Title :
A fast fault diagnosis method for wind turbine generator system based on rough set-decision tree
Author :
Wang, Huizhong ; Peng, Anqun ; Wang, Xiaolan
Author_Institution :
Sch. of Electr. Eng. & Inf. Eng., Lanzhou Univ. of Technol., Lanzhou, China
Abstract :
With rough set theory for knowledge reduction capability and C4.5 decision tree algorithm for fast classification of strengths, an improved rough set-decision tree model for fault diagnosis of wind generation system is built. The results show that the proposed method can not only decreases the workload of feature datum extraction, but also identifies the fault patterns rapidly and accurately, and it exhibits better engineering practicality comparing with the C4.5-based method.
Keywords :
AC generators; fault diagnosis; feature extraction; power generation faults; rough set theory; trees (mathematics); wind turbines; C4.5 decision tree algorithm; fast fault diagnosis method; fault patterns; feature datum extraction; knowledge reduction capability; rough set-decision tree; wind turbine generator system; Classification algorithms; Clustering algorithms; Decision trees; Fault diagnosis; Matrix converters; Signal processing algorithms; Wind turbines; C4.5 arithmetic; WTGS; fault diagnosis; rough set;
Conference_Titel :
Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on
Conference_Location :
Deng Leng
Print_ISBN :
978-1-4577-0535-9
DOI :
10.1109/AIMSEC.2011.6010152
