A Generalized Policy Iteration Adaptive Dynamic Programming Algorithm for Optimal Control of Discrete-Time Nonlinear Systems with Actuator Saturation

In this study, a nonquadratic performance function is introduced to overcome the saturation nonlinearity in actuators. Then a novel solution, generalized policy iteration adaptive dynamic programming algorithm, is applied to deal with the problem of optimal control. To achieve this goal, we use two...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Neural Networks - ISNN 2017 Vol. 10262; pp. 60 - 65
Main Authors Lin, Qiao, Wei, Qinglai, Zhao, Bo
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2017
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Adaptive dynamic programming
Neural network
Optimal control
Saturating actuators
Online AccessGet full text
ISBN9783319590806
3319590804
ISSN0302-9743
1611-3349
DOI10.1007/978-3-319-59081-3_8

Cover

More Information
Summary:In this study, a nonquadratic performance function is introduced to overcome the saturation nonlinearity in actuators. Then a novel solution, generalized policy iteration adaptive dynamic programming algorithm, is applied to deal with the problem of optimal control. To achieve this goal, we use two neural networks to approximate control vectors and performance index function. Finally, this paper focuses on an example simulated on Matlab, which verifies the excellent convergence of the mentioned algorithm and feasibility of this scheme.
ISBN:9783319590806
3319590804
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-59081-3_8