Search

Enhanced Fault Diagnosis of Vertical Friction Torque Using Improved VGG-CNN Network

Author(s)

Xiangjun Du1,*, Ling Yu2

Affiliation(s)

1School of Mechanical Engineering, Tiangong University, Tianjin, China 2Tianjin Light Industry Vocational Technical College; Tianjin, China *Corresponding Author.

Abstract

This paper presents a CNN-based fault diagnosis method utilizing Infrared Thermography (IRT) to improve the low diagnostic rates of friction torque faults in upright placements and to address bearing faults in a test bench. Employing non-destructive, non-contact infrared thermal imaging technology, the study conducts tests across six scenarios: undamaged, damaged inner ring, damaged outer ring, defective marble, insufficient lubrication, and damaged inner and outer ring bearings. This article implements a thermal image processing technique based on two-dimensional discrete wavelet transform, combining VGG Net model with CBAM attention mechanism to improve classification accuracy while reducing training time. Convolutional neural networks were then employed for fault classification and performance evaluation, demonstrating superior results compared to support vector machines. This approach effectively identifies bearing torque faults, achieving an impressive 99.80% accuracy in classifying faulty bearings, indicating its broad applicability.

Keywords

Infrared Thermography; Friction Torque; Convolutional Neural Networks; Support Vector Machines; Bearings; Fault Diagnosis

References

[1] Choudhary A, Mian T, Fatima S. Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images. Measurement, 2021, 176: 109196. [2] Choudhary A, Goyal D, Letha S S. Infrared thermography-based fault diagnosis of induction motor bearings using machine learning. IEEE Sensors Journal, 21(2): 1727-1734, 15 Jan.15, 2021, doi: 10.1109/JSEN.2020.3015868. [3] Li Z, Li Y, Sun Q, et al. Bearing fault diagnosis method based on convolutional neural network and knowledge graph. Entropy, 2022, 24(11): 1589. [4] Pan R, Lin T, Li C, et al. Research on a deep learning based weld seam detection and positioning system for multi size automotive rims. Optical Precision Engineering, 2023, 31(08): 1174-1187 [5] Liu Z, Wang J, Duan L, et al. Infrared image combined with CNN based fault diagnosis for rotating machinery. 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), Shanghai, China, 2017, 137-142, doi: 10.1109/SDPC.2017.35. [6] Lucchi E, Roberti F, Alexandra T. Definition of an experimental procedure with the hot box method for the thermal performance evaluation of inhomogeneous walls. Energy & Buildings, 2018, 179. [7] Jia Z, Liu Z, Vong C M, et al. A rotating machinery fault diagnosis method based on feature learning of thermal images. IEEE Access, 2019, 7: 12348-12359. [8] Li Y, Du X, Wan F, et al. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging. Chinese Journal of Aeronautics, 2020, 33(02): 427-438. [9] Mehta A, Goyal D, Choudhary A, et al. Machine learning-based fault diagnosis of self-aligning bearings for rotating machinery using infrared thermography. Mathematical Problems in Engineering, 2021, 2021. [10] Goyal D, Dhami S S, Pabla B S. Non-contact fault diagnosis of bearings in machine learning environment. IEEE Sensors Journal, 2020. [11] Du Y, Tong L, Wei L, et al. Self updating control algorithm and verification of laser radar shaft friction torque detection equipment. Infrared and Laser Engineering, 2022, 51(08): 344-350 [12] Shao H, Wei L, Yi L, et al. Fault diagnosis of rotor bearing systems based on dual threshold attention generation adversarial networks and small samples under time-varying speed. Journal of Mechanical Engineering, 2023, 59(12): 215-224 [13] Wang X, Zhang H, Zhu J, et al. Fault diagnosis method for aviation high-speed bearings driven by multi head attention. Vibration and Shock, 2023,42 (04): 295-305. DOI: 10.13465/j.cnki.jvs.2023.04.035 [14] Sun S, Huang Z, Yang J. Research status and progress in infrared thermal non-destructive testing image processing. Infrared Technology, 2019,41 (12): 1133-1140 [15] Mian T, Choudhary A, Fatima S. Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning. Nondestructive Testing and Evaluation, 2023, 38(2): 275-296. [16] Jin K, Zhang J, Wang Z, et al. Application of deep learning based on thermal images to identify the water stress in cotton under film-mulched drip irrigation. Agricultural Water Management, 2024, 299: 108901. [17] Trejo-Chavez O, Cruz-Albarran I A, Resendiz-Ochoa E, et al. A CNN-based methodology for identifying mechanical faults in induction motors using thermography. Machines, 2023, 11(7): 752. [18] Gana M, Achour H, Belaid K, et al. Non-invasive intelligent monitoring system for fault detection in induction motor based on lead-free-piezoelectric sensor using ANN. Measurement Science and Technology, 2022, 33(6): 065105. [19] Goyal D, Choudhary A, Pabla B S, et al. Support vector machines based non-contact fault diagnosis system for bearings. Journal of Intelligent Manufacturing, 2019, 31(5): 1275-1289. [20] Zhou X, Zhang H, Hao X, et al. Investigation on thermal behavior and temperature distribution of bearing inner and outer rings. Tribology International, 2019, 130: 289-298. [21] Ullah I, Khan R U, Yang F, et al. Deep learning image-based defect detection in high voltage electrical equipment. Energies, 2020, 13(2): 392. [22] Tieleman T, Hinton G. Divide the gradient by a running average of its recent magnitude. Neural networks for machine learning. Technical Report, 2017.