Efficient Cutting Tool Wear Segmentation Based on Segment Anything Model

TL;DR

This paper introduces an efficient tool wear segmentation method using the Segment Anything Model combined with U-Net, demonstrating high accuracy even with limited training data, suitable for industrial applications.

Contribution

It presents a novel integration of Segment Anything Model with U-Net for automated tool wear segmentation, improving performance with small datasets.

Findings

Outperforms U-Net in wear segmentation accuracy

Effective with limited training data

Potential for industrial application

Abstract

Tool wear conditions impact the surface quality of the workpiece and its final geometric precision. In this research, we propose an efficient tool wear segmentation approach based on Segment Anything Model, which integrates U-Net as an automated prompt generator to streamline the processes of tool wear detection. Our evaluation covered three Point-of-Interest generation methods and further investigated the effects of variations in training dataset sizes and U-Net training intensities on resultant wear segmentation outcomes. The results consistently highlight our approach's advantage over U-Net, emphasizing its ability to achieve accurate wear segmentation even with limited training datasets. This feature underscores its potential applicability in industrial scenarios where datasets may be limited.