Surface Roughness Prediction in End-Milling Process

Surface roughness prediction for the end-milling process, which is one of the major cutting processes, is a very important economical consideration in order to increase machine operation and decrease production cost in an automated manufacturing environment. In this study; prediction of surface roughness (Ra) for Brass (60/40) material based on cutting parameters: cutting speed, feed rate, and depth of cut; was studied. 

Adaptive neuro-fuzzy inference system (ANFIS) was used to predict the surface roughness in the end milling process. Surface roughness was used as dependant variable while cutting speed of range (750 - 1750rpm), feed rate of range (50 - 250mm/min) and depth of cut of range (0.3 - 0.7mm) were used as predictor variables. Normal and feed forces were used as predictor variables to verify the ANFIS model. Different membership functions were adopted during the training process of ANFIS.The effects of cutting parameters on the normal force, feed force and surface roughness were discussed. Experimental test data were used to examine the ANFIS model by defining the reliability and percentage error of the model. Experimental results demonstrate the effectiveness of the proposed model. While the predicted surface roughness was compared with measured data; the mean square error has been found equal to 8.5 % hence the achieved accuracy is equal to 91.5 %. Although this work focuses on prediction of surface roughness for endmilling operation, the concepts introduced are general; ie., prediction of surface roughness using ANFIS can be applied to many other cutting and machining processes.

 Download

If you need more information about my research work, visit my website.

www.kfs.edu.eg/ibrahemmaher.html
 

Surface roughness prediction in end milling using multiple regression and adaptive neuro-fuzzy inference system

Multiple regression and adaptive neuro-fuzzy inference system (ANFIS) were used to predict the surface roughness in the end milling process. Spindle speed, feed rate and depth of cut were used as predictor variables. Generalized bell memberships function (gbellmf) was adopted during the training process of ANFIS in this study. The predicted surface roughness using multiple regression and ANFIS were compared with measured data, the achieved accuracy were 91.9% and 94% respectively. These results indicate that the training of ANFIS with the gbellmf is accurate than multiple regression in the prediction of surface roughness.

Download

If you need more information about my research work, visit my website.
www.kfs.edu.eg/ibrahemmaher.html

System configuration of Intelligent CNC machining

Machining processes are fundamentally complex, nonlinear, multi variate, and often subjected to various unknown external disturbances. A machining process is usually performed by a skilled operator who uses decision-making capabilities based on the intuition and rules of thumb gained from experience. This process is not accurate enough and in many cases product faults occur. For this reason and to realize highly productive and flexible machining, a reliable, automated machining system with intelligent functions (intelligent machining) is needed.

 

I tried to solve this problem in the following paper. 
http://link.springer.com/article/10.1007/s00170-014-6379-1 

If you need more information about intelligent machines visit my webpage.
www.kfs.edu.eg/ibrahemmaher.html

Or scan me here