Hybrid Metaheuristics and Linear Programming for Finite Capacity MRP in Multi-Stage Flexible Flow Shop with Permutation and Non-permutation Scheduling Options

Abstract

This paper presents a new algorithm for Finite Capacity MRP (FCMRP) in a multi-stage flexible flow shop. The proposed algorithm consists of four conventional metaheuristics namely, Genetic Algorithm (GA), Tabu Search (TS), Variable Neighborhood Search (VNS), and Simulated Annealing (SA) hybridized with Linear Programming (LP). The objective is to minimize the total cost, which is the sum of tardiness, earliness, and flow-time costs. There are two main steps of the proposed algorithm. Firstly, an efficient sequence of orders is generated by the proposed metaheuristics in a way that reduce the total cost. In this step, the required operations of the orders are scheduled based on two scheduling options called permutation and non-permutation. Secondly, the total cost is minimized by the LP model. The required parameters of the metaheuristics are tuned by using real data from automotive companies. The result shows that the proposed algorithm significantly outperforms the existing algorithm, and GA obtains the best total cost.