TOWARDS AUTOMATED CLASSIFICATION OF PRODUCT DATA BASED ON MACHINE LEARNING. (May 2020)

• Record Type: Journal Article
• Authors: Schleibaum, S.; Kehl, S.; Stiefel, P.; Müller, J. P.
• Is Part Of: Proceedings of the Design Society: DESIGN Conference. Volume 1(2020)
• Page Start: 375
• Page End: 382
• Publication Date: 2020-05
• Subjects: product lifecycle management (PLM) -- machine learning -- classification -- product structure -- product data management (PDM); Engineering design -- Congresses; Industrial design -- Congresses; 620.0042
• DOI: 10.1017/dsd.2020.139
• Languages: English
• ISSNs: 2633-7762

Abstract

Abstract: Modern machine learning methods have the potential to supply industrial product lifecycle management (PLM) with automated classification of product components. However, there is only little work in the literature on this topic. We propose to apply supervised machine learning on component meta-data. By analysing an industrial case study, we identify requirements and opportunities for automating classification, e.g. in part numbers and product structures. We validate our novel approach through a classification experiment comparing four machine learning methods on a realistic component dataset.