Welding penetration monitoring for pulsed GTAW using visual sensor based on AAM and random forests

被引:56
作者
Chen, Chao [1 ]
Lv, Na [2 ]
Chen, Shanben [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Mat Sci & Engn, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Dept Instrument Sci & Engn, Shanghai 200240, Peoples R China
基金
中国国家自然科学基金;
关键词
Pulsed GTAW; Penetration state monitoring; Pattern-based visual features extraction; Random forest;
D O I
10.1016/j.jmapro.2020.04.005
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
On-line welding penetration state monitoring based on passive visual sensing technology in pulsed gas tungsten arc welding (GTAW) has been a hot research topic in industry and academia. Passive vision sensing technology has some disadvantages. It is easy to be affected by some common disturbance during pulsed GTAW, like spattering, the change of arc intensity, the slightly change of focal length and viewing angle of visual sensor, etc. This paper proposed an intelligent penetration monitoring methodology for GTAW by combining pattern-based visual feature extraction method and supervised machine learning method. The proposed methodology mainly includes two parts: (a) visual features extraction for weld pool images based on active appearance model (AAM); (b) the implementation of penetration monitoring based on supervised machine learning method, random forests (RF). The extracted weld pool visual features include width, length and area size of weld pool. Then the extracted features are utilized to train RF model. Further, the trained RF model can implement the evaluation of penetration states and backside weld seam width. The experiments verify that the proposed method is effective with high accuracy and robustness, which also lays the foundation for online welding penetration control.
引用
收藏
页码:152 / 162
页数:11
相关论文
共 26 条
[1]   Closed-Loop Control of Robotic Arc Welding System with Full-penetration Monitoring [J].
Chen, Huabin ;
Lv, Fenglin ;
Lin, Tao ;
Chen, Shanben .
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2009, 56 (05) :565-578
[2]   Online monitoring and evaluation of the weld quality of resistance spot welded titanium alloy [J].
Chen, S. ;
Sun, T. ;
Jiang, A. ;
Qi, J. ;
Zeng, R. .
JOURNAL OF MANUFACTURING PROCESSES, 2016, 23 :183-191
[3]  
Chen SB, 2011, Robot. Weld. Intell. Autom., V88, P3, DOI [10.1007/978-3-642-19959-2_1, DOI 10.1007/978-3-642-19959-2_1]
[4]   Welding penetration prediction with passive vision system [J].
Chen, Zongyao ;
Chen, Jian ;
Feng, Zhili .
JOURNAL OF MANUFACTURING PROCESSES, 2018, 36 :224-230
[5]   Active appearance models [J].
Cootes, TF ;
Edwards, GJ ;
Taylor, CJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (06) :681-685
[6]   Investigation of porosity in pulsed GTAW of aluminum alloys based on spectral and X-ray image analyses [J].
Huang, Yiming ;
Wu, Di ;
Lv, Na ;
Chen, Huabin ;
Chen, Shanben .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2017, 243 :365-373
[7]   EMD-based pulsed TIG welding process porosity defect detection and defect diagnosis using GA-SVM [J].
Huang, Yiming ;
Wu, Di ;
Zhang, Zhifen ;
Chen, Huabin ;
Chen, Shanben .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2017, 239 :92-102
[8]   Real-time image processing for monitoring of free weld pool surface [J].
Kovacevic, R ;
Zhang, YM .
JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME, 1997, 119 (02) :161-169
[9]  
Kovacevic R, 1996, WELD J, V75, pS317
[10]   Machine learning of weld joint penetration from weld pool surface using support vector regression [J].
Liang, Rong ;
Yu, Rui ;
Luo, Yu ;
Zhang, YuMing .
JOURNAL OF MANUFACTURING PROCESSES, 2019, 41 :23-28