Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/70589
Title: Industrial fault detection and isolation using Dominant Feature Identification
Authors: Pang, C.K. 
Zhou, J.-H.
Zhong, Z.-W.
Lewis, F.L.
Keywords: Least Square Error (LSE)
Neural Network (NN)
Singular Value Decomposition (SVD)
Issue Date: 2011
Source: Pang, C.K.,Zhou, J.-H.,Zhong, Z.-W.,Lewis, F.L. (2011). Industrial fault detection and isolation using Dominant Feature Identification. ASCC 2011 - 8th Asian Control Conference - Final Program and Proceedings : 1018-1023. ScholarBank@NUS Repository.
Abstract: In this paper, we show how to find a reduced feature subset which is optimal in both estimation and clustering least square errors using two new Dominant Feature Identification (DFI) methods. We apply DFI to to identify the important features in a given set of faults, and a Neural Network (NN) is used for online fault classification based on the determined reduced feature set in the proposed two-stage framework. Our experimental results on an industrial machine fault simulator show the effectiveness in fault diagnosis and classification. Accuracy of 99.4% for fault identification is observed when using proposed new DFI followed by NN classification, reducing the number of required features from 120 to 13 and the number of sensors from 8 to 4. © 2011 Asian Control Association.
Source Title: ASCC 2011 - 8th Asian Control Conference - Final Program and Proceedings
URI: http://scholarbank.nus.edu.sg/handle/10635/70589
ISBN: 9788995605646
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

10
checked on Dec 16, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.