Session: 02-09-01: Computational Modeling and Simulation for Advanced Manufacturing-I

Paper Number: 68468

Start Time: Tuesday, 10:05 AM

68468 - Analysis of Surface Roughness in End-Milling of Aluminium Using an Adaptive Network-Based Fuzzy Inference System 

End-milling is considered one of the well-known cutting processes in the manufacturing industry. It is a step-by-step process that creates machined surfaces using an end-milling cutter that operates at relatively high speed. The cutting tool generally revolves around an axis that is perpendicular to the work-piece material. In order to manufacture mechanical parts, the speed of the spindle, the radial and axial depth of cut, and the feed rate are important parameters affecting the shapes and the roughness of the work-piece of the material considered. Many existing studies suggest that minimum roughness could be obtained if the radial and axial depth of the cut, the feed rate, and the spindle speed are adequately adjusted. This study considers the results of an experimental investigation conducted on thirty (30) samples of aluminium alloy AL-6061 using a CNC machine and a Mitutoyo surface roughness tester and Press-o-firm. This study seeks to analyse how the end milling setting, such as the spindle speed, the feed rate, and the axial/radial depth cut, affect the surface roughness. The machining parameters varied from 1000 to 3000 RPM. The feed rate was adjusted between 100 and 500 mm/min. The axial and radial depth was adjusted between 10 to 30 mm and 0.5 to 2.5 mm, respectively. Thirty (30) experimental configuration runs have been generated to analyse the relationship between independent input parameters that characterise the machine setting and output performance or surface roughness. Because the surface finish is a major concern for the end milling process, the present study considers an Adaptive Network-based Fuzzy Inference System (ANFIS) for the modelling. ANFIS combines an Artificial Neural Network (ANN) and Fuzzy logic (FL) theory. Existing studies have demonstrated that ANFIS models can capture nonlinearity inherent to processes such as end-milling. In addition, ANFIS has a strong learning capacity and prediction accuracy. The proposed approach will use the data generated during the experimental investigation conducted in the case study considered in this paper. The use of data for modelling is expected to reduce the complexity of the mathematical formulation. With a suitable model, the surface roughness prediction model is expected to improve the cutting processes and enhance the surface roughness of a material's work-piece. Also, the prediction model could assist with identifying the optimum parametric setting that minimises surface roughness. This study will exceptionally assist the manufacturing process of machine parts via computer numerical machining by having a sustainable prediction analysis via ANFIS.

Presenting Author: Serge Balonji University of Johannesburg

Authors:

Serge Balonji University of Johannesburg
I. P. Okokpujie University of Johannesburg
L. K. Tartibu University of Johannesburg