Neurocontrol of nonlinear systems via local memory neurons

S. M. Amin; E. Y. Rodin; A. Y. Wu

doi:10.1016/S0895-7177(97)00266-5

Neurocontrol of nonlinear systems via local memory neurons

S. M. Amin, E. Y. Rodin, A. Y. Wu

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

1 Scopus citations

Abstract

In this report, we consider the part of our work which concerns the approximation of nonlinear dynamic systems using neural networks. Based on a new paradigm of neurons with local memory (NNLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NNLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed. For illustration of the approach simulation results for no nonlinear control of an aircraft encountering wind shear on take-off is presented.

Original language	English (US)
Pages (from-to)	65-92
Number of pages	28
Journal	Mathematical and Computer Modelling
Volume	27
Issue number	3
DOIs	https://doi.org/10.1016/S0895-7177(97)00266-5
State	Published - Feb 1998
Externally published	Yes

Bibliographical note

Funding Information:
*The work of the authors affiliated with the Center for Optimization and Semantic Control was supported in part by AFOSR under Grants No. 890158, F49 620-93-01-0012, and F49 620-96-l-0151. Earlier versions of this work have been reported in references [l-9].

Keywords

Aircraft
Control
Dynamic neural networks
Neurocontrol
Nonlinear control

Publisher link

10.1016/S0895-7177(97)00266-5

Find It

Find It at U of M Libraries

Cite this

@article{cd898db7f34148d5bf0fea5b9f74ede0,

title = "Neurocontrol of nonlinear systems via local memory neurons",

abstract = "In this report, we consider the part of our work which concerns the approximation of nonlinear dynamic systems using neural networks. Based on a new paradigm of neurons with local memory (NNLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NNLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed. For illustration of the approach simulation results for no nonlinear control of an aircraft encountering wind shear on take-off is presented.",

keywords = "Aircraft, Control, Dynamic neural networks, Neurocontrol, Nonlinear control",

author = "Amin, {S. M.} and Rodin, {E. Y.} and Wu, {A. Y.}",

note = "Funding Information: *The work of the authors affiliated with the Center for Optimization and Semantic Control was supported in part by AFOSR under Grants No. 890158, F49 620-93-01-0012, and F49 620-96-l-0151. Earlier versions of this work have been reported in references [l-9].",

year = "1998",

month = feb,

doi = "10.1016/S0895-7177(97)00266-5",

language = "English (US)",

volume = "27",

pages = "65--92",

journal = "Mathematical and Computer Modelling",

issn = "0895-7177",

publisher = "Elsevier Limited",

number = "3",

}

TY - JOUR

T1 - Neurocontrol of nonlinear systems via local memory neurons

AU - Amin, S. M.

AU - Rodin, E. Y.

AU - Wu, A. Y.

N1 - Funding Information: *The work of the authors affiliated with the Center for Optimization and Semantic Control was supported in part by AFOSR under Grants No. 890158, F49 620-93-01-0012, and F49 620-96-l-0151. Earlier versions of this work have been reported in references [l-9].

PY - 1998/2

Y1 - 1998/2

N2 - In this report, we consider the part of our work which concerns the approximation of nonlinear dynamic systems using neural networks. Based on a new paradigm of neurons with local memory (NNLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NNLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed. For illustration of the approach simulation results for no nonlinear control of an aircraft encountering wind shear on take-off is presented.

AB - In this report, we consider the part of our work which concerns the approximation of nonlinear dynamic systems using neural networks. Based on a new paradigm of neurons with local memory (NNLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NNLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed. For illustration of the approach simulation results for no nonlinear control of an aircraft encountering wind shear on take-off is presented.

KW - Aircraft

KW - Control

KW - Dynamic neural networks

KW - Neurocontrol

KW - Nonlinear control

UR - http://www.scopus.com/inward/record.url?scp=0032004993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032004993&partnerID=8YFLogxK

U2 - 10.1016/S0895-7177(97)00266-5

DO - 10.1016/S0895-7177(97)00266-5

M3 - Article

AN - SCOPUS:0032004993

SN - 0895-7177

VL - 27

SP - 65

EP - 92

JO - Mathematical and Computer Modelling

JF - Mathematical and Computer Modelling

IS - 3

ER -

Neurocontrol of nonlinear systems via local memory neurons

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this