Sound Quality Prediction of Electric Power Train Noise Based on Particle Swarm Optimization and Support Vector Machine[J]. 2016, 50(1): 41-46.
DOI:
Sound Quality Prediction of Electric Power Train Noise Based on Particle Swarm Optimization and Support Vector Machine[J]. 2016, 50(1): 41-46.DOI: 10.7652/xjtuxb201601007.
Sound Quality Prediction of Electric Power Train Noise Based on Particle Swarm Optimization and Support Vector Machine
An electric power train is taken as a sample to predict its radiation noise quality. Studying frequency characteristics of sound quality and sensitive frequency-band energy ratio
a correlation analysis is conducted between subject evaluation and psychoacoustics parameters including loudness
sharpness
roughness
fluctuation and articulation index. Then a predicting model of sound quality of electric powertrain is established based on particle swarm optimization(PSO)and support vector machine(SVM). After optimizing the penalty factor of SVM and parameters of kernel function by PSO
the effectiveness of R is confirmed. The results indicate that subjective feeling can be reflected by sensitive frequency band energy ratio with correlation coefficient being 0.946. The absolute value and maximum value of the relative error are 2.0% and 6.7% respectively
which shows that the prediction accuracy of PSO-SVM is superior to those of the genetic algorithm method and grid search method.
SHEN Xiumin, ZUO Shuguang, HAN Le, et al. Interior vehicle noise quality prediction using support vector machines [J]. Journal of Vibration, Measurement & Diagnosis, 2011(1): 55-58.
MENG Xiangde, ZHANG Junhong, LI Lishun, et al. Sound quality prediction of diesel engine noise based on regression analysis [J]. Transactions of CSICE, 2011, 29(6): 534-537.
LIU Hai, ZHANG Junhong, ZHANG Guichang, et al. Prediction model for diesel engine noise quality [J]. Journal of Mechanical Engineering, 2012, 48(2): 159-164.
LIU Hai, ZHANG Junhong, NI Guangjian, et al. Sound quality prediction of diesel engine noise based on genetic algorithm and support vector machine [J]. Journal of Vibration and Shock, 2013, 32(2): 111-114.
SASAKI M, NAKASHIMA K. Human auditory models and sound quality evaluation method for diesel noise, SAE 2007-01-2219 [R]. New York, USA: SAE, 2007.
HUALLPA B, MARANO J, SCZIBOR V, et al. Gear lever sound quality evaluation, SAE 2010-36-0369 [R]. New York, USA: SAE, 2010.
WANG Changshan, ZHANG Lijun. A study on the method of evaluating the sound quality of vehicle door closing noise [J]. Automotive Engineering, 2011, 33(10): 902-906.
WANG Wanying, PENG Wei, JIN Xiaoxiong, et al. Sound quality analysis on in-car noise induced by tire [J]. Automotive Engineering, 2009, 31(3): 267-270.
XU Xueying, HAN Guohua, WU Ying, et al. Sound character and evaluation method of electric vehicle [J]. Chinese Journal of Automotive Engineering, 2011, 1(z1): 17-20.
OKOSHI M, HASHIMOTO Y, SUZUKI M, et al. Test equipment maker's cooperative approach to the measurement next generation automotives: comparison of noise and vibration characteristics between ice vehicle and EV, SAE 2011-39-7202 [R]. New York, USA: SAE, 2011.
FANG Y, ZHANG T. Modeling and analysis of electric powertrain NVH under multi-source dynamic excitation, SAE 2014-01-2870 [R]. New York, USA: SAE, 2014.
HUSSAIN M, GOLLES J, RONACHE A, et al. Statistical evaluation of an annoyance index for engine noise recordings [C]∥SAE Noise and Vibration Conference and Exhibition. New York, USA: SAE, 1991: 911080.
FANG Yuan, ZHANG Tong, CHEN Feifei, et al. A subjective and objective evaluation model for psychoacoustical quality of electric vehicle noise [J]. Journal of Xi'an Jiaotong University, 2015, 49(8): 97-101.
PENG Ling, NIU Ruiqing, ZHAO Yannan, et al. Prediction of landslide displacement based on KPCA and PSO-SVR [J]. Journal of Wuhan University: Geomatics and Information Science Edition, 2013, 38(2): 148-152.
XU Zhongming, XIE Yaoyi, HE Yansong, et al. Evaluation of car interior sound quality based on PSO-SVM [J]. Journal of Vibration and Shock, 2015, 34(2): 25-29.