In this paper artificial neural network (ANN) and regression analysis were used for the prediction of surface roughness. Five models of neural network were developed and the model that showed best fit with experimental results was with 6 neurons in the hidden layer. Regression analysis was also used to build a mathematical model representing the surface roughness as a function of the process parameters. The coefficient of determination was found to be 94.93% and 93.63%, for the best neural network model and regression analysis, respectively, from the comparison of the models with thirteen validation experimental tests. Optical microscopy was conducted on two machined surfaces with two different values of feed rates while maintaining the spindle speed and depth of cut at the same values. Examining the surface topology and surface roughness profile for the two surfaces revealed that higher feed rate results in relatively thick roughness markings that are distantly spaced, whereas low values of feed rate result in thin surface roughness markings that are closely spaced giving better surface finish.

A full factorial design technique is used to investigate the effect of machining parameters, namely, spindle speed(N), depth of cut(ap),and table feed rate(Vf),on the obtained surface roughness (RaandRt) during face milling operation of high strength steel. A second-order regression model was built using least squares method depending on the factorial design results to approximate a mathematical relationship between the surface roughness and the studied process parameters. Analysis of variance was conducted to estimate the significance of each factor and interaction with respect to the surface roughness. ForRa, the results show that spindle speed, depth of cut, and table feed rate have a significant effect on the surface roughness in both linear and quadratic terms. There is also an interaction between depth of cut and feed rate. It also appears that feed rate has the greatest effect on the data variation followed by depth of cut. ForRt, the results show that the table feed rate is the most effective factor followed by the depth of cut, while the spindle speed had a significant small effect only in its quadratic term. The conditions of minimumRaandRtare identified through least square optimization. Moreover, multiobjective optimization for minimizingRaand maximizing metal removal rateQis conducted and the results are presented.

Single-point incremental forming (SPIF) is a technology that allows incremental manufacturing of complex parts from a flat sheet using simple tools; further, this technology is flexible and economical. Measuring the forming force using this technology helps in preventing failures, determining the optimal processes, and implementing on-line control. In this paper, an experimental study using SPIF is described. This study focuses on the influence of four different process parameters, namely, step size, tool diameter, sheet thickness, and feed rate, on the maximum forming force. For an efficient force predictive model based on an adaptive neuro-fuzzy inference system (ANFIS), an artificial neural network (ANN) and a regressions model were applied. The predicted forces exhibited relatively good agreement with the experimental results. The results indicate that the performance of the ANFIS model realizes the full potential of the ANN model.

Solid state recycling through hot extrusion is a promising technique to recycle machining chips without remelting. Furthermore, equal channel angular pressing (ECAP) technique coupled with the extruded recycled billet is introduced to enhance the mechanical properties of recycled samples. In this paper, the surface roughness of solid state recycled aluminum alloy 6061 turning chips was investigated. Aluminum chips were cold compacted and hot extruded under an extrusion ratio (ER) of 5.2 at an extrusion temperature (ET) of 425°C. In order to improve the properties of the extruded samples, they were subjected to ECAP up to three passes at room temperature using an ECAP die with a channel die angle(Φ)of 90°. Surface roughness (RaandRz) of the processed recycled billets machined by turning was investigated. Box-Behnken experimental design was used to investigate the effect of three machining parameters (cutting speed, feed rate, and depth of cut) on the surface roughness of the machined specimens for four materials conditions, namely, extruded billet and postextrusion ECAP processed billets to one, two, and three passes. Quadratic models were developed to relate the machining parameters to surface roughness, and a multiobjective optimization scheme was conducted to maximize material removal rate while maintaining the roughness below a preset practical value.

AISI 1045 has been widely used in many industrial applications requiring good wear resistance and strength. Surface roughness of produced components is a vital quality measure. A suitable combination of machining process parameters must be selected to guarantee the required roughness values. The appropriate parameters are generally defined based on ideal lab conditions since most of the researchers conduct their experiments in closed labs and ideal conditions. However, when repeating these experiments in industrial workshops, different results are obtained. Imperfect conditions such as the absence of a turning tool with definite specifications as shown in know-how “tool nose radius 0.4 mm” and its replacement with the closest existence tool “tool nose radius 0.8 mm” as well as the interruption of cutting fluid during work as a result of sudden failure in the coolant pump lead to the mentioned different lab-industrial conditions. These complications are common among normal problems that happened during the metal cutting process in realistic conditions and are called noise factors. In this paper, Taguchi robust design is used to select the optimum combination of the cutting speed, depth of cut, and feed rate to enhance the surface roughness of turned AISI 1045 steel bars while minimizing the effects of the two noise factors. The optimum parameters predicted by the developed model showed good agreement with the experimental results.