文档介绍：FAULT PROGNOSIS USING DYNAMIC WAVELET NEURAL
NETWORKS
G. Vachtsevanos and P. Wang; School of Electrical puter Engineering;
ia Institute of Technology; (404) 894-6252; ******@
ABSTRACT
Prognostic algorithms for condition based maintenance of critical machine
components are presenting major challenges to software designers and control
engineers. Predicting time-to-failure accurately and reliably is absolutely
essential if such maintenance practices are to find their way into the industrial
floor. Moreover, means are required to assess the performance and effectiveness
of these algorithms. This paper introduces a prognostic framework based upon
concepts from dynamic wavelet works and virtual sensors and
demonstrates its feasibility via a bearing failure example. Statistical methods to
assess the performance of prognostic routines are suggested that are intended to
assist the user paring candidate algorithms. The prognostic and assessment
methodology proposed here may bined with diagnostic and maintenance
scheduling methods and implemented on a puting platform to
serve the needs of industrial and other critical processes.
Keywords: Diagnostics, Prognostics, Condition-BasedMaintenance
1. INTRODUCTION
The manufacturing and industrial sectors of our economy are increasingly called to produce at
higher throughput and better quality while operating their processes at maximum yield. As
manufacturing facilities e plex and highly sophisticated, the quality of the
production phase has e more crucial. Machine breakdowns mon limiting uptime in
critical situations. Failure conditions are difficult and, in certain cases, almost impossible to
identify and localize in a timely manner. Scheduled maintenance practices tend to reduce
machine lifetime and increase down-time, resulting in loss of productivity. Recent advances in
instrumentation, munications puting are making available to manufacturing
comp