Milling includes a variety of different tasks and tools, ranging from small individual pieces to large, powerful group processes. It is one of the most commonly used techniques for producing custom parts with exact tolerances. Surface roughness of machined parts has a significant impact on the finished item's quality, which may have an impact on its tolerance and performance. This paper studies the prediction of the values of surface roughness of low-carbon steel AISI 1015 in milling operations. Three different machining parameters with nine variable samples are selected to investigate the resultant surface roughness of the AISI 1015 low-carbon steel samples, including different spindle speeds, feed rates, and depths of cut. The results revealed that the feed rate of 100 mm/min at a spindle speed of 930 rpm and a depth of 1.5 mm produced the lowest surface roughness (Ra) value of 1.170 µm, while the feed rate of 300 mm/min at a spindle speed of 1100 rpm produced the greatest surface roughness value of 2.605.
The Artificial Neural Network (ANN) and numerical methods are used widely for modeling andpredict the performance of manufacturing technologies. In this paper, the influence of millingparameters (spindle speed (rpm), feed rate (mm/min) and tool diameter (mm)) on material removalrate were studied based on Taguchi design of experiments method using (L16) orthogonalarray with 3 factor and 4 levels and Neural Network technique with two hidden layers and neurons.The experimental data were tested with analysis of variance and artificial neural networkmodel has been proposed to predict the responses. Analysis of variance result shows that tooldiameters were the most significant factors that effect on material removal rate. The predictedresults show a good agreement between experimental and predicted values with mean squarederror equal to (0.000001), (0.00003025), (0.002601) and (0.006889) respectively, which produceflexibility to the manufacturing industries to select the best setting based on applications.
RSM and DOEs approach were used to optimize parameters for hypoeutectic A356 Alloy. Statistical analysis of variance (ANOVA) was adopted to identify the effects of process parameters on the performance characteristics in the inclined plate casting process of semisolid A356 alloy which are developed using the Response surface methodology (RSM) to explain the influences of two processing parameters (tilting angle and cooling length) on the performance characteristics of the Mean Particle Size (MPS) of α-Al solid phase and to obtain optimal level of the process parameters. The residuals for the particle size were found to be of significant effect on the response and the predicted regression model has extracted all available information from the experimental data. By applying regression analysis, a mathematical predictive model of the particle size was developed as a function of the inclined plate casting process parameters. In this study, the DOEs results indicated that the optimum setting was approx. (44) degree tilt angle and (42) cm cooling length with particle size (30.5) μm
Turning is the most popular machining operation. The quality of the product may be determined using a variety of metrics, such as the surface generation method and the surface roughness of the product. This work uses cutting variables to obtain the best surface quality through a mathematical model. The suggested surface generation in this work results from deriving it using the Bezier technique, with degree (5th) having six chosen control points. One of the critical indicators of the quality of machined components is the surface roughness created during the machining process. Surface roughness improvement via machining process parameter optimization has been extensively researched. The Taguchi Method and actual tests were employed for evaluating the surface quality of complicated forms; regression models with three different variables for the cutting process, such as cutting speed, depth of cut, and feed rate, were also used. According to the experimental findings, the most significant effect of feed rate on the surface roughness is approximately (40.9%), and the more minor effect of depth of cut on the surface roughness is almost (16.23%). In addition, the average percentage error is 4.93%, the maximum error is 0.14 mm, and the minimum error is -0.143 mm for the prediction using the regression equation.