Archives of Acoustics, 49, 3, pp. 307–317, 2024
10.24425/aoa.2024.148794

Evaluation Modeling of Electric Bus Interior Sound Quality Based on Two Improved XGBoost Algorithms Using GS and PSO

Enlai ZHANG
School of Mechanical and Automotive Engineering, Xiamen University of Technology; Xiamen Key Laboratory of Robot Systems and Digital Manufacturing
China

Yi CHEN
School of Mechanical and Automotive Engineering, Xiamen University of Technology
China

Liang SU
Bus Engineering Research Institute, Xiamen King Long United Automotive Industry Co., Ltd
China

Ruoyu ZHONGLIAN
School of Mechanical and Automotive Engineering, Xiamen University of Technology
China

Xianyi CHEN
School of Mechanical and Automotive Engineering, Xiamen University of Technology
China

Shangfeng JIANG
School of Mechanical and Automotive Engineering, Xiamen University of Technology
China

There is no doubt that traffic noise has become one of the main sources of urban noise, and the electric bus, as an important means of transport frequently used by people in daily life, has a direct impact on the psychological and auditory health of passengers due to its interior noise characteristics. Consequently, studying electric bus sound quality is an important way to improve vehicle performance and comfort. In this paper, eight electric buses were selected and 64 noise samples were measured. Acoustic comfort was taken as an evaluation index, professionals were organized to complete the subjective evaluation tests for all noise samples based on rank score comparison (RSC). And nine psycho-acoustic objective parameters such as loudness, sharpness and roughness were calculated using Artemis software to establish the sound quality database of electric buses. Aiming at the practical application requirements of high-precision modeling of acoustic comfort in vehicles, this paper presented two improved extreme gradient boosting (XGBoost) algorithms based on grid search (GS) method and particle swarm optimization (PSO), respectively, with objective parameters and acoustic comfort as input and output variables, and established three regression models of standard XGBoost, GS-XGBoost, and PSO-XGBoost through data training. Finally, the calculation results of three indexes of average relative error, square root error and correlation coefficient indicate that the proposed PSO-XGBoost model is significantly better than GS-XGBoost and standard XGBoost, with its prediction accuracy as high as 97.6 %. This model is determined as the evaluation model of interior acoustic comfort for this case, providing a key technical support for future sound quality optimization of electric buses.
Keywords: electric bus; sound quality; acoustic comfort; GS-XGBoost; PSO-XGBoost
Full Text: PDF
Copyright © 2024 The Author(s). This work is licensed under the Creative Commons Attribution 4.0 International CC BY 4.0.

References

Chen S.M., Wang D.F., Liang J. (2012), Sound quality analysis and prediction of vehicle interior noise based on grey system theory, Fluctuation and Noise Letters, 11(2): 1250016, doi: 10.1142/S0219477512500162.

Chen T.Q., Guestrin C. (2016), XGBoost: A scalable tree boosting system, [in:] KDD ’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, doi: 10.1145/2939672.2939785.

Das G., Pattnaik P.K., Padhy S.K. (2014), Artificial neural network trained by particle swarm optimization for non-linear channel equalization, Expert Systems with Applications, 41(7): 3491–3496, doi: 10.1016/j.eswa.2013.10.053.

Ding F., Xie W.T., Xie X.P. (2023), Research on optimization of car door closing sound quality based on the integration of structural simulation and test, [in:] Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 237(6): 1378–1390, doi: 10.1177/09544070221088370.

Doleschal F., Verhey J.L. (2022), Pleasantness and magnitude of tonal content of electric vehicle interior sounds containing subharmonics, Applied Acoustics, 185: 108442, doi: 10.1016/j.apacoust.2021.108442.

Huang H.B., Huang X.R., Li R.X., Lim T.C., Ding W.P. (2016), Sound quality prediction of vehicle interior noise using deep belief networks, Applied Acoustics, 113: 149–161, doi: 10.1016/j.apacoust.2016.06.021.

Huang H.B., Wu J.H., Lim T.C., Yang M.L., Ding W.P. (2021), Pure electric vehicle nonstationary interior sound quality prediction based on deep CNNs with an adaptable learning rate tree, Mechanical System and Signal Processing, 148: 107170, doi: 10.1016/j.ymssp.2020.107170.

Huang X.R., Huang H.B., Wu J.H., Yang M.L., Ding W.P. (2020), Sound quality prediction and improving of vehicle interior noise based on deep convolutional neural networks, Expert Systems with Applications, 160: 113657, doi: 10.1016/j.eswa.2020.113657.

Kim D., Lee J. (2022), Predictive evaluation of spectrogram-based vehicle sound quality via data augmentation and explainable artificial Intelligence: Image color adjustment with brightness and contrast, Mechanical Systems and Signal Processing, 179: 109363, doi: 10.1016/j.ymssp.2022.109363.

Liang L.Y., Chen S.M., Li P.R. (2020), The evaluation of vehicle interior impact noise inducing by speed bumps based on multi-features combination and support vector machine, Applied Acoustics, 163: 107212, doi: 10.1016/j.apacoust.2020.107212.

Madvari R.F., Sharak M.N., Tehrani M.J., Abbasi M. (2022), Estimation of metal foam microstructure parameters for maximum sound absorption coefficient in specified frequency band using particle swarm optimisation, Archives of Acoustics, 47(1): 33–42, doi: 10.24425/aoa.2022.140730.

Pourseiedrezaei M., Loghmani A., Keshmiri M. (2021), Development of a sound quality evaluation model based on an optimal analytic wavelet transform and an artificial neural network, Archives of Acoustics, 46(1): 55–65, doi: 10.24425/aoa.2021.136560.

Shi W.K., Liu G.Z., Song H.S., Chen Z.Y., Zhang B. (2018), Vibration and noise characteristics of electric bus [in Chinese], Jilin Daxue Xuebao (Gongxueban), 48(2): 373–379, doi: 10.13229/j.cnki.jdxbgxb20170110.

Steinbach L., Altinsoy M.E. (2019), Prediction of annoyance evaluations of electric vehicle noise by using artificial neural networks, Applied Acoustics, 145: 149–158, doi: 10.1016/j.apacoust.2018.09.024.

Wang C., Peng J.X., Zhang X.W. (2020), A classification method related to respiratory disorder events based on acoustical analysis of snoring, Archives of Acoustics, 45(1): 141–151, doi: 10.24425/aoa.2020.132490.

Wang Y., Zhang S., Meng D.J., Zhang L.J. (2022), Nonlinear overall annoyance level modeling and interior sound quality prediction for pure electric vehicle with extreme gradient boosting algorithm, Applied Acoustics, 195: 108857, doi: 10.1016/j.apacoust.2022.108857.

Wang Y.S. (2009), Sound quality estimation for nonstationary vehicle noises based on discrete wavelet transform, Journal of Sound and Vibration, 324(3–5): 1124–1140, doi: 10.1016/j.jsv.2009.02.034.

Zhang E.L., Chen X.Y., Li S.Y., W Q.Q., Zhuo J.M. (2022a), A comprehensive evaluation model of electric bus interior acoustic comfort and its application, International Journal of Acoustics and Vibration, 27(4): 361–366, doi: 10.20855/ijav.2022.27.41887.

Zhang E.L., Chen Y., Chen X.Y., Zhang J.B., Xun P.W., Zhuo J.M. (2023a), High-precision modeling and prediction of acoustic comfort for electric bus based on BPNN and XGBoost, International Journal of Acoustics and Vibration, 28(2): 158–164, doi: 10.20855/ijav.2023.28.21922.

Zhang E.L., Hou L., Shen C. (2016), Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO), Measurement Science and Technology, 27(1): 015801, doi: 10.1088/0957-0233/27/1/015801.

Zhang E.L., Zhang Q.M., Xiao J.J., Hou L., Guo T. (2018), Acoustic comfort evaluation modeling and improvement test of a forklift based on rank score comparison and multiple linear regression, Applied Acoustics, 135: 29–36, doi: 10.1016/j.apacoust.2018.01.026.

Zhang E.L., Zhuo J.M., Hou L., Fu C.H., Guo T. (2021), Comprehensive annoyance modeling of forklift sound quality based on rank score comparison and multi-fuzzy analytic hierarchy process, Applied Acoustics, 173: 107705, doi: 10.1016/j.apacoust.2020.107705.

Zhang X.C., Cheng J., Lu J.W., Yuan B., Jiang P., Sha W. (2022b), Sound quality evaluation of pure electric vehicle with subjective and objective unified evaluation method, International Journal of Vehicle Design, 88(2–4): 283–303, doi: 10.1504/IJVD.2022.127024.

Zhang Y., Meng T., Wang K. (2020), Subjective evaluation model for interior sound quality and optimization of medium-frequency noise, Automotive Engineering, 42(5): 651–657+664, doi: 10.19562/j.chinasae.qcgc.2020.05.013.

Zhang Y., Peng B.T., Yang E.C., Ren K.L., OU J. (2023b), Prediction and analysis of vehicle interior sound quality based on XGBoost algorithm [in Chinese], Noise and Vibration Control, 43(3): 161–166+211, doi: 10.3969/j.issn.1006-1355.2023.03.025.




DOI: 10.24425/aoa.2024.148794