Comparison Analysis of CNC Machine Tool Wear Conditions using Deep Learning

Tool wear significantly affects the efficiency, precision, and cost-effectiveness of CNC machining processes. Early detection of tool wear failure can minimize downtime, improve machining performance, and prevent workpiece damage. This study offers a comparative analysis of different techniques for detecting and classifying tool wear in CNC machining, focusing on deep learning models and fuzzy logicbased systems. Experimental data, collected from vibration sensors during dry milling operations, were analyzed to explore the correlation between vibration signals and tool wear progression. A Mamdani Fuzzy Inference System (FIS) was developed in MATLAB, using vibration amplitude frequency as the primary input variable to classify tool wear conditions. The FIS system demonstrated high reliability in distinguishing between different tool wear levels and was compared with machine learning models like Random Forest and Convolutional Neural Networks (CNN). The results revealed that the Mamdani FIS outperformed traditional machine learning models in terms of tool wear detection of 99.98 % accuracy, and reliability, offering a promising solution for realtime monitoring in CNC machining.