Chip Thickness Prediction Model During Turning of Aluminum Alloy 6061

Chip forming is part of the mechanical method of cutting materials, an understanding of the chip formation theory is an important part of the development of production capability of the products. In this paper a turning cutting tests were conducted to Aluminum Alloy 6061 using uncoated carbide cutting tool to develop a chip thickness prediction models utilizing response surface methodology (RSM) via “Minitab 17” software, and Artificial Neural Network (ANN) predicted model via “Matlab” software. The input of the models consists of feed rate, cutting speed, and depth of cut while the output from the models is the thickness of the chips. The model is tested by comparing the experimental values with their forecasted counterparts. The result of the analysis shows that the contribution of the depth of cut is the largest (43.75%), come after the cutting speed (31.25%), and the interaction of the feed rate is less significant (25%). The analysis shows that the experimental design on the basis of response surface methodology (RSM) and an Artificial Neural Network (ANN) models to predict chip thickness as a function of speed, feed, and depth of cut can be used to reduce the cost of machining with confidence about 87% and 90%, respectively. The distribution of data points for the neural network model is comparable to the real experimental data with a coefficient of correlation (R) of 0.95044; this suggested that the neural network model being developed is competent in estimating with reasonable precision. The resultant models indicate that chip thickness decreases when increasing feed rate, cutting speed, and depth of cut.