loading page

Integrating Machine Learning and Mathematical Optimization for Job Shop Scheduling
  • +2
  • Anbang Liu ,
  • Peter Luh ,
  • Kailai Sun ,
  • Mikhail Bragin ,
  • Bing Yan
Anbang Liu
Tsinghua University, Tsinghua University, Tsinghua University

Corresponding Author:[email protected]

Author Profile
Peter Luh
Author Profile
Kailai Sun
Author Profile
Mikhail Bragin
Author Profile

Abstract

Job-shop scheduling is an important but difficult integer optimization problem for low-volume and high-variety manufacturing, with solutions required to be obtained quickly at the beginning of each shift. In view of the increasing demand of customized products, problem sizes are growing. Machine learning (ML) is a promising solution methodology. Direct learning solutions, however, is difficult because of the NP-hard nature of the problem. In this paper, ML and the decomposition and coordination approach of Surrogate Lagrangian Relaxation are synergistically integrated. ML is used to learn and predict “good enough” solutions of part subproblems, which are not NP-hard. Nevertheless, the task is still challenging in view of the quite different parts to be scheduled from shift to shift, the complicated tardiness-related objective function, and many part-level constraints. To address these issues, a generic pointer network is developed for all parts after part subproblems are innovatively reformulated to be at a much simplified and streamlined level. The pointer network is also novelly enhanced with a masking mechanism so that predictions satisfy all part-level constraints. Numerical results demonstrate that the enhanced pointer network can learn and predict subproblem solutions well, and that near-optimal solutions of large problems are efficiently obtained. The performance of the method is expected to further improve through continual learning.
2023Published in IEEE Transactions on Automation Science and Engineering on pages 1-22. 10.1109/TASE.2023.3303175