Predicting surface roughness of hardened AISI 1040 based on cutting parameters using neural networks and multiple regression

In this study, models for predicting the surface roughness of AISI 1040 steel material using artificial neural networks (ANN) and multiple regression (MRM) are developed. The models are optimized using cutting parameters as input and corresponding surface roughness values as output. Cutting parameters considered in this study include cutting speed, feed rate, depth of cut, and nose radius. Surface roughness is characterized by the mean (R (a)) and total (R (t)) of the recorded roughness values at different locations on the surface. A total of 81 different experiments were performed, each with a different setting of the cutting parameters, and the corresponding R (a) and R (t) values for each case are measured. Input-output pairs obtained through these 81 experiments are used to train an ANN is achieved at the 200,00th epoch. Mean squared error of 0.002917120% achieved using the developed ANN outperforms error rates reported in earlier studies and can also be considered admissible for real-time deployment of the developed ANN algorithm for robust prediction of the surface roughness in industrial settings.