As the intelligent manufacturing paradigm evolves, it is urgent to design a near real-time decision-making framework for handling the uncertainty and complexity of production line control. The dynamic flexible job shop scheduling problem (DFJSP) is frequently encountered in the manufacturing industry. However, it is still challenging to obtain high-quality schedules for DFJSP with dynamic job arrivals in real-time, especially facing thousands of operations from a large-scale scene with complex contexts in an assembly plant. This article aims to propose a novel end-to-end hierarchical reinforcement learning framework for solving the large-scale DFJSP in near real-time. In the DFJSP, the processing information of newly arrived jobs is unknown in advance. Besides, two optimization tasks, including job operation selection and job-to-machine assignment, have to be handled, which means multiple actions must be controlled simultaneously. In our framework, a higher-level layer is designed to automatically divide the DFJSP into subproblems, i.e., static FJSPs with different scales. And two lower-level layers are constructed to solve the subproblems. In particular, one layer based on a graph neural network is in charge of sequencing job operations, and another layer based on a multilayer perceptron is used to assign a machine to process the job operations. Numerical experiments, including offline training and online testing, are conducted on several instances with different scales. The results verify the superior performance of the proposed framework compared with existing dynamic scheduling methods, such as well-known dispatching rules and metaheuristics.

Modern rail-road container terminals serve as important consolidation nodes in intermodal transportation networks where containers are transferred between freight trains and trucks. Among the most important decision problems in these yards is the crane scheduling problem, which decides on the sequences of container moves executed by each of the parallel gantry cranes. This paper treats a rich crane scheduling problem, which considers plenty relevant constraints and is directly applicable in Chinese intermodal terminals. For solving this problem, we propose a fix-and-optimise procedure, which is easy to implement and shown to successfully solve even large-sized instances with 100 container moves in reasonable time.

The single-row facility layout problem (SRFLP) decides upon the arrangement of facilities in a straight row so as to minimise the material handling cost. Generally, this problem allows the placement of the facilities in any location in any order without any restriction, but some practical SRFLP cases are required to meet various types of constraints imposed on the placement of its facilities in the engineering of the placement of factory machinery and equipment. According to this new perspective, we studied the constrained SRFLP (cSRFLP) in this paper. In this problem, a few facilities need to be placed in certain positions or specified orders with or without the requirement to be located next to each other. To address this novel layout problem, related constraints are defined and classified, and novel mixed-integer programming models for the problem are formulated. Subsequently, the CPLEX software is employed to solve this problem. Then a constrained improved fireworks algorithm is presented, which is discretised to solve the considered cSRFLP. Our computational experiments demonstrate that the proposed algorithm performs better than the existing algorithms in solving the problem.