CN106779200A - Based on the Wind turbines trend prediction method for carrying out similarity in the historical data - Google Patents
Based on the Wind turbines trend prediction method for carrying out similarity in the historical data Download PDFInfo
- Publication number
- CN106779200A CN106779200A CN201611116628.3A CN201611116628A CN106779200A CN 106779200 A CN106779200 A CN 106779200A CN 201611116628 A CN201611116628 A CN 201611116628A CN 106779200 A CN106779200 A CN 106779200A
- Authority
- CN
- China
- Prior art keywords
- data
- blower fan
- wind turbines
- historical data
- carrying
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000009467 reduction Effects 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000007621 cluster analysis Methods 0.000 claims abstract description 5
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 241001269238 Data Species 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000003897 fog Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The present invention provides a kind of based on the Wind turbines trend prediction method for carrying out similarity in the historical data, is related to Wind turbines Condition Monitoring Technology field.After the method is pre-processed to historical data, blower fan Attributions selection and dimensionality reduction are carried out, cluster analysis is carried out to the data after dimensionality reduction by improved K mean cluster algorithm, Li Tong historical datas are similar to inquire about the prediction for carrying out fan operation state.The present invention provide based on the Wind turbines trend prediction method for carrying out similarity in the historical data, the history data of Wind turbines can be set up database, and by real-time service data and blower fan itself and the blower fan historical data similar to its be estimated the state for comparing Wind turbines.
Description
Technical field
It is based on carrying out phase in the historical data the present invention relates to Wind turbines Condition Monitoring Technology field, more particularly to one kind
Like the Wind turbines trend prediction method of search.
Background technology
At present, the research in Wind turbines condition monitoring and fault diagnosis field is in starting stage, existing achievement in research
In, state estimation and failure predication are laid particular emphasis on for the research of whole machine, laying particular emphasis on failure for the critical component research of unit examines
It is disconnected.The mainly residual analysis in fan condition assessment, by SCADA (Supervisory Control And Data
Acquisition, i.e. data acquisition and supervisor control) Monitoring Data as the input of forecast model, pass through to be set up
Forecast model such as artificial neural network or SVMs obtains predicted value, and then actual monitoring value is combined with predicted value asks
Residual error is taken, the threshold residual value for determining by methods such as expertise or normal distributions in advance is combined with, by detecting whether to surpass
Cross threshold value or realized to failure predication by residual error trend analysis, but the prediction of following running status of blowing machine can not be given.
Main method includes vibration analysis and oil analysis in the method for diagnosing faults of blower fan.Vibration analysis has for low frequency signal
Certain limitation, and install sensor acquisition vibration signal need to increase investment and maintenance cost on gear-box body.Fluid
Analysis has that measurement error is larger, the low factor of precision because being limited to monitoring hardware (sensor) design and fabrication technology, does not have also
Online oil liquid monitoring is realized in practice.Therefore, existing method can not obtain preferable effect.
Chinese patent CN201310098308, discloses a kind of wind turbine state evaluation early warning based on similarity statistics
Method and system, and Chinese patent CN201310107926, disclose a kind of Wind turbines shape based on historical failure data
State appraisal procedure and system, its disclosed method is：Step 1, Wind turbines are generated according to Wind turbines history datas
The security criteria line of multiple normal condition models and the Wind turbines；Step 2, the real time execution number for obtaining the Wind turbines
According to the real-time running data of the Wind turbines is contrasted with the normal condition model to determine the real time execution number
According to the similarity with the normal condition model；By the safety of the real-time running data of the Wind turbines and the Wind turbines
Datum line is contrasted with real-time running data exception alarm；Step 3, the real-time running data is analyzed
Estimated with to the Wind turbines failure.The subject matter that the patent is present is Wind turbines long-term work severe
In natural environment, by factors such as normal and limit extreme temperature, solar radiation, rainfall, accumulated snow, salt fog, sand and dust, terrain profiles
Influence has certain undulating movement with the running status of the change blower fan of running environment, and the health status model of generation is not
All changes of the blower fan under health status can necessarily be reflected, limitation is there is.And due to the change of natural conditions, wind
The security baseline of machine should also be and change with season, temperature, and simple fixed base can not well identify blower fan
Running status whether safety.
The content of the invention
For the defect of prior art, the present invention provides a kind of based on the wind turbine for carrying out similarity in the historical data
Group trend prediction method, can set up database by the history data of Wind turbines, and by real-time service data with
Blower fan itself and the blower fan historical data similar to its state for comparing Wind turbines is estimated.
It is a kind of based on the Wind turbines trend prediction method for carrying out similarity in the historical data, comprise the following steps：
Step 1, the history data for obtaining sufficiently long blower fan sensor, it is ensured that the history data can be included
Blower fan institute that may be present is stateful；
Step 2, Wind turbines history data is pre-processed, delete the data of useless variable and mistake, mended
The data of full missing；
Step 3, blower fan attribute learnt using random forests algorithm and is extracted importance attribute；
Step 4, dimensionality reduction is carried out to blower fan attribute using principal component analysis, the One-dimension Time Series for generating blower fan comprehensively refer to
Mark；
Step 5, cluster analysis is carried out to the blower fan data after dimensionality reduction using improved K mean cluster algorithm, obtain similar
Wind turbines；
Step 6, during running of wind generating set, system calculates dynamic between data in real time by current operating data
State Time Warp distance, is matched in itself and its similar Wind turbines historical data, is found and current state most phase
As historical data, with the data of the historical data subsequent time as running status after blower fan prediction, sector-style of going forward side by side machine
Status early warning.
Further, the specific method of the step 3 is：
Step 3.1, according to an expert view and document, chooses appropriate variable as output valve, and other variables are used as defeated
Enter value, using random forests algorithm, machine learning is carried out under pre-set parameter；
Step 3.2, the result obtained according to step 3.1 machine learning, each attribute is carried out according to mean square error increment
Sequence, obtains other each variables to being chosen for the importance of output valve variable, and chooses the forward some variables work of importance
It is research object.
Further, the specific method of the step 4 is：
Step 4.1, the data for choosing a large amount of normal blower fans for running, carry out principal component analysis, obtain characteristic vector and power
Value；
Step 4.2, using the characteristic vector and weights for obtaining corresponding blower fan data are carried out with dimensionality reduction, generate one-dimensional time sequence
Row overall target；
Step 4.3, by the data storage after Wind turbines dimensionality reduction in a computer, as the search library of fan condition.
As shown from the above technical solution, the beneficial effects of the present invention are：The present invention provide based in the historical data
The Wind turbines trend prediction method of similarity is carried out, the history data of Wind turbines database can be set up, and
The shape to comparing Wind turbines is carried out by real-time service data and blower fan itself and the blower fan historical data similar to its
State is estimated.On the basis of using mass historical data similarity digging technology, Wind turbines synthesis is obtained by dimensionality reduction
Attribute, carries out similarity analysis to Wind turbines current state and history with work condition state online, quantitatively calculates wind turbine
Group current state and the similarity degree of historic state, search out the historic state most like with current state, using historic state
Fan condition is predicted, while the comprehensive security evaluation for realizing Wind turbines real-time running state, while the event to blower fan
Barrier carries out early warning diagnosis.
Brief description of the drawings
Fig. 1 is provided in an embodiment of the present invention based on the Wind turbines status predication for carrying out similarity in the historical data
Method flow diagram；
Fig. 2 is that provided in an embodiment of the present invention 01300,01400 and No. 01500 contrast of the draught fan impeller rotating speed of blower fan is bent
Line chart；
Fig. 3 is provided in an embodiment of the present invention 01300,01400 and No. 01500 correlation curve of the generator speed of blower fan
Figure；
Fig. 4 is provided in an embodiment of the present invention 01300,01400 and No. 01500 correlation curve of the generator-temperature detection of blower fan
Figure；
Fig. 5 is provided in an embodiment of the present invention 01300,01400 and No. 01500 contrast of the box bearing temperature of blower fan
Curve map；
Fig. 6 is provided in an embodiment of the present invention 01300,01400 and No. 01500 correlation curve of the gear-box oil temperature of blower fan
Figure；
Fig. 7 is provided in an embodiment of the present invention 01300,01400 and No. 01500 correlation curve of the active power of blower fan
Figure；
Fig. 8 is that the draught fan impeller rotating speed that No. 01500 blower fan provided in an embodiment of the present invention is matched with inquiry data one is contrasted
Curve map；
Fig. 9 is that No. 01500 blower fan provided in an embodiment of the present invention contrasts bent with the generator speed that inquiry data one are matched
Line chart；
Figure 10 is that No. 01500 blower fan provided in an embodiment of the present invention contrasts bent with the generator-temperature detection that inquiry data one are matched
Line chart；
Figure 11 is the box bearing temperature pair that No. 01500 blower fan provided in an embodiment of the present invention is matched with inquiry data one
Compare curve map；
Figure 12 is that No. 01500 blower fan provided in an embodiment of the present invention contrasts bent with the gear-box oil temperature that inquiry data one are matched
Line chart；
Figure 13 is the active power correlation curve that No. 01500 blower fan provided in an embodiment of the present invention is matched with inquiry data one
Figure；
Figure 14 is that the draught fan impeller rotating speed that No. 01300 blower fan provided in an embodiment of the present invention is matched with inquiry data two is contrasted
Curve map；
Figure 15 is that No. 01300 blower fan provided in an embodiment of the present invention contrasts bent with the generator speed that inquiry data two are matched
Line chart；
Figure 16 is that No. 01300 blower fan provided in an embodiment of the present invention contrasts bent with the generator-temperature detection that inquiry data two are matched
Line chart；
Figure 17 is the box bearing temperature pair that No. 01300 blower fan provided in an embodiment of the present invention is matched with inquiry data two
Compare curve map；
Figure 18 is that No. 01300 blower fan provided in an embodiment of the present invention contrasts bent with the gear-box oil temperature that inquiry data two are matched
Line chart；
Figure 19 is the active power correlation curve that No. 01300 blower fan provided in an embodiment of the present invention is matched with inquiry data two
Figure.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiment of the invention is described in further detail.Hereinafter implement
Example is not limited to the scope of the present invention for illustrating the present invention.
As shown in figure 1, the present embodiment provides a kind of based on the Wind turbines state for carrying out similarity in the historical data
Forecasting Methodology, comprises the following steps.
Step 1, the history data for obtaining sufficiently long blower fan sensor, it is ensured that the history data is comprising various
Meteorological condition, the data of seasonal variations can be stateful comprising that may be present of blower fan.
Step 2, the Wind turbines history data to existing data acquisition and supervisor control collection are carried out clearly
Pretreatment is washed, useless variable and wrong data, the data of completion missing are deleted.
Step 3, blower fan attribute learnt using random forests algorithm and is extracted importance attribute, specific method is：
Step 3.1, according to an expert view and document, chooses appropriate variable as output valve, and other variables are used as defeated
Enter value, using random forests algorithm, machine learning is carried out under pre-set parameter；
Step 3.2, the result obtained according to step 3.1 machine learning, each attribute is carried out according to mean square error increment
Sequence, obtains other each variables to being chosen for the importance of output valve variable, and chooses the forward some variables work of importance
It is research object.
Step 4, dimensionality reduction is carried out to blower fan attribute using principal component analysis, the One-dimension Time Series for generating blower fan comprehensively refer to
Mark, specific method is：
Step 4.1, the data for choosing a large amount of normal blower fans for running, carry out principal component analysis, obtain characteristic vector and power
Value；
Step 4.2, using the characteristic vector and weights for obtaining corresponding blower fan data are carried out with PCA dimensionality reductions, when generating one-dimensional
Between sequence synthesis index；
Step 4.3, by the data storage after Wind turbines dimensionality reduction in a computer, as the search library of fan condition.
Step 5, cluster analysis is carried out to the blower fan data after dimensionality reduction using improved K mean cluster algorithm, by blower fan according to
It is grouped according to similitude, it is the blower fan of a class to incorporate into, can be retrieved mutually when similarity is carried out.
Step 6, during running of wind generating set, system calculates dynamic between data in real time by current operating data
State Time Warp distance, is matched in itself and its similar Wind turbines historical data, is found and current state most phase
As historical data, with the data of the historical data subsequent time as running status after blower fan prediction, using in history
The state of this period blower fan is to fan condition early warning.
The present embodiment carries out data clear using the true blower fan data for coming from wind field, the preferable blower fan sample of selected part
Wash, including deleting duplicated data, constant row, null value filling etc. are deleted, to each blower fan erasing time sequence.
Using gear case oil temperature value as output valve, other attributes carry out random forest training as input value, obtain square
Error increment (Increase in MSE) takes average, retains five after decimal point, and normalization result is as shown in table 1.
Table 1
Generator speed, wheel speed, tooth are included than first five larger attribute variable to gear-box oil temperature influence factor
Roller box bearing temperature, generator-temperature detection and active power, choose this five attribute variables and gear case oil temperature value right as studying
As.
Because blower fan data are not necessarily all complete available, the data of 40 more intact Fans of data are chosen, chosen
Several attribute variables, constitute 40 multidimensional time-series matrixes above, and for each matrix, choosing identical timeslice is carried out
PCA dimensionality reductions, ordinal series when forming one-dimensional.
Finally, using improved K mean cluster algorithm, blower fan is classified, classification results are as shown in table 2.
The classification results of the cluster analysis of table 2
Choose 01300,01400 and No. 01500 blower fan to be analyzed, normal condition similarly hereinafter organizes 01300,01400 and 01500
Number fan operation shape has very much uniformity and similitude very high.As shown in Figures 2 to 7, it is blower fan 01300,01400 and
01500 draught fan impeller rotating speed, generator speed, generator-temperature detection, box bearing temperature, the gentle active power of gear case oil
Contrast curve.
In the case of extraneous ambient stable, the running status of blower fan also has certain stability, current using blower fan
The ruuning situation of time period carries out historical data search, finds most like with current slot running status data in history,
By the use of following blower fan in history state as current fan condition prediction.
Because blower fan data volume is larger, first blower fan is clustered, scanned in the affiliated class of current blower fan, Neng Gouji
The earth lifting search efficiency.
(1) No. 01,300 the 14501 of blower fan are taken in data to 14600 datas as inquiry data one, 01300,
01400th, set of metadata of similar data is searched in No. 01500 historical data of blower fan, obtains following result：
(first 100 are No. 01500 the 4379 of the blower fan matching degree highests to 4478 datas and above-mentioned inquiry data one
For match data, afterwards 100 be predicted value and actual value comparing), as shown in Fig. 8 to Figure 13, be draught fan impeller rotating speed,
Generator speed, generator-temperature detection, box bearing temperature, the matching contrast curve of the gentle active power of gear case oil, from
As can be seen that the result for searching out has similitude very high in figure, especially in active power, engine speed and wheel speed
On have very big similitude, and No. 01500 blower fan there occurs failure at this moment in history, it can be determined that 01300 blower fan is herein
It is also possible at quarter produce failure；
(2) matching degree highest is obtained as inquiry data two using No. 01,300 30301 of blower fan to 30400 datas
Data be No. 01,300 the 26336 of blower fan to 26435 datas, as shown in Figure 14 to Figure 19, it can be seen that blower fan is basic
In normal operating condition, it is relatively good that active power, generator speed and wheel speed are predicted.
The history data of Wind turbines can be set up database by the method that the present embodiment is provided, and by real-time
Service data and blower fan itself and the blower fan historical data similar to its state for comparing Wind turbines is estimated.
It is different from rule-based diagnostic system, this method system using on the basis of mass historical data similarity digging technology,
Wind turbines synthesized attribute is obtained by dimensionality reduction, similar searching is carried out with work condition state to Wind turbines current state and history online
Rope is analyzed, and quantitatively calculates the similarity degree of Wind turbines current state and historic state, is searched out most like with current state
Historic state, fan condition is predicted using historic state, realize Wind turbines real-time running state while comprehensive
Security evaluation, while carrying out early warning diagnosis to the failure of blower fan.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
Modified with to the technical scheme described in previous embodiment, or which part or all technical characteristic are equal to
Replace；And these modifications or replacement, the essence of appropriate technical solution is departed from the model that the claims in the present invention are limited
Enclose.
Claims (3)
1. a kind of based on the Wind turbines trend prediction method for carrying out similarity in the historical data, it is characterised in that：Including
Following steps：
Step 1, the history data for obtaining sufficiently long blower fan sensor, it is ensured that the history data can include blower fan
Institute that may be present is stateful；
Step 2, Wind turbines history data is pre-processed, delete the data of useless variable and mistake, completion lacks
The data of mistake；
Step 3, blower fan attribute learnt using random forests algorithm and is extracted importance attribute；
Step 4, dimensionality reduction is carried out to blower fan attribute using principal component analysis, generate the One-dimension Time Series overall target of blower fan；
Step 5, cluster analysis is carried out to the blower fan data after dimensionality reduction using improved K mean cluster algorithm, obtain similar wind
Group of motors；
Step 6, during running of wind generating set, when system calculates the dynamic between data in real time by current operating data
Between deflection distance, matched in itself and its similar Wind turbines historical data, find most like with current state
Historical data, with the data of the historical data subsequent time as the prediction of running status after blower fan, and carries out fan condition
Early warning.
2. according to claim 1 based on the Wind turbines trend prediction method for carrying out similarity in the historical data,
It is characterized in that：The specific method of the step 3 is：
Step 3.1, according to an expert view and document, chooses appropriate variable as output valve, other variables as input value,
Using random forests algorithm, machine learning is carried out under pre-set parameter；
Step 3.2, the result obtained according to step 3.1 machine learning, each attribute is ranked up according to mean square error increment,
Other each variables are obtained to being chosen for the importance of output valve variable, and chooses the forward some variables of importance as research
Object.
3. according to claim 1 based on the Wind turbines trend prediction method for carrying out similarity in the historical data,
It is characterized in that：The specific method of the step 4 is：
Step 4.1, the data for choosing a large amount of normal blower fans for running, carry out principal component analysis, obtain characteristic vector and weights；
Step 4.2, using the characteristic vector and weights for obtaining corresponding blower fan data are carried out with dimensionality reduction, generation One-dimension Time Series are comprehensive
Close index；
Step 4.3, by the data storage after Wind turbines dimensionality reduction in a computer, as the search library of fan condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116628.3A CN106779200A (en) | 2016-12-07 | 2016-12-07 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116628.3A CN106779200A (en) | 2016-12-07 | 2016-12-07 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106779200A true CN106779200A (en) | 2017-05-31 |
Family
ID=58882223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611116628.3A Pending CN106779200A (en) | 2016-12-07 | 2016-12-07 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779200A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301564A (en) * | 2017-06-12 | 2017-10-27 | 河南科技大学 | Abnormal consumer behavior detection method based on clustering algorithm and echo state network |
| CN107832896A (en) * | 2017-11-29 | 2018-03-23 | 广东电网有限责任公司电力科学研究院 | A kind of electric power factory equipment soft fault method for early warning and device |
| CN108509645A (en) * | 2018-04-13 | 2018-09-07 | 华润电力风能(威海)有限公司 | A kind of equipment method for early warning |
| CN108549332A (en) * | 2017-12-19 | 2018-09-18 | 中南大学 | A kind of production status prediction technique based on cobalt acid lithium feed proportioning system |
| CN109086793A (en) * | 2018-06-27 | 2018-12-25 | 东北大学 | A kind of abnormality recognition method of wind-driven generator |
| CN109213127A (en) * | 2018-09-25 | 2019-01-15 | 浙江工业大学 | A kind of HVAC system gradual failure diagnostic method based on deep learning |
| CN109408554A (en) * | 2018-09-17 | 2019-03-01 | 顺丰科技有限公司 | Data analysing method, system, equipment and the storage medium of logistics node |
| CN109991500A (en) * | 2019-04-29 | 2019-07-09 | 中国水电工程顾问集团有限公司 | A kind of method of wind-powered electricity generation fault pre-alarming prediction |
| CN110727257A (en) * | 2019-08-27 | 2020-01-24 | 华润置地控股有限公司 | Equipment operation diagnosis method and device based on K-means clustering algorithm |
| CN110836786A (en) * | 2019-11-19 | 2020-02-25 | 北京瑞莱智慧科技有限公司 | Mechanical fault monitoring method, device, system, medium and computing equipment |
| CN111080039A (en) * | 2020-03-17 | 2020-04-28 | 浙江上风高科专风实业有限公司 | Fan cluster fault prediction method and system |
| CN111192163A (en) * | 2019-12-23 | 2020-05-22 | 明阳智慧能源集团股份公司 | Generator reliability medium-short term prediction method based on wind turbine generator operating data |
| CN111209934A (en) * | 2019-12-26 | 2020-05-29 | 大唐新疆清洁能源有限公司 | Fan fault prediction and alarm method and system |
| CN111738536A (en) * | 2020-08-28 | 2020-10-02 | 北京每日优鲜电子商务有限公司 | Device operation method, device, electronic device and computer readable medium |
| CN112529059A (en) * | 2020-12-04 | 2021-03-19 | 湖南五凌电力科技有限公司 | Unit electromagnetic vibration diagnosis method, system, computer equipment and storage medium |
| CN113239957A (en) * | 2021-04-08 | 2021-08-10 | 同济大学 | Online identification method for sudden water pollution event |
| CN113297291A (en) * | 2021-05-08 | 2021-08-24 | 上海电气风电集团股份有限公司 | Monitoring method, monitoring system, readable storage medium and wind driven generator |
| CN113486585A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Method and device for predicting remaining service life of equipment, electronic equipment and storage medium |
| CN113780621A (en) * | 2021-08-03 | 2021-12-10 | 南方电网电动汽车服务有限公司 | Charging pile fault prediction method and device, computer equipment and storage medium |
| CN113984111A (en) * | 2021-09-30 | 2022-01-28 | 北京华能新锐控制技术有限公司 | Wind turbine generator control method and device based on external environment change |
| CN115079626A (en) * | 2022-07-21 | 2022-09-20 | 东方电气风电股份有限公司 | Early warning method and system for potential operation risk of wind generating set component |
| TWI819824B (en) * | 2022-09-30 | 2023-10-21 | 中國鋼鐵股份有限公司 | Method for applying different rotation-speed-vibration thresholds to diagnose abnormality of equipment with variable rotation speeds |
| US11847619B2 (en) | 2018-09-20 | 2023-12-19 | Siemens Ltd., China | System-state monitoring method and device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103217286A (en) * | 2013-03-23 | 2013-07-24 | 中国水利电力物资有限公司 | Wind power unit transmission system failure identification method and system based on failure data |
| CN103226651A (en) * | 2013-03-23 | 2013-07-31 | 中国水利电力物资有限公司 | Wind turbine state evaluation and early-warning method and system based on similarity statistics |
| CN103324980A (en) * | 2013-04-25 | 2013-09-25 | 华北电力大学（保定） | Wind power station wind speed prediction method |
| CN103822786A (en) * | 2012-11-16 | 2014-05-28 | 中国水利电力物资有限公司 | Wind turbine generator set mechanical equipment state diagnosis method based on multivariate statistical analysis |
| US20140239639A1 (en) * | 2013-02-28 | 2014-08-28 | International Business Machines Corporation | Controlling wind turbine |
-
2016
- 2016-12-07 CN CN201611116628.3A patent/CN106779200A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103822786A (en) * | 2012-11-16 | 2014-05-28 | 中国水利电力物资有限公司 | Wind turbine generator set mechanical equipment state diagnosis method based on multivariate statistical analysis |
| US20140239639A1 (en) * | 2013-02-28 | 2014-08-28 | International Business Machines Corporation | Controlling wind turbine |
| CN103217286A (en) * | 2013-03-23 | 2013-07-24 | 中国水利电力物资有限公司 | Wind power unit transmission system failure identification method and system based on failure data |
| CN103226651A (en) * | 2013-03-23 | 2013-07-31 | 中国水利电力物资有限公司 | Wind turbine state evaluation and early-warning method and system based on similarity statistics |
| CN103324980A (en) * | 2013-04-25 | 2013-09-25 | 华北电力大学（保定） | Wind power station wind speed prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 刘鹏辉等: "基于动态时间弯曲距离的小电流接地故障区段定位方法", 《电网技术》 * |
| 孙科: "基于Spark的机器学习应用框架研究与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301564A (en) * | 2017-06-12 | 2017-10-27 | 河南科技大学 | Abnormal consumer behavior detection method based on clustering algorithm and echo state network |
| CN107832896A (en) * | 2017-11-29 | 2018-03-23 | 广东电网有限责任公司电力科学研究院 | A kind of electric power factory equipment soft fault method for early warning and device |
| CN108549332B (en) * | 2017-12-19 | 2020-08-25 | 中南大学 | Production state prediction method based on lithium cobaltate batching system |
| CN108549332A (en) * | 2017-12-19 | 2018-09-18 | 中南大学 | A kind of production status prediction technique based on cobalt acid lithium feed proportioning system |
| CN108509645A (en) * | 2018-04-13 | 2018-09-07 | 华润电力风能(威海)有限公司 | A kind of equipment method for early warning |
| CN109086793B (en) * | 2018-06-27 | 2021-11-16 | 东北大学 | Abnormity identification method for wind driven generator |
| CN109086793A (en) * | 2018-06-27 | 2018-12-25 | 东北大学 | A kind of abnormality recognition method of wind-driven generator |
| CN109408554A (en) * | 2018-09-17 | 2019-03-01 | 顺丰科技有限公司 | Data analysing method, system, equipment and the storage medium of logistics node |
| US11847619B2 (en) | 2018-09-20 | 2023-12-19 | Siemens Ltd., China | System-state monitoring method and device and storage medium |
| CN109213127A (en) * | 2018-09-25 | 2019-01-15 | 浙江工业大学 | A kind of HVAC system gradual failure diagnostic method based on deep learning |
| CN109991500A (en) * | 2019-04-29 | 2019-07-09 | 中国水电工程顾问集团有限公司 | A kind of method of wind-powered electricity generation fault pre-alarming prediction |
| CN109991500B (en) * | 2019-04-29 | 2021-12-21 | 中国水电工程顾问集团有限公司 | Wind power fault early warning and prediction method |
| CN110727257A (en) * | 2019-08-27 | 2020-01-24 | 华润置地控股有限公司 | Equipment operation diagnosis method and device based on K-means clustering algorithm |
| CN110836786B (en) * | 2019-11-19 | 2020-10-23 | 北京瑞莱智慧科技有限公司 | Mechanical fault monitoring method, device, system, medium and computing equipment |
| CN110836786A (en) * | 2019-11-19 | 2020-02-25 | 北京瑞莱智慧科技有限公司 | Mechanical fault monitoring method, device, system, medium and computing equipment |
| CN111192163A (en) * | 2019-12-23 | 2020-05-22 | 明阳智慧能源集团股份公司 | Generator reliability medium-short term prediction method based on wind turbine generator operating data |
| CN111192163B (en) * | 2019-12-23 | 2023-03-28 | 明阳智慧能源集团股份公司 | Generator reliability medium-short term prediction method based on wind turbine generator operating data |
| CN111209934A (en) * | 2019-12-26 | 2020-05-29 | 大唐新疆清洁能源有限公司 | Fan fault prediction and alarm method and system |
| CN111209934B (en) * | 2019-12-26 | 2023-11-21 | 大唐新疆清洁能源有限公司 | Fan fault pre-alarm method and system |
| CN111080039A (en) * | 2020-03-17 | 2020-04-28 | 浙江上风高科专风实业有限公司 | Fan cluster fault prediction method and system |
| CN111080039B (en) * | 2020-03-17 | 2023-10-20 | 浙江上风高科专风实业有限公司 | Fan cluster fault prediction method and system |
| CN111738536A (en) * | 2020-08-28 | 2020-10-02 | 北京每日优鲜电子商务有限公司 | Device operation method, device, electronic device and computer readable medium |
| CN112529059A (en) * | 2020-12-04 | 2021-03-19 | 湖南五凌电力科技有限公司 | Unit electromagnetic vibration diagnosis method, system, computer equipment and storage medium |
| CN113239957A (en) * | 2021-04-08 | 2021-08-10 | 同济大学 | Online identification method for sudden water pollution event |
| CN113297291A (en) * | 2021-05-08 | 2021-08-24 | 上海电气风电集团股份有限公司 | Monitoring method, monitoring system, readable storage medium and wind driven generator |
| CN113486585A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Method and device for predicting remaining service life of equipment, electronic equipment and storage medium |
| CN113780621A (en) * | 2021-08-03 | 2021-12-10 | 南方电网电动汽车服务有限公司 | Charging pile fault prediction method and device, computer equipment and storage medium |
| CN113984111A (en) * | 2021-09-30 | 2022-01-28 | 北京华能新锐控制技术有限公司 | Wind turbine generator control method and device based on external environment change |
| CN115079626A (en) * | 2022-07-21 | 2022-09-20 | 东方电气风电股份有限公司 | Early warning method and system for potential operation risk of wind generating set component |
| TWI819824B (en) * | 2022-09-30 | 2023-10-21 | 中國鋼鐵股份有限公司 | Method for applying different rotation-speed-vibration thresholds to diagnose abnormality of equipment with variable rotation speeds |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779200A (en) | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data | |
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| CN111539553B (en) | Wind turbine generator fault early warning method based on SVR algorithm and off-peak degree | |
| CN110006552B (en) | Method for detecting abnormal temperature of equipment | |
| CN113614359A (en) | Method and system for predicting risk of observable damage in wind turbine gearbox assembly | |
| CN110362045B (en) | Marine doubly-fed wind turbine generator fault discrimination method considering marine meteorological factors | |
| CN109299208B (en) | Intelligent visual risk assessment method for transmission tower in typhoon disaster | |
| CN111461564A (en) | Wind turbine generator power characteristic evaluation method based on cloud model and optimal combined weighting | |
| CN114399081A (en) | Photovoltaic power generation power prediction method based on weather classification | |
| CN115238573A (en) | Hydroelectric generating set performance degradation trend prediction method and system considering working condition parameters | |
| CN114742363A (en) | Energy efficiency state evaluation method, system and medium for wind turbine generator | |
| CN112798290B (en) | Abnormal state monitoring method of gas turbine based on spectrum reconstruction error | |
| CN116821610B (en) | Method for optimizing wind power generation efficiency by utilizing big data | |
| JP6830414B2 (en) | Diagnostic device and diagnostic method | |
| CN117151684A (en) | Wind power fan data analysis early warning method, system, device and readable storage medium | |
| Surjandari et al. | Fault detection system using machine learning on geothermal power plant | |
| CN115795999B (en) | Early warning method for abnormal performance of long-term service pumped storage unit | |
| CN116451608A (en) | Mixed wind power prediction method and device for complex terrain | |
| Jastrzebska et al. | Measuring wind turbine health using fuzzy-concept-based drifting models | |
| US20180087489A1 (en) | Method for windmill farm monitoring | |
| Souza et al. | Evaluation of data based normal behavior models for fault detection in wind turbines | |
| CN112699598A (en) | Intelligent diagnosis method and device for abnormal oil temperature of gear box | |
| Shen | Classification of Wind Turbine Blade Performance State Through Statistical Methods | |
| Fawzy et al. | WFEC: Wind farms economic classifier using big data analytics | |
| Nunes | Use of Learning Mechanisms to Improve Wind Farms Operation Conditions Monitoring |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |