Immunized neurocontrol-concepts and initial results

Author

KrishnaKumar, K.

Author_Institution

Dept. of Aerosp. Eng., Alabama Univ., Tuscaloosa, AL, USA

fYear

1992

fDate

6/6/1992 12:00:00 AM

Firstpage

146

Lastpage

168

Abstract

The role of artificial neural networks in control of complex systems is seeing a rapid growth due to the potential of these networks to emulate complex, non-linear systems and thus help in the automated control of such systems. The paper addresses an important area in automatic control, namely, adaptive control. Strong connections between concepts from immunology, genetic algorithms, and adaptive neurocontrol are drawn. Immunology is the science of in-built defense mechanism that is present in all living beings to protect them against external attacks. The science of immunology has many parallels to the robust adaptive control problem. Some of these parallels are presented and based on these parallels, a procedure to realize an immunized neurocontrol structure is developed. Initial results of the implementation of this procedure in adaptive control of an uncertain UH-1 longitudinal helicopter model are included

Keywords

adaptive control; genetic algorithms; neural nets; adaptive control; artificial neural networks; automatic control; complex systems; genetic algorithms; immunized neurocontrol; uncertain UH-1 longitudinal helicopter model; Adaptive control; Adaptive systems; Artificial neural networks; Automatic control; Control systems; Evolution (biology); Genetic algorithms; Immune system; Nonlinear control systems; Robust control;

fLanguage

English

Publisher

ieee

Conference_Titel

Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92. International Workshop on

Conference_Location

Baltimore, MD

Print_ISBN

0-8186-2787-5

Type

conf

DOI

10.1109/COGANN.1992.273941

Filename

273941