Adaptive Learning of Hybrid Models for Nonlinear Model Predictive Control of Distillation Columns

TL;DR

This paper presents an adaptive hybrid modeling approach using neural networks trained on plant data to improve nonlinear model predictive control of distillation columns, enabling real-time application and performance enhancement over time.

Contribution

It introduces a novel adaptive learning framework that updates hybrid models solely based on plant measurements, replacing static models with continuously improved ones.

Findings

Control performance improves steadily with adaptation.

Approaches high fidelity model performance in the limit.

Enables real-time, data-driven NMPC for distillation columns.

Abstract

Nonlinear model predictive control (NMPC) requires accurate and computationally efficient plant models. Our previous work has shown that the classical compartmentalization model reduction approach for distillation columns can be enhanced by replacing parts of the system of equations by artificial neural networks (ANNs) trained on offline solved solutions to improve computational performance. In real-life applications, the absence of a high-fidelity model for data generation can, however, prevent the deployment of this approach. Therefore, we propose a method that utilizes solely plant measurement data, starting from a small initial data set and then continuously adapting to newly measured data. The efficacy of the proposed approach is examined in silico for a distillation column from literature. To this end, we first adjust our reduced hybrid mechanistic/data-driven modeling approach that originally builds on compartmentalization to a stage-aggregation procedure, tailoring it for the application within the adaptive learning framework. Second, we apply an adaptive learning algorithm that trains the ANNs replacing the stationary stage-to-stage calculations on newly available data. We apply the adaptive learning of the hybrid model within a regulatory NMPC framework and conduct closed-loop simulations. We demonstrate that by using the proposed method, the control performance can be steadily improved over time compared to a non-adaptive approach while being real-time applicable. Moreover, we show that the performance when using either a model trained on excessive amounts of offline generated data or the original high-fidelity model can be approached in the limit.