A real-time dynamic optimal guidance scheme using a general regression neural network

M. A. Hossain, A. A. M. Madkour, K. P. Dahal, Li Zhang

Research output: Contribution to journalArticle

Abstract

This paper presents an investigation into the challenges in implementing a hard real-time optimal non-stationary system using general regression neural network (GRNN). This includes investigation into the dynamics of the problem domain, discretisation of the problem domain to reduce the computational complexity, parameters selection of the optimization algorithm, convergence guarantee for real-time solution and off-line optimization for real-time solution. In order to demonstrate these challenges, this investigation considers a real-time optimal missile guidance algorithm using GRNN to achieve an accurate interception of the maneuvering targets in three-dimension. Evolutionary Genetic Algorithms (GAs) are used to generate optimal guidance training data set for a large missile defense space to train the GRNN. The Navigation, Constant of the Proportional Navigation Guidance and the target position at launching are considered for optimization using GAs. This is achieved by minimizing the. miss distance and missile flight time. Finally, the merits of the proposed schemes for real-time accurate interception are presented and discussed through a set of experiments.
Original languageEnglish
Pages (from-to)1230-1236
JournalEngineering Applications of Artificial Intelligence
Volume26
Issue number4
DOIs
Publication statusPublished - Apr 2013
Externally publishedYes

Keywords

  • Optimal guidance algorithms
  • Proportional navigation guidance
  • Genetic algorithm
  • General regression neural network
  • Computational complexity
  • Real-time solution

Cite this

@article{ca745f5065ce4d7ca70841b47371ec1c,
title = "A real-time dynamic optimal guidance scheme using a general regression neural network",
abstract = "This paper presents an investigation into the challenges in implementing a hard real-time optimal non-stationary system using general regression neural network (GRNN). This includes investigation into the dynamics of the problem domain, discretisation of the problem domain to reduce the computational complexity, parameters selection of the optimization algorithm, convergence guarantee for real-time solution and off-line optimization for real-time solution. In order to demonstrate these challenges, this investigation considers a real-time optimal missile guidance algorithm using GRNN to achieve an accurate interception of the maneuvering targets in three-dimension. Evolutionary Genetic Algorithms (GAs) are used to generate optimal guidance training data set for a large missile defense space to train the GRNN. The Navigation, Constant of the Proportional Navigation Guidance and the target position at launching are considered for optimization using GAs. This is achieved by minimizing the. miss distance and missile flight time. Finally, the merits of the proposed schemes for real-time accurate interception are presented and discussed through a set of experiments.",
keywords = "Optimal guidance algorithms, Proportional navigation guidance, Genetic algorithm, General regression neural network, Computational complexity, Real-time solution",
author = "Hossain, {M. A.} and Madkour, {A. A. M.} and Dahal, {K. P.} and Li Zhang",
year = "2013",
month = "4",
doi = "10.1016/j.engappai.2012.10.007",
language = "English",
volume = "26",
pages = "1230--1236",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier B.V.",
number = "4",

}

A real-time dynamic optimal guidance scheme using a general regression neural network. / Hossain, M. A.; Madkour, A. A. M.; Dahal, K. P.; Zhang, Li.

In: Engineering Applications of Artificial Intelligence, Vol. 26, No. 4, 04.2013, p. 1230-1236.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A real-time dynamic optimal guidance scheme using a general regression neural network

AU - Hossain, M. A.

AU - Madkour, A. A. M.

AU - Dahal, K. P.

AU - Zhang, Li

PY - 2013/4

Y1 - 2013/4

N2 - This paper presents an investigation into the challenges in implementing a hard real-time optimal non-stationary system using general regression neural network (GRNN). This includes investigation into the dynamics of the problem domain, discretisation of the problem domain to reduce the computational complexity, parameters selection of the optimization algorithm, convergence guarantee for real-time solution and off-line optimization for real-time solution. In order to demonstrate these challenges, this investigation considers a real-time optimal missile guidance algorithm using GRNN to achieve an accurate interception of the maneuvering targets in three-dimension. Evolutionary Genetic Algorithms (GAs) are used to generate optimal guidance training data set for a large missile defense space to train the GRNN. The Navigation, Constant of the Proportional Navigation Guidance and the target position at launching are considered for optimization using GAs. This is achieved by minimizing the. miss distance and missile flight time. Finally, the merits of the proposed schemes for real-time accurate interception are presented and discussed through a set of experiments.

AB - This paper presents an investigation into the challenges in implementing a hard real-time optimal non-stationary system using general regression neural network (GRNN). This includes investigation into the dynamics of the problem domain, discretisation of the problem domain to reduce the computational complexity, parameters selection of the optimization algorithm, convergence guarantee for real-time solution and off-line optimization for real-time solution. In order to demonstrate these challenges, this investigation considers a real-time optimal missile guidance algorithm using GRNN to achieve an accurate interception of the maneuvering targets in three-dimension. Evolutionary Genetic Algorithms (GAs) are used to generate optimal guidance training data set for a large missile defense space to train the GRNN. The Navigation, Constant of the Proportional Navigation Guidance and the target position at launching are considered for optimization using GAs. This is achieved by minimizing the. miss distance and missile flight time. Finally, the merits of the proposed schemes for real-time accurate interception are presented and discussed through a set of experiments.

KW - Optimal guidance algorithms

KW - Proportional navigation guidance

KW - Genetic algorithm

KW - General regression neural network

KW - Computational complexity

KW - Real-time solution

U2 - 10.1016/j.engappai.2012.10.007

DO - 10.1016/j.engappai.2012.10.007

M3 - Article

VL - 26

SP - 1230

EP - 1236

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 4

ER -