We propose a data-driven generative design framework that can facilitate the design exploration of engineering products in support of creative conceptual design and optimization. The framework consists of two modules: 1) a 3D mesh generative design module that can generate part-aware 3D objects using variational auto-encoder (VAE), and 2) an evaluation module that can assess the engineering performance of 3D objects in real-time based on locally linear embedding (LLE). The novelty of our framework lies in three aspects. First, it generates 3D shapes with the consideration of individual parts’ interconnection and constraints (i.e., part-aware) as opposed to generating a holistic 3D shape. Second, it transfers 3D shapes to watertight meshes with the same connectivity (i.e., the same number of vertices and the same way how vertices are connected) so that the surface details (e.g., smoothness, curvature) can be captured by mesh representation and learned by neural networks. Third, the LLE-based solver can quickly assess the engineering performance of the generated 3D shapes to realize real-time evaluation. In this study, we apply our framework to the aerodynamic car design.

In engineering design, on one hand, we want to generate a variety of design concepts to meet the diverse customer needs and preferences. On the other hand, products must meet desired engineering performance, such as the sit-stability of chairs, the aerodynamic performance of automobiles. However, human designers have cognitive limitations, thus cannot create diverse engineeringly-desired 3D shapes without computer-aided design (CAD) and computer-aided engineering (CAE) software. But current CAD software is primarily a drawing and modeling tool that cannot automatically create new designs, and the use of CAE tools is often time-consuming leading to a stretched design cycle that hinders the entire design process and increases the development cost. Even if we would be able to generate a large number of different design candidates, the evaluation of every single design using a CAE tool will be expensive both computationally and economically. Our framework aims to tackle these challenges by integrating generative design techniques and a fast solver for 3D shape aerodynamics.

 


Part-Aware Product Design Using Deep Generative Network

Division / Sponsors: 
Design Engineering Division and Computers & Information In Engineering Division


Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2020/volume/83907

IDETC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.