期刊文献+

用电弧声信号监测GMAW焊丝干伸长的SVM模型 被引量:4

SVM classifier for wire extension monitoring using arc sound signal in GMAW
下载PDF
导出
摘要 为了探索电弧声在焊接质量监控中的应用途径,在对短路过渡GMAW电弧声信号频谱分析的基础上提出电弧声道概念,认为声道是受焊接参数、电弧形态等众多因素影响的分布参数系统。电弧声的LPC(线性预测)模型是声道传输特性的一个参数化估计。电弧声频谱与焊丝干伸长密切相关,但呈现出高度复杂性和非线性。利用电弧声LPC预测系数和反射系数构造输入向量,建立了支持向量机(SVM)的焊丝干伸长分类模型。训练和测试结果表明,采用不同形式核函数的SVM(支持向量机)分类器均能实现干伸长的正确分类,其性能明显优于相同条件下的RBF(径向基函数)神经网络分类模型,小样本情况下仍具有较好的推广能力。其中,用反射系数作为输入向量训练三次多项式核函数的SVM分类器性能最优,测试正确率在98%以上。据此认为,利用LPC分析提取电弧声的特征向量,建立SVM模型是一种焊接动态参数监控的可行方法。 To find the approach of monitoring welding quality by arc sound, the frequency spectral characteristics of the arc sound signals in short circuit GMAW process were analyzed. The concept of tone channel of welding arc was introduced, which was considered a time dependent distributed parameters system influenced by welding parameters, arc behavior and the other factors. The LPC (linear prediction coding) model of the arc sound signal was an estimation of transmission properties of the tone channel. The spectrum analyses indicated that the frequency characteristics of the arc sound signal were closely related to the wire extension, but the correlation presented high complexity and nonlinearity. The classifiers based on SVM (support vector machine) for monitoring wire extensions were established, in which the input vectors of sample sets were built with the predictor coefficients and reflection coefficients of LPC model of the arc sound signals. The training and testing results showed that the SVM classifiers with different kernels are all capable of classifying the wire extension, whose performances were obviously better than that of the RBF (radial basis function) neural networks under the same condition, and present good capability of generalization at small sample set. The classifiers with 3rd order polynomial kernel trained with reflection coefficients input vectors has the best accuracy, i.e. over 98%. The study indicated that forming characteristic vectors by the LPC coefficients of arc sound to build SVM pattern recognition model is a feasible way for welding parameters monitoring.
出处 《焊接学报》 EI CAS CSCD 北大核心 2006年第5期21-26,共6页 Transactions of The China Welding Institution
基金 国家自然科学基金资助项目(50275028)
关键词 电弧声 线性预测模型 支持向量机 熔化极气体保护焊 焊接参数监控 Data acquisition Inference engines Monitoring Pattern recognition Quality control
  • 相关文献

参考文献9

  • 1Manz A.Welding arc sounds[J].Welding Journal,1981,60(5):23-27. 被引量:1
  • 2Saini D,Floyd S.An investigation of gas metal arc welding sound signature for on-line quality control[J].Welding Journal,1998,77(4):172-179. 被引量:1
  • 3Cudina M,Prezelj J.Evaluation of the sound signal based on the welding current in the gas-metal arc welding process[J].Proceeding of the Institution of Mechanical Engineers Part C,Journal of Mechanical Engineering Science,2003,217 (5):483-494. 被引量:1
  • 4Matteson A,Morris R,Tate R.Real time GMAW quality classification using an artificial neural network with airborne acoustic signals as inputs[J].Proceedings of the International Conference on Offshhore Mechanic and Arctic Engineeing,1993,3(PartA):273-287. 被引量:1
  • 5马跃洲,马春伟,张鹏贤,陈剑虹.基于电弧声波特征的CO_2焊接飞溅预测[J].焊接学报,2002,23(3):19-22. 被引量:13
  • 6Vapink V.The nature of statistical learning theory[ M].Beijing:Tsinghua University Press,2000. 被引量:1
  • 7Nello Cristianini,John Shawe-Taylor.An introduction to support vector machines and other kernel-based learning methods[M].Beijing:Publishing House of Electronics Industry,2004.82-128. 被引量:1
  • 8张雄伟 ... ..现代语音处理技术及应用[M],2003.
  • 9李建民,张钹,林福宗.支持向量机的训练算法[J].清华大学学报(自然科学版),2003,43(1):120-124. 被引量:46

二级参考文献29

  • 1VapnikV.统计学习理论的本质[M].北京:清华大学出版社,2000.. 被引量:27
  • 2Osuna E,Freund R,Girosi F. Support Vector Machines: Training and Application [R]. CBCL Paper #144 / AI Memo #1602,Cambridge,MA: Massachusetts Institute of Technology,AI Lab,1997. 被引量:1
  • 3Osuna E,Freund R,Girosi F. An improved training algorithm for support vector machines [A]. Principe J,Gile L,Morgan N,et al. Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing [C]. IEEE,1997. 276-285. 被引量:1
  • 4Joachims T. Making large-scale support vector machine learning practical [A]. Scholkopf B,Burges C,Smola A. Advances in Kernel Methods - Support Vector Learning [C]. Cambridge,MA: MIT Press,1999. 169-184. 被引量:1
  • 5LIN Chihjen. On the convergence of the decomposition method for support vector machines [J]. IEEE Transactions on Neural Networks,2001,12(6): 1288-1298. 被引量:1
  • 6Laskov P. An improved decomposition algorithm for regression support vector machines [A]. Solla S,Leen T,Muller K-R. Advances in Neural Information Processing Systems 12 [C]. Cambridge,MA: MIT Press,2000. 484-490. 被引量:1
  • 7Laskov P. Feasible direction decomposition algorithms for training support vector machines [J]. Machine Learning,2002,46(1/3): 315-349. 被引量:1
  • 8Pérez-Cruz F,Alarcón-Diana P,Navia-Vázquez A,et al. Fast training of support vector classifiers [A]. Leen T,Dietterich T,Tresp V. Advances in Neural Information Processing Systems 13 [C]. Cambridge,MA: MIT Press,2001. 734-740. 被引量:1
  • 9Platt J. Fast training of support vector machines using sequential minimal optimization [A]. Scholkopf B,Burges C,Smola A. Advances in Kernel Methods - Support Vector Learning [C]. Cambridge,MA: MIT Press,1999. 185-208. 被引量:1
  • 10Platt J. Using analytic QP and sparseness to speed training of support vector machines [A]. Kearns M,Solla S,Cohn D. Advances in Neural Information Processing Systems 11 [C]. Cambridge,MA: MIT Press,1999. 557-563. 被引量:1

共引文献57

同被引文献31

引证文献4

二级引证文献15

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部