SplineLearner: Generative learning system of design constraints for models represented using B-spline surfaces. (January 2022)

• Record Type: Journal Article
• Authors: Tasmektepligil, A. Alper; Gunpinar, Erkan
• Is Part Of: Advanced engineering informatics. Volume 51(2022)
• Publication Date: 2022-01
• Subjects: B-spline surface -- Design constraints -- Generative design -- Computer-aided design -- Constraint-based modeling -- Machine learning; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2021.101478
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: Product design involves a computer-aided design (CAD) model with its design (dimensional) parameters. A generative design (GD) system can then be utilized to generate new designs by modifying these parameters. There is a need for a GD system to determine the visual validity of a design that is obtained after parametric modification. In this context, this paper introduces an approach to learn visual (i.e., design) constraints of a CAD model (represented using B-spline surfaces) by means of user feedbacks. A deformation technique (utilizing modification and limit curves) for B-spline surfaces is first introduced, which involves a few design (deformation) parameters. Via a generative learning process, the proposed system, SplineLearner, generates random designs, which are shown to user(s) for visual validity classifications. In a machine learning step, a mathematical model is computed that can perform prediction for a design to be valid or not. The mathematical model is also integrated into SplineLearner (after some user interactions) to prevent imbalances between the numbers of valid and invalid designs. As a proof of concept, B-spline surface models of a car body parts (hood, roof, side and trunk) are utilized, and two user studies are conducted to demonstrate the efficacy of the proposed method. Highlights: A generative learning method to extract design constraints of a B-spline surface model is proposed. A novel deformation technique for B-spline surfaces is suggested. Design constraints are learned by means of user(s) in an interactive process. Deformation parameters are employed to generate surfaces, which are then labeled by user(s). User studies are conducted to demonstrate the efficacy of the proposed technique.