„I am firmly convinced that AI is on the cusp of disrupting simulations at industry-scale. Every day thousands and thousands of compute hours are spent on turbulence modeling, simulations of fluid or air flows, heat transfer in materials, traffic flows, and many more. Many of these processes follow similar underlying patterns, but yet need different and extremely specialized softward to simulate. Even worse, for different parameter settings the costly simulations need to be run at full length from scratch“, says Prof. Dr. Johannes Brandstetter from JKU Linz. He is one of a few top researchers in the field of simulation and AI.

Back to Siemens Energy: Our key take aways

Integration of Machine Learning: Siemens Energy has been integrating machine learning into their design process to overcome the limitations of computational time in turbine optimization. This has allowed for faster and more robust designs.

Machine Learning Models: The company experimented with various machine learning models to find the most efficient in predicting outcomes with minimal training data. Bayesian models and Gaussian processes emerged as effective, with the ability to predict their own certainty levels.

Simulation Acceleration: By incorporating AI tools into their workflow, Siemens Energy managed to replace time-consuming simulations with machine learning predictions, thus speeding up the design process significantly.

Generative Design: The latest research focuses on generative design and 3D surrogates, aiming to make predictions about any turbine geometry within seconds, a task that previously took weeks.

Applications in Robust Design: Machine learning models have been used to ensure the robustness of turbine designs by testing them against a myriad of variations, thereby guaranteeing their performance under different conditions.

Efficiency Gains: Over the years, Siemens Energy has increased the efficiency of their turbines by integrating machine learning, moving closer to their goal of achieving higher efficiency levels without the need for physical modifications that could compromise the turbine's size or cost-effectiveness.

Computational Savings: The implementation of machine learning has led to an exponential decrease in the amount of computational time and resources needed for turbine design, highlighting the transformative impact of AI in industrial engineering.