Improving Detection of Induction Motor Bearing Faults: A Study on Hyperparameter Tuning and ResNet-18 Layer Modification

International Journal of Electrical and Electronics Engineering

© 2024 by SSRG - IJEEE Journal

Volume 11 Issue 9

Year of Publication : 2024

Authors : Lydiah Aywa Sikinyi, Christopher Maina Muriithi, Livingstone Ngoo, Duncan Shitubi

10.14445/23488379/IJEEE-V11I9P104

How to Cite?

Lydiah Aywa Sikinyi, Christopher Maina Muriithi, Livingstone Ngoo, Duncan Shitubi, "Improving Detection of Induction Motor Bearing Faults: A Study on Hyperparameter Tuning and ResNet-18 Layer Modification," SSRG International Journal of Electrical and Electronics Engineering, vol. 11,  no. 9, pp. 39-56, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I9P104

Abstract:

Detecting incipient bearing faults of an induction motor is crucial for minimizing downtime, reducing maintenance costs, and ensuring safety. In this study, a novel approach to improve the detection accuracy of induction motor bearing faults using a combination of hyperparameter tuning and modifications to the Residual Network - 18 (ResNet-18) architecture is investigated. The effect of optimizing these aspects to enhance ResNet-18’s ability to classify various fault types within a dataset of bearing vibration signals is explored. This research focuses on ResNet-18 architecture, which has demonstrated remarkable performance in various image classification tasks, to evaluate the impact of specific modifications to its layers in order to improve further its suitability for bearing fault detection. The appropriate balance between model complexity and interpretability is achieved by altering the depth, width, and skip connections within ResNet-18. Next, parameters such as batch sizes, learning rates, L2 regularization, number of epochs, and optimizer are investigated by systematically tuning these hyperparameters and applying layer modifications, a new Bayesian Optimized Squeeze and Excitation ResNet model, which has a higher training accuracy of 98.44%, a validation accuracy of 99.48%, testing accuracy of 99.48%, and lower computational cost, as compared to the ResNet-18 model, is achieved. The proposed BOSE-ResNet contributes to the development of a more effective and precise bearing fault diagnosis model while enhancing machinery reliability in industrial applications and providing valuable insights for practitioners and researchers in the field of condition-based maintenance.

Keywords:

Bayesian optimization, Fault diagnosis, Hyperparameters, ResNet-18, Squeeze and excitation block.

References:

[1] Guilherme Beraldi Lucas et al., “Sensors Applied to Bearing Fault Detection in Three-Phase Induction Motors,” Engineering Proceedings, vol. 10, no. 1, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] David Gonzalez-Jimenez et al., “Data-Driven Fault Diagnosis for Electric Drives: A Review,” Sensors, vol. 21, no. 12, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Guoguo Wu et al., “Signal-to-Image: Rolling Bearing Fault Diagnosis Using ResNet Family Deep-Learning Models,” Processes, vol. 11, no. 5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Laith Alzubaidi et al., “Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions,” Journal of Big Data, vol. 8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Niloy Sikder et al., “Induction Motor Bearing Fault Classification Using Extreme Learning Machine Based on Power Features,” Arabian Journal for Science and Engineering, vol. 46, no. 9, pp. 8475-8491, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Dada Saheb Ramteke, Anand Parey, and Ram Bilas Pachori, “A New Automated Classification Framework for Gear Fault Diagnosis Using Fourier-Bessel Domain-Based Empirical Wavelet Transform,” Machines, vol. 11, no. 12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Hejun Ye et al., “Bearing Fault Diagnosis Based on Randomized Fisher Discriminant Analysis,” Sensors, vol. 22, no. 21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Long Wen, Xinyu Li, and Liang Gao, “A Transfer Convolutional Neural Network for Fault Diagnosis Based on ResNet-50,” Neural Computing and Applications, vol. 32, no. 10, pp. 6111-6124, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yi Liu et al., “A Domain Adaption ResNet Model to Detect Faults in Roller Bearings Using Vibro-Acoustic Data,” Sensors, vol. 23, no. 6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Zhenzhong Xu et al., “Hybrid Multimodal Feature Fusion with Multi-Sensor for Bearing Fault Diagnosis,” Sensors, vol. 24, no. 6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Shuyi Liu et al., “Fault Diagnosis Strategy Based on BOA-ResNet18 Method for Motor Bearing Signals with Simulated Hydrogen Refueling Station Operating Noise,” Applied Sciences, vol. 14, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mustafa Musa Jaber et al., “Resnet-Based Deep Learning Multilayer Fault Detection Model-Based Fault Diagnosis,” Multimedia Tools and Applications, vol. 83, no. 7, pp. 19277-19300, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Jialin Yan, Jiangming Kan, and Haifeng Luo, “Rolling Bearing Fault Diagnosis Based on Markov Transition Field and Residual Network,” Sensors, vol. 22, no. 10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Guoxin Sui, and Yong Yu, “Bayesian Contextual Bandits for Hyper Parameter Optimization,” IEEE Access, vol. 8, pp. 42971-42979, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Modupe Odusami et al., “Analysis of features of Alzheimer’s Disease: Detection of Early Stage from Functional Brain Changes in Magnetic Resonance Images Using a Finetuned Resnet18 Network,” Diagnostics, vol. 11, no. 6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Miao He, and David He, “Deep Learning Based Approach for Bearing Fault Diagnosis,” IEEE Transactions on Industry Applications, vol. 53, no. 3, pp. 3057-3065, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Christian Lessmeier et al., “Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification,” PHM Society European Conference, vol. 3, no. 1, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Data Sets and Download, Design and Drive Technology (KAt), Paderborn University, 2024. [Online]. Available: https://mb.uni-paderborn.de/en/kat/research/kat-datacenter/bearing-datacenter/data-sets-and-download
[20] Display Image with Scaled Colors - MATLAB imagesc, MathWorks, 2024. [Online]. Available: https://www.mathworks.com/help/matlab/ref/imagesc.html
[21] Dimas Aryo Anggoro, and Wiwit Supriyanti, “Improving Accuracy Bb Applying Z-Score Normalization in Linear Regression and Polynomial Regression Model for Real Estate Data,” International Journal of Emerging Trends in Engineering Research, vol. 7, no. 11, pp. 549-555, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Roy Jafari, Hands-On Data Preprocessing in Python : Learn How to Effectively Prepare Data for Successful Data Analytics, O’Reilly, Packt Publishing, 2022.
[Google Scholar] [Publisher Link]
[23] Charu C. Aggarwal, Neural Networks and Deep Learning: A Textbook, Springer Cham, 2nd ed., pp. 1-529, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Sergey Ioffe, and Christian Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” 32nd International Conference on Machine Learning (ICML), vol. 37, pp. 448-456, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Phil Kim, MATLAB Deep Learning with Machine Learning, Neural Networks and Artificial Intelligence, Apress Berkeley, CA, 1st ed., pp. 1-151, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84-90, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Shuiqin Zhou et al., “Application of Convolutional Neural Network in Motor Bearing Fault Diagnosis,” Computational Intelligence and Neuroscience, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] François Chollet, Deep Learning with Python, Second Edition, Manning, 2021.
[Google Scholar] [Publisher Link]
[29] Fu Zhu et al., “An Improved MobileNet Network with Wavelet Energy and Global Average Pooling for Rotating Machinery Fault Diagnosis,” Sensors, vol. 22, no. 12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] K.A. Saneera Hemantha Kulathilake et al., “A Review on Deep Learning approaches for Low-Dose Computed Tomography Restoration,” Complex and Intelligent Systems, vol. 9, no. 3, pp. 2713-2745, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Jeff Heaton, “Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning,” Genetic Programming and Evolvable Machines, vol. 19, no. 1-2, pp. 305-307, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Meng-Hao Guo et al., “Attention Mechanisms in Computer Vision: A Survey,” Computational Visual Media, vol. 8, no. 3, pp. 331-368, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Dongwoo Lee et al., “A Study on the Super Resolution Combining Spatial Attention and Channel Attention,” Applied Sciences, vol. 13, no. 6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Jie Hu, Li Shen, and Gang Sun, “Squeeze-and-Excitation Networks,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 7132-7141, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Yanzhao Wu et al., “Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks,” 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, pp. 1971-1980, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Zhen Li, Yang Wang, and Jianeng Ma, “Fault Diagnosis of Motor Bearings Based on a Convolutional Long Short-Term Memory Network of Bayesian Optimization,” IEEE Access, vol. 9, pp. 97546-97556, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Mettu Srinivas et al., Machine Learning Algorithms and Applications,” Scrivener Publishing LLC, 1st ed., pp. 1-335, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Syifa Auliyah Hasanah et al., “A Deep Learning Review of ResNet Architecture for Lung Disease Identification in CXR Image,” Applied Sciences, vol. 13, no. 24, 2023.
[CrossRef] [Google Scholar] [Publisher Link]