Circularity-based hybrid learning framework for disassembly sequence planning in early-stage design
In the early-stage design phase, disassembly sequence planning must often rely on an incomplete engineering bill of materials rather than on detailed CAD geometry. This paper proposes a circularity-based hybrid learning framework that combines a genetic algorithm, Q-learning, and a graph neural network to generate and refine feasible disassembly sequences from the physical-contact relationships between components. The method evaluates candidate sequences against four criteria: disassembly time, component quality, adjacency preservation, and structural complexity. Across two case studies, a smart switch and a modular battery pack, the framework achieved competitive performance and improved interpretability of circularity trade-offs under incomplete product information.
Authors
- Bertrand Marconnet (ORCID: https://orcid.org/0000-0002-4009-9872)
- Benoît Eynard (ORCID: https://orcid.org/0000-0002-5393-4363)
- Frédéric Demoly (ORCID: https://orcid.org/0000-0002-5825-6573)
- Julien Le Duigou (ORCID: https://orcid.org/0000-0001-8723-2506)
- Anicet Barrios (ORCID: https://orcid.org/0009-0000-0318-179X)
Institutions
- Université de Technologie de Compiègne (FR)
- Shanghai University (CN)
- Centre National de la Recherche Scientifique (FR)
- Institut Universitaire de France (FR)
- Université de Lyon (FR)
- Université de technologie de belfort-montbéliard (FR)
- ECAM School of Engineering (FR)
- Laboratoire Interdisciplinaire Carnot de Bourgogne (FR)
- Université Bourgogne Europe (FR)
- Université Marie et Louis Pasteur (FR)
Publication Details
- Journal
- CIRP journal of manufacturing science and technology
- Published
- 2026-10-16
- DOI
- https://doi.org/10.1016/j.cirpj.2026.10.003
- Primary Topic
- Manufacturing Process and Optimization
- Type
- article
- Field-Weighted Citation Impact
- 0.00