Abstract

This paper presents a class of modified Hopfield neural networks and their use in solving aircraft optimal control and identification problems. This class of networks consists of parallel recurrent networks which have variable dimensions that can be changed to fit the problems under consideration. It has a structure to implement an inverse transformation that is essential for embedding optimal control gain sequences. Equilibrium solutions are discussed. Energy minimization of the networks leads to identification of the system parameters. Numerical results are provided to identify the dynamics of an aircraft, and the corresponding optimal control is calculated online. Comparison of the neural network solutions with point-wise optimal control using LQR formulation for this multivariable control problem shows near identical results throughout the trajectories.

Department(s)

Mechanical and Aerospace Engineering

Publication Status

Open Access

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 American Institute of Aeronautics and Astronautics, All rights reserved.

Publication Date

01 Jan 1996

Share

 
COinS