|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|138551||2018||15 صفحه PDF||سفارش دهید||5267 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Materials Today: Proceedings, Volume 5, Issue 2, Part 1, 2018, Pages 4971-4985
Process modelling and optimization are among the two important main issues in manufacturing. Optimization of process parameters not only increases the efficacy for machining economics, but also the product quality to a great extent. In this context, an effort has been made in the current research work to optimize the surface roughness value using Simulated Annealing and Neural Networks taking cutting speed, feed rate, tool rake angle and nose radius as input machining parameters. With the experimental data, objective function in the form of mathematical model is formulated by Response surface methodology. The response model of the system with independent variables is developed in the form of second order equation using regression analysis with the available experimental data and the statistical validation is done. Simulated Annealing and Artificial Neural Network Algorithms are used to optimize the response. The predicted values using genetic algorithm , simulated annealing and neural network algorithm are compared and analysed. The predicted values are in good agreement with the experimental values. It can be concluded that the artificial neural network, with the optimum structure, is a helpful approach to predict a target specially the surface roughness of the work piece for different cutting conditions and tool geometry.