The prediction of the surface roughness for the end-milling process is a very important economic consideration to decrease the production cost in manufacturing environments. In this research, the prediction of the surface roughness (Ra) for GFRP composite material based on the cutting parameters; the cutting speed, the feed rate, the volume fraction ratio and the cutter diameter are studied. Response Surface Methodology (RSM) and Artificial Neural Network (ANN) are used to present the application to predicting the surface roughness for end milling process. The results revealed that; the deviation between the experimental results and the predicted values using (ANOVA) is between (-0.2 and 0.3) and for (ANN) is between (-0.3 and 0.1). The cutting speed and the feed rate are the most significant factors followed by the volume fraction ratio and the cutter diameter respectively. The used techniques, (RSM) and (ANN) can be used for direct evaluation of (Ra) under various combinations of machining parameters during end milling of the GFRP composite materials.
Eisa, A. S. (2019). Prediction of the Surface Roughness for Milling of GFRP Composites Using R.S.M. and ANN. ERJ. Engineering Research Journal, 42(3), 201-210. doi: 10.21608/erjm.2019.66259
MLA
Abeer S. Eisa. "Prediction of the Surface Roughness for Milling of GFRP Composites Using R.S.M. and ANN". ERJ. Engineering Research Journal, 42, 3, 2019, 201-210. doi: 10.21608/erjm.2019.66259
HARVARD
Eisa, A. S. (2019). 'Prediction of the Surface Roughness for Milling of GFRP Composites Using R.S.M. and ANN', ERJ. Engineering Research Journal, 42(3), pp. 201-210. doi: 10.21608/erjm.2019.66259
VANCOUVER
Eisa, A. S. Prediction of the Surface Roughness for Milling of GFRP Composites Using R.S.M. and ANN. ERJ. Engineering Research Journal, 2019; 42(3): 201-210. doi: 10.21608/erjm.2019.66259
)
View on SCiNiTO