Real-time monitoring of high-power disk laser welding based on support vector machine

被引：40
|
作者：
Chen, Juequan [1 ]
Wang, Teng [1 ]
Gao, Xiangdong [2 ]
Li, Wei [3 ]
机构：
[1] South China Normal Univ, Sch Comp, Guangzhou 510631, Guangdong, Peoples R China
[2] Guangdong Univ Technol, Sch Electromech Engn, Guangzhou 510090, Guangdong, Peoples R China
[3] South China Normal Univ, Sch Phys & Telecommun Engn, Guangzhou 510631, Guangdong, Peoples R China
来源：
COMPUTERS IN INDUSTRY | 2018年 / 94卷
基金：
中国国家自然科学基金;
关键词：
Laser welding; Support vector machine; Real-time monitoring; Feature selection; Welding quality; SYSTEM; CLASSIFICATION;
D O I：
10.1016/j.compind.2017.10.003
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this paper, an efficient quality monitoring system for monitoring high-power disk laser welding in real time was developed. Fifteen features of laser-induced metal vapor plume and spatters were extracted and support vector machine was adopted to establish a classifier to evaluate the welding quality. Feature selection method was employed to choose suitable features. The experiment results demonstrated that this method had satisfactory performance and could be applied to real-time monitoring application. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：75 / 81
页数：7
相关论文
共 50 条
  • [31] Real-time monitoring of GPS flex power based on machine learning
    Xin Yang
    Wenxiang Liu
    Jinquan Huang
    Wei Xiao
    Feixue Wang
    GPS Solutions, 2022, 26
  • [32] Direct, Real-time, High-resolution Beam profiler for High-power Laser
    Tsunekane, M.
    Sato, K.
    Takahashi, T.
    Yoshino, S.
    Yoshimori, N.
    Ohno, J.
    HIGH-POWER LASER MATERIALS PROCESSING: APPLICATIONS, DIAGNOSTICS, AND SYSTEMS IX, 2020, 11273
  • [33] Analysis of high-power disk laser welding stability based on classification of plume and spatter characteristics
    Gao, Xiang-dong
    Wen, Qian
    Katayama, Seiji
    TRANSACTIONS OF NONFERROUS METALS SOCIETY OF CHINA, 2013, 23 (12) : 3748 - 3757
  • [34] A REAL-TIME VISUAL-DISPLAY OF A HIGH-POWER LASER-BEAM
    BOYD, IW
    CROWDER, JG
    JOURNAL OF PHYSICS E-SCIENTIFIC INSTRUMENTS, 1982, 15 (04): : 421 - 422
  • [35] REAL-TIME DETECTION OF OPTICAL DAMAGE INDUCED BY HIGH-POWER LASER PULSES
    Zorila, Alexandru
    Simion, Sandel
    Rusen, Laurentiu
    Stratan, Aurel
    Schiopu, Paul
    UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN-SERIES A-APPLIED MATHEMATICS AND PHYSICS, 2013, 75 (04): : 241 - 250
  • [36] A REAL-TIME METHOD FOR MONITORING THE 3-DIMENSIONAL EXTENT OF HIGH-POWER CW LASER-BEAMS
    BOYD, IW
    OPTICS AND LASER TECHNOLOGY, 1983, 15 (03): : 150 - 152
  • [37] Electromyography signal analysis with real-time support vector machine
    Murshid, Mohammad Manzur
    Salehi, Hassan S.
    SIGNAL PROCESSING, SENSOR/INFORMATION FUSION, AND TARGET RECOGNITION XXIX, 2020, 11423
  • [38] Real-time flood forecast using a Support Vector Machine
    Li, Xiaoli
    Lu, Haishen
    An, Tianqing
    Jia, Yangwen
    Liu, Di
    HYDROLOGICAL CYCLE AND WATER RESOURCES SUSTAINABILITY IN CHANGING ENVIRONMENTS, 2011, 350 : 584 - +
  • [39] Optical techniques for real-time penetration monitoring for laser welding
    Bardin, F
    Cobo, A
    Lopez-Higuera, JM
    Collin, O
    Aubry, P
    Dubois, T
    Högström, M
    Nylen, P
    Jonsson, P
    Jones, JDC
    Hand, DP
    APPLIED OPTICS, 2005, 44 (19) : 3869 - 3876
  • [40] A Real-Time Spectroscopic Sensor for Monitoring Laser Welding Processes
    Sibillano, Teresa
    Ancona, Antonio
    Berardi, Vincenzo
    Lugara, Pietro Mario
    SENSORS, 2009, 9 (05): : 3376 - 3385
12345