AI surrogate modeling for industrial CAE

Artificial intelligence (AI) and machine learning (ML) are rapidly reshaping engineering workflows by accelerating simulation-driven design. In computer-aided engineering (CAE), surrogate models can predict simulation outcomes in seconds rather than hours/days, enabling faster design exploration, optimization and decision-making.

This paper provides an AI and ML methodologies overview relevant to Simcenter™ PhysicsAI™ software and the geometric deep learning capabilities introduced in Simcenter STAR-CCM+™ software version 2602.

Learn the core ML concepts underpinning modern AI approaches, examine AI surrogate modeling scopes and challenges in CAE and review the principal surrogate modeling methodologies used today. This culminates in a comparative perspective on the current methodological landscape and outlines the Simcenter PhysicsAI approach to industrial-scale AI surrogate modeling.

Download the white paper today.