Learning-enabled stochastic predictive control for nonlinear discrete-time step backward high-order fully actuated systems

International Journal of Systems Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 16

Published: Jan. 3, 2025

In this paper, we seamlessly integrate machine learning techniques with stochastic Model Predictive Control (MPC) to address the regulation problem of nonlinear discrete-time step backward High-Order Fully Actuated (HOFA) systems additive disturbance. By exploiting full-actuation characteristic HOFA system, neatly eliminate non-linearity thus circumventing complex computation uncertainty propagation in MPC. To cope random disturbance, its probability distribution on each principal component is well captured from data based analysis, and bound effectively estimated via kernel density estimation quantile functions. Based upon such probabilistic information, impose constraint tightening state limits define terminal sets by drawing concept tubes. On basis, employ MPC for receding horizon control systems, which recursive feasibility stability are proved theoretically. Finally, numerical experiments an application hydrogen electrolyzer temperature used demonstrate merits proposed approach comparison state-of-the-art methods.

Language: Английский

Sliding-Mode Disturbance Observer-Based HOFA Predictive Control of Spacecraft Flying-Around

Published: May 10, 2024

Language: Английский