ĐIỀU KHIỂN THÍCH NGHI BỀN VỮNG DÙNG HỌC CỦNG CỐ CHO HỆ THỐNG PHI TUYẾN VỚI RÀNG BUỘC NGÕ VÀO

Abstract

ROBUST ADAPTIVE CONTROL USING REINFORCEMENT LEARNING FOR NONLINEAR SYSTEM WITH INPUT CONSTRAINTS

Nguyen Tan Luy⁽¹⁾, Nguyen Thien Thanh⁽¹⁾, Nguyen Thi Phưong Ha⁽²⁾

(1) National Key Lab of Digital Control and System Engineering, VNU-HCM

(2) University of Technology, VNU-HCM

ABSTRACT: This paper proposes a novel approach to design a controller in discrete time for the class of uncertain nonlinear systems in the presence of magnitude constrains of control signal which are treated as the saturation nonlinearity. A associative law between reinforcement learning algorithm based on adaptive NRBF neural networks  and the theory of robust control  is set up in a novel control structure, in which the proposed controller allows learning and control on-line to compensate multiple uncertain nonlinearities as well as minimizing both the tracking performance index function and the unknown nonlinear dynamic approximation errors. The novel theorem of  robust stabilization of the closed-loop system is declared and proved. Simulation results verify the theoretical analysis.