Capability to predict the steady and unsteady reduced aerodynamic forces on a square cylinder by ANN and GEP

摘要: The reduction in the drag and lift forces on a square cylinder is obtained by attaching an extended solid (thorn) with it positioned at front stagnation point rear separately low Reynolds number, Re = 40, 100 180. effect of variation thorn length (l′ = 0.2, 0.4 0.6) inclination angle (θ = 5°, 10°, 15° 20°) drag, this forecasted ANN (artificial neural network) GEP (gene expression programming). required input output data to train models have been taken from available published results present authors (Dey Das Eng Sci Technol 18:758–768 [2015]; Ain Shams J 6:929–938 [2015]). It found that are minimized 16 46 % for Re = 100, respectively, 22 60 % Re = 180 compared model. has perceived both prediction tools (ANN GEP) can forecast aerodynamic behavior correctly quickly within given range training than simulation, which takes much longer time complete computation. further observed model efficient