A semi-supervised learning method combining tool wear laws for machining tool wear states monitoring

被引:0
|
作者
Niu, Mengmeng [1 ]
Liu, Kuo [1 ,2 ]
Wang, Yongqing [1 ,2 ]
机构
[1] Dalian Univ Technol, State Key Lab High Performance Precis Mfg, Dalian 116024, Peoples R China
[2] Intelligent Mfg Longcheng Lab, Changzhou 213164, Peoples R China
基金
中国国家自然科学基金;
关键词
Tool wear monitoring; Semi-supervised learning; Tool wear laws; Pseudo label; FAULT; PREDICTION;
D O I
10.1016/j.ymssp.2024.112032
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
In tool wear states monitoring, obtaining tool wear labels is an expensive and difficult task, and deep learning models trained under limited labelled samples are prone to overfitting. Moreover, tool wear is a continuous, slow and irreversible process, and this physical law should be taken into account. In response to this issue, this article proposes a semi-supervised learning method combining tool wear laws (SSLTWL) for machining tool wear states monitoring. Specifically, under limited data, establish a deep learning model based on metric learning to learn compact feature representations of labeled samples. The pseudo-label sample selection mechanism is designed based on the confidence level and tool wear law to ensure the diversity and accuracy of pseudo-label samples. In order to effectively update the classifier, the improved generative adversarial networks is used to generate minority samples to adaptively maintain data class balance during the semi-supervised learning process. Adopting an iterative self-training strategy to train the model multiple times. Milling experiments and boring engineering experiments were carried out to verify the effectiveness of the proposed method. Compared with other methods, the proposed method can accurately identify the tool wear state and achieve the optimal performance.
引用
收藏
页数:19
相关论文
共 50 条
  • [41] Prediction of Tool Wear Progress in Machining of Carbon Steel using different Tool Wear Mechanisms
    Umbrello, D.
    Filice, L.
    Micari, F.
    Matsumura, T.
    Shirakashi, T.
    INTERNATIONAL JOURNAL OF MATERIAL FORMING, 2008, 1 (Suppl 1) : 571 - 574
  • [42] On-line tool wear monitoring during ultrasonic machining using tool resonance frequency
    Hocheng, H
    Kuo, KL
    JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2002, 123 (01) : 80 - 84
  • [43] On-line Monitoring of Tool Wear Conditions in Machining Processes Based on Machine Tool Data
    Lu Z.
    Ma P.
    Xiao J.
    Wang M.
    Tang X.
    Zhongguo Jixie Gongcheng/China Mechanical Engineering, 2019, 30 (02): : 220 - 225
  • [44] Tool Wear Condition Monitoring Method Based on Deep Learning with Force Signals
    Zhang, Yaping
    Qi, Xiaozhi
    Wang, Tao
    He, Yuanhang
    SENSORS, 2023, 23 (10)
  • [45] An artificial neural network method for tool wear monitoring
    Jiang, LG
    Sun, H
    Jiang, L
    ICEMI'99: FOURTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOLS 1 AND 2, CONFERENCE PROCEEDINGS, 1999, : 1004 - 1008
  • [46] Application of machine vision method in tool wear monitoring
    Peng, Ruitao
    Liu, Jiachen
    Fu, Xiuli
    Liu, Cuiya
    Zhao, Linfeng
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2021, 116 (3-4): : 1357 - 1372
  • [47] Application of machine vision method in tool wear monitoring
    Ruitao Peng
    Jiachen Liu
    Xiuli Fu
    Cuiya Liu
    Linfeng Zhao
    The International Journal of Advanced Manufacturing Technology, 2021, 116 : 1357 - 1372
  • [48] Advances in Research on Tool Wear Online Monitoring Method
    Wu X.
    Li G.
    Shao Z.
    Liu W.
    Ma G.
    Recent Patents on Engineering, 2024, 18 (06) : 124 - 139
  • [49] A novel method for online monitoring of surface quality and predicting tool wear conditions in machining of materials
    Panda, Anton
    Nahornyi, Volodymyr
    Valicek, Jan
    Harnicarova, Marta
    Kusnerova, Milena
    Baron, Petr
    Pandova, Iveta
    Sorocin, Patrik
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2022, 123 (9-10): : 3599 - 3612
  • [50] A novel method for online monitoring of surface quality and predicting tool wear conditions in machining of materials
    Anton Panda
    Volodymyr Nahornyi
    Jan Valíček
    Marta Harničárová
    Milena Kušnerová
    Petr Baron
    Iveta Pandová
    Patrik Soročin
    The International Journal of Advanced Manufacturing Technology, 2022, 123 : 3599 - 3612