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.