多频谱融合评价方法及高铁转向架轴承故障诊断方法

doi:10.3901/JME.260038

摘要/Abstract

摘要： 转向架是高铁的重要动力传输单元，转向架轴承作为转向架中的承力元件，长期承受交变载荷，是极易发生故障的部位。现有用于滚动轴承故障诊断的频域分析方法对适用条件有严格的要求，如快速谱峭度方法在分析具有较大干扰信息或是背景噪声的信号时，极易导致方法的失效，大大限制了相关方法在实际工程中的广泛应用。针对上述问题，提出多频谱融合评价的故障诊断与决策方法。构建一种频域分析方法的加权评价准则，从诊断效果、稳定性以及计算时间等三个方面进行构建，实现算法工程适配性的量化。提出一种频谱评价准则，实现对频域分析方法诊断效果的评价。针对高铁运营中的数据积累与完备的两个阶段，分别通过频谱特征降维融合以及最优化Fisher判别比进行频谱评价赋权，以获得具有最好诊断效果的融合频谱。通过数据采集试验对方法进行了有效性验证，表明该方法具有较好的工程适用性及鲁棒性。

关键词: 高铁, 转向架轴承, 频谱评价, 频域分析方法

Abstract: The rail bogie is recognized as an important power transmission unit in high-speed trains, and the bogie bearing, serving as a load-bearing element within it, is subjected to prolonged alternating loads and is highly prone to failure. Existing frequency domain analysis methods for rolling bearing fault diagnosis are limited by strict applicability conditions. For example, the fast kurtogram method often fails when analyzing signals contaminated by interference or excessive background noise, significantly limiting the widespread practical application of those methods. To address these limitations, a fault diagnosis and decision-making method based on multi-spectrum fusion evaluation is developed. A weighted evaluation criterion is constructed for frequency domain analysis methods, considering three aspects-diagnostic effect, stability, and calculation time-to quantify their engineering suitability. Furthermore, a spectrum evaluation criterion is established to assess the diagnostic effectiveness of frequency domain analysis methods. To accommodate the distinct requirements of data accumulation and completion phases in high-speed rail operation, the proposed spectrum evaluation criterion incorporates downscaled spectral feature fusion and an optimized Fisher's discriminant ratio, respectively. This facilitates the selection of the fusion spectrum yielding optimal diagnostic performance. The validity of the method is confirmed through data collection experiments. The results demonstrate its good engineering applicability and robustness.

Key words: high-speed railway, bogie bearing, spectrum evaluation, frequency domain analysis method

中图分类号:

TP277

张兴武, 孙浩瑜, 李妍琦, 刘一龙, 陈雪峰. 多频谱融合评价方法及高铁转向架轴承故障诊断方法[J]. 机械工程学报, 2026, 62(2): 73-90.

ZHANG Xingwu, SUN Haoyu, LI Yanqi, LIU Yilong, CHEN Xuefeng. Multi-spectrum Fusion Evaluation Method and Fault Diagnosis Method for High-speed Rail Bogie Bearings[J]. Journal of Mechanical Engineering, 2026, 62(2): 73-90.

参考文献

[1] 金学松，赵国堂，梁树林，等. 高速铁路轮轨磨损特征、机理、影响和对策—车轮踏面横向磨耗[J]. 机械工程学报， 2018， 54(4)： 3-13. JIN Xuesong， ZHAO Guotang， LIANG Shulin， et al. Characteristics ， mechanisms ， influences and counter measures of high speed wheel/rail wear： Transverse wear of wheel tread[J]. Journal of Mechanical Engineering， 2018， 54(4)： 3-13.
[2] 杜家豪，秦娜，贾鑫明，等. 基于联邦学习的多线路高速列车转向架故障诊断[J]. 西南交通大学学报， 2022， 1： 185-192. DU Jiahao， QIN Na， JIA Xinming， et al. Fault diagnosis of multiple railway high speed train bogies based on federated learning[J]. Journal of Southwest Jiaotong University， 2022， 1： 185-192.
[3] 杨绍普，顾晓辉，刘永强，等. 转向架关键运动部件动力学机理与故障诊断研究综述[J]. 机械工程学报， 2023， 59(20)： 225-243. YANG Shaopu， GU Xiaohui， LIU Yongqiang， et al. Review of dynamic mechanism and fault diagnosisfor key rotating components of bogies[J]. Journal of Mechanical Engineering， 2023， 59(20)： 225-243.
[4] CHEN Xuefeng， WANG Shibin， QIAO Baijie， et al. Basic researchon machinery fault diagnostics： Past， present， and future trends[J]. Frontiers of Mechanical Engineering， 2018， 13(2)： 264-291.
[5] KIM S W， KONG J H， LEE S W， et al. Recent advances of artificial intelligence in manufacturing industrial sectors： A review[J]. International Journalof Precision Engineering and Manufacturing， 2022， 23(1)： 111-129.
[6] 覃嘉恒，张鹰. 实信号的FFT在齿轮减速器故障诊断系统中的应用[J]. 大众科技， 2010， 7： 115-116， 122. TAN Jiaheng， ZHANG Ying. Application of real signal FFT in gear reducer fault diagnosis system[J]. Popular Science & Technology. 2010， 7： 115-116， 122.
[7] 李辉，郑海起，唐力伟. 阶次包络谱在轴承故障诊断中的应用[J]. 机械强度， 2007， 29(3)： 351-355. LI Hui， ZHENG Haiqi， TANG Liwei. Application oforder envelope analysis to bearing fault diagnosis[J]. Journal of Mechanical Strength， 2007， 29(3)： 351-355.
[8] 陈果，于明月，刘永泉，等. 基于倒频谱分析的航空发动机转静碰摩部位识别[J]. 机械工程学报， 2014， 50(7)： 32-38. CHEN Guo， YU Mingyue， LIU Yongquan， et al. Research on fault diagnosis method of Axle-box bearing of high-speed train under wheel-rail excitation[J]. Journal of Mechanical Engineering， 2014， 50(7)： 32-38.
[9] XU Xiaoli， JIANG Zhanglei， LIANG Hao， et al. Fault diagnosis method of rolling bearing based on 1.5-dimensional envelope spectrum[C] // Proceedings of the 14th IEEE International Conference on Electronic Measurement and Instruments (ICEMI)， Nov 01-03， 2019， Changsha， China： IEEE， 2019： 1163-1168.
[10] XU Lang， CHATTERTON S， PENNACCHI P. Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum[J]. Mechanical Systems and Signal Processing， 2021， 148： 107174.
[11] TANG Daijie， BI Fengrong， LIN Jiewei， et al. Adaptive recursive variational mode decomposition for multiple engine faults detection[J]. IEEE Transactions on Instrumentation and Measurement， 2022， 71： 1-11.
[12] NAIMA G， ELIAS H A， SALAH S. An improved fast kurtogram based on an optimal wavelet coefficient for wind turbine gear fault detection[J]. Journal of Electrical Engineering & Technology， 2022， 17(2)： 1335-1346.
[13] ZHANG Xin， MIAO Qiang， ZHANG Heng， et al. A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery[J]. Mechanical Systems and Signal Processing， 2018， 108： 58-72.
[14] 张忠强，张新，王家序，等. 基于重加权谱峭度方法的航空发动机故障诊断[J]. 航空学报， 2022， 43(9)： 148-157. ZHANG Zhongqiang， ZHANG Xin， WANG Jiaxu， et al. Reweighted kurtogram for aero-engine fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica， 2022， 43(9)： 148-157.
[15] ANTONI J. Fast computation of the kurtogram for the detection of transient faults[J]. Mechanical Systems and Signal Processing， 2007， 21(1)： 108-124.
[16] 申弢，黄树红，韩守木，等. 旋转机械振动信号的信息熵特征[J]. 机械工程学报， 2001， 37(6)： 94-98. SHEN Tao， HUANG Shuhong， HAN Shoumu， et al. Extracting information entropy features for rotating machinery vibration signals[J]. Journal of Mechanical Engineering， 2001， 37(6)： 94-98.
[17] 李红贤，汤宝平，韩延，等. 基于增强熵权峭度图的滚动轴承最优频带解调的故障诊断[J]. 振动与冲击，2019， 38(17)： 24-31， 50. Hongxian， TANG Baoping， HAN Yan， et al. Fault diagnosis of rolling bearings using optimal demodulation frequency bandbased on enhanced entropy weight kurtosis graph[J]. Journalof Vibration and Shock， 2019： 24-31， 50.
[18] 谢平. 故障诊断中信息熵特征提取及融合方法研究[D]. 秦皇岛：燕山大学， 2006. XIE Ping. Study on information entropy feature extraction and fusion methods in fault diagnosis[D]. Qinhuangdao： Yanshan University， 2006.
[19] 陈是扦，彭志科，周鹏. 信号分解及其在机械故障诊断中的应用研究综[J]. 机械工程学报， 2020， 56(17)： 91-107. CHEN Shiqian， PENG Zhike， ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis[J]. Journal of Mechanical Engineering， 2020， 56(17)： 91-107.
[20] LI Yongbo ， XU Minqiang ， LIANG Xihui ， et al. Application of band width EMD and adaptive multiscale morphology analysis for incipient fault diagnosis of rolling bearings[J]. IEEE Transactions on Industrial Electronics， 2017， 64(8)： 6506-6517.
[21] 潘明清，周晓军，杨辰龙，等. 基于信息谱熵的支持向量机机械状态识别[J]. 传感技术学报， 2005(2) ： 277-280. PAN Mingqing， ZHOU Xiaojun， YANG Chenlong， et al. Application of support vector machine based on information spectrum entropy in machine state ldentification[J]. Chinese Journal of Sensors and Actuators， 2005(2)： 277-280.
[22] QU Liangsheng ， LI Liangming ， LEE J. Enhanced diagnostic certainty using information entropy theory[J]. Advanced Engineering Informatics ， 2003， 17(3-4) ： 141-150.
[23] 孙鲜明，刘欢，赵新光，等. 基于瞬时包络尺度谱熵的滚动轴承早期故障奇异点识别及特征提取[J]. 机械工程学报， 2017， 53(3)： 73-80. SUN Xianming， LIU Huan， ZHAO Xingung， et al. Singular point recognition and feature extraction for incipient bearing fault based on instantaneous envelope scalogram entropy[J]. Journal of Mechanical Engineering， 2017， 53(3)： 73-80.
[24] PAN Yunna ， CHEN Jianjun ， LI Xiaoling. Spectral entropy： A comple mentary index for rolling element bearing performance degradation assessment[J]. Proceedings of the Institution of Mechanical Engineers， Part C： Journal of Mechanical Engineering Science， 2009， 223(5)： 1223-1231.
[25] ZHANG Zhenyue， ZHA Hongyuan. Nonlinear dimension reduction via local tangent space alignment[C] // International Conference on Intelligent Data Engineering and Automated Learning， March 21-23， 2003， Berlin， Heidelberg： Springer Berlin Heidelberg， 2003： 477-481.
[26] 苏祖强，汤宝平，刘自然，等. 基于正交半监督局部Fisher判别分析的故障诊断[J]. 机械工程学报， 2014， 50(18)： 7-13. SU Zuqiang， TANG Baoping， LIU Ziran， et al. Fault diagnosis method based on orthogonal semi-supervised local fisher discriminant analysis[J]. Journal of Mechanical Engineering， 2014， 50(18)： 7-13.
[27] WU Ping， LOU Siwei， ZHANG Xujie， et al. Data-driven fault diagnosis using deep canonical variate analysis and fisher discriminant analysis[J]. IEEE Transactions on Industrial Informatics， 2020， 17(5)： 3324-3334.