Embedded TinyML for Predictive Maintenance: Vibration Analysis on ESP32 with Real-Time Fault Detection in Industrial Equipment
DOI:
https://doi.org/10.63503/j.ijcma.2025.114Keywords:
TinyML, Predictive Maintenance, ESP32, ADXL345, Vibration Analysis, Fault Detection, Edge Computing, Industrial IoT, Real-Time MonitoringAbstract
The rapid evolution of embedded intelligence within industrial environments has catalyzed the development of lightweight, real-time predictive maintenance systems. Conventional fault diagnosis approaches often depend on centralized, resource-intensive infrastructures that are ill-suited for distributed and energy-constrained settings. Addressing these limitations, this paper introduces a TinyML-based framework for real-time vibration analysis and fault detection deployed on the ESP32 microcontroller, a cost-effective, ultra-low-power embedded platform. Vibration data—acquired using a triaxial ADXL345 accelerometer—serve as key indicators of mechanical integrity, enabling the early identification of anomalies such as misalignment, imbalance, and bearing defects.
The proposed system features an optimized 1D convolutional neural network (CNN) designed to operate within the memory and processing limitations of the ESP32. The architecture incorporates adaptive sampling, in-situ feature extraction, and edge-based classification, allowing for autonomous decision-making without cloud dependency. A custom dataset encompassing four machine states—normal, misaligned, imbalanced, and bearing-worn—is created using controlled experimental setups to simulate real-world operational conditions. Two deep learning models are implemented and compared for performance in terms of accuracy, memory usage, and inference time on-device. Results demonstrate that the proposed TinyML approach achieves over 92% fault detection accuracy while maintaining a compact computational footprint.
This framework offers a scalable, low-latency solution for predictive maintenance in Industry 4.0 applications, reducing unplanned downtime and enhancing machine reliability. The integration of vibration-based analysis with embedded machine learning advances the field toward decentralized, real-time condition monitoring in smart industrial systems.
References
[1] Chen, H. Y., & Lee, C. H. (2020). Vibration signals analysis by explainable artificial intelligence (XAI) approach: Application on bearing faults diagnosis. IEEE Access, 8, 134246-134256. doi: 10.1109/ACCESS.2020.3006491
[2] Chaudhari, B. S., Ghorpade, S. N., Zennaro, M., & Paškauskas, R. (Eds.). (2024). TinyML for Edge Intelligence in IoT and LPWAN Networks. Elsevier. https://doi.org/10.1016/C2023-0-00166-2
[3] Katib, I., Albassam, E., Sharaf, S. A., & Ragab, M. (2025). Safeguarding IoT consumer devices: Deep learning with TinyML driven real-time anomaly detection for predictive maintenance. Ain Shams Engineering Journal, 16(2), 103281. https://doi.org/10.1016/j.asej.2025.103281
[4] Qian, G., Lu, S., Pan, D., Tang, H., Liu, Y., & Wang, Q. (2019). Edge computing: A promising framework for real-time fault diagnosis and dynamic control of rotating machines using multi-sensor data. IEEE Sensors Journal, 19(11), 4211-4220. doi: 10.1109/JSEN.2019.2899396
[5] Liu, S., Ha, D. S., Shen, F., & Yi, Y. (2021). Efficient neural networks for edge devices. Computers & Electrical Engineering, 92, 107121. https://doi.org/10.1016/j.compeleceng.2021.107121
[6] Kumar, S. R., & Devakumar, J. (2023). Recurrent neural network based sensor fault detection and isolation for nonlinear systems: Application in PWR. Progress in Nuclear Energy, 163, 104836. https://doi.org/10.1016/j.pnucene.2023.104836
[7] Navardi, M., Humes, E., & Mohsenin, T. (2022, December). E2edgeai: Energy-efficient edge computing for deployment of vision-based dnns on autonomous tiny drones. In 2022 IEEE/ACM 7th Symposium on Edge Computing (SEC) (pp. 504-509). IEEE. doi: 10.1109/SEC54971.2022.00077
[8] Wu, Y., Ianakiev, K., & Govindaraju, V. (2002). Improved k-nearest neighbor classification. Pattern recognition, 35(10), 2311-2318. https://doi.org/10.1016/S0031-3203(01)00132-7
[9] Dantas, P. V., Sabino da Silva Jr, W., Cordeiro, L. C., & Carvalho, C. B. (2024). A comprehensive review of model compression techniques in machine learning. Applied Intelligence, 54(22), 11804-11844. https://doi.org/10.1007/s10489-024-05747-w
[10] Ficco, M., Guerriero, A., Milite, E., Palmieri, F., Pietrantuono, R., & Russo, S. (2024). Federated learning for IoT devices: Enhancing TinyML with on-board training. Information Fusion, 104, 102189. https://doi.org/10.1016/j.inffus.2023.102189
[11] Mendula, M., Bellavista, P., Levorato, M., & de Guevara Contreras, S. L. (2025). A novel middleware for adaptive and efficient split computing for real-time object detection. Pervasive and Mobile Computing, 108, 102028. https://doi.org/10.1016/j.pmcj.2025.102028
[12] Kioko, P. C. K., Abuodha, S., Mwero, J., & Kuria, Z. (2023). Experimental assessment of train-induced soil vibration characteristics using Arduino-based accelerometers. Cogent Engineering, 10(2), 2245201. https://doi.org/10.1080/23311916.2023.2245201
[13] Ranganathan, G., Fernando, X., & Fuqian, S. (2021). Inventive Communication and Computational Technologies. https://doi.org/10.1007/978-981-97-7710-5
[14] Iannelli, P., Angeletti, F., Gasbarri, P., Panella, M., & Rosato, A. (2022). Deep learning-based Structural Health Monitoring for damage detection on a large space antenna. Acta Astronautica, 193, 635-643. https://doi.org/10.1016/j.actaastro.2021.08.003
[15] Neupane, D., Bouadjenek, M. R., Dazeley, R., & Aryal, S. (2025). Data-driven machinery fault diagnosis: A comprehensive review. Neurocomputing, 129588. https://doi.org/10.1016/j.neucom.2025.129588
[16] Aldin, H. N. S., Ghods, M. R., Nayebipour, F., & Torshiz, M. N. (2024). A comprehensive review of energy harvesting and routing strategies for IoT sensors sustainability and communication technology. Sensors International, 5, 100258. https://doi.org/10.1016/j.sintl.2023.100258
[17] Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9, 611-629. https://doi.org/10.1007/s13244-018-0639-9
[18] Djenouri, Y., Belbachir, A. N., Cano, A., & Belhadi, A. (2024). Spatio-temporal visual learning for home-based monitoring. Information Fusion, 101, 101984. https://doi.org/10.1016/j.inffus.2023.101984
[19] Bibi, U., Mazhar, M., Sabir, D., Butt, M. F. U., Hassan, A., Ghazanfar, M. A., ... & Abdul, W. (2024). Advances in Pruning and Quantization for Natural Language Processing. IEEE Access. doi: 10.1109/ACCESS.2024.3465631
[20] Wu, Y., Sicard, B., & Gadsden, S. A. (2024). Physics-informed machine learning: A comprehensive review on applications in anomaly detection and condition monitoring. Expert Systems with Applications, 124678. https://doi.org/10.1016/j.eswa.2024.124678
[21] Sandeep Singh Sikarwar. (2025). Computation Intelligence Techniques for Security in IoT Devices. International Journal on Computational Modelling Applications, 2(1), 15–27. https://doi.org/10.63503/j.ijcma.2025.48
[22] Rohan Vaghela, & Jigar Sarda. (2025). Optimized Symmetric Positive Definite Neural Networks: A Novel Approach to Weather Prediction . International Journal on Computational Modelling Applications, 2(1), 1–14. https://doi.org/10.63503/j.ijcma.2025.47
[23] Prakhar Mittal, & Rahul Malik. (2025). Optimized Physics-Informed Neural Network Framework for Wild Animal Activity Detection and Classification with Real Time Alert Message Generation. International Journal on Computational Modelling Applications, 2(1), 42–52. https://doi.org/10.63503/j.ijcma.2025.50
