An integrated database and expert system for failure mechanism identification: Part I—automated knowledge acquisition

An integrated database and expert system has been developed for identifying the failure mechanism of mechanical components. The system comprises six major modules: database and management system, case maintenance; knowledge acquisition and editing; expert system; explanation and test-recommendation facilities; and user interface. Part I of a two-part paper details the knowledge acquisition and editing module, as presented here. Part II describes the remaining modules and also gives test results 9]. The method used for automated knowledge acquisition is an inductive learning algorithm, which was modified from PRISM 2] to handle noisy and missing data. Using the algorithm, a total of 48 rules were induced from 477 training examples gathered for the identification of 15 different failure mechanisms such as brittle fracture, fatigue, and stress corrosion cracking. Fifty-nine attributes were used to distinguish one failure mechanism from the others. They include pitted, beach marks, microvoids, etc. The knowledge editing function is provided to allow the verification of induced rules by the human expert.