Tire lateral force is a critical state for vehicle dynamics control, yet conventional sensor-based methods suffer from limited accuracy due to nonlinear tire characteristics and signal noise contamination. This paper presents a novel iTransformer-KAN architecture that integrates advanced signal preprocessing with hybrid neural networks for enhanced force estimation. The approach employs a three-stage denoising method combining Improved Complete Ensemble Empirical Mode Decomposition (ICEEMDAN), Permutation Entropy (PE), and Wavelet Threshold Denoising (WTD) to extract clean features from three-axis acceleration signals, followed by an innovative iTransformer-KAN network where Kolmogorov-Arnold Networks replace traditional MLPs to capture complex nonlinear tire-road interactions through spline-based mappings. Experimental validation demonstrates that the proposed method achieves superior performance with an NRMSE of 4.75%, representing a 12.5% improvement over GRU networks and a 21.2% improvement over MLP approaches, while maintaining computational efficiency with a 77.82-s training time. The method enables real-time lateral force monitoring for vehicle dynamics control systems, advancing the development of intelligent tire technologies for enhanced automotive safety and performance.
DingXWangZZhangL, et al. A comprehensive vehicle stability assessment system based on enabling tire force estimation. IEEE Trans Veh Technol2022; 71(11): 11571–11588.
2.
MazzilliVIvoneDDe PintoS, et al. On the benefit of smart tyre technology on vehicle state estimation. Veh Syst Dyn2022; 60(11): 3694–3719.
3.
ChengSLiLYanB, et al. Simultaneous estimation of tire side-slip angle and lateral tire force for vehicle lateral stability control. Mech Syst Signal Process2019; 132: 168–182.
4.
HashemiEPiraniMKhajepourA, et al. Corner-based estimation of tire forces and vehicle velocities robust to road conditions. Control Eng Pract2017; 61: 28–40.
5.
LeeEJungHChoiS. Tire lateral force estimation using Kalman filter. Int J Automot Technol2018; 19(4): 669–676.
6.
AcostaMKanarachosS. Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares. Neural Comput Appl2018; 30(11): 3445–3465.
7.
SongCXiaoFSongS, et al. Design of a novel nonlinear observer to estimate sideslip angle and tire forces for distributed electric vehicle. Math Probl Eng2015; 2015(1): 134615. https://doi.org/10.1155/2015/134615
8.
WangWYuanLTaoS, et al. Estimation of vehicle side slip angle in nonlinear condition based on the state feedback observer. In: 2010 IEEE international conference on automation and logistics, Hong Kong, China, 16–20 August 2010, pp.632–636. IEEE. https://doi.org/10.1109/ICAL.2010.5585359
9.
QinZChenLHuM, et al. A lateral and longitudinal dynamics control framework of autonomous vehicles based on multi-parameter joint estimation. IEEE Trans Veh Technol2022; 71(6): 5837–5852. https://doi.org/10.1109/TVT.2022.3163507
ZhuBHanJZhaoJ. Tire-pressure identification using intelligent tire with three-axis accelerometer. Sensors2019; 19(11): 2560. https://doi.org/10.3390/s19112560
12.
QuanZLiBBeiS, et al. Tire-road friction coefficient estimation method design for intelligent tires equipped with PVDF piezoelectric film sensors. Sens Actuators A Phys2023; 349: 114007. https://doi.org/10.1016/j.sna.2022.114007
13.
AskariHSaadatniaZAsadiE, et al. A flexible hybridized electromagnetic-triboelectric multi-purpose self-powered sensor. Nano Energy2018; 45: 319–329. https://doi.org/10.1016/j.nanoen.2018.01.011
14.
Garcia-PozueloDYuntaJOlatunbosunO, et al. A strain-based method to estimate slip angle and tire working conditions for intelligent tires using fuzzy logic. Sensors2017; 17(4): 874. https://doi.org/10.3390/s17040874
15.
MatsuzakiRKamaiKSekiR. Intelligent tires for identifying coefficient of friction of tire/road contact surfaces using three-axis accelerometer. Smart Mater Struct2015; 24(2): 025010. https://doi.org/10.1088/0964-1726/24/2/025010
16.
XuNHuangYAskariH, et al. Tire slip angle estimation based on the intelligent tire technology. IEEE Trans Veh Technol2021; 70(3): 2239–2249. https://doi.org/10.1109/TVT.2021.3059432
17.
BarbosaBHGXuNAskariH, et al. Lateral force prediction using Gaussian process regression for intelligent tire systems. IEEE Trans Syst Man Cybern Syst2022; 52(8): 5332–5343. https://doi.org/10.1109/TSMC.2021.3123310
18.
XuNAskariHHuangY, et al. Tire force estimation in intelligent tires using machine learning. IEEE Trans Intell Transp Syst2020; 23(4): 3565–3574. https://doi.org/10.1109/TITS.2020.3038155
19.
HanZLiuWGaoZ, et al. A method for real-time road surface identification of intelligent tire systems based on random convolutional kernel neural network. IEEE Trans Intell Veh2024; 9: 6487–6501. https://doi.org/10.1109/TIV.2024.3369951
20.
VaswaniAShazeerNParmarN, et al. Attention is all you need. Adv Neural Inf Process Syst2017; 30: 5998–6008.
ZhangZGaoHSunW, et al. Multivariate time series generation based on dual-channel Transformer conditional GAN for industrial remaining useful life prediction. Knowl Based Syst2025; 308: 112749. https://doi.org/10.1016/j.knosys.2024.112749
23.
CastangiaMGrajalesLMMAlibertiA, et al. Transformer neural networks for interpretable flood forecasting. Environ Model Softw2023; 160: 105581. https://doi.org/10.1016/j.envsoft.2022.105581
24.
LiuYHuTZhangH, et al. itransformer: inverted transformers are effective for time series forecasting. arXiv preprint arXiv:2310.06625, 2023. https://doi.org/10.48550/arXiv.2310.06625
ChenYZhuZZhuS, et al. Sckansformer: fine-grained classification of bone marrow cells via kansformer backbone and hierarchical attention mechanisms. IEEE J Biomed Health Inform2024; 29(1): 558–571. https://doi.org/10.1109/JBHI.2024.3471928
28.
YangQJiJJingR, et al. Reynolds rules in swarm fly behavior based on KAN transformer tracking method. Sci Rep2025; 15(1): 6982. https://doi.org/10.1038/s41598-025-91674-w
29.
TangYTaoLLiY, et al. Estimation of tire side-slip angles based on the frequency domain lateral acceleration characteristics inside tires. Machines2024; 12(4): 229. https://doi.org/10.3390/machines12040229
30.
ColominasMASchlotthauerGTorresME. Improved complete ensemble EMD: a suitable tool for biomedical signal processing. Biomed Signal Process Control2014; 14: 19–29. https://doi.org/10.1016/j.bspc.2014.06.009
