Selective disassembly sequence planning (SDSP) is regarded as an efficient strategy to determine optimal disassembly sequences for extracting target parts (TP) from complex end-of-life (EOL) products. Previous research assumes that all EOL products have the same structure and the optimal selective disassembly sequences are given before the EOL products are removed. However, the products have different operation states during their use stage, which results in high structure uncertainty of EOL products. The structure uncertainty of EOL products often makes the predetermined selective disassembly sequences impractical for minimizing disassembly time and maximizing disassembly profit. This letter undertakes this challenge by integrated reinforcement learning (RL) to determine the optimal disassembly sequences adaptive to the structure uncertainty of the EOL products. Firstly, a multi-level selective disassembly hybrid graph model (MSDHGM) is developed to illustrate the contact, precedence, and level relationships among parts. Then, the SDSP is formulated as a finite Markov Decision Process and a deep Q-network based selective disassembly sequence planning (DQN-SDSP) is proposed. Finally, extensive comparative experiments are conducted to verify the proposed method compared with NSGA-II and ABC algorithms.

Re-manufacturing is recycling by manufacturing as-good-as-new products from used products, often involving disassembly, cleaning, testing, part replacement/repair, and re-assembly operations. Production planning and inventory control is one of the most important research issues for re-manufacturing system, which are faced with a greater degree of uncertainty and complexity. This leads to a critical need for planning and control systems designed to deal with the added uncertainty and complexity. We formulate a stochastic dynamic programming based model to study the production planning, i.e. dynamic lot sizing problem, of re-manufacturing systems. In the model the demand and return amounts are stochastic over the finite planning horizon. The objective is to determine the quantities that have to be re-manufactured at each period in order to minimise the total cost, including re-manufacturing cost, holding cost for returns and re-manufactured products and backlog cost. The optimal production plan of the re-manufacturing system over a finite planning horizon can be obtained with the policy iteration method. In the end, a numerical example is performed to illustrate how the model is applied and to prove its feasibility.