Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear Detection

TL;DR

This study evaluates how different data augmentation techniques and loss functions affect the performance of a U-Net based semantic segmentation model for detecting tool wear in drilling applications, emphasizing binary classification with IoU loss.

Contribution

It systematically compares binary and multiclass segmentation approaches, loss functions, and augmentation strategies for tool wear detection in microscopy images.

Findings

Binary models outperform multiclass models.

Moderate augmentation yields best results.

IoU-based loss improves segmentation accuracy.

Abstract

Tool wear monitoring is crucial for quality control and cost reduction in manufacturing processes, of which drilling applications are one example. In this paper, we present a U-Net based semantic image segmentation pipeline, deployed on microscopy images of cutting inserts, for the purpose of wear detection. The wear area is differentiated in two different types, resulting in a multiclass classification problem. Joining the two wear types in one general wear class, on the other hand, allows the problem to be formulated as a binary classification task. Apart from the comparison of the binary and multiclass problem, also different loss functions, i. e., Cross Entropy, Focal Cross Entropy, and a loss based on the Intersection over Union (IoU), are investigated. Furthermore, models are trained on image tiles of different sizes, and augmentation techniques of varying intensities are deployed. We find, that the best performing models are binary models, trained on data with moderate augmentation and an IoU-based loss function.