A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Flow Resistance in an Open Channel over Movable Beds Using Artificial Neural Network
Estimating flow resistance is essential for the hydraulic analysis of a river and the evaluation of conveyance in a specific flow condition. Under bed-load transport conditions, the resistance to the flow in an open channel is different from fixed-bed condition and requires a distinct method for its evaluation. The geometric and hydraulic parameters influence flow resistance characteristics in the mobile bed load. In the present study, a wide range of experimental flume data sets are investigated to derive the dependency of the dimensionless parameters on the flow resistance under mobile bed-load conditions. The five most important dimensionless parameters, such as relative submergence depth, bed slope, aspect ratio, Reynolds number, and Froude number, are suggested because they show a unique relationship to the dependent parameter. An artificial neural network (ANN) model to predict the flow resistance is proposed by considering these independent parameters as the input parameters. To verify the strength of the model, the performances of previous researchers’ models were also evaluated and compared with the present work by considering a wide range of data sets. It is found that the previous models can be used for a specific range of data sets only, whereas the proposed ANN-based model is capable of performing well for a wide range of geometric and hydraulic conditions of a channel.
Prediction of Flow Resistance in an Open Channel over Movable Beds Using Artificial Neural Network
Estimating flow resistance is essential for the hydraulic analysis of a river and the evaluation of conveyance in a specific flow condition. Under bed-load transport conditions, the resistance to the flow in an open channel is different from fixed-bed condition and requires a distinct method for its evaluation. The geometric and hydraulic parameters influence flow resistance characteristics in the mobile bed load. In the present study, a wide range of experimental flume data sets are investigated to derive the dependency of the dimensionless parameters on the flow resistance under mobile bed-load conditions. The five most important dimensionless parameters, such as relative submergence depth, bed slope, aspect ratio, Reynolds number, and Froude number, are suggested because they show a unique relationship to the dependent parameter. An artificial neural network (ANN) model to predict the flow resistance is proposed by considering these independent parameters as the input parameters. To verify the strength of the model, the performances of previous researchers’ models were also evaluated and compared with the present work by considering a wide range of data sets. It is found that the previous models can be used for a specific range of data sets only, whereas the proposed ANN-based model is capable of performing well for a wide range of geometric and hydraulic conditions of a channel.
Prediction of Flow Resistance in an Open Channel over Movable Beds Using Artificial Neural Network
Kumar, Satish (author) / Khuntia, Jnana Ranjan (author) / Khatua, Kishanjit Kumar (author)
2021-03-13
Article (Journal)
Electronic Resource
Unknown
Resistance to Reversing Flows Over Movable Beds
| ASCE | 2021
Resistance to reversing flows over movable beds
| Engineering Index Backfile | 1969