Adaptive feedback control by constrained approximate dynamic programming

被引：33

作者：

Ferrari, Silvia ^{[1
]}

Steck, James E. ^{[2
]}

Chandramohan, Rajeev ^{[2
]}

机构：

[1] Duke Univ, Dept Mech Engn, Durham, NC 27708 USA

[2] Wichita State Univ, Dept Aerosp Engn, Wichita, KS 67260 USA

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2008年 / 38卷 / 04期

基金：

美国国家科学基金会;

关键词：

approximate dynamic programming (ADP); constrained optimization; feedback control; neural networks (NNs);

D O I：

10.1109/TSMCB.2008.924140

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A constrained approximate dynamic programming (ADP) approach is presented for designing adaptive neural network (NN) controllers with closed-loop stability and performance guarantees. Prior knowledge of the linearized equations of motion is used to guarantee that the closed-loop system meets performance and stability objectives when the plant operates in a linear parameter-varying (LPV) regime. In the presence of unmodeled dynamics or failures, the NN controller adapts to optimize its performance online, whereas constrained ADP guarantees that the LPV baseline performance is preserved at all times. The effectiveness of an adaptive NN flight controller is demonstrated for simulated control failures, parameter variations, and near-stall dynamics.

引用

页码：982 / 987

页数：6

共 19 条

[1] Nearly optimal state feedback control of constrained nonlinear systems using a neural networks HJB approach [J].