Using Genetic Algorithm to bridge Decision Making Grid data gaps in Small and Medium Industries

Abstract

Maintenance management is certainly the important factor to support the successfulness of Small and Medium Industries (SMIs). The SMIs will gain larger profits with the correctness of maintenance system which can minimize the expenses incurred. The application with Decision Making Grid (DMG) for appropriate maintenance strategy has been achieved with favorable outcome. However, the problems, i.e. incompleteness, unavailability and inconsistency of data are the common practice gaps in SMIs. The presences of data gaps cause adverse effects on the DMG process which is certainly not able to provide satisfactory results of maintenance strategies. To overcome the problems, the current research applies the most optimal heuristic adaptive methods of Genetic Algorithm (GA) to generate optimal variable values of machine breakdowns from a DMG process on observed SMIs to be processed into other related problematic SMIs. The combination method has produced remarkable validation results against decision-making of maintenance strategies for all machines with the accuracy of 90,81%. The results deliver the trust toward related SMIs with the data problems or even new concerned SMIs with the absences of data to utilize this DMG-GA method for maintenance decision making which can help maintenance personnel by giving the correct selection of the maintenance strategy.