SNAC Convergence and Use in Adaptive Autopilot Design

Songjie Chen; Yang Yang; S. N. Balakrishnan; Nhan T. Nguyen; Kalmanje Krishnakumar

doi:10.1109/IJCNN.2009.5178706

SNAC Convergence and Use in Adaptive Autopilot Design

Songjie Chen
, Yang Yang
, S. N. Balakrishnan
, Nhan T. Nguyen
, Kalmanje Krishnakumar

Missouri University of Science and Technology

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, approximate dynamic programming (ADP)based design tools are developed for adaptive control of aircraft control under nominal and damaged conditions. Nominal control of the system is computed with a Single Network Adaptive Critic(SNAC) derived through principles of ADP. Convergence of SNAC training is shown by reducing it to solving a set of nonlinear algebraic equations in weights. Unlike many adaptive control approaches, we develop approximate optimal control expressions to handle uncertainties. Uncertainties are calculated with an online neural network with guaranteed convergence. Longitudinal dynamics of an aircraft is used to illustrate the working of the developed algorithms. ©2009 IEEE.

Original language	American English
Journal	Proceedings of the International Joint Conference on Neural Networks
DOIs	https://doi.org/10.1109/IJCNN.2009.5178706
State	Published - Jan 1 2009

Disciplines

Aerospace Engineering
Mechanical Engineering

Access to Document

10.1109/IJCNN.2009.5178706License: Unspecified

https://doi.org/10.1109/IJCNN.2009.5178706

Cite this

@article{4714bc02392643a68e9fcb6624f89d19,

title = "SNAC Convergence and Use in Adaptive Autopilot Design",

abstract = " In this paper, approximate dynamic programming (ADP)based design tools are developed for adaptive control of aircraft control under nominal and damaged conditions. Nominal control of the system is computed with a Single Network Adaptive Critic(SNAC) derived through principles of ADP. Convergence of SNAC training is shown by reducing it to solving a set of nonlinear algebraic equations in weights. Unlike many adaptive control approaches, we develop approximate optimal control expressions to handle uncertainties. Uncertainties are calculated with an online neural network with guaranteed convergence. Longitudinal dynamics of an aircraft is used to illustrate the working of the developed algorithms. {\textcopyright}2009 IEEE.",

author = "Songjie Chen and Yang Yang and Balakrishnan, \{S. N.\} and Nguyen, \{Nhan T.\} and Kalmanje Krishnakumar",

year = "2009",

month = jan,

day = "1",

doi = "10.1109/IJCNN.2009.5178706",

language = "American English",

journal = "Proceedings of the International Joint Conference on Neural Networks",

issn = "2161-4407",

}

TY - JOUR

T1 - SNAC Convergence and Use in Adaptive Autopilot Design

AU - Chen, Songjie

AU - Yang, Yang

AU - Balakrishnan, S. N.

AU - Nguyen, Nhan T.

AU - Krishnakumar, Kalmanje

PY - 2009/1/1

Y1 - 2009/1/1

N2 - In this paper, approximate dynamic programming (ADP)based design tools are developed for adaptive control of aircraft control under nominal and damaged conditions. Nominal control of the system is computed with a Single Network Adaptive Critic(SNAC) derived through principles of ADP. Convergence of SNAC training is shown by reducing it to solving a set of nonlinear algebraic equations in weights. Unlike many adaptive control approaches, we develop approximate optimal control expressions to handle uncertainties. Uncertainties are calculated with an online neural network with guaranteed convergence. Longitudinal dynamics of an aircraft is used to illustrate the working of the developed algorithms. ©2009 IEEE.

AB - In this paper, approximate dynamic programming (ADP)based design tools are developed for adaptive control of aircraft control under nominal and damaged conditions. Nominal control of the system is computed with a Single Network Adaptive Critic(SNAC) derived through principles of ADP. Convergence of SNAC training is shown by reducing it to solving a set of nonlinear algebraic equations in weights. Unlike many adaptive control approaches, we develop approximate optimal control expressions to handle uncertainties. Uncertainties are calculated with an online neural network with guaranteed convergence. Longitudinal dynamics of an aircraft is used to illustrate the working of the developed algorithms. ©2009 IEEE.

UR - https://scholarsmine.mst.edu/mec_aereng_facwork/897

UR - https://doi.org/10.1109/IJCNN.2009.5178706

U2 - 10.1109/IJCNN.2009.5178706

DO - 10.1109/IJCNN.2009.5178706

M3 - Article

SN - 2161-4407

JO - Proceedings of the International Joint Conference on Neural Networks

JF - Proceedings of the International Joint Conference on Neural Networks

ER -

SNAC Convergence and Use in Adaptive Autopilot Design

Abstract

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this