期刊
出版社
ASME
DOI: 10.1115/1.4051829
关键词
convolutional neural network; image segmentation; resistance spot welding; nondestructive evaluation; thermal video; nugget size; inspection and quality control; sensing; monitoring and diagnostics; welding and joining
资金
- US Department of Energy
- Office of Nuclear Energy (Advanced Methods for Manufacturing Program)
- AI Initiative at Oak Ridge National Laboratory
Resistance spot welding is a widely used joining technique in the automotive industry, and thermal videos collected using an infrared camera can be analyzed to enable nondestructive evaluation of weld nuggets. However, the unique data-level challenges in these thermal videos compromise the effectiveness of most pre-trained deep learning models. In this study, we propose a novel image segmentation method to improve the prediction performance of deep learning models in resistance spot welding.
Resistance spot welding (RSW) is a widely adopted joining technique in automotive industry. Recent advancement in sensing technology makes it possible to collect thermal videos of the weld nugget during RSW using an infrared (IR) camera. The effective and timely analysis of such thermal videos has the potential of enabling in situ nondestructive evaluation (NDE) of the weld nugget by predicting nugget thickness and diameter. Deep learning (DL) has demonstrated to be effective in analyzing imaging data in many applications. However, the thermal videos in RSW present unique data-level challenges that compromise the effectiveness of most pre-trained DL models. We propose a novel image segmentation method for handling the RSW thermal videos to improve the prediction performance of DL models in RSW. The proposed method transforms raw thermal videos into spatial-temporal instances in four steps: video-wise normalization, removal of uninformative images, watershed segmentation, and spatial-temporal instance construction. The extracted spatial-temporal instances serve as the input data for training a DL-based NDE model. The proposed method is able to extract high-quality data with spatial-temporal correlations in the thermal videos, while being robust to the impact of unknown surface emissivity. Our case studies demonstrate that the proposed method achieves better prediction of nugget thickness and diameter than predicting without the transformation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据