The application of non-destructive evaluation approaches has attracted strong interests in modern automotive industries. This study presents an autonomous deep-computing framework to analyze raw videos from infrared systems and to predict weld nugget shape and size with unprecedented accuracy and speed. In a comprehensive training and testing experiment with 90 videos (seven sets of welding material stack-ups), a new method was developed to assemble sufficient datasets for neural network training. Our framework successfully predicts all the nugget shapes with F1 scores that range from 0.84 to 0.92. The total training time on Nvidia DGX station takes less than 10 min for each set of welding material stack-up. The real inference time of an individual dataset (with 30 video frames) takes about 0.005 s. The procedure and methods developed in the study can be applied to other image-based weld property prediction, as well as other manufacturing processes. Furthermore, our well-trained neural networks take limited memory resources (2.3 MB) and are suitable for embedded microprocessors for in-situ welding quality control as edge computing within an intelligent welding framework.

无损评估方法的应用引起了现代汽车行业的强烈兴趣。这项研究提出了一种自主的深度计算框架，可以分析来自红外系统的原始视频，并以前所未有的准确性和速度预测焊点熔核的形状和大小。在一个包含90个视频（七组焊接材料堆叠）的综合培训和测试实验中，开发了一种新方法来组装足够的数据集以进行神经网络培训。我们的框架成功地预测了F1分数介于0.84至0.92之间的所有核块形状。对于每组焊接材料，在Nvidia DGX工作站上的总培训时间少于10分钟。单个数据集（带有30个视频帧）的实际推理时间约为0.005 s。研究中开发的程序和方法可以应用于其他基于图像的焊接性能预测以及其他制造过程。此外，我们训练有素的神经网络占用的内存资源有限（2.3 MB），适用于嵌入式微处理器，用于在智能焊接框架中进行边缘计算的原位焊接质量控制。