Abstrait

Prediction of Drag Coefficient of Spherical Particle Using ANN, ANFIS, Regression and GA Optimization

Saroj Kumar Samantaray, Siddharth Sekhar Sahoo, Soumya Sanjeeb Mohapatra and Basudeb Munshi

The present work includes the successful prediction of the experimental drag coefficients (CD) as function Reynolds number (Re), collected from the open source literatures by regression analysis method, Artificial intelligence models i.e. artificial neural network (ANN), adaptive Neuro fuzzy interface system (ANFIS) and Genetic Algorithm (GA). A non-linear equation is assumed to relate drag coefficient and Reynolds number and optimized using GA. To confirm the predicted output, twenty-one numbers of inputs are tested and simulated. The comparative study of the prediction models is carried out in terms of the error functions and coefficient of determination. This study has revealed that ANFIS neural model has predicted the desired drag coefficient with minimal error and high coefficient of determination and outperformed the rest prediction models.