TY - GEN
T1 - Causal Deep Operator Networks for Data-Driven Modeling of Dynamical Systems
AU - Nghiem, Truong X.
AU - Nguyen, Thang
AU - Nguyen, Binh T.
AU - Nguyen, Linh
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The deep operator network (DeepONet) architecture is a promising approach for learning functional operators, that can represent dynamical systems described by ordinary or partial differential equations. However, it has two major limitations, namely its failures to account for initial conditions and to guarantee the temporal causality - a fundamental property of dynamical systems. This paper proposes a novel causal deep operator network (Causal-DeepONet) architecture for incorporating both the initial condition and the temporal causality into data-driven learning of dynamical systems, overcoming the limitations of the original DeepONet approach. This is achieved by adding an independent root network for the initial condition and independent branch networks conditioned, or switched on/off, by time-shifted step functions or sigmoid functions for expressing the temporal causality. The proposed architecture was evaluated and compared with two baseline deep neural network methods and the original DeepONet method on learning the thermal dynamics of a room in a building using real data. It was shown to not only achieve the best overall prediction accuracy but also enhance substantially the accuracy consistency in multistep predictions, which is crucial for predictive control.
AB - The deep operator network (DeepONet) architecture is a promising approach for learning functional operators, that can represent dynamical systems described by ordinary or partial differential equations. However, it has two major limitations, namely its failures to account for initial conditions and to guarantee the temporal causality - a fundamental property of dynamical systems. This paper proposes a novel causal deep operator network (Causal-DeepONet) architecture for incorporating both the initial condition and the temporal causality into data-driven learning of dynamical systems, overcoming the limitations of the original DeepONet approach. This is achieved by adding an independent root network for the initial condition and independent branch networks conditioned, or switched on/off, by time-shifted step functions or sigmoid functions for expressing the temporal causality. The proposed architecture was evaluated and compared with two baseline deep neural network methods and the original DeepONet method on learning the thermal dynamics of a room in a building using real data. It was shown to not only achieve the best overall prediction accuracy but also enhance substantially the accuracy consistency in multistep predictions, which is crucial for predictive control.
UR - http://www.scopus.com/inward/record.url?scp=85187275650&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85187275650&partnerID=8YFLogxK
U2 - 10.1109/SMC53992.2023.10394294
DO - 10.1109/SMC53992.2023.10394294
M3 - Conference contribution
AN - SCOPUS:85187275650
T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SP - 1136
EP - 1141
BT - 2023 IEEE International Conference on Systems, Man, and Cybernetics
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023
Y2 - 1 October 2023 through 4 October 2023
ER -