An improved adaptive hybrid algorithm for solving distributed flexible job shop scheduling problem

Abstract

With economic globalization, collaboration between enterprises has increased significantly. Complex products are now often produced in multiple workshops, either within a single company or across several. This shift has led to the rise of distributed manufacturing, a modern and rapidly expanding production method. This paper puts forward an Improved Adaptive Hybrid Algorithm (IAHA) to address the Distributed Flexible Job Shop Problem (DFJSP). A mathematical model of DFJSP is established based on the characteristics of distributed manufacturing. A hybrid decoding rule is proposed, using a dual-layer encoding approach to represent both factories and jobs. The initialization, crossover, and mutation operators are designed to efficiently tackle the job allocation challenge across distributed factories. In the local search phase, an adaptive variable neighborhood search method focuses on critical factories. Numerical experiments on a benchmark set of DFJSP instances with 2, 3, and 4 factories demonstrate the effectiveness of IAHA, breaking records for several instances and achieving optimal results for others. Comparisons with other algorithms show the IAHA's superior performance in solving the DFJSP.