Wind turbine state prediction model establishing method based on grey relation-regression SVM (support vector machine)

A support vector machine and prediction model technology, applied in the field of power grids, can solve problems such as long model training time, many input vectors, and data redundancy

Active Publication Date: 2015-09-30
HUAQIAO UNIVERSITY
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0029] The purpose of the invention is to overcome the deficiencies in the prior art, provide a method for establishing a wind turbine state prediction model based on gray relational regression support vector machine, and overcome the standard support vector machine state prediction model with many input vectors, redundant data, a

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Wind turbine state prediction model establishing method based on grey relation-regression SVM (support vector machine)
  • Wind turbine state prediction model establishing method based on grey relation-regression SVM (support vector machine)
  • Wind turbine state prediction model establishing method based on grey relation-regression SVM (support vector machine)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] See figure 1 with figure 2 As shown, a method for establishing a wind turbine state prediction model based on gray relational regression support vector machines of the present invention includes: determining input variables, regression support vector machine training modeling and prediction stages;

[0089] The step of determining the input variable is:

[0090] A1. Collect historical data with forecasting units through the wind power plant SCADA system;

[0091] A2. Select a state quantity that needs to be predicted as the reference sequence, that is, the output; the remaining monitoring items are used as the comparison sequence, that is, the input;

[0092] A3. Calculate the correlation coefficient and degree of correlation between all comparison sequences and reference sequences;

[0093] A4. Arrange the degree of relevance in descending order, and select the monitoring items with greater relevance as the final input for prediction;

[0094] The training modeling steps of the ...

Embodiment 2

[0137] In this example, the SCADA historical record of a single unit of a wind farm in Northeast China that safely operated for one month from March 16 to April 15, 2012 is used as the data source. The system has a total of 44 continuous monitoring items, and the sampling frequency is 1. Times / min.

[0138] (1) Data preprocessing

[0139] The total number of samples in the sampling period is 44600×44 groups, and the data is preprocessed as follows:

[0140] a) When the unit fails, its status and related parameters will fluctuate greatly, which will affect the prediction. Therefore, in order to avoid the impact of wind turbine failure data on the establishment of the model, it is necessary to ensure that there is no unplanned occurrence in the first half month of the selected sample Downtime

[0141] b) The state of wind turbines is inseparable from the wind speed. When the wind speed is too low, the impeller speed is unstable and the unit's operating state is not stable. When the win...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a wind turbine state prediction model establishing method based on a grey relation-regression SVM (support vector machine). The method comprises input variable determination, regression SVM training modeling and a prediction stage. The invention aims to solve the problems of multiple input vectors, data redundancy, poor prediction accuracy, long model training time and the like of a standard SVM state prediction model and provides the wind turbine state prediction model establishing method based on the grey relation-regression SVM, firm technological support is provided for guarantee of safe running of the wind turbine and reduction of non-planned shutdown times, traditional methods are improved, two methods are combined skillfully, a state prediction model is established, the wind turbine state is predicted with a simple and practical method, grey relational analysis is performed on each monitoring program, main factors are screened out, and unrelated information is rejected, so that the method is high in prediction accuracy, short in model training time and practicable.

Description

Technical field [0001] The invention relates to the technical field of power grids, and in particular to a method for establishing a state prediction model of a wind turbine based on a gray correlation regression support vector machine, which can be used for trend prediction of the state of the wind turbine. Background technique [0002] The state prediction of wind turbines is an important method recommended by the International Electrotechnical Commission to effectively and timely discover early failures of wind turbines. Predicting the future change trend of the state quantity based on historical data, discovering the latent failure of the unit in advance, and monitoring the operation status of the unit are of great significance to the reasonable arrangement of the state maintenance of the wind turbine. [0003] At present, most of the research on state prediction is based on the different characteristics of the various sub-systems of the wind turbine and the different character...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/04G06Q50/06
CPCY04S10/50
Inventor 方瑞明李玉洁
Owner HUAQIAO UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap