Deep-Learning Approach to the Self-Piercing Riveting of Various Combinations of Steel and Aluminum Sheets

Abstract

Deep-learning architectures were employed to simulate the self-piercing riveting process of steel and aluminum sheets and predict the cross-sectional joint shape with a zero head height. Four steels (SPRC440, SPFC590DP, GI780DP, SGAF980Y) and three aluminum alloys (Al5052, Al5754, Al5083) were considered as the materials for the top and bottom sheets, respectively. The key objective was to consider the material properties of these metal sheets (Young's modulus, Poisson's ratio, and ultimate tensile strength) in a deep-learning framework. Two deep-learning models were considered: In the first model, the properties of the top and bottom sheets were adopted as the scalar inputs, and in the second model, the three properties were graphically assigned to the three channels of the input image. Both the models generated a segmentation image of the cross-section. To assess the accuracy of the predictions, the generated images were compared with ground truth images, and three key geometrical factors (interlock, bottom thickness, and effective length) were measured. The first and second models achieved prediction accuracies of 91.95% and 92.22%, respectively.INDEX TERMS self-piercing riveting; cross-sectional shape prediction; deep learning; segmentation map prediction; material properties This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

Triple joining of different sheets with self-pierce riveting method

“…The spread ratio and interlocking ratio of the specimen are calculated according to Equations ( 1) and ( 2). The spread ratio and interlocking ratio are important criteria for SPR process quality [16]. Where A is the spread ratio, where d max (mm) is the maximum flare measured across the rivet tails and d min (mm) is the minimum flare measured across the rivet shank, E is the interlocking ratio [23].…”

“…The highest interlock ratio and inlet length were achieved by using a 6 mm rivet length at a sheet thickness ratio of 1.2 mm/1.8 mm [15]. Kim et al estimated the mechanical properties of different steel and aluminium sheet combinations joined with self-piercing riveting using a deep learning approach [16]. Deng et al used different die geometries for the self-piercing riveting process of AA6061-T6 and SPFC340 sheet materials.…”

Application of reinforcement learning for the optimization of clinch joint characteristics

“…In comparison to the data-driven analysis of clinch joint, few contributions investigated the application of machine learning algorithm, especially artificial neural networks, for the prediction of joint characteristics in the field of selfpiercing riveting. For example, Oh and Kim et al [16,17] introduced a data-driven approach to estimate the crosssectional shape of the punch forces' scalar input using supervised deep-learning algorithms (convolutional neural network and generative adversarial network). Therefore, the models enabled the generation of segmentation images of the particular cross-sections showing a high prediction accuracy of 92.22% and 91.95%.…”

Mechanical performance and failure modes of self-piercing riveted joints between AA6061 and solution-treated TC4 alloy

“…Lin et al [20] used finite element simulation to study the cross tensile strength of SPR joints, and verify the simulation results with experimental results. Kim et al [21] calculated the formation of the SPR joint with the help of the machine learning method. Karathanasopoulos et al [22] predicted SPR joint formation through neural network modeling.…”