高级检索

电压近似熵-SVM铝合金双丝PMIG焊过程稳定性评价

周晓晓, 王克鸿, 杨嘉佳, 黄勇, 周芷兰

周晓晓, 王克鸿, 杨嘉佳, 黄勇, 周芷兰. 电压近似熵-SVM铝合金双丝PMIG焊过程稳定性评价[J]. 焊接学报, 2017, 38(3): 107-111.
引用本文: 周晓晓, 王克鸿, 杨嘉佳, 黄勇, 周芷兰. 电压近似熵-SVM铝合金双丝PMIG焊过程稳定性评价[J]. 焊接学报, 2017, 38(3): 107-111.
ZHOU Xiaoxiao, WANG Kehong, YANG Jiajia, HUANG Yong, ZHOU Zhilan. Process stability evaluation on aluminum alloy twin-wire PMIG welding by approximate entropy based SVM of voltage signal[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2017, 38(3): 107-111.
Citation: ZHOU Xiaoxiao, WANG Kehong, YANG Jiajia, HUANG Yong, ZHOU Zhilan. Process stability evaluation on aluminum alloy twin-wire PMIG welding by approximate entropy based SVM of voltage signal[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2017, 38(3): 107-111.

电压近似熵-SVM铝合金双丝PMIG焊过程稳定性评价

基金项目: 总装先进制造重点资助项目(51318050117);国家国防科工局基础科研资助项目(A2620130005)

Process stability evaluation on aluminum alloy twin-wire PMIG welding by approximate entropy based SVM of voltage signal

  • 摘要: 提出了弧压信号近似熵-支持向量机(support vector machine,SVM)算法来评价铝合金双丝脉冲熔化极惰性气体保护(pulse metal insert gas,PMIG)焊焊接过程稳定性,并经试验验证该方法具有可行性和一定的可靠性.铝合金双丝PMIG焊电流、电压信号近似熵值越大对应焊接过程越不稳定,且相比于电流近似熵值,电压近似熵值能更加明确的表现焊接过程稳定性的差异,所以选取电压近似熵值进行SVM分类.结果表明,文中数据情况下,训练数据集在20%以上时分类准确率均在90%以上,且训练数据越充足分类结果越准确.
    Abstract: An approximate entropy (ApEn)-support vector machine (SVM) method of arc voltage was proposed to evaluate the stability of aluminum alloy twin-wire pulse metal insert gas (PMIG) welding process. A set of welding experiments were carried out and the ApEn of welding current and voltage signals was calculated. The results showed that the smaller the ApEn of current and voltage signals is the more stable, the welding process is. The application of ApEn on the welding current and the welding voltage was compared. It showed that the voltage based ApEn is sounder in measuring the stability of aluminum alloy twin-wire PMIG welding. Then a support vector machine (SVM) algorithm based on approximate entropy (ApEn) has been developed on voltage signals. And the results of the classification showed that the SVM algorithm based on ApEn can mark off the stable processes from the unstable ones. When the training data is more than 20%, the classification accuracy is more than 90%.
  • [1] Suban M, Tušek J. Methods for the determination of arc stability[J]. Journal of Materials Processing Technology, 2003, 143(1): 430-437.
    [2] 高 飞, 王克鸿, 梁永顺, 等. MAG焊熔池图像各区域定义及近似熵分析[J]. 焊接学报, 2012, 33(10): 29-32. Gao Fei, Wang Kehong, Liang Yongshun, et al. MAG welding pool image of regional definitions and approximate entropy analysis[J]. Transactions of the China Welding Institution, 2012, 33(10): 29-32.
    [3] 石 玗, 聂 晶, 黄健康, 等. 基于电弧电压概率密度铝合金脉冲MIG焊稳定性分析[J]. 焊接学报, 2010, 31(5): 13-16. Shi Yu,Nie Jing, Huang Jiankang, et al. Evaluation method of pulsed MIG welding of aluminum alloy based on probability density of arc voltage signal[J]. Transactions of the China Welding Institution, 2010, 31(5): 13-16.
    [4] 石 玗, 黄健康, 聂 晶, 等. 电弧声与铝合金脉冲MIG焊熔滴过渡的相关性[J]. 焊接学报, 2009, 30(3): 29-32. Shi Yu, Huang Jiankang, Nie Jing, et al. Correlation of arc acoustic signals and droplet transfer in aluminum pulsed MIG welding[J]. Transactions of the China Welding Institution, 2009, 30(3): 29-32.
    [5] Pincus S. Approximate entropy (ApEn) as a complexity measure[J]. Chaos, 1995, 5(1): 110-117.
    [6] Vapnik V N. The nature of statistical learning theory[M]. New York: Springer Verlag, 1995.
    [7] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1): 2-10. Ding Shifei, Qi Bingjuan, Tan Hongyan. An overview on theory and algorithm of university of supprot vector machines[J]. Journal of University of Electronic Science and Technology of China, 2011, 40(1): 2-10.
  • 期刊类型引用(2)

    1. 郑凯文,黄瑞生,滕彬,聂鑫,武鹏博. 钛合金激光填丝增材制造技术综述. 焊接. 2025(05): 62-72+88 . 百度学术
    2. 董逸君,王勇刚,李东亚,朱珊珊,许淑红,王瑶. 激光熔覆碳化物增强镍基涂层组织与性能的热处理调控. 焊接学报. 2024(10): 59-68 . 本站查看

    其他类型引用(0)

计量
  • 文章访问数:  272
  • HTML全文浏览量:  32
  • PDF下载量:  120
  • 被引次数: 2
出版历程
  • 收稿日期:  2015-12-28

目录

    /

    返回文章
    返回