An Evaluation of Cutting Forces in CNC Machining Processes Using Machine Learning Approach: A Review

Abstract

Cutting forces play a pivotal role in determining the efficiency, accuracy, and quality of CNC machining processes. Accurate prediction and control of these forces are essential for optimizing tool life, surface finish, and energy consumption. Traditional modeling approaches, such as analytical and empirical methods, often fall short in capturing the complex, nonlinear interactions among machining parameters. In recent years, machine learning (ML) has emerged as a powerful alternative, offering data-driven solutions capable of modeling intricate relationships in real time. This review explores the application of various ML techniques—including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forests, and Deep Learning models such as Long Short-Term Memory (LSTM) networks—for predicting cutting forces in CNC machining. It evaluates the methodologies used for data acquisition, preprocessing, and model training, and compares the performance of different approaches using key metrics like RMSE and R². The paper also discusses current limitations, such as data scarcity and generalization issues, and proposes future directions including real-time deployment, hybrid models, and integration with digital twins. The review concludes that ML offers significant potential for advancing intelligent machining systems by enabling accurate, adaptive, and real-time force prediction.