The sound insulation performance of an electric vehicle’s body system serves as a critical metric for evaluating the noise, vibration, and harshness (NVH) quality of the vehicle. The accurate and efficient prediction of sound insulation performance is foundational for undertaking noise reduction design and optimization. Current engineering practices predominantly rely on Computer-Aided Engineering (CAE) methodologies to address this challenge. However, inherent shortcomings such as low modeling efficiency and difficulty in ensuring prediction accuracy often characterize these approaches. In an effort to overcome these limitations, we propose a decomposition framework for predicting the sound insulation performance of the electric vehicle body system. This framework is established based on a comprehensive analysis of the noise transmission paths within the system. Subsequently, the support vector regression (SVR) method is introduced to construct a machine learning model specifically designed for predicting the sound insulation performance of the body system. This approach aims to mitigate the inherent weaknesses associated with the conventional CAE processes using a ‘data-driven’ paradigm. Furthermore, the Multiple Kernel Learning (MKL) method is used to enhance the processing efficacy of the SVR model. The proposed method is validated using practical application and testing on a specific electric vehicle. The results demonstrate commendable performance in terms of prediction accuracy and robustness. This research contributes to advancing the field by presenting a more effective and reliable approach to predicting the sound insulation performance of electric vehicle body systems, offering valuable insights for noise reduction strategies and optimization efforts in the automotive industry.

Phononic crystal is a new kind of sound insulation material, which has an elastic wave gap. When the elastic wave falls within the band gap, it will attenuate strongly in phononic crystal, and its attenuation degree is far greater than the predicted value of the mass density theorem. In this paper, the practical application of phononic crystals in low frequency sound insulation is taken as the breakthrough point. Firstly, the theory of phononic crystal band gap generation is calculated and analyzed, and the band structure of one-dimensional two-component Bragg scattering phononic crystals is calculated. Hypermesh is used to build the model, and the sound insulation performance of phononic crystals is simulated and analyzed through Nastran. A sound isolation test platform was built for the local resonant phononic crystal samples to verify its sound isolation ability.

Wiper motor noise has an important impact on vehicle comfort. Accurate prediction of wiper motor noise can obtain motor NVH performance in motor manufacturing or earlier stage and provide necessary support for NVH performance design of parts and vehicles. However, the prediction accuracy of wiper motor noise by the traditional CAE or testing method is low. Data-driven technology provides a new idea for wiper motor noise prediction with its advantages of high efficiency and high precision. This paper studies the wiper motor noise prediction algorithm based on the motor vibration signal, respectively, using the transmission path analysis theory and the support vector machine theory, and carries on the test verification and comparative analysis of the effect. The results show that the method based on support vector machine is more accurate in the prediction of wiper motor noise and has higher practical engineering value.