CN112613183A - Power curve modeling and calculating method of wind generating set - Google Patents
Power curve modeling and calculating method of wind generating set Download PDFInfo
- Publication number
- CN112613183A CN112613183A CN202011592478.XA CN202011592478A CN112613183A CN 112613183 A CN112613183 A CN 112613183A CN 202011592478 A CN202011592478 A CN 202011592478A CN 112613183 A CN112613183 A CN 112613183A
- Authority
- CN
- China
- Prior art keywords
- data
- event
- power curve
- modeling
- calculating
- 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 31
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000013499 data model Methods 0.000 claims abstract description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Wind Motors (AREA)
Abstract
A power curve modeling and calculating method of a wind generating set comprises the following steps: the method comprises the steps of collecting event data and related parameter information of the wind generating set, preprocessing the collected event data, adding a mark symbol, screening primary event information, collecting operation data of the wind generating set, preprocessing the operation data, enabling the screened primary event information to correspond to the preprocessed operation data, screening useful data, establishing a standard power curve data model, and calculating related indexes of a power curve. The method can eliminate abnormal data at the beginning of data modeling, and screen out effective sample data.
Description
Technical Field
The invention relates to the technical field of post-evaluation of wind power plant performance, in particular to a power curve modeling and calculating method of a wind generating set.
Background
The power curve is a curve representing the corresponding relation between the output power and the wind speed of the wind turbine generator under the normal operation condition, and is a main method for measuring the power generation performance of the wind turbine generator. The power curve can be combined with wind distribution to calculate technical indexes such as annual generated energy of a single unit and a wind power plant. The accuracy of the power curve is therefore particularly important.
At present, the common method for fitting the power curve of the wind turbine generator is to collect SCADA (supervisory control and data acquisition) operation data of the wind turbine generator to obtain a group of average wind speed and average power, and to remove abnormal data and screen effective sample data from the average wind speed and average power by adopting a mathematical statistics, big data or machine learning method. The core of the method depends on a data screening method, and due to the fact that 'bad' data are introduced at the beginning of data modeling, one hundred percent of abnormal data can not be eliminated no matter how sophisticated the data screening method is, so that the deviation of a power curve obtained through calculation from the actual situation is large.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a power curve modeling and calculating method of a wind generating set, which eliminates abnormal data and screens out effective sample data at the beginning of data modeling.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a power curve modeling and calculating method of a wind generating set comprises the following steps:
step S1: collecting event data of a wind generating set to be analyzed and related parameter information of the wind generating set;
step S2: preprocessing the collected event data;
step S3: adding a mark symbol to the preprocessed event data;
step S4: screening primary event information according to the marked event data;
step S5: collecting operation data of the wind generating set to be analyzed;
step S6: preprocessing the collected operation data;
step S7: corresponding the primary event information obtained by screening with the preprocessed operation data;
step S8: useful data are screened, a standard power curve data model is established, and relevant indexes of a power curve are calculated.
Preferably, the time range of the wind turbine generator event data collected in step S1 is at least one year, and the time stamp of the event is accurate to seconds.
Preferably, the step S2 specifically includes: and in the statistical time period, determining the fan number, the starting time, the ending time, the event code and the event name of each event on the basis of the original event data, and sequencing according to the sequence of the starting time.
Preferably, the step S3 specifically includes: on the basis of the preprocessed event data, a mark symbol is added to each piece of event data according to the code and name of the event and the nature and reason of the event.
Preferably, the step S4 specifically includes: and combining adjacent event data with the same mark symbol on the basis of the event data added with the mark symbol, wherein the combined start time is the start time of the first event in the combined event data, and the end time is the end time of the last event in the combined event data.
Preferably, the wind turbine generator system operation data collected in step S5 is SCADA operation data, the time range is at least one year, the time stamp is accurate to minutes, and the time interval is 10 minutes.
Preferably, the step S6 specifically includes: and performing data cleaning and abnormal value screening on the collected SCADA operation data.
Preferably, the step S7 specifically includes: and carrying out one-to-one correspondence on the primary event information obtained by screening in the step S4 and the operation data preprocessed in the step S6 according to time.
Preferably, the step S8 specifically includes: and (4) screening out the operation data with the mark symbol of 1 on the basis of the corresponding data obtained in the step (S7), selecting the wind speed and the power, and making a wind speed-power fitting curve, thereby obtaining a standard power curve model and calculating the relevant indexes of the power curve.
The invention provides a power curve modeling and calculating method of a wind generating set. The method has the following beneficial effects: abnormal data is removed at the beginning of data modeling, effective sample data is screened out, introduction of 'bad' data is avoided, a complex mathematical statistics, big data or machine learning method is not needed, the modeling process is simple and clear, and operability is high. Compared with the traditional power curve modeling method, the method can obviously improve the accuracy of the calculation result.
Drawings
In order to more clearly illustrate the present invention or the prior art solutions, the drawings that are needed in the description of the prior art will be briefly described below.
FIG. 1 is a flow chart of a method for modeling and calculating a wind turbine power curve according to an embodiment of the present invention;
fig. 2 is a graph of a power curve fit according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings.
As shown in fig. 1, according to an embodiment of the present invention, a method for modeling and calculating a power curve of a wind turbine generator system is provided, the method comprising the steps of:
step S1: and collecting event data of the wind generating set to be analyzed and related parameter information of the wind generating set.
Specifically, the time range of the collected wind generating set event data is at least one year, and the time stamp of the event is accurate to seconds.
Step S2: the collected event data is pre-processed.
Specifically, in a statistical time period, on the basis of original event data, a fan number, a start time, an end time, an event code and an event name of each event are determined, and sequencing is performed according to the sequence of the start time.
Step S3: adding a mark symbol to the preprocessed event data;
specifically, on the basis of the preprocessed event data, a marker is added to each piece of event data according to the code number and name of the event and in combination with the nature and reason of the event. The marker symbol includes: 1 (normal operation), 2 (abnormal operation), 3 (technical standby), 4 (out of environmental condition), 5 (commanded shutdown), 6 (out of electrical specification), 7 (scheduled maintenance), 8 (planned improvement), 9 (forced shutdown).
Step S4: screening primary event information according to the marked event data;
specifically, based on the event data to which the marker symbol has been added, adjacent event data with the same marker symbol are combined, the start time after combination is the start time of the first event in the combined event data, and the end time is the end time of the last event in the combined event data.
Step S5: collecting operation data of the wind generating set to be analyzed;
specifically, the collected wind generating set operation data is SCADA operation data, the time range is at least one year, the time stamp is accurate to minutes, and the time interval is 10 minutes.
Step S6: preprocessing the collected operation data;
specifically, data cleaning and outlier screening are performed on the collected SCADA operating data.
Step S7: corresponding the primary event information obtained by screening with the preprocessed operation data;
specifically, the primary event information obtained by screening in step S4 and the operation data preprocessed in step S6 are in one-to-one correspondence according to time.
Step S8: useful data are screened, a standard power curve data model is established, and relevant indexes of a power curve are calculated.
Specifically, on the basis of the corresponding data obtained in step S7, the operation data with the marker symbol of 1 is screened out, and then the wind speed and the power are selected to make a wind speed-power fitting curve, so as to obtain a standard power curve model and calculate the relevant index of the power curve.
And collecting event data and operation data of a wind power plant 2019 all year round, processing the data according to the steps, and making a wind speed-power fitting curve on the basis of the finally screened data. As shown in fig. 2, the blue scatter point is the data point screened in the above step for modeling the power curve, and the red curve is the power curve fitted by the scatter point. As can be seen from fig. 2, the finally screened data points are distributed in the power curve accessory in a centralized manner, and the dispersion is very small, so that the method can indirectly reflect that the abnormal data can be effectively removed and the power curve can be accurately simulated.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A power curve modeling and calculating method of a wind generating set is characterized by comprising the following steps:
step S1: collecting event data of a wind generating set to be analyzed and related parameter information of the wind generating set;
step S2: preprocessing the collected event data;
step S3: adding a mark symbol to the preprocessed event data;
step S4: screening primary event information according to the marked event data;
step S5: collecting operation data of the wind generating set to be analyzed;
step S6: preprocessing the collected operation data;
step S7: corresponding the primary event information obtained by screening with the preprocessed operation data;
step S8: useful data are screened, a standard power curve data model is established, and relevant indexes of a power curve are calculated.
2. The method of modeling and calculating a power curve for a wind turbine generator set of claim 1, wherein: the time range of the wind generating set event data collected in the step S1 is at least one year, and the time stamp of the event is accurate to seconds.
3. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S2 specifically includes: and in the statistical time period, determining the fan number, the starting time, the ending time, the event code and the event name of each event on the basis of the original event data, and sequencing according to the sequence of the starting time.
4. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S3 specifically includes: on the basis of the preprocessed event data, a mark symbol is added to each piece of event data according to the code and name of the event and the nature and reason of the event.
5. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S4 specifically includes: and combining adjacent event data with the same mark symbol on the basis of the event data added with the mark symbol, wherein the combined start time is the start time of the first event in the combined event data, and the end time is the end time of the last event in the combined event data.
6. The method for modeling and calculating the power curve of a wind turbine generator system according to claim 1, wherein the wind turbine generator system operation data collected in step S5 is SCADA operation data with a time range of at least one year, a time stamp accurate to minutes, and a time interval of 10 minutes.
7. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S6 specifically includes: and performing data cleaning and abnormal value screening on the collected SCADA operation data.
8. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S7 specifically includes: and carrying out one-to-one correspondence on the primary event information obtained by screening in the step S4 and the operation data preprocessed in the step S6 according to time.
9. The method for modeling and calculating the power curve of a wind turbine generator set according to claim 1, wherein the step S8 specifically includes: and (4) screening out the operation data with the mark symbol of 1 on the basis of the corresponding data obtained in the step (S7), selecting the wind speed and the power, and making a wind speed-power fitting curve, thereby obtaining a standard power curve model and calculating the relevant indexes of the power curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011592478.XA CN112613183A (en) | 2020-12-29 | 2020-12-29 | Power curve modeling and calculating method of wind generating set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011592478.XA CN112613183A (en) | 2020-12-29 | 2020-12-29 | Power curve modeling and calculating method of wind generating set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613183A true CN112613183A (en) | 2021-04-06 |
Family
ID=75248726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011592478.XA Pending CN112613183A (en) | 2020-12-29 | 2020-12-29 | Power curve modeling and calculating method of wind generating set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613183A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103323772A (en) * | 2012-03-21 | 2013-09-25 | 北京光耀能源技术股份有限公司 | Wind driven generator operation state analyzing method based on neural network model |
| CN106368908A (en) * | 2016-08-30 | 2017-02-01 | 华电电力科学研究院 | Wind turbine generator set power curve testing method based on SCADA (supervisory control and data acquisition) system |
| CN106991508A (en) * | 2017-05-25 | 2017-07-28 | 华北电力大学 | A kind of running of wind generating set state identification method based on DBSCAN |
| CN109002650A (en) * | 2018-08-21 | 2018-12-14 | 同济大学 | A kind of Wind turbines power curve modeling method |
| CN109800931A (en) * | 2017-11-13 | 2019-05-24 | 北京普华亿能风电技术有限公司 | Wind power plant generated energy loss measurement method and system based on blower SCADA data |
| CN110067708A (en) * | 2019-05-13 | 2019-07-30 | 北京天泽智云科技有限公司 | A method of it is not positive to wind using power curve identification yaw |
| CN110457821A (en) * | 2019-08-12 | 2019-11-15 | 华北电力大学 | Wind power curve Objective Comprehensive Evaluation Method method, apparatus and server |
-
2020
- 2020-12-29 CN CN202011592478.XA patent/CN112613183A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103323772A (en) * | 2012-03-21 | 2013-09-25 | 北京光耀能源技术股份有限公司 | Wind driven generator operation state analyzing method based on neural network model |
| CN106368908A (en) * | 2016-08-30 | 2017-02-01 | 华电电力科学研究院 | Wind turbine generator set power curve testing method based on SCADA (supervisory control and data acquisition) system |
| CN106991508A (en) * | 2017-05-25 | 2017-07-28 | 华北电力大学 | A kind of running of wind generating set state identification method based on DBSCAN |
| CN109800931A (en) * | 2017-11-13 | 2019-05-24 | 北京普华亿能风电技术有限公司 | Wind power plant generated energy loss measurement method and system based on blower SCADA data |
| CN109002650A (en) * | 2018-08-21 | 2018-12-14 | 同济大学 | A kind of Wind turbines power curve modeling method |
| CN110067708A (en) * | 2019-05-13 | 2019-07-30 | 北京天泽智云科技有限公司 | A method of it is not positive to wind using power curve identification yaw |
| CN110457821A (en) * | 2019-08-12 | 2019-11-15 | 华北电力大学 | Wind power curve Objective Comprehensive Evaluation Method method, apparatus and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Artigao et al. | Wind turbine reliability: A comprehensive review towards effective condition monitoring development | |
| CN110259646B (en) | Wind generating set component state early warning method based on historical data | |
| CN112231361B (en) | Wind power project power generation amount evaluation method based on fan operation data | |
| DE212016000186U1 (en) | simulation system | |
| CN108448625B (en) | Fan cut-in wind speed calculation method based on data driving | |
| CN108732494A (en) | A kind of wind-driven generator abnormity diagnosis processing system | |
| CN109356798B (en) | Wind driven generator gearbox state monitoring method based on co-integration analysis | |
| CN103793856A (en) | Power grid equipment state evaluating system based on multiple data sources and method thereof | |
| CN113837604A (en) | Multi-source heterogeneous data fusion and multi-dimensional data correlation analysis system | |
| Bond et al. | Continuous Reliability Enhancement for Wind (CREW) database: wind plant reliability benchmark. | |
| CN110580586A (en) | wind power plant power calculation method considering wake effect and power collection system | |
| CN113987817A (en) | Degradation analysis method for power generation equipment of hydraulic power plant | |
| CN113671922A (en) | Production plan management system based on block chain | |
| CN112613183A (en) | Power curve modeling and calculating method of wind generating set | |
| CN111626542B (en) | Big data-based detection method for generator excitation system | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| CN111367254B (en) | Photovoltaic power station analytic single machine equivalence method, system and equipment | |
| CN115099713A (en) | Smart power grid operation log collection and analysis management system based on big data | |
| CN115170347A (en) | Array wind power plant low-efficiency wind turbine generator digging method based on operating wind power curve | |
| Han et al. | An online calculation method of theoretical power losses for high-voltage distribution system based on rapid modeling and data quality analysis | |
| CN117152355B (en) | Visual supervision system based on factory data | |
| CN110660002B (en) | Method and device for determining failure rate curve of component of wind generating set | |
| CN105243604B (en) | Large photovoltaic power generation cluster light abandoning amount evaluation method based on benchmark photovoltaic power station | |
| CN115860532A (en) | Comprehensive energy operation and maintenance system and method for industrial park | |
| CN113627628B (en) | Method for online calculating repeated overhaul times of same fan based on working ticket |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210406 |
|
| RJ01 | Rejection of invention patent application after publication |