Fault Diagnosis of Ball Bearings by Wavelet Transform and Morlet Support Vector Machine and Comparison them with Empirical Mode Decomposition

Document Type : Mechanics article

Author

Department of Mechanical Engineering, Aligudarz Branch, Islamic Azad University, Aligudarz, Iran

Abstract

In this study, a comparison among the empirical mode decomposition, ensemble empirical mode decomposition and Morlet continuous wavelet transform in fault diagnosis of bearings are performed. A Morlet wavelet support vector machine with one against one strategy that was optimized by a genetic algorithm was used for fault classification. A scale selection criterion based on the maximum relative energy to Renyi entropy ratio is proposed to determine the optimal decomposition scale for wavelet analysis. A comparison between the performances of optimized and non-optimized of support vector machines were also carried out. Vibration signals were collected by a test rig for different fault of a bearing such as normal case, bearing with inner and outer race fault, and bearing with ball fault and combine fault. After the processing of vibration signals their frequency components, several statistical features were extracted from each frequency component as input of wavelet support vector machine for the fault classification of ball bearings. For reducing of time and process of fault diagnosis, optimum feature sets of statistical parameters are selected by Utans method. K-fold cross validation method is used for evaluation of classifier. The results show that continuous wavelet transform with Morlet base has higher accuracy with respect to other methods in fault classification of bearings.

Keywords

Main Subjects

References

[1] J. Wanga, RX. Gao, R. Yan, "A hybrid approach to bearing defect diagnosis in rotary machines", CIRP J. Manuf. Sci. Vol. l5, 2012, pp.357–365.
[2] HDM. De Azevedo,AM.  Araújo, N. Bouchonneau, "A review of wind turbine bearing condition monitoring, State of the art and challenges", Renew. Sustainable Energy Rev., Vol.56, 2016, pp.368–379.
[3]  J. Tlusty, I. Hernandez , S. Smith ,C. Zamudio , "High speed high power spindles with roller bearings", CIRP Ann. Manuf. Technol. Vol.36(1), 1987, pp.267-272.
[4] AM. Al-Ghamd , D. Mba, "A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size", Mech. Syst. Signal Process, Vol. 20(7), 2006, pp.1537–1571.
[5] Y. Lei, "Intelligent Fault Diagnosis and Remaining Useful Life Prediction of Rotating Machinery", Oxford, United Kingdom: Butterworth-Heinemann, 2017.
[6] M. Heidari, S. Shateyi, "Wavelet support vector machine and multi‑layer perceptron neural network with continues wavelet transform for fault diagnosis of gearboxes", J. Vibroeng. Vol. 19(1), 2017,  pp.125‑137.
[7] J.Huang, X. Hu, X. Geng, "An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine", Electr. Pow. Syst. Res. Vol. 81, 2011, pp.400–407.
[8] Y.Gan, L. Sui,  J. Wu,  B. Wang, Q.  Zhang, G. Xiao, "An EMD threshold de-noising method for inertial sensors", Meas. Vol. 49, 2014, pp. 34–41.
[9] J. Singh, AK. Darp, SP. Singh, "Bearing damage assessment using Jensen-Rényi Divergence based on EEMD", Mech. Syst. Signal Process, Vol. 87, 2017, pp.307–339.
[10] Y. Lv,  R. Yuan,  G. Song, "Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing" Mech. Syst. Signal Process, Vol.81,2016, pp.219–234.
[11] M. Kedadouche,  M. Thomas, A. Tahan, "A comparative study between Empirical Wavelet Transforms and Empirical Mode Decomposition Methods: Application to bearing defect diagnosis", Mech. Syst. Signal Process, Vol. 81, 2016, pp. 88-107.
[12] Y. Lei, Z. He, Y. Zi, "Application of the EEMD method to rotor fault diagnosis of rotating machinery" Mech. Syst. Signal Process, Vol. 23(4), 2009, pp.1327-1338.
[13] X. Gong , L. Ding, W. Du , H. Wang, "Gear Fault Diagnosis Using Dual Channel Data Fusion and EEMD Method", Procedia Eng., Vol.74, 2017, pp.918–926.
[14] C. Mishra, AK. Samantaray , G. Chakraborty , "Rolling element bearing fault diagnosis under slow speed operation using wavelet de-noising" Meas. ,Vol.113, 2017, pp.77–86.
]15[ پانیذ تیموری، مهدی مزینانی و راحیل حسینی، «ارائه یک مدل هوشمند قطعه بندی جهت شناسایی همپوشانی سلولی در تصاویر دیجیتال مبتنی بر منطق فازی و تبدیل موجک گسسته جهت شناسایی سرطان معده»، نشریه مدل سازی در مهندسی، شماره 63، دوره 18 ، زمستان1399 ، صفحه 131-150.
]16[ سید امیر فرهاد قاضی میرسعید، محسن معدنی و مهدی زارع، «بهبود سیستم پایش سلامت سازه در شناسایی محل ترک‌های ریز تیر با استفاده از تبدیل موجک و فیلتر دیجیتال»،  نشریه  مدل سازی در مهندسی، شماره 58،  دوره 17،پاییز 1398، صفحه 305-316.
]17[ مصطفی سبزه کار، ریحانه خزاعی، وحیده بابائیان و یونس اکبری، «تشخیص نویسنده از دست‌خط‌های برون‌خط مستقل از زبان نوشتاری مبتنی بر بافت با بهره‌گیری از تبدیل موجک در محیط دو زبانه فارسی – انگلیسی»، نشریه  مدل سازی در مهندسی ، شماره 63 ، دوره 18، زمستان 1399، صفحه 1-13.
[18] WJ. Wang , PD. McFadden, "Application of the wavelet transform to gearbox vibration analysis", ASME, Petroleum Division (Publication) PD, Vol.52,1993, pp.13–20.
[19] WJ. Wang, PD. McFadden, "Application of wavelets to gearbox vibration signals for fault detection", J. Sound Vib. Vol. 192(5),1996, pp.927–939.
[20] WJ. Wang ,PD. McFadden , "Application of orthogonal wavelets to early gear damage detection", Mech. Syst. Signal Process Vol. 9(5), 1995, pp.497–507.
[21] Z.Wu, H. Jiang, K. Zhao, X. Li,"An adaptive deep transfer learning method for bearing fault diagnosis", Meas., Vol.151, 2020, 107227.
[22] DT. Hoang, HJ. Kang, "A survey on Deep Learning based bearing fault diagnosis", Neurocomputing, Vol. 335, 2019, pp.327-335.
[23] J. Zhangyisun, L. Guo, H. Gao, X. Hong, H. Song, "A new bearing fault diagnosis method based on modified convolutional neural networks",  Chinese. J. Aeronaut., Vol.33(2), 2020, pp.439-447.
[24] P. Wang, Y. Yang, H. Ma, H. Xu, X. Li, Z. Luo, B.Wen,"Vibration characteristics of rotor-bearing system with angular misalignment and cage fracture: Simulation and experiment", Mech. Syst. Signal Process , Vol.182, 2023, 109545.
[25] S.NezamivandChegini, A.Bagheri, F.Najafi," Application of a new EWT-based denoising technique in bearing fault diagnosis", Meas. Vol.144, 2019, pp.275-297.
[26] X. Chen, B. Zhang, D. Gao, "Bearing fault diagnosis base on multi-scale CNN and LSTM model", J. Intell. Manuf.,Vol. 32, 2021,  pp. 971–987.
[27] E. Lopatinskaia,J. Zhu , J. Mathew, "Monitoring varying speed machinery vibration-II. Recursive filters and angle domain", Mech. Syst. Signal Process, Vol. 9(6),1995, pp. 647-655.
[28] Z. Zhang , J. Zhou, "Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines", Mech. Syst. Signal Process, Vol. 41(1–2), 2013, pp.127-140.
[29] M. Heidari , H. Homaei, H. Golestanian ,A. Heidari, "Fault diagnosis of gearboxes using wavelet support vector machine, least square support vector machine and wavelet packet transform", J. Vibroeng. Vol. 18(2), 2016, pp.860-875.
[30] J. Mercer, "Functions of positive and negative type and their connection with the theory of integral equations", Phil. Trans. R. Soc. A. , Vol. 209,1909, pp.415-446.
[31] L. Zhang,  W. Zhou, L. Jiao, "Wavelet support vector machine", IEEE Trans. Syst. Man Cybern B, Vol. 34(1), 2004, pp.34-39.
[32] Q. Hu, Z. He, Z. Zhang, Y. Zi, "Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble", Mech. Syst. Signal Process, Vol. 21(2), 2007, pp.688–705.
[33]  P. Zhou, S. Lu ,  F. Liua,  Y. Liu, G. Lia,  J. Zha, "Novel synthetic index-based adaptive stochastic resonance method and its application in bearing fault diagnosis", J. Sound Vib., Vol. 391,2017, pp.194–210.
[34] A. Hajnayeb, A. Ghasemloonia, SE. Khadem , MH. Moradi, "Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis", Expert. Syst. Appl. Vol. 38(8), 2011, pp.10205-10209.
[35]  PK. Kankar, SC. Sharma, SP. Harsha, "Fault diagnosis of ball bearings using continuous wavelet transform", Appl. Soft Comput., Vol. 11, 2011, pp.2300-2312.
[36] A. Rényi, On measures of entropy and information. Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, University of California Press, Berkeley, Calif 1, 1961.
 
Journal of Modeling in Engineering
Volume 21, Issue 72
March 2023
Pages 147-158

Files

History

  • Receive Date: 31 January 1401
  • Revise Date: 09 June 1401
  • Accept Date: 27 June 1401

Share

How to cite

Statistics