期刊
NATIONAL ACADEMY SCIENCE LETTERS-INDIA
卷 38, 期 5, 页码 425-428出版社
SPRINGER INDIA
DOI: 10.1007/s40009-015-0359-3
关键词
Artificial neural network; Back propagation algorithm; Bratu's equations; Levenberg-Marquardt algorithm; Conjugate gradient algorithm
In this article, an artificial neural network (ANN) method is presented to obtain the closed analytic form of the one dimensional Bratu type equations, which are widely applicable in fuel ignition of the combustion theory and heat transfer. Our goal is to provide optimal solution of Bratu type equations with reduced calculus effort using ANN method in comparison to the other existing methods. Various test cases have been simulated using proposed neural network model and the accuracy has been substantiated by considering a large number of simulation data for each model with enough independent runs. Numerical results show that this method has potentiality to become an efficient approach for solving Bratu's problems with less computing time and memory space.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据