Deep Learning of Delay-Compensated Backstepping for Reaction–Diffusion PDEs
Shanshan Wang, Mamadou Diagne, Miroslav Krstić
Abstract
With deep neural network approximations of partial differential equation (PDE) backstepping, for each new functional coefficient of the PDE plant, the gains are obtained through a function evaluation. In this article, we expand this framework to control of cascaded PDE systems from distinct classes: a reaction–diffusion plant, which is a parabolic PDE, with input delay, which is a hyperbolic PDE. The DeepONet-approximated nonlinear operator for the control gain is a cascade/composition of the operators defined by one hyperbolic PDE of the Goursat form and one parabolic PDE on a rectangle, both of which are bilinear in their input functions and not explicitly solvable. For the DeepONet-approximated delay-compensated PDE backstepping controller, we guarantee exponential stability in the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$L^{2}$</tex-math></inline-formula> norm of the plant state and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H^{1}$</tex-math></inline-formula> norm of the input delay state.