Dump combustor swirling flow reconstruction using neural network
Ahmed, S., El Kadi, H. (2010). Dump combustor swirling flow reconstruction using neural network. EKB Journal Management System, 14(14th International Conference on Applied Mechanics and Mechanical Engineering.), 1-10. doi: 10.21608/amme.2010.37547
Saad Ahmed; Hany El Kadi. "Dump combustor swirling flow reconstruction using neural network". EKB Journal Management System, 14, 14th International Conference on Applied Mechanics and Mechanical Engineering., 2010, 1-10. doi: 10.21608/amme.2010.37547
Ahmed, S., El Kadi, H. (2010). 'Dump combustor swirling flow reconstruction using neural network', EKB Journal Management System, 14(14th International Conference on Applied Mechanics and Mechanical Engineering.), pp. 1-10. doi: 10.21608/amme.2010.37547
Ahmed, S., El Kadi, H. Dump combustor swirling flow reconstruction using neural network. EKB Journal Management System, 2010; 14(14th International Conference on Applied Mechanics and Mechanical Engineering.): 1-10. doi: 10.21608/amme.2010.37547

Dump combustor swirling flow reconstruction using neural network

The International Conference on Applied Mechanics and Mechanical Engineering
Article 11, Volume 14, 14th International Conference on Applied Mechanics and Mechanical Engineering., May 2010, Page 1-10  XML PDF (545.25 K)
Document Type: Original Article
DOI: 10.21608/amme.2010.37547
View on SCiNiTO View on SCiNiTO
Authors
Saad Ahmed; Hany El Kadi
Mechanical Engineering Department, College of Engineering, American University of Sharjah, Sharjah, PO Box 26666, UAE.
Abstract
Abstract:
Knowledge of continuous evolution of fluid flow characteristics is very useful and essential for better designs of efficient combustors. Many experimental techniques such as Laser Doppler Velocimetry (LDV) measurements provide only limited discrete information at given points; especially, for the cases of complex flows such as swirling flows of dump combustors. For these types of flows, usual numerical interpolating schemes appear to be unsuitable. Artificial Neural Network (ANN) methods are thus proposed and their results are presented in this paper and are compared with the experimental data used for training purposes. This pilot study showed that ANN is an appropriate method for predicting swirl flow velocity in a model of a dump combustor. In summary, this detailed information is fundamental for better designs and optimization of dump combustors.
Keywords
Swirl flow; dump combustors and neural network
Statistics
Article View: 136
PDF Download: 94