A Variable Group Parallel Flexible Job Shop Scheduling in a SMEs Manufacturing Platform

Abstract

Manufacturing is a broad field with different types of production processes. Therefore, specific processes can accommodate multiple parallel machines operating simultaneously in some production environments. This assumption is particularly crucial in factory scheduling for industries such as textile, aircraft, and semiconductor manufacturing. The assumption proposed in this paper is differ from FJSP in that they are closer to the real world by allowing different machines to perform the same multiple processes. In this paper, a new approach for solving the flexible job shop scheduling problem has been proposed, which is referred to as the flexible job shop scheduling problem in a parallel machine environment with a variable group. We proposed a hybrid genetic algorithm-based variable neighborhood search algorithm (GA-VNS) to solve this problem, where the multiple parallel machines can operate the same operations simultaneously and are grouped as a variable group. The GA-VNS algorithm combines the global searching ability of GA with the local searching ability of VNS to fully reflect the condition of the parallel machines with variable groups. The objective functions of the algorithm are to minimize the production makespan and to improve facility usage. Multiple simulation experiments are conducted using forty-seven test instances to assess the feasibility and effectiveness of the new approach. This study is expected to reduce processing time and production costs for Small and Medium Enterprises (SMEs) with low cost and high efficiency compared to existing systems, such as the manufacturing execution system, enterprise resource planning, and job shop scheduling system.

Keywords

• Genetic algorithms
• variable neighborhood search algorithm
• flexible job shop scheduling problem
• global and local searching algorithm
• parallel machines
• small and medium sized enterprises