A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network
Tool wear condition monitoring during the machining process is one of the most important considerations in precision manufacturing. Cutting force is one of the signals that has been widely used for tool wear condition monitoring, which contains the dynamical information of tool wear conditions. This...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/21/8343 |
_version_ | 1797466473589899264 |
---|---|
author | Xu Yang Rui Yuan Yong Lv Li Li Hao Song |
author_facet | Xu Yang Rui Yuan Yong Lv Li Li Hao Song |
author_sort | Xu Yang |
collection | DOAJ |
description | Tool wear condition monitoring during the machining process is one of the most important considerations in precision manufacturing. Cutting force is one of the signals that has been widely used for tool wear condition monitoring, which contains the dynamical information of tool wear conditions. This paper proposes a novel multivariate cutting force-based tool wear monitoring method using one-dimensional convolutional neural network (1D CNN). Firstly, multivariate variational mode decomposition (MVMD) is used to process the multivariate cutting force signals. The multivariate band-limited intrinsic mode functions (BLIMFs) are obtained, which contain a large number of nonlinear and nonstationary tool wear characteristics. Afterwards, the proposed modified multiscale permutation entropy (MMPE) is used to measure the complexity of multivariate BLIMFs. The entropy values on multiple scales are calculated as condition indicators in tool wear condition monitoring. Finally, the one-dimensional feature vectors are constructed and employed as the input of 1D CNN to achieve accurate and stable tool wear condition monitoring. The results of the research in this paper demonstrate that the proposed approach has broad prospects in tool wear condition monitoring. |
first_indexed | 2024-03-09T18:40:22Z |
format | Article |
id | doaj.art-b4b5009a2fb94105b53527b6cde73efc |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T18:40:22Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b4b5009a2fb94105b53527b6cde73efc2023-11-24T06:46:34ZengMDPI AGSensors1424-82202022-10-012221834310.3390/s22218343A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural NetworkXu Yang0Rui Yuan1Yong Lv2Li Li3Hao Song4Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaKey Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, ChinaTool wear condition monitoring during the machining process is one of the most important considerations in precision manufacturing. Cutting force is one of the signals that has been widely used for tool wear condition monitoring, which contains the dynamical information of tool wear conditions. This paper proposes a novel multivariate cutting force-based tool wear monitoring method using one-dimensional convolutional neural network (1D CNN). Firstly, multivariate variational mode decomposition (MVMD) is used to process the multivariate cutting force signals. The multivariate band-limited intrinsic mode functions (BLIMFs) are obtained, which contain a large number of nonlinear and nonstationary tool wear characteristics. Afterwards, the proposed modified multiscale permutation entropy (MMPE) is used to measure the complexity of multivariate BLIMFs. The entropy values on multiple scales are calculated as condition indicators in tool wear condition monitoring. Finally, the one-dimensional feature vectors are constructed and employed as the input of 1D CNN to achieve accurate and stable tool wear condition monitoring. The results of the research in this paper demonstrate that the proposed approach has broad prospects in tool wear condition monitoring.https://www.mdpi.com/1424-8220/22/21/8343tool wear condition monitoringmultivariate cutting force signalsmodified multiscale permutation entropyone-dimensional convolutional neural network |
spellingShingle | Xu Yang Rui Yuan Yong Lv Li Li Hao Song A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network Sensors tool wear condition monitoring multivariate cutting force signals modified multiscale permutation entropy one-dimensional convolutional neural network |
title | A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network |
title_full | A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network |
title_fullStr | A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network |
title_full_unstemmed | A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network |
title_short | A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network |
title_sort | novel multivariate cutting force based tool wear monitoring method using one dimensional convolutional neural network |
topic | tool wear condition monitoring multivariate cutting force signals modified multiscale permutation entropy one-dimensional convolutional neural network |
url | https://www.mdpi.com/1424-8220/22/21/8343 |
work_keys_str_mv | AT xuyang anovelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT ruiyuan anovelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT yonglv anovelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT lili anovelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT haosong anovelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT xuyang novelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT ruiyuan novelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT yonglv novelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT lili novelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork AT haosong novelmultivariatecuttingforcebasedtoolwearmonitoringmethodusingonedimensionalconvolutionalneuralnetwork |