(769a) A Modifier Adaptation Approach to Real-Time Optimization Employing Machine Learning and Trust-Region Techniques

The business benefits of real-time optimization (RTO) are not disputed, but deployment penetration and success have been relatively low, e.g. compared with long established advanced control techniques. The causes for this are many, but in particular, companies invariably need to employ highly-qualified process control engineers to design, install and continually maintain RTO applications to preserve benefits.

Modifier Adaptation [1,2] has its origins in the technique of Integrated System Optimization and Parameter Estimation [3], but differs in the fact that no parameter estimation is required. These RTO schemes have the ability to reach plant optimality upon convergence, despite the presence of structural plant-model mismatch. However, this comes at the cost of having to estimate gradient terms from process measurements.

This work investigate a new class of modifier-adaptation schemes, which embed a physical model in order to minimize risk during the exploration, in combination with machine learning techniques to capture the plant-model mismatch in a non-parametric way. Building upon the recent work by Ferreira et al. [4], our focus is on Gaussian processes herein, and we present an improved algorithm that relies on trust-region ideas in order to expedite and robustify convergence. The size of the trust region is adjusted based on the Gaussian process predictors' ability to capture the plant-model mismatch in the cost and constraints. Conditions under which this approach is globally convergence are studied by establishing a parallel with trust-region methods in derivative-free optimization [5]. Finally, we illustrate these new modifier-adaptation schemes on several benchmark problems and compare their performance to other RTO approaches.

References:

1. Chachuat B., Srinivasan B., Bonvin D. (2009) Adaptation strategies for real-time optimization. Comput. Chem. Eng. 33:1557-1567
2. Marchetti A.G., François G., Faulwasser T., Bonvin D. (2016) Modifier adaptation for real-time optimization—Methods and applications. Processes 4:55.
3. Roberts P.D., Williams T.W. (1981) On an algorithm for combined system optimisation and parameter estimation. Automatica 17:199-209.
4. Ferreira T.A., Shukla H.A., Faulwasser T., Jones C.N., Bonvin D. (2018) Real-time optimization of uncertain process systems via modifier adaptation and Gaussian processes, in: European Control Conference (ECC’18).
5. Conn A.R., Scheinberg K., Vicente L.N. (2009) Introduction to Derivative-Free Optimization, MPS-SIAM Book Series on Optimization, Philadelphia (PA).