Fuat Kara

Prediction of cutting temperature in orthogonal machining of AISI 316L using artificial neural network

Exp. (experimental) and num. (numerical) cutting forces were obtained by the exp. studies and FEM analysis.The best convergence between exp. and num. cutting forces was provided.Num. cutting temperatures were predicted by ANN within very low error interval.Exp. cutting temperatures were obtained using exp. cutting forces.Exp. temperature results were quite satisfactory. In this study, an approach based on artificial neural network (ANN) was proposed to predict the experimental cutting temperatures generated in orthogonal turning of AISI 316L stainless steel. Experimental and numerical analyses of the cutting forces were carried out to numerically obtain the cutting temperature. For this purpose, cutting tests were conducted using coated (TiCN+Al2O3+TiN and Al2O3) and uncoated cemented carbide inserts. The Deform-2D programme was used for numerical modelling and the Johnson-Cook (J-C) material model was used. The numerical cutting forces for the coated and uncoated tools were compared with the experimental results. On the other hand, the cutting temperature value for each cutting tool was numerically obtained. The artificial neural network model was used to predict numerical cutting temperatures by means of the numerical cutting forces. The best results in predicting the cutting temperature were obtained using the network architecture with a hidden layer which has seven neurons and LM learning algorithm. Finally, the experimental cutting temperatures were predicted by entering the experimental cutting forces into a formula obtained from the artificial neural networks. Statistical results (R2, RMSE, MEP) were quite satisfactory. This demonstrates that the established ANN model is a powerful one for predicting the experimental cutting temperatures.

Prediction of Damage Factor in end Milling of Glass Fibre Reinforced Plastic Composites Using Artificial Neural Network

Glass fibre reinforced plastic (GFRP) composites are an economic alternative to engineering materials because of their superior properties. Some damages on the surface occur due to their complex cutting mechanics in cutting process. Minimisation of the damages is fairly important in terms of product quality. In this study, a GFRP composite material was milled to experimentally minimise the damages on the machined surfaces, using two, three and four flute end mills at different combinations of cutting parameters. Experimental results showed that the damage factor increased with increasing cutting speed and feed rate, on the other hand, it was found that the damage factor decreased with increasing depth of cut and number of the flutes. In addition, analysis of variance (ANOVA) results clearly revealed that the feed rate was the most influential parameter affecting the damage factor in end milling of GFRP composites. Also, in present study, Artificial Neural Network (ANN) models with five learning algorithms were used in predicting the damage factor to reduce number of expensive and time-consuming experiments. The highest performance was obtained by 4-10-1 network structure with LM learning algorithm. ANN was notably successful in predicting the damage factor due to higher R2 and lower RMSE and MEP.

Artificial neural network based modelling of performance of a beta-type Stirling engine

In this article, artificial neural network has been used in order to predict the power (P) and torque (T) values obtained from a beta-type Stirling engine that uses air as working fluid. Experimental data have been obtained for different charge pressures and hot source temperatures using ZrO2-coated and uncoated displacers. The closest artificial neural network results to experimental torque and power values were obtained with double hidden layer 5–13–9–1 and 5–13–7–1 network architectures, respectively. The best prediction values were obtained by Levenberg–Marquardt learning algorithm. Correlation coefficient (R2) for the torque values were 0.998331 and 0.997231 for the training and test sets, respectively, while R2 value for power values were 0.998331 and 0.997231 for the training and test sets, respectively. R2 values show that the developed artificial neural network is an acceptable and powerful modelling technique in predicting the torque and power values of the beta-type Stirling engine.