CN109543210A - A kind of Wind turbines failure prediction system based on machine learning algorithm platform - Google Patents
A kind of Wind turbines failure prediction system based on machine learning algorithm platform Download PDFInfo
- Publication number
- CN109543210A CN109543210A CN201811136084.6A CN201811136084A CN109543210A CN 109543210 A CN109543210 A CN 109543210A CN 201811136084 A CN201811136084 A CN 201811136084A CN 109543210 A CN109543210 A CN 109543210A
- Authority
- CN
- China
- Prior art keywords
- data
- failure
- fault diagnosis
- classification
- fault
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 25
- 238000003745 diagnosis Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000013500 data storage Methods 0.000 claims abstract description 7
- 230000004888 barrier function Effects 0.000 claims abstract description 5
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000007418 data mining Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 230000015654 memory Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000007435 diagnostic evaluation Methods 0.000 claims description 2
- 230000007257 malfunction Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000034303 cell budding Effects 0.000 abstract description 2
- 230000008439 repair process Effects 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Public Health (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A kind of Wind turbines failure prediction system based on machine learning algorithm platform.The system includes data acquisition module, data storage and processing module, machine learning algorithm platform, fault diagnosis, analysis and prediction module.The present invention solves the unpredictability that wind power plant Wind turbines failure occurs, fault diagnosis, accident analysis, the failure predication of Wind turbines are realized using machine learning algorithm platform, to realize the look-ahead of failure, great barrier is eliminated in budding state, to effectively reduce the occurrence frequency and degree of Wind turbines failure.
Description
Technical field
The present invention relates to internet big data technology and energy wind power generation fields, and in particular to one kind is based on machine learning
The Wind turbines failure prediction system of algorithm platform.
Background technique
Since wind power plant local environment is severe and Wind turbines load is unstable, leads to the safety to Wind turbines, passes through
Ji property all produces extreme influence.The accumulation diagnosis judgement investigation of traditional Wind turbines failure and alarm by working experience, equipment
It is low to overhaul priority discrimination, often wastes the best time available of troubleshooting, misses the Best Times of overhaul of the equipments, make
At rate of breakdown height；The useless fault warning of thousands of repetitions daily simultaneously, causes true equipment deficiency to fail in time
It was found that；Without targetedly maintenance plan layout, investment manpower and material resources cost, assets is caused to waste.
At present major part failure prediction system by be the scientific algorithm such as decision tree, linear equation in the way of, section
It learns to calculate and will use historical data to be fitted these equations, but scientific algorithm also has certain drawbacks and limitation, mainly
There are problems that two: 1) ability for solving challenge is limited, can only be fitted some simple data, encounter special data and industry
Business situation, which will do it, to be given up；2) result is inaccurate, the problem of for some Decision Classes, often due to sample size is few etc.
The biased solution fruit of output.
Summary of the invention
The purpose of the present invention is propose a kind of based on machine for shortcoming existing for current Wind turbines failure predication
The Wind turbines failure prediction system of learning algorithm platform realizes the accurate prediction of Wind turbines failure.
Present general inventive concept is to introduce machine learning algorithm platform in failure prediction system, and machine learning is special
Mankind's learning behavior is simulated or realized to door research computer how, to obtain new knowledge or technical ability, can reorganize
Some knowledge constantly to improve a kind of method of self performance, and machine learning algorithm platform has the ability for solving challenge
And can be realized thousand machines, thousand face, it can provide Comprehensive Evaluation by continuous iteration, can carry out mass data and feature dimensions
The calculating of degree can provide the suggestion of the materialization of fault diagnosis, failure predication according to the characteristic of each Wind turbines.
The technical scheme is that such:
A kind of Wind turbines failure prediction system based on machine learning algorithm platform.The system includes data acquisition module, number
According to storage and processing module, machine learning algorithm platform, fault diagnosis, analysis and prediction module.The function of each section is as follows:
(1) data acquisition module: the big component sensors prison of data collecting module collected Wind turbines SCADA operation data, unit
Measured data, OA systems management data, internet data, weather data, expert knowledge library data etc. are used as data source.
(2) data storage and processing module: data storage and processing mainly use Hadoop cloud computing platform, utilize
HDFS high serious forgiveness and handling capacity, can meet magnanimity very well, and the memory requirement of enriched data low cost is suitble to Storm
Deng based on flow data access process mode；And Storm stream calculation, Spark memory are used according to different calculating demands respectively
It calculates and MR batches calculates.
(3) machine learning algorithm platform: new experience class is extracted on the basis of data calculate, self study class failure is known
Know, is stored in expert knowledge library.Using various data mining algorithms, according to the knowledge excavated, in conjunction with expert knowledge library, to wind
Electric unit equipment carries out on-line fault diagnosis and alarm, and extracts fault signature, constantly improve or extend all kinds of fault diagnosises, report
Alert algorithm.
(4) fault diagnosis, analysis and prediction module: GBDT(Gradient Iteration decision tree is chosen) algorithm and LSTM(shot and long term
Memory network) algorithm carry out model training, export trained machine learning model for diagnose, analysis and prediction calculate.
Fault diagnosis, prediction realize to include following steps:
(1) data mining.
Traditional data analysis mode is incompetent to handle so much processing for largely seeming incoherent data, therefore
Data mining technology is needed to go to extract the correlation between various data and variable, thus refined data.Data mining be from
The mode and mould of data are extracted in all data informations of Wind turbines (including SCADA data, meteorological data, management data)
Type realizes the screening and classification of data, that is, chooses most important information, selection, which only retains those, has High relevancy with failure
Measuring point signal and there is the measuring point signal of known threshold as key feature, then in combination using all characteristic points as one
A combination carries out data input, to use for subsequent machine learning algorithm platform data.The purpose of core of data mining is to look for
To stealth relationship existing between data variable.
(2) fault diagnosis.
Fault diagnosis is with data for driving, by the observation for fan operation state, the major system of real-time judge blower
Whether system breaks down, and fault diagnosis result should be consistent with the remote signals of failure.Using Wind turbines available data, by wind
Motor group failure is divided into several major class, such as generator system failure, gearbox system failure and pitch-controlled system failure etc..
1) a certain number of data training sets are formed, machine learning algorithm platform is constructed, form " knowing from passing experience
Know " deposit；
2) after machine learning, if there is a new data set x, need to diagnose its failure, machine learning algorithm can basis
" knowledge " after this new data and study matches (in fact, knowledge refers to the model after study), then by this number
It is diagnosed according to collection x.
(3) fault diagnosis classification and process.
Fault diagnosis is divided into offline diagnosis and inline diagnosis both of which, and offline diagnosis is by the study to historical data
Inherent parameters are promoted, and inline diagnosis refers to that the trained neural network of use carries out in fact according to the fan operation state of online acquisition
When fault diagnosis.
(4) diagnostic evaluation.
Fault diagnosis evaluation uses false dismissed rate, and false alarm rate and overall accuracy are evaluated and tested.Their formula are as follows:
False dismissed rate=FN/(TP+FN)
False alarm rate=FP/(TN+FP)
Overall accuracy=(FP+FN)/(TP+TN+FP+FN)
Wherein, case that TP classification is 1 (faulty) is appropriately determined by system as classification 1, FN classification is 1 (faulty)
Case classification 0 is set to by system erroneous judgement；There is the case that FP classification is 0 (fault-free) to be set to classification 1 by system erroneous judgement, TN is a
Classification is that the case of 0 (fault-free) is appropriately determined by system as classification 0.False dismissed rate evaluation and test is the ratio that do not alarm in the event of failure
Example, and false alarm rate assessment be the false alarm in fault-free ratio.In fault diagnosis, false dismissed rate and false alarm rate need as far as possible
Although balance is very high but the case where be not carried out fault diagnosis functions to avoid overall accuracy.
(5) failure predication.
Failure predication is to predict that following 10 minutes to the 1 hour inner blowers are each by the observation to current fan operation state
The probability of big system jam.In fan operation, field personnel can move towards according to the probability value and probability of prediction
The position that future malfunction occurs, time and confidence level are understood, to take maintenance and maintenance measure to provide clue in advance.
The invention has the advantages that:
1) unpredictability that wind power plant Wind turbines failure occurs is solved, realizes Wind turbines using machine learning algorithm platform
Fault diagnosis, accident analysis, failure predication great barrier is eliminated in budding state to realize the look-ahead of failure, from
And effectively reduce the occurrence frequency and degree of Wind turbines failure；
2) in Wind turbines remaining life section, specific aim inspection is carried out to potential risk existing for Wind turbines and failure in time
Maintenance is repaired, the service life of equipment is effectively extended, increases equipment reliability of operation；
3) so that blower operation maintenance personnel is effectively grasped fan trouble and intervene in advance, improve operation maintenance personnel working efficiency, improve
Running of wind generating set performance increases the generated energy of Wind turbines.
Detailed description of the invention
Fig. 1 is each composition part system configuration diagram of the present invention.
Fig. 2 is fault diagnosis of the present invention classification and flow chart.
Specific embodiment
A kind of Wind turbines failure prediction system based on machine learning algorithm platform.The system includes data acquisition module
Block, data storage and processing module, machine learning algorithm platform, fault diagnosis, analysis and prediction module.
The system predicts that wind-driven generator breaks down the probability of shutdown within following a period of time first, and to will send out
Raw failure realizes the failure predication to wind-driven generator by the basis for forecasting of analysis model:
1. choosing sample: 100 UP82 model blower 2015-2017 second measuring point datas, failure cause Wind turbines to shut down note
Record data, wind farm meteorological data；
2. construction feature: finally choosing the online current and related data configuration of historical measurements such as with temperature, revolving speed, wind speed
Feature, and produce assemblage characteristic, temporal aspect；
3. model training: final choice GBDT model and LSTM model optimize tune ginseng.
GBDT model is the decision forest being made of many regression trees, and prediction result is the prediction of all decision trees
As a result the sum of weighting.GBDT model includes 6 adjustable parameters altogether, be respectively as follows: learning rate, single tree depth capacity, tree
Number, minimum leaf weight, minimum division threshold value, L2 canonical；
LSTM(Long Short-Term Memory) it is shot and long term memory network, it is a kind of time recurrent neural network, is suitble to
Relatively long critical event is spaced and postponed in processing and predicted time sequence.It joined a judgement letter in the algorithm
The structure of " processor " whether ceasing useful, the effect of this processor is referred to as cell.Three fans have been placed in one cell
Door is called input gate respectively, forgets door and out gate.One information enters in the network of LSTM, can be sentenced according to rule
It is disconnected whether useful.The information for only meeting algorithm certification can just leave, and the information not being inconsistent then passes through forgetting door and passes into silence.
Adjusting ginseng work is the process that more preferable result is found in continuous modeling, and project team carries out GBDT model and LSTM model more
Wheel adjusts ginseng, final choice to one group of most suitable parameter configuration, so that model is stablized in training set and assessment concentrated expression.
4. model evaluation:
Under some score threshold: recall rate=
Recall rate is a kind of algorithm model evaluation index, and the accuracy of model algorithm is to be sentenced according to recall rate come calculated result
It is disconnected.Recall rate is the ratio of the information bar number in the correct information item number that extracts and sample, recall=TP/ (TP+FN) (TP:
Correctly be divided into the number of positive example, i.e., it is practical to be positive example and be classified the instance number that device is divided into positive example；FN: by mistakenly
Divide the number for the example that is negative, i.e., practical to be positive example but be classified the instance number that device divides the example that is negative).
Such as: the number that failure was broken down and actually occurred in prediction is A, does not predict to break down but actually occurs event
The number of barrier is B, then recall rate recall=A/ (A+B) that failure predication determines.
Based on the methods of big data platform and integrated use gradient decision tree, shot and long term prediction model to gear-box, power generation
The important components such as machine construct ffault matrix prediction model, and the failure being affected for warm oil, transmission, braking etc. carries out
Line look-ahead realizes Wind turbines emphasis fault diagnosis, prediction etc., and predicts that recall rate reaches 98% or more.
System failure processing:
Based on Wind turbines failure predication as a result, take do not handle, reset, the different processing mode such as maintenance, repair, according to need
The set state for overhauling or safeguarding works out repair and maintenance plan, and the best opportunity to repair and maintenance, standard technology and standby
Detailed, specific, stringent treatment measures are formulated in the formulations such as product spare parts management, form Wind turbines from safeguarding to thing in subsequent, thing
The cost of overhaul is effectively reduced in the transformation of preceding preventive maintenance, improves equipment availability, realizes the intelligent equipment inspection of wind power plant
It repairs.
Claims (2)
1. a kind of Wind turbines failure prediction system based on machine learning algorithm platform, which is characterized in that the system system
Including data acquisition module, data storage and processing module, machine learning algorithm platform, fault diagnosis, analysis and prediction module,
The function of each section is as follows:
(1) data acquisition module: the big component sensors prison of data collecting module collected Wind turbines SCADA operation data, unit
Measured data, OA systems management data, internet data, weather data, expert knowledge library data etc. are used as data source；
(2) data storage and processing module: data storage and processing mainly use Hadoop cloud computing platform, utilize HDFS
High serious forgiveness and handling capacity, can meet magnanimity very well, and the memory requirement of enriched data low cost is suitble to the bases such as Storm
In flow data access process mode；And Storm stream calculation is used according to different calculating demands respectively, Spark memory calculates
It is calculated with MR batches；
(3) machine learning algorithm platform: new experience class, self study class fault knowledge are extracted on the basis of data calculate, is deposited
Enter expert knowledge library.Using various data mining algorithms, according to the knowledge excavated, in conjunction with expert knowledge library, to wind turbine
Group equipment carries out on-line fault diagnosis and alarm, and extracts fault signature, constantly improve or extend all kinds of fault diagnosises, alarm is calculated
Method；
(4) fault diagnosis, analysis and prediction module: choose GBDT(Gradient Iteration decision tree) algorithm and LSTM(shot and long term memory
Network) algorithm carry out model training, export trained machine learning model for diagnose, analysis and prediction calculate.
2. failure prediction system according to claim 1, which is characterized in that fault diagnosis, prediction realize to include as follows
Step:
(1) data mining:
Data mining is extracted from all data informations of Wind turbines (comprising SCADA data, meteorological data, management data)
The mode and model of data realize the screening and classification of data, that is, choose most important information, and selection only retains those and event
Barrier has the measuring point signal of High relevancy and has the measuring point signal of known threshold as key feature, then will own in combination
Characteristic point carry out data input as combination, to be used for subsequent machine learning algorithm platform data.Data mining
Core the purpose of be find between data variable it is existing stealth relationship；
(2) fault diagnosis:
Fault diagnosis is with data for driving, and by the observation for fan operation state, the major system of real-time judge blower is
No to break down, fault diagnosis result should be consistent with the remote signals of failure, using Wind turbines available data, by wind turbine
Group failure is divided into generator system failure, gearbox system failure and pitch-controlled system failure；
(3) fault diagnosis classification and process:
Fault diagnosis is divided into offline diagnosis and inline diagnosis both of which, and offline diagnosis is promoted by the study to historical data
Inherent parameters, and inline diagnosis refers to using trained neural network according to the fan operation state of online acquisition progress event in real time
Barrier diagnosis；
(4) diagnostic evaluation:
Fault diagnosis evaluation is evaluated and tested using false dismissed rate, false alarm rate and overall accuracy, their formula are as follows:
False dismissed rate=FN/(TP+FN)
False alarm rate=FP/(TN+FP)
Overall accuracy=(FP+FN)/(TP+TN+FP+FN)
Wherein, case that TP classification is 1 (faulty) is appropriately determined by system as classification 1, FN classification is 1 (faulty)
Case classification 0 is set to by system erroneous judgement；There is the case that FP classification is 0 (fault-free) to be set to classification 1 by system erroneous judgement, TN is a
Classification is that the case of 0 (fault-free) is appropriately determined by system as classification 0, and false dismissed rate evaluation and test is the ratio that do not alarm in the event of failure
Example, and false alarm rate assessment be the false alarm in fault-free ratio, in fault diagnosis, false dismissed rate and false alarm rate need as far as possible
Although balance is very high but the case where be not carried out fault diagnosis functions to avoid overall accuracy；
(5) failure predication:
Failure predication is to predict following 10 minutes to the 1 hour major systems of inner blower by the observation to current fan operation state
The probability that system breaks down, in running of wind generating set, field personnel can move towards according to the probability value and probability of prediction
The position that future malfunction occurs, time and confidence level are understood, to take maintenance and maintenance measure to provide clue in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811136084.6A CN109543210A (en) | 2018-09-28 | 2018-09-28 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811136084.6A CN109543210A (en) | 2018-09-28 | 2018-09-28 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543210A true CN109543210A (en) | 2019-03-29 |
Family
ID=65843608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811136084.6A Pending CN109543210A (en) | 2018-09-28 | 2018-09-28 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543210A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163389A (en) * | 2019-05-27 | 2019-08-23 | 上海电气泰雷兹交通自动化系统有限公司 | Apply to the Neural Networks Learning Algorithm in predictive maintenance management |
| CN110489805A (en) * | 2019-07-22 | 2019-11-22 | 中国电子科技集团公司第二十九研究所 | A kind of method that airborne electronic equipment information equipment BIT false alarm rate is estimated |
| CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
| CN110817636A (en) * | 2019-11-20 | 2020-02-21 | 上海电气集团股份有限公司 | Elevator door system fault diagnosis method, device, medium and equipment |
| CN110968010A (en) * | 2019-12-24 | 2020-04-07 | 中冶建筑研究总院有限公司 | Novel non-process dust removal centralized monitoring system |
| CN110987166A (en) * | 2019-12-17 | 2020-04-10 | 北京昊鹏智能技术有限公司 | Method, device, equipment and storage medium for predicting health state of rotating machine |
| CN110988563A (en) * | 2019-12-23 | 2020-04-10 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
| CN111008919A (en) * | 2019-12-19 | 2020-04-14 | 国家电网有限公司 | Anti-electricity-stealing system based on artificial intelligence |
| CN111103137A (en) * | 2019-12-16 | 2020-05-05 | 南京松数科技有限公司 | Wind turbine gearbox fault diagnosis method based on deep neural network |
| CN111239672A (en) * | 2020-03-19 | 2020-06-05 | 东南大学 | Machine learning algorithm-based gradient fault prediction method for optical fiber current transformer |
| CN111287912A (en) * | 2020-02-18 | 2020-06-16 | 广州特种承压设备检测研究院 | Fault diagnosis method for variable pitch system of wind driven generator |
| CN111380686A (en) * | 2020-04-26 | 2020-07-07 | 华风数据(深圳)有限公司 | XGboost algorithm model-based fan main bearing fault monitoring and diagnosis method |
| CN111582392A (en) * | 2020-05-12 | 2020-08-25 | 河北工业大学 | Multi-working-condition health state online monitoring method for key components of wind turbine generator |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN112016806A (en) * | 2020-07-28 | 2020-12-01 | 上海发电设备成套设计研究院有限责任公司 | Method, system, medium and device for overhauling state of power station equipment |
| CN112052296A (en) * | 2020-08-24 | 2020-12-08 | 中国水电工程顾问集团有限公司 | Wind power fault diagnosis knowledge base construction method |
| CN112316703A (en) * | 2020-09-30 | 2021-02-05 | 广东华电韶关热电有限公司 | Intelligent monitoring method and system for urea solution spray gun for flue gas denitration |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN113076694A (en) * | 2019-06-20 | 2021-07-06 | 北京实力伟业环保科技有限公司 | Fan fault evaluation equipment based on Internet of things |
| CN113258678A (en) * | 2021-06-03 | 2021-08-13 | 长沙理工大学 | Intelligent power distribution cabinet fault first-aid repair system, method and device |
| CN113449913A (en) * | 2021-06-25 | 2021-09-28 | 上海电机学院 | Rail transit line tripping intelligent early warning system based on SCADA |
| CN113468728A (en) * | 2021-06-11 | 2021-10-01 | 国电南京自动化股份有限公司 | Variable pitch system fault prediction method based on neural network |
| CN113495607A (en) * | 2020-03-18 | 2021-10-12 | 台达电子企业管理（上海）有限公司 | Fault diagnosis method and system for high-voltage generator |
| CN113762536A (en) * | 2021-04-23 | 2021-12-07 | 通辽霍林河坑口发电有限责任公司 | Fault early warning system of generator set equipment |
| WO2023065580A1 (en) * | 2021-10-18 | 2023-04-27 | 中国华能集团清洁能源技术研究院有限公司 | Fault diagnosis method and apparatus for gearbox of wind turbine generator set |
| CN116816578A (en) * | 2023-08-24 | 2023-09-29 | 青岛科技大学 | Impact turbine wave energy power generation system |
| CN117454232A (en) * | 2023-12-22 | 2024-01-26 | 山东未来集团有限公司 | Production network construction fault diagnosis, prediction and health management system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503399A (en) * | 2014-12-09 | 2015-04-08 | 华电电力科学研究院 | Group stage wind power generator set state monitoring and fault diagnosis platform |
| CN105510038A (en) * | 2015-12-31 | 2016-04-20 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| US20170097860A1 (en) * | 2015-10-01 | 2017-04-06 | International Business Machines Corporation | System component failure diagnosis |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN107797063A (en) * | 2017-09-19 | 2018-03-13 | 北京瑞盈同创智能技术研究院有限公司 | Running of wind generating set state estimation and method for diagnosing faults based on SCADA |
-
2018
- 2018-09-28 CN CN201811136084.6A patent/CN109543210A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503399A (en) * | 2014-12-09 | 2015-04-08 | 华电电力科学研究院 | Group stage wind power generator set state monitoring and fault diagnosis platform |
| US20170097860A1 (en) * | 2015-10-01 | 2017-04-06 | International Business Machines Corporation | System component failure diagnosis |
| CN105510038A (en) * | 2015-12-31 | 2016-04-20 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN107797063A (en) * | 2017-09-19 | 2018-03-13 | 北京瑞盈同创智能技术研究院有限公司 | Running of wind generating set state estimation and method for diagnosing faults based on SCADA |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163389A (en) * | 2019-05-27 | 2019-08-23 | 上海电气泰雷兹交通自动化系统有限公司 | Apply to the Neural Networks Learning Algorithm in predictive maintenance management |
| CN113076694B (en) * | 2019-06-20 | 2023-10-20 | 北京实力伟业环保科技有限公司 | Fan fault evaluation equipment based on thing networking |
| CN113076694A (en) * | 2019-06-20 | 2021-07-06 | 北京实力伟业环保科技有限公司 | Fan fault evaluation equipment based on Internet of things |
| CN110489805A (en) * | 2019-07-22 | 2019-11-22 | 中国电子科技集团公司第二十九研究所 | A kind of method that airborne electronic equipment information equipment BIT false alarm rate is estimated |
| CN110489805B (en) * | 2019-07-22 | 2022-03-25 | 中国电子科技集团公司第二十九研究所 | Method for predicting BIT false alarm rate of airborne electronic information equipment |
| CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN112486136B (en) * | 2019-09-11 | 2022-03-15 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN110817636A (en) * | 2019-11-20 | 2020-02-21 | 上海电气集团股份有限公司 | Elevator door system fault diagnosis method, device, medium and equipment |
| CN111103137A (en) * | 2019-12-16 | 2020-05-05 | 南京松数科技有限公司 | Wind turbine gearbox fault diagnosis method based on deep neural network |
| CN110987166A (en) * | 2019-12-17 | 2020-04-10 | 北京昊鹏智能技术有限公司 | Method, device, equipment and storage medium for predicting health state of rotating machine |
| CN111008919A (en) * | 2019-12-19 | 2020-04-14 | 国家电网有限公司 | Anti-electricity-stealing system based on artificial intelligence |
| CN110988563B (en) * | 2019-12-23 | 2022-04-01 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
| CN110988563A (en) * | 2019-12-23 | 2020-04-10 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
| CN110968010B (en) * | 2019-12-24 | 2021-07-30 | 中冶建筑研究总院有限公司 | Non-process dust removal centralized monitoring system |
| CN110968010A (en) * | 2019-12-24 | 2020-04-07 | 中冶建筑研究总院有限公司 | Novel non-process dust removal centralized monitoring system |
| CN111287912A (en) * | 2020-02-18 | 2020-06-16 | 广州特种承压设备检测研究院 | Fault diagnosis method for variable pitch system of wind driven generator |
| CN113495607A (en) * | 2020-03-18 | 2021-10-12 | 台达电子企业管理（上海）有限公司 | Fault diagnosis method and system for high-voltage generator |
| US11852686B2 (en) | 2020-03-18 | 2023-12-26 | Delta Electronics (Shanghai) Co., Ltd. | Fault diagnosis method and system for high-voltage generator |
| CN111239672A (en) * | 2020-03-19 | 2020-06-05 | 东南大学 | Machine learning algorithm-based gradient fault prediction method for optical fiber current transformer |
| CN111239672B (en) * | 2020-03-19 | 2022-07-29 | 东南大学 | Machine learning algorithm-based gradient fault prediction method for optical fiber current transformer |
| CN111380686A (en) * | 2020-04-26 | 2020-07-07 | 华风数据(深圳)有限公司 | XGboost algorithm model-based fan main bearing fault monitoring and diagnosis method |
| CN111582392A (en) * | 2020-05-12 | 2020-08-25 | 河北工业大学 | Multi-working-condition health state online monitoring method for key components of wind turbine generator |
| CN112016806A (en) * | 2020-07-28 | 2020-12-01 | 上海发电设备成套设计研究院有限责任公司 | Method, system, medium and device for overhauling state of power station equipment |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN111985561B (en) * | 2020-08-19 | 2023-02-21 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN112052296B (en) * | 2020-08-24 | 2024-01-09 | 中国水电工程顾问集团有限公司 | Wind power fault diagnosis knowledge base construction method |
| CN112052296A (en) * | 2020-08-24 | 2020-12-08 | 中国水电工程顾问集团有限公司 | Wind power fault diagnosis knowledge base construction method |
| CN112316703A (en) * | 2020-09-30 | 2021-02-05 | 广东华电韶关热电有限公司 | Intelligent monitoring method and system for urea solution spray gun for flue gas denitration |
| CN113762536A (en) * | 2021-04-23 | 2021-12-07 | 通辽霍林河坑口发电有限责任公司 | Fault early warning system of generator set equipment |
| CN113258678A (en) * | 2021-06-03 | 2021-08-13 | 长沙理工大学 | Intelligent power distribution cabinet fault first-aid repair system, method and device |
| CN113468728A (en) * | 2021-06-11 | 2021-10-01 | 国电南京自动化股份有限公司 | Variable pitch system fault prediction method based on neural network |
| CN113468728B (en) * | 2021-06-11 | 2024-02-02 | 国电南京自动化股份有限公司 | Variable pitch system fault prediction method based on neural network |
| CN113449913B (en) * | 2021-06-25 | 2022-10-28 | 上海电机学院 | Rail transit line tripping intelligent early warning system based on SCADA |
| CN113449913A (en) * | 2021-06-25 | 2021-09-28 | 上海电机学院 | Rail transit line tripping intelligent early warning system based on SCADA |
| WO2023065580A1 (en) * | 2021-10-18 | 2023-04-27 | 中国华能集团清洁能源技术研究院有限公司 | Fault diagnosis method and apparatus for gearbox of wind turbine generator set |
| CN116816578A (en) * | 2023-08-24 | 2023-09-29 | 青岛科技大学 | Impact turbine wave energy power generation system |
| CN116816578B (en) * | 2023-08-24 | 2023-12-22 | 青岛科技大学 | Impact turbine wave energy power generation system |
| CN117454232A (en) * | 2023-12-22 | 2024-01-26 | 山东未来集团有限公司 | Production network construction fault diagnosis, prediction and health management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543210A (en) | A kind of Wind turbines failure prediction system based on machine learning algorithm platform | |
| Fu et al. | Condition monitoring of wind turbine gearbox bearing based on deep learning model | |
| CN108897954A (en) | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations | |
| Udo et al. | Data-driven predictive maintenance of wind turbine based on SCADA data | |
| Dao | On Wilcoxon rank sum test for condition monitoring and fault detection of wind turbines | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| US11840998B2 (en) | Hydraulic turbine cavitation acoustic signal identification method based on big data machine learning | |
| CN111582392B (en) | Multi-working-condition health state online monitoring method for key components of wind turbine generator | |
| CN105550943A (en) | Method for identifying abnormity of state parameters of wind turbine generator based on fuzzy comprehensive evaluation | |
| Zhan et al. | Abnormal vibration detection of wind turbine based on temporal convolution network and multivariate coefficient of variation | |
| CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
| CN107038453A (en) | The fault early warning system and determination methods of a kind of Wind turbines | |
| Joshuva et al. | A comparative study of Bayes classifiers for blade fault diagnosis in wind turbines through vibration signals | |
| Ramirez et al. | Alarms management by supervisory control and data acquisition system for wind turbines | |
| Marugán et al. | SCADA and artificial neural networks for maintenance management | |
| CN107229017A (en) | A kind of wind generating set pitch control battery abnormal failure Forecasting Methodology | |
| Shi et al. | Study of wind turbine fault diagnosis and early warning based on SCADA data | |
| Liang et al. | Multi-running state health assessment of wind turbines drive system based on BiLSTM and GMM | |
| Zhan et al. | Condition monitoring of wind turbines based on spatial-temporal feature aggregation networks | |
| Surjandari et al. | Fault detection system using machine learning on geothermal power plant | |
| CN115600695B (en) | Fault diagnosis method for metering equipment | |
| Zhao | Fault Diagnosis Method for Wind Power Equipment Based on Hidden Markov Model | |
| Jing et al. | Two-layer PSDG based fault diagnosis for wind turbines | |
| Song et al. | Anomaly detection of wind turbine generator based on temporal information | |
| Souza et al. | Evaluation of data based normal behavior models for fault detection in 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |