Design of A Knowledge Based Trouble Call System with Colored Petri Net Models

A knowledge based trouble call system with colored Petri net (CPN) inference models is designed to identify the most probable faulted device for trouble call analysis (TCA) of distribution systems. The CPN model for inference engine considers two major parts: the traditional escalation method and the load comparison method. To identify the faulted device more accurately according to the outage reports by service customers, the searching procedures based on the improved escalation method are included in the best first search of the CPN. The most possible outage locations with corresponding blown out protective device are determined by applying parallel-like reasoning in the CPN to solve multiple fault events simultaneously. One of the distribution systems in Taiwan Power Company (Taipower) with 36000 customers is selected for computer simulation to demonstrate the effectiveness of the proposed methodology to enhance the function of distribution outage management