Sequential diagnosis method for rotating machinery using support vector machines and possibility theory

Authors:
Hongtao Xue;Ke Li;Huaqing Wang;Peng Chen
Affiliations:
Graduate School of Bioresources, Mie University, Japan;School of Mechanical Engineering, Jiangnan University, Wuxi, China;Beijing University of Chemical Technology, Beijing, China;Graduate School of Bioresources, Mie University, Japan
Venue:
ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories
Year:
2013

Citing 2
Cited 0

Artificial Intelligence in Maintenance

Artificial Intelligence in Maintenance
Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study proposes a new intelligent diagnosis method for rotating machinery using support vector machines (SVMs) and possibility theory on basis of the vibration signals, to detect faults and identify fault types at an early stage. The non-dimensional symptom parameters (NSPs) in the frequency domain are defined to reflect the features of the vibration signals. SVMs are used to construct the optimal classification hyper-plane, then to integrate a new symptom parameter, which is called as synthetic symptom parameter (SSP). Finally, the possibility distributions of the SSP are used to distinguish faults by sequential inference and possibility theory. The proposed method has been applied to detect the faults of the V-belt driving equipment in a centrifugal fan, and the efficiency of the method has been verified using practical examples.