Unsupervised Condition Change Detection In Large Diesel Engines

Niels Henrik Pontoppidan, Jan Larsen

AbstractThis paper presents a new method for unsupervised change detection which combines independent component modeling and probabilistic outlier etection. The method further provides a compact data representation, which is amenable to interpretation, i.e., the detected condition changes can be investigated further. The method is successfully applied to unsupervised condition change detection in large diesel engines from acoustical emission sensor signal and compared to more classical techniques based on principal component analysis and Gaussian mixture models.
KeywordsIndependent component analysis, change detection, large diesel engines
TypeConference paper [With referee]
Conference2003 IEEE Workshop on Neural Networks for Signal Processing
EditorsC. Molina, T. Adali, J. Larsen, M. Van Hulle, S. Douglas and Jean Rouat
Year2003    Month September    pp. 565-574
PublisherIEEE Press
AddressPiscataway, New Jersey
ISBN / ISSN0-7803-8178-5
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications