Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System

This paper proposes a two-rate hybrid neural network system, which consists of two artificial neural network subsystems. These neural network subsystems are used as the dynamic subsystems controllers.1 This is because such neuromorphic controllers are especially suitable to control complex systems....

Full description

Bibliographic Details
Main Authors: ASTROV, I., TATARLY, S.
Format: Article
Language:English
Published: Stefan cel Mare University of Suceava 2007-04-01
Series:Advances in Electrical and Computer Engineering
Subjects:
Online Access:http://dx.doi.org/10.4316/AECE.2007.01004
id doaj-50fdb15e786146c89a77098b017001ed
record_format Article
spelling doaj-50fdb15e786146c89a77098b017001ed2020-11-24T23:13:03ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002007-04-01711822Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network SystemASTROV, I.TATARLY, S.TATARLY, S.This paper proposes a two-rate hybrid neural network system, which consists of two artificial neural network subsystems. These neural network subsystems are used as the dynamic subsystems controllers.1 This is because such neuromorphic controllers are especially suitable to control complex systems. An illustrative example - two-rate neural network hybrid control of decomposed stochastic model of a rigid guided missile over different operating conditions - was carried out using the proposed two-rate state-space decomposition technique. This example demonstrates that this research technique results in simplified low-order autonomous control subsystems with various speeds of actuation, and shows the quality of the proposed technique. The obtained results show that the control tasks for the autonomous subsystems can be solved more qualitatively than for the original system. The simulation and animation results with use of software package Simulink demonstrate that this research technique would work for real-time stochastic systems.http://dx.doi.org/10.4316/AECE.2007.01004Control systemsguided missilemulti-rateneural networkssimulation
collection DOAJ
language English
format Article
sources DOAJ
author ASTROV, I.
TATARLY, S.
TATARLY, S.
spellingShingle ASTROV, I.
TATARLY, S.
TATARLY, S.
Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
Advances in Electrical and Computer Engineering
Control systems
guided missile
multi-rate
neural networks
simulation
author_facet ASTROV, I.
TATARLY, S.
TATARLY, S.
author_sort ASTROV, I.
title Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
title_short Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
title_full Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
title_fullStr Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
title_full_unstemmed Simulation of Missile Autopilot with Two-Rate Hybrid Neural Network System
title_sort simulation of missile autopilot with two-rate hybrid neural network system
publisher Stefan cel Mare University of Suceava
series Advances in Electrical and Computer Engineering
issn 1582-7445
1844-7600
publishDate 2007-04-01
description This paper proposes a two-rate hybrid neural network system, which consists of two artificial neural network subsystems. These neural network subsystems are used as the dynamic subsystems controllers.1 This is because such neuromorphic controllers are especially suitable to control complex systems. An illustrative example - two-rate neural network hybrid control of decomposed stochastic model of a rigid guided missile over different operating conditions - was carried out using the proposed two-rate state-space decomposition technique. This example demonstrates that this research technique results in simplified low-order autonomous control subsystems with various speeds of actuation, and shows the quality of the proposed technique. The obtained results show that the control tasks for the autonomous subsystems can be solved more qualitatively than for the original system. The simulation and animation results with use of software package Simulink demonstrate that this research technique would work for real-time stochastic systems.
topic Control systems
guided missile
multi-rate
neural networks
simulation
url http://dx.doi.org/10.4316/AECE.2007.01004
work_keys_str_mv AT astrovi simulationofmissileautopilotwithtworatehybridneuralnetworksystem
AT tatarlys simulationofmissileautopilotwithtworatehybridneuralnetworksystem
AT tatarlys simulationofmissileautopilotwithtworatehybridneuralnetworksystem
_version_ 1725599657270181888