Title: Soft computing based comparative analysis of Al/Gr/Cp₅ MMC WEDM

Authors: Mangesh R. Phate; Shraddha Toney; Sarang Toney

Addresses: Department of Mechanical Engineering, AISSMS College of Engineering, Shivajinagar, Pune, Maharashtra, 411001, India ' Department of Computer Engineering, AISSMS, Institute of Information Technology, Shivajinagar, Pune, Maharashtra, 411001, India ' Wells Fargo International Solution Pvt. Ltd., Bengalure, Karnataka, 560103, India

Abstract: The work looks at how surface roughness is predicted for an alloy based on aluminium, aluminium and 5% graphite (Al/Gr/Cp₅), which is made of aluminium and graphite, during wire electro-discharge machining. The wire electrical discharge machining (WEDM) performance of the composite was examined using methods such as artificial neural networks and response surface-based modelling. Using Taguchi's L₂₇ orthogonal array and process variables such as material pulse-on-time, pulse-off-time, wire feed rate, and input current, the study examined surface properties. Significant factors influencing surface properties were found using analysis of variance. The results showed that the response surface method (RSM) and artificial neural network (ANN) approaches were the most successful, with correlation coefficients of 0.9859 and 0.99201, respectively. It is advised that ANN models be used since a comparative analysis of RSM and ANN models revealed their accuracy.

Keywords: RSM; artificial neural network; ANN; analysis of variance; ANOVA; Taguchi; surface roughness; Al/Gr/CP₅.

DOI: 10.1504/IJMMM.2025.147842

International Journal of Machining and Machinability of Materials, 2025 Vol.27 No.3, pp.251 - 270

Received: 30 Aug 2024
Accepted: 28 Nov 2024
Published online: 04 Aug 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article