Published June 2, 2025 | Version 1.0.0
Conference paper Open

Integrating Linear and Nonlinear Models for Enhanced Process Monitoring

Creators

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

Description

This study explores data-driven approaches for modeling industrial processes by employing linear and nonlinear techniques to predict output variables based on available input measurements. Linear regression-based techniques are compared with nonlinear machine learning models to evaluate their predictive capabilities. The analysis considers models trained on high-accuracy & low-frequency laboratory data alongside models leveraging low-accuracy & high-frequency sensor measurements. A hybrid methodology enhances predictive performance by integrating additional process information in the training process. Our findings show that this hybrid approach reduces the RMSE from 0.74 to 0.38 compared to models that rely solely on sensor measurements.

Files

IEEE_PC25draft.pdf

Files (569.4 kB)

Name Size Download all
md5:6da581a7a85dc9bc8f72744e789980d7
569.4 kB Preview Download

Additional details

Funding

Slovak Research and Development Agency
Data Based Process Control APVV-21-0019
The Vega Science Trust
Efficient control of industrial plants using data 1/0691/21
European Commission
FrontSeat – Fostering Opportunities Towards Slovak Excellence in Advanced Control for Smart Industries Twinning 101079342

References

  • Mohsen Soori, Behrooz Arezoo, and Roza Dastres. Internet of things for smart factories in industry 4.0, a review. Internet of Things and Cyber-Physical Systems, 3:192– 204, 2023.
  • Xiao Wang and Han Liu. Soft sensor based on stacked auto-encoder deep neural network for air preheater rotor deformation prediction. Advanced Engineering Informatics, 36:112–119, 2018.
  • Robust model-based soft sensor: Design and application. IFAC Proceedings Volumes, 47(3):5491–5496, 2014. 19th IFAC World Congress.
  • Matthias Medl, Vignesh Rajamanickam, Gerald Striedner, and Joseph Newton. Development and validation of an artificial neural-network-based optical density soft sensor for a high-throughput fermentation system. Processes, 11(1), 2023.
  • Xianglin Zhu, Khalil Ur Rehman, Bo Wang, and Muhammad Shahzad. Modern soft-sensing modeling methods for fermentation processes. Sensors, 20(6):1771, 2020.
  • George E Dahl, Dong Yu, Li Deng, and Alex Acero. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on audio, speech, and language processing, 20(1):30–42, 2011.
  • Ladislav Švistun, Norbert Kováˇc, and Miroslav Variny. Prevádzková optimalizácia a možnosti uplatnenia nových technológií pri výrobe alkylátu, 2021.
  • J. Weitkamp and Y. Traa. Isobutane/butene alkylation on solid catalysts. where do we stand? Catalysis Today, 49(1):193–199, 1999.
  • Surinder Parkash. Gasoline manufacturing processes. In Refining Processes Handbook, pages 109–152. Gulf Professional Publishing, Burlington, 2003.
  • R. Fáber, M. Vaccari, R. Bacci di Capaci, K. L'ubušký, G. Pannocchia, and R. Paulen. Improving process monitoring via dynamic multi-fidelity modeling. In 14th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems, 2025.
  • Karl Pearson. Liii. on lines and planes of closest fit to systems of points in space. London Edinburgh Philos. Mag. & J. Sci., 2(11):559–572, 1901.
  • Paul Geladi and Bruce Kowalski. Partial least square regression: A tutorial. Anal. Chim. Acta, 35:1–17, 1986.
  • Fadil Santosa and William W. Symes. Linear inversion of band-limited reflection seismograms. SIAM Journal on Scientific and Statistical Computing, 7(4):1307–1330, 1986.
  • Frank Rosenblatt. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6):386–408, 1958.
  • Guido Van Rossum and Fred L Drake Jr. Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam, 1995.
  • Francois Chollet et al. Keras, 2015.
  • Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. Scikit-learn: Machine learning in python. Journal of machine learning research, 12(Oct):2825– 2830, 2011.