检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:周云阳 孙跃东[1] 王岩松[2] 冯天培[1] ZHOU Yun-yang;SUN Yue-dong;WANG Yan-song;FENG Tian-pei(School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai University of Engineering Science,Shanghai 201620,China)
机构地区:[1]上海理工大学机械工程学院,上海200093 [2]上海工程技术大学,上海201620
出 处:《机械设计与制造》2020年第1期300-304,共5页Machinery Design & Manufacture
基 金:国家自然科学基金项目(51175320)
摘 要:响度、尖锐度等心理声学客观参量常作为声学特征建立车辆噪声品质客观评价模型。考虑人耳听觉多频带滤波特性,研究听觉频带声能量对声品质客观评价的影响。建立基于频带声能量的汽车车内噪声品质客观量化模型,提高声品质识别的精度和稳定性。采集汽车匀速车内噪声并进行综合烦躁度主观评价试验,建立小波包耳蜗滤波器组提取听觉特征频带内声能量,利用支持向量机建立频带能量与主观评价结果之间的回归模型。交叉验证结果表明,相比于建立的基于心理声学客观参量综合烦躁度模型,建立的人耳听觉特征频带能量综合烦躁度客观评价模型预测的误差均值和误差方差更小,车内噪声品质评价的精度、稳定性均有提高。Objective parameters such as loudness and sharpness,which are regarded as acoustic parameters,are often designed to establish objective evaluation model of vehicle sound quality. Taking account of the characteristics of human auditory multi-band filtering,this paper studies the influence of auditory featurebandon objective evaluation of sound quality.According to the research,build an objective quantitative model of vehicle interior noise based on energy of band energy,so the accuracy and stability of sound quality recognition was be improved. The vehicle interior noise is collected and the subjective evaluation test of the comprehensive annoyance is carried out. The energy of the auditory feature band was exacted by wavelet packet cochlea filter group,and the regression model between the band energy and the subjective evaluation was established by using the support vector machine. Cross validation results show that compared with established thepsychoacoustic metrics based comprehensive annoyance evaluation model,the sound energy within auditory feature band based comprehensive annoyance evaluation model prediction is smaller than expected in error mean and error variance. The precision of the interior noise quality evaluation and stability were increased.
关 键 词:车内噪声 特征频带 小波包 支持向量机 交叉验证
分 类 号:TH16[机械工程—机械制造及自动化] U467.493[机械工程—车辆工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222