Deep Learning Based Tool Wear Estimation Considering Cutting Conditions

TL;DR

This paper introduces a deep learning model that incorporates cutting conditions to accurately estimate tool wear and enhance transferability across different milling scenarios, addressing industrial needs for reliable, zero-shot tool wear prediction.

Contribution

The study presents a convolutional neural network that integrates cutting conditions as inputs, improving tool wear estimation accuracy and transferability compared to traditional models.

Findings

Outperforms conventional models in accuracy

Maintains performance across various cutting parameters

Demonstrates potential for industrial application

Abstract

Tool wear conditions impact the final quality of the workpiece. In this study, we propose a deep learning approach based on a convolutional neural network that incorporates cutting conditions as extra model inputs, aiming to improve tool wear estimation accuracy and fulfill industrial demands for zero-shot transferability. Through a series of milling experiments under various cutting parameters, we evaluate the model's performance in terms of tool wear estimation accuracy and its transferability to new fixed or variable cutting parameters. The results consistently highlight our approach's advantage over conventional models that omit cutting conditions, maintaining superior performance irrespective of the stability of the wear development or the limitation of the training dataset. This finding underscores its potential applicability in industrial scenarios.