Modeling of machining parameters of Ti-6Al-4V for electric discharge machining: A neural network approach

This paper presents the artificial intelligence model to predict the optimal machining parameters for Ti-6Al-4V through electrical discharge machining (EDM) using copper as an electrode and positive polarity of the electrode. The objective of this paper is to investigate the peak current, servo voltage, pulse on- and pulse off-time in EDM effects on material removal rate (MRR), tool wear rate (TWR) and surface roughness (SR). Radial basis function neural network (RBFNN) is used to develop the artificial neural network (ANN) modeling of MRR, TWR and SR. Design of experiments (DOE) method by using response surface methodology (RSM) techniques are implemented.  The validity test of the fit and adequacy of the proposed models has been carried out through analysis of variance (ANOVA). The optimum machining conditions are estimated and verified with proposed ANN model. It is observed that the developed model is within the limits of the agreeable error with experimental results. Sensitivity analysis is carried out to investigate the relative influence of factors on the performance measures. It is observed that peak current effectively influences the performance measures. The reported results indicate that the proposed ANN models can satisfactorily evaluate the MRR, TWR as well as SR in EDM. Therefore, the proposed model can be considered as valuable tools for the process planning for EDM and leads to economical industrial machining by optimizing the input parameters.   Key words: Ti-6AL-4V, material removal rate, tool wear rate, surface roughness, radial basis function neural network, response surface method.

[1]  Kazuo Yamazaki,et al.  A fundamental study on Ti–6Al–4V's thermal and electrical properties and their relation to EDM productivity , 2008 .

[2]  Harshit K. Dave,et al.  Investigations on Prediction of MRR and Surface Roughness on Electro Discharge Machine Using Regression Analysis and Artificial Neural Network Programming , 2008 .

[3]  U. Çaydas,et al.  Electrical discharge machining of titanium alloy (Ti–6Al–4V) , 2007 .

[4]  I. Puertas,et al.  Spacing roughness parameters study on the EDM of silicon carbide , 2005 .

[5]  Bogdan Filipič,et al.  Machine learning induction of a model for online parameter selection in EDM rough machining , 2009 .

[6]  Pei-Jen Wang,et al.  Predictions on surface finish in electrical discharge machining based upon neural network models , 2001 .

[7]  Parametric optimization in EDM of Ti-6Al-4V using copper tungsten electrode and positive polarity: a statistical approach , 2011 .

[8]  K. Kadirgama,et al.  Optimization of Machining Parameters on Tool Wear Rate of Ti-6Al-4V through EDM Using Copper Tungsten Electrode: A Statistical Approach , 2010 .

[9]  Mahmudur Rahman,et al.  Optimization of Machining Parameters on Surface Roughness in EDM of Ti-6Al-4V Using Response Surface Method , 2011 .

[10]  Valentin N. Moiseyev,et al.  Titanium Alloys: Russian Aircraft and Aerospace Applications , 2005 .

[11]  Surjya K. Pal,et al.  Modeling of electrical discharge machining process using back propagation neural network and multi-objective optimization using non-dominating sorting genetic algorithm-II , 2007 .

[12]  Sachin Maheshwari,et al.  Some investigations into the electric discharge machining of hardened tool steel using different electrode materials , 2004 .

[13]  Rosli Abu Bakar,et al.  Mathematical modeling of material removal rate for Ti-5Al-2.5Sn through EDM process: a surface response method , 2010 .