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.

It has been widely reported that the reuse of previously created components, or features, in new engineering designs will improve the efficiency of a company’s product development process. Although the reuse of engineering components has established metrics and methodologies, the reuse of specific design features (e.g. stiffening ribs, hole patterns or lubrication grooves, etc.) has received less attention in the literature. Typically, researchers have reported approaches to partial design reuse that identify patterns predominately in terms of geometrically similar shapes (i.e. a set of features) whose elements are adjacent, cohesive, and decoupled from the overall form of a component. In contrast, this paper defines a common design structure (CDS) as collections of frequently occurring features (e.g. holes) with common parametric values (e.g. diameters) in a CAD database (irrespective of their locations or spatial connectivity between other features on a component). By exploiting the established data-mining technology of association rules and item-sets the authors show how CDSs can be efficiently computed for hundreds of 3D CAD models. A case study, with hole data extracted from a publicly available dataset of hydraulic valves, is presented to illustrate how item-sets associated with CDS can be computed and used to support predictive design by identifying potentially ‘substitutable features’ during an interactive design process. This is done using a combination of association rules and geometric compatibility checks to ensure the system’s suggestion are implementable. The use of the Kullback–Leibler divergence to assess the degree of similarity between components is identified as a crucial step in the process of identifying the “best” suggestions. The results illustrate how the prototype implementation successfully mines the CDSs and identifies substitutable hole features in a dataset of industrial valve designs.

The ability to interpret and reason about shapes is a peculiarly human capability that has proven difficult to reproduce algorithmically. So despite the fact that geometric modeling technology has made significant advances in the representation, display and modification of shapes, there have only been incremental advances in geometric reasoning. For example, although today's CAD systems can confidently identify isolated cylindrical holes, they struggle with more ambiguous tasks such as the identification of partial symmetries or similarities in arbitrary geometries. Even well defined problems such as 2D shape nesting or 3D packing generally resist elegant solution and rely instead on brute force explorations of a subset of the many possible solutions.