Expert system for analysis of power system harmonics

Abstract

The authors report on one effort to employ artificial intelligence (AI) in the form of a harmonics analysis expert system. The resulting PC-based software program has captured the knowledge of expert power system engineers in a rule base which can use information about the topology, power signature, operating practices, symptoms, equipment type and ratings, and chronology of system development to diagnose harmonics-caused problems. The goal is to accomplish the analysis with a less experienced engineer, thereby multiplying the available nationwide pool of expertise. Additionally, repeated use of the system imparts knowledge to the user. The process of applying this AI approach involves training the user, measurements (optional), diagnosis, and reducing the power system harmonics to achieve acceptable power supply quality. The emphasis is on the diagnostic module. An example of its use is presented.<>