TOOL WEAR SEGMENTATION USING YOLOv11 FOR ENHANCED MACHINING EFFICIENCY

Abstract

Tool wear monitoring is crucial to ensure machining accuracy and extend tool life in turning operations. This study presents a novel method using YOLOv11 for tool wear segmentation in turning processes. Unlike traditional wear detection methods that rely on manual inspection or indirect sensorbased techniques, our method leverages deep learning to accurately identify and segment wear zones from images captured during machining. The proposed model is trained on a tool wear image dataset and optimized for real-time performance. Experimental results demonstrate that YOLOv11 achieves high segmentation accuracy, effectively distinguishing wear zones during machining. The study enhances tool wear assessment, helping machining engineers and improving production efficiency.