Performance Analysis of SLM-Fabricated SS316L EDM Tools and Surface Roughness Prediction Using ANN
Sandesh Patil and Arati Mulay
Metal Additive Manufacturing (AM) using Selective LASER Melting (SLM) technologies are catalyzing a new industrial revolution, significantly transforming the manufacturing landscape. Notably, tools used in conventional processes like Electric Discharge Machining (EDM) can be efficiently produced by SLM. This research focuses on evaluating the performance of SS316L EDM tools fabricated by using SLM, optimizing critical control parameters like Laser power and scanning speed while keeping layer height and hatch distance constant. Post-manufacturing of SLM technology metal 3D printed EDM Tools, a comprehensive geometrical and surface roughness analysis of fabricated parts was conducted.
Minimizing the surface roughness of EDM tools is critical for achieving superior machining results. Therefore, research also emphasizes on analyzing tool wear and surface roughness, alongside optimizing process parameters using the Taguchi method, Analysis of Variance (ANOVA) and Multi-Decision-Making techniques like TOPSIS.
Furthermore, the study develops an Artificial Neural Network (ANN) model to predict the surface roughness of EDM tools produced by Metal AM. A detailed literature review covers key process parameters influencing Selective Laser Melting (SLM) technology, the material characteristics of SS316L, and the experimental framework for manufacturing EDM tools. The ANN was trained and tested on data obtained from Metal AM-produced EDM tools, yielding a near-perfect fit, demonstrating the model’s effectiveness.
Keywords: SLM, powdered bed fusion, EDM, taguchi, TOPSIS, ANN