Artificial Intelligent Approach for Machining Titanium Alloy in a Nonconventional Process

• Main Authors: Khan, Md. Ashikur Rahman, M. M., Rahman, K., Kadirgama
• Format: Article
• Language: English
• Published: World Academy of Science, Engineering and Technology 2013
• Subjects: TJ Mechanical engineering and machinery
• Online Access: http://umpir.ump.edu.my/id/eprint/6458/1/Artificial_Intelligent_Approach_for_Machining_Titanium_Alloy_in_a_Nonconventional_Process.pdf; http://umpir.ump.edu.my/id/eprint/6458/; http://waset.org/publications/9997233/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.