Sustainable Energy and Artificial Intelligence

A Low Cost IoT-Based Hybrid Multiscale CNN-LSTM Approach for Bearing Fault Diagnosis Using Low Sampling Rate Vibration Data

Document Type : Original Article

Authors

Seyed Mohammad Mahdi Moosavi 1
Sajad Khoshbakht 1
Hossein Taheri 2

1 Electrical and Computer Engineering Department, Hamedan University of Technology, Hamedan, Iran

2 Department of Manufacturing Engineering, Georgia Southern University

https://doi.org/10.61186/seai.2409-1005
Abstract
Electric motors are vital in energy systems for converting energy efficiently. Their reliability ensures consistent performance, making them indispensable in renewable energy applications and industrial processes. Bearings are crucial for motor operation, yet they are vulnerable to faults that can impair performance and reduce lifespan. Conventional fault detection methods require high sampling rate vibration data and expensive sensors. This paper presents a cost-effective solution by introducing a hybrid model combining Multiscale Convolutional Neural Networks (MSCNN) with Long Short-Term Memory (LSTM) networks for bearing fault diagnosis using low sampling rate data. We developed dedicated IoT-based hardware and a web server for real-time monitoring. Our approach leverages MSCNN for spatial feature extraction and LSTM for temporal pattern recognition, achieving high diagnostic accuracy with lower resolution data. Experimental results show that our MSCNN-LSTM model provides diagnostic accuracy comparable to or surpassing that of high sampling rate methods, offering a robust and economical solution for bearing fault detection.

Highlights

  • Developed an IoT-based fault diagnosis system utilizing low sampling rate vibration data.
  • Proposed a robust hybrid CNN-LSTM model for accurate and efficient fault detection.
  • Achieved cost-effective, real-time monitoring for industrial bearing systems.
  • Enhanced fault diagnosis accuracy while reducing hardware and maintenance costs.
  • Improved equipment reliability through early fault detection.

Keywords

Multiscale Fault Diagnosis
Convolutional Neural Network
Long Short-Term Memory
Bearing Fault, Internet of Things
Subjects
  1. Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2020). Deep learning algorithms for bearing fault diagnostics—A comprehensive review. IEEE Access, 8, 29857-29881.
  2. Toliyat, H. A., Nandi, S., Choi, S., & Meshgin-Kelk, H. (2017). Electric machines: modeling, condition monitoring, and fault diagnosis. CRC press.
  3. Liang, X., Ali, M. Z., & Zhang, H. (2019). Induction motors fault diagnosis using finite element method: A review. IEEE Transactions on Industry Applications, 56(2), 1205-1217.
  4. Hsueh, Y. M., Ittangihal, V. R., Wu, W. B., Chang, H. C., & Kuo, C. C. (2019). Fault diagnosis system for induction motors by CNN using empirical wavelet transform. Symmetry, 11(10), 1212.
  5. Soualhi, A., Medjaher, K., Celrc, G., & Razik, H. (2020). Prediction of bearing failures by the analysis of the time series. Mechanical Systems and Signal Processing, 139, 106607.
  6. Wang, P., Wang, H., & Yan, R. (2019). Bearing degradation evaluation using improved cross recurrence quantification analysis and nonlinear auto-regressive neural network. IEEE Access, 7, 38937-38946.
  7. Xue, Y., Wen, C., Wang, Z., Liu, W., & Chen, G. (2024). A novel framework for motor bearing fault diagnosis based on multi-transformation domain and multi-source data. Knowledge-Based Systems, 283, 111205.
  8. Mahesh, T. R., Saravanan, C., Ram, V. A., Kumar, V. V., Vivek, V., & Guluwadi, S. (2024). Data-driven intelligent condition adaptation of feature extraction for bearing fault detection using deep responsible active learning. IEEE Access.
  9. Guan, B., Bao, X., Qiu, H., & Yang, D. (2024). Enhancing bearing fault diagnosis using motor current signals: A novel approach combining time shifting and CausalConvNets. Measurement, 226, 114049.
  10. Jiang, P., Xia, J., Li, W., Xu, C., & Sun, W. (2024). Innovative Bearing Fault Diagnosis Method: Combining Swin Transformer Deep Learning and Acoustic Emission Technology. ASCE-ASME J Risk and Uncert in Engrg Sys Part B Mech Engrg, 1-14.
  11. Mian, T., Choudhary, A., & Fatima, S. (2023). Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning. Nondestructive Testing and Evaluation, 38(2), 275-296.
  12. Luo, G., Habetler, T. G., & Hurwitz, J. (2020, October). Stray flux-based incipient stage bearing fault detection for induction machines via noise cancellation techniques. In 2020 IEEE Energy Conversion Congress and Exposition (ECCE) (pp. 764-768). IEEE. 
  13. Li, J., Shen, C., Kong, L., Wang, D., Xia, M., & Zhu, Z. (2022). A new adversarial domain generalization network based on class boundary feature detection for bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 71, 1-9.
  14. Chen, X., Yang, Y., Cui, Z., & Shen, J. (2020). Wavelet denoising for the vibration signals of wind turbines based on variational mode decomposition and multiscale permutation entropy. IEEE Access, 8, 40347-40356.
  15. Wang, J., Mo, Z., Zhang, H., & Miao, Q. (2019). A deep learning method for bearing fault diagnosis based on time-frequency image. IEEE Access, 7, 42373-42383.
  16. Hsia, S.-C., & Hsu, C.-Y. (2024). Real-time monitor and control system for abnormal motor vibrations. IEEE Transactions on Instrumentation and Measurement, 73, Article 2000511, 1–11.
  17. Nishat Toma, R., & Kim, J. M. (2020). Bearing fault classification of induction motors using discrete wavelet transform and ensemble machine learning algorithms. Applied Sciences, 10(15), 5251.
  18. Mushtaq, S., Islam, M. M., & Sohaib, M. (2021). Deep learning aided data-driven fault diagnosis of rotatory machine: A comprehensive review. Energies, 14(16), 5150.
  19. Liu, D., Cui, L., Cheng, W., Zhao, D., & Wen, W. (2022). Rolling bearing fault severity recognition via data mining integrated with convolutional neural network. IEEE Sensors Journal, 22(6), 5768-5777.
  20. Eren, L., Ince, T., & Kiranyaz, S. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. Journal of Signal Processing Systems, 91(2), 179-189.
  21. Mao, W., Feng, W., Liu, Y., Zhang, D., & Liang, X. (2021). A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mechanical Systems and Signal Processing, 150, 107233.
  22. Shao, H., Jiang, H., Li, X., & Liang, T. (2018). Rolling bearing fault detection using continuous deep belief network with locally linear embedding. Computers in Industry, 96, 27-39.
  23. Bai, G., Sun, W., Cao, C., Wang, D., Sun, Q., & Sun, L. (2024). GAN-based bearing fault diagnosis method for short and imbalanced vibration signal. IEEE Sensors Journal, 24(2), 1894–1904.
  24. An, Y., Zhang, K., Liu, Q., Chai, Y., & Huang, X. (2022). Rolling bearing fault diagnosis method base on periodic sparse attention and LSTM. IEEE Sensors Journal, 22(12), 12044-12053.
  25. Song, X., Zhu, D., & Sun, S. (2022). A new fault diagnosis model of rolling element bearing based on a recurrent neural network. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 236(4), 1430-1439.
  26. Irgat, E., Çinar, E., Ünsal, A., & Yazıcı, A. (2023). An IoT-Based Monitoring System for Induction Motor Faults Utilizing Deep Learning Models. Journal of Vibration Engineering & Technologies, 11(7), 3579-3589.
  27. Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems, 33(12), 6999-7019.
  28. Sunal, C. E., Dyo, V., & Velisavljevic, V. (2022). Review of machine learning based fault detection for centrifugal pump induction motors. IEEE access, 10, 71344-71355.
  29. Afrasiabi, S., Afrasiabi, M., Parang, B., & Mohammadi, M. (2019, February). Real-time bearing fault diagnosis of induction motors with accelerated deep learning approach. In 2019 10th international power electronics, drive systems and technologies conference (PEDSTC) (pp. 155-159). IEEE.
  30. Wang, R., Shi, R., Hu, X., & Shen, C. (2021). Remaining useful life prediction of rolling bearings based on multiscale convolutional neural network with integrated dilated convolution blocks. Shock and Vibration, 2021(1), 6616861.
  31. Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2019, December). The performance of LSTM and BiLSTM in forecasting time series. In 2019 IEEE International conference on big data (Big Data) (pp. 3285-3292). IEEE. 
  32. Karim, F., Majumdar, S., Darabi, H., & Chen, S. (2017). LSTM fully convolutional networks for time series classification. IEEE access, 6, 1662-1669.
  33. Analog Devices, Inc. (n.d.). ADXL345 data sheet. Retrieved February 20, 2024, from https://www.analog.com/media/en/technical-documentation/data-sheets/ADXL345.pdf
  34. Dong, K., & Lotfipoor, A. (2023). Intelligent bearing fault diagnosis based on feature fusion of one-dimensional dilated CNN and multi-domain signal processing. Sensors, 23(12), 5607.
  35. Wang, J., Wang, D., Wang, S., Li, W., & Song, K. (2021). Fault diagnosis of bearings based on multi-sensor information fusion and 2D convolutional neural network. IEEE Access, 9, 23717-23725.
  36. Li, X., Zhang, W., & Ding, Q. (2018). Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks. IEEE Transactions on Industrial Electronics, 66(7), 5525-5534.
  37. Shan, S., Liu, J., Wu, S., Shao, Y., & Li, H. (2023). A motor bearing fault voiceprint recognition method based on Mel-CNN model. Measurement, 207, 112408.
  38. Xiao, L., Yang, X., & Yang, X. (2023). A graph neural network-based bearing fault detection method. Scientific Reports, 13(1), 5286.
  39. Wu, G., Ji, X., Yang, G., Jia, Y., & Cao, C. (2023). Signal-to-image: Rolling bearing fault diagnosis using ResNet family deep-learning models. Processes, 11(5), 1527.
  40. Yan, J., Kan, J., & Luo, H. (2022). Rolling bearing fault diagnosis based on Markov transition field and residual network. Sensors, 22(10), 3936.
  41. Li, H., Huang, J., & Ji, S. (2019). Bearing fault diagnosis with a feature fusion method based on an ensemble convolutional neural network and deep neural network. Sensors, 19(9), 2034.
  42. Ali, J. B., Saidi, L., Mouelhi, A., Chebel-Morello, B., & Fnaiech, F. (2015). Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations. Engineering Applications of Artificial Intelligence, 42, 67-81.
  43. Wang, S., Xiang, J., Zhong, Y., & Zhou, Y. (2018). Convolutional neural network-based hidden Markov models for rolling element bearing fault identification. Knowledge-Based Systems, 144, 65-76.
  44. Lu, W., Liang, B., Cheng, Y., Meng, D., Yang, J., & Zhang, T. (2016). Deep model based domain adaptation for fault diagnosis. IEEE Transactions on Industrial Electronics, 64(3), 2296-2305.
Sustainable Energy and Artificial Intelligence
Volume 1, Issue 2
Spring 2025
Pages 113-125

  • Receive Date 07 September 2024
  • Revise Date 14 September 2024
  • Accept Date 17 September 2024
  • First Publish Date 28 September 2024

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us