Abstract
Measurement results, sediment transport and pollutant dispersion in confluence regions are highly affected by flow structures of open channel junction and it is necessary to find an efficient method that can fully describe the velocity fields in junctions. In this study the velocity field in an open channel junction was investigated by using Artificial Neural Network (ANN) and three dimensional modelling. First, a modified Genetic Algorithm (GA) was introduced, then, an ANN model was optimized and the flow velocity was predicted in a 90 degree channel junction. Also, for three dimensional simulation of the free surface flow in the considered junction ANSYS-CFX software was used. Comparison of the results obtained from ANN and CFX models with laboratory data with root mean square error of 0.094 and 0.182 and percent standard error of prediction of −9.75 and −25.71 respectively, showed that the introduced ANN perform better than CFX in modelling velocity field in open channel junction and it was able to predict accurate in different areas and flow-rates.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Engineering Applications of Computational Fluid Mechanics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
