Stochastic numerical treatment for solving Falkner–Skan equations using feedforward neural networks

Ahmad, Iftikhar and Ahmad, Siraj-ul-Islam and Bilal, Muhammad Qamar and Anwar, Nabeela (2017) Stochastic numerical treatment for solving Falkner–Skan equations using feedforward neural networks. Neural Computing and Applications, 28. pp. 1131-1144. ISSN 0941-0643. (Published)

[img] Pdf
Stochastic Numerical Treatment for Solving Falkner–Skan Equations Using Feedforward Neural Networks.pdf - Published Version
Restricted to Repository staff only

Download (1MB) | Request a copy
[img]
Preview
Pdf
Stochastic Numerical Treatment for Solving Falkner–Skan Equations Using Feedforward Neural Networks 1.pdf

Download (187kB) | Preview

Abstract

In this article, the artificial intelligence techniques have been used for the solution of Falkner–Skan (FS) equations based on neural networks optimized with three methods including active set technique, sequential quadratic programming and genetic algorithms (GA) hybridization. Log-sigmoid activation function is used in artificial neural network architecture. The proposed techniques are applied to a number of cases for Falkner–Skan problems, and results were compared with GA hybrid results in all cases and were found accurate. The level of accuracy is examined through statistical analyses based on a sufficiently large number of independent runs.

Item Type: Article
Additional Information: Indexed by Scopus
Uncontrolled Keywords: Falkner–Skan; ANN; Log-sigmoid; Boundary value problems
Subjects: G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography
Faculty/Division: Faculty of Industrial Sciences And Technology
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 01 Aug 2018 04:31
Last Modified: 01 Aug 2018 04:31
URI: http://umpir.ump.edu.my/id/eprint/20424
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item