Artificial Neural Network Model for Predicting Discharges over Weirs of Finite Crest Widths. | ||||
| MEJ- Mansoura Engineering Journal | ||||
| Article 5, Volume 27, Issue 4, December 2002, Page 60-74 PDF (356.22 K) | ||||
| Document Type: Research Studies | ||||
| DOI: 10.21608/bfemu.2021.143000 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
A. A. Ibrahim  ; A. M. Negm; A. A. El-Saiad; G. M. Abdel-Aal
| ||||
| Department. of Water & Water Structures Engineering., Faculty of Engineering., Zagazig University., Zagazig., Egypt. | ||||
| Abstract | ||||
| Multilayers feedforward Artificial Neural Network (ANN) with back propagation learning algorithm is used to develop a computational model to predict discharge over weirs of finite crest widths. A network of size of 4-6-I is found suitable for this purpose with 3300 iterations and hyperbolic tangent (tansh) activation function The results of the trained, verified and tested ANN model are compared to the experimental measurements. Also, results from previously developed models based on statistical methods are compared to results of ANN model. The effect of using filter applied on the lead over weir on the performance of the ANN model is investigated The sensitivity analysis that conducted using the ANN model indicated that the most contributing variables to flow rate are the head over the weir and the weir width followed by the length of the weir and its height. Results indicated that the prediction of discharge over broad-crested weirs using ANN is more accurate than predictions offered by other previously developed models | ||||
| Keywords | ||||
| Discharge measurement structures; Flow measurements; Flow modeling; Free surface flow; Artificial neural networks; Artificial intelligence | ||||
|
Statistics Article View: 87 PDF Download: 160 |
||||
