A Data-Driven Interactive System for Aerodynamic and User-centred Generative Vehicle Design

Abstract

In this work, we propose a data-driven design pipeline for quick design exploration of performance and appearance guided alternatives for vehicle design. At the heart of our system is a machine learning-based generative design method to provide users with a set of diverse optimal design alternatives and an interactive design technique to induce users' preference into the design exploration. The generative design method is structure on two search process, qualitative and quantitative. To avoid the curse of dimensionality, the qualitative search process first builds up a lower-dimensional representation of a given design space, which is then explored using the unsupervised k-means clustering to synthesise a representative set of user-preferred designs. The quantitative search process explores the design space to find an optimal design in terms of performance criterion such as drag coefficient. To reduce the computational complexity, instead of evaluating drag via Computational Fluid Dynamics simulations, a surrogate model is developed to predict the drag coefficients. The designs generated after the generative design step are presented to the user at the interactive step, where potential regions of the design space are identified around the user-selected designs. Afterwards, a new design space is generated by removing the nonpreferred regions, which helps to focus the computational efforts on exploring the user preferred regions of the design space for a design tailored to the user's requirements. We demonstrated the performance of the proposed approach on a two-dimensional side silhouette of a sport-utility vehicle.

Navigating from data-driven design to designing with ML: a case study of truck HMI system design

“…Yadav and Goel proposed a mathematical framework to relate customer satisfaction level to component-level product requirements, such as interior quietness (Yadav and Goel, 2008). Another example is an ML-based vehicle silhouette design system that auto-generated the vehicle design based on user selection (Usama et al, 2021). However, most research related to AI/ML in automobiles has focused on integrating AI/ML in vehicles: autonomous driving (Yurtsever et al, 2020), driver assistance (Joshi et al, 2019), and predictive maintenance (Theissler et al, 2021).…”

Generative vs. Non-Generative Models in Engineering Shape Optimization

“…Optimizing such surfaces often plays a crucial role in enhancing their functional performance; see, for example, Refs. [1][2][3][4]. Effective design parameterization, facilitating high levels of intuitiveness, flexibility, and representational accuracy, is a crucial prerequisite for such shape optimization approaches.…”