arXiv:2606.16587v1 Announce Type: cross Abstract: Designing spray nozzles requires predicting how geometry shapes transient two-phase breakup, but high-fidelity volume-of-fluid (VOF) simulations with adaptive mesh refinement (AMR) are too expensive for iterative design exploration. Standard surrogate models are also challenged by this setting because both the liquid--gas interface and the underlying adaptive discretization evolve across time and geometries. We introduce a geometry-conditioned latent surrogate trained on 797 two-phase nozzle simulations that addresses this by encoding the AMR c
The increasing complexity of engineering simulations and the growing capabilities of AI for surrogate modeling converge to enable more efficient design processes.
This development allows for faster and more cost-effective design and optimization of critical components like spray nozzles, impacting various industries that rely on fluid dynamics.
Traditional iterative design processes constrained by expensive high-fidelity simulations can now be significantly accelerated through AI-driven latent surrogates.
- · Aerospace Industry
- · Automotive Industry
- · Chemical Engineering
- · AI/ML Research in Engineering
- · Traditional CFD Software Vendors (without AI integration)
- · Manual Iterative Design Teams
Reduced development cycles and manufacturing costs for fluid-dynamic systems become possible.
Novel designs previously unattainable due to simulation complexity can be explored and realized.
This methodology could be generalized to other complex multi-physics simulations, further accelerating innovation across engineering disciplines.
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.AI