Professor Seunghwa Ryu's research team develops an optimized adhesive pillar shape and design framework using deep learning.
(Left) Ph. D candidate Yongtae KIM. (Right)Professor. Seunghwa RYU.
Figure 1. Graphical abstract of “Designing an Adhesive Pillar Shape with Deep Learning-Based Optimization”
Figure 2. Overall workflow chart for to find a free-form optimized adhesive pillar shape out of extensive design space with deep learning and genetic algorithm. The flow about data preprocessing is represented with solid arrow line, and the flow about optimization process are represented with dashed line.
Figure 3. Cross-sectional area and corresponding interfacial stress distribution of optimized adhesive pillar with (a) ideally sharp edges and (b) truncated edge shape considering realistic fabrication resolution.
Over the past decades, significant effort has been made to improve the adhesive properties of adhesive pillars, by searching for pillar shapes with optimized interfacial stress distribution. However, the shape optimizations in the previous studies are conducted by considering specific pillar forms with a few parameters, hence with limited design space. In this study, we present a framework to find a free-form optimized adhesive pillar shape out of extensive design space. We generate 200 000 different shapes of adhesive pillars based on the Bézier curve with a few control points by considering two distinct edge shapes, sharp and truncated edges, to account for the limitation in the realistic manufacturing resolution. The resulting interfacial stress distributions from numerical simulations are used to train deep neural networks for each edge type. Our deep learning model shows greater than 99% classification accuracy on a limited data set with orders of magnitude speedup in computation time compared to finite element analyses. On the basis of the trained neural network, we conduct genetic optimization by maximizing a fitness function that prefers the uniform interfacial stress distribution with neither stress peak nor singularity. The optimized adhesive pillar shape is composed of smoothly mixed convex and concave parts and shows improved uniformity in the interfacial stress distribution. This study is conducted by Ph.D candidate Yongtae Kim, Professor Seunghwa Ryu, and Grace X. Gu and Charles Yang in UC Berkley, and it is published in ACS applied material & Interfaces as paper called “Designing an Adhesive Pillar Shape with Deep Learning-Based Optimization”. Our study also demonstrates that the deep learning can be used for multi-objective nonparametric curve optimization task with diverse fitness function.
Kim, Y., Yang, C., Kim, Y., Gu, G. X., & Ryu, S. (2020). Designing adhesive pillar shape with deep learning-based optimization. ACS Applied Materials & Interfaces.