Optimization of Product Remanufacturing Process across Multifactories with Reinforcement Learning

With the rapid development of information technology and logistics technology, traditional centralized factories are transforming into distributed production systems, forming a multi-factory manufacturing model. This study uses Petri nets to model the disassembly processes of end-of-life (EOL) products, integrates the disassembly line balancing issue with the resource sharing over multiple factories, propose a hybrid layout for multi-factory remanufacturing, and establishes a linear programming mathematical model that optimizes the disassembly profit. Deep deterministic policy gradient(DDPG), a deep reinforcement learning algorithm, is employed to solve the model. Experimental results demonstrate the feasibility of the proposed approach.