Optimization of End milling process for minimizing surface roughness with combined artificial Neural Network and Genetic Algorithm

Authors

1 M.Sc., Department of Mechanical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.

2 Prof., Department of Mechanical Engineering, Lean Production Engineering Research Center, Ferdowsi University of Mashhad, Mashhad, Iran.

Abstract

Through enormous development of machining methods, applying optimization method in machining process to improve quality seems to be important. One of the most important parameter of a work piece is its surface roughness. As surface roughness decrease, the quality of work piece increase. In this study, optimization of input parameter of end mill machining to reach minimum surface roughness is investigated. Among these parameters five of them selected and Taguchi method is used for the design of experiments. The process is modeled with neural network method and using try and error test 5-8-6-1 architecture. Genetic algorithm is used for process optimizing and neural network model is selected as the target function. For three different tool path strategies, optimization has been conducted and results are discussed. Using genetic algorithm decrease surface roughness to 0.85 μm. Finally selected level of Taguchi method is analyzed and levels with maximum signal to noise ratio are introduced as optimized level that have minimum surface roughness.

Keywords

Main Subjects

References

[1] Stephenson DA, Agapiou JS (2005) Metal cutting theory and practice. 68.CRC press.
[2] Zain AM, Haron H, Sharif S (2008) An overview of GA technique for surface roughness optimization in milling process. ITSim 2008. International Symposium. Kuala Lumpur, Malaysia.
[3] Oktem H, Erzurumlu T, Erzincanli F (2006) Prediction of minimum surface roughness in end milling mold parts using neural network and genetic algorithm. Mater Design 27(9): 735-744.
[4] Zain AM, Haron H, Sharif S (2010) Application of GA to optimize cutting conditions for minimizing surface roughness in end milling machining process. Expert Syst Appl 37(6): 4650-4659.
[5] Suresh P, Rao PV, Deshmukh S (2002) A genetic algorithmic approach for optimization of surface roughness prediction model. Int J Mach Tool Manu 42(6): 675-680.
[6] Brezocnik M, Kovacic M, Ficko M (2004) Prediction of surface roughness with genetic programming. J Mater Process Tech 157: 28-36.
[7] Çolak O, Kurbanoğlu C, Kayacan MC (2007) Milling surface roughness prediction using evolutionary programming methods. Mater Design 28(2): 657-666.
[8] Tanse IN (2006) Selection of optimal cutting conditions by using GONNS. Int J Mach Tool Manu 46(1): 26-35.
[9] Palanisamy P, Rajendran I, Shanmugasundaram S (2007) Optimization of machining parameters using genetic algorithm and experimental validation for end-milling operations. Int J Adv Manuf Tech 32(7-8): 644-655.
[10] Gologlu C, Sakarya N (2008) The effects of cutter path strategies on surface roughness of pocket milling of 1.2738 steel based on Taguchi method. J Mater Process Tech 206(1): 7-15.
[11] Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press.
[12] Golberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Longman Publishing Co Inc. Boston, MA, USA.
Journal of Solid and Fluid Mechanics
Volume 7, Issue 2
July and August 2017
Pages 81-91

Files

Share

How to cite

Statistics