Improvised Failure Detection for Centrifugal Pumps Using Delta and Python: How Effectively Iot Sensors Data Can Be Processed and Stored for Monitoring to Avoid Latency in Reporting
DOI:
https://doi.org/10.64917/fecsit/Volume02Issue10-03Keywords:
Centrifugal Pumps, Predictive Maintenance, IoT Sensors, Vibration Analysis, Motor Current Monitoring, Mechanical Seal Leakage, Delta LakeAbstract
Centrifugal pumps are critical in industrial operations where unplanned failures can cause costly downtime and safety risks. Traditional maintenance methods often fail to detect early anomalies in vibration, motor current, and seal integrity. This study addresses that gap by developing an IoT-enabled failure detection framework that leverages Delta Lake and Python to enable scalable, real-time monitoring and predictive maintenance. The proposed system integrates MEMS accelerometers, SCT 013 current sensors, and leak detection modules through an ESP32 microcontroller, ensuring reliable data acquisition and ACID-compliant storage. Delta Lake facilitates seamless handling of both streaming and batch data while maintaining version control and schema integrity. Experimental validation using real and simulated datasets demonstrates reliable anomaly detection, efficient schema evolution, and resilience under high-frequency sensor loads. The research provides strong quantitative validation that Delta Lake with Python enables 25% less downtime, 30% higher maintenance efficiency and with improved real-time responsiveness (<500 ms), proving Delta Lake as a more robust, scalable, ACID- compliant, and high-performance data framework for IoT- based predictive maintenance in centrifugal pumps compared to traditional formats like Parquet. Overall, this research contributes to enhance Industry 4.0-driven predictive maintenance by integrating dependable IoT sensing with resilient data management and analytics for centrifugal pump monitoring.
References
Donthi, Sai Nikhil (2025). Evaluating effectiveness of Delta Lake over Parquet in Python pipeline. International Journal of Data Science and Machine Learning, 5(2), 126–144. https://doi.org/10.55640/ijdsml-05-02-12
Luo, Y., Zhang, W., Fan, Y., Han, Y., Li, W., & Acheaw, E. (2021). Analysis of vibration characteristics of centrifugal pump mechanical seal under wear and damage degree. Shock and Vibration, 2021, Article 6670741. https://doi.org/10.1155/2021/6670741
Kumar, V. N., V. A., & Kumar, M. L. H. (2024).IoT-based predictive maintenance for electrical machines and industrial automation. International Research Journal of Modern Engineering and Technology Science, 6(12), 4013–4027. https://doi.org/10.56726/IRJMETS65758
Chevtchenko, S. F., et al. (2023, October). Predictive maintenance model based on anomaly detection in induction motors: A machine learning approach using real-time IoT data. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 3173–3180. https://doi.org/10.3850/978-981-18-8071-1_P578-cd
Varanis, M., Silva, A., Mereles, A., & Pederiva, R. (2018, November). MEMS accelerometers for mechanical vibrations analysis: A comprehensive review with applications. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40(11). https://doi.org/10.1007/S40430-018-1445-5
Y. Ziegler, S., Woodward, R. C., Iu, H. H. C., & Borle, L. J. (2009, April). Current sensing techniques: A review. IEEE Sensors Journal, 9(4), 354–376. https://doi.org/10.1109/JSEN.2009.2013914
Bruinsma, S., Geertsma, R. D., Loendersloot, R., & Tinga, T. (2024, February). Motor current and vibration monitoring dataset for various faults in an E-motor-driven centrifugal pump. Data in Brief, 52. https://doi.org/10.1016/J.DIB.2023.109987
Zöller, M. A., Mauthe, F., Zeiler, P., Lindauer, M., & Huber, M. F. (2023). Automated machine learning for remaining useful life predictions. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2907–2912. https://doi.org/10.1109/SMC53992.2023.10394031
Balali, F., Nouri, J., Nasiri, A., & Zhao, T. (2020, January). Data intensive industrial asset management: IoT-based algorithms and implementation (pp. 1– 236). https://doi.org/10.1007/978-3-030-35930-0 Wu, F., Wu, Q., Tan, Y., & Xu, X. (2024, May 27).
Remaining useful life prediction based on deep learning: A survey. Sensors (Basel), 24(11), 3454. https://doi.org/10.3390/s24113454
Garcia, J., Rios-Colque, L., Peña, A., & Rojas, L. (2025). Condition monitoring and predictive maintenance in industrial equipment: An NLP- assisted review of signal processing, hybrid models, and implementation challenges. Applied Sciences, 15(10), 5465. https://doi.org/10.3390/app15105465
Jang, H.-C., & Chang, H.-P. (2024). AL-powered EdgeFL: Achieving low latency and high accuracy in federated learning. In Proceedings of the 2024 IEEE 99th Vehicular Technology Conference (VTC2024- Spring) (pp. 1–5). IEEE. https://doi.org/10.1109/VTC2024-Spring62846.2024.10683166
Albshaier, L., Almarri, S., & Albuali, A. (2025). Federated learning for cloud and edge security: A systematic review of challenges and AI opportunities. Electronics, 14(5), 1019. https://doi.org/10.3390/electronics14051019
Zhan, S., Huang, L., Luo, G., Zheng, S., Gao, Z., & Chao, H. C. (2025). A review on federated learning architectures for privacy-preserving AI: Lightweight and secure cloud–edge–end collaboration. Electronics, 14(13), 2512. https://doi.org/10.3390/electronics14132512
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 sai nikhil
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their articles published in this journal. All articles are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly cited.