[1]曾发林,蔡嘉伟,孙苏民.基于CEEMD的非稳态排气噪声声品质预测[J].郑州大学学报(工学版),2020,41(06):19-25.[doi:10.13705/j.issn.1671-6833.2020.04.008]
　ZENG Falin,CAI Jiawei,SUN Sumin.Sound Quality Prediction for Exhaust Noise Based on CEEMD Sample Entropy and GA-BP[J].Journal of Zhengzhou University (Engineering Science),2020,41(06):19-25.[doi:10.13705/j.issn.1671-6833.2020.04.008]
点击复制

基于CEEMD的非稳态排气噪声声品质预测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
41卷
期数:
2020年06期
页码:
19-25
栏目:
出版日期:
2020-12-31

文章信息/Info

Title:
Sound Quality Prediction for Exhaust Noise Based on CEEMD Sample Entropy and GA-BP
作者:
曾发林; 蔡嘉伟; 孙苏民
江西省汽车噪声与振动重点实验室,江西南昌330013, 江苏大学汽车工程研究院,江苏镇江212013, 江苏大学汽车工程研究院,江苏镇江212013

Author(s):
ZENG Falin1; 2;  CAI Jiawei2;  SUN Sumin2
1.Jiangxi Province Key Laboratory of Vehicle Noise and Vibration, Nanchang 330013, China; 2.Automobile Engineering Research Institute, Jiangsu University, Zhenjiang 212013, China
关键词:
Keywords:
unsteady exhaust noise; GA-BP; sound quality; CEEMD; sample entropy; principal component analysis
DOI:
10.13705/j.issn.1671-6833.2020.04.008
文献标志码:
A
摘要:
为了预测汽车非稳态排气噪声声品质，采用Zwicker时变算法计算了样车加速排气噪声的心理声学客观参量值，并建立基于心理声学客观参量的GA-BP声品质预测模型.同时，运用互补总体经验模态分解（CEEMD）对非稳态排气噪声信号进行分解，得到多个IMF分量，并对IMF分量进行样本熵特征计算，为了减少冗余和过度拟合的可能性并尽可能地保留原始数据的主特征，采用主成分分析（PCA）对数据进行降维处理，得到新参量SQP-CSP（Sound quality parameter base on CEEMD and then proceed SE-PCA），并建立新的预测模型.结果表明，根据新参量建立的模型对非稳态信号声品质预测具有更高的精度，更能体现非稳态信号的特征
Abstract:
In order to predict the sound quality of automobile unsteady exhaust noise, 2G WOT and 3G WOT tests were conducted. The main factors of satisfaction level were analyzed. Via the correlation analysis, internal relations between the psychoacoustic objective parameters and the subjective evaluation were revealed. The complementary ensemble empirical mode decomposition(CEEMD) was used to decompose the signals of the accelerated exhaust noise, obtaining multiple IMF components and calculating sample entropy of the IMF components. In order to reduce the possibility of redundancy and retain the main features of the original data, principal component analysis(PCA) was applied to reduce dimension of data, so as to establish a new sound quality parameter SQP-CSP(sound quality parameter base on CEEMD and then proceed SE-PCA). Meanwhile, the genetic algorithm(GA) was used to optimize the weights and thresholdsin BP neural network, so that a GA-BP was developed to predict the sound quality of the accelerated exhaust noise. In order to validate the newly extracted unsteady exhaust noise features，the psychoacoustic parameters were also taken as the model’s inputs to predict the sound quality．The results showed that the model based on the new parameters had higher accuracy for predicting the sound quality of unsteady exhaust noise.

参考文献/References:

[1] CHANDRIKA U K,KIM J H.Development of an algorithm for automatic detection and rating of squeak and rattle events[J].Journal of sound and vibration, 2010,329(21):4567-4577.

[2] 刘程,贺岩松,于海兴,等.汽车制动工况下车内时变噪声响度特征[J].汽车工程学报,2013,3(1):40-46.
[3] 沈哲,左言言,宋乃华,等.影响车辆声品质听审实验的相关因素研究[J].噪声与振动控制,2008,28(6):97-100.
[4] 鲍海鹏.车辆排气噪声声品质评价的方法研究[D].太原：太原理工大学,2016.
[5] 陈娟娟,王生昌,刘丹,等.乘用车转向性能主观评价与客观评价的相关性[J].公路交通科技,2018,35(1):137-141.
[6] HUSSAIN M,GÖLLES J,RONACHER A,et al.Statistical evaluation of an annoyance index for engine noise recordings[C]//SAE Technical Paper Series,400 Commonwealth Drive. New York: SAE International, 1991: 1-9.
[7] LIU H,ZHANG J H,GUO P,et al.Sound quality prediction for engine-radiated noise[J].Mechanical systems and signal processing, 2015,55-57:277-287.
[8] 毕凤荣,李琳,张剑,等.基于EEMD-HT与LSSVM的柴油机辐射噪声品质预测技术[J].天津大学学报(自然科学与工程技术版),2017,50(1):28-34.
[9] 蔡艳平,李艾华,王涛,等.基于EMD-Wigner-Ville的内燃机振动时频分析[J].振动工程学报,2010,23(4):430-437.
[10] YEH J R,SHIEH J S,HUANG N E.Complementary ensemble empirical mode decomposition:a novel noise enhanced data analysis method[J].Advances in adaptive data analysis, 2010,2(2):135-156.
[11] WU Z H,HUANG N E.A study of the characteristics of white noise using the empirical mode decomposition method[J].Proceedings of the royal society of london series A:mathematical,physical and engineering sciences, 2004,460(2046):1597-1611.
[12] 赵晓华,许士丽,荣建,等.基于ROC曲线的驾驶疲劳脑电样本熵判定阈值研究[J].西南交通大学学报,2013,48(1):178-183.
[13] 穆瑞杰. 基于遗传算法的地铁车站引导标识布点探析[J].郑州大学学报(工学版), 2018, 39(1):73-77,89.

更新日期/Last Update: 2021-02-10