| Autor: |
Waseem Waseem, Muhammad Sulaiman, Saeed Islam, Poom Kumam, Rashid Nawaz, Muhammad Asif Zahoor Raja, Muhammad Farooq, Muhammad Shoaib |
| Jazyk: |
angličtina |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Alexandria Engineering Journal, Vol 59, Iss 1, Pp 11-24 (2020) |
| Druh dokumentu: |
article |
| ISSN: |
1110-0168 |
| DOI: |
10.1016/j.aej.2019.12.001 |
| Popis: |
For analysis of physical properties of different materials, rectangular porous fins are used to examine the heat transformation through a system. In this paper, a metaheuristic is combined with neural computing modelling to study the effects of temperature changes in a porous fin model. Cuckoo search algorithm is used as an efficient optimization technique to find the best weights to reduce the mean squared error in the required temperature profile. The governing partial differential equation is converted into a non-linear ordinary differential equation subject to certain boundary conditions. Two individual cases, of silicon nitride (Si3N4) and Aluminium (Al), are considered. In the proposed procedure, the Cuckoo Search(CS) algorithm is combined with the artificial neural network (ANN), namely CS-ANN, to solve the differential equations and obtain solutions with better accuracy. Keywords: Heat distribution, Porous fin, Artificial intelligence, Metaheuristics, Cuckoo search algorithm, Differential equations, Optimization problems |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
