Parametric optimization on electro chemical machining process using PSO algorithm

Many real-world optimization problems are covered by Multi-Objective Optimization (MOO). Due to the inherent contradictory existence of the goals to be optimised, solving these problems is a difficult challenge. Multi-Objective Optimization problems have been solved using a variety of computational intelligence techniques. Particle Swarm Optimization (PSO) is a quick and easy computational technique that belongs to the swarm intelligence technique. The PSO with combined normalised objectives is presented in this paper to solve Multi-Objective Optimization problems choosing the optimal values for key process parameters of the electrolytic machining process, such as tool feed rate, electrolyte flow rate, applied voltage, applied voltage, plays an important role in optimizing the metric of process performance. PSO quickly reaches the best answer in the population at the each iteration because it is a population-based evolutionary technique. The proposed PSO is evaluated the performance of Material Removal Rate (MRR) and Surface Roughness of the regression model and validated using experimental findings from Electro Chemical Machining (ECM) of aluminium composite materials, as well as validation tests. The proposed algorithm, when combined with an intelligent manufacturing method, resulted in a reduction in production cost and time, as well as a greater increase in machining parameter selection flexibility. Copyright (C) 2022 Elsevier Ltd. All rights reserved.