Teaching—Learning-Based Optimization Coupled with Response Surface Methodology for Micro Electrochemical Machining of ALUMINIUM NANOCOMPOSITE

Abstract

In this work, Micro Electro Chemical Machining (μECM) of aluminium alloy (AA) 7075 reinforced with nano silicon carbide particles (1.5 wt.%) has been effectively investigated and reported. The ultrasonic cavitation-based solidification process was employed for fabricating the nanocomposite, and machining studies were performed based on the experimental design matrix formulated using the central composite approach of Response Surface Methodology (RSM). The parameters which were applied to study their effects are: voltage, concentration of electrolyte, duty cycle, and rate of tool feed with an objective of optimizing Material Removal Rate (MRR), radial overcut, surface roughness and wear on tool electrode. Multi-Objective optimization was performed with desirability analysis, a second-order empirical equation was formulated for all outputs, and the most influential input parameters were recognized by applying Analysis of Variance (ANOVA). An evolutionary Teaching-Learning-Based Optimization (TLBO) algorithm was also performed considering surface roughness as a constraint, in order to compare the results with desirability analysis. The results obtained have coincided very well with the RSM result considering a target surface roughness value of 0.4 μm, proving the superiority of the TLBO algorithm over the RSM approach.