Development of a Deep Learning-Based Framework for Real-Time Detection and Classification of Mechanical Faults in Rotating Machinery

Ayesha Rahman

Authors

Ayesha Rahman Mechanical Design Engineer, Bangladesh Author

Keywords:

Rotating Machinery, Deep Learning, Fault Diagnosis, Vibration Analysis, CNN-LSTM, Predictive Maintenance, Real-Time Monitoring

Abstract

The early and accurate detection of mechanical faults in rotating machinery is critical for predictive maintenance and operational efficiency across industrial systems. This study proposes a novel deep learning-based framework that performs real-time detection and multi-class classification of mechanical faults in rotating machinery using vibration signal data. Our approach utilizes a combination of convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to extract spatial and temporal features from time-series signals, offering enhanced performance compared to traditional signal processing methods. Evaluated on publicly available benchmark datasets, the model demonstrates superior fault classification accuracy and real-time response capability, thereby presenting a promising tool for integration into Industry 4.0 smart maintenance systems.

References

Ince, T. A., Kiranyaz, S., Eren, L., Askar, M., and Gabbouj, M. “Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks.” IEEE Transactions on Industrial Electronics, vol. 63, no. 11, 2016, pp. 7067–7075.

Zhao, Ruqiang, et al. “Deep Learning and Its Applications to Machine Health Monitor-ing.” Mechanical Systems and Signal Processing, vol. 115, 2019, pp. 213–237.

Zhang, Wenlei, et al. “A New Deep Learning Model for Fault Diagnosis with Imbal-anced and Small Datasets.” Knowledge-Based Systems, vol. 190, 2020, article no. 105101.

Verstraete, D., Ferrada, P., Droguett, E. L., Meruane, V., and Modarres, M. “Deep Learning Enabled Fault Diagnosis Using Time–Frequency Image Analysis of Rolling Element Bearings.” Shock and Vibration, vol. 2017, 2017, article ID 5067651.

Li, Xuefeng, Ding, Qian, and Sun, Jing. “Remaining Useful Life Estimation in Prognos-tics Using Deep Convolution Neural Networks.” Reliability Engineering & System Safety, vol. 172, 2018, pp. 1–11.

Janssens, O., Van de Walle, R., Van Hoecke, S., and Van Langenhove, W. “Deep Learn-ing for Infrared Thermal Image-Based Machine Health Monitoring.” IEEE Transactions on Automation Science and Engineering, vol. 14, no. 2, 2017, pp. 642–653.

Guo, Lei, et al. “A Deep Convolutional Neural Network-Based Method for Fault Diag-nosis of Rotating Machinery.” Neurocomputing, vol. 290, 2018, pp. 140–149.

Babu, G. S., Zhao, P., and Li, X. “Deep Convolutional Neural Network Based Regres-sion Approach for Estimation of Remaining Useful Life.” Proceedings of the Annual Conference of the Prognostics and Health Management Society, 2016.

Liu, Rui, et al. “An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data.” IEEE Transactions on Industrial Electronics, vol. 63, no. 5, 2016, pp. 3137–3147.

Wang, T., Yu, J., and Siegel, D. “A Machine Learning Framework for Detecting and Diagnosing Faults in Wind Turbines.” Renewable Energy, vol. 133, 2019, pp. 422–432.

Lei, Yaguo, et al. “Machinery Health Prognostics: A Systematic Review from Data Ac-quisition to RUL Prediction.” Mechanical Systems and Signal Processing, vol. 104, 2018, pp. 799–834.

Mao, Kezhi, Yan, Ruqiang, and Liu, Yaguo. “Diagnosis of Wind Turbine Fault Based on Vibration Signal and Deep Learning.” Journal of Intelligent Manufacturing, vol. 30, no. 3, 2019, pp. 1111–1123.