Data-driven tool wear prediction in milling, based on a process-integrated single-sensor approach

2024-12-27

AI Summary

Tool wear prediction in milling operations suffers from reliance on multi-sensor setups, poor generalizability across machining processes, and severe performance degradation under small-sample conditions. Method: This paper proposes a lightweight cross-process transfer learning framework leveraging a single accelerometer. It introduces a novel paradigm—“single sensor + STFT-based time-frequency representation + ConvNeXt”—integrating short-time Fourier transform feature extraction with a lightweight vision backbone. The model is trained on minimal data (full lifecycle signals from only four tools) and adapted across diverse machining processes via transfer learning. Contribution/Results: Experimental evaluation achieves 99.1% accuracy in wear-state classification, substantially outperforming CNN, LSTM, SVM, and decision tree baselines. The approach reduces hardware cost, enables rapid adaptation across machining processes, and provides an efficient, deployable solution for edge-enabled intelligent maintenance.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate tool wear prediction is essential for maintaining productivity and minimizing costs in machining. However, the complex nature of the tool wear process poses significant challenges to achieving reliable predictions. This study explores data-driven methods, in particular deep learning, for tool wear prediction. Traditional data-driven approaches often focus on a single process, relying on multi-sensor setups and extensive data generation, which limits generalization to new settings. Moreover, multi-sensor integration is often impractical in industrial environments. To address these limitations, this research investigates the transferability of predictive models using minimal training data, validated across two processes. Furthermore, it uses a simple setup with a single acceleration sensor to establish a low-cost data generation approach that facilitates the generalization of models to other processes via transfer learning. The study evaluates several machine learning models, including convolutional neural networks (CNN), long short-term memory networks (LSTM), support vector machines (SVM) and decision trees, trained on different input formats such as feature vectors and short-time Fourier transform (STFT). The performance of the models is evaluated on different amounts of training data, including scenarios with significantly reduced datasets, providing insight into their effectiveness under constrained data conditions. The results demonstrate the potential of specific models and configurations for effective tool wear prediction, contributing to the development of more adaptable and efficient predictive maintenance strategies in machining. Notably, the ConvNeXt model has an exceptional performance, achieving an 99.1% accuracy in identifying tool wear using data from only four milling tools operated until they are worn.

Problem

• Tool Wear Prediction
• Milling Process
• Sensor Data Analysis

Innovation

• Depth Learning
• ConvNeXt Model
• Predictive Maintenance