Home // ADVCOMP 2024, The Eighteenth International Conference on Advanced Engineering Computing and Applications in Sciences // View article
Authors:
Dominique Briechle
Andreas Rausch
Keywords: Collaboration, Disassembly, AI-based planning, PDDL, Circular Economy.
Abstract:
Product disassembly has become more and more relevant to leverage repair, refurbish and remanufature (3Rs) operations while simultaneously enabling access to spare parts from products whichs lifecycle cannot be extended. Such processes can help tackling global ecological production impact as well as overall resource shortage. Nowadays, those operations are still expensive, time-consuming and error-prone because of the high variety in overall product composition, the cost of manual labour and the limitations of disassembly systems in terms of adaption. Artificial intelligence (AI)-based planning could hereby act as a suitable solution to enable automated systems dealing with decomposition tasks. The Planning Domain Definition Language (PDDL) offers a domainindependent canvas, which is suited to deal with a broad level of compositional variety. However, the lack of a suitable systematic methods to describe hierarchical compositions in PDDL limits its application for adaptive disassembly task planning. This work, therefore, aims to overcome these limitations by proposing a methodology to describe compositions and disassembly systems. We introduce, in the scope of the paper, a formal domain metamodel, capable of depicting such hierarchical structures and therefore enabling a precise disassembly of product compositions. Finally, we conduct two disassembly planning tasks and show the applicability of our method to handle hierarchical compositions and product variety.
Pages: 17 to 25
Copyright: Copyright (c) IARIA, 2024
Publication date: September 29, 2024
Published in: conference
ISSN: 2308-4499
ISBN: 978-1-68558-184-8
Location: Venice, Italy
Dates: from September 29, 2024 to October 3, 2024