Mixed-model product disassembly sequence optimization based on cognitive digital twin

As a core step in remanufacturing, the disassembly process for multiple product structures in mixed-model products can improve disassembly efficiency and reduce costs. There are structure uncertainties in the mixed-model product disassembly process, which must be considered and used to optimize the disassembly strategy and improve the disassembly efficiency. This paper proposes a framework of a cognitive digital twin for mixed-model product disassembly sequence optimization. The cognitive model can reason, predict, and complete missing disassembly information due to uncertainty in the mixed-model product structure. Its cognitive capability is achieved by a knowledge graph and a TransD-based method. To provide a basis for semantic inference and relate different knowledge types, an ontology is designed based on the digital twin, and a knowledge graph is developed. Finally, a cognitive digital twin model is built. Upon that, the Soft Actor-Critic algorithm is utilized to optimize the mixed-model product sequence. The proposed model and algorithm are applied to transmissions disassembly case. The results show that the proposed method is effective in optimizing the disassembly sequences of three different products that make up the mixed-model products. It not only realizes the disassembly sequence optimization under the uncertain product structures, but also reduces the disassembly time of individual products and all products.