Online Identification and Control of Aerospace Vehicles Using Recurrent Networks

Zhenning Hu; S. N. Balakrishnan

doi:10.1109/CCA.1999.806180

Online Identification and Control of Aerospace Vehicles Using Recurrent Networks

Zhenning Hu
, S. N. Balakrishnan

Missouri University of Science and Technology

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

Abstract

Methods for estimating the aerospace system parameters and controlling them through two neural networks are presented in this study. We equate the energy function of Hopfield neural network to integral square of errors in the system dynamics and extract the parameters of a system. Parameter convergence is proved. For control, we equate the equilibrium status of a "modified" Hopfield neural network to the steady state Riccati solution with the system parameters as inputs. Through these two networks, we present the online identification and control of an aircraft using its nonlinear dynamics.

Original language	American English
Journal	Proceedings of the 1999 IEEE International Conference on Control Applications, 1999
DOIs	https://doi.org/10.1109/CCA.1999.806180
State	Published - Jan 1 1999

Keywords

Aerospace Control
Aerospace Vehicle Control
Energy Function
Hopfield Neural Nets
Hopfield Neural Network
Integral Square of Errors
Neural Networks
Neurocontrollers
Nonlinear Dynamical Systems
Nonlinear Dynamics
Online Control
Online Identification
Parameter Convergence
Recurrent Networks
Recurrent Neural Nets
Riccati Equations
Steady State Riccati Solution
System Dynamics
System Parameters

Disciplines

Aerospace Engineering
Mechanical Engineering

Access to Document

10.1109/CCA.1999.806180License: Unspecified

Online Identification and Control of Aerospace Vehicles Using RecFinal published version, 517 KBLicense: Unspecified

Cite this

@article{bd47c5a249384e0e9523c83bbc592fec,

title = "Online Identification and Control of Aerospace Vehicles Using Recurrent Networks",

abstract = " Methods for estimating the aerospace system parameters and controlling them through two neural networks are presented in this study. We equate the energy function of Hopfield neural network to integral square of errors in the system dynamics and extract the parameters of a system. Parameter convergence is proved. For control, we equate the equilibrium status of a {"}modified{"} Hopfield neural network to the steady state Riccati solution with the system parameters as inputs. Through these two networks, we present the online identification and control of an aircraft using its nonlinear dynamics.",

keywords = "Aerospace Control, Aerospace Vehicle Control, Energy Function, Hopfield Neural Nets, Hopfield Neural Network, Integral Square of Errors, Neural Networks, Neurocontrollers, Nonlinear Dynamical Systems, Nonlinear Dynamics, Online Control, Online Identification, Parameter Convergence, Recurrent Networks, Recurrent Neural Nets, Riccati Equations, Steady State Riccati Solution, System Dynamics, System Parameters",

author = "Zhenning Hu and Balakrishnan, \{S. N.\}",

year = "1999",

month = jan,

day = "1",

doi = "10.1109/CCA.1999.806180",

language = "American English",

journal = "Proceedings of the 1999 IEEE International Conference on Control Applications, 1999",

}

TY - JOUR

T1 - Online Identification and Control of Aerospace Vehicles Using Recurrent Networks

AU - Hu, Zhenning

AU - Balakrishnan, S. N.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Methods for estimating the aerospace system parameters and controlling them through two neural networks are presented in this study. We equate the energy function of Hopfield neural network to integral square of errors in the system dynamics and extract the parameters of a system. Parameter convergence is proved. For control, we equate the equilibrium status of a "modified" Hopfield neural network to the steady state Riccati solution with the system parameters as inputs. Through these two networks, we present the online identification and control of an aircraft using its nonlinear dynamics.

AB - Methods for estimating the aerospace system parameters and controlling them through two neural networks are presented in this study. We equate the energy function of Hopfield neural network to integral square of errors in the system dynamics and extract the parameters of a system. Parameter convergence is proved. For control, we equate the equilibrium status of a "modified" Hopfield neural network to the steady state Riccati solution with the system parameters as inputs. Through these two networks, we present the online identification and control of an aircraft using its nonlinear dynamics.

KW - Aerospace Control

KW - Aerospace Vehicle Control

KW - Energy Function

KW - Hopfield Neural Nets

KW - Hopfield Neural Network

KW - Integral Square of Errors

KW - Neural Networks

KW - Neurocontrollers

KW - Nonlinear Dynamical Systems

KW - Nonlinear Dynamics

KW - Online Control

KW - Online Identification

KW - Parameter Convergence

KW - Recurrent Networks

KW - Recurrent Neural Nets

KW - Riccati Equations

KW - Steady State Riccati Solution

KW - System Dynamics

KW - System Parameters

UR - https://scholarsmine.mst.edu/mec_aereng_facwork/3450

U2 - 10.1109/CCA.1999.806180

DO - 10.1109/CCA.1999.806180

M3 - Article

JO - Proceedings of the 1999 IEEE International Conference on Control Applications, 1999

JF - Proceedings of the 1999 IEEE International Conference on Control Applications, 1999

ER -

Online Identification and Control of Aerospace Vehicles Using Recurrent Networks

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this