CN103899482A - Method for compressing data of status monitoring system of wind turbine generator system - Google Patents
Method for compressing data of status monitoring system of wind turbine generator system Download PDFInfo
- Publication number
- CN103899482A CN103899482A CN201410152223.XA CN201410152223A CN103899482A CN 103899482 A CN103899482 A CN 103899482A CN 201410152223 A CN201410152223 A CN 201410152223A CN 103899482 A CN103899482 A CN 103899482A
- Authority
- CN
- China
- Prior art keywords
- data
- wind
- generating set
- condition monitoring
- power generating
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000005611 electricity Effects 0.000 claims abstract description 41
- 238000007906 compression Methods 0.000 claims abstract description 10
- 230000006835 compression Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 230000005540 biological transmission Effects 0.000 claims abstract description 4
- 230000008878 coupling Effects 0.000 claims description 14
- 238000010168 coupling process Methods 0.000 claims description 14
- 238000005859 coupling reaction Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 12
- 238000013481 data capture Methods 0.000 claims description 6
- 238000013499 data model Methods 0.000 claims description 5
- 206010008190 Cerebrovascular accident Diseases 0.000 claims description 3
- 208000006011 Stroke Diseases 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 abstract description 4
- 238000013144 data compression Methods 0.000 abstract description 3
- 238000011084 recovery Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Wind Motors (AREA)
Abstract
The invention provides a method for compressing data of a status monitoring system of a wind turbine generator system. Strong features are extracted in the mode that mathematical modeling is conducted on the monitoring data locally in the wind turbine generator system, and data compression and recovery are conducted according to a high compression ratio. The method comprises the following steps of collection of the wind electricity status monitoring data, identification of operating conditions of the wind turbine generator system, filtration of the wind electricity status monitoring data, local collating of monitoring data information, wind electricity status storage mode selection, identification and matching of intelligent modeling structures, estimation of parameters of the intelligent modeling structures, local primary processing of the monitoring data and upper monitoring terminal secondary processing. By means of the method, mass data on-line transmission and long-term continuous monitoring storage are achieved.
Description
Technical field
The invention belongs to technical field of wind power generation, relate in particular to data modeling wind power generating set condition monitoring system data compression technique field.
Background technique
In existing wind-power electricity generation method for monitoring state, wind power generating set condition monitoring system need to be monitored all set state information in wind energy turbine set, monitoring parameter is huge, and because wind energy turbine set monitor data time domain specification and frequency domain character are all difficult to occur significant change in a short time, if therefore will monitor continuously reflection wind power generating set change of state by state need to store a large amount of long-term monitor datas, require high to memory storage capabilities, storing queries inefficiency, particularly in the time that needs are analyzed long-term wind power equipment change of state situation, need to carry out centralized Analysis to mass data, take greatly watch-dog data analysis resource, condition monitoring effect is poor.
Summary of the invention
A kind of method of compressing wind power generating set condition monitoring system data, carry out strong feature extraction by the mode of Monitoring Data being carried out to mathematical modeling in wind power generating set this locality, carry out data reduction and reduction in high compression ratio mode, it is characterized in that: comprise the following steps, the data capture of S1 wind-powered electricity generation condition monitoring, the identification of S2 running of wind generating set operating mode, S3 wind-powered electricity generation condition monitoring data screening, S4 monitor data information is local to be arranged, S5 wind-powered electricity generation state memory module is selected, S6 intelligent modeling Structure Identification coupling, S7 model of mind on-line identification, the local single treatment of S8 monitor data, the secondary treatment of S9 upper monitoring terminal.
In the data capture of step S1 wind-powered electricity generation condition monitoring, wind power generating set condition monitoring data acquistion system gathers and filtering operation Sensor monitoring data, noise in filtering monitors physical signal, and physics supervisory signal is converted into the digital signal with physical significance.
Monitor state information includes but are not limited to the information such as wind power generating set and assembly vibration thereof, rotating speed, temperature, pressure, stress, moment of torsion, oil product oil, video, audio frequency, wind speed, security protection, electric network information.
In the identification of step S2 running of wind generating set operating mode, the identification of running of wind generating set operating mode mainly refers to by monitor data is analyzed, the typical Operational Limits in conjunction with wind power generating set under different operating conditionss, intelligent recognition wind power generating set running state.
In step S3 wind-powered electricity generation condition monitoring data screening, wind-powered electricity generation condition monitoring data screening mainly refers to be differentiated the validity of monitor message, screens out manifest error data, and it is carried out to interpolation processing.
In the local arrangement of step S4 monitor data information, the local arrangement of monitor data information is mainly the valid data according to step S3 wind-powered electricity generation condition monitoring data screening, it,, according to set form requirement, is packaged into operating states of the units information and monitor message to the data module of fixed length.
During step S5 wind-powered electricity generation state memory module is selected, wind-powered electricity generation state memory module selects the local and outside fault alarm information of Main Basis, monitor data Query Information, the non-compression monitor data transmission information of timing etc. to carry out data model storage selection.
In step S5 wind-powered electricity generation state memory module is selected, wind-powered electricity generation state memory module selection result is that compact model directly enters step S6 intelligent modeling Structure Identification coupling; Otherwise directly jump to the local single treatment of step S8 monitor data.
In step S6 intelligent modeling Structure Identification coupling, intelligent modeling Structure Identification coupling is according to step S2 running of wind generating set operating mode identification apoplexy group of motors operation mode recognition result, Intelligent Matching monitor data under different operating modes is carried out to data model coupling according to data type.
In step S7 model of mind on-line identification, model of mind on-line identification is the model structure according to coupling, based on the local data that arrange after according to fixed format packing of monitor data information in the local arrangement of step S4 monitor data information, according to setup parameter identifying method, and estimate identification model parameter based on computational intelligence.
In the local single treatment of step S8 monitor data, the local single treatment of monitor data mainly refers to by wind-powered electricity generation unit local information processing unit carries out data processing, in the time that step S5 wind-powered electricity generation state memory module selection result is non-compact model, directly unpacked data is uploaded to upper monitoring terminal; In the time that step S5 wind-powered electricity generation state memory module selection result is compact model, will after step step S2 running of wind generating set operating mode identification apoplexy group of motors operation mode recognition result, data modeling Matching Model information, the packing of modeler model parameter information, issue upper monitoring terminal.
In the secondary treatment of step S9 upper monitoring terminal, in the time that the wind-powered electricity generation state memory module selection result of step S5 wind-powered electricity generation state memory module selection is non-compact model, directly unpacked data is stored to upper location supervisory designated storage area; In the time that the wind-powered electricity generation state memory module selection result of step S5 wind-powered electricity generation state memory module selection is compact model, the secondary treatment of upper monitoring terminal is mainly carried out Intelligent Fusion classification processing by the local single treatment data of monitor data in the local single treatment of step S8 monitor data continuously to multiple, the model parameter that make in long period section under same operating conditions, model structure the is identical set of model parameter that permeates, realizes mass data secondary compression.
In the secondary treatment of step S9 upper monitoring terminal, carry out Intelligent Fusion classification processing method by the local single treatment data of monitor data in the local single treatment of step S8 monitor data continuously to multiple, its mathematic(al) manipulation unified approach can adopt direct weighted mean method to realize, and directly the identical model parameter of model structure is weighted on average.
Of the present inventionly be not only applicable to the data reduction of wind power generating set condition monitoring based on data modeling wind power generating set condition monitoring system data compression method, be also applicable to various different occasions based on the continuous monitor data of magnanimity compression storing data and method of reducing.
accompanying drawing explanation
Fig. 1 is a kind of method schematic diagram that compresses wind power generating set condition monitoring system data.
Embodiment
A kind of method of compressing wind power generating set condition monitoring system data that the present invention proposes, can be based on PLC platform or embedded development platform, by by local to data acquisition module, data processing module, logic analysis module and monitor message memory module integration realization.
In the data capture of step S1 wind-powered electricity generation condition monitoring, monitor state information gathering can realize by PLC or embedded data acquisition board.
In the identification of step S2 running of wind generating set operating mode, the identifying method of running of wind generating set operating mode can be carried out operating mode identification according to mean wind velocity information or wind power generator rotor rotary speed information.
In step S3 wind-powered electricity generation condition monitoring data screening, wind-powered electricity generation condition monitoring data screening is mainly to consider to eliminate in data capture or transmitting procedure owing to being subject to the issuable wrong report data of influence of noise, improves the accuracy of data modeling.
Step S4 monitor data information is local to be arranged, and the valid data that screen according to step S3 wind-powered electricity generation condition monitoring data screening according to set form requirement, are packaged into operating states of the units information and monitor message the data module of fixed length to it.Wherein set form requires to refer to monitor message is converted into the reference variable information that can be convenient to state analysis, mainly comprises that filtering processing, a variable are converted into secondary or high order variable etc.For example: velocity information is converted into mean velocity information, vibration velocity is converted into vibration severity information or obtains the specific frequency domain segment data of signal etc. by wave filter.
Step S4 monitor data information is local to be arranged, and the valid data that screen according to step S3 wind-powered electricity generation condition monitoring data screening according to set form requirement, are packaged into operating states of the units information and monitor message the data module of fixed length to it.Wherein, when the data module that is packaged into fixed length mainly considers that upper location supervisory secondary compression is processed, the convenience that modeling parameters is calculated.Particularly, in the time that data model is linear model or statistical model, when processing, upper location supervisory secondary compression only need average to same model parameter under identical operating mode.
During step S5 wind-powered electricity generation state memory module is selected, wind-powered electricity generation state memory module is mainly considered directly data to be packed under normal circumstances, in the time breaking down or have query demand, detailed status monitor message is uploaded, for upper monitoring terminal provides detailed state analysis data.
In step S6 intelligent modeling Structure Identification coupling, Matching Model includes but are not limited to: statistics class model, linearity and non-new relationship mapping class model etc.Wherein, statistical model typically refers to describes the distribution character of monitored variable, can adopt to include but are not limited to the method such as data statistics, fitting of a polynomial the distribution character of monitored variable is carried out to modeling.
In step S6 intelligent modeling Structure Identification coupling, Matching Model includes but are not limited to: statistics class model, linearity and non-new relationship mapping class model etc.Wherein, linear and non-new relationship mapping class model typically refers to the mapping relations of describing between two or more variablees, can realize by including but are not limited to the linear non-linear modeling method such as transfer function, neuron network.
In step S7 model of mind on-line identification, model of mind on-line identification method can adopt intelligent search algorithms such as including but are not limited to statistical approach, polynomial fitting method, method of least squares, random search etc.
In the local single treatment of step S8 monitor data, the local single treatment of monitor data can realize by DDP, and by monitor network, monitor data is sent to upper monitoring terminal.One is preferably in scheme, and the local single treatment of monitor data can realize in wind power generating set local monitoring system, and monitor message is sent to the upper monitoring terminal that is positioned at central control chamber by wind energy turbine set fiber optic Ethernet looped network.
Step S9 upper monitoring terminal secondary treatment: the secondary treatment of upper monitoring terminal can realize by Centralized Monitoring processor, receives by Centralized Monitoring processor the single treatment data that in wind energy turbine set, each typhoon group of motors sends and concentrates secondary treatment.One is preferably in scheme, and the secondary treatment of upper monitoring terminal can realize by the Centralized Monitoring processing server that is arranged on central control chamber.
The present invention carries out strong feature extraction, carries out data reduction and reduction in high compression ratio mode in the mode of mathematical modeling Monitoring Data local realization of wind-powered electricity generation unit, replace traditional Real-time Monitoring Data with modeling parameters, and the data that can realize on statistical significance are recovered, effectively solve the online transmission of wind power generating set condition monitoring system mass data and the long-term storage problem of monitoring continuously, make up prior art defect, further promote validity and the practicability of wind power generating set condition monitoring system.
Claims (10)
1. one kind is compressed the method for wind power generating set condition monitoring system data, carry out strong feature extraction by the mode of Monitoring Data being carried out to mathematical modeling in wind power generating set this locality, carry out data reduction and reduction in high compression ratio mode, it is characterized in that: comprise the following steps, the data capture of S1 wind-powered electricity generation condition monitoring, the identification of S2 running of wind generating set operating mode, S3 wind-powered electricity generation condition monitoring data screening, S4 monitor data information is local to be arranged, S5 wind-powered electricity generation state memory module is selected, S6 intelligent modeling Structure Identification coupling, S7 model of mind on-line identification, the local single treatment of S8 monitor data, the secondary treatment of S9 upper monitoring terminal.
2. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in the data capture of step S1 wind-powered electricity generation condition monitoring, wind power generating set condition monitoring data acquistion system gathers and filtering operation Sensor monitoring data, noise in filtering monitors physical signal, and physics supervisory signal is converted into the digital signal with physical significance.
3. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, is characterized in that: monitor state information includes but are not limited to the information such as wind power generating set and assembly vibration thereof, rotating speed, temperature, pressure, stress, moment of torsion, oil product oil, video, audio frequency, wind speed, security protection, electric network information.
4. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in the identification of step S2 running of wind generating set operating mode, the identification of running of wind generating set operating mode mainly refers to by monitor data is analyzed, typical Operational Limits in conjunction with wind power generating set under different operating conditionss, intelligent recognition wind power generating set running state.
5. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in step S3 wind-powered electricity generation condition monitoring data screening, wind-powered electricity generation condition monitoring data screening mainly refers to be differentiated the validity of monitor message, screen out manifest error data, and it is carried out to interpolation processing.
6. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in the local arrangement of step S4 monitor data information, the local arrangement of monitor data information is mainly the valid data according to step S3 wind-powered electricity generation condition monitoring data screening, it,, according to set form requirement, is packaged into operating states of the units information and monitor message to the data module of fixed length.
7. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: during step S5 wind-powered electricity generation state memory module is selected, wind-powered electricity generation state memory module selects the local and outside fault alarm information of Main Basis, monitor data Query Information, the non-compression monitor data transmission information of timing etc. to carry out data model storage selection.
8. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in step S5 wind-powered electricity generation state memory module is selected, wind-powered electricity generation state memory module selection result is that compact model directly enters step S6 intelligent modeling Structure Identification coupling; Otherwise directly jump to the local single treatment of step S8 monitor data.
9. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in step S6 intelligent modeling Structure Identification coupling, intelligent modeling Structure Identification coupling is according to step S2 running of wind generating set operating mode identification apoplexy group of motors operation mode recognition result, Intelligent Matching monitor data under different operating modes is carried out to data model coupling according to data type.
10. a kind of method of compressing wind power generating set condition monitoring system data according to claim 1, it is characterized in that: in step S7 model of mind on-line identification, model of mind on-line identification is the model structure according to coupling, based on the local data that arrange after according to fixed format packing of monitor data information in the local arrangement of step S4 monitor data information, according to setup parameter identifying method, and estimate identification model parameter based on computational intelligence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410152223.XA CN103899482A (en) | 2014-04-16 | 2014-04-16 | Method for compressing data of status monitoring system of wind turbine generator system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410152223.XA CN103899482A (en) | 2014-04-16 | 2014-04-16 | Method for compressing data of status monitoring system of wind turbine generator system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103899482A true CN103899482A (en) | 2014-07-02 |
Family
ID=50991011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410152223.XA Pending CN103899482A (en) | 2014-04-16 | 2014-04-16 | Method for compressing data of status monitoring system of wind turbine generator system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103899482A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292411A (en) * | 2015-06-03 | 2017-01-04 | 安顺市晶英科技研发有限责任公司 | A kind of tea picking machine group control optimizes system |
| CN106656537A (en) * | 2015-11-03 | 2017-05-10 | 中国移动通信集团公司 | IT cluster system monitoring method, device, terminal and system |
| CN107748830A (en) * | 2017-11-15 | 2018-03-02 | 北京工业大学 | The equivalent scale model and its dynamic Characteristic Simulation method of a kind of wind power speed-increasing system |
| CN113661458A (en) * | 2019-04-01 | 2021-11-16 | Ntn株式会社 | Condition monitoring system and wind power generation system provided with the same |
| CN114095570A (en) * | 2021-11-24 | 2022-02-25 | 国网河北省电力有限公司电力科学研究院 | Data transmission method for power transmission and transformation Internet of things and power transmission and transformation Internet of things |
-
2014
- 2014-04-16 CN CN201410152223.XA patent/CN103899482A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292411A (en) * | 2015-06-03 | 2017-01-04 | 安顺市晶英科技研发有限责任公司 | A kind of tea picking machine group control optimizes system |
| CN106292411B (en) * | 2015-06-03 | 2019-02-01 | 安顺市晶英科技研发有限责任公司 | A kind of tea picking machine group control optimization system |
| CN106656537A (en) * | 2015-11-03 | 2017-05-10 | 中国移动通信集团公司 | IT cluster system monitoring method, device, terminal and system |
| CN106656537B (en) * | 2015-11-03 | 2020-02-14 | 中国移动通信集团公司 | IT cluster system monitoring method, device, terminal and system |
| CN107748830A (en) * | 2017-11-15 | 2018-03-02 | 北京工业大学 | The equivalent scale model and its dynamic Characteristic Simulation method of a kind of wind power speed-increasing system |
| CN113661458A (en) * | 2019-04-01 | 2021-11-16 | Ntn株式会社 | Condition monitoring system and wind power generation system provided with the same |
| US12071928B2 (en) | 2019-04-01 | 2024-08-27 | Ntn Corporation | Condition monitoring system and wind power generation system including the same |
| CN114095570A (en) * | 2021-11-24 | 2022-02-25 | 国网河北省电力有限公司电力科学研究院 | Data transmission method for power transmission and transformation Internet of things and power transmission and transformation Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103758694A (en) | Wind turbine generator system state monitoring system data compressing method | |
| CN103899482A (en) | Method for compressing data of status monitoring system of wind turbine generator system | |
| CN103604622B (en) | Wind turbine generator system on-line monitoring instant alarm and fault diagnosis system | |
| CN107035602A (en) | A kind of turbine state monitoring and fault diagnosis system | |
| CN103278728B (en) | Short Circuit Between Generator Rotor Windings method for diagnosing faults and system | |
| CN103711645B (en) | Based on the wind power generating set state evaluating method of modeling parameters signature analysis | |
| CN103742358B (en) | A kind of Combined type wind driven generator group condition monitoring system | |
| Zhang et al. | A novel fault diagnosis method for wind turbine based on adaptive multivariate time-series convolutional network using SCADA data | |
| CN112834224B (en) | Nuclear power steam turbine generator health state assessment method and system | |
| CN107061183A (en) | A kind of automation method for diagnosing faults of offshore wind farm unit | |
| CN104048749A (en) | Vibration fault detection system and method for wind turbine generator units | |
| CN103670373B (en) | Method and system for diagnosing faults of oil pumping unit | |
| CN102840101A (en) | Distributed condition monitoring system | |
| CN105587463A (en) | Remote monitoring method of wind power generation | |
| CN102758727B (en) | Wind turbine state monitoring and error diagnosis system and method integrated into control system | |
| CN213149750U (en) | State evaluation and fault prediction system for steam turbine generator unit | |
| CN104865860A (en) | Sampling, storing and inquiring method and device of WTGS (Wind Turbine Generator System) state monitoring system | |
| CN106227127A (en) | Generating equipment intelligent monitoring and controlling device and monitoring method | |
| CN202793793U (en) | Large wind generation set bearing fault diagnosis system | |
| CN117189508A (en) | Wind turbine status monitoring method based on multi-view spatio-temporal feature fusion | |
| CN103034207A (en) | Infrastructure health monitoring system and implementation process thereof | |
| CN111555776A (en) | Fusion sensing and joint diagnosis method, system and device for power transmission line | |
| CN104238521A (en) | Offshore wind plant remote management system | |
| CN106934728A (en) | A kind of power grid security risk management and control intelligent evaluation method | |
| CN114564804A (en) | Blade breakage early warning method and device for wind turbine generator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140702 |
|
| WD01 | Invention patent application deemed withdrawn after publication |