Work

Deep learning architectures for automated change detection and classification in mechanical design

Year: 2025

Type: article

Abstract: This paper addresses the challenge of supporting dynamic mechanical design processes in distributed, multi-user environments. Although mechanical CAD is a mature technology, assessing the functional and manufacturing impact of design changes remains a labour-intensive manual task. To address this issue, the authors introduce the concept of “3D CAD Change Detection and Classification” (3D-CDC) and present a novel dataset, “3D-GCD” (3D Geometric Change Dataset), consisting of pairs of 3D CAD components with a variety of technically plausible changes. The dataset represents 3D components in multiple 2D image formats (e.g., grayscale and comparative heatmaps) with renderings generated from single or multiple viewpoints. This dataset is used to train four deep learning architectures—Siamese Networks with convolutional encoders, transformer encoders, 3D Convolutional Networks (3D Conv), and Convolutional Recurrent Neural Networks (CRNN)—to classify the engineering significance of changes to a component’s design. The results indicate that while three architectures (Siamese Networks, transformer encoders, and CRNN) exhibit similar accuracy, the CRNN demonstrates greater consistency and efficiency, requiring fewer trainable parameters for 3D-CDC tasks.

Source: Advanced Engineering Informatics

DOI: 10.1016/j.aei.2025.103942

Authors: Shuang Li, Jonathan Corney, Andrew Sherlock, Justin Savage

Institutions: University of Edinburgh, University of Strathclyde, ShapeSpace (United Kingdom)

Language: English

Topic: Manufacturing Process and Optimization

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,560

Funders: University of Edinburgh, Engineering and Physical Sciences Research Council