Transfer learning enabled convolutional neural networks for estimating health state of cutting tools

Mohamed Marei; Shirine El Zaatari; Weidong Li

doi:10.1016/j.rcim.2021.102145

Transfer learning enabled convolutional neural networks for estimating health state of cutting tools

Mohamed Marei, Shirine El Zaatari, Weidong Li

College of Engineering, Environment & Science

Research output: Contribution to journal › Article › peer-review

77 Citations (Scopus)

143 Downloads (Pure)

Abstract

Effective Prognostics and Health Management (PHM) for cutting tools during Computerized Numerical Control (CNC) processes can significantly reduce downtime and decrease losses throughout manufacturing processes. In recent years, deep learning algorithms have demonstrated great potentials for PHM. However, the algorithms are still hindered by the challenge of the limited amount data available in practical manufacturing situations for effective algorithm training. To address this issue, in this research, a transfer learning enabled Convolutional Neural Networks (CNNs) approach is developed to predict the health state of cutting tools. With the integration of a transfer learning strategy, CNNs can effectively perform tool health state prediction based on a modest number of the relevant images of cutting tools. Quantitative benchmarks and analyses on the performance of the developed approach based on six typical CNNs models using several optimization techniques were conducted. The results indicated the suitability of the developed approach, particularly using ResNet-18, for estimating the wear width of cutting tools. Therefore, by exploiting the integrated design of CNNs and transfer learning, viable PHM strategies for cutting tools can be established to support practical CNC machining applications.

Original language	English
Article number	102145
Number of pages	11
Journal	Robotics and Computer-Integrated Manufacturing
Volume	71
Early online date	2 Mar 2021
DOIs	https://doi.org/10.1016/j.rcim.2021.102145
Publication status	Published - Oct 2021

Bibliographical note

© 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

Funder

Coventry University , Unipart Powertrain Application Ltd. (U.K.), Institute of Digital Engineering (U.K.), and the National Natural Science Foundation of China (Project no. 51975444 ).

Funding

This research is funded by Coventry University , Unipart Powertrain Application Ltd. (U.K.), Institute of Digital Engineering (U.K.), and the National Natural Science Foundation of China (Project no. 51975444 ).

Funders	Funder number
Institute of Digital Engineering
Unipart Powertrain Applications Ltd.
Coventry University
National Natural Science Foundation of China	51975444

Keywords

Prognostics and Health Management
Transfer Learning
convolutional neural networks (CNN)
CNC

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1016/j.rcim.2021.102145

Post-PrintAccepted author manuscript, 1.52 MBLicence: CC BY-NC-ND

Cite this

@article{51071ee451734b3fbc2d62cabef3ac34,

title = "Transfer learning enabled convolutional neural networks for estimating health state of cutting tools",

abstract = "Effective Prognostics and Health Management (PHM) for cutting tools during Computerized Numerical Control (CNC) processes can significantly reduce downtime and decrease losses throughout manufacturing processes. In recent years, deep learning algorithms have demonstrated great potentials for PHM. However, the algorithms are still hindered by the challenge of the limited amount data available in practical manufacturing situations for effective algorithm training. To address this issue, in this research, a transfer learning enabled Convolutional Neural Networks (CNNs) approach is developed to predict the health state of cutting tools. With the integration of a transfer learning strategy, CNNs can effectively perform tool health state prediction based on a modest number of the relevant images of cutting tools. Quantitative benchmarks and analyses on the performance of the developed approach based on six typical CNNs models using several optimization techniques were conducted. The results indicated the suitability of the developed approach, particularly using ResNet-18, for estimating the wear width of cutting tools. Therefore, by exploiting the integrated design of CNNs and transfer learning, viable PHM strategies for cutting tools can be established to support practical CNC machining applications.",

keywords = "Prognostics and Health Management, Transfer Learning, convolutional neural networks (CNN), CNC",

author = "Mohamed Marei and {El Zaatari}, Shirine and Weidong Li",

note = "{\textcopyright} 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Copyright {\textcopyright} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author{\textquoteright}s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it. ",

year = "2021",

month = oct,

doi = "10.1016/j.rcim.2021.102145",

language = "English",

volume = "71",

journal = "Robotics and Computer-Integrated Manufacturing",

issn = "0736-5845",

publisher = "Elsevier",

}

TY - JOUR

T1 - Transfer learning enabled convolutional neural networks for estimating health state of cutting tools

AU - Marei, Mohamed

AU - El Zaatari, Shirine

AU - Li, Weidong

N1 - © 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

PY - 2021/10

Y1 - 2021/10

N2 - Effective Prognostics and Health Management (PHM) for cutting tools during Computerized Numerical Control (CNC) processes can significantly reduce downtime and decrease losses throughout manufacturing processes. In recent years, deep learning algorithms have demonstrated great potentials for PHM. However, the algorithms are still hindered by the challenge of the limited amount data available in practical manufacturing situations for effective algorithm training. To address this issue, in this research, a transfer learning enabled Convolutional Neural Networks (CNNs) approach is developed to predict the health state of cutting tools. With the integration of a transfer learning strategy, CNNs can effectively perform tool health state prediction based on a modest number of the relevant images of cutting tools. Quantitative benchmarks and analyses on the performance of the developed approach based on six typical CNNs models using several optimization techniques were conducted. The results indicated the suitability of the developed approach, particularly using ResNet-18, for estimating the wear width of cutting tools. Therefore, by exploiting the integrated design of CNNs and transfer learning, viable PHM strategies for cutting tools can be established to support practical CNC machining applications.

AB - Effective Prognostics and Health Management (PHM) for cutting tools during Computerized Numerical Control (CNC) processes can significantly reduce downtime and decrease losses throughout manufacturing processes. In recent years, deep learning algorithms have demonstrated great potentials for PHM. However, the algorithms are still hindered by the challenge of the limited amount data available in practical manufacturing situations for effective algorithm training. To address this issue, in this research, a transfer learning enabled Convolutional Neural Networks (CNNs) approach is developed to predict the health state of cutting tools. With the integration of a transfer learning strategy, CNNs can effectively perform tool health state prediction based on a modest number of the relevant images of cutting tools. Quantitative benchmarks and analyses on the performance of the developed approach based on six typical CNNs models using several optimization techniques were conducted. The results indicated the suitability of the developed approach, particularly using ResNet-18, for estimating the wear width of cutting tools. Therefore, by exploiting the integrated design of CNNs and transfer learning, viable PHM strategies for cutting tools can be established to support practical CNC machining applications.

KW - Prognostics and Health Management

KW - Transfer Learning

KW - convolutional neural networks (CNN)

KW - CNC

UR - http://www.scopus.com/inward/record.url?scp=85101816329&partnerID=8YFLogxK

U2 - 10.1016/j.rcim.2021.102145

DO - 10.1016/j.rcim.2021.102145

M3 - Article

SN - 0736-5845

VL - 71

JO - Robotics and Computer-Integrated Manufacturing

JF - Robotics and Computer-Integrated Manufacturing

M1 - 102145

ER -

Transfer learning enabled convolutional neural networks for estimating health state of cutting tools

Abstract

Bibliographical note

Funder

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this