Optimization of powder mixed electrical discharge machining parameter of metal matrix composite by nature inspired algorithm

Abstract

Electrical discharge machining is among the most innovative machining processes developed for machining conductive materials such as super alloys composite materials ceramics and more This study investigates the influence of different tool materials and varying powder concentrations on the EDM performance of Al LM25SiC metal matrix composites with weight fractions of 0 5 and 10 These MMCs are gaining importance in industries like tool manufacturing aerospace and automotive The study employs response surface methodology and Artificial Neural Network methods along with the Non-Dominated Sorting Genetic Algorithm II to analyze the impact of machining parameters on material removal rate tool wear rate and surface roughness Various factors including discharge current pulse on time open-circuit voltage tool material and powder concentration are examined through analysis of variance to develop mathematical models The microstructure of machined AlLM25SiC MMCs is analyzed using Scanning Electron Microscope with X ray powder diffraction and Energy Dispersive Xray Analysis for detailed analysis Artificial Neural Network models are developed to predict machining outcomes while Non-Dominated Sorting Genetic AlgorithmII is used for optimization. Thermal modeling and finite element simulation predict machining parameters effects while the Nature inspired meta heuristic algorithm Dragonfly is utilized for optimization and compared with RSM ANN and NSGA II models The study proposes strategies for enhancing EDM capabilities through precise control of machining parameters and optimized powder concentration in dielectric fluid newline