Feature Extraction Based on Deep Learning for Mechanical Bearing Fault Detection and Classification in Squirrel Cage Induction Machine

Authors

1 Asst. Prof., Elec. Eng., Shahrood Univ., Shahrood, Iran

2 M. Sc., Computer Eng., Shahrood Univ., Shahrood, Ira

3 Asst. Prof., Computer Eng., Shahrood Univ., Shahrood, Iran

Abstract

Bearings are one of the main components used in the drive-train of electrical machines. Early fault diagnosis and classification of bearing fault for maintenance of electromechanical system are very important. With progresses in measurement and digital systems, extensive range of real-time data can be available in electrical machines. Since fault diagnosis based on signal processing methods from extracted signals may not be possible due to different reasons such as noise level, natural frequencies of system, saturation of core,, severity of fault and load torque, deep learning methods have been considered in recent years. In this paper, time series deep learning method for condition monitoring of bearing in electrical machine for the purpose of detection and classification of fault is considered. Obtained results by means of proposed method have been compared with pervious techniques. Experimental results show that proposed deep learning method can detect and classify bearing fault with accuracy above 90%.

Keywords

References

[1] Marzebali MH, Kia SH, Henao H, Capolino G, Faiz J (2016) Planetary gearbox torsional vibration effects on wound-rotor induction generator electrical signatures. IEEE Trans Ind Appl 52(6): 4770-4780.
[2] Henao H et al (2014) Trends in fault diagnosis for electrical machines: A review of diagnostic techniques. IEEE Ind Electron Mag 8(2): 31-42.
[3] Liu Z, Zhang L (2019) A review of failure modes, condition monitoringand fault diagnosis methods for large-scale wind turbine bearings. Meas 149:  107002.
[4] Nezamivand Chegini S, Kakroudi S, Bagheri A (2019) A new intelligent method for bearing fault detection based on co-integration concept and selecting the optimal feature set at time-varying speed conditions. Journal of Solid and Fluid Mechanics (JSFM) 9(4): 41-57.
[5] Cheng Y, Wang Z, Chen B, Zhang W, Huang G (2019) An improved complementary ensemble empirical mode decomposition with adaptive noise and its application to rolling element bearing fault diagnosis. ISA Trans 91: 218-234.
[6] Mishra C, Samantaray AK, Chakraborty G  (2017) Rolling element bearing fault diagnosis under slow speed operation using wavelet de-noising. Measurement 103: 77-86.
[7] Jiang K, Zhou Y, Chen Q, Han L (2019) In processing fault detection of machinery based on instantaneous phase signal. IEEE Access 7: 123535-123543.
[8] Wang L, Liu Z, Miao Q,  Zhang X (2018) Time–frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis. Mech Syst Signal Process 103: 60-75.
[9] Marzebali MH, Faiz J, Capolino G, Kia SH, Henao H (2018) Planetary gear fault detection based on mechanical torque and stator current signatures of a wound rotor induction generator. IEEE Trans Energy Convers 33(3): 1072-1085.
[10] Hedayati Kia S, Hoseintabar Marzebali M (2020) Electrical signatures analysis for condition monitoring of gears. Electrical Systems 1: From Diagnosis to Prognosis 83:119.
[11] Razavi-Far R, et al (2018) Information fusion and semi-supervised deep learning scheme for diagnosing gear faults in induction machine systems. IEEE Trans Ind Electron 66(8): 6331-6342.
[12] Bagheri A, Nezamivand Chegini S, Ramezani Dashtemian M, Najafi F, (2018) Gear fault detection based on best feature selection by particle swarm optimization. Journal of Solid and Fluid Mechanics (JSFM) 8(3): 49-64.
[13] Shao S, McAleer S, Yan R, Baldi P (2018)  Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform 15(4): 2446-2455.
[14] He M, He D (2017)  Deep learning based approach for bearing fault diagnosis. IEEE Trans Ind Appl 53(3): 3057-3065.
[15] Ghorbanian V, Faiz J, Sabouri M, Ojaghi M (2014) Exact modeling and simulation of saturated induction motors with broken rotor bars fault using winding function approach. Int J Eng 27(1): 69-78.
[16] Gholami M, Shahryari OK,  Tarimoradi H (2021) An extended winding function model for induction machine modelling considering saturation effect. IET Electr Power Appl 15(1): 79-91.
[17] Asad B, Vaimann T, Belahcen A, Kallaste A, Rassõlkin A, Iqbal MN (2020)  Modified winding function-based model of squirrel cage induction motor for fault diagnostics. IET Electr Power Appl 14(9): 1722-1734.
[18] Asad B, Vaimann T, Kallaste A, Rassõlkin A, Belahcen A (2019) Winding function based analytical model of squirrel cage induction motor for fault diagnostics. In 2019 26th International Workshop on Electric Drives: Improvement in Efficiency of Electric Drives (IWED) (pp. 1-6). IEEE.
[19] Cibulka J, Ebbesen MK, Robbersmyr KG (2012)  Bearing fault detection in induction motor-gearbox drivetrain. In Journal of Physics: Conference Series 364(1): 1-20.
[20] Zaremba W, Sutskever I, Vinyals O (2014) Recurrent neural network regularization. arXiv preprint arXiv:1409.2329.
[21] Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8): 1735-1780.
[22] Wu S D, Wu PH, Wu CW, Ding JJ,  Wang CC (2012) Bearing fault diagnosis based on multiscale permutation entropy and support vector machine. Entropy 14(8): 1343-1356.
[23] Gu YK, Zhou XQ, Yu DP, Shen YJ (2018) Fault diagnosis method of rolling bearing using principal component analysis and support vector machine. J Mech Sci Technol 32(11): 5079-5088.
[24] Toma RN, Prosvirin AE, Kim JM (2020) Bearing fault diagnosis of induction motors using a genetic algorithm and machine learning classifiers. Sensors 20(7), 1884.
[25] Shao SY, Sun WJ, Yan RQ, Wang P, Gao RX (2017) A deep learning approach for fault diagnosis of induction motors in manufacturing. Chin J Mech Eng-En 30(6): 1347-1356.
[26] Yu L, Qu J, Gao F, Tian Y (2019) A novel hierarchical algorithm for bearing fault diagnosis based on stacked LSTM. Shock and Vibration, 2019.
Journal of Solid and Fluid Mechanics
Volume 11, Issue 5
November and December 2021
Pages 33-48

Files

Share

How to cite

Statistics