Asilturk, I.2020-03-262020-03-2620140732-88181747-1567https://dx.doi.org/10.1111/j.1747-1567.2012.00827.xhttps://hdl.handle.net/20.500.12395/30608This article proposes for predicting the surface roughness of AISI 1040 steel material using the artificial intelligent. Cutting speed, feed rate, depth of cut, and nose radius have been taken into consideration as input factors and corresponding surface roughness values (R-a, R-t) as output. A series of experiments have been carried out in accordance with a full factorial design on the CNC lathe to obtain the data used for the training and testing of an artificial neural network (ANN). The developed MATLAB TM interface was used to predict surface roughness. Multilayer perceptron structure, which is a kind of feed forward ANNs, is applied to model and prediction of the surface roughness in turning operations. The number of iterations used was 20,000. MSE = 1E-4 and R-2 = 0.9991 were achieved using the developed ANN Model. The obtained results indicate that the ANN algorithm coupled with back propagation neural network is an efficient and accurate method in predicting of surface roughness in turning.en10.1111/j.1747-1567.2012.00827.xinfo:eu-repo/semantics/closedAccessNeural NetworkCNC TurningSurface RoughnessPrediction ModelArticle3845460Q2WOS:000339551200008Q3