![]() ![]() ![]() Burr height observed is found minimum at a cutting velocity of 10 m/min, feed of 0.08 mm/rev, and depth of hole within backup support of 0.2 mm, whereas burr thickness is the lowest in this work at a cutting velocity of 3.9 m/min, a feed rate of 0.095 mm/rev and depth of hole inside backup support of 0.56 mm. Mathematical model of burr height and burr thickness are developed using this experimental input data and ANN-FPA based output data and it is optimized using Genetic Algorithm (GA) and RSM desirability function optimization techniques. The developed ANN-FPA predictive model is found to be more accurate than the only ANN model. Two types of predictive models namely, artificial neural networks (ANN), and a combination of ANN with flower pollination algorithm (ANN-FPA) are constructed using the experimental data to predict burr height and burr thickness. In this work, drilling experiments are performed on an aluminum alloy following the L 27 orthogonal array of response surface methodology (RSM) to find out suitable drilling parameters to minimize burr height and thickness.
0 Comments
Leave a Reply. |