Multi-Objective Optimization of Wire-EDM Using ANN-NSGA-II Hybrid Approach

View at publisher Summarise with VIRAT
Authors: Abhijit Saha, Dipika Sarkar, Prosun Mandal
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The present research work is focused on solving the multi-objective optimization problem of wire electrical discharge machining (wire-EDM) for the machining of nanostructured hardfaced material using an artificial neural network (ANN)- non-dominated sorting genetic algorithm II (NSGA-II) hybrid approach. Hardfacing is one of the cost-effective methods for improving performance as well as increasing the reliability of the components. Due to the presence of nano-particles, the hardness of the nanostructured hardfaced material drastically increased. Wire-EDM is one of the useful techniques to machine hard materials. For increasing the machining performance of hardfaced material, the proper selection of wire-EDM parameters is needed. The ANN is an artificial intelligence technique, which has an efficient ability to model any non-linear complicated process. The ANN technique was used for developing a prediction model of a complicated wire-EDM process, and further, this prediction model was used as a fitness function of a multi-objective genetic algorithm (GA) to find the optimal process parameters. The ANN model with 14 and 3 neurons in each of the 2 hidden layers predicts the responses most efficiently. A total of 35 sets of optimal parameters were found using NSGA-II.

Fields of Study & Subjects

Advanced Machining and Optimization Techniques Advanced machining processes and optimization Advanced Multi-Objective Optimization Algorithms

Publication details

Journal / source
CRC Press eBooks
Pages
109–121
Publication date
30 March 2026
Language
EN
Document type
Book chapter