Wind noise is a significant source of noise when vehicles are driven at high speeds. While wind tunnel experiments are commonly method to study real automotive wind noise, anechoic wind tunnel laboratory are prohibitive for automakers on account of their high costs and limited experimental period. Therefore, this paper proposes to extract automotive wind noise through combining road experiment and drum experiment, define significant wind noise prime regions, and verify its effectiveness. Subsequently, the Long Short-Term Memory Neural Network algorithm (LSTM) is employed to reveal the complex nonlinear relationship between wind noise and its impact areas, in order to establish an identification model for automotive wind noise. The performance of the model is then compared with Backpropagation Neural Networks (BPNN) and Support Vector Regression (SVR) models. The results indicate that the LSTM wind noise identification model exhibits higher accuracy, shorter training time, and stronger generalization ability, thus demonstrating the superiority of this model.
OettleNSims-WilliamsD.Automotive aeroacoustics: an overview. Proc IMechE, Part H: J Automobile Engineering2017; 231(9): 1177–1189.
3.
MüllerGGrabnerGWieseneggerM, et al. Assessment of the vehicle’s interior wind noise due to measurement of exterior flow quantities in early project phases. In: FuchsANijmanEPriebschH-H (eds) Automotive NVH technology. New York, NY: Springer, 2016, pp.1–12.
4.
MüllerGGrabnerGWieseneggerM, et al. Assessment of the vehicle’s interior wind noise due to measurement of exterior flow quantities. SAE technical paper 2014-01-2050, 2014.
5.
PinelliJPSubramanianCPlamondonM.Wind effects on emergency vehicles. J Wind Eng Ind Aerodynamics2004; 92(7–8): 663–685.
6.
D’HoogeARebbeckLPalinR, et al. Application of real-world wind conditions for assessing aerodynamic drag for on-road range prediction. SAE technical paper 2015-01-1551, 2015.
7.
Clar-GarciaDVelasco-SanchezECampillo-DavoN, et al. A new methodology to assess sound power level of tyre/road noise under laboratory controlled conditions in drum test facilities. Appl Acoust2016; 110: 23–32.
8.
GiorgettaFGobbiMMastinuG.On the testing of vibration performances of road vehicle suspensions. Exp Mech2007; 47(4): 485–495.
9.
Campillo-DavoNPeral-OrtsRVelasco-SanchezE, et al. An experimental procedure to obtain sound power level of tyre/road noise under Coast-By conditions. Appl Acoust2013; 74(5): 718–727.
10.
WatkinsSRiegelMWiedemannJ. The effect of turbulence on wind noise: a road and wind tunnel study. In: BargendeMWiedemannJ (hrsg.) 4. Internationales stuttgarter symposium. Renningen: Expert-Verlag, 2001, pp.326–340.
11.
KounenisCSims-WilliamsDDominyR, et al. The effects of unsteady flow conditions on vehicle in cabin and external noise generation. SAE technical paper 2015-01-1555, 2015.
12.
BremnerPApriliaVMarD. Developing aerodynamic design diagnostics for control of interior wind noise. In: Proceedings of the 14ème Congrès Français D’acoustique, 2014, pp.22–25. Poitiers: CFA.
13.
HeYShiZWuY, et al. Sound radiation analysis of a front side window glass of DrivAer model under wind excitation. Shock Vib2018; 1: 5828725.
14.
ZaareerMNMouradA-HIDarabsehT, et al. Aeroacoustics wind noise optimization for vehicle’s side mirror base. Int J Thermofluids2023; 18: 100332.
15.
HartmannMOckerJLemkeT, et al. Wind noise caused by the side-mirror and a-pillar of a generic vehicle model. In: 18th AIAA/CEAS aeroacoustics conference (33rd AIAA aeroacoustics conference), Colorado Springs, CO, USA, 2012, p.2205. Reston, VA: American Institute of Aeronautics and Astronautics.
16.
OettleNSims-WilliamsDDominyR, et al. The effects of unsteady on-road flow conditions on cabin noise. SAE technical paper 2010-01-0289, 2010.
17.
YuanHYangZWangY, et al. Experimental analysis of hydrodynamic and acoustic pressure on automotive front side window. J Sound Vib2020; 476: 115296.
18.
DruaultPHekmatiARicotD.Discrimination of acoustic and turbulent components from aeroacoustic wall pressure field. J Sound Vib2013; 332(26): 7257–7278.
CheYXiaoWXChenLJ, et al. GA-BP neural network based tire noise prediction. Adv Mater Res2012; 443: 65–70.
21.
YildirimŞErkayaSEskiİ, et al. Noise and vibration analysis of car engines using proposed neural network. J Vib Control2009; 15(1): 133–156.
22.
LiMZhouWLiuJ, et al. Vehicle interior noise prediction based on Elman neural network. Appl Sci2021; 11(17): 8029.
23.
YangXTanLHeL.A robust least squares support vector machine for regression and classification with noise. Neurocomputing2014; 140: 41–52.
24.
CherkasskyVMaY.Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw2004; 17(1): 113–126.
25.
LeeS-KLeeHBackJ, et al. Prediction of tire pattern noise in early design stage based on convolutional neural network. Appl Acoust2021; 172: 107617.
26.
YooJLeeC-HJeaH-M, et al. Classification of road surfaces based on CNN architecture and tire acoustical signals. Appl Sci2022; 12(19): 9521.
27.
ParkHEJungHLeeMS, et al. Interior wind noise prediction and visual explanation system for exterior vehicle design using combined convolution neural networks. Int J Automot Technol2022; 23(4): 1013–1021.
28.
HuangXHuangHWuJ, et al. Sound quality prediction and improving of vehicle interior noise based on deep convolutional neural networks. Expert Syst Appl2020; 160: 113657.
HouWDarakanandaDEldredgeJD.Machine-learning-based detection of aerodynamic disturbances using surface pressure measurements. AIAA J2019; 57(12): 5079–5093.
31.
BruntonSL. Machine learning of dynamics with applications to flow control and aerodynamic optimization. In: Advances in critical flow dynamics involving moving/deformable structures with design applications: proceedings of the IUTAM symposium on critical flow dynamics involving moving/deformable structures with design applications, 18–22 June 2018, pp.327–335. Santorini, Greece: Springer.
32.
MengH-YXuZ-XYangJ, et al. Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network. Chin Phys B2022; 31(6): 064305.
33.
LiSSunYGaoH, et al. An interpretable aerodynamic identification model for hypersonic wind tunnels. IEEE Trans Industr Inform2023; 20(1): 12–22.
34.
SunYLiSGaoH, et al. Transfer learning: a new aerodynamic force identification network based on adaptive EMD and soft thresholding in hypersonic wind tunnel. Chin J Aeronaut2023; 36(8): 351–365.
35.
HuangLNWangDFCaoXL, et al. Deep learning-based wind noise prediction study for automotive clay model. Meas Sci Technol2024; 35(4): 045302.
36.
PericCWatkinsSLindqvistE, et al. Effects of on-road turbulence on automotive wind noise: comparing wind-tunnel and on-road tests. SAE technical paper970406, 1997.
37.
GabrielCMüllerSUllrichF, et al. A new kind of sensor array for measuring spatial coherence of surface pressure on a car’s side window. J Sound Vib2014; 333(3): 901–915.
38.
PowellRMoronPBalasubramanianG, et al. Simulation of underbody contribution of wind noise in a passenger automobile. SAE Int J Passeng Cars Mech Syst2013; 6(2): 1251–1261.
39.
LiuNSunYWangY, et al. Mechanism of interior noise generation in high-speed vehicle based on anti-noise operational transfer path analysis. Proc IMechE, Part H: J Automobile Engineering2021; 235(1): 273–287.
40.
Cervantes-MadridGPeral-OrtsRCampillo-DavoN, et al. Inverse transfer path analysis, a different approach to shorten time in NVH assessments. Appl Acoust2021; 181: 108178.
HeYSchröderSShiZ, et al. Wind noise source filtering and transmission study through a side glass of DrivAer model. Appl Acoust2020; 160: 107161.
43.
Vivó-TruyolsGSchoenmakersPJ.Automatic selection of optimal Savitzky–Golay smoothing. Anal Chem2006; 78(13): 4598–4608.
44.
KimMYLeeSKimJH. A wide & deep learning sharing input data for regression analysis. In: IEEE international conference on big data and smart computing (BigComp 2020), Busan, Korea, 19–22 February 2020, pp.8–12. New York: IEEE.
