Surface Roughness Optimization in End Milling Using the Multi Objective Genetic Algorithm Approach

Abstract

In finishing end milling, not only good accuracy but also good roughness levels must be achieved. Therefore, determining the optimum cutting levels to achieve the minimum surface roughness is important for it is economical and mechanical issues. This paper presents the optimization of machining parameters in end milling processes by integrating the genetic algorithm (GA) with the statistical approach. Two objectives have been considered, minimum arithmetic mean roughness (Ra) and minimum Root-mean-square roughness (Rq). The mathematical models for the surface roughness parameters have been developed, in terms of cutting speed, feed rate, and axial depth of cut by using Response Methodology Method (RSM). Due to complexity of this machining optimization problem, a multi objective genetic algorithm (MOGA) has been applied to resolve the problem, and the results have been analyzed.

Modeling and Prediction of Surface Roughness in Ultra-High Precision Diamond Turning of Contact Lens Polymer Using RSM and ANN Methods

“…Others used mathematical modelling based on the physics of the machining process [7]. The recent researches concentrated and recommended the artificial intelligent techniques such as: genetic algorithm, fuzzy-set, [1,8,9] and neural network. Some researchers try to compare between two different methods such as NN and regression analysis [10,11].…”

Surface Roughness Prediction in High Speed End Milling Using Adaptive Neuro-Fuzzy Inference System

“…Others choose to use mathematical modelling based on the physics of the process [4]. However, the recent researches concentrated on using the artificial intelligent techniques such as: fuzzy-set [5], genetic algorithm [6] and neural network [7]. Other researchers try to compare between two different methods such as NN and regression analysis [8] or fuzzy logic and regression analysis [9].…”

Multi Objective Optimisation for High Speed End Milling Using Simulated Annealing Algorithm

“…The conventional methods based on the mathematical methods such as linear programming, nonlinear programming, geometric programming and dynamic programming or the statistical methods such as the desirability function method [2,3] and Taguchi method [4]. The nonconventional methods usually give a near optimal solution and based on the artificial intelligence methods such as genetic algorithm [5][6], neural network [7], Particle swarm algorithm [9], ant colony algorithm [9] and simulated annealing algorithm [10,11]. However, any optimization should come after modeling step.…”