基于GA-BP神经网络的加速工况车内声品质研究

遴选出15辆乘用车三挡全油门加速工况车内噪声，选择专业评审者进行主观评价试验，选择具有噪声时变特征的4个客观评价参量，基于GA-BP神经网络建立精准的预测模型，同时将用该模型与多元线性回归模型得出的结果进行对比。研究表明，GA-BP神经网络模型更适合描述车内噪声品质评价的复杂性和非线性，可以获得更好的预测结果，可较大程度的提高预测精度。

Research on vehicle interior sound quality based on GA-BP neural network

The interior noises sample of 15 passenger vehicles under the 3rd gear full throttle acceleration were selected, the juries of acoustic experience experts are used to subjective evaluation, and 4 objective characters of time-varying characteristics are used to describe the interior noise, GA-BP neural network theory was used to establish the prediction model of sound quality, and the model prediction results were compared to the results obtained by the multiple linear regression model. The results show that the GA-BP neural network model is more suitable to describe the complexity and nonlinear noise quality evaluation of vehicle noise. It could largely improve the predictive accuracy of sound quality evaluation and has reference value to the evaluation and analysis of vehicle noise.