Affiliation:
1. Indian Institute of Technology, India
2. RGM College of Engineering and Technology, India
Abstract
The problem of predicting flow resistance in alluvial channels with sufficient accuracy is of great interest to hydraulic engineers. As the process is extremely complex, getting deterministic or analytical form of process phenomena is too difficult. Neural network modeling (ANN), which is particularly useful in modeling processes about which adequate knowledge of the physics is limited, is presented here as a tool complimentary to predict the complex non-linear relationship between the friction factor of an alluvial channel and its influencing factors. Friction factor comprises of different hydraulic and geometric parameters. Hence it is important to know the influences of these parameters on friction factor. Based on the input significant techniques through ANN model, it has been found that flow velocity influences more friction factor. The least influencing parameter is channel width. This shows the importance of determining the flow velocity more correctly.
Reference22 articles.
1. Bavarian, B. (1988). Introduction to neural networks for intelligence control. IEEE controls Syst. Mag., 3-7.
2. Artificial neural network model for prediction of friction factor in Pipe flow.;D. A.Fadare;Journal of Applied Sciences Research,2009
3. Interpreting neural-network connection weights.;G. D.Garson;Artif. Intell. Expert,1991
4. Review and comparison of methods to study the contribution of variables in artificial neural network models