RT Journal Article ID 3bdf517114f208c4 A1 Debnath, Suman A1 Banik, Anirban A1 Bandyopadhyay, Tarun Kanti A1 Majumder, Mrinmoy A1 Saha, Apu Kumar T1 ESTIMATION OF PRESSURE DROP FOR NON-NEWTONIAN LIQUID FLOW THROUGH BENDS USING ADAPTIVE NON-PARAMETRIC MODEL JF International Journal of Fluid Mechanics Research JO FMR YR 2020 FD 2020-02-12 VO 47 IS 1 SP 59 OP 69 K1 bends K1 non-Newtonian fluid K1 GMDH K1 optimization AB Studies of non-Newtonian pseudo-plastic liquid flow through bends are important as it is used in many chemical process industries like petroleum and refinery, pharmaceutical, rubber, paper pulp, and food industries, as a piping component for fluid flow transfer and heat transfer equipment in boiler, heat exchanger, distillation column, and air-crafts. In the concerned study, non-Newtonian pseudo-plastic SCMC solution (sodium salt of carboxy methyl cellulose solution) liquid flow through different types of angle of 0.0127 m diameter pipe bends has been investigated experimentally to optimize the frictional pressure drop across the bends in laminar and water flow in turbulent condition. The Group Method of Data Handling (GMDH) with multilayered neural network is used to predict and minimize the pressure drop. Pressure drop is minimized at the optimal concentration of the fluid and the bend angle. The GMDH model is validated against the validation techniques like Nash−Sutcliffe efficiency (NSE), percent bias (PBIAS), RMSE-observations standard deviation ratio (RSR), etc. It has been found that software-predicted data can be used for the trouble shooting in industry and in equipment design. PB Begell House LK https://www.dl.begellhouse.com/journals/71cb29ca5b40f8f8,17da9ab21c8d7d67,3bdf517114f208c4.html