Recursive Encoder Network for the Automatic Analysis of STEP Files

Miles, Victoria; Giani, Stefano; Vogt, Oliver

Abstract

Automated tools which can understand and interface with CAD (computer-aided design) models are of significant research interest due to the potential for improving efficiency in manufacturing processes. At present, most research into the use of artificial intelligence to interpret threedimensional data takes input in the form of multiple twodimensional images of the object or in the form of threedimensional grids of voxels. The transformation of the input data necessary for these approaches inevitably leads to some loss of information and limitations of resolution. Existing research into the direct analysis of model files in STEP (standard for the exchange of product data) format tends to follow a rules-based approach to analyse models of a certain type, resulting in algorithms without the benefits of flexibility and complex understanding which artificial intelligence can provide. In this paper, a novel recursive encoder network for the automatic analysis of STEP files is presented. The encoder network is a flexible model with the potential for adaptation to a wide range of tasks and fine-tuning for specific CAD model datasets. Performance is evaluated using a machining feature classification task, with results showing accuracy approaching 100% and training time comparable to that of existing multi-view and voxel-based solutions without the need for a GPU.

Citation

Miles, V., Giani, S., & Vogt, O. (2023). Recursive Encoder Network for the Automatic Analysis of STEP Files. Journal of Intelligent Manufacturing, 34(1), 181-196. https://doi.org/10.1007/s10845-022-01998-x

• Journal Article Type: Article
• Acceptance Date: Jul 15, 2022
• Online Publication Date: Aug 7, 2022
• Publication Date: 2023-01
• Deposit Date: May 11, 2022
• Publicly Available Date: Mar 8, 2023
• Journal: Journal of Intelligent Manufacturing
• Print ISSN: 0956-5515
• Electronic ISSN: 1572-8145
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 34
• Issue: 1
• Pages: 181-196
• DOI: https://doi.org/10.1007/s10845-022-01998-x
• Public URL: https://durham-repository.worktribe.com/output/1208736