A view-based 3D CAD model reuse framework enabling product lifecycle reuse. (January 2019)

• Record Type: Journal Article
• Authors: Zhang, Chao; Zhou, Guanghui
• Is Part Of: Advances in engineering software. Volume 127(2019)
• Page Start: 82
• Page End: 89
• Publication Date: 2019-01
• Subjects: Product lifecycle reuse -- View-based approach -- Deep learning -- Residual network -- Model retrieval; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2018.09.001
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: Proposing a view-based 3D CAD model reuse framework for product lifecycle reuse. Views refer to 2D projections of a 3D CAD model from multiple fixed viewpoints. Defining the problem of 3D CAD model retrieval as a view recognition problem. Using a deep learning approach for facilitating the view-based 3D CAD model reuse. Abstract: 3D CAD models have great significances for product lifecycle reuse as each model aggregates abundant knowledge in a vivid 3D CAD model and enables engineers to reuse the existing mature designs from a high-level perspective. The effective reuse of the pre-existing 3D CAD models could greatly save time and cost in new product development. Consequently, this paper proposes a novel view-based 3D CAD model reuse framework, which supports the effective reuse of 3D CAD models throughout the new product lifecycle by a deep learning approach. In this framework, each 3D CAD model is first represented by a series of orthogonal two-dimensional views, which contain rich spatial information for differentiating 3D CAD models. Then, we define the problem of model retrieval as a view recognition problem, where a deep residual network (ResNet) is successfully trained to facilitate the view-based 3D CAD model retrieval. With the learned ResNet, engineers could take the understandable views of a model that represent their query intents as input and acquire the relevant 3D CAD models for product lifecycle reuse. Finally, the typical application scenario demonstrates the feasibility of the proposed framework, and the evaluation experiments show the superiorities of ResNet used in this framework.