TY - GEN
T1 - Unmatched Uncertainty Mitigation Through Neural Network Supported Model Predictive Control
AU - Gasparino, Mateus V.
AU - Mishra, Prabhat K.
AU - Chowdhary, Girish
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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, DNNs as oracle are considered difficult to employ with LBMPC due to the technical difficulties associated with the 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 a jet engine. These results indicate that the proposed approach is implementable in real time and carries the theoretical guarantees of LBMPC.
AB - 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, DNNs as oracle are considered difficult to employ with LBMPC due to the technical difficulties associated with the 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 a jet engine. These results indicate that the proposed approach is implementable in real time and carries the theoretical guarantees of LBMPC.
UR - http://www.scopus.com/inward/record.url?scp=85184822920&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85184822920&partnerID=8YFLogxK
U2 - 10.1109/CDC49753.2023.10384150
DO - 10.1109/CDC49753.2023.10384150
M3 - Conference contribution
AN - SCOPUS:85184822920
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 3555
EP - 3560
BT - 2023 62nd IEEE Conference on Decision and Control, CDC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 62nd IEEE Conference on Decision and Control, CDC 2023
Y2 - 13 December 2023 through 15 December 2023
ER -