Font Size: a A A

Research On Wind Turbine Fault Diagnosis Based On SCADA Data

Posted on:2017-03-22Degree:MasterType:Thesis
Country:ChinaCandidate:C C LiFull Text:PDF
GTID:2272330503482351Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
With the development of wind power industry, the operation and maintenance of the wind farm have attracted great attention. The SCADA system records the real-time operation state information of the key components of the wind turbine generator. Through the data mining and forecast analysis, it is an effective way to reduce the operation cost of the wind turbine without other sensor and monitoring system.Firstly, the category, working principle and main technical performance of wind turbines have been introduced in this thesis. The phenomenon and reason of common faults have been analyzed. Failure causes and manifestations of several typical parts have been summarized. Then the characteristics and classification of SCADA system have been introduced in detail, which lays a theoretical foundation for the further research.Secondly, traditional fixed step size method, improved mahalanobis distance based nonlinear state estimation fault diagnosis method, BP ANN-based and PSO-based fault diagnosis method has been researched. Nonlinear state estimation method is modeled, which relies on the principle of similarity wherein. On the basis of understanding the knowledge of gear box, to predict the temperature of which as an example, selecting rational input variables, and preprocessing the data, four methods have been used to verify the validity by means of modeling respectively. By researching of diagnoses principle and procedure of these four methods, comparing and analyzing the diagnoses result, the advantages and practicability of the improved mahalanobis distance based non-linear state estimation method is proved to be true.At last, an improved nonlinear state estimation algorithm has been proposed in this thesis, and a man-machine interaction interface of the wind turbine generator fault diagnosis system has been designed, which based on the mixed programming technique of Lab VIEW and MATLAB. The system can effectively alarm and diagnose the common parts of the wind turbine, and has positive effect on the safety production and economic operation of wind turbines.
Keywords/Search Tags:wind turbines, fault diagnosis, SCADA datas, non-linear state estimation
PDF Full Text Request
Related items