Digital Twin-Driven Robotic Disassembly Sequence Dynamic Planning Under Uncertain Missing Condition

Disassembly is an inevitable process of recycling end-of-life products and robotic disassembly sequence planning could improve disassembly efficiency. However, the missing condition of component is uncertain and it could not be pre-known before execution of disassembly process. The optimal solution should be dynamically generated according to the recognized condition during disassembly process. In this article, digital twin is utilized to solve robotic disassembly sequence dynamic planning under uncertain missing condition. First, the framework of the proposed method is studied and digital twin of robotic disassembly process is established. Afterwards, deep Q-learning network is utilized to solve the proposed problem. Finally, case studies are carried out to verify the effectiveness of proposed method. The results show the converged deep Q-learning network model could dynamically find the optimal solutions after the missing condition of component is recognized during disassembly process using less running time, compared with the other meta-heuristics algorithms.