Design of Mexican Hat Wavelet neural networks for solving Bratu type nonlinear systems

详细信息    查看全文

• 作者：Zaheer Masood^a ; ^{masood.zaheer@yahoo.com}Author Vitae ; Khalid Majeed^a ; ^{malikuet@yahoo.com}Author Vitae ; Raza Samar^a ; ^{Raza.samar@gmail.com}Author Vitae ; Muhammad Asif Zahoor Raja^b ; ^{rasifzahoor@yahoo.com} ; ^{Muhammd.asif@ciit-attock.edu.pk}Author Vitae
• 关键词：Wavelet-based neural networks ; fuel ignition model ; Genetic algorithm ; Sequential quadratic programming ; Electrical conducting solids ; Boundary value problems
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：19 January 2017
• 年：2017
• 卷：221
• 期：Complete
• 页码：1-14
• 全文大小：1714 K
• 卷排序：221

文摘

In this paper a Mexican Hat Wavelet based neural network is designed and applied for solving the nonlinear Bratu type equation. This equation is widely used in fuel ignition models, electrically conducting solids and heat transfer studies. The Mexican Hat Wavelet Differential equation artificial neural networks (MHW-DEANN) are used for the first time to construct an energy function of the system in an unsupervised manner. The tunable parameters of MHW-DEANN are trained with a hybrid evolutionary computing approach: we exploit the strength of Genetic Algorithms (GA) and Sequential Quadratic Programming (SQP) to find the best weights. Monte-Carlo simulations are performed for the proposed scheme with statistical analysis to validate the effectiveness and convergence of the proposed method for Bratu-type equations. It is observed that the proposed method converges in all cases and can solve the equation with high accuracy and reliability.