Designing Rubber Flaps for Resonance Management: High-Frequency Tuning in Electric Vehicles Using AI/ML Approaches

High-frequency whine noise in electric vehicles (EVs) poses a significant challenge, affecting customer perception and the overall vehicle experience. One primary source of this undesirable noise is the interaction between motor pole resonance and the resonance of the engine mount rubber. This paper presents an innovative method for predicting and tuning the frequency response of engine mounts by precisely adjusting the dimensions of rubber flaps, specifically their length and width. The proposed solution employs a dual approach: fine-tuning rubber flap dimensions and utilizing machine learning (ML) techniques. An ML model, trained on historical data, predicts how varying flap dimensions impact frequency response, providing a data-driven foundation for optimization. This prediction capability is enhanced by a Python program that automates the optimization process using a linear combination formula, efficiently addressing resonance issues. By integrating ML insights with the linear combination formula, the method effectively manages dynamic peaks during frequency sweeps and reduces resonance problems through dual dynamic absorber theory. This comprehensive strategy improves the acoustic environment within the vehicle cabin, serving as a preventive measure against resonance issues and ultimately enhancing the overall user experience. Keywords: Electric Vehicles (EVs), Rubber bushes, Rubber Flaps, Machine Learning (ML), Python Optimization,