汽车声品质的GA-BP网络预测与权重分析

高印寒; 唐荣江; 梁杰; 赵彤航; 张澧桐

doi:10.3788/OPE.20132102.0462

您当前的位置：

首页 >

文章列表页 >

汽车声品质的GA-BP网络预测与权重分析

信息科学 | 更新时间：2020-08-12

- 汽车声品质的GA-BP网络预测与权重分析
- Sound quality prediction and weight analysis of vehicles based on GA-BP neural network
- 光学精密工程 2013年21卷第2期页码：462-468
- 作者机构：
  
  吉林大学汽车仿真与控制国家重点实验室2. 吉林大学仪器科学与电气工程学院3. 一汽集团技术中心
- 作者简介：
- 基金信息：
  
  吉林省科技发展计划项目(20140203011GX)
- DOI：10.3788/OPE.20132102.0462
  中图分类号： TP183;U467.4
- 收稿日期：2012-07-24，
  
  修回日期：2012-10-10，
  
  网络出版日期：2013-02-23，
  
  纸质出版日期：2013-02-15
- 稿件说明：
移动端阅览
高印寒唐荣江梁杰赵彤航张澧桐. 汽车声品质的GA-BP网络预测与权重分析[J]. 光学精密工程, 2013,21(2): 462-468

GAO Yin-han TANG Rong-jiang LIANG Jie ZHAO Tong-hang ZHANG Li-tong. Sound quality prediction and weight analysis of vehicles based on GA-BP neural network[J]. Editorial Office of Optics and Precision Engineering, 2013,21(2): 462-468
高印寒唐荣江梁杰赵彤航张澧桐. 汽车声品质的GA-BP网络预测与权重分析[J]. 光学精密工程, 2013,21(2): 462-468 DOI： 10.3788/OPE.20132102.0462.

GAO Yin-han TANG Rong-jiang LIANG Jie ZHAO Tong-hang ZHANG Li-tong. Sound quality prediction and weight analysis of vehicles based on GA-BP neural network[J]. Editorial Office of Optics and Precision Engineering, 2013,21(2): 462-468 DOI： 10.3788/OPE.20132102.0462.

摘要

为了高效而准确地评价与控制车内噪声品质，以B级车稳态工况下副驾位置的车内噪声为研究对象，采用等级评分法对采集到的声音样本进行了主观评价试验，同时计算了7个客观参数。以客观参量为输入，声品质主观结果为输出，引入基于遗传算法的BP神经网络建立了声品质预测模型。实验显示该模型输出结果与实际评分的相关系数达到0.928，检验组的预测最大误差为±8%。以所建模型的连接权值，分析了客观参数对主观评价结果的贡献度，并以影响系数较大的参数为输入重新构建了预测模型。研究结果表明：稳态工况下，车内声品质主要受响度、粗糙度和尖锐度的影响，其预测模型可由这3个参数来描述。

Abstract

This paper carried out a subjective evaluation test with magnitude estimation for 78 noise samples to evaluate the sound quality of vehicles. In the test

six types of B-Class vehicles were taken as the study objects and sound signals collected in co-driver locations at steady states as experimental samples. Meanwhile

seven objective parameters were calculated to describe the sound characteristics. By using objective parameters as inputs

subjective values as outputs

a GA-BP neural network was adopted to establish a sound quality prediction model. Experiments show that the model gives good predictions of high correlation (0.928) and low error (±8%). Then

the network connection coefficients were used to calculate the impact weight of objective parameters on the results of subjective evaluation

and a new model with main parameters was established. As expected

the loudness

sharpness and roughness with a total relative importance of 83% are the most influential parameters in vehicle interior sound quality.

关键词

Keywords

references

GENUIT K. The sound quality of vehicle interior noise: a challenge for the NVH engineers [J]. Vehicle Noise and Vibration, 2004, 1(1):158-168. [2]SANG-KWON L. Objective evaluation of interior sound quality in passenger cars during acceleration [J]. Journal of Sound and Vibration, 2008, 310(5):149-168.[3]高印寒,孙强,梁杰.B级轿车车内噪声品质的主观评价研究[J].噪声与振动控制,2010,30(4):115-118.GAO YH, SUN Q, LIANG J. Subjective evaluation research of B·class car’s interior sound quality [J]. Noise and Vibration Control, 2010, 30(4):115-118. (in Chinese)[4]申秀敏,左曙光,李林,等.车内噪声声品质的支持向量机预测[J].振动与冲击,2010,29(6):66-68.SHEN X M, ZUO S G, LI L, et al.. SVM predictor of vehicle interior sound quality [J]. Journal of Vibration and Shock, 2010, 29(6):66-68. (in Chinese)[5]SAHIN Y, IKBALK E. Sound quality analysis of cars using hybrid neural networks[J]. Simulation Modeling Practice and Theory, 2008, 16(4):410-418.[6]孙强.基于人工神经网络的汽车声品质评价与应用研究[D].长春：吉林大学,2011:50-53.SUN Q. Research on evaluation and application of vehicle sound quality based on artificial neural network[D]. Changchun:Jilin University, 2011: 50-53. (in Chinese)[7]董长虹.Matlab神经网络与应用[M].北京:国防工业出版社工程,2005:89-93.DONG C H. Matlab Neural Network and Application[M]. Beijing:National Defense Industry Press, 2005:89-93. (in Chinese)[8]郭海湘,诸克军,胡杰.GA-BP 嵌套算法的理论及应用[J].数学的实践与认识,2008,38(1):116-125.GUO H X, ZHU K J, HU J. The theory and application of GA-BP-NESTING algorithm [J]. Mathematics in Practice and Theory, 2008, 38 (1):116-125. (in Chinese)[9]王平,王彩芸,王文健. GA-BP网络在钢轨磨损量预测中的应用[J].润滑与密封,2011,36(2):99-102.WANG P, WANG C Y, WANG W J. Application of GA-BP ANN in the prediction of wear volumes of rail steel [J]. Lubrication Engineering, 2011, 36(2):99-102. (in Chinese)[10]MENG X P, ZHANG H G, TAN W Y.A hybrid method of GA and BP for short-term economic dispatch of hydrothermal power systems [J]. Mathematics and Computers in Simulation,2000,51(4):341-348. [11]ALEBOYEH A, KASIRI M B. Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks[J]. Dyes and Pigments, 2008(77):288-294.

浏览量

227

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据