Artificial Neural Networking (ANN) Model for Drag Coefficient Optimization for Various Obstacles

For various obstacles in the path of a flowing liquid stream, an artificial neural networking (ANN) model is constructed to study hydrodynamic force depending on object. The multilayer perceptron (MLP), back propagation (BP), and feed-forward (FF) network models were employed create ANN model, which has high prediction accuracy strong structure. To be more specific, circular-, octagon-, hexagon-, square-, triangular-shaped cylinders are installed rectangular channel. fluid from left wall channel by following two velocity profiles explicitly linear parabolic velocity. no-slip condition maintained upper bottom walls. Neumann applied outlet. entire physical design mathematically regulated using flow equations. result presented finite element approach, with LBB-stable pair hybrid meshing scheme. drag coefficient values calculated doing line integration around obstructions for both profiles. predicted developing toward obstacles.