Fault diagnosis method of AC motor rolling bearing based on heterogeneous data fusion of current and infrared image

Abstract

In order to improve the accuracy of rolling bearing fault diagnosis when the motor is running under non-stationary conditions, an AC motor rolling bearing fault diagnosis method was proposed based on heterogeneous data fusion of current and infrared images. Firstly, VMD was used to decompose the motor current signal and extract the low-frequency component of the bearing fault signal. On this basis, the current signal was transformed into a two-dimensional graph suitable for convolutional neural network, and the data set was classified by convolutional neural network and softmax classifier. Secondly, the infrared image was segmented and the fault features were extracted, so as to calculate the similarity with the infrared image of the fault bearing in the library, and further the sigmod classifier was used to classify the data. Finally, a decision-level fusion method was introduced to fuse the current signal with the infrared image signal diagnosis result according to the weight, and the motor bearing fault diagnosis result was obtained. Through experimental verification, the proposed fault diagnosis method could be used for the fault diagnosis of motor bearing outer ring under the condition of load variation, and the accuracy of fault diagnosis can reach 98.85%.

Keywords

current signal / infrared image / decision level fusion / rolling bearing / fault diagnosis

References

[1] LEE D, SIU V, CRUZ R. Convolutional neural net and bearing fault analysis//International Conference on Data Mining (DMIN). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp),December 12-16, 2016, Barcelona, Spain. New York: IEEE, 2016: 194-200.

[2] TIAN Y L, LIU X Y. A deep adaptive learning method for rolling bearing fault diagnosis using immunity. Tsinghua Science and Technology, 2019, 24(6): 750-762.

[3] YANG P, SU Y C. Falut diagnosis of rolling bearing based on convolution gated recurrent network. Journal of Aerospace Power, 2019, 34(11): 2432-2439.

[4] BIAN H, WANG X L, DENG Z Q. Bearing fault detection for brushless DC motors based on stator current. Journal of Nanjing University of Aeronautics and Astronautics, 2020, 52(2): 224-231.

[5] QI R S, FAN J, LI Y T, et al. A fault diagnosis method of wind turbine bearings based on an enhanced morphological filter. Journal of Vibration and Shock, 2021, 40(4): 212-220.

[6] SCHOEN R R, HABETLER T G, KAMRAN F, et al. Motor bearing damage detection using stator current monitoring. IEEE Transactions on Industry Applications, 1995, 31(6): 1274-1279.

[7] BLODT M, GRANJON P, RAISON B, et al. Models for bearing damage detection in induction motors using stator current monitoring. IEEE Transactions on Industrial Electronics, 2008, 55(4): 1813-1822.

[8] SONG X J, HU J T, ZHU H Y, et al. Effects of the slot harmonics on the stator current in an induction motor with bearing fault. Mathematical Problems in Engineering, 2017, 2017(1): 2640796.

[9] HAN Q K, DING Z, XU X P, et al. Stator current model for detecting rolling bearing faults in induction motors using magnetic equivalent circuits. Mechanical Systems and Signal Processing, 2019, 131: 554-575.

[10] KARATZINIS G, BOUTALIS Y S, KARNAVAS Y L. Motor fault detection and diagnosis using fuzzy cognitive networks with functional weights//2018 26th Mediterranean Conference on Control and Automation (MED), June 19-22, 2018, Zadar, Croatia. New York: IEEE, 2018: 709-714.

[11] BAGAVATHIAPPAN S, SARAVANAN T, GEORGE N P, et al. Condition monitoring of exhaust system blowers using infrared thermography. Insight, 2008, 50(9) 512-515.

[12] SUN B,WANG Y W, YANG L. Study of fault diagnosis of induction motor bearing based on infrared inspection. Electric Machines and Control, 2012, 16(1): 50-55.

[13] AZEEZ A A, ALKHEDHER M, GADALA M S. Thermal imaging fault detection for rolling element bearings//2020 Advances in Science and Engineering Technology International Conferences (ASET). Dubai, United Arab Emirates. New York: IEEE, 2020: 1-5.

[14] HOANG D T, KANG H J. A motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Transactions on Instrumentation and Measurement, 2020, 69(6): 3325-3333.

[15] HOU X G, WU Z G, XIA L, et al. Bearing fault detection method for induction motor based on fusion analysis. Journal of Data Acquisition ＆ Processing, 2006(1): 113-117.

[16] WANG H X, WANG B, DONG X Z, et al. Heterogeneous multi-parameter feature-level fusion for multi-source power sensing terminals: fusion mode, fusion framework and application scenarios. Transactions of China Electrotechnical Society, 2021, 36(7): 1314-1323.

[17] STACK J R, HABETLER T G, HARLEY R G. Fault classification and fault signature production for rolling element bearings in electric machines//4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED. Atlanta, GA, USA. New York: IEEE, 2003: 172-176.

[18] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

[19] LI J, GUO J Y, LIU Y C, et al. Vietnamese combinational ambiguity disambiguation based on weighted voting method of multiple classifier. Computer Science, 2018, 45(1): 167-172.

[20] JIANG X J, MALIK H, PANDA S K. An optimized intelligent technique for bearing fault diagnosis using motor current signal analysis//2022 International Power Electronics Conference (IPEC-Himeji 2022-ECCE Asia), May 15-19, 2022, Himeji, Japan. New York: IEEE, 2022: 730-735.