许文天,梁树林,池茂儒,温泽峰,吴兴文,王辰浩,蔡吴斌,陶功权,吴越

• 1:西南交通大学轨道交通运载系统全国重点实验室
• 2:西南交通大学机械工程学院
• 3:智奇铁路设备有限公司工程技术部

摘要(Abstract)：

车轮多边形磨耗是高速列车运营面临的典型缺陷，会引发强烈的轮轨冲击，严重威胁行车安全与乘坐舒适性。为实现其精准诊断，基于轴箱加速度的车载监测技术已成为研究热点。现有基于单点振动的诊断方法普遍假设各车轮响应相互独立，难以处理实际运行中显著存在的跨轮耦合效应，从而导致诊断不稳定、易受邻轮干扰。为解决这一问题，提出一种面向高速动车组的多传感器融合多轮协同诊断方法。通过融合转向架4个轮位的轴箱振动数据，构建一维卷积与长短时记忆网络结合的深度模型(Mul-CNN-LSTM),实现多轮多边形磨耗的同步定量识别。所提方法能够从系统层面提取跨轮传递特征，抑制邻轮干扰，并提升识别的准确性和稳健性。仿真与实车试验结果表明，相较于单点诊断方法，本文方法多边形诊断准确率与鲁棒性显著提升，验证了多传感器融合在高速列车多边形诊断中的有效性和优越性，对于实现高精度的车载多边形定量监测具有关键意义。

关键词(KeyWords)： 车轮多边形;多传感数据融合;神经网络;高速列车;轴箱加速度

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(U21A20168,52202464,52475138,52505218);; 中央高校科技创新项目(2682026CX053);; 四川省青年基金(2025ZNSFSC1322);; 四川省重大科技专项(2023ZDZX0011-3)

作者(Author): 许文天,梁树林,池茂儒,温泽峰,吴兴文,王辰浩,蔡吴斌,陶功权,吴越

参考文献(References)：

• [1] 金学松，吴越，梁树林，等.高速列车车轮多边形磨耗、机理、影响和对策分析 [J].机械工程学报，2020,56(16):118-136.Jin Xuesong,Wu Yue,Liang Shulin,et al.Characteristics,mechanism,influences and countermeasures of polygonal wear of high-speed train wheels [J].Journal of Mechanical Engineering,2020,56(16):118-136.
• [2] Zhai W M,Jin X S,Wen Z F,et al.Wear problems of high-speed wheel/rail systems:observations,causes,and countermeasures in China [J].Applied Mechanics Reviews,2020,72(6):060801.
• [3] Iwnicki S,Nielsen J C O,Tao G Q.Out-of-round railway wheels and polygonisation [J].Vehicle System Dynamics,2023,61(7):1787-1830.
• [4] 宋春元，沈文林，李晓峰，等.高速动车组车轮多边形影响因素及抑制措施研究 [J].中国铁路，2017(11):33-40.Song Chunyuan,Shen Wenlin,Li Xiaofeng,et al.On the influencing factors and inhibiting measures of wheel polygons of high-speed EMUs [J].China Railway,2017(11):33-40.
• [5] Bogacz R,Frischmuth K.On dynamic effects of wheel-rail interaction in the case of Polygonalisation [J].Mechanical Systems and Signal Processing,2016,79:166-173.
• [6] Barke D W,Chiu W K.A review of the effects of out-of-round wheels on track and vehicle components [J].Proceedings of the Institution of Mechanical Engineers,Part F:Journal of Rail and Rapid Transit,2005,219(3):151-175.
• [7] M??LLER-BBM RAIL TECHNOLOGIES GMBH.Wheel roughness measuring device ■].[2025-09-28].https://www.muellerbbm -rail.com/products/wheel-roughness-measuring-device/.
• [8] Krummenacher G,Ong C S,Koller S,et al.Wheel defect detection with machine learning [J].IEEE Transactions on Intelligent Transportation Systems,2018,19(4):1176-1187.
• [9] Magalh??es J,Jorge T,Silva R,et al.A strategy for out-of-roundness damage wheels identification in railway vehicles based on sparse autoencoders [J].Railway Engineering Science,2024,32(4):421-443.
• [10] Guo X X,Ji Z Y,Sun H Y,et al.A multiline laser vision sensor array-driven overall-wheel-profile 3-D reconstruction and measurement [J].IEEE Transactions on Industrial Informatics,2025,21(9):7220-7231.
• [11] Sun Q,Chen C J,Kemp A H,et al.An on-board detection framework for polygon wear of railway wheel based on vibration acceleration of axle-box [J].Mechanical Systems and Signal Processing,2021,153:107540.
• [12] Xu W T,Chi M R,Cai W B,et al.An anti-disturbance method for on-board detection of early wheel polygonal wear by weighted angle-synchronous moving average [J].Measurement,2023,216:112999.
• [13] Chen S Q,Wang K Y,Zhou Z W,et al.Quantitative detection of locomotive wheel polygonization under non-stationary conditions by adaptive chirp mode decomposition [J].Railway Engineering Science,2022,30(2):129-147.
• [14] Mosleh A,Montenegro P A,Costa P A,et al.Railway vehicle wheel flat detection with multiple records using spectral kurtosis analysis [J].Applied Sciences,2021,11(9):4002.
• [15] Song Y,Sun B C.Recognition of wheel polygon based on W/R force measurement by piezoelectric sensors in GSM-R network [J].Wireless Personal Communications,2018,102(2):1283-1291.
• [16] Xie Q L,Tao G Q,Lo S M,et al.High-speed railway wheel polygon detection framework using improved frequency domain integration [J].Vehicle System Dynamics,2024,62(6):1424-1445.
• [17] Xu W T,Cui L T,Cai W B,et al.Enhanced onboard quantitative diagnosis of wheel polygonal wear using Cepstral-Bayesian calibrated FRF [J].Measurement,2024,234:114904.
• [18] Hao S J,Ge F X,Li Y M,et al.Multisensor bearing fault diagnosis based on one-dimensional convolutional long short-term memory networks [J].Measurement,2020,159:107802.
• [19] Zhu S Y,Zhang Q L,Zhai W M,et al.Sensor deploying for damage identification of vibration isolator in floating-slab track using deep residual network [J].Measurement,2021,183:109801.
• [20] Ye Y G,Zhu B,Huang P,et al.OORNet:a deep learning model for on-board condition monitoring and fault diagnosis of out-of-round wheels of high-speed trains [J].Measurement,2022,199:111268.
• [21] Dong M Y,Chen S Q,Xie B,et al.A quantitative detection method for wheel polygonization of heavy-haul locomotives based on a hybrid deep learning model [J].Measurement,2024,227:114206.
• [22] Jiang J N,Tao G Q,Liang H Q,et al.A structure information-assisted generalization network for fault diagnosis of out-of-round wheels of metro trains [J].Measurement,2025,244:116519.
• [23] Wang J B,Qu S,Li G D,et al.Field test study on vibration transmission of high speed train with polygonised wheels[C]//Proceedings of the 25th International Symposium on Dynamics of Vehicles on Roads and Tracks (IAVSD 2017).London:CRC Press,2017:1353-1358.
• [24] Cai W B,Chi M R,Wu X W,et al.A long-term tracking test of high-speed train with wheel polygonal wear [J].Vehicle System Dynamics,2021,59(11):1735-1758.
• [25] Qu S,Zhu B,Zeng J,et al.Experimental investigation for wheel polygonisation of high-speed trains [J].Vehicle System Dynamics,2021,59(10):1573-1586.
• [26] Zhang F B,Wang H,Zeng Q H,et al.Novel method for measuring high-frequency wheel-rail force considering wheelset vibrations [J].Scientific Reports,2025,15:15044.
• [27] Carrigan T D,Talbot J P.A new method to derive rail roughness from axle-box vibration accounting for track stiffness variations and wheel-to-wheel coupling [J].Mechanical Systems and Signal Processing,2023,192:110232.
• [28] Lin T T,Ren Z J,Zhu L B,et al.A systematic review of multisensor information fusion for equipment fault diagnosis [J].IEEE Transactions on Instrumentation and Measurement,2025,74:3507848.
• [29] Xie T L,Huang X F,Choi S K.Intelligent mechanical fault diagnosis using multisensor fusion and convolution neural network [J].IEEE Transactions on Industrial Informatics,2022,18(5):3213-3223.
• [30] TG/CL 127—2025 铁路动车组运用维修规则[S].TG/CL 127—2025 Rules for the operation and maintenance of railway electric multiple units[S].
• [31] 许文天，梁树林，池茂儒，等.基于频响函数的车轮多边形磨耗车载定量诊断方法 [J].中国机械工程，2025,36(5):942-953.Xu Wentian,Liang Shulin,Chi Maoru,et al.Wheel polygonal wear on-board quantitative diagnostic method based on frequency response function [J].China Mechanical Engineering,2025,36(5):942-953.
• [32] Zhai W M.Vehicle-track coupled dynamics:theory and applications [M].Beijing:Science Press,2020.
• [33] Wu H Y,Triebe M J,Sutherland J W.A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing:a rotary system application [J].Journal of Manufacturing Systems,2023,67:439-452.