Fault diagnosis method of machinery based on fisher's linear discriminant and possibility theory

Authors:
Weijuan Jiang;Zhongxing Li;Ke Li;Hongtao Xue;Peng Chen
Affiliations:
School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, Jiangsu, China,Graduate School of Bioresources, Mie University, Tsu, Mie, Japan;School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, Jiangsu, China;Graduate School of Bioresources, Mie University, Tsu, Mie, Japan;Graduate School of Bioresources, Mie University, Tsu, Mie, Japan;Graduate School of Bioresources, Mie University, Tsu, Mie, Japan
Venue:
ICIC'12 Proceedings of the 8th international conference on Intelligent Computing Theories and Applications
Year:
2012

Citing 4
Cited 0

Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems

Applied Soft Computing
Fault diagnosis and condition surveillance for plant rotating machinery using partially-linearized neural network

Computers and Industrial Engineering
Application of an intelligent classification method to mechanical fault diagnosis

Expert Systems with Applications: An International Journal
Intelligent diagnosis method for a centrifugal pump using features of vibration signals

Neural Computing and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new condition diagnosis method for plant machinery using Fisher's linear discriminant and possibility theory. The non-dimensional symptom parameters (NSPs) are defined to reflect the features of the vibration signals measured in each state. Fisher's linear discriminant is used to project the multiple SPs from a high dimensional space to a low dimensional space for distinguishing states, and discriminant rules are set by possibility theory. Moreover, sequential diagnosis is also proposed by which the conditions of the machinery can be identified sequentially. Sensitive evaluation method for selecting good symptom parameters using Distinction Index (DI) is also suggested for detecting faults in rotating machinery. Finally, practical examples of the diagnosis for rotating machine are shown to verify the efficiency of the method.