Knowledge graph-driven process reasoning of human-robot collaborative disassembly strategy for end-of-life products

• A novel disassembly process reasoning method combines KG-driven GAT with information decomposition modular. • The SURD mechanism enables the network structure for semantic information and relation analysis. • KG-driven process reasoning provides the decision support for disassembly task allocations and tool selections. • A practical demonstration is accomplished through the overall disassembly strategy of the battery pack. Due to the complex structures and heterogeneous information inherent in End-of-Life (EOL) products, determining optimal disassembly solutions based on Human-Robot Collaboration (HRC) remains a challenging task. As structural and functional uncertainties in EOL products increase, traditional disassembly approaches struggle to meet the practical disassembly demands. Although various algorithms have been proposed for optimizing disassembly processes, significant challenges persist. These include the limited adaptability of existing models and difficulties in representing dynamic structured information effectively. To address these challenges, this study proposes a novel method combining knowledge graph-driven neural networks with an information decomposition module. This mechanism enables the network to discover structural semantic information and relational connections, facilitating the prediction of optimal disassembly strategies and enhancing the process reasoning capability of EOL product data and knowledge. Similarly, the proposed method provides reliable decision support for HRC disassembly task allocations and tool selections, enabling efficient and safe disassembly operations within complex disassembly processes. Finally, we demonstrate the method’s efficacy by using an example of an EOL battery pack, reasoning optimal disassembly strategies and potential process relations in the complex HRC disassembly scenario.