DEVELOPMENT AND IMPLEMENTATION OF A POWER-SYSTEM FAULT-DIAGNOSIS EXPERT-SYSTEM

This paper describes a fault diagnosis expert system installed at the Tohoku Electric Power Company. The main features of this system are ca reful selection of the inferencing input data, rapid inferencing, inte gration of tile expert system with other systems in a practical struct ure, and the adoption of a domain shell. This system aims for improved practicability by using time-tagged data from circuit breakers, prote ctive relays, and automatic reclosing relays in addition to the input data used in earlier systems. Furthermore, this system also uses data from fault detection systems that locate fault points within electric stations. This system uses an AI-specific back-end processor to perfor m inferencing rapidly. Additionally, this fault diagnosis expert syste m is interfaced acid integrated with a restorative operations expert s ystem, an intelligent alarm processing system, and a protective relay setting and management system. Authors developed and adopted a power s ystem fault diagnosis domain shell to ease system development, and use d the protective relay operation simulation function of a protective r elay setting and management system for system verification.