Estimation and Optimization Cutting Conditions of Surface Roughness in Hard Turning Using Taguchi Approach and Artificial Neural Network
One of the most important requirements of part manufacturing is the surface quality. This is so because the most important part is meeting the specific requirements of customers. The surface roughness is a leading indicator of the quality of the machined surface Parts. In the present work in an experimental study to achieve by application of Taguchi method to investigate the effect of three parameters, which known as cutting speeds of (45, 90, and 135 m/min), feed rate of (0.1, 0.2, and 0.3 mm/rev), and cut depth of (0.05, 0.1, and 0.15 mm) on performance measure of surface roughness (Ra). Thus to determine the optimal levels and to analyze the cutting parameter’s effect on the surface finish values by employing different method of Orthogonal array, S/N ratio, analysis of variance (ANOVA). During our work two models for prediction have been used. The first one is known as the method of regression analysis, and the second is the method of Adaptive - Neural Network (ANN) relying on practical results. The achieved results show that the estimation and prediction ability of neural networks is better than the regression analysis. Experimental results confirmed with optimal levels of the machining parameters which are clarified by using Taguchi optimization method. Also, the indicated results of the Taguchi’s method show its ability to improve the process.
A. A. Abdullah et al., "Estimation and Optimization Cutting Conditions of Surface Roughness in Hard Turning Using Taguchi Approach and Artificial Neural Network", Advanced Materials Research, Vols. 463-464, pp. 662-668, 2012