Prediction of surface roughness in turning process using soft computing techniques

Surface quality and dimensional precision will greatly affect parts during their useful life especially in cases where the components will be in direct contact with other elements during their application. This paper deals with three soft computing techniques namely Adaptive Neuro Fuzzy Inference System ANFIS, Neural Networks NN and regression in predicting the surface roughness in turning process. Some of machining variables that have a major impact on the surface roughness in turning process such as spindle speed, feed rate and depth of cut were considered as inputs and surface roughness as output. Here 27 data sets were considered for training and 9 data sets were considered for testing. The predicted surface roughness values computed from ANFIS, NN and regression are compared with experimental data. The comparison indicates that the adoption of ANFIS achieved good accuracy when compared with remaining.