Sound Quality Evaluation Control of Car Interior Noise

Abstract:

According to the complexity and non-linear characteristics of car interior sound quality evaluation, the technology of BP neural network is used in sound quality evaluation. The interior noise samples from actual cars were obtained by road experiment. The subjective evaluation test of sound quality annoyance was carried out. Meanwhile, several objective psycho-acoustical parameters of these samples were calculated. The sound quality prediction model of vehicle interior noise was established based on BP neural network. Annoyance of samples was obtained by means of the prediction model and the results were compared with that obtained by multiple liner regression prediction model. The results indicate that the prediction results from BP neural network model were close to the measured values. The BP neural network model was more effective than multiple liner regression model, and it can be used effectively to the evaluation of modern car noise.

• Periodical: Applied Mechanics and Materials (Volume 415)
• Pages: 569-573
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.415.569
• Online since: September 2013
• Authors: Fang Li, Yan Yan Zuo
• Keywords: Annoyance, BP Neural Network (BPNN), Prediction Model, Sound Quality, Vehicle Interior Noise

References

[1] Shu G Q , Wang Y J, Wei H Q, et al. Measurement and evaluation of sound quality of interior noise of vehicle cabin, Transactions of CSICE. 25 (2007) 77-83. (in Chinese).

[2] Chen S J, Chen D S. Sound quality preference evaluation for car interior noise based on psychoacoustic parameters, Noise and Vibration Control. 25 (2005) 45-47. (in Chinese).

[3] Shin S H, IH J G, Hashimoto T, et al. Sound quality evaluation of the booming sensation for passenger cars, Applied Acoustics. 70 (2009) 309-320.

DOI: 10.1016/j.apacoust.2008.03.009

[4] Sang Kwon Lee, Tae Gue Kim, and Usik Lee. Sound quality evaluation based on artificial neural network, Advances in Natural Computation. 2 (2006) 545-554.

DOI: 10.1007/11881070_75

[5] Y. S. Wang, C. M. Lee, D. G. Kin, et al. Sound quality prediction for nonstationary vehicle interior noise based on wavelet pre-processing neural network model, Journal of Sound and Vibration. 29 (2007) 933-947.

DOI: 10.1016/j.jsv.2006.07.034

[6] Wen Xin, MATLAB neural network: simulation and application, third ed., Science Press, Beijing, 2003. (in Chinese).

[7] Otto N, Amman S, Eaton C, Guidelines for jury evaluations of automotive sounds, SAE International. 01(1999) 1822.

DOI: 10.4271/1999-01-1822

[8] Li Meng, The study on evaluation system of automobile's noise sound quality, Jiangsu Zhenjiang: Jiangsu University, (2008).

[9] Sonoko Kuwano, Seiichiro Namba, Takehisa Okamoto, Psychological evaluation of sound environment in a compartment of a high-speed train, Journal of Sound and Vibration. 277 (2004) 491-500.

DOI: 10.1016/j.jsv.2004.03.010

[10] Mao dongxing, Wang yong, Jiang zaixiu, Paremetric model for low-frequency index of subjective car interior sound quality, Technical Acoustics. 25 ( 2006) 533-539.

[11] Mungiole M, Wilson D K, Prediction of outdoor sound transmission loss with an artificial neural network, Applied Acoustics. 67 (2006) 324-345.

DOI: 10.1016/j.apacoust.2005.06.003

[12] Shi Yan, Shu Gequn, Bi Fengrong, et al. Sound quality prediction of vehicle exhaust noise based on neural network, Transactions of the Chinese society for Agricultural Machinery. 41 (2010) 16-20. (in Chinese).

[13] Shen Xiumin, Zuo Shuguang, He Lvchang, et al. BP neural network prediction of car interior sound quality, Technical Acoustics. 28 (2009) 264-268. (in Chinese).

[14] R&D center of Feisi IT products, Neural network Theory and MATLAB 7 realization, 2nd, Electronics Industry Press, Beijing, 2005. (in Chinese).

[15] Cao Shumin, Du Qingling, Human resources demond forecast based on back-propagation neural network, Journal of Shandong University of Technology(Natural Science Edition), 22 (2008) 26-29.