Solving complex maintenance planning optimizationproblems using stochastic simulation and multi-criteriafuzzy decision making

Abstract: The main goal of this project is to explore the use of stochastic simulation,genetic algorithms, fuzzy decision making and other tools for solvingcomplex maintenance planning optimization problems. We use two dierentmaintenance activities, corrective maintenance and preventive maintenance.Since the evaluation of specic candidate maintenance policies can take a longtime to execute and the problem of nding the optimal policy is both nonlinearand non-convex, we propose the use of genetic algorithms (GA) for theoptimization. The main task of the GA is to nd the optimal maintenancepolicy, which involves: (1) the probability of breakdown, (2) calculation ofthe cost of corrective maintenance, (3) calculation of the cost of preventivemaintenance and (4) calculation of ROI (Return On Investment).Another goal of this project is to create a decision making model for multicriteriasystems. To nd a near-optimal maintenance policy, we need to havean overview over the health status of the system components. To modelthe health of a component we should nd all the operational criteria thataect it. We also need to analyze alternative maintenance activities in orderto make the best maintenance decisions. In order to do that, the TOPSISmethod and fuzzy decision making has been used.To evaluate the proposed methodology, internal combustion engine coolingof a typical Scania truck was used as a case study.