Comparison of a full factorial experiment to fractional and taguchi designs in a lathe dry turning operation

This paper presents a comparison of three different experimental designs aimed at studying the effects of cutting parameters variations on surface finish. The results revealed that the effects obtained by analyzing both fractional and Taguchi designs (16 trials each) were comparable to the main effects and tow-level interactions obtained by the full factorial design (288 trials). Thus, we conclude that screening designs appear to be reliable and more economical since they permit to reduce by a factor 18 the amount of time and effort required to conduct the experimental design without losing valuable information.     

Effect of tool vibrations on surface roughness during lathe dry turning process

Choice of optimized cutting parameters is very important to control the required surface quality. In fact, the difference between the real and theoretical surface roughness can be attributed to the influence of physical and dynamic phenomena such as: built-up edge, friction of cut surface against tool point and vibrations. The focus of this study is the collection and analysis of surface roughness and tool vibration data generated by lathe dry turning of mild carbon steel samples at different levels of speed, feed, depth of cut, tool nose radius, tool length and work piece length. A full factorial experimental design (288 experiments ) that allows to consider the three-level interactions between the independant variables has been conducted. Vibration analysis has revealed that the dynamic force, related to the chip-thickness variation acting on the tool, is related to the amplitude of tool vibration at resonance and to the variation of the tool's natural frequency while cutting. The analogy of the effect of cutting parameters between tool dynamic forces and surface roughness is also investigated. The results show that second order interactions between cutting speed and tool nose radius, along with third-order interaction between feed rate, cutting speed and depth of cut are the factors with the greatest influence on surface roughness and tool dynamic forces in this type of operation and parameter levels studied. The analysis of variance revealed that the best surface roughness condition is achieved at a low feed rate (less than 0.35 mnt/rev), a large tool nose radius (1.59 mm) and a high cutting speed (265 m/min and above). The results also show that the depth of cut has not a significant effect on surface roughness, except when operating within the built-up edge range. It is shown that a correlation between surface roughness and tool dynamic force exist only when operating in the built-up edge range. In these cases, built-u edge formation deteriorates surface roughness and increases dynamic forces acting on the tool. The effect of built-up edge formation on surface roughness can be minimized by increasing depth of cut and increasing tool vibration. Key words:design of experiments, lathe dry turning operation, full factorial design, surface roughness, measurements, cutting parameters, tool vibrations.     

Prediction of surface roughness in CNC face milling using neural networks and Taguchi''s design of experiments

In this paper, a neural network modeling approach is presented for the prediction of surface roughness (R_a) in CNC face milling. The data used for the training and checking of the networks’ performance derived from experiments conducted on a CNC milling machine according to the principles of Taguchi design of experiments (DoE) method. The factors considered in the experiment were the depth of cut, the feed rate per tooth, the cutting speed, the engagement and wear of the cutting tool, the use of cutting fluid and the three components of the cutting force. Using feedforward artificial neural networks (ANNs) trained with the Levenberg–Marquardt algorithm, the most influential of the factors were determined, again using DoE principles, and a 5×3×1 ANN based on them was able to predict the surface roughness with a mean squared error equal to 1.86% and to be consistent throughout the entire range of values.     

The experimental investigation of the effects of uncoated,PVD- and CVD-coated cemented carbide inserts and cutting parameters on surface roughness in CNC turning and its prediction using artificial neural networks

In this study the machining of AISI 1030 steel (i.e. orthogonal cutting) uncoated, PVD- and CVD-coated cemented carbide insert with different feed rates of 0.25, 0.30, 0.35, 0.40 and 0.45 mm/rev with the cutting speeds of 100, 200 and 300 m/min by keeping depth of cuts constant (i.e. 2 mm), without using cooling liquids has been accomplished. The surface roughness effects of coating method, coating material, cutting speed and feed rate on the workpiece have been investigated. Among the cutting tools—with 200 mm/min cutting speed and 0.25 mm/rev feed rate—the TiN coated with PVD method has provided 2.16 μm, TiAlN coated with PVD method has provided 2.3 μm, AlTiN coated with PVD method has provided 2.46 μm surface roughness values, respectively. While the uncoated cutting tool with the cutting speed of 100 m/min and 0.25 mm/rev feed rate has yielded the surface roughness value of 2.45 μm. Afterwards, these experimental studies were executed on artificial neural networks (ANN). The training and test data of the ANNs have been prepared using experimental patterns for the surface roughness. In the input layer of the ANNs, the coating tools, feed rate (f) and cutting speed (V) values are used while at the output layer the surface roughness values are used. They are used to train and test multilayered, hierarchically connected and directed networks with varying numbers of the hidden layers using back-propagation scaled conjugate gradient (SCG) and Levenberg–Marquardt (LM) algorithms with the logistic sigmoid transfer function. The experimental values and ANN predictions are compared by statistical error analyzing methods. It is shown that the SCG model with nine neurons in the hidden layer has produced absolute fraction of variance (R²) values about 0.99985 for the training data, and 0.99983 for the test data; root mean square error (RMSE) values are smaller than 0.00265; and mean error percentage (MEP) are about 1.13458 and 1.88698 for the training and test data, respectively. Therefore, the surface roughness value has been determined by the ANN with an acceptable accuracy.