Prediction of Tool Life when End Milling of Ti6Al4V Alloy Using Hybrid Learning System

Tool life significantly affects the machining cost and productivity. A wide number of techniques have been applied to modelling metal cutting processes. Techniques of artificial intelligence are new soft computing methods which suit solutions of nonlinear and complex problems such as metal cutting processes. The current study is concerned with the application of an adaptive neuro-fuzzy inference system (ANFIS). This ANFIS model is developed to predict tool life when end milling of Ti6Al4V alloy with coated (PVD) and uncoated cutting tools are under dry cutting conditions. By carrying out training and testing the ANFIS models, the current study employed real experimental results, and based on such results, a selection of the best model was conducted based on the mean absolute percentage error (%). For the modelling process, the study adopted a generalised bell shape membership function, and there was a change in its number from 2 to 5. The findings revealed that ANFIS is capable of modelling tool life in end milling process, and that there was good matching obtained between experimental and predicted results.

[1]  U. Zuperl,et al.  A generalized neural network model of ball-end milling force system , 2006 .

[2]  Zuperl Uros,et al.  Adaptive network based inference system for estimation of flank wear in end-milling , 2009 .

[3]  Habibollah Haron,et al.  Application of Regression and ANN Techniques for Modeling of the Surface Roughness in End Milling Machining Process , 2009, 2009 Third Asia International Conference on Modelling & Simulation.

[4]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[5]  Cevdet Göloglu,et al.  Zigzag machining surface roughness modelling using evolutionary approach , 2009, J. Intell. Manuf..

[6]  Habibollah Haron,et al.  Prediction of surface roughness in the end milling machining using Artificial Neural Network , 2010, Expert Syst. Appl..

[7]  B. K. Vinayagam,et al.  Optimization of Ball Burnishing Process on Tool Steel (T215Cr12) in CNC Machining Centre Using Response Surface Methodology , 2011 .

[8]  S. Abdullah,et al.  Prediction of fatigue crack growth rate using rule-based systems , 2011, 2011 Fourth International Conference on Modeling, Simulation and Applied Optimization.

[9]  M. R. Soleymani Yazdi,et al.  Finite Volume Analysis and Neural Network Modeling of Wear During Hot Forging of a Steel Splined Hub , 2012 .

[10]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[11]  Ning Wang,et al.  Adaptive network-based fuzzy inference system with leave-one-out cross-validation approach for prediction of surface roughness , 2011 .

[12]  Haslina Arshad,et al.  Performance of alloyed uncoated and CVD-coated carbide tools in dry milling of titanium alloy Ti-6242S , 2007 .

[13]  Ahmet Murat Pinar,et al.  Optimization of Process Parameters with Minimum Surface Roughness in the Pocket Machining of AA5083 Aluminum Alloy via Taguchi Method , 2013 .

[14]  M. A. El Baradie,et al.  Prediction of tool life in end milling by response surface methodology , 1997 .

[15]  Fikri Dweiri,et al.  Fuzzy surface roughness modeling of CNC down milling of Alumic-79 , 2003 .

[16]  Bor-Tsuen Lin,et al.  Adaptive network-based fuzzy inference system for prediction of surface roughness in end milling process using hybrid Taguchi-genetic learning algorithm , 2009, Expert Syst. Appl..

[17]  Mahmudur Rahman,et al.  Optimization of Surface Roughness in End Milling Using Potential Support Vector Machine , 2012, Arabian Journal for Science and Engineering.

[18]  Ship-Peng Lo,et al.  An adaptive-network based fuzzy inference system for prediction of workpiece surface roughness in end milling , 2003 .