Identification of Size and Location of Bearing Damage via Deep Learning

Document Type : Original Article


Aerospace Research Institute


Rotating machine is one of the most important machines used in various sectors. The most important unit is the rotating part and the shaft held by bearings. Most of the maintenance and repair cost of these machines is related to the replacement and service of bearings. Therefore, it is very important to identify the damaged bearings and determine the location of the damage. Different methods have been developed to monitor their condition, including recording and analyzing the vibration signals of bearings. So far, vibration-based methods have often been used to analyze them. Recently, the use of machine learning and deep learning techniques have been considered. Therefore, in this paper, a convolutional neural network is developed that directly receives the raw information recorded by vibration sensors as input and after analysis, a healthy bearing is detected from a defective one, the location and size of the damage are determined. In this research, the data set of Case Western Reserve University is used to validate the model and the results show that the proposed model has very high accuracy for analysis of samples.


Main Subjects

[1] Yeping Peng, JunhaoCai, Tonghai Wu, Gugangzhong Cao, Ngaiming Kwok, Shengxi Zhou, Zhongxiao Peng, "Online wear characterisation of rolling element bearing using wear particle morphological features", Wear, 2019: 430–431, p. 369-375.
[2] Wontae KIM, Jinju SEO, Dongpyp HONG. "Infrared Thermographic Inspection of Ball Bearing; Condition Monitoring for Defects under Dynamic Loading Stages", 18th World conference on Nondestructive Testing, 16-20 April 2012, Durban, South Africa.

[3]Carlos Morales-PerezJose Rangel-MagdalenoHaydePeregrina-BarretoJuan Ramirez-CortesEmmanuel Vazquez-Pacheco. "Bearing Fault Detection Technique by using Thermal Images: A case of Study",  2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Auckland, New Zealand, 2019.

[4] Zepeng LiuXuefei WangLong Zhang. "Fault Diagnosis of Industrial Wind Turbine Blade Bearing Using Acoustic Emission Analysis",IEEE Transactions on Instrumentation and Measurement, 2020. 69(9): p.6630 – 6639.

[5]  Bakhtiarinejad F., H. Ali, S. Ehsani,Bearingdiagnoise via vibration analysis, 13th conference on Mechanical engineering, 2004, Isfahan, Iran.

[6] PawelEwert,Czeslaw T. Kowalski and Teresa Orlowska-Kowalska. Low-Cost Monitoring and Diagnosis System for Rolling Bearing Faults of the Induction Motor Based on Neural Network Approach. Electronics 2020, 9(9): p.1334
[7] Jaouher Ben Ali, Nader Fnaiech, LotfiSaidi, Brigitte Chebel-Morello, FarhatFnaiech, "Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals", Applied Acoustics, 2015.89: p. 16-27.
[8] Mohammad Ali Farsi, S. Masood Hosseini. "Statistical distributions comparison for remaining useful life prediction of components via ANN",Int J Syst Assur Eng Manag2019. 10: p.429–436. doi:10.1007/s13198-019-00813-w.
[9] Sawaqed, L.S., Alrayes, A.M. "Bearing fault diagnostic using machine learning algorithms". ProgArtif Intell.2020.9: p.341–350doi: 10. 1007/s13748-020-00217-z.
[10] Duy-Tang Hoang, Hee-Jun Kang, "A survey on Deep Learning based bearing fault diagnosis",Neuro computing, 2019. 335: p. 327-335.

[11] Shen Zhang, Shibo Zhang,  "Bingnan Wang, Thomas G. Habetler, Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review", IEEE Access, 2020.8:p. 29857-29881, doi: 10.1109/ACCESS.2020.2972859.

[12] Lu W, Liang B, Cheng Y, Meng D, Yang J, Zhang T. "Deep Model Based Domain Adaptation for Fault Diagnosis". IEEE Trans Ind Electron; 2017, 64: p.2296–305. 2017, doi:10.1109/TIE.2016.2627020.
[13] M. Elforjani and S. Shanbr, “Prognosis of bearing acoustic emissionsignals using supervised machine learning,” IEEE Trans. Ind. Electron., 2018. 65(7): p. 5864–5871.
[14] C. Lu, Z.-Y Wang, W.-L. Qin, J. Ma, “Fault diagnosis of rotarymachinery components using a stacked denoisingautoencoder-basedhealth state identification,” Signal Process., 2017. 130: p. 377–388.
[15] Nectoux, R. Gouriveau, K. Medjaher, E. Ramasso, B. Morello, N. Zerhouni, C. Varnier. PRONOSTIA: An Experimental Platform for Bearings Accelerated Life Test. IEEE International Conference on Prognostics and Health Management, Denver, CO, USA, 2012.
[16] Bearing Datacenter Paderborn University, Accessed on line:
[17] Case Western Reserve university, Bearing Datacenter, Accessed on line:
 [18]  MihirMody and Kumar Desappan and P. Swami and M. Mathew and S. Nagori."Low cost and power CNN/deep learning solution for automated driving", 19th International Symposium on Quality Electronic Design (ISQED), 2018.P. 432-436.
Volume 4, Issue 1
January 2021
Pages 69-74
  • Receive Date: 23 August 2021
  • Revise Date: 29 September 2021
  • Accept Date: 29 September 2021
  • First Publish Date: 29 September 2021