Real-time diagnostic expert systems

Abstract

The aim of the paper is to point out the most important factors that should be taken into account during the designing of expert systems for technical diagnostics and advanced condition monitoring. The first such factor is the proper design of unified databases. It was assumed that discussed system consists of a network of coexisting and related nodes containing active statements looking for an equilibrium state. Such network represents a diagnostic model. Diagnostic models describe the relations between observed symptoms and their causes, i.e. the technical states of the object. Direct specification of such models is difficult due to the complex nature of state-symptom relations. An interesting idea is connected with example based inverse diagnostic models. Suggested solutions simplify the development and reduce maintenance costs for the whole system. A very important benefit for industrial application is the opportunity to arrange an incremental development of the final diagnostic expert system.