Article Sidebar

Download
Statistic
Read Counter : 0

Main Article Content

Abstract

This study analyzes a centrifugal pumping system in an industrial facility using fifteen months of operational data collected from a Supervisory Control and Data Acquisition (SCADA) system. Applying a flow greater than zero criterion, 15,049 records corresponding to active operation were retained; after quality control and removal of incomplete and feature-inconsistent observations, 14,501 records were used for the multivariable analysis. Instead of analyzing variables independently, the study characterizes system behavior through the relationships among hydraulic, electrical, and fluid-related variables. Principal Component Analysis (PCA) is applied first, and the first two components explain 69.8% of the total variance. Based on this reduced representation, K-means clustering identifies two operational regimes, corresponding to dominant and low-load conditions. A Gaussian Mixture Model (GMM) applied to fluid density reveals two product regimes with mean values of 716.84 kg/m³ and 830.35 kg/m³. In addition, anomaly detection based on the Mahalanobis distance identifies 73 anomalous observations (0.5% of the dataset), associated with reduced discharge pressure, lower pressure differential, and decreased power consumption, indicating degraded operating conditions. The proposed framework provides a physically interpretable representation of system behavior, enabling the identification of operational regimes, product-related variations, and anomalous conditions within a unified analytical approach. This supports its application in industrial monitoring environments aligned with Industry 4.0 (I4.0) principles.  

Keywords

SCADA data analytics Multivariable analysis Anomaly detection Operational regimes Centrifugal pumps Condition monitoring

Article Details

Author Biographies

Johnatan Corrales-Bonilla, Universidad Técnica de Cotopaxi, Cotopaxi, Ecuador

Johnatan Corrales-Bonilla is a Mechatronics Engineer and holds a Master’s degree in Applied Mathematics. He is affiliated with Universidad Técnica de Cotopaxi, Ecuador. His research focuses on industrial systems, multivariable data analysis, and data-driven methodologies for monitoring electromechanical processes. His areas of interest include SCADA systems, anomaly detection, and industrial applications aligned with Industry 4.0.

William Hidalgo-Osorio, Universidad Técnica de Cotopaxi, Cotopaxi, Ecuador

Electrical Engineer with expertise in industrial systems, energy systems, and data-driven analysis. Currently affiliated with Universidad Técnica de Cotopaxi. Research interests include SCADA systems, predictive maintenance, and industrial data analytics.

How to Cite
Corrales Bonilla, J., Hidalgo Osorio, W., Corrales Oñate, C., & Viteri Tapia, F. (2026). A data-driven multivariable framework for operational regime identification, product transition detection, and anomaly detection in industrial pumping systems using SCADA data. Future Technology, 5(3), 150–163. Retrieved from https://fupubco.com/futech/article/view/964
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. D. Leite, E. Andrade, D. Rativa, and A. M. A. Maciel, “Fault Detection and Diagnosis in Industry 4.0: A Review on Challenges and Opportunities,” Sensors, vol. 25, no. 1, 2025, doi: 10.3390/s25010060.
  2. T. K. Das, S. Adepu, and J. Zhou, “Anomaly Detection in Industrial Control Systems Using Logical Analysis of Data,” Computers & Security, vol. 96, 2020, doi: 10.1016/j.cose.2020.101935.
  3. S. Mokhtari, A. Abbaspour, K. K. Yen, and A. Sargolzaei, “A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data,” Electronics, vol. 10, no. 4, 2021, doi: 10.3390/electronics10040407.
  4. E. Dong, X. Zhan, H. Yan, Y. Bai, R. Wang, and Z. Cheng, “A data-driven intelligent predictive maintenance decision framework for mechanical systems integrating transformer and kernel density estimation,” Computers & Industrial Engineering, vol. 201, 2025, doi: 10.1016/j.cie.2025.110868.
  5. Y. Du, Y. Huang, G. Wan, and P. He, “Deep Learning-Based Cyber–Physical Feature Fusion for Anomaly Detection in Industrial Control Systems,” Mathematics, vol. 10, no. 22, 2022, doi: 10.3390/math10224373.
  6. M.-C. Kim, J.-H. Lee, D.-H. Wang, and I.-S. Lee, “Induction Motor Fault Diagnosis Using Support Vector Machine, Neural Networks, and Boosting Methods,” Sensors, vol. 23, no. 5, 2023, doi: 10.3390/s23052585.
  7. C. Han and G. Gim, “Time-Series-Based Anomaly Detection in Industrial Control Systems Using Generative Adversarial Networks,” Processes, vol. 13, no. 9, 2025, doi: 10.3390/pr13092885.
  8. J. Cho and S. Gong, “Dynamic data abstraction-based anomaly detection for industrial control systems,” Electronics, vol. 13, no. 1, p. 158, 2024, doi: 10.3390/electronics13010158.
  9. J. Liu, Y. Sha, W. Zhang, Y. Yan, and X. Liu, “Anomaly Detection Method for Industrial Control System Operation Data Based on Time–Frequency Fusion Feature Attention Encoding,” Sensors, vol. 24, no. 18, 2024, doi: 10.3390/s24186131.
  10. M. M. Aslam, L. C. D. Silva, R. A. A. H. M. Apong, and A. Tufail, “An Optimized Anomaly Detection Framework in Industrial Control Systems Through Grey Wolf Optimizer and Autoencoder Integration,” Scientific Reports, vol. 15, 2025, doi: 10.1038/s41598-025-12775-0.
  11. J. Pang, X. Pu, and C. Li, “A Hybrid Algorithm Incorporating Vector Quantization and One-Class Support Vector Machine for Industrial Anomaly Detection,” IEEE Transactions on Industrial Informatics, vol. 18, no. 12, pp. 8786-8796., 2022, doi: 10.1109/TII.2022.3145834.
  12. C. Goetz and B. G. Humm, “Process Anomaly Detection in Cyber–Physical Production Systems Based on Conditional Discrete-Time Dynamic Graphs,” Applied Sciences, vol. 15, no. 21, 2025, doi: 10.3390/app152111354.
  13. L. Xu, K. Shang, X. Zhang, C. Zheng, and L. Pan, “Multi-Scale Feature Fusion-Based Real-Time Anomaly Detection in Industrial Control Systems,” Electronics, vol. 14, no. 8, 2025, doi: 10.3390/electronics14081645.
  14. B. Kim, M. A. Alawami, E. Kim, S. Oh, J. Park, and H. Kim, “A Comparative Study of Time Series Anomaly Detection Models for Industrial Control Systems,” Sensors, vol. 23, no. 3, 2023, doi: 10.3390/s23031310.
  15. S. Kim et al., “Two-Phase Industrial Control System Anomaly Detection Using Communication Patterns and Deep Learning,” Electronics, vol. 13, no. 8, 2024, doi: 10.3390/electronics13081520.
  16. A. L. Alfeo, M. G. C. A. Cimino, G. Manco, E. Ritacco, and G. Vaglini, “Using an Autoencoder in the Design of an Anomaly Detector for Smart Manufacturing,” Pattern Recognition Letters, vol. 136, 2020, doi: 10.1016/j.patrec.2020.06.008.
  17. W. Zaman, M. F. Siddique, S. Ullah, F. Saleem, and J.-M. Kim, “Hybrid Deep Learning Model for Fault Diagnosis in Centrifugal Pumps,” Machines, vol. 12, no. 12, 2024, doi: 10.3390/machines12120905.
  18. C. E. Sunal, V. Velisavljevic, V. Dyo, B. Newton, and J. Newton, “Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning,” Sensors, vol. 24, no. 8, 2024, doi: 10.3390/s24082442.
  19. Z. Zhao et al., “Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study,” ISA Transactions, vol. 107, pp. 224-255., 2020, doi: 10.1016/j.isatra.2020.08.010.
  20. Z. Xu et al., “A Digital Twin System for Centrifugal Pump Fault Diagnosis Driven by Transfer Learning Based on Graph Convolutional Neural Networks,” Computers in Industry, vol. 163, 2024, doi: 10.1016/j.compind.2024.104155.
  21. A. Kumar, R. Kumar, J. Xiang, Z. Qiao, Y. Zhou, and H. Shao, “Digital Twin-Assisted AI Framework for Bearing Defect Diagnosis in Centrifugal Pump,” Measurement, vol. 235, 2024, doi: 10.1016/j.measurement.2024.115013.
  22. C. V. Prasshanth, S. N. Venkatesh, T. K. Mahanta, N. R. Sakthivel, and V. Sugumaran, “Fault Diagnosis of Monoblock Centrifugal Pumps Using Pre-Trained Deep Learning Models,” Engineering Applications of Artificial Intelligence, vol. 136, 2024, doi: 10.1016/j.engappai.2024.109022.
  23. M. A. B. Syed, M. R. Hasan, N. I. Chowdhury, M. H. Rahman, and I. Ahmed, “A Systematic Review of Time Series Algorithms and Analytics in Predictive Maintenance,” Decision Analytics Journal, vol. 15, 2025, doi: 10.1016/j.dajour.2025.100573.
  24. H. Chen, J. Li, X.-B. Wang, L.-Q. Yu, and Z.-X. Yang, “Review of Intelligent Fault Diagnosis for Rotating Machinery under Imperfect Data Conditions,” Expert Systems with Applications, vol. 285, 2025, doi: 10.1016/j.eswa.2025.127726.
  25. Z. Li, H. Jiang, and Y. Dong, “A Convolutional-Transformer Reinforcement Learning Agent for Rotating Machinery Fault Diagnosis,” Expert Systems with Applications, vol. 198, 2025, doi: 10.1016/j.eswa.2025.126669.
  26. O. Rashad, O. Attallah, and I. Morsi, “A smart PLC-SCADA framework for monitoring petroleum products terminals in industry 4.0 via machine learning,” Measurement and Control, vol. 55, no. 5–6, pp. 1–14, 2022, doi: 10.1177/00202940221103305.
  27. J. Zheng, C. Wang, Y. Liang, Q. Liao, Z. Li, and B. Wang, “Deeppipe: A deep-learning method for anomaly detection of multi-product pipelines,” Energy, vol. 252, p. 125025, 2022, doi: 10.1016/j.energy.2022.125025.
  28. A. Melo, M. Melo, and J. Pinto, “Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey,” Processes, vol. 12, no. 2, p. 251, 2024, doi: 10.3390/pr12020251.
  29. Y. Cui, W. Fan, and Y. Zhou, “Dimensionality reducing Gaussian mixture-based reconstruction for fault detection in multimode processes,” The Canadian Journal of Chemical Engineering, vol. 102, no. 12, pp. 4267–4280, 2024, doi: 10.1002/cjce.25308.
  30. J. K. Seo, J. Lee, B. Kim, W. Shim, and J. T. Seo, “AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems,” Electronics, vol. 15, no. 1, 2026, doi: 10.3390/electronics15010020.