Investigation of the performance of the MQL, dry, and wet turning by response surface methodology (RSM) and artificial neural network (ANN)

In this approach, response surface methodology (RSM) and artificial neural network (ANN) techniques were used in order to search for optimal prediction of uncontrollable machining factors that leads to better machining performance. The experiment has been established using 3 levels and 4 factors Box-Behnken design (BBD) for tangential force and surface roughness measurements according to combinations of cutting speed, feed rate, and cutting depth using multilayer-coated tungsten carbide insert with various nose radius in turning of X210Cr12 steel under dry, wet, and MQL machining. Consequently, it could be possible to investigate the efficiency of MQL technique for an environment-friendly ecological machining. Then, a comparative between ANN and RSM models has been established to determine the best approach according to model accuracy and capability for predicting surface roughness and cutting force. The ANN method provides more accurate results and proved its effectiveness as soon as its correlation coefficients, mean prediction errors (MPEs), and root mean square errors are rather small compared to those obtained by the RSM method.