论文信息 - MULTI-INDEX FUSION-BASED FAULT DIAGNOSIS THEORIES AND METHODS

MULTI-INDEX FUSION-BASED FAULT DIAGNOSIS THEORIES AND METHODS

Abstract In this paper, using the information theory and the statistics analysis method, we have established the theory and method of faults diagnosis based on the multi-index fusion, including the information theory of multi-index diagnosis, diagnosis ability testing, indexes selecting, and Bayesian diagnosis modelling. And then, we applied the theories and methods to analyse the piston–liner wear condition of a diesel engine. In that, satisfactory results are achieved.

[1] H. Saunders,et al. Mechanical Signature Analysis—Theory and Applications , 1988 .

[2] Robert P. Goldman,et al. A Bayesian Model of Plan Recognition , 1993, Artif. Intell..

[3] Ren C. Luo,et al. Multisensor integration and fusion for intelligent machines and systems , 1995 .

[4] Henry E. Kyburg,et al. Bayesian and Non-Bayesian Evidential Updating , 1987, Artificial Intelligence.

[5] M. West,et al. Bayesian forecasting and dynamic models , 1989 .

[6] Thomas M. Cover,et al. Elements of Information Theory , 2005 .

[7] John Swan,et al. Multisensor fusion methodologies compared , 1991, Defense, Security, and Sensing.

[8] Solomon Kullback,et al. Information Theory and Statistics , 1960 .