基于多源加权频谱重构模型的轴承故障诊断方法

doi:10.3901/JME.260727

机械工程学报 ›› 2026, Vol. 62 ›› Issue (16): 406-418.doi: 10.3901/JME.260727

• 特邀专辑：轨道运载装备动态设计理论与运维技术 • 上一篇

扫码分享

基于多源加权频谱重构模型的轴承故障诊断方法

胡忠硕^1,2,3, 杨建伟^1,3, 姚德臣^1,3, 王金海^1,3, 霍纪元^1,3, 孙润韬^1,2,3, 任宇腾^1,3

1. 北京建筑大学机电与车辆工程学院北京 100044;
2. 北京交通大学机械与电子控制工程学院北京 100044;
3. 北京建筑大学城市轨道交通车辆服役性能保障北京市重点实验室北京 100044

收稿日期:2025-08-14 修回日期:2026-03-03 发布日期:2026-10-14
作者简介:胡忠硕，男，1996年出生，博士研究生。主要研究方向为旋转机械故障诊断。E-mail：huzhongshuo@163.com;杨建伟(通信作者)，男，1971年出生，博士，教授，博士研究生导师。主要研究方向为城轨车辆系统动力学、振动噪声分析与控制、旋转机械故障诊断。E-mail：yangjianwei@bucea.edu.cn
基金资助:
国家自然科学基金(52272385、52205083)和北京市自然科学基金(L241033)资助项目。

Bearing Fault Diagnosis Method Based on Multi-source Weighted Spectrum Reconstruction Model

HU Zhongshuo^1,2,3, YANG Jianwei^1,3, YAO Dechen^1,3, WANG Jinhai^1,3, HUO Jiyuan^1,3, SUN Runtao^1,2,3, REN Yuteng^1,3

1. School of Mechanical-electronic and Vehicle Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044;
2. School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044;
3. Beijing Key Laboratory of Performance Guarantee on Urban Rail Transit Vehicles, Beijing University of Civil Engineering and Architecture, Beijing 100044

Received:2025-08-14 Revised:2026-03-03 Published:2026-10-14

摘要/Abstract

摘要： 滚动轴承是城市轨道列车的关键部件，其健康监测对运营安全具有重大工程意义。然而，单一测点信号易受轮轨冲击、系统部件振动等噪声影响。针对上述问题，提出多源加权频谱重构(Multi-source weighted spectrum reconstruction，MWSR)模型。首先，对计算分析多测点信息的加权熵谱子带能量分布，动态调整子带边界使其接近预设目标的能量分布；其次，构建基于自回归滑动平均(Auto-regressive moving average model，ARMA)模型的多测点间频带耦合关系，迭代各测点信息的子带边界；最后设计基于子带边界的滤波器组，对多测点信号进行融合重构，实现轴承故障特征的增强。通过包络谱实现对轴承的故障诊断。与传统信号分解方法相比，所提方法在不同信噪比下故障特征能量比(Fault characteristic energy ratio，FCER)均保持最高水平，故障特征更具可辨识性，能够为故障诊断提供高辨识度的故障特征。

关键词: 多源信息融合, 故障诊断, 自回归滑动平均模型, 加权谱熵

Abstract: Rolling bearings are critical components of urban rail trains, and their health monitoring holds significant engineering importance for operational safety. However, signals from a single measurement point are susceptible to noise interference such as wheel-rail impacts and vibrations from system components. Therefore, this paper proposes a multi-source weighted spectrum reconstruction(MWSR) model. First, the sub-band energy distribution of the weighted entropy spectrum from multi-point measurement information is calculated and analyzed to dynamically adjust the sub-band boundaries, making them approximate the energy distribution of a preset target. Second, a frequency-band coupling relationship between multiple measurement points is constructed based on an ARMA model, iteratively refining the sub-band boundaries for each measurement point’s information. Finally, a filter bank based on the optimized sub-band boundaries is designed to fuse and reconstruct signals from multiple measurement points, thereby enhancing bearing fault features. Fault diagnosis is achieved through envelope spectrum analysis. Compared to traditional signal decomposition methods, the proposed method maintains the highest fault characteristic energy ratio(FCER) across varying signal-to-noise ratios(SNRs), resulting in more identifiable fault characteristics that provide highly distinguishable features for fault diagnosis.

Key words: multi-source information fusion, fault diagnosis, autoregressive moving average model, weighted spectral entropy

中图分类号:

TH17

胡忠硕, 杨建伟, 姚德臣, 王金海, 霍纪元, 孙润韬, 任宇腾. 基于多源加权频谱重构模型的轴承故障诊断方法[J]. 机械工程学报, 2026, 62(16): 406-418.

HU Zhongshuo, YANG Jianwei, YAO Dechen, WANG Jinhai, HUO Jiyuan, SUN Runtao, REN Yuteng. Bearing Fault Diagnosis Method Based on Multi-source Weighted Spectrum Reconstruction Model[J]. Journal of Mechanical Engineering, 2026, 62(16): 406-418.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260727

http://www.cjmenet.com.cn/CN/Y2026/V62/I16/406

参考文献

[1] 王彪，秦勇，贾利民，等. 监测数据驱动的城轨列车轴箱轴承剩余寿命预测[J]. 西南交通大学学报，2024，59(1)：229-238. WANG Biao，QIN Yong，JIA Limin，et al. Monitoring data-driven prediction of remaining useful life ofaxle-box bearings for urban rail transit trains[J]. Journal of Southwest Jiaotong University，2024，59(1)：229-238.
[2] 白永亮. 城轨列车轮对-轴箱故障表征与解耦算法研究[D]. 北京：北京交通大学，2021. BAI Yongliang. Research on the representation and decoupling algorithms of urban rail train wheelset-axle box fault[D]. Beijing：Beijing Jiaotong University，2021.
[3] IUNUSOVA E，GONZALEZ M K，SZIPKA K，et al. Early fault diagnosis in rolling element bearings：Comparative analysis of a knowledge-based and a data-driven approach[J]. Journal of Intelligent Manufacturing，2024，35(5)：2327-2347.
[4] 李军宁，温金鹏，白梦莎，等. 多源信号融合的滚动轴承故障诊断研究综述[J]. 西安工业大学学报，2025，45(4)：516-529. LI Junning，WEN Jinpeng，BAI Mengsha，et al. Review of bearing fault diagnosis based on multi-signal fusion[J]. Journal of Xi’an Technological University，2025，45(4)：516-529.
[5] 侯俊琪，肖松华，孙蓓蓓. 基于能量分布的自适应超小波变换在轴承故障诊断中的应用[J]. 振动与冲击，2025，44(15)：224-234. HOU Junqi，XIAO Songhua，SUN Beibei. Application of energy distribution-based adaptive superlet transform in bearing fault diagnosis[J]. Journal of Vibration and Shock，2025，44(15)：224-234.
[6] 盛嘉玖，陈果，贺志远，等. 一种用于滚动轴承故障诊断的VMD参数优化方法[J/OL]. 振动工程学报，2025：1-12. https://doi.org/10.16385/j.cnki.issn.1004-4523.202410048. SHENG Jiajiu，CHEN Guo，HE Zhiyuan，et al. A VMD parameter optimization method for rolling bearing fault diagnosis[J/OL]. Journal of Vibration Engineering，2025：1-12. https://doi.org/10.16385/j.cnki.issn.1004-4523.202410048.
[7] 崔朝阳，杨绍普，顾晓辉，等. 基于多层联合分布自适应的高速列车轴箱轴承故障诊断方法[J]. 铁道学报，2025，47(8)：65-72. CUI Zhaoyang，YANG Shaopu，GU Xiaohui，et al. Fault diagnosis method for axlebox bearings of high-speed trains based on multi-layer joint distribution adaptation[J]. Journal of the China Railway Society，2025，47(8)：65-72.
[8] WANG Simai，WANG Meiling，GONG Zifeng，et al. Liquid circular angular accelerometer-based incipient bearing fault diagnosis[J]. Measurement，2025，241：115584.
[9] WU Chunming，ZHENG Shupeng. Fault diagnosis method of rolling bearing based on MSCNN-LSTM[J]. Computers，Materials & Continua，2024，79(3)：4395-4411.
[10] SONG D，BAEK A，KIM N. Forecasting stock market indices using padding-based fourier transform denoising and time series deep learning models[J]. IEEE Access，2021，9：83786-83796.
[11] CHEN Bingyan，ZHANG Weihua，GU J，et al. Product envelope spectrum optimization-gram：An enhanced envelope analysis for rolling bearing fault diagnosis[J]. Mechanical Systems and Signal Processing，2023，193：26.
[12] YAN Ruqiang，SHANG Zuogang，XU Hong，et al. Wavelet transform for rotary machine fault diagnosis：10 Years revisited[J]. Mechanical Systems and Signal Processing，2023，200：24.
[13] LIU Minghui，XIONG Jianbin，LI Chunlin，et al. Application of improved adaptive method of CEEMD and data-drive in fault diagnosis[J]. Robotic Intelligence and Automation，2024，44(6)：770-782.
[14] YANG Jianwei，HUO Jiyuan，YAO Dechen. Rail corrugation detection based on optimal position window and weighted-bandwidth mode decomposition[J]. Measurement，2025，255：13.
[15] ZHANG Zhenghe，ZHU Jiahao，LIU Nan，et al. Signal fusion method for networked radar motivated by data fusion[J]. IEEE Sensors Journal，2025，25(1)：951-961.
[16] LI Jingjing，WANG Qiang. Multi-modal bioelectrical signal fusion analysis based on different acquisition devices and scene settings：Overview，challenges，and novel orientation[J]. Information Fusion，2022，79：229-247.
[17] ZHANG Tianhong，XU Limei，YANG Enpin，et al. A novel method of signal fusion based on dimension expansion[J]. Circuits Systems and Signal Processing，2018，37(10)：4295-4318.
[18] MUSLUOGLU C，BERTRAND A. A unified algorithmic framework for distributed adaptive signal and feature fusion problems-part I：Algorithm derivation[J]. IEEE Transactions on Signal Processing，2023，71：1863-1878.
[19] LIU Kang，LIU Weijian，HE Minghao，et al. A high-precision frequency estimation algorithm based on multi-segment signal fusion[J]. IET Radar Sonar and Navigation，2023，17(1)：128-138.
[20] YANG Jianwei，BAI Yongliang，WANG Jinhai，et al. Tri-axial vibration information fusion model and its application to gear fault diagnosis in variable working conditions[J]. Measurement Science and Technology，2019，30(9)：10.
[21] SHI Huaitao，LI Yangyang，BAI Xiaotian，et al. A two-stage sound-vibration signal fusion method for weak fault detection in rolling bearing systems[J]. Mechanical Systems and Signal Processing，2022，172：22.
[22] 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.
[23] 李方烜. 基于MODWPT平方包络峭度谱的轴承声信号故障诊断方法[J]. 铁道机车车辆，2024，44(1)：16-23. LI Fangxuan. Application of MODWPT square envelope kurtosis spectrum in fault diagnosis of the rolling bearing acoustic signal[J]. Railway Locomotive & Car，2024，44(1)：16-23.
[24] NOGUCHI Y，YAMADA T. Topology optimization for acoustic structures considering viscous and thermal boundary layers using a sequential linearized Navier- Stokes model[J]. Computer Methods in Applied Mechanics and Engineering，2022，394：114863.
[25] LIANG Rubing，XIA Qiang，PAN Jiazhu，et al. Testing a linear ARMA model against threshold-ARMA models：A Bayesian approach[J]. Communications in Statistics- simulation and Computation，2017，46(2)：1302-1317.
[26] 赵振兵，李延旭，甄珍，等. 结合KL散度和形状约束的Faster R-CNN典型金具检测方法[J]. 高电压技术，2020，46(9)：3018-3026. ZHAO Zhenbing，LI Yanxu，ZHEN Zhen，et al. Typical fittings detection method with faster R-CNN combining kl divergence and shape constraints[J]. High Voltage Engineering，2020，46(9)：3018-3026.
[27] MIAO Yonghao，ZHANG Boyao，LI Chenhui，et al. Feature mode decomposition：New decomposition theory for rotating machinery fault diagnosis[J]. IEEE Transactions on Industrial Electronics，2022，70(2)：1949-1960.
[28] 雷亚国，韩天宇，王彪，等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报，2019，55(16)：1-6. LEI Yaguo，HAN Tianyu，WANG Biao，et al. XJTU-SY Rolling element bearing accelerated life test datasets：A tutorial[J]. Journal of Mechanical Engineering，2019，55(16)：1-6.
[29] SUN Runtao，YANG Jianwei，YAO Dechen，et al. A new method of wheelset bearing fault diagnosis[J]. Entropy，2022，24(10)：1381.

基于多源加权频谱重构模型的轴承故障诊断方法

Bearing Fault Diagnosis Method Based on Multi-source Weighted Spectrum Reconstruction Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李志农, 余紫莹, 王奉涛, 李喆. 小波赋能联邦学习的机械故障诊断[J]. 机械工程学报, 2026, 62(9): 182-190.
[2]	潘海洋, 陈春安, 郑近德, 童靳于, 程健. 基于多任务孪生核矩阵机的机械故障诊断方法[J]. 机械工程学报, 2026, 62(9): 191-200.
[3]	郑思远, 李晓宇, 魏欣宇, 魏卓豪. 基于磁场的电池外部短路故障诊断方法[J]. 机械工程学报, 2026, 62(6): 220-227.
[4]	王维民, 刘延振. 基于叶尖监测的航空发动机故障诊断与预警技术研究综述[J]. 机械工程学报, 2026, 62(2): 1-16.
[5]	王海明, 刘永强, 杨绍普, 魏沐雨, 魏海石, 李昊, 王艳丽. 高速列车故障诊断与健康管理技术研究综述[J]. 机械工程学报, 2026, 62(16): 343-354.
[6]	郭志斌, 谢劲松, 王田天, 潘彤阳, 牛步钊. 专家知识嵌入的高泛化可解释高速列车转向架轴箱轴承故障诊断大模型[J]. 机械工程学报, 2026, 62(16): 355-368.
[7]	李乃鹏, 张涛, 雷亚国, 李响, 杨彬, 江金泽. 数字孪生模型驱动的永磁同步电机偏心故障定量诊断方法[J]. 机械工程学报, 2026, 62(14): 59-71.
[8]	王强, 尚泽明, 王志勇, 任泽, 殷国栋. 基于改进SDP-CNN方法的永磁轮毂电机退磁故障诊断研究[J]. 机械工程学报, 2026, 62(14): 364-375.
[9]	刘志亮, 张潇楠, 陈志鹏, 唐瑜君, 梅松政, 钟春波, 顾小明, 左明健. 基于变分循环冲击模态分解的氢气压缩机增压缸同型多源混叠信号分析方法[J]. 机械工程学报, 2026, 62(13): 193-206.
[10]	江星星, 宋秋昱, 邢黄坤, 张龙, 叶小芬, 朱忠奎. 感知代理学习开集域泛化机械故障智能诊断方法[J]. 机械工程学报, 2026, 62(13): 220-230.
[11]	王振亚, 刘韬, 吴峰崎, 伍星. 多模态机制改进差分自编码的时变速滚动轴承数据增强方法[J]. 机械工程学报, 2026, 62(11): 353-361.
[12]	吴艳灵, 汤宝平, 邓蕾, 付豪. 低通筛选优化神经架构搜索的风电齿轮箱边缘侧故障诊断方法[J]. 机械工程学报, 2025, 61(7): 361-372.
[13]	雷亚国, 李熹伟, 李响, 李乃鹏, 杨彬. 面向机械设备通用健康管理的智能运维大模型[J]. 机械工程学报, 2025, 61(6): 1-13.
[14]	韩长坤, 卢威, 宋浏阳, 王华庆. 特征原子稀疏解析的多状态机械故障诊断方法[J]. 机械工程学报, 2025, 61(6): 33-42.
[15]	刘文朋, 杨绍普, 刘永强, 顾晓辉, 王久健. 轮轨激励下高速列车轴箱轴承故障诊断方法研究[J]. 机械工程学报, 2025, 61(6): 249-259.