100,000 Simulations a Day! AI Powered Simulation with PhysicsX

Our customers can do 100,000 simulations in a day no problem” is the quote that you’ll hear from PhysicsX co-founder Robin Tuluie at the start of this podcast. We spend a lot of time on the Engineer Innovation Podcast trying to work out what the future of engineering simulation will look like, particularly with regard to Machine Learning, Artificial Intelligence and the Digital Twin. This episode provides the clearest view of the future. And what’s better is that it’s available today. In the podcast Robin and Nico explain it better than I can, but PhysicsX use “Deep Learning Surrogates”, which are AI models that are trained using engineering simulations (such as CFD or FEA) but are then capable of – almost instantly – producing thousands of “CFD quality” surrogate solutions. It’s the closest we’ve ever got to “real time CFD”. I started off this interview by being slightly skeptical about some of the claims - after all there is an enormous amount of hype surrounding AI - but by the end I was utterly convinced that the sort of technology that Physics X is set to absolutely revolutionize, and massively increase the impact of engineering simulation, and its ability to solve the huge challenges that our species is facing. This episode of the Engineer Innovation podcast is brought to you by  Siemens Digital Industries Software — bringing electronics, engineering and manufacturing together to build a better digital future. If you enjoyed this episode, please leave a 5-star review to help get the word out about the show, and subscribe on Apple or Spotify so you never miss an episode. For more unique insights on all kinds of cutting-edge topics, tune in to siemens.com/simcenter-podcast   ▶️ About Simcenter: Engineering departments today must develop smart products that integrate mechanical functions with electronics and controls. They should utilize new materials and manufacturing methods and deliver new designs within ever shorter design cycles. This requires current engineering practices for product performance verification to evolve into a Digital Twin approach, which enables us to follow a more predictive process for systems-driven product development. Simcenter™ software uniquely combines system simulation, 3D CAE and tests, to help predict performance across all critical attributes, early and throughout the entire product lifecycle. By combining physics-based simulations with insights gained from data analytics, Simcenter helps you optimize design, and deliver innovations faster and with greater confidence.