A History-Guided Regional Partitioning Evolutionary Optimization for Solving the Flexible Job Shop Problem with Limited Multi-load Automated Guided Vehicles

TL;DR

This paper introduces a history-guided regional partitioning evolutionary algorithm tailored for flexible job shop scheduling with limited multi-load AGVs, improving solution quality and efficiency.

Contribution

The study proposes a novel regional partitioning strategy and local search method specifically designed for multi-load AGV scheduling in flexible job shops, enhancing optimization performance.

Findings

HRPEO outperforms existing algorithms on benchmark tests.

The regional partitioning effectively prevents local optima.

The local search improves solution exploitation.

Abstract

In a flexible job shop environment, using Automated Guided Vehicles (AGVs) to transport jobs and process materials is an important way to promote the intelligence of the workshop. Compared with single-load AGVs, multi-load AGVs can improve AGV utilization, reduce path conflicts, etc. Therefore, this study proposes a history-guided regional partitioning algorithm (HRPEO) for the flexible job shop scheduling problem with limited multi-load AGVs (FJSPMA). First, the encoding and decoding rules are designed according to the characteristics of multi-load AGVs, and then the initialization rule based on the branch and bound method is used to generate the initial population. Second, to prevent the algorithm from falling into a local optimum, the algorithm adopts a regional partitioning strategy. This strategy divides the solution space into multiple regions and measures the potential of the regions. After that, cluster the regions into multiple clusters in each iteration, and selects individuals for evolutionary search based on the set of clusters. Third, a local search strategy is designed to improve the exploitation ability of the algorithm, which uses a greedy approach to optimize machines selection and transportation sequence according to the characteristics of FJSPMA. Finally, a large number of experiments are carried out on the benchmarks to test the performance of the algorithm. Compared with multiple advanced algorithms, the results show that the HRPEO has a better advantage in solving FJSPMA.