CN108760302A - A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing - Google Patents
A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing Download PDFInfo
- Publication number
- CN108760302A CN108760302A CN201810431637.4A CN201810431637A CN108760302A CN 108760302 A CN108760302 A CN 108760302A CN 201810431637 A CN201810431637 A CN 201810431637A CN 108760302 A CN108760302 A CN 108760302A
- Authority
- CN
- China
- Prior art keywords
- fault
- vibration
- signal
- evidence
- formula
- 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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing, step 1：Create template library：Offline created wind power generating set bear vibration template library；Step 2：Data acquire：In Wind turbines monitor platform on-line, the vibration acceleration signal of the bearing on synchronous acquisition four direction, the configuration work of data acquisition interface data acquisition card；Step 3：Signal tentatively merges：During signal acquisition, sensor can be influenced by noise and sensor itself, pre-processed to the collected signal of institute, enable acquired signals retention fault information to greatest extent；Step 4：Characteristics extraction：The vibration signal after fusion is decomposed into different frequency bands using EMD algorithms；Step 5：Malfunction monitoring：BP neural network, mode calculating fault features vector and the similarity for vibrating masterplate of Euclidean distance is respectively adopted, the result of two methods is sent into as evidence body in D-S evidence theory and carries out decision judgement, and carries out fault pre-alarming.
Description
Technical field
The present invention relates to wind power generation plant, the specifically a kind of on-line monitoring and failure of wind power generating set bearing
Diagnostic system.
Background technology
Wind power bearing is the core component of wind power generating set, and projected life requires to be more than 20 years, once failure can be led
The failure for causing wind power generating set complete machine, causes huge economic loss.In order to find bearing in the process of running latent in time
In failure factor, ensures the operation of Wind turbines efficient stable, it is implemented to monitor on-line, is carried out at the same time fault diagnosis meaning very
It is great.
The monitoring running state of current existing Wind turbines typically utilizes slave computer progress signal acquisition, then on
It is transmitted to long-range host computer and does analyzing processing, alarm signal is sent out when noting abnormalities, there are apparent hysteresis qualitys for diagnosis process, lack
Weary online and alarm function.
Existing Patent No.：201310619384, patent is entitled：A kind of Wind turbines on-line monitoring instant alarming and failure
In diagnostic system, the structure used in terms of signal analysis and processing is pre-processed to gathered data, and the feature of signal specific is extracted,
Characteristic value is differentiated, due to the complexity of mechanical structure, the reason of causing mechanical equipment fault is varied, adjoint in addition
The sign of failure is also to become increasingly complex, single phenomena such as data progress analyzing processing is often led to false-alarm, failed to report.
In conclusion being directed to problems of the prior art, it is necessary to provide a kind of with practicability, novelty and wound
The device for the property made.
Invention content
Due to the complexity of mechanical structure, the reason of causing mechanical equipment fault, is varied, with the sign of failure
It is to become increasingly complex, single phenomena such as is often caused by false-alarm, is failed to report for data progress analyzing processing, and deposit in the prior art
Alarm signal cannot be sent out when lacking the function of online and alarm, and noting abnormalities, diagnosis process exists apparent stagnant
Afterwards the problems such as property, therefore, the present invention provides a kind of on-line monitoring and fault diagnosis system of wind power generating set bearing, the system
Use information integration technology carries out a variety of analyzing processings such as related, combination and estimation, to carry to multiple sensor measurement signals
The precision of high state identification, realizes the comprehensive assessment to status information to be measured.It may finally be in Wind turbine operational process
It synchronizes and bearing is monitored on-line, alarm promptly and accurately simultaneously finds fault type.
The present invention by the following technical programs, a kind of on-line monitoring and fault diagnosis system of wind power generating set bearing,
Specifically include following steps：
Step 1：Create template library：Offline created wind power generating set bear vibration template library, including：Bearing inner race event
Barrier, bearing outer ring failure, bearing roller failure and bearing normal condition；
Step 2：Data acquire：In Wind turbines monitor platform on-line, bearing on synchronous acquisition four direction shakes
Dynamic acceleration signal, the configuration work of data acquisition interface data acquisition card specifically include：The selection of device number, channel
Number selection, buffer size, sampling rate and sampling number；
Step 3：Signal tentatively merges：During signal acquisition, sensor can be by noise and sensor itself
It influences, the collected signal of institute is pre-processed, enables acquired signals retention fault information to greatest extent, passes through related letter
Number weighting method merges the vibration acceleration signal of the four direction of synchronous acquisition.
Step 4：Characteristics extraction：The vibration signal after fusion is decomposed into different frequency bands using EMD algorithms, then
The energy value of the natural mode of vibration component IMF after decomposing is calculated, formula is such as shown in (1)：
Wherein, n is the signal total length of j-th of IMF, xjmIt is the m-th point of corresponding signal amplitude of j-th of IMF；
The energy of i IMF is calculated separately, then is with the feature vector of its composition, formula is such as shown in (2)：
T=[Ec1,Ec2,,Eci] (2)
Rear final fault feature vector is normalized in it, and formula is such as shown in (3)：
T=[E1,E2,,Ei] (3)
Step 5：Malfunction monitoring：Be respectively adopted BP neural network, Euclidean distance mode calculating fault features vector with shake
The result of two methods is sent into as evidence body in D-S evidence theory and carries out decision judgement, and carries out by the similarity of dynamic model version
Fault pre-alarming.
As a kind of perferred technical scheme, step 5 specifically includes following steps：
Step 5.1：BP neural network, and preservation model are trained using the energy feature Value Data in vibration masterplate；
Step 5.2：N fault feature vector will be obtained and be sent into trained BP neural network model as input vector
In, obtain diagnostic result and as an evidence body；
Step 5.3：N fault feature vector of acquisition and the energy eigenvalue in vibration masterplate are subjected to Euclidean distance phase
Estimate matching like degree, used matching, formula is such as shown in (4)：
Wherein, xiFor i-th of component of fault feature vector x, xjIt is j-th point of feature vector x in vibration template library
Amount, D (xi,xj) it is Euclidean distance similarity measure value, and as second evidence body；
Step 5.4：Two evidence bodies are carried out to the synthesis of D-S evidence theory, setting identification framework U={ F1,F2,F3,F4}
Respectively represent inner ring failure, outer ring failure, rolling element failure, normal condition；The elementary probability that two evidences carry is calculated separately to assign
Value, formula is such as shown in (5)：
Wherein：dijThe manhatton distance (ManhattanDistance) of-evidence body i and target j output vectors；
Q-fault type number；The sum of p-evidence body；
The coefficient of reliability of each evidence bodies of α-indicates the trusting degree to the judging result of this evidence body；
mi(U) probabilistic probability assignment of-i-th evidence body；
Then shown according to formula such as (6)：
Wherein：The conflict spectrum between each evidence body is represented, if K ≠ 1,
Then m (C) is as basic probability assignment；If K=1, m1,m2,…,mnBetween it is conflicting, can not be combined by formula,
CoefficientReferred to as normalization coefficient, the effect of the coefficient are the probability for preventing from imparting non-zero to empty set in anabolic process
Value.
Step 5.5：Decision based on Basic Probability As-signment is alarmed：
IfAnd meeting the following conditions, formula is such as shown in (7)：
If it does, formula such as (8) is shown：
Then by A1As the final result of judgement, ε1And ε2It is preset decision threshold threshold value, threshold value ε1=0.55, ε2
=0.1.
Compared with prior art, with the beneficial effects of the present invention are：
(1) it is more to carry out related, combination and estimation etc. to multiple sensor measurement signals for use information integration technology of the present invention
Kind analyzing processing realizes the comprehensive assessment to status information to be measured to improve the precision of state recognition, may finally be in wind
It is synchronized in power unit running process and bearing is monitored on-line, alarm promptly and accurately simultaneously finds fault type.
(2) present invention is in terms of software analyzing processing, the method being combined with barrier diagnostic techniques using information fusion technology,
Create Wind turbines on-line monitoring and fault diagnosis system.
(3) present invention selects four acceleration sensors to be separately mounted to four direction up and down in terms of data acquisition,
And carry out synchronous data collection.
(4) it compared with prior art, the present invention improving vibration fault monitoring method, is extracted by Hilbert-Huang transform
The energy of vibration signal characteristics frequency range constructs fault feature vector, and BP neural network, Euclidean distance, D-S cards is then respectively adopted
The similarity that characteristic spectra energy and the characteristic spectra energy in vibration signal template library are calculated according to theoretical method, according to similar
Degree is estimated matching result and is predicted fault verification alarm.
Description of the drawings
The line of Fig. 1 present invention monitors Troubleshooting Flowchart；
Acceleration transducer point layout in a kind of specific embodiment of Fig. 2 present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with attached drawing 1 and embodiment,
The present invention will be described in further detail.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention,
It is not intended to limit the present invention.
In conjunction with Fig. 1 and Fig. 2, the present invention is further described in detail：A kind of on-line monitoring of wind power generating set bearing
With fault diagnosis system, following steps are specifically included：
Step 1：Create template library：Offline created wind power generating set bear vibration template library, including：Bearing inner race event
Barrier, bearing outer ring failure, bearing roller failure and bearing normal condition；
Step 2：Data acquire：In Wind turbines monitor platform on-line, bearing on synchronous acquisition four direction shakes
Dynamic acceleration signal, the configuration work of data acquisition interface data acquisition card specifically include：The selection of device number, channel
Number selection, buffer size, sampling rate and sampling number；
Step 3：Signal tentatively merges：During signal acquisition, sensor can be by noise and sensor itself
It influences, the collected signal of institute is pre-processed, enables acquired signals retention fault information to greatest extent, passes through related letter
Number weighting method merges the vibration acceleration signal of the four direction of synchronous acquisition.
Step 4：Characteristics extraction：The vibration signal after fusion is decomposed into different frequency bands using EMD algorithms, then
The energy value of the natural mode of vibration component IMF after decomposing is calculated, formula is such as shown in (1)：
Wherein, n is the signal total length of j-th of IMF, xjmIt is the m-th point of corresponding signal amplitude of j-th of IMF；
The energy of i IMF is calculated separately, then is with the feature vector of its composition, formula is such as shown in (2)：
T=[Ec1,Ec2,,Eci] (2)
Rear final fault feature vector is normalized in it, and formula is such as shown in (3)：
T=[E1,E2,,Ei] (3)
Step 5：Malfunction monitoring：Be respectively adopted BP neural network, Euclidean distance mode calculating fault features vector with shake
The result of two methods is sent into as evidence body in D-S evidence theory and carries out decision judgement, and carries out by the similarity of dynamic model version
Fault pre-alarming.
As a kind of perferred technical scheme, step 5 specifically includes following steps：
Step 5.1：BP neural network, and preservation model are trained using the energy feature Value Data in vibration masterplate；
Step 5.2：N fault feature vector will be obtained and be sent into trained BP neural network model as input vector
In, obtain diagnostic result and as an evidence body；
Step 5.3：N fault feature vector of acquisition and the energy eigenvalue in vibration masterplate are subjected to Euclidean distance phase
Estimate matching like degree, used matching, formula is such as shown in (4)：
Wherein, xiFor i-th of component of fault feature vector x, xjIt is j-th point of feature vector x in vibration template library
Amount, D (xi,xj) it is Euclidean distance similarity measure value, and as second evidence body；
Step 5.4：Two evidence bodies are carried out to the synthesis of D-S evidence theory, setting identification framework U={ F1,F2,F3,F4}
Respectively represent inner ring failure, outer ring failure, rolling element failure, normal condition；The elementary probability that two evidences carry is calculated separately to assign
Value, formula is such as shown in (5)：
Wherein：dijThe manhatton distance (Manhattan Distance) of-evidence body i and target j output vectors；
Q-fault type number；The sum of p-evidence body；
The coefficient of reliability of each evidence bodies of α-indicates the trusting degree to the judging result of this evidence body；
mi(U) probabilistic probability assignment of-i-th evidence body；
Then shown according to formula such as (6)：
Wherein：The conflict spectrum between each evidence body is represented, if K ≠ 1,
Then m (C) is as basic probability assignment；If K=1, m1,m2,…,mnBetween it is conflicting, can not be combined by formula,
CoefficientReferred to as normalization coefficient, the effect of the coefficient are the probability for preventing from imparting non-zero to empty set in anabolic process
Value.
Step 5.5：Decision based on Basic Probability As-signment is alarmed：
IfAnd meeting the following conditions, formula is such as shown in (7)：
If it does, formula such as (8) is shown：
Then by A1As the final result of judgement, ε1And ε2It is preset decision threshold threshold value, threshold value ε1=0.55, ε2
=0.1.
It is four kinds of operating statuses of bearing below, including：Inner ring failure, outer ring failure, rolling element failure, normal condition
Preliminary matches between fault feature vector and feature database are as a result, table 1 indicates that the diagnostic result of BP neural network, table 2 are European
The diagnostic result of distance, table 3 are the results after D-S evidence theory fusion.
Table 1：BP neural network is estimated
Table 2：Euclidean distance is estimated
The probability assignment and uncertainty for calculating separately each evidence body, as table 3 shows：
Table 3：Basic Probability As-signment mi(Fj) and uncertainty mi(U)
To sum up described in three charts, the similarity of normal condition is much smaller than malfunction, can effectively alarm, and
It can be seen from Table 3 that after being merged by D-S, uncertainty substantially reduces, and it is F3 that can be accurately judged to fault type, i.e.,
Rolling element failure.
It is a variety of to carry out related, combination and estimation etc. to multiple sensor measurement signals for use information integration technology of the present invention
Analyzing processing realizes the comprehensive assessment to status information to be measured to improve the precision of state recognition, may finally be in wind-force
It is synchronized in unit running process and bearing is monitored on-line, alarm promptly and accurately simultaneously finds fault type.
The present invention is in terms of software analyzing processing, the method being combined with barrier diagnostic techniques using information fusion technology, wound
Build Wind turbines on-line monitoring and fault diagnosis system.
The present invention selects four acceleration sensors to be separately mounted to four direction up and down in terms of data acquisition, goes forward side by side
Row synchronous data collection.
Compared with prior art, the present invention improving vibration fault monitoring method, shaken by Hilbert-Huang transform extraction
The energy of dynamic signal characteristic frequency range constructs fault feature vector, and BP neural network, Euclidean distance, D-S evidences is then respectively adopted
Theoretical method calculates the similarity of characteristic spectra energy and the characteristic spectra energy in vibration signal template library, according to similarity
Estimate matching result to predict fault verification alarm.
In the description of the present invention, it is to be understood that, term " one end ", " front upper place ", " end ", " length ", " width
The orientation or position of the instructions such as degree ", "inner", "upper", " other end ", " both ends ", "horizontal", " coaxial ", " bottom ", " lower section " are closed
System is merely for convenience of description of the present invention and simplification of the description to be based on the orientation or positional relationship shown in the drawings, rather than indicates
Or imply that signified device or element must have a particular orientation, with specific azimuth configuration and operation, therefore cannot understand
For limitation of the present invention.
In the present invention unless specifically defined or limited otherwise, term " setting ", " engagement ", " connection ", " embedded ",
Terms such as " the covers " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral；It can be with
It is mechanical connection, can also be electrical connection；It can be directly connected, can also can be indirectly connected through an intermediary two
The interaction relationship of connection or two elements inside a element, unless otherwise restricted clearly.For the common of this field
For technical staff, the specific meanings of the above terms in the present invention can be understood according to specific conditions.
The foregoing is merely the preferred embodiment of the present invention, are not intended to limit the scope of the invention, every utilization
Equivalent structure transformation made by present specification, directly or indirectly with the technology neck for being attached to other Related products
Domain is included within the scope of the present invention.
Claims (2)
1. a kind of on-line monitoring and fault diagnosis system of wind power generating set bearing, it is characterised in that：It specifically includes following several
A step：
Step 1：Create template library：Offline created wind power generating set bear vibration template library, including：Bearing inner race failure, axis
Bearing outer-ring failure, bearing roller failure and bearing normal condition；
Step 2：Data acquire：In Wind turbines monitor platform on-line, the vibration of the bearing on synchronous acquisition four direction adds
Speed signal, the configuration work of data acquisition interface data acquisition card, specifically includes：The selection of device number, channel number
Selection, buffer size, sampling rate and sampling number；
Step 3：Signal tentatively merges：During signal acquisition, sensor can be by the shadow of noise and sensor itself
It rings, the collected signal of institute is pre-processed, enables acquired signals retention fault information to greatest extent, passes through correlation function
Weighting method merges the vibration acceleration signal of the four direction of synchronous acquisition.
Step 4：Characteristics extraction：The vibration signal after fusion is decomposed into different frequency bands using EMD algorithms, is then calculated
The energy value of natural mode of vibration component IMF after decomposition, formula is such as shown in (1)：
Wherein, n is the signal total length of j-th of IMF, xjmIt is the m-th point of corresponding signal amplitude of j-th of IMF；
The energy of i IMF is calculated separately, then is with the feature vector of its composition, formula is such as shown in (2)：
T=[Ec1,Ec2,…,Eci] (2)
Rear final fault feature vector is normalized in it, and formula is such as shown in (3)：
T=[E1,E2,…,Ei] (3)
Step 5：Malfunction monitoring：BP neural network, the mode calculating fault features vector of Euclidean distance and vibration mould is respectively adopted
The result of two methods is sent into as evidence body in D-S evidence theory and carries out decision judgement, and carries out failure by the similarity of version
Early warning.
2. the on-line monitoring and fault diagnosis system of a kind of wind power generating set bearing according to claim 1, special
Sign is：The step 5 specifically includes following steps：
Step 5.1：BP neural network, and preservation model are trained using the energy feature Value Data in vibration masterplate；
Step 5.2：N fault feature vector will be obtained to be sent into trained BP neural network model as input vector, obtained
Obtain diagnostic result and as an evidence body；
Step 5.3：N fault feature vector of acquisition and the energy eigenvalue in vibration masterplate are subjected to Euclidean distance similarity
Estimate matching, used matching, formula is such as shown in (4)：
Wherein, xiFor i-th of component of fault feature vector x, xjFor j-th of component of feature vector x in vibration template library, D
(xi,xj) it is Euclidean distance similarity measure value, and as second evidence body；
Step 5.4：Two evidence bodies are carried out to the synthesis of D-S evidence theory, setting identification framework U={ F1,F2,F3,F4Respectively
Represent inner ring failure, outer ring failure, rolling element failure, normal condition；The Basic Probability As-signment that two evidences carry is calculated separately, it is public
Formula is such as shown in (5)：
Wherein：dijThe manhatton distance (Manhattan Distance) of-evidence body i and target j output vectors；
Q-fault type number；The sum of p-evidence body；
The coefficient of reliability of each evidence bodies of α-indicates the trusting degree to the judging result of this evidence body；
mi(j) Basic Probability As-signment of-i-th evidence body to target j；
mi(U) probabilistic probability assignment of-i-th evidence body；
Then shown according to formula such as (6)：
Wherein：The conflict spectrum between each evidence body is represented, if K ≠ 1, m
(C) as basic probability assignment；If K=1, m1,m2,…,mnBetween it is conflicting, can not be combined by formula, coefficientReferred to as normalization coefficient, the effect of the coefficient are the probability values for preventing from imparting non-zero to empty set in anabolic process.
Step 5.5：Decision based on Basic Probability As-signment is alarmed：
IfAnd meeting the following conditions, formula is such as shown in (7)：
If it does, formula such as (8) is shown：
Then by A1As the final result of judgement, ε1And ε2It is preset decision threshold threshold value, threshold value ε1=0.55, ε2=
0.1。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810431637.4A CN108760302A (en) | 2018-05-08 | 2018-05-08 | A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810431637.4A CN108760302A (en) | 2018-05-08 | 2018-05-08 | A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108760302A true CN108760302A (en) | 2018-11-06 |
Family
ID=64009383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810431637.4A Pending CN108760302A (en) | 2018-05-08 | 2018-05-08 | A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108760302A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109341780A (en) * | 2018-11-29 | 2019-02-15 | 浙江省环境保护科学设计研究院 | A kind of more means low cost fan trouble monitoring methods |
| CN109540520A (en) * | 2018-11-29 | 2019-03-29 | 中国船舶重工集团海装风电股份有限公司 | A kind of rolling bearing fault fusion diagnosis method based on improvement D-S evidence theory |
| CN109751173A (en) * | 2019-01-16 | 2019-05-14 | 哈尔滨理工大学 | Hydraulic turbine operation method for diagnosing faults based on probabilistic neural network |
| CN110188642A (en) * | 2019-05-21 | 2019-08-30 | 国网江苏省电力有限公司检修分公司 | A kind of Reactor Fault detection method |
| CN110458248A (en) * | 2019-09-18 | 2019-11-15 | 华北电力大学（保定） | Transformer exception condition detection method based on multi-measuring point vibration signal |
| CN110781612A (en) * | 2019-11-14 | 2020-02-11 | 哈工大机器人（山东）智能装备研究院 | Fault diagnosis method and device for ball screw, computer device and storage medium |
| CN110907207A (en) * | 2019-11-25 | 2020-03-24 | 湃方科技(天津)有限责任公司 | Running state detection method and device for non-marking mechanical equipment |
| CN111381161A (en) * | 2018-12-29 | 2020-07-07 | 中国葛洲坝集团装备工业有限公司 | Remote online health state diagnosis method for generator set |
| CN111897304A (en) * | 2019-05-06 | 2020-11-06 | 埃尔构人工智能有限责任公司 | Method, apparatus and system for real-time diagnostics and fault monitoring in a machine system |
| CN113114748A (en) * | 2021-04-02 | 2021-07-13 | 天津一重电气自动化有限公司 | Intelligent prediction system based on data analysis |
| CN113806893A (en) * | 2021-11-16 | 2021-12-17 | 常州和利时信息系统工程有限公司 | Fan state monitoring and fault diagnosis method and system based on industrial internet |
| US20220043445A1 (en) * | 2019-05-06 | 2022-02-10 | Argo AI, LLC | Method and System for Real-Time Diagnostics and Fault Monitoring in a Robotic System |
| CN114593917A (en) * | 2022-03-08 | 2022-06-07 | 安徽理工大学 | Small sample bearing fault diagnosis method based on triple model |
| CN115049852A (en) * | 2022-08-15 | 2022-09-13 | 中国长江三峡集团有限公司 | Bearing fault diagnosis method and device, storage medium and electronic equipment |
| CN117109720A (en) * | 2023-09-04 | 2023-11-24 | 江南大学 | Distributed optical fiber vibration sensor based on time division multiplexing technology |
| CN117250004A (en) * | 2023-11-13 | 2023-12-19 | 山东省宇捷轴承制造有限公司 | Bearing fault diagnosis method and system based on digital signal processing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101539241A (en) * | 2009-05-07 | 2009-09-23 | 北京航空航天大学 | Hierarchical multi-source data fusion method for pipeline linkage monitoring network |
| CN103308855A (en) * | 2013-05-29 | 2013-09-18 | 上海电机学院 | Wind turbine generator system fault diagnosis method and device based on gray correlation |
| CN103914064A (en) * | 2014-04-01 | 2014-07-09 | 浙江大学 | Industrial process fault diagnosis method based on multiple classifiers and D-S evidence fusion |
| CN105373700A (en) * | 2015-10-30 | 2016-03-02 | 哈尔滨工程大学 | Method for mechanical fault diagnosis based on information entropies and evidence theory |
| CN105675274A (en) * | 2016-01-07 | 2016-06-15 | 西安交通大学 | Time-domain parameter and D-S evidence theory-based rotor running state monitoring method |
| CN106022366A (en) * | 2016-07-04 | 2016-10-12 | 杭州电子科技大学 | Rotary mechanical equipment fault diagnosis method based on neighbor evidence fusion |
| CN106347578A (en) * | 2016-10-27 | 2017-01-25 | 江苏科技大学 | Method for monitoring marine propulsion shafting bearing vibration failure |
| CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
-
2018
- 2018-05-08 CN CN201810431637.4A patent/CN108760302A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101539241A (en) * | 2009-05-07 | 2009-09-23 | 北京航空航天大学 | Hierarchical multi-source data fusion method for pipeline linkage monitoring network |
| CN103308855A (en) * | 2013-05-29 | 2013-09-18 | 上海电机学院 | Wind turbine generator system fault diagnosis method and device based on gray correlation |
| CN103914064A (en) * | 2014-04-01 | 2014-07-09 | 浙江大学 | Industrial process fault diagnosis method based on multiple classifiers and D-S evidence fusion |
| CN105373700A (en) * | 2015-10-30 | 2016-03-02 | 哈尔滨工程大学 | Method for mechanical fault diagnosis based on information entropies and evidence theory |
| CN105675274A (en) * | 2016-01-07 | 2016-06-15 | 西安交通大学 | Time-domain parameter and D-S evidence theory-based rotor running state monitoring method |
| CN106022366A (en) * | 2016-07-04 | 2016-10-12 | 杭州电子科技大学 | Rotary mechanical equipment fault diagnosis method based on neighbor evidence fusion |
| CN106347578A (en) * | 2016-10-27 | 2017-01-25 | 江苏科技大学 | Method for monitoring marine propulsion shafting bearing vibration failure |
| CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109540520A (en) * | 2018-11-29 | 2019-03-29 | 中国船舶重工集团海装风电股份有限公司 | A kind of rolling bearing fault fusion diagnosis method based on improvement D-S evidence theory |
| CN109341780A (en) * | 2018-11-29 | 2019-02-15 | 浙江省环境保护科学设计研究院 | A kind of more means low cost fan trouble monitoring methods |
| CN111381161A (en) * | 2018-12-29 | 2020-07-07 | 中国葛洲坝集团装备工业有限公司 | Remote online health state diagnosis method for generator set |
| CN109751173A (en) * | 2019-01-16 | 2019-05-14 | 哈尔滨理工大学 | Hydraulic turbine operation method for diagnosing faults based on probabilistic neural network |
| US20220043445A1 (en) * | 2019-05-06 | 2022-02-10 | Argo AI, LLC | Method and System for Real-Time Diagnostics and Fault Monitoring in a Robotic System |
| CN111897304A (en) * | 2019-05-06 | 2020-11-06 | 埃尔构人工智能有限责任公司 | Method, apparatus and system for real-time diagnostics and fault monitoring in a machine system |
| CN111897304B (en) * | 2019-05-06 | 2023-12-05 | 埃尔构人工智能有限责任公司 | Method, apparatus and system for real-time diagnostics and fault monitoring in a machine system |
| CN110188642A (en) * | 2019-05-21 | 2019-08-30 | 国网江苏省电力有限公司检修分公司 | A kind of Reactor Fault detection method |
| CN110458248A (en) * | 2019-09-18 | 2019-11-15 | 华北电力大学（保定） | Transformer exception condition detection method based on multi-measuring point vibration signal |
| CN110458248B (en) * | 2019-09-18 | 2022-08-30 | 华北电力大学（保定） | Transformer abnormal state detection method based on multi-point vibration signals |
| CN110781612A (en) * | 2019-11-14 | 2020-02-11 | 哈工大机器人（山东）智能装备研究院 | Fault diagnosis method and device for ball screw, computer device and storage medium |
| CN110907207A (en) * | 2019-11-25 | 2020-03-24 | 湃方科技(天津)有限责任公司 | Running state detection method and device for non-marking mechanical equipment |
| CN113114748A (en) * | 2021-04-02 | 2021-07-13 | 天津一重电气自动化有限公司 | Intelligent prediction system based on data analysis |
| CN113806893A (en) * | 2021-11-16 | 2021-12-17 | 常州和利时信息系统工程有限公司 | Fan state monitoring and fault diagnosis method and system based on industrial internet |
| CN114593917A (en) * | 2022-03-08 | 2022-06-07 | 安徽理工大学 | Small sample bearing fault diagnosis method based on triple model |
| CN115049852A (en) * | 2022-08-15 | 2022-09-13 | 中国长江三峡集团有限公司 | Bearing fault diagnosis method and device, storage medium and electronic equipment |
| CN115049852B (en) * | 2022-08-15 | 2022-12-02 | 中国长江三峡集团有限公司 | Bearing fault diagnosis method and device, storage medium and electronic equipment |
| CN117109720A (en) * | 2023-09-04 | 2023-11-24 | 江南大学 | Distributed optical fiber vibration sensor based on time division multiplexing technology |
| CN117109720B (en) * | 2023-09-04 | 2024-04-26 | 江南大学 | Distributed optical fiber vibration sensor based on time division multiplexing technology |
| CN117250004A (en) * | 2023-11-13 | 2023-12-19 | 山东省宇捷轴承制造有限公司 | Bearing fault diagnosis method and system based on digital signal processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108760302A (en) | A kind of on-line monitoring and fault diagnosis system of wind power generating set bearing | |
| Liu et al. | Deep adversarial domain adaptation model for bearing fault diagnosis | |
| Gou et al. | Aeroengine control system sensor fault diagnosis based on CWT and CNN | |
| CN106338406B (en) | The on-line monitoring of train traction electric drive system and fault early warning system and method | |
| CN110795510B (en) | Spacecraft system health state evaluation method based on high-dimensional data association mining | |
| WO2023123593A1 (en) | Variational mode decomposition and residual network-based aviation bearing fault diagnosis method | |
| US11669080B2 (en) | Abnormality detection device, abnormality detection method, and program | |
| CN108073158A (en) | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN106644484A (en) | Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set | |
| Chen et al. | Acoustical damage detection of wind turbine blade using the improved incremental support vector data description | |
| CN107423190B (en) | Method and device for identifying abnormal direction of log data | |
| Yan et al. | Fault diagnosis of rotating machinery equipped with multiple sensors using space-time fragments | |
| Yue et al. | An end-to-end model based on cnn-lstm for industrial fault diagnosis and prognosis | |
| CN108956111B (en) | Abnormal state detection method and detection system for mechanical part | |
| Chen et al. | A novel knowledge transfer network with fluctuating operational condition adaptation for bearing fault pattern recognition | |
| CN109000921A (en) | A kind of diagnostic method of wind generator set main shaft failure | |
| US6519575B1 (en) | System and method for classifying unknown data patterns in multi-variate feature space | |
| CN108918111A (en) | Breaker mechanical method for diagnosing faults based on the classification of k- neighbour's Bayes's multi-tag | |
| Li et al. | Intelligent fault diagnosis of aeroengine sensors using improved pattern gradient spectrum entropy | |
| Lei et al. | Fault diagnosis of rotating machinery based on a new hybrid clustering algorithm | |
| CN114443338A (en) | Sparse negative sample-oriented anomaly detection method, model construction method and device | |
| CN111428772B (en) | Photovoltaic system depth anomaly detection method based on k-nearest neighbor adaptive voting | |
| CN111539381B (en) | Construction method of wind turbine bearing fault classification diagnosis model | |
| Bilendo et al. | An intelligent data-driven machine learning approach for fault detection of wind turbines |
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 |
Application publication date: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |