An integrated convolutional neural network-based surrogate model for crashworthiness performance prediction of hot-stamped vehicle panel components

Dyson School of Design Engineering, Imperial College London, Exhibition Road, London SW7 2AZ, UK

^* Corresponding author: n.li09@imperial.ac.uk

Abstract

During the structural design of vehicle components, Finite Element (FE) modelling has been extensively used for simulations of physical experiments. A typical design optimisation task requires iterative simulations to identify the optimum design, where FE simulations can be too time-consuming. Surrogate models have been developed to approximate complex simulations, which can reduce computational time and improve the efficiency of the design cycle. This paper presents a novel application of convolutional neural network (CNN) on rapid predictions of crashworthiness performance of vehicle panel components considering manufacturability. The dataset for training the model was generated based on the FE results of hot-stamped ultra-high strength steel (UHSS) B-pillar components. The formed components were analysed with a simplified lateral crash test to evaluate the deformation under impact. The trained model can instantly predict the deformation of the designed component with high accuracy compared to the FE results. Due to its high computational efficiency and precision, the surrogate model enables faster and more extensive design evaluations.