Automotive Hood Design Based on Machine Learning and Structural Design Optimization

Abstract

<div class="section abstract"><div class="htmlview paragraph">Nowadays, the automobile industry is booming and the number of vehicles is proliferating while the road traffic environment is also deteriorating. Therefore, attention should be paid to the protection of vulnerable road users in traffic accidents, such as pedestrians. In order to reduce the pedestrians’ head injury in collision accidents, in this study, the vehicle engine hood which responds significantly to head injuries was taken as the design object, so as to put forward a new optimization design process. The parameters of the hood’s main components, manufacturing materials and structural scheme were considered to carry out simultaneous optimization from various aspects such as pedestrian protection and hood stiffness. Meanwhile, the approximate model approach was adopted to design the main parameters to improve the efficiency, and based on Bayesian inference, the approximate model bias correction method was proposed which solved the related problems of low accuracy of the approximate model. The correction method was validated by testing the model prediction accuracy, and nine out of ten samples validated passed. The reliability of the optimization design solution was improved. Finally, a variety of hood structure topology optimization schemes was obtained by topological optimization of the variable density method with a minimum weighted strain energy objective and a 50% volume fraction as a constraint. And three active hood pop-up heights were proposed by level selection of orthogonal experimental factors. By combining the main parameters and different structural design schemes, the optimal configuration of the hood system for pedestrian protection was designed, and compared to the initial vehicle model hood, the simulation results showed that the design scheme reduces mass by 20 percent and HIC values were reduced by up to 300 in each sample point, with an average reduction of 30%, the optimization objective is achieved, proving that the optimization framework proposed in this study is effective.</div></div>