Advanced Search
FENG Bao1,2, QIN Ke1,2, JIANG Zhiyong1. ELM with L1/L2 regularization constraints[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(9): 31-35. DOI: 10.12073/j.hjxb.2018390219
Citation: FENG Bao1,2, QIN Ke1,2, JIANG Zhiyong1. ELM with L1/L2 regularization constraints[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(9): 31-35. DOI: 10.12073/j.hjxb.2018390219
shu

ELM with L1/L2 regularization constraints

  • 1. Key laboratory of robot and welding, Guilin university of aerospace technology, Guilin 541004, China;
    2. Guangxi Key Laboratory for Nonlinear Circuit and Optical Communication, Guangxi normal university, Guilin 541004, China

More Information
  • Received Date: August 28, 2017
    Graphical Abstract
    • Abstract
  • An L1/L2 constrained ELM penetration identification model is proposed to solve the low accuracy problem for penetration state identification, caused by nonlinear factors during arc welding. Images of the molten pools are obtained by high speed visual sensing system. Then, feature extraction and dimensionality reduction are carried out by principal component analysis. ELM algorithm is used to train the penetration identification model for identification. To obtain generalization ability, L1 norm constraint is imposed on ELM optimization process to constraint suppresses outliers in ELM output weights. L2 norm constraint is introduced to obtain cluster features and smooth ELM output weights to improve the identification accuracy of the weld penetration. The results show that the weld penetration state recognition model based on L1/L2-ELM can quickly and effectively distinguish the three states of full penetration, partial-penetration and over-penetration.
    • FullText(HTML)
    • References (12)
  • 杨嘉佳, 王克鸿, 吴统立, 等. 基于熔池视觉特征的铝合金双丝焊熔透识别[J]. 焊接学报, 2017, 38(3):49-52 Yang Jiajia, Wang Kehong, Wu Tongli et al. Welding penetration recognition in aluminum alloy tandem arc welding based on visual characters of weld pool[J]. Transactions of the China Welding Institution, 2017, 38(3):49-52
    丁度坤, 高向东, 赵传敏, 等. BP神经网络在焊缝位置识别中的应用[J]. 焊接技术, 2007, 36(3):15-17 Ding Dukun, Gao Xiangdong, Zhao Chuanmin, et al. Application of the BP neural network in seam position recognition[J]. Welding Technology, 2007, 36(3):15-17, doi: 10.3969/j.issn.1002-025X.2007.03.006
    陈华斌, 孔萌, 吕娜, 等. 视觉传感技术在机器人智能化焊接中的研究现状[J]. 电焊机, 2017, 47(3):1-16 Chen Huabin, Kong Meng, Lü Na, et al. Status and development of vision sensors on intelligentized robotic welding technologies[J]. Electric Welding Machine, 2017, 47(3):1-16
    林俊, 高向东. 电弧焊熔池表征与熔透状态映射研究[J]. 焊接, 2016(10):34-37 Lin Jun, Gao Xiangdong. Mapping relationship between weld pool surface feature and weld penetration during arc welding[J]. Welding & Joining, 2016(10):34-37, doi: 10.3969/j.issn.1001-1382.2016.10.008
    张艳喜. 大功率盘型激光焊熔池形态在线识别及焊缝成形预测模型[D].广州, 广东工业大学, 2014.
    武传松, Polte T, Rehfeldt D. GMAW焊接过程监测Kohonen神经网络系统[J]. 机械工程学报, 2002, 38(1):131-134 Wu Chuansong, Polte T, Rehfeldt D. Kohonen network system for process monitoring in gas metal arc welding[J]. Chinese Journal of Mechanical Engineering, 2002, 38(1):131-134, doi: 10.3321/j.issn:0577-6686.2002.01.032
    刘学艺, 李平, 郜传厚. 极限学习机的快速留一交叉验证算法[J]. 上海交通大学学报, 2011, 45(8):1140-1145 Liu Xueyi, LI Ping, Hao Chuanhou. Fast leave-one-out cross-validation algorithm for extreme learning machine[J]. Journal of Shanghai Jiaotong University, 2011, 45(8):1140-1145, doi: 10.3969/j.issn.1674-8115.2011.08.021
    袁玉龙. 基于极限学习机的选择性集成学习算法研究[D].镇江, 江苏科技大学, 2015.
    杨明轩, 从保强, 齐铂金, 等. 脉冲电流参数对奥氏体不锈钢电弧行为的影响[J]. 焊接学报, 2012, 33(10):67-70 Yang Mingxuan, Cong Baoqiang, Qi Bojin, et al. Influence of pulse current parameters on arc behavior by austenite stainless steel[J]. Transactions of the China Welding Institution, 2012, 33(10):67-70
    刘茂林. 一个大脑学习与记忆的现实性神经网络模型[J]. 重庆大学学报:自然科学版, 2002, 25(12):110-113 Liu Maolin. A realistic neural network on cerebral learning-memory[J]. Journal of Chongqing University (Natural Science Edition), 2002, 25(12):110-113
    田垅, 刘宗田. 最小二乘法分段直线拟合[J]. 计算机科学, 2012, 39(6A):482-484 Tian Long, Liu Zongtian. Least-squares method piecewise linear fitting[J]. Computer Science, 2012, 39(6A):482-484
    王凯, 侯著荣, 王聪丽. 基于交叉验证SVM的网络入侵检测[J]. 测试技术学报, 2010, 24(5):419-423 Wang Kai, Hou Zhurong, Wang Congli. Intrusion detection based on cross-validation SVM[J]. Journal of Test and Measurement Technology, 2010, 24(5):419-423, doi: 10.3969/j.issn.1671-7449.2010.05.011
    • Related Articles

  • Related Articles

    [1]JIANG Weiqi, HUANG Haihong, LIU Yun, LI Lei, LIU Zhifeng. Prediction for emission of environmental burden in GTAW based on combined neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(10): 77-85. DOI: 10.12073/j.hjxb.20211104002
    [2]LUO Liuxiang, XING Yanfeng. CMT spot welding deformation of sheet metal based on BP neural network and genetic algorithm[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2019, 40(4): 79-83. DOI: 10.12073/j.hjxb.2019400104
    [3]YANG Yachao, QUAN Huimin, DENG Linfeng, ZHAO Zhenxing. Prediction method of welding machine parameters based on neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(1): 32-36. DOI: 10.12073/j.hjxb.2018390008
    [4]CHEN Yuquan, GAO Xiangdong. Neural network compensation for micro-gap weld detection by magneto-optical imaging[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2016, 37(10): 33-36.
    [5]LIU Lipeng, WANG Wei, DONG Peixin, WEI Yanhong. Mechanical properties predication system for welded joints based on neural network optimized by genetic algorithm[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2011, (7): 105-108.
    [6]LIU Lijun, LAN Hu, ZHENG Hongyan. Feature evaluation and selection of penetration arc sound signal based on neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2010, (3): 25-28.
    [7]WEN Jianli, LIU Lijun, LAN Hu. Penetration state recognition of MIG welding based on genetic wavelet neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2009, (8): 41-44.
    [8]DI Xinjie, LI Wushen, BAI Shiwu, LIU Fangming. Metal magnetic memory signal recognition by neural network for welding crack[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2008, (3): 13-16.
    [9]DONG Zhibo, WEI Yanhong, Zhan Xiaohong, WEI Yongqiang. Optimization of mechanical properties prediction models of welded joints combined neural network with genetic algorithm[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2007, (12): 69-72.
    [10]LEI Yu cheng, LIU Wei, CHENG Xiao nong. BP Neural Network Predicting Model for Aluminium Alloy Keyhole Plasma Arc Welding in Vertical Position[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2002, (6): 41-43.

  • Cited by

    Periodical cited type(3)

    1. 刘秀航，叶广文，黄宇辉，张艳喜，冯桑，高向东. 激光-MIG复合焊根部驼峰缺陷预测. 机械制造文摘(焊接分册). 2023(03): 18-24 .
    2. 刘秀航，叶广文，黄宇辉，张艳喜，冯桑，高向东. 激光-MIG复合焊根部驼峰缺陷预测. 焊接学报. 2022(12): 47-52+99+115-116 . 本站查看
    3. 谢非，朱腾飞，杨继全，余圣甫，史建军，刘益剑. 基于边缘夹角附加损失函数的熔池形貌检测方法. 焊接学报. 2021(07): 82-90+103-104 . 本站查看

    Other cited types(2)

Catalog

    Get Citation
    XML
    Article views (647) PDF downloads (215) Cited by(5)
    Turn off MathJax
    Article Contents
    Abstract
    References
    Related Articles

    Website Copyright © Editorial Office of Transactions of the China Welding Institution, Welding Journals Publishing HouseTel：0451-86323218Address：No. 2077, Chuangxin Road, Songbei District, Harbin

    Supported by: Beijing Renhe Information Technology Co. Ltd    Baidu Analytics

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return