基于轮胎内嵌传感器阵列的智能轮胎磨损检测方法

doi:10.19562/j.chinasae.qcgc.2025.06.019

摘要/Abstract

摘要：

为充分利用智能轮胎内嵌集成传感器阵列能够采集轮胎-地面接触状态多模态信息的优势，并用以提升轮胎磨损检测精度，本文提出一种基于轮胎内嵌传感器阵列感知信息的智能轮胎磨损检测方法。首先，构建了由加速度传感器与PVDF压电薄膜传感器组成的传感器阵列，设计智能轮胎嵌入式阵列数据采集系统，采集不同磨损程度轮胎在多种工况下的传感器阵列数据。其次，对传感器阵列波形数据进行Butterworth滤波并提取其多维时域特征。分析车辆行驶工况变化时传感器阵列数据的时域特征变化规律，发现车速与载荷变化时加速度传感器与PVDF压电薄膜传感器的时域特征（长度特征、面积特征）变化特性具有显著差异。最后，建立了融合两种传感器时域特征信息的联合特征集，并构建了轮胎磨损检测机器学习模型。测试结果表明基于传感器阵列的轮胎磨损检测平均绝对误差为0.13 mm，相较于仅使用加速度传感器和仅使用PVDF压电薄膜传感器分别下降了67.67%和56.81%。在磨损误差0.3 mm内，传感器阵列的轮胎磨损检测准确率达到88.81%；在磨损误差0.5 mm内，传感器阵列的轮胎磨损检测准确率达到96.42%。证明了基于传感器阵列的智能轮胎磨损检测机器学习模型的有效性与准确性。

关键词: 智能轮胎, 传感器阵列, 磨损检测, 机器学习

Abstract:

In order to fully utilize the advantages of embedded integrated sensor arrays in smart tires for collecting multi-modal information of the tire-ground contact state， and to enhance the accuracy of tire wear detection， a smart tire wear detection method based on the embedded sensor array is proposed in this paper. Firstly， a sensor array composed of accelerometers and PVDF piezoelectric film sensors is constructed， and an embedded data acquisition system for the smart tire is designed to collect sensor array data from tires with various degrees of wear under different operating conditions. Next， the waveform data from the sensor array is processed using Butterworth filtering， and multidimensional time-domain features are extracted. The variations in the time-domain characteristics of the sensor array data are analyzed under changing vehicle operating conditions， revealing significant differences in the time-domain feature variations （length features and area features） of the accelerometer and PVDF piezoelectric film sensors with the change of vehicle speed and vertical load. Finally， a joint feature set that integrates the time-domain feature information from both types of sensors is established， and a machine learning model for tire wear detection is constructed. The test results show that the average absolute error of tire wear detection based on the sensor array is 0.13 mm， a reduction of 67.67% and 56.81%， respectively， compared to using only the accelerometer or only the PVDF piezoelectric film sensor. The detection accuracy of tire wear within a 0.3 mm error reaches 88.81%， while the accuracy within a 0.5 mm error reaches 96.42， which proves the effectiveness and accuracy of the machine learning model for tire wear detection based on the sensor array.

Key words: intelligent tire, sensor array, wear detection, machine learning

金立生,赵鑫,谢宪毅,杨浩,路波,宋明亮,郭柏苍,曹耀光. 基于轮胎内嵌传感器阵列的智能轮胎磨损检测方法[J]. 汽车工程, 2025, 47(6): 1207-1218.

Lisheng Jin,Xin Zhao,Xianyi Xie,Hao Yang,Bo Lu,Mingliang Song,Baicang Guo,Yaoguang Cao. Intelligent Tire Wear Detection Method Based on an Embedded Sensor Array Within the Tire[J]. Automotive Engineering, 2025, 47(6): 1207-1218.

图/表 37

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

图11

图12

图13

表2

特征参数表"

类型	符号	表达
长度特征	H_Z₁	$L C y - m e a n f$
长度特征	H_Z₂	$R C y - m e a n f$
长度特征	S_Z	$R C x - L C x$
长度特征	H_Z	$m a x m e a n f - f$
面积特征	A_Z₁	$∫ L C x L I f n - m e a n f n d n$
面积特征	A_Z₂	$∫ R I R C x f n - m e a n f n d n$
面积特征	A_Z	$∫ L I R I m e a n f n - f n d n$

表2

图14

表3

图15

表4

图16

表5

表6

图17

表7

图18

表8

图19

表9

表10

图20

图21

表11

图22

表12

图23

表13

图24

参考文献 29

1	LIU H， DENG W， ZONG C， et al. Development of active control strategy for flat tire vehicles［C］. SAE Paper 2014-01-0859.
2	WANG F， CHEN H， CAO D. Nonlinear coordinated motion control of road vehicles after a tire blowout［J］. IEEE Transactions on Control Systems Technology， 2015， 24（3）： 956-970.
3	ASKARI H， HASHEMI E， KHAJEPOUR A， et al. Tire condition monitoring and intelligent tires using nanogenerators based on piezoelectric， electromagnetic， and triboelectric effects［J］. Advanced Materials Technologies， 2019， 4（1）： 1800105.
4	TJIU W， AHANCHIAN A， MAJLIS B Y. Development of tire condition monitoring system （TCMS） based on MEMS sensors［C］.2004 IEEE International Conference on Semiconductor Electronics. IEEE， 2004.
5	TONG G， WANG Q， YANG K， et al. An experiment investigation to the radial tire noise［J］. Advanced Materials Research， 2013， 694： 361-365.
6	庞博维，崔敏，杨琨，等. 轮胎胎面磨损检测技术研究进展［J］.无损检测，2021，43（7）：83-89，94.
	PANG B W， CUI M， YANG K， et al. Research progress of tire tread wear detection technology ［J］. Non-destructive Testing， 2021， 43（7）： 83-89，94.
7	HORNE W B， LELAND T J. Influence of the tire tread pattern and runway surface condition on breaking friction and rolling resistance of a modern aircraft tire ［M］. National Aeronautics and Space Administration， 1962.
8	王国林，王晨，张建，等.基于有限元分析的轮胎磨损性能优化［J］.汽车工程，2009，31（9）：867-870.
	WANG G L， WANG C， ZHANG J， et al. Tire wear performance optimization based on finite element analysis ［J］. Automotive Engineering，2009，31（9）：867-870.
9	WU J， ZHANG C， WANG Y， et al. Wear predicted model of tread rubber based on experimental and numerical method［J］. Experimental Techniques， 2018， 42： 191-198.
10	PARK H J， LEE Y W， KIM B G. Efficient tire wear and defect detection algorithm based on deep learning［J］. Journal of Korea Multimedia Society， 2021， 24（8）： 1026-1034.
11	MIN Y， XIAO B， DANG J， et al. Real time detection system for rail surface defects based on machine vision［J］. EURASIP Journal on Image and Video Processing， 2018， 2018（1）： 1-11.
12	CHANG W H， JUANG R T， HUANG M H， et al. Estimation of tire mileage and wear using measurement data［J］. Electronics， 2021， 10（20）： 2531.
13	LI B， QUAN Z， BEI S， et al. An estimation algorithm for tire wear using intelligent tire concept［J］. Proceedings of the Institution of Mechanical Engineers， Part D： Journal of Automobile Engineering， 2021， 235（10-11）： 2712-2725.
14	POHL A， STEINDL R， REINDL L. The" intelligent tire" utilizing passive SAW sensors measurement of tire friction［J］. IEEE Transactions on Instrumentation and Measurement， 1999， 48（6）： 1041-1046.
15	TUONONEN A J， MATILAINEN M J. Real-time estimation of aquaplaning with an optical tyre sensor［J］. Proceedings of the Institution of Mechanical Engineers， Part D： Journal of Automobile Engineering， 2009， 223（10）： 1263-1272.
16	MATSUZAKI R， TODOROKI A， KOBAYASHI H， et al. Passive wireless strain monitoring of a tire using capacitance and electromagnetic induction change［J］. Advanced Composite Materials， 2005， 14（2）： 147-164.
17	BRAGHIN F， BRUSAROSCO M， CHELI F， et al. Measurement of contact forces and patch features by means of accelerometers fixed inside the tire to improve future car active control［J］. Vehicle System Dynamics， 2006， 44（sup1）： 3-13.
18	YANG S， CHEN Y， SHI R， et al. A survey of intelligent tires for tire-road interaction recognition toward autonomous vehicles［J］. IEEE Transactions on Intelligent Vehicles， 2022， 7（3）： 520-532.
19	XU N， ASKARI H， HUANG Y， et al. Tire force estimation in intelligent tires using machine learning［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 23（4）： 3565-3574.
20	SINGH K B， TAHERI S. Estimation of tire-road friction coefficient and its application in chassis control systems［J］. Systems Science & Control Engineering， 2015， 3（1）： 39-61.
21	XU N， HUANG Y， ASKARI H， et al. Tire slip angle estimation based on the intelligent tire technology［J］. IEEE Transactions on Vehicular Technology， 2021， 70（3）： 2239-2249.
22	LI B， QUAN Z， BEI S， et al. An estimation algorithm for tire wear using intelligent tire concept［J］. Proceedings of the Institution of Mechanical Engineers， Part D： Journal of Automobile Engineering， 2021， 235（10-11）： 2712-2725.
23	ZHANG H， ZHANG S， ZHANG Y， et al. Abrasion status prediction with BP neural network based on an intelligent tire system［C］.2020 4th CAA International Conference on Vehicular Control and Intelligence （CVCI）. IEEE， 2020： 619-622.
24	HAN J Y， KWON J H， LEE S， et al. Experimental evaluation of tire tread wear detection using machine learning in real-road driving conditions［J］. IEEE Access， 2023， 11： 32996-33004.
25	KIM Y J， KIM H J， HAN J Y， et al. Classification of tire tread wear using accelerometer signals through an artificial neural network［J］. Journal of the Korean Society of Industry Convergence， 2020， 23（2_2）： 163-171.
26	陶亮，唐钰，戚文杰，等.基于轮内加速度的乘用车胎面磨损程度分类试验［J］.中国机械工程，2023，34（22）：2737-2745.
	TAO L， TANG Y， QI W， et al. Classification test of tread wear degree of passenger vehicle based on in-wheel acceleration ［J］. China Mechanical Engineering， 2023，34（22）：2737-2745.
27	陶亮，唐钰，李元强，等.多胎内传感器智能轮胎开发平台设计与侧偏试验研究［J］.机械工程学报，2024，60（8）：245-255.
	TAO L， TANG Y， LI Y， et al. Design and side-deflection test of intelligent tire development platform with multi-tire inner sensor ［J］. Chinese Journal of Mechanical Engineering，2024，60（8）：245-255.
28	王岩，梁冠群，危银涛.基于支持向量机的智能轮胎路面辨识算法［J］.汽车工程，2020，42（12）：1671-1678，1717.
	WANG Y， LIANG G， WEI Y. Intelligent tire road recognition algorithm based on support vector machine ［J］. Automotive Engineering， 2019，42（12）：1671-1678，1717.
29	刘卫东，韩宗志，高镇海，等.基于智能轮胎系统的实时路面辨识技术［J］.汽车工程，2024，46（4）：617-625.
	LIU W， HAN Z， GAO Z， et al. Real-time road recognition technology based on intelligent tire system ［J］. Automotive Engineering， 2019，46（4）：617-625.

工况	范围
轮胎花纹磨损程度/mm	0/1/2/3/4/5
车速/（km·h^-1）	20/40/60
载荷/kN	4/5/6
胎压/bar	2.3/2.5/2.7

速度/（km·h^-1）	20	40	60
H_Z₁	2.880	14.809	38.164
H_Z₂	3.422	18.269	45.108
S_Z	318	167	113
H_Z	9.630	47.748	112.356
A_Z₁	97.993	311.674	580.975
A_Z₂	597.458	1 585.483	2 480.233
A_Z	1 145.998	2 958.727	4 745.111

载荷/kN	4	5	6
H_Z₁	3.648	4.094	4.235
H_Z₂	4.080	4.512	4.635
S_Z	318	334	356
H_Z	10.520	11.534	11.714
A_Z₁	130.364	151.305	160.366
A_Z₂	618.168	756.688	906.023
A_Z	1 206.742	1 436.353	1 627.966

胎压/bar	2.3	2.5	2.7
H_Z₁	2.357	2.214	2.125
H_Z₂	3.180	3.009	2.898
S_Z	314	313	307
H_Z	8.845	8.718	8.453
A_Z₁	77.299	71.050	66.200
A_Z₂	518.592	496.864	467.449
A_Z	1 020.595	997.187	948.706

工况	车速	载荷	胎压
H_Z₁	↑↑↑↑	↑↑	↓
H_Z₂	↑↑↑↑	↑↑	↓
S_Z	↓↓↓	↑↑	↓
H_Z	↑↑↑↑	↑↑	↓
A_Z₁	↑↑↑↑	↑↑	↓↓
A_Z₂	↑↑↑↑	↑↑	↓
A_Z	↑↑↑↑	↑↑	↓