Enhancing Predictive Maintenance in Contour Cutting Machines: A Similarity-Based Approach for Band Blade Remaining Useful Life Estimation and Early Fault Detection

被引：0
|
作者：
Sharma, Shubham [1 ]
Richter, Wolfgang [1 ]
Bertelmann, Philipp [2 ]
Kraemer, Peter [1 ]
机构：
[1] University of Siegen, Siegen, Germany
[2] Albrecht Bäumer GmbH & Co. KG, Freudenberg, Germany
来源：
e-Journal of Nondestructive Testing | 2024年 / 29卷 / 07期
关键词：
Anticipating the Remaining Useful Life (RUL) of cutting tools is crucial for optimising operational efficiency; ensuring safety; and minimising maintenance costs. This paper addresses the unresolved challenge of unexpected band blade failures in contour cutting machines within the foam and plastic industry; where such failures disrupt production; lead to material wastage; and pose operational hazards. Band blades circulate continuously at very high speeds during operation; and no classic sensor technology can be applied to them. Any information required to estimate the condition of the band blades must be acquired externally. Using similarity-based prediction models; a strategy for estimating band blades' effective RUL is proposed. Historical failure data is systematically collected from a contour-cutting machine operating under various load conditions using multiple contact and non-contact sensors mounted on the machine. Features are extracted and processed from the mounted sensors in both time and frequency domains using classical condition monitoring techniques. The classification of damaged and undamaged states of the blade is performed using bagged decision trees; which consider predefined health levels of the band blade during test runs. Degradation trends are generated for a test set of blade failures and a similarity model is trained on this data to determine the remaining life. Different features are selected based on their prognostic capabilities to optimise the proposed algorithm's performance. The developed model is tested on new data; demonstrating efficacy in predicting band blades' health status and RUL with good accuracy. This research contributes to cutting tool condition monitoring and predictive maintenance by offering a novel and reliable approach for early fault detection and estimation of the RUL of band blades in contour cutting machines; mitigating disruptions; reducing material wastage and enhancing overall operational efficiency. The procedures are validated in situ with a latest generation's real contour-cutting machine. © 2024; NDT. net GmbH and Co. KG. All rights reserved;
D O I：
10.58286/29807
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 21 条
  • [1] A Similarity-Based Prognostics Approach for Remaining Useful Life Estimation of Engineered Systems
    Wang, Tianyi
    Yu, Jianbo
    Siegel, David
    Lee, Jay
    2008 INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT (PHM), 2008, : 53 - +
  • [2] A neural network filtering approach for similarity-based remaining useful life estimation
    Oguz Bektas
    Jeffrey A. Jones
    Shankar Sankararaman
    Indranil Roychoudhury
    Kai Goebel
    The International Journal of Advanced Manufacturing Technology, 2019, 101 : 87 - 103
  • [3] A neural network filtering approach for similarity-based remaining useful life estimation
    Bektas, Oguz
    Jones, Jeffrey A.
    Sankararaman, Shankar
    Roychoudhury, Indranil
    Goebel, Kai
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2019, 101 (1-4): : 87 - 103
  • [4] Multi-class Similarity-based Approach for Remaining Useful Life Estimation
    Onofri, Silvia
    Marchioni, Alex
    Setti, Gianluca
    Mangia, Mauro
    Rovatti, Riccardo
    2024 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC 2024, 2024,
  • [5] An unsupervised approach for health index building and for similarity-based remaining useful life estimation
    Schwartz, Sebastien
    Jimenez, Juan Jose Montero
    Vingerhoeds, Rob
    Salaun, Michel
    COMPUTERS IN INDUSTRY, 2022, 141
  • [6] Remaining Useful Life estimation for electric vehicle batteries using a similarity-based approach
    Catelani, Marcantonio
    Ciani, Lorenzo
    Grasso, Francesco
    Patrizi, Gabriele
    Reatti, Alberto
    2022 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AUTOMOTIVE (IEEE METROAUTOMOTIVE 2022), 2022, : 82 - 87
  • [7] A Similarity-Based Remaining Useful Life Prognostic Approach of Equipment Components
    Lei, Cong-Ying
    Xia, Liang-Hua
    Wu, Bo
    Liu, Gang
    PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON QUALITY, RELIABILITY, RISK, MAINTENANCE, AND SAFETY ENGINEERING (QR2MSE), VOLS I-IV, 2013, : 1874 - 1877
  • [8] Robot fault detection and remaining life estimation for predictive maintenance
    Pinto, Riccardo
    Cerquitelli, Tania
    10TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT 2019) / THE 2ND INTERNATIONAL CONFERENCE ON EMERGING DATA AND INDUSTRY 4.0 (EDI40 2019) / AFFILIATED WORKSHOPS, 2019, 151 : 709 - 716
  • [9] Similarity-based deep learning approach for remaining useful life prediction
    Hou, Mengru
    Pi, Dechang
    Li, Bingrong
    MEASUREMENT, 2020, 159
  • [10] A Framework of Multi-Index Modeling for Similarity-Based Remaining Useful Life Estimation
    Gu, Mengyao
    Chen, Youling
    2016 3RD INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CONTROL ENGINEERING (ICISCE), 2016, : 31 - 37
123