EXPERIMENTAL INVESTIGATION & FEM MODELING OF ECDM USING MACHINE LEARNING ALGORITHM

Abstract

This thesis presents a comprehensive study on the Experimental Investigation and Finite Element Method (FEM) Modeling of Electrochemical Discharge Machining (ECDM) process, focusing on the application of machine learning algorithms. The main objective is to optimize the ECDM process by developing a regression equation using machine learning and applying advanced optimization algorithms, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Additionally, the impact of a magnetic field on machining performance is investigated, and FEM simulations are performed to analyze the process. Various machine learning algorithms, including Neural Networks, Support Vector Machines, and Decision Trees, are employed to establish a regression equation that relates the process parameters to the response variable. The Neural Network model is found to be the most accurate and effective in generating the regression equation. Using the regression equation, GA and PSO algorithms are utilized to determine the optimal values of the process parameters for achieving the desired response variable. The comparison reveals that the PSO algorithm outperforms GA in optimizing the process parameters. The influence of a magnetic field on the machining performance of ECDM is thoroughly examined, with a focus on material removal rate, surface quality, and tool wear. FEM simulations are conducted to analyze the ECDM process and predict the outcomes. These simulations provide a deeper understanding of the complex interactions between the process parameters and response variables, facilitating process optimization and performance enhancement. By combining machine learning algorithms, advanced optimization techniques, experimental investigations, and FEM modeling, this research contributes to the advancement of the ECDM process. The findings have practical implications for industries utilizing ECDM for precision machining applications. Overall, this thesis offers valuable insights and provides a comprehensive approach to optimize the process, improve efficiency, and enhance quality for precision machining applications.