摘要
对高速列车车内噪声进行了现场测试,使用等级评分法组织被试者开展主观评价试验,并计算心理声学客观参量。以客观参量为特征、主观烦恼度为标签,建立基于支持向量回归机的声品质预测模型,通过相关性分析确定影响烦恼度的主要因素。研究结果表明:支持向量回归机在测试集的预测精度为0.92,可以有效实现由心理声学客观参量到主观烦恼度的映射。响度是影响高速列车车内声学舒适性的主要因素,随着列车运行速度增大,低频噪声成分的特性响度迅速增大。当速度达到300 km/h时,特性响度曲线的最大值出现在低频段且非常显著,对人体的声学舒适性产生巨大影响。相关研究结果可为高速列车车内噪声控制和设计提供科学依据和参考。
The interior noise of a high-speed train is tested on the spot.The grading method is adopted to conduct the subjective evaluation test on the participants,and the objective parameters of psychoacoustics is calculated.With objective parameters as characteristics and subjective annoyance as labels,a sound quality prediction model based on support vector regression machine is established,and the main factors affecting the degree of annoyance are determined through the correlation analysis.The research results show that the prediction accuracy of support vector regression machine in the test set is 0.92,which can effectively realize the mapping from objective parameters of psychoacoustics to subjective annoyance.Loudness is the main factor affecting the interior acoustic comfort of high-speed trains.With the increase of the train speed,the characteristic loudness of low-frequency noise components increases rapidly.When the speed reaches 300 km/h,the maximum value of the characteristic loudness curve appears in the low frequency band and is very significant,which has a great impact on the acoustic comfort of the human body.The relevant research results can provide scientific basis and reference for the control and design of interior noise of high-speed trains.
作者
胡秦
徐涆文
陈鹏
黄佳程
肖新标
HU Qin;XU Hanwen;CHEN Peng;HUANG Jiacheng;XIAO Xinbiao(State Key Laboratory of Traction Power,Southwest Jiaotong University,Chengdu 610031,China)
出处
《机械》
2023年第12期41-47,共7页
Machinery
基金
国家自然科学基金(U1934203)。
关键词
高速列车
声品质
预测模型
支持向量回归机
响度
high-speed train
sound quality
prediction model
support vector regression machine
loudness