XAI-driven digital twin for cobot dynamic error compensation
Puthanveettil Madathil, Abhilash and Walker, Charlie and Luo, Xichun and Liu, Qi and Madarkar, Rajeshkumar and Qin, Yi (2024) XAI-driven digital twin for cobot dynamic error compensation. Procedia CIRP, 126. pp. 176-181. ISSN 2212-8271 (https://doi.org/10.1016/j.procir.2024.08.320)
Preview |
Text.
Filename: Madathil-etal-PCIRP-2024-XAI-driven-digital-twin-for-cobot-dynamic-error-compensation.pdf
Final Published Version License: Download (842kB)| Preview |
Abstract
Process and product fingerprints (FP) have been approved as effective parameters to reveal the principal contributing factors towards functionality in smart manufacturing processes. Though AI-driven methods outperform other approaches for fingerprint extraction, the lack of explainability in its black-box style predictions leads to misconceptions and trust issues among stakeholders. In this study, a novel explainable-AI (XAI) approach is proposed to identify mathematical fingerprint expressions by formulating them as graphs using the QLattice algorithm, inspired by path integral formulation. Here, the Qlattice model identifies explainable and human-comprehensible FP expressions for cobot dynamic error based on accelerometer signal features. The discovered symbolic model is subsequently applied to a digital twin which successfully tracked and compensated for dynamic errors autonomously in real time.
ORCID iDs
Puthanveettil Madathil, Abhilash ORCID: https://orcid.org/0000-0001-5655-6196, Walker, Charlie, Luo, Xichun ORCID: https://orcid.org/0000-0002-5024-7058, Liu, Qi ORCID: https://orcid.org/0000-0002-1960-7318, Madarkar, Rajeshkumar and Qin, Yi ORCID: https://orcid.org/0000-0001-7103-4855;-
-
Item type: Article ID code: 90423 Dates: DateEvent9 October 2024Published6 May 2023AcceptedSubjects: Technology > Engineering (General). Civil engineering (General) > Engineering design
Technology > Mechanical engineering and machineryDepartment: Faculty of Engineering > Design, Manufacture and Engineering Management
Technology and Innovation Centre > Advanced Engineering and ManufacturingDepositing user: Pure Administrator Date deposited: 30 Aug 2024 14:31 Last modified: 13 Oct 2024 00:48 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/90423