• DOI:10.1109/TII.2019.2937563
• Corpus ID: 202783302

DeepWelding: A Deep Learning Enhanced Approach to GTAW Using Multisource Sensing Images

@article{Feng2020DeepWeldingAD,
  title={DeepWelding: A Deep Learning Enhanced Approach to GTAW Using Multisource Sensing Images},
  author={Yunhe Feng and Zongyao Chen and Dali Wang and Jian Chen and Zhili Feng},
  journal={IEEE Transactions on Industrial Informatics},
  year={2020},
  volume={16},
  pages={465-474}
}

• Yunhe Feng, Zongyao Chen, +2 authors Zhili Feng
• Published 1 January 2020
• Computer Science
• IEEE Transactions on Industrial Informatics

Deep learning has great potential to reshape manufacturing industries. In this article, we present DeepWelding, a novel framework that applies deep learning techniques to improve gas tungsten arc welding process monitoring and penetration detection using multisource sensing images. The framework is capable of analyzing multiple types of optical sensing images synchronously and consists of three deep learning enhanced consecutive phases: image preprocessing, image selection, and weld penetration classification. Specifically, we adopted generative adversarial networks (pix2pix) for image denoising and classic convolutional neural networks (AlexNet) for image selection. Both pix2pix and AlexNet delivered satisfactory performance. However, five individual neural networks with heterogeneous architectures demonstrated inconsistent generalization capabilities in the classification phase when holding out multisource images generated with specific experimental settings. Therefore, two ensemble methods combining multiple neural networks are designed to improve the model performance on unseen data collected from different experimental settings. We have also found that the quality of model prediction is heavily influenced by the data stream collection environment. We think these findings are beneficial for the broad intelligent welding community.