Treffer: A multi-objective bi-population evolutionary algorithm for human-robot collaborative disassembly sequence planning with interval type-2 fuzzy modelling.

Efficient disassembly of end-of-life products is important to the viability of recycling and remanufacturing. With the advancement of automation technology and driven by Industry 5.0, which emphasises human-centric principles and the collaborative synergy between humans and robots, human-robot collaborative disassembly has become a promising alternative to purely manual disassembly. However, most existing research into human-robot collaborative disassembly sequence planning focuses on complete disassembly, neglecting the uncertainties in the disassembly process or relying on methods that face constraints within modern complex industrial systems. In contrast, this study considers human-robot collaborative selective disassembly sequence planning and pioneers the application of type-2 fuzzy sets to manage these uncertainties. The proposed problem includes three conflicting objectives of minimising time and energy consumption while maximising profit. To solve the problem efficiently, another contribution of this paper is the development of an efficient multi-objective bi-population evolutionary algorithm. This algorithm is based on the non-dominated sorting genetic algorithm and enhanced by a monarchical strategy, a variable neighbourhood search approach, and a simulated annealing criterion. To demonstrate the applicability of the proposed algorithm, we apply it to two distinct and comprehensive case studies inspired by real-world disassembly operations. Through extensive numerical experiments, we show that our approach is highly effective. The results not only highlight the algorithm's computational efficacy but also generate actionable managerial insights for optimising disassembly processes in realistic, uncertain environments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Engineering Design is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)