Predictive Modeling of the Ti6Al4V Alloy Surface Roughness

Authors:
Nikos C. Tsourveloudis
Affiliations:
Department of Production Engineering and Management, Intelligent Systems and Robotics Laboratory, Technical University of Crete, Chania, Greece
Venue:
Journal of Intelligent and Robotic Systems
Year:
2010

Citing 3
Cited 1

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Response Surface Methodology: Process and Product in Optimization Using Designed Experiments

Response Surface Methodology: Process and Product in Optimization Using Designed Experiments
A Comparison between Back Propagation and the Maximum Sensibility Neural Network to Surface Roughness Prediction in Machining of Titanium (Ti 6Al 4V) Alloy

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence

Prediction of surface roughness in end milling process using intelligent systems: a comparative study

Applied Computational Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The prediction of surface roughness is important for all materials that undergo manufacturing processes. The Ti6Al4V titanium alloy is commonly used in aerospace, automotive and power generation industries but also in the manufacturing of medical implants, mainly because of its biocompatibility. Here we study the relationship of Ti6Al4V's surface roughness with critical machining parameters and conditions based on experimental input (machining parameters)-output (surface roughness) data derived during the turning operation. The experimental findings are converted into polynomial models through the Response Surface Methodology (RSM) and into a fuzzy logic system through the Adaptive Neuro-Fuzzy Inference System (ANFIS). The ability of these two methodologies to predict Ti6Al4V's surface roughness when machined is presented and compared. It is observed that the ANFIS predicts surface roughness with less error mainly when the data used for evaluation are not completely different to those used for training.