Surface roughness modeling using machine learning approaches for wire electro-spark machining of titanium alloy
International Journal of Structural Integrity
ISSN: 1757-9864
Article publication date: 24 October 2022
Issue publication date: 16 November 2022
Abstract
Purpose
In the present study, wire electro-spark machining of Titanium alloy is performed with the machining parameter such as spark-on time, spark-off time, current and servo voltage. The purpose of this study is to model surface roughness using machine learning approach for input/controllable variable. Machined surface examined using scanning electron microscope (SEM) and XRD methods.
Design/methodology/approach
Full factorial approach has been used to design the experiments with varying machining parameters into three-level four factors. Obtained surface roughness was modeled using machine learning methods namely Gaussian process regression (GPR) and support vector machine (SVM) methods. These methods were compared for both training and testing data with a coefficient of correlation and root mean square error basis. Machined surface examined using scanned electron microscopy and XRD for surface quality produced and check migration of tool material to workpiece material.
Findings
Machine learning algorithms has excellent scope for prediction quality response for the wire electric discharge machining (WEDM) process, resulting in saving of time and cost as it is difficult to find each time experimentally. It has been found that the proposed model with minimum computational time, provides better solution and avoids priority weightage calculation by decision-makers.
Originality/value
The proposed modeling provides better predication about surface produced while machining of Ti6Al7Nb using zinc-coated brass wire electrode during WEDM operation.
Keywords
Citation
Sharma, V., Misra, J.P. and Singhal, S. (2022), "Surface roughness modeling using machine learning approaches for wire electro-spark machining of titanium alloy", International Journal of Structural Integrity, Vol. 13 No. 6, pp. 999-1012. https://doi.org/10.1108/IJSI-08-2022-0108
Publisher
:Emerald Publishing Limited
Copyright © 2022, Emerald Publishing Limited