Physics-informed GRU model for vehicle road noise prediction: Integrating transfer path analysis and hybrid data

  • Yan Ma Global R&D Center, China FAW Corporation Limited, Changchun 130013, China
  • Ruxue Dai School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
  • Tao Liu Global R&D Center, China FAW Corporation Limited, Changchun 130013, China
  • Mingzheng Wang Global R&D Center, China FAW Corporation Limited, Changchun 130013, China
  • Qichen Ying School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
  • Haibo Huang School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
Article ID: 3143
DOI: https://doi.org/10.59400/sv3143
Keywords: road noise; vehicle NVH; mechanism-data fusion; GRU; hybrid data

Abstract

With the continuous release of automobile market potential and the steady growth of automobile ownership, consumers’ concern for automobile NVH problems makes the road noise performance directly affect the sales of automobiles. Therefore, it is of great significance to study the problem of vehicle road noise. In the actual research process, it often faces the challenge of insufficient effective sample size. In this paper, 102 sets of sample data are collected by combining the real vehicle test method and the CAE simulation method. By comparing the road noise prediction model based on the GRU algorithm with the LSTM model and the CNN model, the results show that the GRU model performs roughly similarly to the LSTM model in terms of prediction accuracy (RMSE = 2.18) and robustness (MSE = 7.66%), and the GRU model and the LSTM model are significantly better than the CNN model, but the prediction efficiency of the GRU model is significantly better than the LSTM model. Therefore, the vehicle road noise prediction model based on the GRU algorithm is optimal. This paper provides an efficient method for road noise performance analysis and prediction, which can be applied to the vehicle design and performance improvement process and provide technical support for improving vehicle comfort and market competitiveness.

Published
2025-07-04
How to Cite
Ma, Y., Dai, R., Liu, T., Wang, M., Ying, Q., & Huang, H. (2025). Physics-informed GRU model for vehicle road noise prediction: Integrating transfer path analysis and hybrid data. Sound & Vibration, 59(3), 3143. https://doi.org/10.59400/sv3143
Issue
Vol. 59 No. 3 (2025)
Section
Article

Copyright (c) 2025 Author(s)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Xue H, Previati G, Gobbi M, et al. Research and Development on Noise, Vibration, and Harshness of Road Vehicles Using Driving Simulators—A Review. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2023; 7(4). doi: 10.4271/10-07-04-0035

[2]Huang H, Huang X, Ding W, et al. Vehicle vibro-acoustical comfort optimization using a multi-objective interval analysis method. Expert Systems with Applications. 2023; 213: 119001. doi: 10.1016/j.eswa.2022.119001

[3]Huang H, Lim TC, Wu J, et al. Multitarget prediction and optimization of pure electric vehicle tire/road airborne noise sound quality based on a knowledge- and data-driven method. Mechanical Systems and Signal Processing. 2023; 197: 110361. doi: 10.1016/j.ymssp.2023.110361

[4]Diez-Ibarbia A, Battarra M, Palenzuela J, et al. Comparison between transfer path analysis methods on an electric vehicle. Applied Acoustics. 2017; 118: 83-101. doi: 10.1016/j.apacoust.2016.11.015

[5]Cervantes-Madrid G, Peral-Orts R, Campillo-Davo N, et al. Inverse transfer path analysis, a different approach to shorten time in NVH assessments. Applied Acoustics. 2021; 181: 108178. doi: 10.1016/j.apacoust.2021.108178

[6]Zhu P, Wang Z, Qin Z, et al. The transfer path analysis method on the use of artificial excitation: Numerical and experimental studies. Applied Acoustics. 2018; 136: 102-112. doi: 10.1016/j.apacoust.2018.02.007

[7]Li M, Zhu Z, Deng T, et al. An investigation into high-speed train interior noise with operational transfer path analysis method. Railway Engineering Science. 2021; 29(1): 1-14. doi: 10.1007/s40534-021-00235-0

[8]Vaitkus D, Tcherniak D, Brunskog J. Application of vibro-acoustic operational transfer path analysis. Applied Acoustics. 2019; 154: 201-212. doi: 10.1016/j.apacoust.2019.04.033

[9]Liu W, Huang H, Fan D, et al. An LSTM-based method for predicting road noise in automobiles. Noise and vibration control. 2023; 3: 145-152. doi: 10.3969/j.jssn.1006-1355.2023.03.023

[10]Rapino L, Ripamonti F, Dallasta S, et al. Synthesis of equivalent sources for tyre/road noise simulation and analysis of the vehicle influence on sound propagation. Applied Acoustics. 2024; 216: 109751. doi: 10.1016/j.apacoust.2023.109751

[11]Bartolozzi G, Danti M, Camia A, et al. Enhancement of Full-Vehicle Road Noise Simulation Including Detailed Road Surface and Innovative Tire Modeling. SAE International Journal of Passenger Cars - Mechanical Systems. 2016; 9(3): 1091-1099. doi: 10.4271/2016-01-1827

[12]Su J, Lou J, Jiang X. Research on optimization control of vehicle road noise performance. IOP Conference Series: Earth and Environmental Science. 2021; 769(4): 042055. doi: 10.1088/1755-1315/769/4/042055

[13]Yoshida J, Tanaka K, Nakamoto R, et al. Combination Analysis of Operational TPA and CAE Technique for Obtaining High Contributing Vibration Mode. SAE Technical Paper Series; 2017. doi: 10.4271/2017-01-1856

[14]Harbi Y, Medani K, Gherbi C, et al. Roadmap of Adversarial Machine Learning in Internet of Things-Enabled Security Systems. Sensors. 2024; 24(16): 5150. doi: 10.3390/s24165150

[15]Huang HB, Wu JH, Huang XR, et al. The development of a deep neural network and its application to evaluating the interior sound quality of pure electric vehicles. Mechanical Systems and Signal Processing. 2019; 120: 98-116. doi: 10.1016/j.ymssp.2018.09.035

[16]Wang J, Han H, Han X, et al. Reinforcement learning path planning method incorporating multi-step Hindsight Experience Replay for lightweight robots. Displays. 2024; 84: 102796. doi: 10.1016/j.displa.2024.102796

[17]Zhao J, Yin Y, Chen J, et al. Evaluation and Prediction of Vibration Comfort in Engineering Machinery Cabs Using Random Forest with Genetic Algorithm. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2024; 8(4). doi: 10.4271/10-08-04-0027

[18]An LS, Jung S. Data-driven prediction of wind pressure on low-rise buildings in complex heterogeneous terrains. Building and Environment. 2024; 265: 112022. doi: 10.1016/j.buildenv.2024.112022

[19]Chen L, Zhang K, Yan J. Data-driven study on shear bearing capacity of segmental concrete joints. Structures. 2024; 68: 107145. doi: 10.1016/j.istruc.2024.107145

[20]Oh JY, Jung HW, Lee MH, et al. Enhancing active noise control of road noise using deep neural network to update secondary path estimate in real time. Mechanical Systems and Signal Processing. 2024; 206: 110940. doi: 10.1016/j.ymssp.2023.110940

[21]Luo YK, Chen SX, Zhou L, et al. Evaluating railway noise sources using distributed microphone array and graph neural networks. Transportation Research Part D: Transport and Environment. 2022; 107: 103315. doi: 10.1016/j.trd.2022.103315

[22]Sun P, Dai R, Li H, et al. Multi-Objective Prediction of the Sound Insulation Performance of a Vehicle Body System Using Multiple Kernel Learning–Support Vector Regression. Electronics. 2024; 13(3): 538. doi: 10.3390/electronics13030538

[23]Huang H, Wang Y, Wu J, et al. Prediction and optimization of pure electric vehicle tire/road structure-borne noise based on knowledge graph and multi-task ResNet. Expert Systems with Applications. 2024; 255: 124536. doi: 10.1016/j.eswa.2024.124536

[24]Guo R, Wang J, Yuan Y, et al. Interpretation of dual time-dependent chloride diffusion in concrete based on physical information neural networks. Case Studies in Construction Materials. 2024; 21: e03769. doi: 10.1016/j.cscm.2024.e03769

[25]Cong J, Liu Z, Zhou S, et al. Predicting fatigue life and crack growth rate of TC4 titanium alloy based on PINN before and after ultrasonic impact treatment. Engineering Failure Analysis. 2024; 166: 108875. doi: 10.1016/j.engfailanal.2024.108875

[26]Liu CX, Wang X, Liu W, et al. A physics-informed neural network for Kresling origami structures. International Journal of Mechanical Sciences. 2024; 269: 109080. doi: 10.1016/j.ijmecsci.2024.109080

[27]Fan JL, Zhu G, Zhu ML, et al. A data-physics integrated approach to life prediction in very high cycle fatigue regime. International Journal of Fatigue. 2023; 176: 107917. doi: 10.1016/j.ijfatigue.2023.107917

[28]Jeong H, Bai J, Batuwatta-Gamage CP, et al. A Physics-Informed Neural Network-based Topology Optimization (PINNTO) framework for structural optimization. Engineering Structures. 2023; 278: 115484. doi: 10.1016/j.engstruct.2022.115484

[29]Pang J, Mao T, Jia W, et al. Prediction and Analysis of Vehicle Interior Road Noise Based on Mechanism and Data Series Modeling. Sound & Vibration. 2024; 58(1): 59-80. doi: 10.32604/sv.2024.046247

[30]Fan D, Dai P, Yang M, et al. Research on Maglev Vibration Isolation Technology for Vehicle Road Noise Control. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2022; 6(3). doi: 10.4271/10-06-03-0016

[31]Del Pizzo LG, Bianco F, Moro A, et al. Relationship between tyre cavity noise and road surface characteristics on low-noise pavements. Transportation Research Part D: Transport and Environment. 2021; 98: 102971. doi: 10.1016/j.trd.2021.102971

[32]Yang M, Dai P, Yin Y, et al. Predicting and optimizing pure electric vehicle road noise via a locality-sensitive hashing transformer and interval analysis. ISA Transactions. 2025; 157: 556-572. doi: 10.1016/j.isatra.2024.11.059

[33]Cao Y, Hou H, Liu Y, et al. Sound Pressure Level Control Methods for Electric Vehicle Active Sound Design. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2021; 5(2). doi: 10.4271/10-05-02-0014

[34]Li Q, Ripamonti F, Corradi R, et al. Simulation of deterministic tyre noise based on a monopole substitution model. Applied Acoustics. 2021; 178: 108009. doi: 10.1016/j.apacoust.2021.108009

[35]Duan Y, Wu J, Zhang Y. Kinematics characteristics of unsprung mass in a double wishbone suspension based on velocity transformation. Acta Mechanica Sinica. 2024; 41(2). doi: 10.1007/s10409-024-23661-x

[36]Zhang S, Gao Y, Gao D, et al. Serial combinational optimization method for double wishbone suspension’s pseudo damage improvement. Structural and Multidisciplinary Optimization. 2023; 66(6). doi: 10.1007/s00158-023-03579-9

[37]Schmitz T. Chassis concept of the individually steerable five-link suspension: a novel approach to maximize the road wheel angle to improve vehicle agility. Automotive and Engine Technology. 2024; 9(1). doi: 10.1007/s41104-024-00142-6

[38]Alizadeh R, Fataliyev V, Akhundov E. Improving the Design of the Linkage Suspension of a Robotic Mobile Modular System. Journal of Machinery Manufacture and Reliability. 2024; 53(6): 539-543. doi: 10.1134/s1052618824701322

[39]Xu M, Han Y, Zhu N, et al. A method for recognizing individual dynamic thermal adaptations using wireless signals. Energy and Buildings. 2025; 333: 115448. doi: 10.1016/j.enbuild.2025.115448

[40]Choi SW, Li Y, Yang X, et al. Reachability analysis of recurrent neural networks. Nonlinear Analysis: Hybrid Systems. 2025; 56: 101581. doi: 10.1016/j.nahs.2025.101581

[41]Zeng C, Xu C, Li H, et al. A novel ensemble learning model for state of health estimation of lithium-ion batteries. Journal of Power Sources. 2025; 638: 236608. doi: 10.1016/j.jpowsour.2025.236608

[42]Huang H, Huang X, Ding W, et al. Optimization of electric vehicle sound package based on LSTM with an adaptive learning rate forest and multiple-level multiple-object method. Mechanical Systems and Signal Processing. 2023; 187: 109932. doi: 10.1016/j.ymssp.2022.109932

[43]National Acoustics Standardization Technical Committee. Acoustics-Measurement Method for In-vehicle Noise of Automobiles: GB/T 18697-2002. Beijing: China Standard Press; 2002.

[44]Xu S, Dai Y, Yan C, et al. On the preprocessing of physics-informed neural networks: How to better utilize data in fluid mechanics. Journal of Computational Physics. 2025; 528: 113837. doi: 10.1016/j.jcp.2025.113837

[45]Sagar N, Suresh KP, Sridhara S, et al. Precision detection of grapevine downy and powdery mildew diseased leaves and fruits using enhanced ResNet50 with batch normalization. Computers and Electronics in Agriculture. 2025; 232: 110144. doi: 10.1016/j.compag.2025.110144

[46]Yang Y, Zhao Q, Yang J. Optimization-Based Parameter Identification for Coupled Biodynamic Model of Seated Posture under Vibration. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2022; 6(2). doi: 10.4271/10-06-02-0011

[47]Trivedi R, Singh TN, Raina AK. Simultaneous prediction of blast-induced flyrock and fragmentation in opencast limestone mines using back propagation neural network. International Journal of Mining and Mineral Engineering. 2016; 7(3): 237. doi: 10.1504/ijmme.2016.078350

[48]Sathe S, Samak C, Samak T, et al. Data Driven Vehicle Dynamics System Identification Using Gaussian Processes. SAE Technical Paper Series; 2024. doi: 10.4271/2024-01-2022

[49]Liu Y, Cai K, Tian Z. A 3D discrete modeling strategy for predicting the cooling performance of the central cone laminate. Applied Thermal Engineering. 2025; 269: 125998. doi: 10.1016/j.applthermaleng.2025.125998

[50]Petrone B, Giovannardi E, Brusa A, et al. Development of an Automatic Pipeline for Data Analysis and Pre-Processing for Data Driven-Based Engine Emission Modeling in a Real Industrial Application. SAE Technical Paper Series; 2024. doi: 10.4271/2024-01-2018

[51]Wu Y, Li T, Zhang R, et al. Establishment of nomogram of early death in elderly pancreatic cancer patients with liver metastasis. Discover Oncology. 2025; 16(1). doi: 10.1007/s12672-025-02059-4

[52]Huang H, Huang X, Ding W, et al. Uncertainty optimization of pure electric vehicle interior tire/road noise comfort based on data-driven. Mechanical Systems and Signal Processing. 2022; 165: 108300. doi: 10.1016/j.ymssp.2021.108300