Published June 20, 2025 | Version 1.0.0
Conference paper Open

Improving Process Monitoring via Dynamic Multi-Fidelity Modeling

Creators

  • 1. ROR icon Slovak University of Technology in Bratislava
  • 2. ROR icon University of Pisa
  • 3. Slovnaft

Description

We study real-time process monitoring, where employed online sensors yield inaccurate information. A multi-fidelity (MF) modeling approach is adopted that integrates dynamic information from online, low-fidelity (LF) data with infrequent, high-fidelity (HF) laboratory measurements. The proposed methodology is demonstrated on a composition monitoring problem derived from real oil refinery operations. The developed MF model exhibits a significant improvement in accuracy with respect to both LF data (online sensor) and the HF model (standard soft sensor). The results highlight the potential of MF modeling for improving process monitoring and control through the integration of diverse data sources.

Files

DYCOPS25_faber_final.pdf

Files (2.6 MB)

Name Size Download all
md5:3cede03d694aded5ce06a0ae4cb67c8d
2.6 MB Preview Download

Additional details

Funding

European Commission
FrontSeat – Fostering Opportunities Towards Slovak Excellence in Advanced Control for Smart Industries 101079342
The Vega Science Trust
Efficient control of industrial plants using data VEGA 1/0691/21
Slovak Research and Development Agency
Energy-efficient Safe and Secure Process Control APVV-20-0261

References

  • Armenise, G., Vaccari, M., Bacci di Capaci, R., and Pannocchia, G. (2018). An open-source system identification package for multivariable processes. In UKACC 12th International Conference on Control, 152–157.
  • Bahramian, M., Dereli, R.K., Zhao, W., Giberti, M., and Casey, E. (2023). Data to intelligence: The role of data-driven models in wastewater treatment. Expert Systems with Applications, 217, 119453.
  • Bastos, P.D.A., Galinha, C.F., Santos, M.A., Carvalho, P.J., and Crespo, J.G. (2022). Predicting the concentration of hazardous phenolic compounds in refinery wastewater—a multivariate data analysis approach. Environmental Science and Pollution Research, 29(1), 1482–1490.
  • Bradford, E., Imsland, L., Zhang, D., and del Rio Chanona, E.A. (2020). Stochastic data-driven model predictive control using gaussian processes. Computers & Chemical Engineering, 139, 106844.
  • Colombo, A.W., Karnouskos, S., Kaynak, O., Shi, Y., and Yin, S. (2017). Industrial cyberphysical systems: A backbone of the fourth industrial revolution. IEEE Industrial Electronics Magazine, 11(1), 6–16.
  • Efroymson, M.A. (1960). Multiple regression analysis. In A. Ralston and H.S. Wilf (eds.), Mathematical Methods for Digital Computers. Wiley, New York.
  • Fáber, R., Mojto, M., Ľubušký, K., and Paulen, R. (2024). From data to alarms: Data-driven anomaly detection techniques in industrial settings. In ESCAPE34 - PSE24.
  • Ge, Z., Chen, T., and Song, Z. (2011). Quality prediction for polypropylene production process based on CLGPR model. Control Engineering Practice, 19(5), 423–432.
  • Geladi, P. and Kowalski, B. (1986). Partial least square regression: A tutorial. Anal. Chim. Acta, 35, 1–17.
  • Giselle Fernández-Godino, M. (2023). Review of multifidelity models. Advances in Computational Science and Engineering, 1(4), 351–400.
  • Kadlec, P., Gabrys, B., and Strandt, S. (2009). Datadriven soft sensors in the process industry. Computers & Chemical Engineering, 33(4), 795–814.
  • Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R.P., Tang, J., and Liu, H. (2017). Feature selection: A data perspective. ACM Comput. Surv., 50(6).
  • Pall (2018). Refineries: Application focus h2so4 alkylation process description. Technical report, Pall Corp.
  • Pannocchia, G. and Calosi, M. (2010). A predictor form parsimonious algorithm for closed-loop subspace identification. J. Process Control, 20(4), 517– 524.
  • Pearson, K. (1901). Liii. on lines and planes of closest fit to systems of points in space. London Edinburgh Philos. Mag. & J. Sci., 2(11), 559–572.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. J. Machine LearningResearch, 12, 2825– 2830.
  • Perdikaris, P., Venturi, D., Royset, J.O., and Karniadakis, G.E. (2015). Multi-fidelity modelling via recursive co-kriging and gaussian–markov random fields. Proc. of the Royal Society A, 471(2171), 20150018.
  • Rasmussen, C.E. (2004). Gaussian Processes in Machine Learning, 63–71. Springer Berlin Heidelberg.
  • Rousseeuw, P. and Driessen, K. (1999). A fast algorithm for the minimum covariance determinant estimator. Technometrics, 41, 212–223.
  • Santosa, F. and Symes, W.W. (1986). Linear inversion of band-limited reflection seismograms. SIAM Journal on Scientific and Statistical Computing, 7(4), 1307–1330.
  • Speight, J.G. (2020). The refinery of the future. Gulf Professional Publishing, Elsevier.
  • Yin, S. and Kaynak, O. (2015). Big data for modern industry: challenges and trends [point of view]. Proceedings of the IEEE, 103(2), 143–146.
  • Zhu, J., Ge, Z., Song, Z., and Gao, F. (2018). Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data. Annu. Rev. Control, 46, 107–133.