Expert System for Detecting Genset Engine Faults Using the Case Based Reasoning Method

Abstract

PT. Sabindo Raya Gemilang is an exporter of shrimp and fish in Indonesia. This company requires an enormous flow of electricity to support activities so that it is not bothered by blackouts from the PLN. A generator set or genset is a substitute for a voltage source. The problem is that genset damage requires reliable mechanical handling. Junior mechanics sometimes misanalyze damage, requiring the supervision of a senior mechanic. This study applies an expert system with the Case-Based Reasoning (CBR) method to detect genset damage. It meets the case researched for having old cases to compare to new ones through the Retrieve, Reuse, Revise, and Retain so that problems are solved easily and quickly. The validity test showed that 5 of 6 test data were equal to the expert's diagnosis. Expert system accuracy 83%. There was a system diagnosis different from experts because the system’s diagnosis was based on the symptoms weight calculation and made a diagnosis with the highest similarity value. Meanwhile, experts observed the genset damage directly.