Bayesian Optimization for Tuning Nonlinear Predictive Control of an Acetone Purification Column
DOI:
https://doi.org/10.6919/ICJE.202611_12(11).0005Keywords:
Acetone Purification Column; Nonlinear Predictive Control; Bayesian Optimization; Logarithmic Impurity Model; Controller Tuning; Co-Simulation.Abstract
A Bayesian optimization method is developed to tune predictive control for an acetone purification column operating in a high-purity region. Aspen Dynamics is coupled with MATLAB through OPC DA. With the reboiler duty fixed, reflux flow is manipulated using an incremental ridge regression model identified from 20 historical trajectories in logarithmic impurity coordinates. A nonlinear inverse transformation provides overhead composition predictions. The inner controller optimizes three move blocks subject to magnitude and rate limits, while an outer Gaussian process and expected improvement criterion select the move penalty with post-run purity-margin screening. Fifteen valid co-simulation runs include relative feed-flow change up to ±0.1% and relative feed-acetone mole-fraction decrease up to 0.1%. In the negative-flow confirmation run, the frozen penalty value of 0.01 has a minimum overhead acetone mole fraction value of 0.999004900 and causes a 22.41% reduction in the fixed performance score value relative to the mean of two runs with an original penalty value of 0.05. All valid samples from the three frozen-parameter confirmation runs meet the 0.999 criterion; but too much purity still remains when faced with the positive-flow disturbance. These results indicate sampled product-quality satisfaction and higher aggregate performance in the negative-flow case, within the local disturbance range and operating limits investigated here.
Downloads
References
[1] Skogestad, S. (1997). Dynamics and control of distillation columns-A critical survey. Modeling, Identification and Control, 18(3), 177–217. https://doi.org/10.4173/mic.1997.3.1
[2] Rawlings, J. B., Mayne, D. Q., & Diehl, M. M. (2017). Model predictive control: Theory, computation, and design (2nd ed.). Nob Hill Publishing. https://sites.engineering.ucsb.edu/~jbraw/mpc/
[3] Hewing, L., Wabersich, K. P., Menner, M., et al. (2020). Learning based model predictive control: Toward safe learning in control. Annual Review of Control, Robotics, and Autonomous Systems, 3, 269–296. https://doi.org/10.1146/annurev control 090419 075625
[4] Chen, S., & Billings, S. A. (1989). Representations of non linear systems: The NARMAX model. International Journal of Control, 49(3), 1013–1032. https://doi.org/10.1080/00207178908559683
[5] Hoerl, A. E., & Kennard, R. W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55–67. https://doi.org/10.1080/00401706.1970.10488634
[6] Jones, D. R., Schonlau, M., & Welch, W. J. (1998). Efficient global optimization of expensive black box functions. Journal of Global Optimization, 13, 455–492. https://doi.org/10.1023/A:1008306431147
[7] Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian processes for machine learning. MIT Press. https://doi.org/10.7551/mitpress/3206.001.0001
[8] Frazier, P. I. (2018). A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811. https://doi.org/10.48550/arXiv.1807.02811
[9] Marco, A., Hennig, P., Bohg, J., et al. (2016). Automatic LQR tuning based on Gaussian process global optimization. In Proceedings of the 2016 IEEE International Conference on Robotics and Automation (pp. 270–277). IEEE. https://doi.org/10.1109/ICRA.2016.7487144
[10] Kudva, A., Huynh, M. T., Mesbah, A., et al. (2024). Efficient performance based MPC tuning in high dimensions using Bayesian optimization over sparse subspaces. IFAC PapersOnLine, 58(14), 458–463. https://doi.org/10.1016/j.ifacol.2024.08.379
[11] Xu, W., Jones, C. N., Svetozarevic, B., et al. (2024). Violation aware contextual Bayesian optimization for controller performance optimization with unmodeled constraints. Journal of Process Control, 138, 103212. https://doi.org/10.1016/j.jprocont.2024.103212
[12] Gardner, J. R., Kusner, M. J., Xu, Z. E., Weinberger, K. Q., & Cunningham, J. P. (2014). Bayesian optimization with inequality constraints. In Proceedings of the 31st International Conference on Machine Learning (Vol. 32, No. 2, pp. 937–945). PMLR. https://proceedings.mlr.press/v32/gardner14.html
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Core Journal of Engineering

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.




