This paper investigates an integrated production scheduling and vehicle routing problem with soft time windows and fuzzy travel times, where orders are grouped into batches for production and delivered by a limited number of multi-trip heterogeneous vehicles. A bi-objective mixed integer nonlinear programming (MINLP) model is established, which takes total cost and total early and tardy weighted penalty time as optimization objectives. First, a fuzzy superposition operation is proposed to obtain the fuzzy weighted penalty time, and it is extended to a generalized fuzzy operation law in fuzzy sets and systems. Then, we propose a knowledge-driven co-evolutionary algorithm (KDCEA) to solve this problem. The algorithm fuses a dual-subpopulation co-evolution based on different update strategies and a knowledge-driven strategy based on dynamic knowledge sets and problem-specific knowledge. Finally, the correctness of the MINLP model is verified by the CPLEX solver using the ϵ-constraint method. A computational experiment is conducted based on different scale instances and a real-world case, and the results show the superiority of KDCEA in solving this problem.

Disassembly line balancing (DLB) is used for efficient task planning of large-scale end-of-life products, which is a key issue to realize resource recycling and reuse. Robot disassembly and U-shaped station layout can effectively improve disassembly efficiency. To accurately characterize the problem, a mixed-integer linear programming model of U-shaped robotic DLB is proposed. The aim is to minimize the cycle time to shorten the offline time of the product. Since there are many dynamic disturbances in the actual disassembly line, and traditional optimization methods are suitable for dealing with static problems, this article develops a deep reinforcement learning approach based on problem characteristics, namely deep Q network (DQN), to achieve a dynamic balancing of disassembly lines. Eight state features and ten heuristic action rules are designed in the proposed DQN to describe the disassembly environment completely. The effectiveness and superiority of the proposed DQN are verified by numerical experiments. In the case of a laptop disassembly line, not only the cycle time of the robots is reduced, but also intelligent decision-making and dynamic planning of disassembly tasks are realized.