基于遗传支持向量机的柴油机辐射噪声品质预测技术

以一台六缸车用柴油机为例，研究了其在变负荷及转速工况下表面辐射噪声品质情况，为进一步提高整机声品质，开展柴油机结构声学设计奠定了理论基础。研究国内外车用柴油机客观评价特征，并选取响度、尖锐度、粗糙度和波动度来描述辐射噪声的客观评价特征；针对柴油机噪声特点，采用成对比较法开展以专业陪审团人群为目标的满意度评价研究；应用遗传算法优化支持向量机（GA-SVM）建立起该车用柴油机声品质预测模型，并与BP神经网络预测模型进行比较，结果表明，基于遗传算法优化的支持向量机辐射噪声品质预测模型较神经网络建模预测精度更高，能够更准确地反映客观评价参量与主观满意度之间的非线性映射关系。

Sound quality prediction of Diesel engine noise based on genetic algorithm and support vector machine

Six-cylinder diesel engine is taken as a sample; the sound quality of the radiated noise varied with loads/speeds is studied so as to improve the radiated noise quality and establish the theoretical foundation for the structure acoustical design. On the basis of studying the objective evaluation of diesel engine radiated noise at home and abroad, five objective evaluation parameters consisting of loudness, sharpness, roughness and fluctuation strength are chosen to describe the objective characteristics of the diesel engine noise; considering the characteristics of the diesel engine noise, the paired comparison was applied in the jury evaluation; the prediction model of noise quality was established through the genetic support vector machines algorithm(GA-SVM), compared with neural network prediction model, the results showed that the GA-SVM prediction model for forecasting the sound quality of engine radiated noise has achieved higher accuracy than the neural network prediction model, which can reflect the non-linear relationship between characteristic parameters and subjection evaluation results accurately.