Unmatched uncertainty mitigation through neural network supported model predictive control
This work addresses control challenges in systems like jet engines with unmatched uncertainties, offering an incremental improvement by integrating neural networks into existing MPC frameworks.
The paper tackles the problem of controlling systems with unmatched and bounded uncertainties of unknown structure by developing a deep learning-based model predictive control algorithm, achieving real-time implementability with theoretical guarantees as validated on a jet engine compression system model.
This paper presents a deep learning based model predictive control (MPC) algorithm for systems with unmatched and bounded state-action dependent uncertainties of unknown structure. We utilize a deep neural network (DNN) as an oracle in the underlying optimization problem of learning based MPC (LBMPC) to estimate unmatched uncertainties. Generally, non-parametric oracles such as DNN are considered difficult to employ with LBMPC due to the technical difficulties associated with estimation of their coefficients in real time. We employ a dual-timescale adaptation mechanism, where the weights of the last layer of the neural network are updated in real time while the inner layers are trained on a slower timescale using the training data collected online and selectively stored in a buffer. Our results are validated through a numerical experiment on the compression system model of jet engine. These results indicate that the proposed approach is implementable in real time and carries the theoretical guarantees of LBMPC.