Easily build, validate and export reduced order models using best-in-class methods to go faster with simulation or embed predictive power into products or processes.
Simcenter Reduced Order Modeling is an easy-to-use platform for building, validating and exporting reduced order models (ROMs) from simulation and test data.
An open platform for ROM
Use high-fidelity simulation or test data from any source to make super-fast predictions, enabling faster decision-making, co-simulation and real-time applications including control and monitoring.
Easy to use for experts and non-experts
Access a comprehensive range or best-in-class data reduction methods, from control theory to neural networks and Artificial Intelligence (AI). Easily train different ROMs and compare using performance metrics through a simple, no-code, user interface.
Integrated with Simcenter
Simcenter Reduced Order Modeling exchanges data and models seamlessly with Simcenter tools for simulation and physical testing, while also supporting neutral formats for data import and model export.
Find out how reduced-order modeling lets you do more with simulation and test data.
Data reduction methods are a very active area of research today and are used for a variety of tasks in engineering and data science. Simcenter Reduced Order Modeling offers the methods best suited for CAE applications, from response surface models to neural networks, AI and machine learning (ML).
The intuitive user interface and setup wizard deliver these best-in-class methods through an automated workflow, allowing the user to maintain their focus on the application.
Leverage ROM using any form of simulation or test data - from fluids and thermal, mechanical, system simulation or physical test data. While it can import and analyze data from any source, Simcenter Reduced Order Modeling integrates seamlessly with the Simcenter portfolio tools.
Simcenter Reduced Order Modelling guides you through the end-to-end ROM creation process. A single interface handles the workflow from importing data, through selecting, training and validating models, to export.
Different workflows case for for experts and non-experts alike. Not sure which data reduction technique gives the best performance for your application? The automatic model sweep configures and trains all suitable methods and ranks them using standard performance metrics.
Export ROMs to multiple targets including FMI, ONNX and Amesim submodel in one click. Exported models are tool-agnostic and do not require a license or solver to run, making them a cost-effective way to accelerate simulation workflows as well as being a robust and secure means of sharing models with colleagues and customers.