DocumentCode :
2542501
Title :
Hybrid feature selection in fault diagnosis
Author :
Yan, Jian-feng
Author_Institution :
Sch. of Comput. Sci.&Technol., Soochow Univ., Suzhou, China
fYear :
2010
fDate :
16-18 April 2010
Firstpage :
10
Lastpage :
14
Abstract :
To reduce complexity in design of fault diagnosis system for large scale equipments, a hybrid feature selection algorithm is put forth. By introduction of Markov Blanket, reluctant features can be effectively eliminated to decrease the feature space for input parameters of diagnosis system design. An improved Chl-Square method with introduction of frequency, distribution and concentration is adopted to improve the relevance evaluation performance of the Markov Blanket. The hybrid feature selection algorithm showed high performance in design and implementation of an aero-engine automatic fault diagnosis system based on both neural network and decision tree.
Keywords :
Markov processes; fault diagnosis; feature extraction; pattern classification; Markov blanket; fault diagnosis; hybrid feature selection; large scale equipments; Algorithm design and analysis; Computer science; Fault diagnosis; Filters; Frequency; Large-scale systems; Neural networks; Probability distribution; Sensor systems; Space technology; Markov blanket; fault dianosis; feature selection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Management and Engineering (ICIME), 2010 The 2nd IEEE International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-5263-7
Electronic_ISBN :
978-1-4244-5265-1
Type :
conf
DOI :
10.1109/ICIME.2010.5477553
Filename :
5477553
Link To Document :
بازگشت