SAE technical papers on CD-ROM/SAE technical paper series, Journal Year: 2025, Volume and Issue: 1

Published: May 5, 2025

<div class="section abstract"><div class="htmlview paragraph">In the modern automotive industry, squeak and rattle issues are critical factors affecting vehicle perceived quality customer satisfaction. Traditional approaches to predicting mitigating these problems heavily rely on physical testing simulation technologies, which can be time-consuming resource-intensive, especially for larger models. In this study, a data-driven machine learning approach was proposed mitigate risks more efficiently.</div><div paragraph">This study evaluated floor console model using traditional simulation-based E-line method pinpoint high-risk areas. Data generation is performed by varying material properties, thickness, flexible connection stiffness Hammersley sampling algorithm, creating diverse comprehensive dataset generating (ML) model. Utilizing dataset, top contributing variables were identified training ML Various machine-learning models developed evaluated, best-performing selected based accuracy generalizability.</div><div paragraph">A Genetic Algorithm (GA) employed optimize system further, in conjunction with determine optimal set of design parameters mitigation. The operating validated results confirming model's reliability. This optimization process significantly outperformed methods, yielding time gain 92 times compared solver-based similar level accuracy. methodology reduces computational provides robust framework efficiently risks, highlighting potential engineering applications.</div></div>

Language: Английский