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

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

[1]  Prasenjit Dey,et al.  Steady flow over triangular extended solid attached to square cylinder – A method to reduce drag , 2015 .

[2]  Spencer J. Sherwin,et al.  FLOW PAST A BLUFF BODY WITH A WAVY STAGNATION FACE , 2001 .

[3]  K. C. Hung,et al.  Suppression of fluid force on a square cylinder by flow control , 2005 .

[4]  Prasenjit Dey,et al.  Numerical analysis of drag and lift reduction of square cylinder , 2015 .

[5]  S. Prasher,et al.  A NEURAL NETWORK APPROACH FOR EVALUATION of SURFACE HEAT TRANSFER COEFFICIENT , 1999 .

[6]  A. Roshko.  On the Wake and Drag of Bluff Bodies , 1955 .

[7]  Alexander J. Angilella,et al.  Drag reduction on grooved cylinders in the critical Reynolds number regime , 2013 .

[8]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[9]  Spencer J. Sherwin,et al.  Flow past a square-section cylinder with a wavy stagnation face , 2001, Journal of Fluid Mechanics.

[10]  A. Sohankar,et al.  Reduction of fluid forces and heat transfer on a square cylinder in a laminar flow regime using a control plate , 2012 .

[11]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[12]  C. Park,et al.  Reducing the drag on a circular cylinder by upstream installation of a small control rod , 2004 .

[13]  Hiroshi Sakamoto,et al.  Effect of a T-shaped plate on reduction in fluid forces on two tandem cylinders in a cross-flow , 2006 .

[14]  Peter W. Bearman,et al.  Investigation of the flow behind a two-dimensional model with a blunt trailing edge and fitted with splitter plates , 1965, Journal of Fluid Mechanics.

[15]  Dilek Funda Kurtulus,et al.  Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network , 2009, Neural Computing and Applications.

[16]  Abhijit Sarkar,et al.  Prediction of unsteady mixed convection over circular cylinder in the presence of nanofluid- A comparative study of ANN and GEP , 2015 .

[17]  P. W. Bearman,et al.  The Effect of Base Bleed on the Flow behind a Two-Dimensional Model with a Blunt Trailing Edge , 1967 .

[18]  Prasenjit Dey,et al.  Development of GEP and ANN model to predict the unsteady forced convection over a cylinder , 2016, Neural Computing and Applications.