Title :
A novel intelligent neural guidance law design by using adjoint method
Author :
Jium-Ming Lin ; Cheng-Hung Lin
Author_Institution :
Dept. of Commun. Eng., Chung-Hua Univ., Hsinchu, Taiwan
Abstract :
In this study, we propose a novel intelligent neural guidance law by applying several neural network optimization algorithms alternatively in each step, such as Gradient Descent (GD), Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) methods. The missile turning rate time constant, radome slope error, initial heading error and the noise effects in the guidance loop (such as target maneuver, glint, and fading noises) are taken into consideration by using the adjoint simulation technique. Comparisons with the traditional proportional navigation (PN) method and those applying only one optimization algorithm for the cases of lower and higher altitudes are also made; note that the miss distances obtained by the proposed neural guidance law are always lower.
Keywords :
conjugate gradient methods; missile guidance; neurocontrollers; optimisation; GD method; LM method; Levenberg-Marquardt method; SCG method; adjoint method; adjoint simulation technique; gradient descent method; guidance loop; initial heading error; intelligent neural guidance law design; missile turning rate time constant; neural network optimization algorithms; noise effects; radome slope error; scaled conjugate gradient method; Abstracts; Artificial neural networks; Fading; Missiles; Noise; Adjoint simulation method; Guidance law; Neural network; Proportional navigation; Radome slope error;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2014 International Conference on
Conference_Location :
Lanzhou
Print_ISBN :
978-1-4799-4216-9
DOI :
10.1109/ICMLC.2014.7009133