Aggregate production planning (APP) is one of the most important issues carried out in manufacturing environments which seeks efficient planning, scheduling and coordination of all production activities that optimizes the company's objectives. In this paper, we develop a mixed integer linear programming (MILP) model for an integrated aggregate production planning system with closed loop supply chain and preventive maintenance. The goal is to minimize setup costs, production costs, labor costs and preventive maintenance (PM) costs and instabilities in the work force and inventory levels. Due to NP-hard class of APP, we implement genetic algorithm (GA), harmony search (HS) and vibration damping optimization (VDO) for solving this model. Additionally, the Taguchi method is conducted to calibrate the parameter of the meta-heuristics and select the optimal levels of the algorithm’s performance influential factors. Finally, computational results on a set of randomly generated instances show the efficiency of the VDO algorithm against the other meta-heuristics, and this algorithm obtain good quality solutions for aggregate production planning with preventive maintenance and could be efficient for large scale problems.