Siemens has announced the expansion of the Simcenter advanced engineering simulation and test solutions portfolio with Simcenter™ PhysicsAI™ software, which empowers engineers to almost instantly evaluate bold design concepts and variations.
Simcenter PhysicsAI brings proven geometric deep learning technology in Siemens’ Simcenter™ STAR-CCM+™ software to accelerate AI-powered design exploration. The new capabilities enable engineers to create highly efficient AI reduced-order models (ROMs) from computational fluid dynamics (CFD) simulation data and to conduct what-if exploration in a fraction of the time (in the order of 1,000x faster) and with fewer computational resources than traditional workflows.
“Engineering simulation isn’t limited by physics - it’s limited by how quickly we can explore possibilities. Our strategy is to help customers learn from past work, accelerate exploration, and use AI as a prescriptive engine for innovation. We’re not replacing deterministic truth - we’re making it scalable and immediate,” said Sam Mahalingam, executive vice president, Simulation, HPC and AI, Siemens Digital Industries Software. “We’re harnessing AI to help engineers rapidly explore and pinpoint the best solutions to their problems. Simcenter PhysicAI allows customers to target challenges with unprecedented speed and intelligence, frees teams from repetitive tasks and fragmented data and empowers engineers to focus on what matters most: driving creativity and accelerating innovation.”
Simcenter PhysicsAI allows engineers to train and validate AI surrogate models using simulation results, run near instant predictions on new geometries within their simulation integrated environment and retain easy access to high-fidelity CFD simulation as the validation reference. This approach enables engineering teams to dramatically cut turnaround time to minutes, explore more designs with less computing power, and speed up decision-making.
Simcenter PhysicsAI empowers engineers to reuse existing CFD results as GDL training data and build predictive models faster
Key capabilities
Designed for engineers, Simcenter PhysicsAI streamlines the creation and use of AI ROMs to support:
- Broader design space exploration: Rapidly evaluate performance across thousands of design variants in minutes. Train predictive models using an advanced transformer neural network architecture optimized for geometric data.
- Better reuse of existing simulation investments: Train AI models from historical data and newly generated results, including previous Design of Experiments (DOE) studies, to reduce the need for re-running CFD simulations.
- Faster iteration cycles: Shift early-stage screening from solver runs to AI inference. Integrate AI ROMs into optimization studies to explore hundreds of design variants in hours instead of weeks.
- Built-in validation and trust: Quantify prediction accuracy with error metrics and validation tools that ensure AI models capture correct performance trends, enabling confident engineering decisions.
- GPU-accelerated design exploration: Simcenter PhysicsAI leverages GPU acceleration for optimal performance, with predictions running up to 100x faster on GPU versus CPU.
Availability
Simcenter PhysicsAI is now available as an add-on to Simcenter STAR-CCM+. Both existing and new customers of Simcenter PhysicsAI will benefit from continued innovation and expanded capabilities across the combined Siemens-Altair product ecosystem. To learn more, visit: https://blogs.sw.siemens.com/simcenter/simcenter-star-ccm-2602-released/
