The development of a generic failure analysis expert system based on case-eased reasoning

PJ Graham-Jones, BG Mellor

Research output: Contribution to journalConference proceedings published in a journalpeer-review

Abstract

Failure analysis is a complex task, requiring considerable knowledge and skill, some of which might |)e outside the experience of the engineer concerned. To help the engineer, a case-based reasoning to al (Failure Analysis Diagnostic Expert System) is beiig developed, using a systemic approach to failuire diagnostic problems, which not only interactively ic entines the failure modes and the critical factors in the design, processing, and end use which cause failures to originate but also suggests methods to improve the reliability of the products. This approach applies a Windows artificial intelligent case-based reasoning technique to generic failure diagnostic problems. Currently, the research is based around the elicitation of failure analysis knowledge and the structuring and planning of this knowledge so that t te expert system behaves in an intelligent and responsive manner. Many problems have arisen, such is understanding what information is required to ideniijy the failure mode and in designing a consistent aijtd economical set of questions that are integrated into an efficient questioning strategy. For the behavio ^r of the system to be intelligent and responsive, research into interface design and the understanding )f human cognitive models for failure analysis decision-making is proposed. The development of structure models will show which factors are critical in a given situation and aid failure analysis diagnosis.
Original languageEnglish
Number of pages0
JournalNACE - International Corrosion Conference Series
Volume0
Issue number0
Publication statusPublished - 1 Jan 1996

Fingerprint

Dive into the research topics of 'The development of a generic failure analysis expert system based on case-eased reasoning'. Together they form a unique fingerprint.

Cite this