انجمن هیدرولیک ایران
نشریه هیدرولیک
2345-4237
3
2
2008
08
22
Estimating the Fall Velocity of Sediment Particles Using Artificial Neural Network
استفاده از شبکه عصبی مصنوعی در تخمین سرعت سقوط ذرات رسوبی
59
65
85467
10.30482/jhyd.2008.85467
FA
سیدمرتضی
سادات هلبر
ابراهیم
امیری تکلدانی
دانشگاه تهران
فاطمه
درزی
Journal Article
2008
03
22
The fall velocity of sediment particles is one of the important parameters in the phenomenon of<br />sediment transport, river bed and bank morphology, reservoir sedimentation and designing settling<br />basins of water transport networks. To estimate the sediment fall velocity, many relationships in the<br />literature have been used by scientists and engineers but they have limitations. In this research, using<br />an Artificial Neural Network, a model to estimate the sediment fall velocity is introduced. The model<br />is designed and validated using 115 series of data presented in different researches covering an<br />extensive range of sediment and fluid characteristics. The multi layer perception network with quick<br />back propagation learning scheme is used to estimate the nonlinear mapping between input data, i.e.<br />independent variables, and the output of the network, i.e. dependent variable. This nonlinear mapping<br />is used to estimate the fall velocity. To evaluate prediction accuracy of the model, predictions of the<br />designed network are compared with 14 experimental data set and analytical models of previous<br />researches. Comparisons were made using different error measures and it is found that the prediction<br />accuracy of the artificial network model is better than existing models.
https://jhyd.iha.ir/article_85467_989045adcc01ed81d4c6a8e4aba6b98b.pdf