Precision enhancement in CNC face milling through vibration-aided AI prediction of surface roughness

This study focuses on leveraging CNC technology to enhance the face milling procedures’ surface quality. Determining the success of machining outputs depends heavily on measuring surface roughness. In order to create an intelligent model for forecasting surface roughness, the study gathered total overall vibration data in the X, Y, and Z directions throughout face milling operations. The model’s effectiveness underwent a careful evaluation and assessment. As a result of predicting surface roughness based on total vibrations in all three dimensions, the authors’ intelligent approach represents a substantial advancement. This breakthrough has the potential to redefine efficiency and profitability standards, revolutionize production processes, and optimize resource allocation. A number of models, including polynomial, decision tree, random forest, and ANFIS models, were created to forecast surface roughness. After comparing these models to other machine learning models, the evaluation revealed that the ANFIS model had a 98% prediction accuracy. This indicates that ANFIS is a better model than other models for estimating surface roughness, particularly when using information from machine tool vibrations in all three directions. The upcoming adoption of these cutting-edge technologies is anticipated to transform a number of industries, underlining the authors’ ground-breaking contributions to the trajectory of industrial advancement.