ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR END MILLING

• Main Authors: ANGELOS P. MARKOPOULOS, SOTIRIOS GEORGIOPOULOS, MYRON KINIGALAKIS, DIMITRIOS E. MANOLAKOS
• Format: Article
• Language: English
• Published: Taylor's University 2016-09-01
• Series: Journal of Engineering Science and Technology
• Subjects: Artificial Intelligence; modelling; milling; surface roughness
• Online Access: http://jestec.taylors.edu.my/Vol%2011%20issue%209%20September%202016/11_9_2.pdf

Soft computing is commonly used as a modelling method in various technological areas. Methods such as Artificial Neural Networks and Fuzzy Logic have found application in manufacturing technology as well. NeuroFuzzy systems, aimed to combine the benefits of both the aforementioned Artificial Intelligence methods, are a subject of research lately as have proven to be superior compared to other methods. In this paper an adaptive neuro-fuzzy inference system for the prediction of surface roughness in end milling is presented. Spindle speed, feed rate, depth of cut and vibrations were used as independent input variables, while roughness parameter Ra as dependent output variable. Several variations are tested and the results of the optimum system are presented. Final results indicate that the proposed model can accurately predict surface roughness, even for input that was not used in training.