Artificial Intelligent Approach for Machining Titanium Alloy in a Nonconventional Process

Artificial neural networks (ANN) are used in distinct researching fields and professions, and are prepared by cooperation of scientists in different fields such as computer engineering, electronic, structure, biology and so many different branches of science. Many models are built correlating the parameters and the outputs in electrical discharge machining (EDM) concern for different types of materials. Up till now model for Ti-5Al-2.5Sn alloy in the case of electrical discharge machining performance characteristics has not been developed. Therefore, in the present work, it is attempted to generate a model of material removal rate (MRR) for Ti-5Al-2.5Sn material by means of Artificial Neural Network. The experimentation is performed according to the design of experiment (DOE) of response surface methodology (RSM). To generate the DOE four parameters such as peak current, pulse on time, pulse off time and servo voltage and one output as MRR are considered. Ti-5Al-2.5Sn alloy is machined with positive polarity of copper electrode. Finally the developed model is tested with confirmation test. The confirmation test yields an error as within the agreeable limit. To investigate the effect of the parameters on performance sensitivity analysis is also carried out which reveals that the peak current having more effect on EDM performance.

[1]  Pei-Jen Wang,et al.  Comparisons of neural network models on material removal rate in electrical discharge machining , 2001 .

[2]  Hakan Gürün,et al.  Effect of traverse speed on abrasive waterjet machining of Ti–6Al–4V alloy , 2007 .

[3]  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 .

[4]  Bogdan Zak.  The Neural Model of Dynamics of Unmanned Underwater Vehicle , 2005, EUSFLAT Conf..

[5]  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 .

[6]  Kuldeep Ojha,et al.  A review of tool electrode designs for sinking EDM process , 2011 .

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

[8]  Mohan Kumar Pradhan,et al.  Comparisons of neural network models on surface roughness in electrical discharge machining , 2009 .

[9]  G. Krishna Mohana Rao,et al.  Development of hybrid model and optimization of surface roughness in electric discharge machining using artificial neural networks and genetic algorithm , 2009 .

[10]  Masanori Kunieda,et al.  Advancing EDM through fundamental insight into the process , 2005 .

[11]  Sameh Habib,et al.  Study of the parameters in electrical discharge machining through response surface methodology approach , 2009 .

[12]  Ulaş Çaydaş,et al.  Modeling and analysis of electrode wear and white layer thickness in die-sinking EDM process through response surface methodology , 2008 .

[13]  G. Krishna Mohana Rao,et al.  DEVELOPMENT OF HYBRID MODEL AND OPTIMIZATION OF METAL REMOVAL RATE IN ELECTRIC DISCHARGE MACHINING USING ARTIFICIAL NEURAL NETWORKS AND GENETIC ALGORITHM , 2008 .

[14]  Hachour Ouarda.  A Neural Network Based Navigation for Intelligent Autonomous Mobile Robots , 2010 .

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

[16]  Yi Wang,et al.  A hybrid intelligent method for modelling the EDM process , 2003 .