Generative Adversarial Networks for spot weld design

Joining element and assembly design remain largely a manual process. This increases risks of more costly and longer development trajectories. Current automation solutions do not consider historical data and traditional machine learning approaches have limitations. Meanwhile, generative adversary networks became benchmark methodologies to perform generation tasks in computer vision. Products in manufacturing industry may contain thousands of spot welds, thus design automation enables engineers to focus on their core competencies. This work presents a methodology to predict spot weld locations using generative adversarial networks. A 2D-based approach implements a variant of StarGAN_v2 to predict locations. It uses domain-based prediction concepts that integrate clustering of geometrical and product manufacturing information, as well as reference guided style generation. Results indicate that generative adversarial networks can predict spot weld positions based on 2D image data.