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

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.

I. Introduction

Arc welding inspection and quality control are crucial to the safety and structural soundness of a large number of metal products, since welding defects such as incomplete penetration, lack of fusion, and porosity left in the structure could become significant threats to the integrity of a welding structure. An experienced welder can use personal sensing ability (e.g., visual observation of the weld pool and sound from the arc) to determine whether a welding defect has occurred [1], but doing so is time-consuming and laborious. Although many welding robots and automation systems have been applied in manufacturing industries to improve productivity and reduce cost, the demand for automatic welding quality detection is still very high [2].