Application of Multiple Level Rules Set in Fault Diagnosis of the Wind Power Generation System

Abstract:

For the incompletion problem of sensors’ collected data in fault diagnosis of the wind power system, this article puts forward a kind of multiple level rules set based on rough set. First, let the sensors’ collected data go through Fourier transform and extract its feature attributes as well as discrete them. Establish the decision table of fault diagnosis according to attribute values. Then set out from the decision table to establish a multiple level set of nodes with diverse reduced levels and deduce the rules of each node, which has a corresponding belief level. When in reasoning and decision-making of the new data using the multiple level rules set, match the information of the new data with the rule of its corresponding node. Finally, achieve the fault diagnosis of wind power generation system by choosing comprehensive evaluation algorithm. The result of the diagnosis example shows the reliability and accuracy of this method in the diagnosis of fault types for wind power generation system.

• Periodical: Advanced Materials Research (Volumes 512-515)
• Pages: 679-685
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.512-515.679
• Online since: May 2012
• Authors: Gui Mei Gu
• Keywords: Fault Diagnosis, Incompletion, Multiple Level Rules Set, Wind Power Generation System

References

[1] Quan Long, Yongqiang Liu, Yongping Yang. Application of condition monitoring and fault diagnosis to wind turbines[J]. Modern electric power, Vol.25(6)(2008),p.55.(In Chinese)

[2] Zhi Shi,Xinwei Cui,Chunlan Li. Application of online monitoring system in wind power generators[J]. Wind power technology, No.4(2007),p.74.(In Chinese)

[3] Zhemin Zhuang, Guohua Yin, Fenlan Li. Fault diagnosis of wind turbine based on wavelet neural network[J].Transactions of china electrotechnical society, Vol.24(4)(2009),p.224.(In Chinese)

[4] Qichang Duan ,Liang Zhang,Jingming Yuan. Fault diagnosis method for power inverter Based on wavelet neural network with improved algorithm[J]. Journal of Computer applications, Vol.31(8)(2001),p.2143.(In Chinese)

[5] Xueli An, Minghao Zhao,Dongxiang Jiang. Direct-drive wind turbine Fault diagnosis based on support vector machine and multi-source information[J]. Power system technology,Vol.35(4)(2011),p.117. (In Chinese)

[6] Xiaobo Zhang, Xinyan Zhang , Weiqing Wang. Fault analysis of power electronic equipment of wind power system by using neural networks[J]. East China electric power, Vol.36(7)(2008),p.16.(In Chinese)

[7] Yu Gao. Fault diagnosis of wind power electronic devices based on SOM neural network[J]. Proceedings of the CSU-EPSA, Vol.22(3)(2010),p.142.(In Chinese)

[8] Zhonghua Liang, Zhanguo An, Xingzhe Pu and so on. Failure prediction for variable-pitch driver in wind power generator based on Grey Theory[J]. Journal of Shenyang University of Technology, Vol.33(6)(2011),p.629.(In Chinese)

[9] Yurong Li . Research on information fusion and intelligent processing[D]. Hangzhou: Zhejiang University, 2002.(In Chinese)

[10] Qingzhen Liu, Jinding Cai, Shaofang Wang. Fault diagnosis of power electronic circuits based on rough set-neural network system[J].Electric power automation Equipment,Vol.24(4)(2004),p.45. (In Chinese) · 支持中英、中日在线互译 · 支持网页翻译，在输入框输入网页地址即可 · 提供一键清空、复制功能、支持双语对照查看，使您体验更加流畅 分享到 翻译结果重试 抱歉，系统响应超时，请稍后再试 · 支持中英、中日在线互译 · 支持网页翻译，在输入框输入网页地址即可 · 提供一键清空、复制功能、支持双语对照查看，使您体验更加流畅 分享到 翻译结果重试 抱歉，系统响应超时，请稍后再试 · 支持中英、中日在线互译 · 支持网页翻译，在输入框输入网页地址即可 · 提供一键清空、复制功能、支持双语对照查看，使您体验更加流畅