Application of Taguchi Grey Approach and Sustainable Development of Hybrid Machine Learning Model for Wire Electrical Discharge Machining of Low Carbon Steel

Read full text Summarise with VIRAT
Authors: Manikandan Natarajan, R. Meenakshi Reddy, Thejasree Pasupuleti, Neeraj Sunheriya, Jayant P Giri, Rajkumar Chadge, Mohammad A. Kanan
Cited by: 0
References: 32

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

SAE 1010 steel is widely used in the automotive industry for fasteners and in aerospace and other engineering applications. Traditional machining of complicated forms is difficult. Wire Electrical Discharge Machining (WEDM), a specialized form of EDM, is effective for complex machining operations. This study optimises WEDM of SAE 1010 steel while considering environmental impact. A naturally available dielectric medium promotes sustainability without reducing machining efficiency. Pulse on time, pulse off time, and peak current affect material removal rate (MRR), surface roughness (Ra), and tolerance errors. ANOVA is used to determine the significance of the parameters. A hybrid Grey-ANFIS (Adaptive Neuro-Fuzzy Inference System) model improves performance predictions. The results show that Grey-ANFIS provides accurate forecasts, improving machining parameter optimization. The prediction model was highly accurate, with a MAPE of 0.0432, RMSE of 0.00029, and MAE of 0.000432. The model also correlated well with actual values, with a Correlation Coefficient of 0.9997.

Fields of Study & Subjects

Advanced Machining and Optimization Techniques Advanced machining processes and optimization Erosion and Abrasive Machining

Publication details

Journal / source
Applied Engineering Letters Journal of Engineering and Applied Sciences
Volume
1
Issue
11
Pages
1–1
Publication date
31 March 2026
Language
EN