Fault Diagnosis Method of Rolling Bearings Based on Improved Refined Composite Multiscale Sample Entropy and Bayesian Network

doi:10.3969/j.issn.1004-132X.2025.12.018

Abstract

Abstract:

To address the issues of traditional MSE， such as the loss of feature information during the coarse-graining processes and the difficulty in extracting feature information from fault signals at large scale factors， a method for rolling bearing fault diagnosis was proposed based on improved refined composite multiscale sample entropy（IRCMSE） combined with an AOA optimized Bayesian network. The traditional coarse-graining processes， which involved averaging， were replaced with a cross-sampling method to obtain time series at each scale， and the method of calculating entropy values at different scales was changed to extract feature information from the time series. IRCMSE was used to extract the fault feature information of rolling bearings， forming fault feature samples. These fault feature samples were then input into the Bayesian network model optimized by AOA for fault recognition. The improved method is experimentally compared with fault diagnosis methods based on MSE， multiscale dispersion entropy， and refined composite multiscale sample entropy （RCMSE）， verifying the feasibility of the proposed method and demonstrating a higher fault recognition rate.

Key words: rolling bearing, multiscale sample entropy （MSE）, fault diagnosis, Bayesian network, arithmetic optimization algorithm（AOA）

摘要：

针对传统多尺度样本熵（MSE）在粗粒化过程中易造成特征信息丢失、在尺度因子较大时故障信号中的特征信息不易提取等问题，提出一种基于改进的精细复合多尺度样本熵（IRCMSE）与算术优化算法（AOA）优化贝叶斯网络的滚动轴承故障诊断方法。将传统粗粒化过程中求均值的处理方式替换为交叉采样的方式，得到每一尺度的时间序列，并改变不同尺度下计算熵值的方法，提取时间序列的特征信息。利用IRCMSE提取滚动轴承故障特征信息，构成故障特征样本，将故障特征样本输入到AOA优化后的贝叶斯网络模型中进行故障识别。将改进方法与基于多尺度样本熵、多尺度散布熵（MDE）和精细复合多尺度样本熵（RCMSE）的故障诊断方法进行对比实验，验证了所提方法的可行性且具有更高的故障识别率。

关键词: 滚动轴承, 多尺度样本熵, 故障诊断, 贝叶斯网络, 算术优化算法

CLC Number:

TH165.3

Zhaojing TONG, Pengchao WANG, Yongkui FAN, Guangyang HAN, Ziqi WANG. Fault Diagnosis Method of Rolling Bearings Based on Improved Refined Composite Multiscale Sample Entropy and Bayesian Network[J]. China Mechanical Engineering, 2025, 36(12): 2952-2959.

仝兆景, 王鹏超, 樊永奎, 韩广洋, 王自奇. 基于改进精细复合多尺度样本熵与贝叶斯网络的滚动轴承故障诊断方法[J]. 中国机械工程, 2025, 36(12): 2952-2959.

Figures/Tables 10

Fig.1 Conventional and improved coarse-graining methods

Fig.2 Comparison between MOA function and Sigmoid function

Fig.3 Frequency domain plot of white noise and pink noise

Fig.4 Comparison of average entropy curves for different entropy methods under various noise conditions

Fig.5 Fault diagnosis flowchart

Tab.1 Bearing fault data

编号	故障类型	故障直径/mm	样本总数
F0	正常	0	50
F1	内圈轻微故障	0.1778	50
F2	滚动体轻微故障	0.1778	50
F3	外圈轻微故障	0.1778	50
F4	内圈中等故障	0.3556	50
F5	滚动体中等故障	0.3556	50
F6	外圈中等故障	0.3556	50
F7	内圈严重故障	0.5334	50
F8	滚动体严重故障	0.5334	50
F9	外圈严重故障	0.5334	50

Fig. 6 Vibration signals under different faults

Fig.7 Comparison of average entropy curves for different entropy methods under various vibration signals

Fig.8 Visualization of PCA processing by different methods

Fig.9 Prediction results of different prediction models

References 13

[1]	于军，丁博，何永军. 基于平均多粒度决策粗糙集和NNBC的滚动轴承故障诊断［J］. 振动与冲击，2019，38（5）：209-215.
	YU Jun， DING Bo， HE Yongjun. Rolling Bearing Fault Diagnosis Based on Mean Multi-granularity Decision Rough Set and NNBC［J］. Journal of Vibration and Shock， 2019，38（5）：209-215.
[2]	ZHANG Xiaoyuan， LIANG Yitao， ZHOU Jianzhong. A Novel Bearing Fault Diagnosis Model Integrated Permutation Entropy， Ensemble Empirical Mode Decomposition and Optimized SVM［J］. Measurement， 2015，69：164-179.
[3]	RICHMAN J S， MOORMAN J R， et al. Physiological Time-series Analysis Using Approximate Entropy and Sample Entropy［J］. American Journal of Physiology， 2000， 278（6）： 2039-2049.
[4]	宋业栋，马光伟，朱小龙，等. 基于强化层次模糊熵的柴油机故障诊断方法［J］. 振动、测试与诊断，2024，44（4）：814-820.
	SONG Yedong， MA Guangwei， ZHU Xiaolong， et al. Vibration Measurement and Comfort Study of Wuhan Railway Station under Multi⁃vibration Sources［J］. Journal of Vibration， Measurement &Diagnosis， 2024，44（4）：814-820.
[5]	郑近德，陈焱，童靳于，等. 精细广义复合多元多尺度反向散布熵及其在滚动轴承故障诊断中的应用［J］. 中国机械工程，2023，34（11）：1315-1325.
	ZHENG Jinde， CHEN Yan， TONG Jinyu， et al. RGCMvMRDE and Its Applications in Rolling Bearing Fault Diagnosis［J］. China Mechanical Engineering， 2023，34（11）：1315-1325.
[6]	肖俊青，金江涛，李春，等. 基于CEEMDAN样本熵与卷积神经网络的轴承故障诊断［J］. 动力工程学报，2022，42（5）：429-436.
	XIAO Junqing， JIN Jiangtao， LI Chun， et al. Bearing Fault Diagnosis Based on CEEMDAN Sample Entropy and Convolutional Neural Network［J］. Journal of Chinese Society of Power Engineering， 2022，42（5）： 429-436.
[7]	谷穗，王红，陈禹州. 双树复小波包与自适应排列熵在轴承故障诊断中的应用［J］. 机械科学与技术，2023，42（7）：1021-1028.
	GU Sui， WANG Hong， CHEN Yuzhou. Application of Double Tree Complex Wavelet Packet and Adaptive Permutation Entropy in Bearing Fault Diagnosis［J］. Mechanical Science and Technology for Aerospace Engineering， 2023，42（7）：1021-1028.
[8]	COSTA M， GOLDBERGER A L， PENG C K. Multiscale Entropy Analysis of Complex Physiologic Time Series［J］. Physical Review Letters，2007，89（6）： 705-708.
[9]	王振亚，姚立纲. 广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法［J］. 中国机械工程，2020，31（20）：2463-2471.
	WANG Zhenya， YAO Ligang. Rolling Bearing Fault Diagnosis Method Based on Generalized Refined Composite Multiscale Sample Entropy and Manifold Learning［J］. China Mechanical Engineering，2020， 31（20）：2463-2471.
[10]	仝兆景，石秀华，王文斌，等. 基于优化分簇贝叶斯网的转子振动故障诊断［J］. 振动、测试与诊断，2014，34（2）：237-241.
	TONG Zhaojing， SHI Xiuhua， WANG Wenbin， et al. Generator Rotor Vibration Fault Diagnosis Based on Optimization Clustering Bayesian Network［J］. Journal of Vibration， Measurement & Diagnosis，2014， 34（2）： 237-241.
[11]	郑磊，蒋玮，胡仁杰，等. 基于小波变换和神经网络的模拟电子电路故障诊断［J］. 南京理工大学学报，2024，48（3）：310-317.
	ZHENG Lei， JIANG Wei， HU Renjie， et al. Fault Diagnosis of Analog Electronic Circuits Based on Wavelet Transform and Neural Network［J］. Journal of Nanjing University of Science and Technology， 2024，48（3）：310-317.
[12]	Zheng B， Liao R， GRZYBOWSKI S， et al. Fault Diagnosis of Power Transformers Using Multi Class Least Square Support Vector Machines Classifiers with Particle Swarm Optimization［J］. IET Electric Power Application，2011，5（9）：691-696.
[13]	黄学雨，罗华. 融合正余弦策略的算术优化算法［J］. 计算机工程与科学，2023，45（7）：1320-1330.
	HUANG Xueyu， LUO Hua. An Arithmetic Optimization Algorithm Integrating Sine-cosine Strategy［J］. Computer Engineering & Science， 2023，45 （7）：1320-1330.

[1]	LUO Ji-Sai, XU De-Ge, SHI Mei-Li. Gearbox Fault Diagnosis with Rotating Speed Fluctuation Based on SVD and Chirplet Path Pursuit Algorithm [J]. J4, 201016, 21(16): 1947-1951.
[2]	HU Chao, LIU Zuo-Min. Research on Rolling Bearing’s Heathcote’s Stick-slip Model Based on Materials Compatibility [J]. J4, 201016, 21(16): 1969-1973.
[3]	Huiming YANG, Xia YANG, Yuqi HUANG. Full-cycle Fatigue Life Prediction of Rolling Bearings Based on Paris Modeling [J]. China Mechanical Engineering, 2025, 36(09): 2003-2010.
[4]	Siqian FENG, Jiaxu WANG, Xin ZHANG, Xinyue HUANG. Rolling Bearing Fault Diagnosis Using a New Resonance Demodulation Method [J]. China Mechanical Engineering, 2025, 36(09): 2022-2031.
[5]	Jian CHEN, Minghui YAN, Pin CHEN. Acoustic Signal Fault Diagnosis Method of Centrifugal Pumps Based on Bayesian Optimization Multiscale DenseNet [J]. China Mechanical Engineering, 2025, 36(09): 2032-2038.
[6]	ZHANG Jianyu, WANG Liuzhen, XIAO Yong, MA Yanan. Fusion of Degradation Feature Information and Remaining Life Prediction for Rolling Bearings [J]. China Mechanical Engineering, 2025, 36(07): 1553-1561.
[7]	SONG Lijun, LIU Songlin, XIN Yu, MA Jinghua, XIE Zhengqiu. Residual Life Prediction for Bearings Based on Bearing Degradation State Assessment and IGAT-BiGRU Network [J]. China Mechanical Engineering, 2025, 36(07): 1562-1572.
[8]	YANG Kang1, CHEN Xuejun1, 2, ZHANG Lei3, LIU Feng3. Cross-domain Fault Diagnosis of Bearings Based on Joint Subdomain Contrast Alignment [J]. China Mechanical Engineering, 2025, 36(05): 1065-1073.
[9]	JIAO Huachao, SUN Wenlei, WANG Hongwei. Bearing Fault Data Generation Method Based on WLT-ACGAN [J]. China Mechanical Engineering, 2025, 36(03): 546-557.
[10]	LI Jimeng, WANG Ze, SHI Qingxin, MENG Zong. Rolling Bearing Fault Diagnosis of Wind Turbines Based on Frequency Domain Group Sparse Model with Graph Regularization Constraints [J]. China Mechanical Engineering, 2024, 35(11): 1909-1919.
[11]	GUO Haiyu1, ZOU Shenggong1, ZHANG Xiaoguang2, 3, 4, LU Fanfan2CHEN Yang2, WANG Han2, XU Xinzhi2. Fault Diagnosis of Rotating Machinery Bearings Based on Multi-source Wavelet Transform Neural Network [J]. China Mechanical Engineering, 2024, 35(11): 2026-2034.
[12]	LI Can1, 2, WANG Guangbin2, 1, ZHAO Shubiao1, 2, ZHONG Zhixian1, ZHANG Hui1, 2. Bearing Fault Diagnosis Method Based on Intensive Distribution Alignment with Open Set Difference [J]. China Mechanical Engineering, 2024, 35(09): 1622-1633.
[13]	ZOU Xiaoyu1, 3, SUN Guoqing1, WANG Zhongbin1, 3, PAN Jie2, LIU Xinhua1, 3, LI Xin1, 3. Bearing Fault Diagnosis of Mining Drilling Rig with Time-frequency-fused Deep Network [J]. China Mechanical Engineering, 2024, 35(08): 1405-1413，1448.
[14]	XIAO Gang, GU Hairui, DONG Jinjin, WANG Qibing, LU Jiawei. Simulation Data-driven Migration Diagnosis Method for Guide Rail Faults in Long-term Service Elevators [J]. China Mechanical Engineering, 2024, 35(01): 125-135.
[15]	YU Shubo, LIU Zhansheng, ZHAO Chen. Dynamics Simulation Data Driven Domain Adaptive Intelligent Fault Diagnosis [J]. China Mechanical Engineering, 2023, 34(23): 2832-2841.