Deep Learning-Assisted Structural Health Monitoring of Rotating Mechanical Systems Using Multi-Sensor Vibration Signals
DOI:
https://doi.org/10.5281/zenodo.22660656Keywords:
Deep Learning (DL), Structural Health Monitoring (SHM), Rotating Mechanical Systems (RMS), Multi-Sensor Vibration Signals (MSVS)Abstract
Mechanical systems such as turbines, compressors, pumps, gearboxes, and electric motors are essential components in today's industrial settings, and failure to maintain them can have serious consequences for the business. They including downtime, maintenance expenses, and safety risks. Structural Health Monitoring (SHM) offers a promising solution for early detection and diagnosis of mechanical degradation. However, traditional vibration monitoring is difficult under complex, nonlinear, and highly variable operating conditions. This paper presents a deep learning-based SHM system for rotating mechanical systems based on multi-sensor vibration signals. The solution combines vibration signals from strategically placed sensors to collect complementary vibration information related to bearing defects, gear damage, shaft misalignment, imbalance, and other structural abnormalities. The data is preprocessed with advanced signal-processing algorithms to remove noise, synchronise it, and extract signal features. In contrast, deep learning algorithms automatically learn discriminative patterns from the complex vibration data. The framework is designed to provide enhanced fault detection, classification, and condition assessment over traditional single-sensor and hand-crafted features. Multiple sensors can be added to increase monitoring reliability. Multi-sensor data fusion provides a more comprehensive picture of machine health and mitigates individual sensor noise and localized measurement limitations. The research methodology can be applied to real-time condition monitoring, predictive maintenance, and initial fault diagnosis of industrial rotating machines. Overall, the study demonstrates the abilities of a multi-sensor vibration-based signal analysis and deep learning approach to design an accurate, intelligent, and scalable SHM system that improves operational reliability and reduces unplanned maintenance.
References
Chen, S., Du, F., Hou, X., & Chen, H. (2026). Deep learning-assisted compound fault diagnosis method of rotating machinery under limited sample and noisy environments. Measurement Science and Technology, 37(20), 206204. https://doi.org/10.1088/1361-6501/ae6799
Cheng, Z., Wen, Y., Xie, Z., Zhang, M., Feng, Q., Wang, Y., Liu, D., Cao, Y., & Mao, Y. (2025). A multi-sensor coupled supramolecular elastomer empowers intelligent monitoring of human gait and arch health. Chemical Engineering Journal, 504, 158760. https://doi.org/10.1016/j.cej.2024.158760
de Oliveira Silva, R., Outa, R., & Chavarette, F. R. (2026). An Intelligent Signal Classification Framework for Crack Detection in Polymeric Materials Using Ensemble Learning. Computer Modeling in Engineering & Sciences, 147(1), 19. https://doi.org/10.32604/cmes.2026.080607
Dubey, A., Shakoor, M., Vasiukov, D., Khoury, B., Deléglise Lagardère, M., & Chaki, S. (2025). An overview of damage identification in composite structures—from computational methods to machine learning. Journal of Composites Science, 9(12), 683. https://doi.org/10.3390/jcs9120683
Gao, J., Niu, H., Li, Y., & Li, Y. (2025). Machine‐learning enabled biocompatible capacitive‐electromyographic bimodal flexible sensor for facial expression recognition. Advanced Functional Materials, 35(14), 2418463. https://doi.org/10.1002/adfm.202418463
Ghasemi, F., Salari, A., Salari, E., & Rastgoo, A. (2025). Machine learning-assisted investigation on nonlinear vibration analysis of bio-inspired auxetic tubes. International Journal of Structural Integrity, 16(5), 1005-1047. https://doi.org/10.1108/IJSI-12-2024-0206
Hasirci, K., Yavas, D., & Irez, A. B. (2026). A Review of Advances in Composite Materials, Structural Optimization, and Machine Learning for Wind Turbine Blades: Challenges and Future Perspectives. Polymer Composites. https://doi.org/10.1002/pc.71353
He, W., Zhang, P., Hu, Z., Yang, S., Chen, W., He, T., Tang, L., Zheng, J., Li, R., & Xue, B. (2025). Enhanced-performance flexible pressure sensors enabled by synergistic effect of hierarchical porous structures for motion sensing and deep learning-assisted speech recognition. Journal of Colloid and Interface Science, 139706. https://doi.org/10.1016/j.jcis.2025.139706
Huang, N. (2024). Anomaly Detection in Structural Health Monitoring with Ensemble Learning and Reinforcement Learning. International Journal of Advanced Computer Science & Applications, 15(1), 121. https://doi.org/10.14569/ijacsa.2024.0150112
Huang, S., Guo, Y., Huo, P., & Li, Q. (2025). Redefining vibration sensing: Ai-driven analytics, self-powered systems, and multimodal fusion: A review. IEEE Sensors Journal, 25(15), 27922-27941. https://doi.org/10.1109/JSEN.2025.3579345
Liu, B., Dong, B., Jin, H., Zhu, P., Mu, Z., Li, Y., Liu, J., Meng, Z., Zhou, X., & Xu, P. (2025). Deep‐Learning‐Assisted Triboelectric Whisker Sensor Array for Real‐Time Motion Sensing of Unmanned Underwater Vehicle. Advanced Materials Technologies, 10(3), 2401053. https://doi.org/10.1002/admt.202401053
Lotfi Karkan, N., Shakeri, E., Sadeghi, N., & Banihashemi, S. (2025). Smart Surveillance of Structural Health: A Systematic Review of Deep Learning-Based Visual Inspection of Concrete Bridges Using 2D Images. Infrastructures, 10(12), 338. https://doi.org/10.3390/infrastructures10120338
Ma, L., Li, Z., Yang, S., & Wang, J. (2025). A review on vibration sensor: key parameters, fundamental principles, and recent progress on industrial monitoring applications. Vibration, 8(4), 56. https://doi.org/10.3390/vibration8040056
Park, S. U., Lee, H. K., Kim, H. B., Kim, D., Kim, W., Joo, J., Kim, B., Lee, B. W., Jung, Y. H., & Park, S. (2025). Wearable interactive full-body motion tracking and haptic feedback network systems with deep learning. Nature Communications, 16(1), 8604. https://doi.org/10.1038/s41467-025-63644-3
Paul, S., & Löfstrand, M. (2026). A review on condition monitoring and control of industrial drilling systems: fault detection, fuzzy control, and human-induced faults. Frontiers in Mechanical Engineering, 12, 1850568. https://doi.org/10.3389/fmech.2026.1850568
Poulopoulos, G., & Avramopoulos, H. (2026). Review of Optical Fiber and Integrated Photonic Sensors for Industry and Smart Manufacturing: Technologies, Applications, Structural Health Monitoring and AI-Enabled Sensing. Sensors, 26(11), 3581. https://doi.org/10.3390/s26113581
Quamar, M. M., & Nasir, A. (2024). Review on fault diagnosis and fault-tolerant control scheme for robotic manipulators: Recent advances in AI, machine learning, and digital twin. arXiv preprint arXiv:2402.02980. https://doi.org/10.48550/arXiv.2402.02980
Silva-Campillo, A., Herreros-Sierra, M., & Pérez-Arribas, F. (2026). Acoustics as a Structural Health Monitoring Tool in Naval and Offshore Structures: A Comprehensive Review. Applied Sciences, 16(3), 1477. https://doi.org/10.3390/app16031477
Soleimanpour, R., Saad, A. S., & Farhat, M. H. (2026). PZT-Based Guided Wave Structural Health Monitoring: A Review of Signal Processing, Machine Learning, and Hybrid Approaches. https://doi.org/10.20944/preprints202604.1930.v1
Su, H., Wang, H., Sang, D., Kumar, S., Xiao, D., Sun, J., & Wang, Q. (2026). Advancements in Machine Learning-Assisted Flexible Electronics: Technologies, Applications, and Future Prospects. Biosensors, 16(1), 58. https://doi.org/10.3390/bios16010058
Wei, C., Yu, Y., & Zhou, P. (2025). Intelligent Fault Diagnosis and Failure Analysis for Harmonic Reducers Using Multi-Sensor Fusion and Deep Learning. Available at SSRN 5587981. https://doi.org/10.2139/ssrn.5587981
Xu, H., Liu, L., Xu, J., Xiang, Y., & Xuan, F.-Z. (2024). Deep learning enables nonlinear Lamb waves for precise location of fatigue crack. Structural Health Monitoring, 23(1), 77-93. https://doi.org/10.1177/14759217231167076
Xu, Z.-Y., Mao, J.-Y., Ren, R.-X., Wu, Z.-Q., Lei, Y.-J., Han, L.-L., Chen, C., Fan, W., & Wang, Y. (2026). Research progress and challenges of intelligent in situ monitoring for laser additive manufacturing processes based on machine learning. Advances in Mechanical Engineering, 18(4), 16878132261442327. https://doi.org/10.1177/16878132261442327
Zhang, K., Li, Z., Zhang, J., Zhao, D., Pi, Y., Shi, Y., Wang, R., Chen, P., Li, C., & Chen, G. (2022). Biodegradable smart face masks for machine learning-assisted chronic respiratory disease diagnosis. ACS sensors, 7(10), 3135-3143. https://doi.org/10.1021/acssensors.2c01628
Zhu, R., Qin, H., Huang, Q., Zhi, Y., Meng, X., & Fu, Q. (2026). Progress and state-of-the-art on intelligent fault diagnosis of sliding bearings in reactor coolant pumps. Nuclear Engineering and Design, 451, 114761. https://doi.org/10.1016/j.nucengdes.2026.114761
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Reports in Mechanical Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.