Deep-learning architectures were developed for the self-piercing riveting (SPR) process to predict the cross-sectional shape from the scalar input of the punch force. Traditionally, the SPR process is studied using a physic-based approach, including finite element modeling, but in this study, a data-driven approach consisting of two supervised deep-learning models was proposed. The first model was used for data transformation from an optical microscopic image to a material segmentation map, which characterizes the shape and location of the two sheets and the rivet by applying a convolutional neural network (CNN)based deep-learning structure. To validate the developed models, two types of sheet combinations were tested, namely, carbon-fiber-reinforced plastic (CFRP) and galvanized dual-phase steel (GA590DP) sheets, and steel alloy (SPFC590DP) and aluminum alloy (Al5052-H32) sheets. The transformation was performed with a mean intersection-over-union of 98.50% and a mean pixel accuracy of 99.78%. The next model, which was a novel generative model based on a CNN and conditional generative adversarial network with residual blocks, was then trained to predict the cross-sectional shape from the input punch force. The predicted cross-sectional shapes were compared with the experimental results of SPR. The overall accuracy was 94.20% for CFRP-GA590DP and 96.31% for SPFC590DP-Al5052, with respect to three key geometrical indexes, namely, rivet head height, interlock length, and bottom thickness.

A deep learning model was applied for predicting a cross-sectional bead image from laser welding process parameters. The proposed model consists of two successive generators. The first generator produces a weld bead segmentation map from laser intensity and interaction time, which is subsequently translated into an optical microscopic (OM) image by the second generator. Both generators exhibit an encoder-decoder structure based on a convolutional neural network (CNN). In the second generator, a conditional generative adversarial network (cGAN) was additionally employed with multiscale discriminators and residual blocks, considering the size of the OM image. For a training dataset, laser welding experiments with AISI 1020 steel were conducted on a large process window using a 2 KW fiber laser, and a total of 39 process conditions were used for the training. High-resolution OM images were successfully generated, and the predicted bead shapes were reasonably accurate (R-Squared: 89.0% for penetration depth, 93.6% for weld bead area). INDEX TERMS Laser welding, weld-bead prediction, deep learning, image-to-image translation.