Data-driven Nonlinear Model Reduction using Koopman Theory: Integrated Control Form and NMPC Case Study
This work addresses model reduction for control applications in domains like chemical engineering, but it appears incremental as it builds on existing Koopman theory with a hybrid method.
The paper tackled the problem of model reduction for nonlinear dynamical systems with controls using Koopman theory, proposing a deep-learning approach that enabled real-time capable nonlinear model predictive control for a high-purity cryogenic distillation column.
We use Koopman theory for data-driven model reduction of nonlinear dynamical systems with controls. We propose generic model structures combining delay-coordinate encoding of measurements and full-state decoding to integrate reduced Koopman modeling and state estimation. We present a deep-learning approach to train the proposed models. A case study demonstrates that our approach provides accurate control models and enables real-time capable nonlinear model predictive control of a high-purity cryogenic distillation column.