Optimization of crashworthiness of wide crash box under axial quasi-static and dynamic impact for electric vehicle using machine learning

Abstract

This study presents a comprehensive multi-objective optimization of a multi-cell crash box under quasi-static and dynamic axial loading conditions. Finite element analysis is conducted to investigate the crashworthiness indicators: total energy absorption (TEA), specific energy absorption (SEA), and peak crushing force (PCF). Extreme Gradient Boosting (XGBoost) and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) were developed to maximize SEA and minimize PCF. The results demonstrate that the optimized multi-cell configurations achieve superior energy absorption capacity. The proposed framework provides a computationally efficient approach for the crashworthiness design of crash boxes for electric vehicle applications.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint