Predicting the Resultant Cutting Force in Hard Turning Using Machine Learning Techniques

In the machining process, the cutting force is used for several purposes, including adaptive control, online tool wear observation, and monitoring. Its modeling and computation are the main facets of metal cutting theory, recognizing that many parameters influence its value. Despite the analytical and numerical approaches developed, the current trend is to use artificial intelligence tools for prediction. In this context, machine-learning techniques are used to predict the resulting cutting force during the hard longitudinal turning of AISI 52100 steel by a cBN insert. This study used Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machines (SVM), and Gaussian Process Regression (GPR). For each model, the response is the resultant cutting force, with machining conditions such as workpiece hardness, cutting speed, feed, and depth-of-cut as inputs. The predicted results are compared with the experimental data to determine the effectiveness of the predictive models, showing that ANFIS is the most promising, offering the best performance.