A new fault diagnosis approach for bearing based on multi-scale entropy of the optimized VMD

HUANG Da-rong1 KE Lan-yan1 LIN Meng-ting1 SUN Guo-xi2

(1.College of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China 400074)
(2.Guangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis, Guangdong University of Petrochemical Technology, Maoming, Guangdong Province, China 525000)

【Abstract】It is well known that the parameter K of variational mode decomposition (VMD) needs to be preset according to prior knowledge without theoretical support for optimal setting. Thus, for the existing fault diagnosis methods of bearings based on VMD, the correctness of characteristic extraction and accuracy of fault diagnosis are extremely difficult to be guaranteed. A novel collaborative diagnosis approach of petrochemical equipment for bearing based on optimal VMD and multiscale entropy (MSE) is proposed to solve this problem. Firstly, because of the difficulty in optimizing the decomposition parameter K of VMD, an effective estimation model of K is constructed according to the frequency distribution characteristics of the decomposition components of local mean decomposition (LMD). Then, a novel characteristic extraction technique combining MSE with linear discriminant analysis (LDA) is proposed to establish characteristic samples. Furthermore, aimed at the fault features of small samples for bearing, support vector machine (SVM) is introduced to identify the fault characteristics. Finally, the bearing fault data collected from the simulation platform of the petrochemical equipment laboratory is used to verify the effectiveness and engineering practicability of the proposed approach. The comparative analyses show that the proposed algorithm can effectively diagnose the faults of the bearing with good engineering operability and scalability.

【Keywords】 bearing faults; VMD algorithm; MSE algorithm; LDA algorithm; SVM fault characteristics recognition;


【Funds】 National Natural Science Foundation of China (61663008, 61573076, 61473094, 61304104, 61004118) Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry (2015-49) Support Program for Outstanding Talents of Higher Education of Chongqing, China (2014-18) Open Fund Project of the Key Laboratory of Petrochemical Equipment Fault Diagnosis of Guangdong Province, China (GDUPKLAB201501/GDUPKLAB201604) Characteristic Innovation Projects of Universities in Guangdong Province, China (201463104) Science and Technology Research Project of Chongqing Municipal Education Commission, China (KJ1705139/KJZD-K201800701)

Download this article


    [1] Luo H, Yang X, Krueger M, et al. A plug-and-play monitoring and control architecture for disturbance compensation in rolling mills [J]. IEEE/ASME Transactions on Mechatronics, 2018, 23 (1): 200–210.

    [2] Ricci F, Rokach L, Shapira B. Recommender systems handbook [M]. Berlin: Springer, 2011: 1–35.

    [3] Dong H, Wang Z, Ding S X, et al. On H-infinity estimation of randomly occurring faults for a class of nonlinear time-varying systems with fading channels [J]. IEEE Transactions on Automatic Control, 2016, 61 (2):479–484.

    [4] Wen C L, Lv F Y, Bao Z J, et al. A review of data driven-based incipient fault diagnosis [J]. Acta Automatica Sinica, 2016, 42 (9): 1285–1299 (in Chinese).

    [5] Liu Z H, Meng X D, Lu B L, et al. Fault diagnosis method of wind turbine rolling bearing based on a node optimized DAG-LDM [J]. Control and Decision, 2019, 34 (7): 1394–1400 (in Chinese).

    [6] Tian K, Zhang T, Ai Y B, et al. Induction motors dynamic eccentricity fault diagnosis based on the combined use of WPD and EMD-simulation study [J]. Applied Sciences-basel, 2018, 8 (10): 1–15.

    [7] Li Y, Xu M, Liang X, et al. Application of bandwidth EMD and adaptive multiscale morphology analysis for incipient fault diagnosis of rolling bearings [J]. IEEE Transactions on Industrial Electronics, 2017, 64 (8): 6506–6517.

    [8] Yu X, Dong F, Ding E J, et al. Rolling bearing fault diagnosis using modified LFDA and EMD with sensitive feature selection [J]. IEEE Access, 2018, 99 (6): 3715–3730.

    [9] Li Y, Liang X, Yang Y, et al. Early fault diagnosis of rotating machinery by combining differential rational spline-based LMD and K-L divergence [J]. IEEE Transactions on Instrumentation & Measurement, 2017, 99 (11): 1–14.

    [10] Wang Z, Wang J, Kou Y, et al. Weak fault diagnosis of wind turbine gearboxes based on MED-LMD [J]. Entropy, 2017, 19 (6): 1–15.

    [11] Shi Z L, Song W Q, Taheri S. Improved LMD, permutation entropy and optimized K-means to fault diagnosis for roller bearings [J]. Entropy, 2016, 18 (3): 1–11.

    [12] Liu C, Cheng G, Chen X, et al. Planetary gears feature extraction and fault diagnosis method based on VMD and CNN [J]. Sensors, 2018, 18 (5): 1–20.

    [13] Liu Y, Wang J, Li Y, et al. Feature extraction method based on VMD and MFDFA for fault diagnosis of reciprocating compressor valve [J]. Journal of Vibro engineering, 2017, 19 (8): 6007–6020.

    [14] Jiang X X, Shen C Q, Shi J J. Initial center frequency-guided VMD for fault diagnosis of rotating machines [J]. Journal of Sound and Vibration, 2018, 435: 36–55.

    [15] Huang D R, Ke L Y, Mi B, et al. A new incipient fault diagnosis method combining improved RLS and LMDalgorithm for rolling bearings with strong background noise [J]. IEEE Access, 2018, 6 (1): 26001–26010.

    [16] Yin J T, Xie Y F, Yang C H. Monitoring of incipient rotor bars broken fault in traction motors based on RVMD method [J]. Control and Decision, 2018, 33 (3): 497–502 (in Chinese).

    [17] Tang G J, Wang X L, He Y L. A novel method of fault diagnosis for rolling bearing based on dual tree complex wavelet packet transform and improved multiscale permutation entropy [J]. Mathematical Problems in Engineering, 2016 (6): 1–13.

    [18] Zheng J D, Jiang Z W, Pan H Y. Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing [J]. Measurement, 2018, 129: 332–342.

    [19] Huang D R, Chen C S, Sun G X, et al. Linear discriminant analysis and back propagation neural network cooperative diagnosis method for multiple faults of complex equipment bearings [J]. Acta Armamentarii, 2017, 38 (8): 1649–1657 (in Chinese).

    [20] Bazdar A, Kazemzadeh R B, Niaki S T A.Fault diagnosis within multistage machining processes using linear discriminant analysis: A case study in automotive industry [J]. Quality Technology & Quantitative Management, 2017, 14 (2): 1–16.

    [21] Xiao Y Q, He Y G, Liu J Q, et al. Fault diagnosis of analog circuit by integrating principal component analysis with linear discriminant analysis [J]. Control and Decision, 2015, 30 (7): 1321–1324 (in Chinese).

This Article


CN: 21-1124/TP

Vol 35, No. 07, Pages 1631-1638

July 2020


Article Outline


  • 0 Introduction
  • 1 Adaptive decomposition model of fault signal of bearing
  • 2 Extraction model of fault features based on MSE and LDA
  • 3 Recognition of fault features of bearing based on SVM
  • 4 Experimental verification
  • 5 Conclusions
  • References