New tools are trained on legacy data and simulation results to better predict product performance.
Siemens is the latest CAE provider to offer AI-based simulation technology via HEEDS AI Simulation Predictor and Simcenter Reduced Order Modeling. The aim of these tools is to help engineers predict product and manufacturing performance quickly, efficiently and accurately.
HEEDS AI Simulation Predictor includes accuracy awareness features to help engineers use digital twins and optimize product designs. These features address simulation AI drift, when models are asked to extrapolate data based on inputs that are outside the scope of the training data. For instance, the tool self-verifies information in these situations to ensure accurate results. Siemens also reports that the tool trains its models based on historical simulation studies and accumulated IP and knowledge to ensure accuracy and a quick time to market.
“With HEEDS AI Simulation Predictor, we have significantly improved various components of the gas turbine, leading to highly optimized designs and accelerated design cycles,” said Behnam Nouri, team lead in Engineering and Platform Design at Siemens Energy. “Our thermo-mechanical fatigue predictions have been effectively upgraded to process ~20,000 design members in only 24 hours, yielding a 20% improvement in component lifetime. This has allowed us to fully characterize the limits of our existing design space, which is required for high-efficiency turbine engines. The HEEDS AI Simulation Predictor technology has enabled us to save over 15,000 hours of computational time.”
As for Simcenter Reduced Order Modeling, it uses high fidelity simulations and test data to train AI/ML models that can predict simulation results in seconds. This helps engineers make decisions faster based on reliable data.
“Simcenter Reduced Order Modeling lets us accelerate our simulation models to the point where a detailed fuel cell plant model runs faster than real time, with the same accuracy as a full system model,” said Jurgen Dedeurwaerder, Simulation Engineer at Plastic Omnium, an automotive bumper manufacturer. “This enables activities such as model-in-the-loop controller development and testing to be done faster, shortening the overall development cycle by around 25%. At the same time, it gives us a reliable, IP-protected and cost-effective way to distribute models to other teams, both internally and to our customers to augment their own products and processes, resulting in better quality products delivered to end users.”
