CN108491622A - A kind of fault diagnosis method and system of Wind turbines - Google Patents
A kind of fault diagnosis method and system of Wind turbines Download PDFInfo
- Publication number
- CN108491622A CN108491622A CN201810231915.1A CN201810231915A CN108491622A CN 108491622 A CN108491622 A CN 108491622A CN 201810231915 A CN201810231915 A CN 201810231915A CN 108491622 A CN108491622 A CN 108491622A
- Authority
- CN
- China
- Prior art keywords
- wind turbines
- wind
- generating set
- running
- inference machine
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Wind Motors (AREA)
Abstract
The present invention provides a kind of fault diagnosis method and system of Wind turbines, by acquiring running of wind generating set state parameter, the running of wind generating set state parameter of acquisition is sent to inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine；Wind turbines state operational factor is analyzed using inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine, determines the failure of Wind turbines.The present invention is combined using expert system module analysis and physical simulation simulation, the failure of analysis emulation Wind turbines, Wind turbines have been carried out with online integration test and assessment, the operating status for grasping Wind turbines in real time is realized, theoretical foundation and technological guidance are provided for the repair based on condition of component of Wind turbines.
Description
Technical field
The invention belongs to Wind turbines condition monitoring and fault diagnosis technical field, more particularly to a kind of event of Wind turbines
Hinder diagnostic method and system.
Background technology
In recent years, the situation of environmental pollution and energy crisis has growed in intensity, a kind of environmentally protective new energy of urgent need
Occur.Wind-powered electricity generation is increasingly paid attention to by world community as a kind of renewable, without discharge new energy, this but also
Wind generating technology has obtained vigorous growth in recent years.In China, a large amount of of wind power plant establish and come into operation, and will be
The call that government improves energy resource structure, copes with climate change is responded, realizes specific body of the traditional energy to new energy gradually transition
It is existing.
Other than renewable, pollution-free, wind-power electricity generation China also have it is resourceful, floor space is wide, single machine hold
Measure the advantages that small.But since wind power plant is usually all built in remote districts, it is poor that there is also technical conditions, and bad environments etc. are asked
Topic.Meanwhile the input application of large-scale wind power unit also makes its security and stability obtain the great attention of people.Due to wind-powered electricity generation
Unit long-term work is in severe natural environment so that wind field wind regime is complicated and changeable, is easy to cause the generation of various failures.
Wind turbine transmission chain failure accounted in unit failure it is relatively high, transmission chain break down caused by power off time most
It is long, and replacement cost highest after failure, therefore, its state is monitored in real time and to carry out health evaluating imperative.Traditional monitoring
Technology cannot identify initial failure, and data acquisition, data analysis, fault diagnosis etc. are relatively weak.According to wind turbine group leader
The summary of experience that phase uses, i.e., study generating set from the thinking of people, and relevant technical staff proposes a series of solution
Certainly scheme, such as Publication No. " CN106124982A ", a kind of entitled " automatic expert's resultant fault diagnostic system of Wind turbines
And diagnostic method " Chinese patent, the patent provide Wind turbines method for diagnosing faults the step of be：Acquire Wind turbines
Operating parameter, and by the data transmission of the Wind turbines of acquisition to expert system module, expert system module to signal processing,
With diagnosis decision, the scheme that this patent provides only uses failure of the single expertise technology to wind turbine for state recognition
Identification and decision are made, really the true operation conditions of Wind turbines is not combined to divide the failure to Wind turbines
Analysis, with the increase of Wind turbines single-machine capacity, the complexity of operational process is higher and higher, single diagnosis theory and technology
It is difficult to realize the condition monitoring and fault diagnosis to whole service process, therefore, the scheme of the prior art is to current Wind turbines
The accuracy rate of fault diagnosis is relatively low, influences the comprehensive analysis to wind power generation set system.
Invention content
The purpose of the present invention is to provide a kind of fault diagnosis method and system of Wind turbines, for solving the prior art
In the method for fault diagnosis of wind turbines problem relatively low to the accuracy rate of the fault diagnosis result of Wind turbines.
To achieve the above object, the present invention provides a kind of method for diagnosing faults of Wind turbines, include the following steps：
1) running of wind generating set state parameter is acquired, the running of wind generating set state parameter of the acquisition is sent to expert
Reasoning machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine；
2) use inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine to wind turbine
Group state operational factor is analyzed, and determines the fault diagnosis result of Wind turbines.
Further, the running of wind generating set state parameter includes wind generating set vibration signal and oil quality.
Further, it after having acquired running of wind generating set state parameter, also needs to carry out the operating status of Wind turbines real
When monitoring and early warning.
Further, inference engine of expert system analyzes running of wind generating set state parameter using failure tree algorithm.
Further, it also needs to classify to the running of wind generating set state parameter of acquisition using Fuzzy Threshold algorithm.
The present invention also provides a kind of fault diagnosis system of Wind turbines, including Wind turbines state monitoring module, specially
Family's system inference machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine, the wind turbine state monitoring module
It is connect with inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine；The Wind turbines shape
State monitoring modular is sent for acquiring running of wind generating set state parameter, and by the running of wind generating set state parameter of the acquisition
To inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine；Inference engine of expert system obscures
ANN Reasoning machine and Fast Fourier Transform inference machine determine wind for analyzing Wind turbines state operational factor
The fault diagnosis result of motor group.
Further, the running of wind generating set state parameter includes wind generating set vibration signal and oil quality.
Further, further include SCADA modules, the SCADA modules are used to acquire running of wind generating set state ginseng
After number, monitoring and early warning in real time are carried out to the operating status of Wind turbines.
Further, inference engine of expert system analyzes running of wind generating set state parameter using failure tree algorithm.
Further, further include data preprocessing module, the data preprocessing module is used to use Fuzzy Threshold algorithm
Classify to the running of wind generating set state parameter of acquisition.
Further, the Wind turbines state monitoring module includes sensor, data collector, the sensor and number
It is used to connect with Wind turbines by optical fiber according to collector.
The beneficial effects of the invention are as follows：
The present invention is sent out the running of wind generating set state parameter of the acquisition by acquiring running of wind generating set state parameter
Give inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine；Using expert system reasoning
Machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine analyze Wind turbines state operational factor, really
Determine the failure of Wind turbines.The present invention is combined using expert system module analysis and physical simulation simulation, analysis emulation wind-powered electricity generation
The failure of unit has carried out Wind turbines online integration test and assessment, realizes the operation for grasping Wind turbines in real time
State provides theoretical foundation and technological guidance for the repair based on condition of component of Wind turbines.
Description of the drawings
Fig. 1 is Double-feed wind power unit online system failure diagnosis structure diagram；
Fig. 2 is data interaction schematic diagram between each module in Double-feed wind power unit fault diagnosis system.
Specific implementation mode
The specific implementation mode of the present invention is further described below in conjunction with the accompanying drawings：
The present invention provides a kind of fault diagnosis system of Wind turbines, which is suitable for various types of
Wind turbine, the present embodiment is by taking Double-feed wind power unit as an example.
The fault diagnosis system of the Wind turbines of the present embodiment, including Wind turbines state monitoring module, expert system push away
Reason machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine, wind turbine state monitoring module are pushed away with expert system
Reason machine, fuzzy neural network inference machine and the connection of Fast Fourier Transform inference machine；Wind turbines state monitoring module is for adopting
Collect running of wind generating set state parameter, and the running of wind generating set state parameter of acquisition is sent to inference engine of expert system, mould
Paste ANN Reasoning machine and Fast Fourier Transform inference machine；Inference engine of expert system, fuzzy neural network inference machine and fast
Fast Fourier transform inference machine determines the fault diagnosis knot of Wind turbines for analyzing Wind turbines state operational factor
Fruit.
Specifically, as shown in Figure 1, fault diagnosis of wind turbines system includes Wind turbines state monitoring module, wind-powered electricity generation
Set state monitoring modular be Wind turbines state on_line monitoring system (Condition Monitoring System,
CMS), Wind turbines state on_line monitoring system includes various kinds of sensors and data collector, and various kinds of sensors and data acquire
Device is connect by optical fiber with Wind turbines；Further include expert system module, Wind turbines state monitoring module and expert system mould
Block connects, and further includes having data preprocessing module, data preprocessing module supervises Wind turbines state using Fuzzy Threshold online
The running of wind generating set status information that examining system sends over is pre-processed, and Wind turbines running state information data is classified
At real-time data base, historical data base and fault database, wherein threshold value refers to judging a limit value of unit failure, by sentencing
It is disconnected whether be more than the threshold value of setting with judge Wind turbines state whether normal or failure, if the threshold value more than setting indicates wind
Motor group failure is then alarmed, and does not have to alarm if indicating Wind turbines normally less than the threshold value of setting；Decision fusion algorithm
Module is connect with real-time data base, historical data base and fault database respectively, is analyzed by the Decision fusion of three kinds of inference machines
Suggestion and the failure modes etc. of fault diagnosis of wind turbines are calculated.
Three kinds of inference machines include that inference engine of expert system, fuzzy neural network (Fuzzy Neural Network, FNN) push away
Reason machine and Fast Fourier Transform (FFT) (Fast Fourier Transformation, FFT) inference machine, inference engine of expert system are negative
Duty diagnosis certainty failure and simple indeterminate fauit, FNN inference machines are mainly responsible for the indeterminate fauit of diagnosis of complex,
FNN inference machines are made of several submodules, and each submodule is relatively independent, are each responsible for the different faults of Wind turbines；Point
Analysis ability is strong, can carry out real-time fault detection.Decision fusion algoritic module triggers expert system, FNN and FFT reasonings
Machine, and inference machine is optimized, form intelligent Fault Diagnose Systems.Wherein it is determined that property failure refers to shaking according to acquisition
The failure that dynamic data can be determined directly, indeterminate fault refer to the failure that cannot be directly determined according to vibration data, due to
Failure Producing reason is complicated, and different faults have different signs, but different faults also have identical sign sometimes,
Same fault also has different signs, for example, rotor unbalance and the abnormal vibration that rotor can be caused such as misalign, because
This, there is the characteristic information for much characterizing its working condition in the vibration signal of rotor.
The mounted CMS system of wind power plant can only be monitored wind turbine transmission chain state and diagnose roughly, not
Data can be carried out analyzing and judging in real time, not have fault diagnosis functions truly；And wind power plant SCADA modules are only
Monitoring and off-limit alarm in real time can be carried out to systematic parameter and state, but gathered data amount is big.By the system and wind power plant of structure
CMS system and SCADA system are combined, and obtain diagnostic result, are then combined with Decision fusion algorithm, to Double-feed wind power machine
Group transmission chain carries out condition monitoring and fault diagnosis, keeps fault diagnosis conclusion more accurate, as shown in Fig. 2, wind turbine failure is examined
Disconnected module by Internet buses and running of wind generating set slip condition database, operator workstation, inference machine work station and
SCADA modules connect, and fault diagnosis result is pushed to remote user by fault diagnosis of wind turbines module, for remote user to wind
Motor group fault diagnosis result is checked and is analyzed.
Using the fault diagnosis system of Wind turbines to the method for fault diagnosis of wind turbines, include the following steps：
1) running of wind generating set state parameter is acquired, the running of wind generating set state parameter of acquisition is sent to expert system
Module；Running of wind generating set state parameter includes wind generating set vibration signal and oil quality.SCADA modules are acquiring wind-powered electricity generation
After operating states of the units parameter, monitoring and early warning in real time are carried out to the operating status of Wind turbines.
2) data preprocessing module runs pretreatment classification to wind turbine running state parameter, obtains running of wind generating set shape
Real-time data base, historical data base and the fault database of state.
3) inference engine of expert system, fuzzy neural network inference machine and Fourier transform inference machine is used to transport Wind turbines
Row state parameter is analyzed, and carries out analyzing and diagnosing according to fault characteristic, is determined the failure of Wind turbines, is provided local diagnosis
Conclusion；By taking Double-feed wind power set main shaft bearing fault as an example, bearing designation 240/600CA, in the case of rotating speed is 9.7rpm
Bearing fault frequency calculates, and it is 1.76Hz that setting, which rolls bulk damage frequency,；It is 2.47Hz that inner ring, which damages frequency,；Frequency is damaged in outer ring
For 2.06Hz；It is 0.07Hz that retainer, which damages frequency,.
4) operator can click the trouble location by mouse, obtain the corresponding operation data of Wind turbines, curve, event
Hinder time of origin, trouble location, fault degree and expert advice etc., as shown in table 1~3.
By taking main shaft bearing breaks down as an example, as shown in table 1, table 1 provides speed, acceleration and envelope 1 respectively in water
Vibration amplitude square in, vertical direction and axial direction.
1 main shaft bearing vibration amplitude of table
Table 2 is time of failure, trouble location and fault degree request for information, and 25 divide 12 when 22 days 15 May in 2013
Second 1# bear vibration is very serious, has reached alarming value.
2 time of failure of table, trouble location and fault degree
Table 3 is expert advice measure, that is, diagnosis, and consensus of opinion is that 1# main shaft bearings are built there are early stage mild wear
It discusses taken at regular intervals vibration data and observes fault progression trend；If it was found that vibration amplitude increases, vibration aggravation should overhaul, increase in time
Add or more oil change, or even replaces bearing.
3 expert opinion of table and suggestion
The present invention monitors its operating status in real time by the vibration signal and oil quality of monitoring Wind turbines；Utilize mould
It pastes neural network to analyze with Fast Fourier Transform, the axis of rolling of Double-feed wind power set drive chain is analyzed in Binding experiment simulation
It holds, the failure mode and failure mechanism of gear-box, shafting；In conjunction with two methods of physical simulation and summary of experience, data are located in advance
Reason, is further diagnosed different types of failure, is optimized to diagnostic result using Decision fusion technology.Utilize failure
Intelligent Diagnosis Technology is set, field failure is diagnosed, carries out health evaluating.By to Double-feed wind power set drive chain in twine helad
Close test and health evaluating, its operating status can be grasped in real time, for Wind turbines repair based on condition of component provide theoretical foundation with
Technological guidance.
Specific embodiment is presented above, but the present invention is not limited to embodiment described above.The present invention
Basic ideas be above-mentioned basic scheme, for those of ordinary skill in the art, introduction according to the present invention is designed each
The model of kind deformation, formula, parameter do not need to spend creative work.The case where not departing from the principle and spirit of the invention
Under to embodiment carry out variation, modification, replacement and deformation still fall in protection scope of the present invention.
Claims (10)
1. a kind of method for diagnosing faults of Wind turbines, which is characterized in that include the following steps：
1) running of wind generating set state parameter is acquired, the running of wind generating set state parameter of the acquisition is sent to expert system
Inference machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine；
2) use inference engine of expert system, fuzzy neural network inference machine and Fast Fourier Transform inference machine to Wind turbines shape
State operating parameter is analyzed, and determines the fault diagnosis result of Wind turbines.
2. the method for diagnosing faults of Wind turbines according to claim 1, which is characterized in that the running of wind generating set shape
State parameter includes wind generating set vibration signal and oil quality.
3. the method for diagnosing faults of Wind turbines according to claim 2, which is characterized in that acquired running of wind generating set
After state parameter, also need to carry out monitoring and early warning in real time to the operating status of Wind turbines.
4. the method for diagnosing faults of Wind turbines according to claim 3, which is characterized in that inference engine of expert system uses
Failure tree algorithm analyzes running of wind generating set state parameter.
5. the method for diagnosing faults of Wind turbines according to claim 1, which is characterized in that also need to calculate using Fuzzy Threshold
Method classifies to the running of wind generating set state parameter of acquisition.
6. a kind of fault diagnosis system of Wind turbines, which is characterized in that including Wind turbines state monitoring module, expert system
Inference machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine, the wind turbine state monitoring module and expert
Reasoning machine, fuzzy neural network inference machine and the connection of Fast Fourier Transform inference machine；The Wind turbines status monitoring
The running of wind generating set state parameter of the acquisition is sent to expert by module for acquiring running of wind generating set state parameter
Reasoning machine, fuzzy neural network inference machine and Fast Fourier Transform inference machine；Inference engine of expert system, fuzznet
Network inference machine and Fast Fourier Transform inference machine determine Wind turbines for analyzing Wind turbines state operational factor
Fault diagnosis result.
7. the fault diagnosis system of Wind turbines according to claim 6, which is characterized in that the running of wind generating set shape
State parameter includes wind generating set vibration signal and oil quality.
8. the fault diagnosis system of Wind turbines according to claim 7, which is characterized in that further include SCADA modules, institute
SCADA modules are stated for after having acquired running of wind generating set state parameter, being supervised in real time to the operating status of Wind turbines
Survey and early warning.
9. the fault diagnosis system of Wind turbines according to claim 8, which is characterized in that inference engine of expert system uses
Failure tree algorithm analyzes running of wind generating set state parameter.
10. the fault diagnosis system of Wind turbines according to claim 6, which is characterized in that further include data prediction
Module, the data preprocessing module is for dividing the running of wind generating set state parameter of acquisition using Fuzzy Threshold algorithm
Class.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810231915.1A CN108491622A (en) | 2018-03-20 | 2018-03-20 | A kind of fault diagnosis method and system of Wind turbines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810231915.1A CN108491622A (en) | 2018-03-20 | 2018-03-20 | A kind of fault diagnosis method and system of Wind turbines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108491622A true CN108491622A (en) | 2018-09-04 |
Family
ID=63318944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810231915.1A Pending CN108491622A (en) | 2018-03-20 | 2018-03-20 | A kind of fault diagnosis method and system of Wind turbines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491622A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270458A (en) * | 2018-11-08 | 2019-01-25 | 国电联合动力技术有限公司 | Intelligent failure diagnosis method, system, Wind turbines and storage medium |
| CN111709453A (en) * | 2020-05-22 | 2020-09-25 | 成都飞机工业（集团）有限责任公司 | Online fault diagnosis method for electrical system of aircraft engine |
| CN113932763A (en) * | 2021-09-24 | 2022-01-14 | 微传智能科技（常州）有限公司 | Geomagnetic vehicle inspection device posture health monitoring system and method and geomagnetic vehicle inspection device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101672723A (en) * | 2009-10-28 | 2010-03-17 | 北京中能联创风电技术有限公司 | Method and system for analyzing vibration and diagnosing failure for wind generating set |
-
2018
- 2018-03-20 CN CN201810231915.1A patent/CN108491622A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101672723A (en) * | 2009-10-28 | 2010-03-17 | 北京中能联创风电技术有限公司 | Method and system for analyzing vibration and diagnosing failure for wind generating set |
Non-Patent Citations (1)
| Title |
|---|
| 任岩: "风电机组传动链综合状态监测与故障诊断技术", 《排灌机械工程学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270458A (en) * | 2018-11-08 | 2019-01-25 | 国电联合动力技术有限公司 | Intelligent failure diagnosis method, system, Wind turbines and storage medium |
| CN111709453A (en) * | 2020-05-22 | 2020-09-25 | 成都飞机工业（集团）有限责任公司 | Online fault diagnosis method for electrical system of aircraft engine |
| CN113932763A (en) * | 2021-09-24 | 2022-01-14 | 微传智能科技（常州）有限公司 | Geomagnetic vehicle inspection device posture health monitoring system and method and geomagnetic vehicle inspection device |
| CN113932763B (en) * | 2021-09-24 | 2024-04-05 | 微传智能科技（常州）有限公司 | Geomagnetic vehicle detector posture health monitoring system and method and geomagnetic vehicle detector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
| CN105787584B (en) | Wind turbine group fault early warning method based on cloud platform | |
| CN110469462B (en) | Wind turbine generator system intelligent state monitoring system based on multiple templates | |
| CN202710100U (en) | Wind generating set remote on-line health state monitoring and fault diagnosing system | |
| CN103343728A (en) | Wind generating set remote on-line multi-mode health state monitoring and fault diagnosis system | |
| CN103234585A (en) | Online monitoring and fault diagnosis system of large wind turbine units | |
| CN202326011U (en) | State-monitoring and fault-diagnosis system of wind-power set | |
| CN110907170B (en) | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method | |
| CN103512651B (en) | The Wind turbines state monitoring method reported to the police based on vibration mutation and device | |
| CN107061183A (en) | A kind of automation method for diagnosing faults of offshore wind farm unit | |
| CN108491622A (en) | A kind of fault diagnosis method and system of Wind turbines | |
| CN104564542B (en) | A kind of fault diagnosis system and its diagnostic method based on big data technology | |
| CN104392082A (en) | Diagnosis method for initial failure of gearbox of wind generating set based on vibration monitoring | |
| CN113806893A (en) | Fan state monitoring and fault diagnosis method and system based on industrial internet | |
| CN104792520A (en) | Fault diagnosis method for gear case of wind turbine generator system | |
| CN115929566A (en) | Online state monitoring and early warning system and method for variable pitch speed reducer of wind turbine generator | |
| CN202453182U (en) | Fault diagnosis device of gearbox of wind generation set | |
| Liu et al. | A review of bearing fault diagnosis for wind turbines | |
| CN103899498A (en) | Data collecting and processing system of wind turbine generator | |
| CN111242329A (en) | Port crane transmission part big data monitoring system and monitoring method | |
| CN110794683A (en) | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics | |
| CN115829411A (en) | Method and system for evaluating operation state of offshore wind turbine generator | |
| CN103728942A (en) | Local data collecting and processing system of wind generating set | |
| Shen et al. | Fault detection method based on multi-scale convolutional neural network for wind turbine gearbox | |
| 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |