Skip to content

IMPROVED EDM PRECISION WITH ADVANCED ENSEMBLE MACHINE LEARNING PREDICTION FOR INC-625 SUPERALLOY

Oct 2026 · Surface review and letters · 0 citations · 42 references

Abstract

This research examines the influence of the electrical discharge machining (EDM) parameters, including servo voltage, current, angle of cut, pulse-on and pulse-off times, on surface roughness (SR) and material removal rate (MRR) in the machining of the INC-625 superalloy. The L[Formula: see text] machining trials were conducted using Response Surface Methodology–Central Composite Design (RSM-CCD) to execute the machining trials. According to ANOVA, servo voltage was the most significant factor affecting both the SR (80.01%) and the MRR (77.33%). The SR decreased by 28.13% when the maximum servo voltage (70[Formula: see text]V) was employed and the MRR increased by 41.36% when the minimum servo voltage (50[Formula: see text]V) was employed. In addition, Desirability Analysis (DA) has been utilized to construct a response model to estimate the optimal setting values. Additionally, this study introduces a new heterogeneous ensemble machine learning model combining Ridge Regression, Random Forest, XGBoost, and Neural Networks to predict EDM performance metrics. The model achieves high accuracy ([Formula: see text] for SR, [Formula: see text] for MRR) using an optimized weighted average ensemble model. The ensemble method effectively represents the complex relationship between important process parameters and machining outputs. The validated ensemble model enables real-time EDM process optimization and provides actionable parameter recommendations for different manufacturing objectives. For quality-focused machining, a high servo voltage (70[Formula: see text]V), low pulse-on time (8[Formula: see text] [Formula: see text]s), and low current (3[Formula: see text]A) produced the lowest SR. For productivity-focused machining, higher pulse-on time (16[Formula: see text] [Formula: see text]s) and current (5[Formula: see text]A) maximized MRR. A balanced machining strategy was achieved at intermediate parameter settings ([Formula: see text]s, [Formula: see text]s, [Formula: see text]–65[Formula: see text]V, [Formula: see text] [Formula: see text]A, [Formula: see text]), offering an effective compromise between machining efficiency and surface quality. These recommendations provide practical decision support guidelines for facilitating data-driven decision-making in industrial EDM applications.

View source

Similar papers

Open access Sep 2026

Machine Learning Based Predictive Modeling of Machining Performance of Ti-6Al-4V under MQL Lubricating Conditions

Evaluating the performance of machined Ti-6AI-4V alloy under Minimum Quantity lubrication (MQL) using machine learning models to support sustainable and efficient milling found the developed models offer a reliable data-driven framework for optimizing machining parameters and improving sustainability.

Muhammad Jawad, Ume Habiba, Bilal Hassan et al. · 0 citations
Aug 2026

Machine learning-assisted prediction and Bayesian optimisation of wire EDM process parameters for surface roughness of AISI S7 tool steel

The study demonstrates that integrating machine learning and Bayesian optimization provides an effective approach for predicting and optimizing surface roughness in WEDM of AISI S7 tool steel.

Saravanan Kasinathan, Lalitha Radhakrishnan, Hariharan Kuppusamy et al. · 0 citations
Aug 2026

Data driven prediction of overcut in electrical discharge drilling of Ti-6Al-4V using machine learning for process improvement

A predictive analysis for overcut of through drilled hole has been carried out by using support vector regression (SVR) modelling with Bayesian, grid search and random search optimisation to improve the dimensional accuracy of electrical discharge drilling for producing miniature holes in Ti-6Al-4V alloy.

Masud Arif, Amit Sharma · 0 citations
Sep 2026

Ensemble Prediction Framework for Abrasive Aqua-Jet Cutting of TiAFL with RSM Integration

The results of this investigation provide an advanced machinability understanding of Hybrid TiAFL and deliver an ensemble-based predictive model for optimizing machining parameters on an industrial scale with improved performance.

Umapathy Venkatesan, Krishnamoorthy Natarajan · 0 citations
Open access Aug 2026

Experimental analysis and regression modeling of EDM performance parameters for SK2MCr4 steel using multi-variable interaction effects

This study investigates the impact of key electrical discharge machining (EDM) parameters: specifically, current, pulseon time, and servo voltage on the material removal rate (MRR) for SK2MCr4 steel. A comprehensive experimental approach employing a full factorial design was utilized to explore both the individual an...

Deepa Singh, B. Karki, Aavesh Kumar et al. · 0 citations
Open access Sep 2026

Machine Learning-Based Prediction of Machinability Responses in Meso-Scale Ultrasonic Vibration-Assisted End Milling (UVAEM) of Inconel 718 Superalloy: A Comparative Study of GPR, SVR, Random Forest, and Ridge Regression

Meso-scale ultrasonic vibration-assisted end milling (UVAEM) is an advanced manufacturing technique. UVAEM of Inconel 718 superalloy presents significant modeling challenges due to complex thermo-mechanical interactions and meso-scale size effects. This study introduces a machine learning framework that systematically...

Danyal Zahid, Muhammad Salman Khan, Muhammad Rizwan Ul Haq et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.