Study on identifying GMAW process deviations by means of optical and electrical process data using ANN

In this study, different process deviations of gas metal arc welding were classified using transient optical and electrical process data by means of artificial neural networks. The examined process deviations varied from massive process disturbances due to insufficient shielding gas coverage to a slight shift of the process operating point due to a mispositioned welding torch. It was found that good classification results can be achieved even with simple, statistical process features. In addition, the classification results derived from the photodiodes used, achieved better results compared to welding current and voltage alone. However, the best results were reached when optical and electrical process data were used together.

[1]  Paul Kah,et al.  Penetration and Quality Control With Artificial Neural Network Welding System , 2017 .

[2]  Chao Lan,et al.  Anomaly Detection , 2018, Encyclopedia of GIS.

[3]  J. K. Kristensen,et al.  Gas metal arc welding of butt joint with varying gap width based on neural networks , 2005 .

[4]  Paul Kah,et al.  Artificial Neural Network Controlled GMAW System: Penetration and Quality Assurance in a Multi-Pass Butt Weld Application , 2019, The International Journal of Advanced Manufacturing Technology.

[5]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[6]  Klaus Wehrle,et al.  Connected, Digitalized Welding Production—Secure, Ubiquitous Utilization of Data Across Process Layers , 2020, Advanced Structured Materials.

[7]  T.Y. Lin,et al.  Anomaly detection , 1994, Proceedings New Security Paradigms Workshop.

[8]  D. Rehfeldt,et al.  Gas metal arc welding process monitoring and quality evaluation using neural networks , 2000 .

[9]  S. Linnainmaa.  Taylor expansion of the accumulated rounding error , 1976 .

[10]  X. Li,et al.  Neural networks for online prediction of quality in gas metal arc welding , 2000 .

[11]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[12]  U. Reisgen,et al.  Connected, digitalized welding production—Industrie 4.0 in gas metal arc welding , 2019, Welding in the World.

[13]  A. A. Mazur,et al.  The main tendencies of development of automation and robotization in welding engineering (Review) , 2017 .