A soft-computing framework for fault diagnosis

The field of fault diagnosis (FD) is undergoing rapid change in the methodo logies it employs, and the vast array of materials/components/structures wh ere it is applied. The field has grown steadily because of(a) the importanc e attached to fail-safe mechanisms; (b) ability to detect impending failure so that preventive and corrective action can be taken and (c) the opportun ities opened up by automating the diagnosis process itself. FD as a tool ha s to draw knowledge and expertise from a variety of scientific fields and a pply multi-disciplined knowledge to empirical domains in order to achieve i ts objectives. Application and use of automated FD concepts to empirical do mains do not require merely crisp rules, but largely, a flexible and natura l framework where "experience" often determines the success or failure of d iagnosis. In this paper, we describe a flexible framework, which incorporat es the ideas and tools of soft computing in its methods and approach. (C) 2 000 Published by Elsevier Science Inc. All rights reserved.