采用生理响度感知机制的车内噪声声品质预测  

Sound quality prediction of vehicle interior noise based on physiological loudness perception mechanism

作　　者：刘后广[1] 赵禹[1,2] 饶柱石 贺志恒[1] 杨建华 刘送永[1] LIU Houguang;ZHAO Yu;RAO Zhushi;HE Zhiheng;YANG Jianhua;LIU Songyong(School of Mechatronic Engineering,China University of Mining and Technology,Xuzhou 221116;Auto Engineering Research Institute,BYD Auto Industry Co.,LTD.,Shenzhen 518118;Institute of Vibration,Shock and Noise,Shanghai Jiao Tong University,Shanghai 200240;State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University,Shanghai 200240)

机构地区：[1]中国矿业大学机电工程学院,徐州221116 [2]比亚迪汽车工业有限公司汽车工程研究院,深圳518118 [3]上海交通大学振动、冲击、噪声研究所,上海200240 [4]上海交通大学机械系统与振动国家重点实验室,上海200240

出　　处：《声学学报》2024年第2期246-253,共8页Acta Acustica

基　　金：国家自然科学基金项目(52275296,52111530235);江苏省高校优势学科建设工程项目(PAPD)资助。

摘　　要：现有车内噪声声品质预测的响度计算中没有考虑真实人耳生理解剖结构的传声特性,因此提出了一种基于生理响度感知模型的车内噪声声品质预估方法。首先,采集两款轿车的车内噪声样本,并通过主观评价试验得到车内噪声的主观评价烦恼度。之后,整合中耳集总参数模型与耳蜗传输线模型,构建生理响度模型。然后,以生理响度模型的响度计算值为主要参数,结合尖锐度、粗糙度与车内噪声的主观评价值,通过TabNet模型构建了车辆声品质预测模型。最终,对比分析了所构建声品质模型与基于现有标准响度模型所构建的声品质模型的预测效果。结果表明,采用生理响度模型的声品质预测平均误差百分比仅有4.73%,优于采用Moore响度(6.13%)与Zwicker响度(6.94%)的声品质预测结果。此外,所构建的TabNet声品质预测模型的平均误差百分比也低于基于BP神经网络模型的平均误差百分比(7.60%)。采用生理响度模型的TabNet声品质预测能够提高车内噪声声品质客观评价的准确率。Aiming at the sound transmission characteristics of the real human ear physiological structure are not considered in the loudness calculation of the existing vehicle interior noise sound quality prediction,a method for predicting the sound quality of vehicle interior noise based on the physiological loudness perception model is proposed.Firstly,the samples of vehicle interior noise from two cars were collected,and the subjective evaluation of annoyance of vehicle interior noise was obtained through subjective evaluation tests.Secondly,by combining the lumped parameter model of the middle ear and the cochlear transmission line model,a physiological loudness model was constructed.Thirdly,taking the calculated loudness of the physiological loudness model and the subjective evaluation values of vehicle interior noise as the main parameters,combined with sharpness,roughness,a sound quality prediction model was constructed by TabNet model.Finally,the prediction effects of the proposed sound quality model and the sound quality models based on the existing standard loudness models were compared.The results show that the average error percentage of sound quality prediction based on the physiological loudness model is only 4.73%,which is lower than that based on Moore loudness model(6.13%)and Zwicker loudness model(6.94%).Meanwhile,the average error percentage of the TabNet sound quality prediction model is also lower than that of the BP neural network prediction model(7.60%).The sound quality TabNet prediction based on the physiological loudness model can improve the accuracy of the objective evaluation of the sound quality of vehicle interior noise.

关 键 词：车内噪声 声品质 生理响度感知 TabNet网络 听觉外周 

分 类 号：U467.493[机械工程—车辆工程]