Multi Objective Optimization for Turning Operation using Hybrid Extreme Learning Machine and Multi Objective Genetic Algorithm

Abstract

Turning operation, a type of machining process using Computer Numerical Control (CNC) machine in which a cutting tool, typically a non-rotary tool bit, moves to describe a helix toolpath while the cylindrical metal workpiece rotates. Numerous conflicting performance functions such as maximizing material removal rate, minimizing the product’s quality, maximizing the tool life and others, remains crucial for a system to optimize in order to obtain optimum benefit. The machinist is required to assign the optimal cutting parameters in CNC turning machine which have direct influence on the performance of each cutting process and machined product. It is very crucial for optimal parameters selection to maximize the performance function. A new optimisation model has been proposed in this paper. This model, uses Box Behnken Design (BBD) for design of experiment and the prediction model has been developed using Extreme Learning Machine (ELM) which is tuned using Particle Swarm Optimization. A powerful and effective, Multi Objective Genetic Algorithm (MOGA) will act as an optimizer of the developed model. Turning input parameters such as feed rate, cutting speed and depth of cut were considered as input variables and surface roughness, specific power consumption and cutting force were used as output variables. This novel approach, BBD-ELM-PSO-MOGA can predict the optimal cutting parameters as demonstrated in our case studies with less number of tunable parameters and number of experiments. Therefore, it is fast, less time consuming and easy to be implemented.

Analysis of Machining Parameters for Turning of AL-6061 and Optimization

“…Tiagrajah V jannharimal et.al [8] discusses effective, Multi Objective Genetic Algorithm (MOGA) will act as an optimizer of the developed model. Turning input parameters such as feed rate, cutting speed and depth of cut were considered as input variables and surface roughness, specific power consumption and cutting force were used as output variables.…”

Experimental Investigation and Optimization of Turning Polymers Using RSM, GA, Hybrid FFD-GA, and MOGA Methods

“…The MOGA parameters selected were as follows: initial population size was 50, optimization was achieved by setting intermediate crossover with a probability of 0.8 and constraint dependent mutation, the generation size was 300, the migration interval was 20, the migration fraction was 0.2, and the Pareto fraction was 0.35. The result of MOGA is the Pareto optimum, a nondominated solution, which is a set of solutions that take into account all of the objectives while not losing any of them [37].…”