Loading [MathJax]/extensions/MathZoom.js
A Learning-Based Multipopulation Evolutionary Optimization for Flexible Job Shop Scheduling Problem With Finite Transportation Resources | IEEE Journals & Magazine | IEEE Xplore

A Learning-Based Multipopulation Evolutionary Optimization for Flexible Job Shop Scheduling Problem With Finite Transportation Resources


Abstract:

In many practical manufacturing systems, transportation equipment such as automated guided vehicles (AGVs) is widely adopted to transfer jobs and realize the collaboratio...Show More

Abstract:

In many practical manufacturing systems, transportation equipment such as automated guided vehicles (AGVs) is widely adopted to transfer jobs and realize the collaboration of different machines, but is often ignored in current researches. In this article, we address the flexible job shop scheduling problem with finite transportation resources (FJSP-Ts). Considering the difficulties caused by the introduction of transportation and the NP-hard nature, the evolutionary algorithm (EA) is adopted as a solution approach. To this end, a learning-based multipopulation evolutionary optimization (LMEO) is proposed to deal with the FJSP-T. First, the multipopulation strategy is introduced and a cooperation-based initialization is designed by combining several heuristics to guarantee the quality and diversity of the initial population. Second, a reinforcement learning (RL)-based mating selection is proposed to realize the cooperation of different subpopulations by selecting appropriate individuals for evolutionary search. Then, a specific local search inspired by the problem properties is designed to enhance the exploitation capability of the LMEO. Moreover, a statistical learning-based replacement is designed to maintain the quality and diversity of the population. Extensive experiments are conducted to test the performances of the LMEO. The statistical comparison shows that the LMEO is superior to the state-of-the-art algorithms in solving the FJSP-T in terms of solution quality and robustness.
Published in: IEEE Transactions on Evolutionary Computation ( Volume: 27, Issue: 6, December 2023)
Page(s): 1590 - 1603
Date of Publication: 03 November 2022

ISSN Information:

Funding Agency:


I. Introduction

Flexible job shop scheduling problem (FJSP) is one of the intractable combinatorial optimization problems which widely exists in actual production scenarios [1]. In the FJSP system, each job requires several operations which need to be transferred to different machines for processing [2]. In order to complete transportation tasks efficiently, many enterprises select transportation resources, such as trucks, conveyors, cranes, and automated guided vehicles (AGVs) to automatically transport jobs [3]. In recent years, many researches have been carried out considering different constraints, such as setup time [4], [5], and preventive maintenance [6], to match the requirements in different scenarios. However, most researchers ignore the transportation time, or just include it in the processing time. This simplification of the problem makes it less realistic and practical. Actually, there exists a strong coupling relationship between processing tasks and transportation tasks [7]. On the one hand, the previous processing task decides the starting position and starting time of the transportation task. On the other hand, the transportation tasks affect the starting time of the next processing task [8]. Thus, considering the scheduling of transportation resources and production resources simultaneously can make the solutions more practical and effective, which is worthy of study.

References

References is not available for this document.