MAXIMIZING THE EFFECTIVENESS OF A PREVENTIVE MAINTENANCE SYSTEM - AN ADAPTIVE MODELING APPROACH

The dynamic nature of an operating environment, such as machine utiliz ation and breakdown frequency results in changing preventive maintenan ce (PM) needs for manufacturing equipment. In this paper, we present a n approach to generate an adaptive PM schedule which maximizes the net savings from PM subject to workforce constraints. The approach consis ts of two components: (a) task prioritization based on a multi-legit r egression model for each type of PM task, and (b) task rescheduling ba sed on a binary integer programming (BIP) model with constraints on si ngle-skilled and multi-skilled workforce availability. The task priori tization component develops a multi-legit regression for machine failu re probability associated with each type of PM task at the beginning o f the year, using historical data on machine utilization, PM, and mach ine breakdowns. At the start of each PM time-bucket (e.g., a month), w e use the updated machine failure probability for each candidate PM ta sk to compute its current contribution to net PM savings, which indica tes its current priority. The task rescheduling BIP model incorporates the priorities in selecting tasks for the current bucket to maximize PM effectiveness subject to workforce availability, yielding an adapti ve and effective PM schedule for each time-bucket of the master PM sch edule. We examine the effect of using multi-skilled workforce on the o verall PM effectiveness, and also provide an illustration from a newsp aper publishing environment to explain the use of the approach. We hav e developed four heuristic algorithms to yield good solutions to large scale versions of this scheduling problem. The heuristics perform ext remely well, and the best heuristic solution is within 1.4% of optimal ity on an average.