Siemens Digital Industries Software and PhysicsX, a startup leveraging generative AI, are collaborating to create the next generation of AI-based deep physics simulation to accelerate performance prediction and optimization. PhysicsX is building its latest pre-trained deep physics model for aerodynamics on high-fidelity simulation data generated with the Siemens Xcelerator portfolio. The collaboration aims to enable breakthrough engineering in advanced industries.
PhysicsX released its Large Geometry Model (LGM) for aerodynamics, LGM-Aero, which is trained on high-fidelity data generated with Siemens Xcelerator portfolio tools. This allows users to fine-tune deep learning models for their own applications with minimal simulation data. PhysicsX also released Ai.rplane, a free-to-use reference application that showcases the power of LGM-Aero in aerodynamics and aircraft structures.
The goal is to create a zero-shot model that generalizes to a broad set of aeroelastic applications. Users can explore the generative design space and optimize performance characteristics in seconds, a significant improvement over traditional numerical simulations. Siemens’ Xcelerator portfolio enables automation of high-quality training data generation, and LGM-Aero and Ai.rplane are available on the PhysicsX AI engineering platform.