Prediction of Viscoelastic Droplet Impact Dynamics Using a Vision Transformer-Based Approach
arXiv:2606.23940v1 Announce Type: cross Abstract: Droplet impact on solid surfaces is a complex fluid dynamics problem with applications in spray cooling, inkjet printing, and pharmaceutical processing. Although numerical simulations are widely used to investigate these dynamics, their computational cost becomes significant when multiple parametric variations are considered. In this work, we investigate the use of a Video Vision Transformer (ViViT) architecture to predict the temporal evolution of viscoelastic droplets impacting solid surfaces using volume fraction fields obtained from the Vol
The increasing availability of advanced AI models like Vision Transformers and the growing need for more efficient computational fluid dynamics simulations are converging to enable new methods for complex physics problems.
This development indicates that AI is becoming a powerful tool for accelerating scientific discovery and engineering, particularly in computationally intensive fields where traditional simulations are bottlenecks.
The ability to predict complex fluid dynamics, such as viscoelastic droplet impacts, with significantly reduced computational cost will accelerate R&D in diverse applications like manufacturing and pharmaceuticals.
- · AI/ML researchers
- · Computational fluid dynamics engineers
- · Manufacturing sector
- · Pharmaceutical industry
- · Traditional numerical simulation firms (unless they adapt AI)
Faster and cheaper R&D cycles for technologies involving fluid dynamics.
New materials and processes become viable due to rapid simulation and optimization capabilities.
Enhanced product performance and novel applications across industries previously constrained by simulation costs.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG