Enhanced crashworthiness performance of auxetic structures using artificial neural network and geyser inspired algorithm

Abstract This study focuses on the optimum design of an auxetic energy absorber intended for automobile applications. The material chosen for this energy absorber is SCGA27D galvanized steel. This research proposes the utilization of an artificial neural network-assisted metaheuristic for optimizing automobile structural components. The geyser inspired algorithm (GEA), ship rescue algorithm, and mountain gazelle algorithm are employed to optimize an automobile energy absorber. The objective of the problem is to obtain optimal geometry for an energy absorber while simultaneously reducing mass and meeting energy absorption constraints. The findings demonstrate that both the GEA algorithm and SCGA27D galvanized steel material exhibit exceptional capabilities in designing vehicle structures.