Process-aware part retrieval for cyber manufacturing using unsupervised deep learning

Abstract

Cyber manufacturing service, which connects end users with manufacturers over the internet, is significantly hampered by the lack of an automated part retrieval method. The state-of-the-art is focused on automatic shape retrieval, which does not consider manufacturing process requirements, such as material properties. This paper proposes a manufacturing process-aware part retrieval method using deep unsupervised learning that considers both part shape and material properties. Part retrieval results show that the proposed method yields 93.0% process and function class label matching precision, which outperforms the shape-only part retrieval model and supervised learning models trained with process, function, or both labels.