Our main objective in this thesis is to investigate three methods: Principal Component Analysis, Vector Space Model, and Signal Analysis, to establish system behaviours of an electromechanical system based on its historical operation data. The system behaviours are constituted by an aggregate number of similar actions which can be represented as patterns or clusters. The results show that we are also able to observe normal behaviours by interpreting a high percentage of similar actions inside patterns or clusters. Any deviations from the established normal behaviours could be interpreted as abnormal which warrant further investigation with respect to fault pre-emption and detection.
Identifer | oai:union.ndltd.org:uvic.ca/oai:dspace.library.uvic.ca:1828/1846 |
Date | January 2006 |
Creators | Fu, Wei |
Contributors | Li, Kin F. |
Source Sets | University of Victoria |
Language | English, English |
Detected Language | English |
Type | Thesis |
Rights | Available to the World Wide Web |
Page generated in 0.001 seconds