CN105784353A - Fault diagnosis method for gear case of aerogenerator - Google Patents
Fault diagnosis method for gear case of aerogenerator Download PDFInfo
- Publication number
- CN105784353A CN105784353A CN201610178646.8A CN201610178646A CN105784353A CN 105784353 A CN105784353 A CN 105784353A CN 201610178646 A CN201610178646 A CN 201610178646A CN 105784353 A CN105784353 A CN 105784353A
- Authority
- CN
- China
- Prior art keywords
- signal
- wind
- box
- gear
- driven generator
- 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
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a fault diagnosis method for a gear case of an aerogenerator. The method comprises the following steps that a vibration sensor obtains a vibration signal when the gear box runs; a wavelet packet analysis method is used to carry out three-layer decomposition analysis on the collected vibration signal; empirical mode decomposition is carried out on the vibration signal after wavelet packet analysis, and a first component of the signal is extracted; characteristic values are extracted from the extracted first signal component, and serve as a characteristic value used for fault diagnosis; a characteristic vector sample of historical fault data of the gear case is obtained; a support vector machine is used to train the characteristic vector sample, and a group of highest classification accuracy is used as parameters for fault diagnosis later; real-time operation data of the gear case is obtained, and a characteristic vector is obtained; and the support vector machine is used to classify the characteristic vector, and a diagnosis result is output. According to the invention, whether the operation state of the gear box is normal can be analyzed, and a fault part can be determined in a fault state.
Description
Technical field
The present invention relates to wind power generating set field of fault detection, and particularly to a kind of wind-driven generator wheel-box method for diagnosing faults.
Background technology
Due to scarcity and the security problems of the conventional energy, the whole world has turned one's attention in green non-pollution, reproducible wind energy.Wind energy, as the regenerative resource of a kind of cleaning, is increasingly subject to the attention of countries in the world.Its amount of accumulateing is huge, and the wind energy in the whole world is about 2.74 × 109MW, wherein available wind energy is 2 × 107MW, than the water energy total amount that can develop on the earth also big 10 times.The kinetic energy kept watch is transformed into mechanical kinetic energy, then is electric power kinetic energy changes mechanical energy, here it is wind-power electricity generation.The principle of wind-power electricity generation, is utilize wind-force to drive air vane to rotate, then the speed rotated is promoted through booster engine, promote electrical power generators.Device required for wind-power electricity generation, is called wind power generating set.This wind power generating set, generally can divide wind wheel (including tail vane), electromotor and steel tower three part.Owing to the rotating ratio of wind wheel is relatively low, and the size and Orientation of wind-force often varies, and this makes again rotary speed unstabilization fixed;So, before drive electrical generators, it is necessary to additional speed-changing gear box rotating speed being brought up to electromotor rated speed, then add a speed adjusting gear and make rotating speed remain stable for, be then connected on electromotor again.
Along with being continuously increased of blower fan installed capacity, the fault of blower fan also occurs continually.Minor failure needs blower fan is carried out maintenance conditions;Great fault then needs to carry out shutdown maintenance, economy not only causes serious loss, but also can cause a series of potential safety hazard.According to statistics, gear-box is as the important drive disk assembly of blower fan, and the fault rate of these parts is very high.So, in order to ensure safe and stable operation and the persistently effectively generating of blower fan, gear-box is carried out fault diagnosis work and is necessary.But traditional method such as spectrum analysis etc., although it is capable of detecting when fault single, simple, but the identification of complex fault cannot be satisfied with.Therefore, it is necessary to propose a kind of efficiency is high, performance is good method for diagnosing faults to solve this problem.
Summary of the invention
In order to overcome the deficiency of existing fault diagnosis technology, it is an object of the invention to provide a kind of method for wind-driven generator wheel-box fault diagnosis, whether the running status that the method can analyze gear-box is normal, it is possible to determine trouble unit under nonserviceabling.
In order to achieve the above object, the present invention proposes a kind of wind-driven generator wheel-box method for diagnosing faults, comprises the following steps:
Vibration signal when gear-box runs is obtained by the vibrating sensor being arranged on gear case of blower casing;
The wavelet packet analysis method vibration signal to collecting is adopted to carry out three layers decomposition analysis;
Vibration signal after wavelet packet analysis is carried out empirical mode decomposition, and extracts the one-component of signal;
First component of signal extracted is carried out characteristics extraction work, characteristic vector used during as fault diagnosis;
Obtain the characteristic vector sample of gear-box historical failure data;
By support vector machine, features described above vector sample is trained, parameter used during using that the highest for classification accuracy group as fault diagnosis afterwards;
Obtain the service data that gear-box is real-time, and obtain characteristic vector;
By support vector machine, features described above vector is classified, and export diagnostic result.
Further, described vibrating sensor is installed point and is respectively distributed to the axially and radially position of the low speed end of gear case of blower casing, intermediate ends, speed end.
Further, described wavelet packet three layers decomposition analysis method adopts the following step:
Set up wavelet packet change three layers exploded relationship formula;
Select corresponding threshold value that the high frequency coefficient under each decomposition scale is carried out threshold value quantizing process according to soft-threshold function;
Bottom low frequency coefficient after decomposing and high frequency coefficient are carried out one-dimensional wavelet reconstruction.
Further, described wavelet packet change three layers exploded relationship formula is expressed as:
S=AAA3+DAA3+ADA3+DDA3+AAD3+DAD3+ADD3+DDD3,
Wherein, A is the low frequency part of signal, and D is the HFS of signal.
Further, described soft-threshold function is:
Wherein, sgn (Wj,k) it is a return shaping function, Wj,kRepresent jth layer kth threshold value, if Wj,k> 0, then sgn returns 1;If Wj,k=0, then sgn returns 0;If Wj,k< 0, then sgn returns-1, and λ represents span (0≤λ≤1).
Further, described wavelet reconstruction function is:
Wherein,Representing the wavelet coefficient of the n-th node in jth layer, x (t) represents the signal after denoising, low frequency that h and g respectively soft-threshold obtains after processing and high frequency coefficient.
Further, described eigenvalue obtains respectively from time domain and frequency domain, and temporal signatures value includes peak index, kurtosis index, degree of bias index, margin index, and frequency domain character value includes that center of gravity of frequency, frequency standard be poor, root-mean-square frequency.
Conventional diagnostic method is primarily present the problems such as diagnosis speed is slow, diagnostic result is inaccurate.Experiments show that, the operation characteristic sample of gear-box plays vital effect in fault diagnosis works.Therefore, in order to improve diagnosis effect, the present invention utilizes the method that WAVELET PACKET DECOMPOSITION is combined with empirical mode decomposition that vibration signal is carried out noise reduction.First gear-box slow-speed shaft, jackshaft, axially and radially going up of high speed shaft, vibrating sensor is all installed, gathers vibration signal when gear-box runs by vibrating sensor.Secondly, the vibration signal line collected is carried out WAVELET PACKET DECOMPOSITION and reconstructs.Signal is after reconstruct, and this signal is processed by recycling empirical mode decomposition again.This method can eliminate the noise interference to signal effectively.
The eigenvalue extracted from the vibration signal after twice process more can characterize the running status of equipment, provides it to support vector machine and carries out sample training and can improve the accuracy rate of classification results.The method can not only be diagnosed to be the fault type of gear-box, and can determine abort situation, have diagnostic result accurately, result show the advantages such as clear.
Accompanying drawing explanation
Fig. 1 show the wind-driven generator wheel-box method for diagnosing faults flow chart of present pre-ferred embodiments.
Fig. 2 show the three layers WAVELET PACKET DECOMPOSITION figure of present pre-ferred embodiments.
Detailed description of the invention
Provide the specific embodiment of the present invention below in conjunction with accompanying drawing, but the invention is not restricted to following embodiment.According to the following describes and claims, advantages and features of the invention will be apparent from.It should be noted that, accompanying drawing all adopts the form simplified very much and all uses non-ratio accurately, is only used for convenient, to aid in illustrating the embodiment of the present invention lucidly purpose.
Refer to Fig. 1, Fig. 1 and show the wind-driven generator wheel-box method for diagnosing faults flow chart of present pre-ferred embodiments.Owing to conventional diagnostic method there will be the problems such as diagnosis speed is slow, diagnostic result is inaccurate, so the present invention proposes a kind of wind-driven generator wheel-box method for diagnosing faults, comprise the following steps:
Step S100: obtain vibration signal when gear-box runs by the vibrating sensor being arranged on gear case of blower casing;
Step S200: adopt the wavelet packet analysis method vibration signal to collecting to carry out three layers decomposition analysis;
Step S300: the vibration signal after wavelet packet analysis is carried out empirical mode decomposition, and extracts the one-component of signal;
Step S400: first component of signal extracted is carried out characteristics extraction work, characteristic vector used during as fault diagnosis;
Step S500: obtain the characteristic vector sample of gear-box historical failure data;
Step S600: by support vector machine, features described above vector sample is trained, parameter used during using that the highest for classification accuracy group as fault diagnosis afterwards;
Step S700: obtain the service data that gear-box is real-time, and obtain characteristic vector;
Step S800: by support vector machine, features described above vector is classified, and export diagnostic result.
According to present pre-ferred embodiments, described vibrating sensor is installed point and is respectively distributed to the axially and radially position of the low speed end of gear case of blower casing, intermediate ends, speed end.
Described wavelet packet three layers decomposition analysis method adopts the following step:
Set up wavelet packet change three layers exploded relationship formula;
Select corresponding threshold value that the high frequency coefficient under each decomposition scale is carried out threshold value quantizing process according to soft-threshold function;
Bottom low frequency coefficient after decomposing and high frequency coefficient are carried out one-dimensional wavelet reconstruction.
Refer to Fig. 2, Fig. 2 and show the three layers WAVELET PACKET DECOMPOSITION figure of present pre-ferred embodiments.The relation that wavelet packet change three layers is decomposed is as follows:
S=AAA3+DAA3+ADA3+DDA3+AAD3+DAD3+ADD3+DDD3 (1)
Wherein, A is the low frequency part of signal, and D is the HFS of signal, and the number of plies of WAVELET PACKET DECOMPOSITION represents with by numeral.
Soft-threshold function is:
Wherein, sgn (Wj,k) it is a return shaping function, Wj,kRepresent jth layer kth threshold value, if Wj,k> 0, then sgn returns 1;If Wj,k=0, then sgn returns 0;If Wj,k< 0, then sgn returns-1, and λ represents span (0≤λ≤1).The method of general selected threshold is to compare the effect of noise reduction by choosing different λ values.
Wavelet reconstruction function is:
Wherein,Representing the wavelet coefficient of the n-th node in jth layer, x (t) represents the signal after denoising, low frequency that h and g respectively soft-threshold obtains after processing and high frequency coefficient.
First component of signal that empirical mode decomposition (EMD) is extracted carries out characteristics extraction work.Eigenvalue obtains respectively from time domain and frequency domain.Temporal signatures value includes peak index, kurtosis index, degree of bias index, margin index etc.;Frequency domain character value includes center of gravity of frequency, poor, the root-mean-square frequency of frequency standard etc..Characteristic vector used during using these time and frequency domain characteristics amounts as fault diagnosis.
Compared with existing diagnostic method, the present invention utilizes the method that WAVELET PACKET DECOMPOSITION is combined with empirical mode decomposition that vibration signal is carried out noise reduction, it is possible to effectively eliminate the noise interference to signal.The eigenvalue extracted from the vibration signal after after-treatment can characterize the running status of equipment exactly, and can improve the accuracy of support vector cassification.The method can not only be diagnosed to be the fault type of gear-box, and can determine abort situation, it is also possible to the method is used in the fault diagnosis of other heavy mechanical equipments.
Although the present invention is disclosed above with preferred embodiment, so it is not limited to the present invention.Persond having ordinary knowledge in the technical field of the present invention, without departing from the spirit and scope of the present invention, when being used for a variety of modifications and variations.Therefore, protection scope of the present invention is when being as the criterion depending on those as defined in claim.
Claims (7)
1. a wind-driven generator wheel-box method for diagnosing faults, it is characterised in that comprise the following steps:
Vibration signal when gear-box runs is obtained by the vibrating sensor being arranged on gear case of blower casing;
The wavelet packet analysis method vibration signal to collecting is adopted to carry out three layers decomposition analysis;
Vibration signal after wavelet packet analysis is carried out empirical mode decomposition, and extracts the one-component of signal;
First component of signal extracted is carried out characteristics extraction work, characteristic vector used during as fault diagnosis;
Obtain the characteristic vector sample of gear-box historical failure data;
By support vector machine, features described above vector sample is trained, parameter used during using that the highest for classification accuracy group as fault diagnosis afterwards;
Obtain the service data that gear-box is real-time, and obtain characteristic vector;
By support vector machine, features described above vector is classified, and export diagnostic result.
2. wind-driven generator wheel-box method for diagnosing faults according to claim 1, it is characterised in that described vibrating sensor is installed point and is respectively distributed to the axially and radially position of the low speed end of gear case of blower casing, intermediate ends, speed end.
3. wind-driven generator wheel-box method for diagnosing faults according to claim 1, it is characterised in that described wavelet packet three layers decomposition analysis method adopts the following step:
Set up wavelet packet change three layers exploded relationship formula;
Select corresponding threshold value that the high frequency coefficient under each decomposition scale is carried out threshold value quantizing process according to soft-threshold function;
Bottom low frequency coefficient after decomposing and high frequency coefficient are carried out one-dimensional wavelet reconstruction.
4. wind-driven generator wheel-box method for diagnosing faults according to claim 3, it is characterised in that described wavelet packet change three layers exploded relationship formula is expressed as:
S=AAA3+DAA3+ADA3+DDA3+AAD3+DAD3+ADD3+DDD3,
Wherein, A is the low frequency part of signal, and D is the HFS of signal.
5. wind-driven generator wheel-box method for diagnosing faults according to claim 3, it is characterised in that described soft-threshold function is:
Wherein, sgn (Wj,k) it is a return shaping function, Wj,kRepresent jth layer kth threshold value, if Wj,k> 0, then sgn returns 1;If Wj,k=0, then sgn returns 0;If Wj,k< 0, then sgn returns-1, and λ represents span (0≤λ≤1).
6. wind-driven generator wheel-box method for diagnosing faults according to claim 3, it is characterised in that described wavelet reconstruction function is:
Wherein,Representing the wavelet coefficient of the n-th node in jth layer, x (t) represents the signal after denoising, low frequency that h and g respectively soft-threshold obtains after processing and high frequency coefficient.
7. wind-driven generator wheel-box method for diagnosing faults according to claim 1, it is characterized in that, described eigenvalue obtains respectively from time domain and frequency domain, temporal signatures value includes peak index, kurtosis index, degree of bias index, margin index, and frequency domain character value includes that center of gravity of frequency, frequency standard be poor, root-mean-square frequency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610178646.8A CN105784353A (en) | 2016-03-25 | 2016-03-25 | Fault diagnosis method for gear case of aerogenerator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610178646.8A CN105784353A (en) | 2016-03-25 | 2016-03-25 | Fault diagnosis method for gear case of aerogenerator |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105784353A true CN105784353A (en) | 2016-07-20 |
Family
ID=56391650
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610178646.8A Pending CN105784353A (en) | 2016-03-25 | 2016-03-25 | Fault diagnosis method for gear case of aerogenerator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105784353A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106292622A (en) * | 2016-07-21 | 2017-01-04 | 中国人民解放军军械工程学院 | Fault distinguishing method based on the simulation of wavelet character value tolerance threshold value random statistical |
CN106596116A (en) * | 2016-11-29 | 2017-04-26 | 西安理工大学 | Vibration fault diagnosis method of wind generating set |
CN106769142A (en) * | 2016-12-23 | 2017-05-31 | 潘敏 | A kind of metallurgic fan machinery method for diagnosing faults |
CN107525671A (en) * | 2017-07-28 | 2017-12-29 | 中国科学院电工研究所 | A kind of wind-powered electricity generation driving-chain combined failure character separation and discrimination method |
CN107560844A (en) * | 2017-07-25 | 2018-01-09 | 广东工业大学 | A kind of fault diagnosis method and system of gearbox of wind turbine |
CN107907324A (en) * | 2017-10-17 | 2018-04-13 | 北京信息科技大学 | A kind of Fault Diagnosis of Gear Case method composed based on DTCWT and order |
CN108318249A (en) * | 2018-01-24 | 2018-07-24 | 广东石油化工学院 | A kind of method for diagnosing faults of bearing in rotating machinery |
CN108710889A (en) * | 2018-04-02 | 2018-10-26 | 天津大学 | A kind of scarce cylinder method for diagnosing faults of automobile engine |
CN109029996A (en) * | 2018-09-11 | 2018-12-18 | 温州大学苍南研究院 | A kind of hub bearing method for diagnosing faults |
CN109063782A (en) * | 2018-08-16 | 2018-12-21 | 中国水利水电科学研究院 | A kind of adaptive pumping plant intelligent fault diagnosis method |
CN109323860A (en) * | 2018-10-31 | 2019-02-12 | 广东石油化工学院 | A kind of rotating machinery gearbox fault data set optimization method |
CN111397901A (en) * | 2019-03-12 | 2020-07-10 | 上海电机学院 | Rolling bearing fault diagnosis method based on wavelet and improved PSO-RBF neural network |
CN111562105A (en) * | 2020-03-25 | 2020-08-21 | 浙江工业大学 | Wind turbine generator gearbox fault diagnosis method based on wavelet packet decomposition and convolutional neural network |
CN111721528A (en) * | 2020-05-18 | 2020-09-29 | 浙江工业大学 | Wind generating set gear box fault early warning method based on CMS system big data |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997043729A1 (en) * | 1996-05-14 | 1997-11-20 | Csi Technology, Inc. | Vibration data analysis based on time waveform parameters |
CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
CN103033362A (en) * | 2012-12-31 | 2013-04-10 | 湖南大学 | Gear fault diagnosis method based on improving multivariable predictive models |
CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
CN104392082A (en) * | 2014-07-10 | 2015-03-04 | 中山火炬职业技术学院 | Diagnosis method for initial failure of gearbox of wind generating set based on vibration monitoring |
CN104792520A (en) * | 2015-04-09 | 2015-07-22 | 中山火炬职业技术学院 | Fault diagnosis method for gear case of wind turbine generator system |
CN104863840A (en) * | 2015-03-16 | 2015-08-26 | 北京化工大学 | Reciprocating compressor intelligent diagnosis method based on EMD-PCA |
-
2016
- 2016-03-25 CN CN201610178646.8A patent/CN105784353A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997043729A1 (en) * | 1996-05-14 | 1997-11-20 | Csi Technology, Inc. | Vibration data analysis based on time waveform parameters |
CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
CN103033362A (en) * | 2012-12-31 | 2013-04-10 | 湖南大学 | Gear fault diagnosis method based on improving multivariable predictive models |
CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
CN104392082A (en) * | 2014-07-10 | 2015-03-04 | 中山火炬职业技术学院 | Diagnosis method for initial failure of gearbox of wind generating set based on vibration monitoring |
CN104863840A (en) * | 2015-03-16 | 2015-08-26 | 北京化工大学 | Reciprocating compressor intelligent diagnosis method based on EMD-PCA |
CN104792520A (en) * | 2015-04-09 | 2015-07-22 | 中山火炬职业技术学院 | Fault diagnosis method for gear case of wind turbine generator system |
Non-Patent Citations (2)
Title |
---|
伍雪冬: "《非线性时间序列在线预测建模与仿真》", 30 November 2015 * |
罗忠辉 等: "小波变换及经验模式分解方法在电机轴承早期故障诊断中的应用", 《中国电机工程学报》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106292622A (en) * | 2016-07-21 | 2017-01-04 | 中国人民解放军军械工程学院 | Fault distinguishing method based on the simulation of wavelet character value tolerance threshold value random statistical |
CN106596116A (en) * | 2016-11-29 | 2017-04-26 | 西安理工大学 | Vibration fault diagnosis method of wind generating set |
CN106769142A (en) * | 2016-12-23 | 2017-05-31 | 潘敏 | A kind of metallurgic fan machinery method for diagnosing faults |
CN107560844A (en) * | 2017-07-25 | 2018-01-09 | 广东工业大学 | A kind of fault diagnosis method and system of gearbox of wind turbine |
CN107525671A (en) * | 2017-07-28 | 2017-12-29 | 中国科学院电工研究所 | A kind of wind-powered electricity generation driving-chain combined failure character separation and discrimination method |
CN107907324A (en) * | 2017-10-17 | 2018-04-13 | 北京信息科技大学 | A kind of Fault Diagnosis of Gear Case method composed based on DTCWT and order |
CN108318249A (en) * | 2018-01-24 | 2018-07-24 | 广东石油化工学院 | A kind of method for diagnosing faults of bearing in rotating machinery |
CN108710889A (en) * | 2018-04-02 | 2018-10-26 | 天津大学 | A kind of scarce cylinder method for diagnosing faults of automobile engine |
CN109063782B (en) * | 2018-08-16 | 2021-08-24 | 中国水利水电科学研究院 | Intelligent fault diagnosis method for self-adaptive pump station |
CN109063782A (en) * | 2018-08-16 | 2018-12-21 | 中国水利水电科学研究院 | A kind of adaptive pumping plant intelligent fault diagnosis method |
CN109029996A (en) * | 2018-09-11 | 2018-12-18 | 温州大学苍南研究院 | A kind of hub bearing method for diagnosing faults |
CN109323860A (en) * | 2018-10-31 | 2019-02-12 | 广东石油化工学院 | A kind of rotating machinery gearbox fault data set optimization method |
CN111397901A (en) * | 2019-03-12 | 2020-07-10 | 上海电机学院 | Rolling bearing fault diagnosis method based on wavelet and improved PSO-RBF neural network |
CN111562105A (en) * | 2020-03-25 | 2020-08-21 | 浙江工业大学 | Wind turbine generator gearbox fault diagnosis method based on wavelet packet decomposition and convolutional neural network |
CN111721528A (en) * | 2020-05-18 | 2020-09-29 | 浙江工业大学 | Wind generating set gear box fault early warning method based on CMS system big data |
CN111721528B (en) * | 2020-05-18 | 2022-04-05 | 浙江工业大学 | Wind generating set gear box fault early warning method based on CMS system big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105784353A (en) | Fault diagnosis method for gear case of aerogenerator | |
Wang et al. | Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: A review | |
CN102798529B (en) | Method and system for diagnosing bearing faults of large-size wind turbine bearing | |
Li et al. | A new noise-controlled second-order enhanced stochastic resonance method with its application in wind turbine drivetrain fault diagnosis | |
Daneshi-Far et al. | Review of failures and condition monitoring in wind turbine generators | |
CN105136454A (en) | Wind turbine gear box fault recognition method | |
CN104677623B (en) | A kind of blade of wind-driven generator fault acoustics in place diagnostic method and monitoring system | |
CN102944418B (en) | Wind turbine generator group blade fault diagnosis method | |
CN102937522B (en) | Composite fault diagnosis method and system of gear case | |
CN106908241A (en) | A kind of bearing fault method of discrimination being combined with Wavelet Denoising Method based on LMD | |
CN103176128A (en) | Method and system for forcasting state of wind generating set and diagnosing intelligent fault | |
CN104392082A (en) | Diagnosis method for initial failure of gearbox of wind generating set based on vibration monitoring | |
CN103234748B (en) | Klingelnberg bevel gear fault diagnosis method based on sensitive IMF (instinct mode function) components | |
CN109655266B (en) | Wind turbine generator bearing fault diagnosis method based on AVMD and spectrum correlation analysis | |
CN103115789A (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
Shifat et al. | EEMD assisted supervised learning for the fault diagnosis of BLDC motor using vibration signal | |
CN202661241U (en) | Vibration test device for wind power gear box simulation | |
CN106055734A (en) | Method for failure diagnosis of wind power gearbox | |
CN107524572A (en) | A kind of wind-driven generator set on line state monitoring and method for diagnosing faults | |
CN103940611A (en) | Self-adaptive anomaly detection method for rolling bearing of wind generator set under variable working conditions | |
CN105065212A (en) | Checking method and system of wind generation sets of wind power plant | |
CN110987494A (en) | Method for monitoring cavitation state of water turbine based on acoustic emission | |
CN202793793U (en) | Large wind generation set bearing fault diagnosis system | |
CN104792520A (en) | Fault diagnosis method for gear case of wind turbine generator system | |
CN111209934A (en) | Fan fault prediction and alarm method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160720 |
|
RJ01 | Rejection of invention patent application after publication |