Operator learning for prescribed-time stabilization of reaction-diffusion systems

TL;DR

This paper introduces a neural-operator-based method to achieve real-time prescribed-time stabilization of reaction-diffusion systems, significantly reducing computational costs compared to traditional kernel PDE solutions.

Contribution

It proposes a neural-operator approach to approximate backstepping kernels, enabling real-time control of reaction-diffusion systems with time-varying coefficients.

Findings

Neural-operator approximation reduces kernel computation time by orders of magnitude.

The method guarantees prescribed-time stability under bounded approximation errors.

Numerical experiments confirm real-time stabilization capabilities.

Abstract

This paper addresses boundary prescribed-time stabilization of a one-dimensional heat equation with spatially and temporally varying coefficients. In contrast to asymptotic or exponential stabilization, prescribed-time stabilization ensures convergence to equilibrium within a user-defined time that is independent of the initial condition, a property that is particularly attractive in applications with stringent transient performance requirements. The backstepping design for this problem requires solving, at each time instant, a two-dimensional time-dependent kernel Partial Differential Equation (PDE) whose solution continuously varies with the plant coefficients. The repeated numerical solution of this parabolic kernel PDE results in a prohibitive computational burden, thereby limiting real-time applicability. To overcome this limitation, we propose a neural-operator-based approximation of the mapping from the time-varying system coefficient to the corresponding backstepping kernel. The operator is trained offline using representative solutions of the kernel PDE and subsequently deployed online to generate the required time-varying kernels in real time. We establish, via Lyapunov analysis, that the resulting neural-operator-based controller preserves prescribed-time stability provided that the operator approximation error satisfies an explicit bound. Furthermore, we investigate a direct approximation of the full feedback law mapping the plant parameter functions and state measurements to the boundary control input. For this setting, we prove semiglobal practical prescribed-time stability of the closed-loop system. Numerical experiments demonstrate that the proposed approach reduces the computational cost of kernel generation by several orders of magnitude, thereby enabling real-time prescribed-time stabilization for heat equations with spatially and temporally varying coefficients.