What if you could create 1D simulation models that retain the precision of your 3D analysis while running up to thousands of times faster?
That’s why we created romAI! It uses machine learning to create reduced order models of your long runtime, highly complex subsystems models with ready-to-use versions for your system performance simulations. The romAI algorithms need just a few results from 3D simulation runs to use as training data to generate the 1D model that delivers fast solve times and accurate results. Also in the context of digital twins, The signalAI feature exists to help you detect and prevent anomalies in sensor or simulation data with signal processing and machine learning. By analyzing available records augmented with synthetic data, the AI algorithms identify issues and discover their root causes. signalAI extracts useful time or frequency domain features automatically from historical, real-time sensor, or simulation data to train a state-of-the-art predictive model. The model can be deployed on the desktop, in the cloud, or on an edge device.