Title :
Machine fault diagnosis using industrial wireless sensor networks and support vector machine
Author :
Bai Jie;Liqun Hou; Ma Yongguang
Author_Institution :
Department of Automation, North China Electric Power University, Baoding 071003, China
fDate :
7/1/2015 12:00:00 AM
Abstract :
A machine fault diagnosis method using industrial wireless sensor networks (IWSNs) and support vector machine (SVM) is presented in this paper as a potential low-cost and effective solution for device condition monitoring and fault diagnosis. On sensor node SVM is proposed and researched to reduce the data transmission between sensor nodes, decrease node energy consumption and increase the fault diagnosis accuracy. Simulation experiments are carried out to verify the proposed method. The simulation results show SVM has strong ability to learn and recognize the machine fault pattern.
Keywords :
"Support vector machines","Fault diagnosis","Induction motors","Feature extraction","Monitoring","Training","Wireless sensor networks"
Conference_Titel :
Electronic Measurement & Instruments (ICEMI), 2015 12th IEEE International Conference on
DOI :
10.1109/ICEMI.2015.7494241