In the evaluation of vehicle noise, vibration and harshness (NVH) performance, interior noise control is the core consideration. In the early stage of automobile research and development, accurate prediction of interior noise caused by road surface is very important for optimizing NVH performance and shortening the development cycle. Although the data-driven machine learning method has been widely used in automobile noise research due to its advantages of no need for accurate physical modeling, data learning and generalization ability, it still faces the challenge of insufficient accuracy in capturing key local features, such as peaks, in practical NVH engineering. Aiming at this challenge, this paper introduces a forecast approach that utilizes an empirical-informed neural network, which aims to integrate a physical mechanism and a data-driven method. By deeply analyzing the transmission path of interior noise, this method embeds the acoustic mechanism features such as local peak and noise correlation into the deep neural network as physical constraints; therefore, this approach significantly enhances the model’s predictive performance. Experimental findings indicate that, in contrast to conventional deep learning techniques, this method is able to develop better generalization capabilities with limited samples, while still maintaining prediction accuracy. In the verification of specific models, this method shows obvious advantages in prediction accuracy and computational efficiency, which verifies its application value in practical engineering. The main contributions of this study are the proposal of an empirical-informed neural network that embeds vibro-acoustic mechanisms into the loss function and the introduction of an adaptive weight strategy to enhance model robustness.

The floor acoustic package is a crucial component of a vehicle’s overall acoustic insulation system, and its performance directly influences the interior sound field distribution and acoustic comfort. Conventional investigations of acoustic package performance primarily rely on experimental testing and computer-aided engineering (CAE) simulations. However, these methods often suffer from limited accuracy control, high computational cost, and low efficiency. In contrast, data-driven modeling approaches have recently demonstrated strong potential in addressing these challenges. In this paper, a Squeeze-and-Excitation Residual Network (SE-ResNet) is proposed to predict and analyze the sound insulation performance of vehicle floor systems based on the original structural and material parameters of acoustic package components. By replacing the conventional CAE process with a data-driven framework, the proposed method enhances prediction accuracy and computational efficiency. With the lowest recorded RMSE of 0.4048 dB across the 200–8000 Hz spectrum, the SE-ResNet model ranks first in overall performance. It substantially outperforms the SE-CNN (0.9207 dB) and also shows a clear advantage over both the SE-LSTM (0.4591 dB) and the ResNet (0.4593 dB). Validation using the acoustic package data of a new vehicle model further confirms the robustness of the proposed approach, yielding an overall RMSE = 0.4089 dB and CORR = 0.9996 on the test dataset. These results collectively demonstrate that the SE-ResNet-based method presents a promising and robust solution for forecasting the sound insulation performance of vehicle floor systems. Moreover, the proposed framework offers methodological and technical support for the data-driven prediction and analysis of other vehicle noise and vibration problems.