Revolutionizing Track Racing Chassis: Performance Enhancements through Geometrical Design and Machine Learning Analysis

Abstract

Developing high-performance track racing vehicles presents numerous design challenges, particularly in optimizing chassis geometry for structural efficiency under extreme dynamic loads. This study investigates the impact of advanced geometric configurations on chassis performance by systematically analyzing and comparing multiple design iterations. Machine learning techniques are integrated to evaluate and validate the structural performance of various chassis designs, providing a data-driven complement to traditional Finite Element Analysis (FEA) methods. The results reveal significant improvements in structural integrity and performance metrics, such as Von
Mises stress distribution and deformation, for two different chassis designs. These findings highlight the importance of innovative design and computational analysis in advancing chassis development for track racing. The research offers practical recommendations for engineers and designers, especially regarding key areas for future innovation and improvement in chassis optimization for track racing.