Adaptive planning of human-robot collaborative disassembly for end-of-life lithium-ion batteries based on digital twin

Increasing numbers of lithium-ion batteries for new energy vehicles that have been retired pose a threat to the ecological environment, making their disassembly and recycling methods a research priority. Due to the variation in models and service procedures, numerous lithium-ion battery brands, models, and retirement states exist. This uncertainty contributes to the complexity of the disassembly procedure, which calls for a great deal of adaptability. Human-Robot Collaboration Disassembly (HRCD) mode maximizes the advantages of both humans and robots, progressively replacing single-person disassembly and single-machine disassembly to become the standard method for disassembling end-of-life lithium-ion batteries (LIBs). However, the HRCD process has more dimensions and uncertainties. In light of the obstacles above, this paper developed an HRCD environment with virtual and real interaction functions, which recommended real-time cooperation strategies in the dynamic production process and significantly enhanced the flexibility of disassembly operations. Based on the genetic algorithm (GA), the Disassembly Sequence Planning (DSP) is developed for waste LIBs in the source domain and imported into the knowledge base. Then, the rapid adaptive generation of HRCD task strategy for LIBs is generated, utilizing the transfer learning approach in the target domain. Two types of end-of-life automobile LIBs are analyzed as case study products. The results demonstrated that the proposed method could plan an effective action sequence, effectively reduce the design time of the target domain disassembly strategy, and enhance the flexibility of HRCD.