear, gear cracking and bearing wear of the pitch, main shaft cracking, and the like.
The method and the device utilize the machine learning algorithm training model to diagnose the fault, can accurately analyze the audio characteristics of the component during the fault, and are beneficial to improving the accuracy of fault diagnosis.
In practical application, the fault judgment model may be used to judge whether a component is faulty or not, and after the fault is judged, the fault alarm module 105 alarms, and the fault classification model is used to further judge the fault type of the component.
The fault diagnosis device for the internal components of the fan engine room of the embodiment respectively collects original operation audio of the components of the engine room and external environmental noise through the component audio collection module 101 arranged on the components and the noise audio collection module arranged in the fan engine room, and obtains actual operation audio of the components with high quality for eliminating noise after processing, so that fault diagnosis of the components is performed, and diagnosis accuracy is improved.
Example 2
Fig. 2 shows a method for diagnosing a fault of an internal component of a wind turbine nacelle according to the embodiment. The fault diagnosis method comprises the following steps:
step 201: the method comprises the steps of collecting original operation audio of at least one part in a fan cabin and environmental noise audio in the fan cabin.
Step 202: and respectively calculating the environmental noise components contained in the original operation audio of each component according to the environmental noise audio.
Step 203: and respectively calculating the actual operation audio frequency of each component, wherein the actual operation audio frequency is equal to the difference between the original operation audio frequency and the contained environmental noise component.
Step 204: and carrying out fault diagnosis on the component according to the actual operation audio.
Wherein the components may be a gearbox, a main shaft and a generator input, respectively. The fault diagnosis method can acquire the original operation audio frequency of the gearbox by using a gearbox component audio acquisition module arranged on the gearbox, acquire the original operation audio frequency of the main shaft by using a main shaft component audio acquisition module arranged on the main shaft, and acquire the original operation audio frequency of the input end of the generator by using a generator input end component audio acquisition module arranged on the input end of the generator. The fault diagnosis method may also collect ambient noise audio using a noise audio collection module disposed inside the wind turbine nacelle at a location between the gearbox, the main shaft, and the generator input (e.g., on a nacelle stand). The audio acquisition modules of the above-mentioned components and the noise audio acquisition module may comprise a microphone array.
The collected original operating audios of all the components may be mixed together due to a data transmission problem, and therefore, in order to separate the original operating audios of the components, the failure diagnosis method may further split the mixed audio into the individual original operating audios of each component when the original operating audios of all the components form the mixed audio.
In order to report the fault in time and enable the technician to process the fault in time, the fault diagnosis method in this embodiment may further include:
step 205: an alarm signal is emitted when the component fails. The alarm signal may take various forms, such as a warning tone, a warning light, etc.
In this embodiment, the environmental noise component in step 202 may be calculated by the following formula:
the ambient noise component [ | original running audio waveform of the component |/(| original running audio waveform of the component | ambient noise audio waveform |) ] | ambient noise audio waveform.
The calculation formula of the actual operating audio of the component can thus be derived:
the actual operating audio of the component is the component's original operating audio waveform- [ | the component's original operating audio waveform environmental noise audio waveform |/(| the component's original operating audio waveform | environmental noise audio waveform |) ] | the environmental noise audio waveform.
Step 205 in this embodiment may specifically include:
extracting at least one of a frequency domain feature, an energy domain feature and a time domain feature from the actual running audio, wherein the time domain feature may comprise at least one of volume, volume change and zero point passing rate; the frequency domain features may include at least one of a center frequency, a bandwidth, a threshold frequency, and a spectral transition, and the energy domain features may include MFCC features; (ii) a
And inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model.
The failure diagnosis model may be a failure determination model for determining whether the component is failed. And when the frequency domain characteristic, the energy domain characteristic and the time domain characteristic are input into the fault judgment model, the output of the fault judgment model is whether the component has a fault or not.
The fault diagnosis model may also be a fault classification model for identifying a fault type of the component. When the frequency domain features, the energy domain features and the time domain features are input into the fault classification model, the output of the fault classification model is which type of fault occurs in the component.
The fault judgment model and the fault classification model may be constructed based on a clustering algorithm and a classification algorithm, for example, by using a large amount of pre-collected component fault data, an abnormal condition is detected by using a clustering algorithm such as KNN (proximity algorithm), GARCH (generalized autoregressive conditional variance model), SOM (self-organizing (competitive) neural network), or the like outlier detection algorithm; when the data label and the rule space are accurate, classification algorithms such as SVM (support vector machine) and the like can be used for classifying normal and abnormal data. The fault types identifiable by the fault classification model may include gear cracking, bearing wear, gear cracking and bearing wear of the pitch, main shaft cracking, and the like.
The method and the device utilize the machine learning algorithm training model to diagnose the fault, can accurately analyze the audio characteristics of the component during the fault, and are beneficial to improving the accuracy of fault diagnosis.
In practical application, the fault judgment model can be used for judging whether the component has a fault or not, the fault alarm module gives an alarm after the fault is judged, and meanwhile, the fault classification model is used for further judging the fault type of the component.
According to the fault diagnosis method for the internal components of the fan engine room, the original operation audio frequency of the components of the engine room and the external environment noise are collected respectively, and the actual operation audio frequency of the components with high noise elimination quality is obtained after processing, so that fault diagnosis of the components is performed, and the diagnosis accuracy is improved.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (12)
1. A failure diagnosis device for internal components of a wind turbine nacelle is characterized by comprising:
the system comprises at least one component audio acquisition module, at least one component audio acquisition module and a control module, wherein each component audio acquisition module corresponds to one component in a fan cabin respectively, and the component audio acquisition modules are arranged on the corresponding components and used for acquiring the original operation audio of the corresponding components;
the noise audio acquisition module is arranged inside the fan cabin and used for acquiring environmental noise audio inside the fan cabin;
and the fault diagnosis module is used for respectively calculating the environmental noise component contained in the original operation audio of each component according to the environmental noise audio, respectively calculating the actual operation audio of each component, and carrying out fault diagnosis on the components according to the actual operation audio, wherein the actual operation audio is equal to the difference between the original operation audio and the contained environmental noise component.
2. The failure diagnosing device according to claim 1, characterized in that the failure diagnosing device further comprises:
and the audio preprocessing module is connected with each component audio acquisition module and used for receiving the original operation audio acquired by each component audio acquisition module to form mixed audio, splitting the mixed audio into the independent original operation audio of each component, and transmitting the split original operation audio to the fault diagnosis module.
3. The failure diagnosis device according to claim 1, wherein performing failure diagnosis of the component based on the actual operation audio specifically includes:
extracting at least one of frequency domain features, energy domain features and time domain features from the actual operating audio;
and inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model, wherein the fault diagnosis model comprises a fault judgment model for judging whether the component is in fault and/or a fault classification model for identifying the fault type of the component.
4. The failure diagnosing device according to claim 1, characterized in that the failure diagnosing device further comprises:
and the fault alarm module is used for sending out an alarm signal when the component is in fault.
5. The fault diagnosis device according to claim 1, characterized in that the ambient noise component [ | original running audio waveform of the component |/(| original running audio waveform of the component | ambient noise audio waveform |) ] | ambient noise audio waveform.
6. The fault diagnosis device of claim 1, wherein the component is at least one of a gearbox, a main shaft and a generator input.
7. A fault diagnosis method for internal components of a wind turbine nacelle is characterized by comprising the following steps:
acquiring original operation audio of at least one part in a fan cabin and environmental noise audio in the fan cabin;
respectively calculating the environmental noise components contained in the original operation audio of each component according to the environmental noise audio;
respectively calculating the actual operation audio frequency of each component, wherein the actual operation audio frequency is equal to the difference between the original operation audio frequency and the contained environmental noise component;
and carrying out fault diagnosis on the component according to the actual operation audio.
8. The fault diagnosis method according to claim 7, characterized in that the fault diagnosis method further comprises:
when the original operation audios of all the components form mixed audio, splitting the mixed audio into the original operation audios of each component.
9. The failure diagnosing method according to claim 7, wherein the step of performing the failure diagnosis of the component based on the actual operation audio specifically includes:
extracting at least one of frequency domain features, energy domain features and time domain features from the actual operating audio;
and inputting at least one of the frequency domain characteristics, the energy domain characteristics and the time domain characteristics into a fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model, wherein the fault diagnosis model comprises a fault judgment model for judging whether the component is in fault and/or a fault classification model for identifying the fault type of the component.
10. The fault diagnosis method according to claim 7, characterized in that the fault diagnosis method further comprises:
an alarm signal is emitted when the component fails.
11. The fault diagnosis method according to claim 7, characterized in that the ambient noise component [ | original running audio waveform of the component |/(| original running audio waveform of the component | ambient noise audio waveform |) ] | ambient noise audio waveform.
12. The fault diagnosis method according to claim 7, wherein the component is at least one of a gearbox, a main shaft and a generator input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010234559.6A CN111456915A (en) | 2020-03-30 | 2020-03-30 | Fault diagnosis device and method for internal components of fan engine room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010234559.6A CN111456915A (en) | 2020-03-30 | 2020-03-30 | Fault diagnosis device and method for internal components of fan engine room |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111456915A true CN111456915A (en) | 2020-07-28 |
Family
ID=71679284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010234559.6A Pending CN111456915A (en) | 2020-03-30 | 2020-03-30 | Fault diagnosis device and method for internal components of fan engine room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111456915A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708885A (en) * | 2022-03-30 | 2022-07-05 | 西安交通大学 | Fan fault early warning method based on sound signals |
| CN118152864A (en) * | 2024-05-11 | 2024-06-07 | 常州全一智能科技有限公司 | Motor detection method and system based on multi-source data fusion |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013023660A1 (en) * | 2011-08-16 | 2013-02-21 | Vestas Wind Systems A/S | Acoustic noise monitoring system for a wind turbine |
| US20130049733A1 (en) * | 2011-08-29 | 2013-02-28 | General Electric Company | Fault detection based on current signature analysis for a generator |
| CN105738806A (en) * | 2016-02-03 | 2016-07-06 | 北京汉能华科技股份有限公司 | Wind driven generator set fault diagnosis system and method |
| CN106593781A (en) * | 2016-11-29 | 2017-04-26 | 上海电机学院 | Wind driven generator fault detecting system and method based on Android platform |
| US20180012585A1 (en) * | 2016-07-11 | 2018-01-11 | Microsoft Technology Licensing, Llc | Microphone noise suppression for computing device |
| CN207600740U (en) * | 2017-11-20 | 2018-07-10 | 深圳市卓尔思科技有限公司 | A kind of monitoring system for wind-driven generator |
-
2020
- 2020-03-30 CN CN202010234559.6A patent/CN111456915A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013023660A1 (en) * | 2011-08-16 | 2013-02-21 | Vestas Wind Systems A/S | Acoustic noise monitoring system for a wind turbine |
| US20130049733A1 (en) * | 2011-08-29 | 2013-02-28 | General Electric Company | Fault detection based on current signature analysis for a generator |
| CN105738806A (en) * | 2016-02-03 | 2016-07-06 | 北京汉能华科技股份有限公司 | Wind driven generator set fault diagnosis system and method |
| US20180012585A1 (en) * | 2016-07-11 | 2018-01-11 | Microsoft Technology Licensing, Llc | Microphone noise suppression for computing device |
| CN106593781A (en) * | 2016-11-29 | 2017-04-26 | 上海电机学院 | Wind driven generator fault detecting system and method based on Android platform |
| CN207600740U (en) * | 2017-11-20 | 2018-07-10 | 深圳市卓尔思科技有限公司 | A kind of monitoring system for wind-driven generator |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708885A (en) * | 2022-03-30 | 2022-07-05 | 西安交通大学 | Fan fault early warning method based on sound signals |
| CN118152864A (en) * | 2024-05-11 | 2024-06-07 | 常州全一智能科技有限公司 | Motor detection method and system based on multi-source data fusion |
| CN118152864B (en) * | 2024-05-11 | 2024-08-02 | 常州全一智能科技有限公司 | Motor detection method and system based on multi-source data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10288043B2 (en) | Wind turbine condition monitoring method and system | |
| CN118209830B (en) | Intelligent monitoring method and system for cable partial discharge abnormality | |
| WO2023279382A1 (en) | Motor bearing running state fault detection method and system | |
| CN104564542B (en) | A kind of fault diagnosis system and its diagnostic method based on big data technology | |
| CN113982850A (en) | Fan comprehensive health analysis method and system fusing high-frequency and low-frequency signals | |
| CN110008350A (en) | A kind of pump Ankang knowledge base lookup method based on Bayesian inference | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN113532848A (en) | Fault diagnosis system for planetary gear box | |
| WO2022147684A1 (en) | Method and apparatus for identifying abnormalities in mechanical apparatus or mechanical component | |
| CN113298134A (en) | BPNN-based remote non-contact health monitoring system and method for fan blade | |
| CN116383633A (en) | Method and system for detecting faults of machine-made sand vibrating screen through multi-factor comprehensive analysis | |
| CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
| KR20210077496A (en) | Equipment failure prediction system having multi-channel sensors for receiving acoustic signals in the ultrasonic band | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| US20210149387A1 (en) | Facility failure prediction system and method for using acoustic signal of ultrasonic band | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| CN115640503A (en) | Wind turbine generator blade abnormity detection method and device | |
| CN111401661A (en) | Predictive maintenance method and maintenance system for mechanical equipment | |
| CN117672255B (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
| CN113516023B (en) | Method and system for diagnosing equipment vibration abnormality | |
| CN117668646A (en) | Speed reducer running state detection method, system, equipment and medium based on multi-feature fusion | |
| CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
| US20240052810A1 (en) | Blade fault diagnosis method, apparatus and system, and storage medium | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| CN113672859B (en) | Fault acoustic diagnosis system for switch machine |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |