Journal of shanghai Jiaotong University (Science) ›› 2014, Vol. 19 ›› Issue (1): 11-16.doi: 10.1007/s12204-014-1471-0

Previous Articles     Next Articles

Feature Extraction and Modeling of Welding Quality Monitoring in Pulsed Gas Touch Argon Welding Based on Arc Voltage Signal

Feature Extraction and Modeling of Welding Quality Monitoring in Pulsed Gas Touch Argon Welding Based on Arc Voltage Signal

ZHANG Zhi-fen* (张志芬), ZHONG Ji-yong (钟继勇), CHEN Yu-xi (陈玉喜), CHEN Shan-ben (陈善本)   

  1. (Institute of Welding Engineering, School of Material Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
  2. (Institute of Welding Engineering, School of Material Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
  • Online:2014-01-15 Published:2014-01-15
  • Contact: ZHANG Zhi-fen(张志芬) E-mail:zzf919@sjtu.edu.cn

Abstract: Arc sensing plays a significant role in the control and monitoring of welding quality for aluminum alloy pulsed gas touch argon welding (GTAW). A method for online quality monitoring based on adaptive boosting algorithm is proposed through the analysis of acquired arc voltage signal. Two feature extraction algorithms were developed in time domain and frequency domain respectively to extract six statistic characteristic parameters before removing the pulse interference using the wavelet packet transform (WPT), based on which the Adaboost classification model is successfully established to evaluate and classify the welding quality into two classes and the classified accuracy of the model is as high as 98.81%. The Adaboost algorithm has been verified to be feasible in the online evaluation of welding quality.

Key words: gas touch argon welding (GTAW)| arc voltage signal| feature extraction| Adaboost algorithm

摘要: Arc sensing plays a significant role in the control and monitoring of welding quality for aluminum alloy pulsed gas touch argon welding (GTAW). A method for online quality monitoring based on adaptive boosting algorithm is proposed through the analysis of acquired arc voltage signal. Two feature extraction algorithms were developed in time domain and frequency domain respectively to extract six statistic characteristic parameters before removing the pulse interference using the wavelet packet transform (WPT), based on which the Adaboost classification model is successfully established to evaluate and classify the welding quality into two classes and the classified accuracy of the model is as high as 98.81%. The Adaboost algorithm has been verified to be feasible in the online evaluation of welding quality.

关键词: gas touch argon welding (GTAW)| arc voltage signal| feature extraction| Adaboost algorithm

CLC Number: