CN106050580B - A kind of driving chain of wind generating set fault diagnosis method and system - Google Patents
A kind of driving chain of wind generating set fault diagnosis method and system Download PDFInfo
- Publication number
- CN106050580B CN106050580B CN201610681478.4A CN201610681478A CN106050580B CN 106050580 B CN106050580 B CN 106050580B CN 201610681478 A CN201610681478 A CN 201610681478A CN 106050580 B CN106050580 B CN 106050580B
- Authority
- CN
- China
- Prior art keywords
- fault
- tree
- event
- probability
- generating set
- 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.)
- Active
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/40—Transmission of power
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/80—Diagnostics
Abstract
The invention discloses a kind of driving chain of wind generating set method for diagnosing faults, including:Establish the driving chain of wind generating set fault message knowledge base of fault tree synthesis;It is retrieved in the knowledge base according to the fault characteristic information detected in real time, positions corresponding fault tree;According to preset data and Bayesian Network Inference in the knowledge base, each fault tree F is found outnPosterior probability P (FnShu S), obtain each fault tree probability distribution sequence;According to the fault tree probability distribution sequence order, the bottom event of all triggerings under all fault trees is retrieved and judged to obtain successively, forms failure cause diagnosis set.The present invention also provides the transmission chain fault diagnosis systems of the above-mentioned method for diagnosing faults of application.The present invention on the basis of Fault Tree Analysis by introducing Bayesian networks technique; extremely favourable foundation is provided quickly and effectively to diagnose blowing machine transmission chain failure cause; Wind turbines downtime is reduced, manual maintenance's cost is reduced, improves Generation Rate and economic benefit.
Description
Technical field
The present invention relates to wind power generating set fault diagnosis technology fields, are driven more particularly to a kind of wind power generating set
Chain fault diagnosis method and system.
Background technology
Wind Power Generation Industry is also faced with the multiple circumstances of unit failure while booming at present, wherein due to transmission
The working order of chain directly affects the performance and safety of wind power generating set, all diagnosis and detection for transmission chain failure
It is particularly important.Existing transmission chain fault detection method predominantly stays in the detection sensor hardware by increasing more redundancies
On, it relies on artificial experience and the redundant state detection information diagnosis of equipment is analyzed so that the diagnosis and detection of the transmission chain failure
Method is inefficient, reliability is not strong, complex steps, cannot obtain the fault message of the transmission chain in time.
Also in industrial control field equipment fault diagnosis, the Fault Tree Analysis (FTA) mostly used, be study system
Target of the malfunction as accident analysis of the mostly undesired generation of system, then look for causing the generation of this failure it is whole because
Element, then find out the next stage whole direct factor for causing these factors to occur, traces always that those are original, no longer need to go into seriously
Factor until.The various approach that can be broken down with analysis system using the fault tree, calculate each characteristic quantities, can
The safety and reliability of system is evaluated.But the fault tree does not have description event polymorphism and fault logic relationship is non-
Deterministic ability is not suitable for analyzing the safety and reliability of complication system.
For the system of this complexity of wind power generating set, the certain failures occurred on transmission chain may be with multiple failures
Tree is related, and it is comprehensive and accurate outstanding to failure cause positioning how quickly to carry out screening and sequencing, system to multiple fault trees
It is important.
It can be seen that above-mentioned existing driving chain of wind generating set method for diagnosing faults is upper in structure, method and use,
It obviously has inconveniences and defects, and needs to be further improved.How a kind of new fast and effectively intelligence is founded
The driving chain of wind generating set fault diagnosis method and system of transmission chain failure cause are diagnosed to be, it is real to belong to current important research and development class
One of topic.
Invention content
The technical problem to be solved in the present invention is to provide a kind of driving chain of wind generating set method for diagnosing faults, can
Fast and effectively intelligent diagnostics go out transmission chain failure cause, to overcome the shortcomings of existing transmission chain method for diagnosing faults.
In order to solve the above technical problems, the present invention provides a kind of driving chain of wind generating set method for diagnosing faults, it is described
Method includes the following steps:
(1) the driving chain of wind generating set fault message knowledge base of fault tree synthesis is established;
(2) correlation is carried out in the transmission chain fault message knowledge base according to the fault characteristic information detected in real time
Retrieval, orients corresponding fault tree number n, i.e. fault tree F1…Fn, wherein the fault characteristic information includes to be diagnosed
The fault status information S of fault message and wind power generating set drive apparatus;
(3) probability P (S), the failure that fault status information S occurs are retrieved in the transmission chain fault message knowledge base
Set FnPrior probability P (Fn), and work as fault tree FnWhen generation, probability P (the S Shu F of fault status information S generationsn), further according to
Bayesian formula P (FnShu S)=P (Fn) P (S Shu Fn)/P (S) finds out fault status information S in the corresponding fault tree Fn
Posterior probability P (FnShu S), then according to each fault tree F1…FnObtained posterior probability values being ranked sequentially from big to small, obtains
To each fault tree F1…FnProbability distribution sequence;
(4) according to each fault tree F1…FnThe sequence of probability distribution sequence from big to small, retrieves each failure successively
The criterion of the corresponding all next stage subevent triggerings of top event of tree, and itself and presence states to be diagnosed fault are judged respectively
Whether value matches, if judging to mismatch, which does not trigger, if being judged as matching, event triggering, and continue to judge to be somebody's turn to do
Whether event is bottom event, if bottom event, then retrieves stopping, if non-bottom event, continues retrieval downwards, until retrieving institute
The bottom event of all triggerings under faulty tree, and by the bottom event of all triggerings with the descending sequence shows of its probability, shape
It diagnoses and gathers at failure cause.
As an improvement of the present invention, the step (1) is established the driving chain of wind generating set fault message and is known
Know library specific method be:
(1) fault tree models are established according to wind power generating set historical failure knowledge information, wherein with trouble location be therefore
Hinder the top event set, sifting sort is carried out to fault message, to cause the event that current event occurs to establish event for its subevent
Hinder the set membership between information;
(2) the reason of causing upper level event to occur next stage event in the fault tree, is sentenced as what event triggered
According to, while setting up the relationship between each fault status information S and fault tree F;
(3) experience occurred according to known historical failure provides the probability P (S) and each failure that fault status information S occurs
Set FnPrior probability P (the F of generationn), it converts fault tree to Bayesian network, is then gone out when event using Bayesian network analysis
Barrier tree FnWhen generation, probability P (the S Shu F of fault status information S generationsn), that is, it completes to pass the wind power generating set of fault tree synthesis
The foundation of dynamic chain fault message knowledge base.
The present invention also provides a kind of transmission chain failures using above-mentioned driving chain of wind generating set method for diagnosing faults to examine
Disconnected system, the diagnostic system include:Fault message base module, fault information acquisition module, fault information analysis module,
Fault message judgment module and fault message output module,
The fault message base module, the driving chain of wind generating set fault message for establishing fault tree synthesis
Knowledge base;
The fault information acquisition module, the fault signature for detecting and acquiring driving chain of wind generating set in real time are believed
Breath, the fault information analysis module is sent to by collected fault characteristic information;
The fault information analysis module, the fault characteristic information for that will receive is in the transmission chain fault message knowledge
It is retrieved in library, orients corresponding fault tree number n, and each according to known wind turbine in the transmission chain fault message knowledge base
The Prior Probability of each node of fault tree is calculated and breaks down relevant each fault tree probability distribution sequence;
The fault message judgment module, for presence states value that will be to be diagnosed fault and the transmission chain fault message
Each event triggering criterion in knowledge base carries out matching judgment, obtains trigger event, and further judges to obtain all relevant
The bottom event of all triggerings under fault tree;
The fault message output module, all relevant fault trees for obtaining the fault message judgment module
Under all triggerings bottom event, according to its probability of happening size output be failure cause diagnosis set.
By adopting such a design, the present invention has at least the following advantages:
The present invention can be obtained fast and effectively by introducing Bayesian networks technique on the basis of Fault Tree Analysis
Failure cause diagnosis set carries out troubleshooting for Maintenance Engineer and provides extremely favourable foundation, and efficient intelligent diagnostics go out
The failure cause of wind turbine transmission chain reduces the downtime of Wind turbines critical component, reduces manual maintenance's cost, improves
Generation Rate and economic benefit solve the situation that existing fault diagnosis manually will diagnose fault message and position, are
Improve operation maintenance, enhancing automatization level provides extremely favourable help.
Description of the drawings
The above is merely an overview of the technical solutions of the present invention, in order to better understand the technical means of the present invention, below
In conjunction with attached drawing, the present invention is described in further detail with specific implementation mode.
Fig. 1 is the flow diagram of driving chain of wind generating set method for diagnosing faults of the present invention.
Fig. 2, which is wind power generating set rotating speed of the present invention, to transfinite the result schematic diagram of fault tree.
Fig. 3 is the result schematic diagram that wind power generating set rotating speed of the present invention mismatches fault tree.
Specific implementation mode
The present invention introduces Bayesian networks technique on the basis of existing Fault Tree Analysis, the Bayesian networks technique
From inference mechanism and system mode description, there is prodigious similitude with fault tree, but the Bayesian networks technique also has
It is described the ability of event polymorphism and fault logic relationship uncertainty, is more suitable for safety to complication system and can
It is analyzed by property.
With reference to shown in attached drawing 1, the step of driving chain of wind generating set method for diagnosing faults of the present invention, is as follows:
(1) the driving chain of wind generating set fault message knowledge base of fault tree synthesis is established.
Specific method is:Fault tree models (FT) are set up according to the historical failure knowledge information of wind power generating set,
Using trouble location as top event, to fault message carry out sifting sort, using cause the event occur event as
The set membership between fault message is established in the subevent of current event;Upper level event is caused to occur next stage event
The criterion that reason is triggered as event, while the relationship between each fault status information S and fault tree F is set up, and by special
Family provides the probability P (S) and each fault tree F that fault status information S occurs according to the experience that history known fault occursnOccur
Probability P (Fn), it then converts fault tree to Bayesian network, is gone out as fault tree F using Bayesian network analysisnWhen generation,
Probability P (the S Shu F that fault status information S occursn), and so on, it is established that the driving chain of wind generating set of fault tree synthesis
Fault message knowledge base.
(2) correlation is carried out in above-mentioned transmission chain fault message knowledge base according to the fault characteristic information detected in real time
Property retrieval, orient corresponding fault tree number n, i.e. fault tree F1…Fn, wherein the fault characteristic information includes to be diagnosed
The fault status information S of fault message and wind power generating set drive apparatus.
(3) probability P (S), the fault tree that fault status information S occurs are retrieved in the transmission chain fault message knowledge base
FnPrior probability P (Fn), and work as FnWhen generation, probability P (the S Shu F of fault status information S generationsn), further according to Bayes's public affairs
Formula (1) finds out fault status information S in the fault tree FnPosterior probability P (FnShu S),
P(FnShu S)=P (Fn) P (S Shu Fn)/P(S) (1)
Then according to each fault tree F1…FnObtained posterior probability values being ranked sequentially from big to small, obtains each fault tree
F1…FnProbability distribution sequence.
(4) according to obtained each fault tree F1…FnProbability distribution sequence, each fault tree of ordered retrieval from big to small
The corresponding all next stage subevents triggering of top event criterion, and judge itself and presence states value to be diagnosed fault respectively
Whether match, if fault status information S is mismatched with the criterion in fault message knowledge base, which does not trigger,
If fault status information S is matched with the criterion in fault message knowledge base, event triggering, and continue to judge the thing
Whether part is bottom event, if the event is bottom event, retrieves stopping, if non-bottom event, system will continue retrieval downwards,
Until retrieving the bottom event of all triggerings under the fault tree, then the bottom of all triggerings in all fault trees is retrieved successively
Event, and the bottom event of all triggerings is formed failure cause diagnosis set, be follow-up with the descending sequence shows of probability
Physical fault processing provides foundation.
Using the transmission chain fault diagnosis system of above-mentioned driving chain of wind generating set method for diagnosing faults, including:Failure
Information knowledge library module, fault information acquisition module, fault information analysis module, fault message judgment module and fault message are defeated
Go out module.
The fault message base module, the driving chain of wind generating set fault message for establishing fault tree synthesis are known
Know library;
The fault information acquisition module, the fault signature for detecting and acquiring driving chain of wind generating set in real time are believed
Breath, the fault information analysis module is sent to by collected fault characteristic information;
The fault information analysis module, the fault characteristic information for that will receive is in the transmission chain fault message knowledge base
Retrieval, orients corresponding fault tree number n, and according to the known each fault tree of wind turbine in the transmission chain fault message knowledge base
The Prior Probability of each node is calculated and breaks down relevant each fault tree probability distribution sequence;
The fault message judgment module, for presence states value and the transmission chain fault message knowledge that will be to be diagnosed fault
Each event triggering criterion in library carries out matching judgment, obtains trigger event, and further judges to obtain all relevant failures
The bottom event of all triggerings under tree;
The fault message output module, institute under all relevant fault trees for obtaining the fault message judgment module
The bottom event for having triggering is failure cause diagnosis set according to the output of its probability of happening size.
The detailed process of driving chain of wind generating set method for diagnosing faults of the present invention is as follows:When wind power generating set is driven
When chain breaks down, the intelligent Fault Diagnose Systems of Wind turbines receive fault characteristic information (including:Failure letter to be diagnosed
The fault status information of breath and wind power generating set drive apparatus), while the fault status information is denoted as S.Existing
It carries out retrieving with the correlation of fault status information S in fault message knowledge base, orients corresponding fault tree number n, i.e.,:Therefore
Barrier tree F1…Fn, and retrieve the probability P (S) that fault status information S occurs, fault tree FnPrior probability be P (Fn), work as FnHair
When raw, probability P (the S Shu F of fault status information S generationsn), its posteriority probability P (F is found out according to Bayesian formulanShu S), then according to
According to the ordered retrieval fault tree F of its posterior probability from big to small1…Fn, and the corresponding institute of each top event is retrieved successively
There is the criterion that next stage subevent is triggered to be matched with presence states value to be diagnosed fault.If fault status information S with
Criterion matching in fault knowledge library, then the event triggers, and continues to judge whether the event is bottom event, if the thing
Part is bottom event, then retrieves stopping, if non-bottom event, system will continue retrieval downwards, until retrieving under the fault tree
The bottom event of all triggerings.By the bottom event triggered under all fault trees with the descending sequence shows of probability, failure is formed
Cause diagnosis set, so far diagnosis terminate.
Specific embodiment is as follows:
When wind power generating set quotes wheel speed failure, intelligent Fault Diagnose Systems are believed with the malfunction first pair
Cease the relevant fault tree F of S1…FnGo through time, retrieve with the relevant all fault trees of the fault message, i.e. wheel speed is super
Limit fault tree F1 and rotating speed and mismatch fault tree F2, such as the fault tree F2 in the fault tree F1 and attached drawing 3 in attached drawing 2, and from therefore
The probability P (S)=0.22 that fault status information S occurs, fault tree F are searched in barrier information knowledge library1Prior probability P (F1)
=0.15;Work as F1When generation, probability P (the S Shu F of fault status information S generations1)=0.9 obtains its posteriority according to bayesian algorithm
Probability P (F1Shu S)=0.61;Fault tree F2Prior probability P (F2)=0.1;Work as F2When generation, what fault status information S occurred
Probability P (S Shu F2)=0.3 obtains its posteriority probability P (F according to bayesian algorithm2Shu S)=0.14.
According to fault tree F1、F2Probability size distribution situation, detect failure successively according to the sequence of probability from big to small
Tree, i.e., the preferentially fault tree F of retrieval maximum probability1, as shown in Fig. 2, " rotation speed of fan transfinites " fault tree, the fault tree F1's
All event S1 ... S21 indicate, intelligent Fault Diagnose Systems are from fault tree F1Top event S1 successively retrieve the next stage of S1
Subevent S2 and S3, according to waiting for that failure judgement characteristic information infers subevent S2 and be triggered, S3 is not triggered, and then judges S2
Whether it is bottom event, if it is not, then next stage subevent S4, S5, S6 and S7 of retrieval S2, infer the bottom thing of triggering failure
Part, i.e. fault tree F1In the failure there may be reasons.And so on, intelligent Fault Diagnose Systems continue the event to probability second
Barrier tree F2All events make inferences, as shown in Fig. 3, be diagnosed to be fault tree F2The middle bottom event that may trigger failure.Most
Eventually, the bottom event (i.e. possible failure cause) that intelligent Fault Diagnose Systems trigger all fault trees is with the descending sequence of probability
Row are shown, and are accumulated failure cause diagnosis set, are provided Maintenance Engineer and carry out troubleshooting, so far diagnosis terminates.
The present invention is based on the polymorphic Fault Tree Analysis of Bayesian network can solve complication system, diagnostic area greatly and nothing
The problem of method quick positioning failure tree, meanwhile, it is successively retrieved using rule-based reasoning method to generating the fault tree belonging to failure
Match, reduce the workload of the fault diagnosis to impossible intermediate event, improves the speed and fault diagnosis of fault diagnosis
Precision, reduce the downtime of Wind turbines critical component, reduce manual maintenance's cost, improve Generation Rate and economical imitate
Benefit.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, this
Field technology personnel make a little simple modification, equivalent variations or modification using the technology contents of the disclosure above, all fall within this hair
In bright protection domain.
Claims (3)
1. a kind of driving chain of wind generating set method for diagnosing faults, which is characterized in that described method includes following steps:
(1) the driving chain of wind generating set fault message knowledge base of fault tree synthesis is established;
(2) correlation retrieval is carried out in the transmission chain fault message knowledge base according to the fault characteristic information detected in real time,
Orient corresponding fault tree number n, i.e. fault tree F1…Fn, wherein the fault characteristic information includes that failure to be diagnosed is believed
The fault status information S of breath and wind power generating set drive apparatus;
(3) probability P (S), the fault tree F that fault status information S occurs are retrieved in the transmission chain fault message knowledge basen's
Prior probability P (Fn), and work as fault tree FnWhen generation, probability P (the S Shu F of fault status information S generationsn), further according to Bayes
Formula P (FnShu S)=P (Fn) P (S Shu Fn)/P (S) finds out fault status information S in the corresponding fault tree FnPosteriority
Probability P (FnShu S), then according to each fault tree F1…FnObtained posterior probability values being ranked sequentially from big to small, obtain it is each therefore
Barrier tree F1…FnProbability distribution sequence;
(4) according to each fault tree F1…FnThe sequence of probability distribution sequence from big to small, retrieves each fault tree successively
The criterion of the corresponding all next stage subevent triggerings of top event, and judge that it is with presence states value to be diagnosed fault respectively
No matching, if judging to mismatch, which does not trigger, if being judged as matching, event triggering, and continue to judge the event
Whether it is bottom event, if bottom event, then retrieves stopping, if non-bottom event, continue retrieval downwards, until retrieves all events
The bottom event of all triggerings under barrier tree, and the bottom event of all triggerings is formed into event with the descending sequence shows of its probability
Hinder cause diagnosis set.
2. driving chain of wind generating set method for diagnosing faults according to claim 1, which is characterized in that the step
(1) specific method for establishing the driving chain of wind generating set fault message knowledge base is:
(1) fault tree models are established according to wind power generating set historical failure knowledge information, wherein using trouble location as fault tree
Top event, to fault message carry out sifting sort, with cause current event occur event be its subevent, establish failure letter
Set membership between breath;
(2) criterion that the reason of causing upper level event to occur next stage event in the fault tree triggers as event, together
When set up relationship between each fault status information S and fault tree F;
(3) experience occurred according to known historical failure provides the probability P (S) and each fault tree F that fault status information S occursnHair
Raw prior probability P (Fn), it converts fault tree to Bayesian network, is then gone out as fault tree F using Bayesian network analysisn
When generation, probability P (the S Shu F of fault status information S generationsn), that is, complete the driving chain of wind generating set to fault tree synthesis
The foundation of fault message knowledge base.
3. a kind of transmission chain failure of application driving chain of wind generating set method for diagnosing faults as claimed in claim 1 or 2
Diagnostic system, which is characterized in that the diagnostic system includes:Fault message base module, fault information acquisition module, failure
Information analysis module, fault message judgment module and fault message output module,
The fault message base module, the driving chain of wind generating set fault message knowledge for establishing fault tree synthesis
Library;
The fault information acquisition module, the fault characteristic information for detecting and acquiring driving chain of wind generating set in real time,
Collected fault characteristic information is sent to the fault information analysis module;
The fault information analysis module, the fault characteristic information for that will receive is in the transmission chain fault message knowledge base
Retrieval, orients corresponding fault tree number n, and according to the known each failure of wind turbine in the transmission chain fault message knowledge base
The Prior Probability for setting each node is calculated and breaks down relevant each fault tree probability distribution sequence;
The fault message judgment module, for presence states value that will be to be diagnosed fault and the transmission chain fault message knowledge
Each event triggering criterion in library carries out matching judgment, obtains trigger event, and further judges to obtain all relevant failures
The bottom event of all triggerings under tree;
The fault message output module, institute under all relevant fault trees for obtaining the fault message judgment module
The bottom event for having triggering is failure cause diagnosis set according to the output of its probability of happening size.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610681478.4A CN106050580B (en) | 2016-08-17 | 2016-08-17 | A kind of driving chain of wind generating set fault diagnosis method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610681478.4A CN106050580B (en) | 2016-08-17 | 2016-08-17 | A kind of driving chain of wind generating set fault diagnosis method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106050580A CN106050580A (en) | 2016-10-26 |
CN106050580B true CN106050580B (en) | 2018-10-23 |
Family
ID=57195034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610681478.4A Active CN106050580B (en) | 2016-08-17 | 2016-08-17 | A kind of driving chain of wind generating set fault diagnosis method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106050580B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115065289A (en) * | 2022-07-28 | 2022-09-16 | 南方电网调峰调频发电有限公司检修试验分公司 | Collaborative maintenance method and system based on rotor magnetic pole defects |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108071562B (en) * | 2016-11-17 | 2021-01-15 | 中国电力科学研究院 | Wind turbine generator energy efficiency state diagnosis method based on energy flow |
CN108226775B (en) * | 2016-12-13 | 2020-06-30 | 北京金风科创风电设备有限公司 | Fault self-detection method and device of wind driven generator |
CN108320040B (en) * | 2017-01-17 | 2021-01-26 | 国网重庆市电力公司 | Acquisition terminal fault prediction method and system based on Bayesian network optimization algorithm |
CN107045584B (en) * | 2017-05-11 | 2020-08-25 | 河海大学 | Power frequency vibration abnormity fault diagnosis method suitable for water pump rotor system |
CN107704933A (en) * | 2017-09-01 | 2018-02-16 | 新疆金风科技股份有限公司 | Wind power generating set fault diagnosis system and method |
CN107544462B (en) * | 2017-09-07 | 2019-07-16 | 新疆金风科技股份有限公司 | For diagnosing the method and system of the failure of wind power generating set |
CN108876002B (en) * | 2018-05-03 | 2021-08-17 | 浙江运达风电股份有限公司 | Method for optimizing inventory of spare parts of wind generating set |
CN110645153B (en) * | 2018-06-27 | 2020-11-24 | 北京金风科创风电设备有限公司 | Wind generating set fault diagnosis method and device and electronic equipment |
CN109580215B (en) * | 2018-11-30 | 2020-09-29 | 湖南科技大学 | Wind power transmission system fault diagnosis method based on deep generation countermeasure network |
CN109697210B (en) * | 2018-12-26 | 2023-09-05 | 天津瑞源电气有限公司 | Online diagnosis method for wind turbine generator set associated faults |
WO2020183340A1 (en) * | 2019-03-14 | 2020-09-17 | Abb Schweiz Ag | A method of detecting faults in intelligent electronic devices |
CN110968619A (en) * | 2019-11-28 | 2020-04-07 | 机械工业仪器仪表综合技术经济研究所 | Hydraulic press self-learning fault diagnosis method and system based on Fault Tree (FTA) |
CN111160579A (en) * | 2019-12-30 | 2020-05-15 | 中国船舶重工集团公司第七一三研究所 | Platform door fault diagnosis and analysis method based on weight |
US11416326B2 (en) | 2020-08-28 | 2022-08-16 | Sap Se | Systems and methods for failure diagnosis using fault tree |
CN112819028B (en) * | 2020-12-29 | 2024-02-02 | 重庆大学 | Fault diagnosis method of medical fresh air system based on fault diagnosis model |
CN114296435B (en) * | 2021-12-30 | 2023-12-01 | 沈阳东睿科技有限公司 | Aeroengine fault diagnosis system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103375349A (en) * | 2012-04-24 | 2013-10-30 | 华锐风电科技(集团)股份有限公司 | Transmission chain of wind generating set and wind generating set |
DE102012024273A1 (en) * | 2012-12-12 | 2014-06-12 | Robert Bosch Gmbh | Method for tuning load-dependent processes in electric components of wind turbine, involves increasing or reducing individual burdens in one component during remaining term, so as to adjust individual residual duration of term life |
CN104005917A (en) * | 2014-04-30 | 2014-08-27 | 叶翔 | Method and system for predicting wind machine state based on Bayesian reasoning mode |
CN104019000A (en) * | 2014-06-23 | 2014-09-03 | 宁夏银星能源股份有限公司 | Load spectrum determination and proactive maintenance system of wind generating set |
CN204553118U (en) * | 2015-04-20 | 2015-08-12 | 中国大唐集团新能源股份有限公司 | A kind of novel Wind turbines condition monitoring system |
CN105569931A (en) * | 2015-12-31 | 2016-05-11 | 三一重型能源装备有限公司 | Transmission chain fault diagnosis method for wind power generator |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5085912B2 (en) * | 2006-11-07 | 2012-11-28 | 那須電機鉄工株式会社 | Fail-safe control device and control method for wind power generator |
-
2016
- 2016-08-17 CN CN201610681478.4A patent/CN106050580B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103375349A (en) * | 2012-04-24 | 2013-10-30 | 华锐风电科技(集团)股份有限公司 | Transmission chain of wind generating set and wind generating set |
DE102012024273A1 (en) * | 2012-12-12 | 2014-06-12 | Robert Bosch Gmbh | Method for tuning load-dependent processes in electric components of wind turbine, involves increasing or reducing individual burdens in one component during remaining term, so as to adjust individual residual duration of term life |
CN104005917A (en) * | 2014-04-30 | 2014-08-27 | 叶翔 | Method and system for predicting wind machine state based on Bayesian reasoning mode |
CN104019000A (en) * | 2014-06-23 | 2014-09-03 | 宁夏银星能源股份有限公司 | Load spectrum determination and proactive maintenance system of wind generating set |
CN204553118U (en) * | 2015-04-20 | 2015-08-12 | 中国大唐集团新能源股份有限公司 | A kind of novel Wind turbines condition monitoring system |
CN105569931A (en) * | 2015-12-31 | 2016-05-11 | 三一重型能源装备有限公司 | Transmission chain fault diagnosis method for wind power generator |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115065289A (en) * | 2022-07-28 | 2022-09-16 | 南方电网调峰调频发电有限公司检修试验分公司 | Collaborative maintenance method and system based on rotor magnetic pole defects |
Also Published As
Publication number | Publication date |
---|---|
CN106050580A (en) | 2016-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106050580B (en) | A kind of driving chain of wind generating set fault diagnosis method and system | |
CN108376298A (en) | A kind of Wind turbines generator-temperature detection fault pre-alarming diagnostic method | |
AU2010344438B2 (en) | Operation machine monitoring diagnosis device | |
CN110287552A (en) | Based on the motor bearings fault diagnosis method and system for improving random forests algorithm | |
JP5081999B1 (en) | How to display abnormal sign diagnosis results | |
CN107563069A (en) | A kind of wind power generating set intelligent fault diagnosis method | |
CN109992440A (en) | A kind of IT root accident analysis recognition methods of knowledge based map and machine learning | |
US20110178963A1 (en) | system for the detection of rare data situations in processes | |
KR102268733B1 (en) | Ship engine failure detection method and system | |
US20210232104A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
CN107238508A (en) | A kind of equipment state diagnostic method and device | |
CN116670608A (en) | Hybrid ensemble method for predictive modeling of Internet of things | |
Xiao et al. | A review of fault diagnosis methods based on machine learning patterns | |
CN110727669B (en) | Electric power system sensor data cleaning device and cleaning method | |
CN111712771B (en) | Data processing apparatus and method capable of performing problem diagnosis | |
CN114577470A (en) | Fault diagnosis method and system for fan main bearing | |
Ploix et al. | A logical framework for isolation in fault diagnosis | |
US11339763B2 (en) | Method for windmill farm monitoring | |
EP4113539A1 (en) | Method and system for intelligent monitoring of state of nuclear power plant | |
US11151008B2 (en) | Intelligent diagnostic system | |
Luis E et al. | Faults diagnosis in industrial processes with a hybrid diagnostic system | |
TWI762101B (en) | Abnormal Diagnosis Device and Abnormal Diagnosis Program | |
RU2297659C1 (en) | Integrated system for automatic coordinated control of object | |
Monroy et al. | Anomaly detection in batch chemical processes | |
Taillefond et al. | Fuzzy clustering and classification for automated leak detection systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information |
Inventor after: Chu Jingchun Inventor after: Wang Fei Inventor after: Li Yongzhan Inventor after: Dong Jian Inventor before: Wang Fei Inventor before: Li Yongzhan Inventor before: Dong Jian |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |