Journal
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
Volume 22, Issue 2, Pages 436-450Publisher
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.ymssp.2007.08.004
Keywords
fault diagnosis (FD); refrigeration system; partial problem descriptions (PPD); similarity transformation matrix (STM); support vector machine (SVM)
Categories
Ask authors/readers for more resources
Fault diagnosis (FD) plays a very important role in the operation and maintenance of mechanical system and equipment. Existing FD methods are not capable of effectively dealing with incompletely described samples. In this paper, a strategy for FD using the incompletely described samples is presented. It is actualized in two steps, namely the determination of the values of unknown features which is the key step of the presented FD strategy, and the utilization of the regenerated completely described samples to diagnose the system based on support vector machine (SVM) classifiers. And the first step is mainly implemented by the following three sub-steps: (1) with the help of domain knowledge, the similarity transformation matrix of partial problem description (PPD)-problems with incomplete feature description-is generated based on the historical database; (2) the unknown features of the samples are transformed to related known features, through which generates a new retrieval feature vector; (3) the values of unknown features are assigned by the optimal cases which can be retrieved by measuring and comparing similarities between the retrieval feature vector and the completely described samples in the historical database. Finally, the presented FD strategy was applied to a real refrigeration system, and achieved satisfying results. (c) 2007 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available