基于支持向量机的柴油机噪声品质客观评价参量权重分析

以一台6缸柴油机为研究对象，采用分类对偶比较法对采集到的目标机型在多工况下的辐射噪声品质进行主观评价试验，同时选取并计算了可以描述其声音特性的5个客观评价参量，引入支持向量机，建立了柴油机噪声品质预测模型，并借助噪声测试样本验证预测模型的准确性。然后以柴油机噪声品质预测模型为基础构建起客观评价参量的权重分析模型，分析柴油机噪声品质客观评价参量对主观评价结果的影响权重。研究表明，柴油机噪声品质主要受响度和粗糙度两个客观评价参量的影响。此次分析对高声品质柴油机的设计起到了指导性的作用。

Weight of object evealuation parameters for diesel engine noise quality with Support Vector Machine

A six-cylinder diesel engine was taken as a sample. The classified-paired comparison method was used to perform subjective evaluation test for the diesel engine radiated noise of the multiple load cases. Meanwhile, five objective evaluation parameters that could describe the objective characteristics of the diesel engine noise were chosen and calculated. A support vector machines was adopted to establish a diesel engine noise quality prediction model, and the accuracy of the prediction model was verified with the noise test samples. Based on the prediction model, the influence weight of objective evaluation of sound quality parameters on the results of subjective evaluation was analyzed and calculated. The results showed that the loudness and roughness were the main objective parameters determining the diesel engine noise quality. This analysis played a significant guiding role in the design of the diesel engine for noise quality.