HyperWorks shapeAI makes it possible to automate pattern and shape recognition within a model, enabling the user to select all similar shapes and edit them at the same time. It uses clustering to group the parts, allowing the user to model a small number of groups rather than a large number of individual parts.

shapeAI contains automatic feature extraction for the specified geometry itself without any additional input or intervention. Combining these features with ML algorithms in HyperWorks’ matching tools puts the power of geometric ML at the fingertips of every user. shapeAI can be used to organize components of complex models by geometric similarity so that modifications to one part can be synchronized to all.

Reduced-order models (ROMs) are useful for incorporating detailed 3D simulation into a more computationally efficient 1D environment for system-level study. Simulation tools like Altair® EDEM™ or Altair CFD™ allow for detailed investigations of time-variant non-linear systems, but because of long simulation runs, analysis is typically focused on a component or subsystem. In the case of a complete system simulation however, it is often sufficient to reduce component behavior to its interaction with the complete system, improving solver run time while still providing sufficiently accurate results.

Leveraging Altair’s romAI artificial intelligence tool, 3D simulations can be used as training data for generating dynamic ROMs. Only a few 3D simulation runs are required, as this approach requires less training data than traditional data-driven methods. romAI can work with any solver and produces highly accurate results when operating within the training space and is even stable and useful for extrapolation outside the space. The same ML technique can also be used for system identification purposes when starting from test data.

Digital twins help organizations optimize product performance, gain visibility into the in-service life of a product, know when and where to perform predictive maintenance, and understand how to extend a product’s remaining useful life (RUL). The Altair digital twin integration platform blends physics- and data-driven twins to support optimization throughout the products lifecycle. We take a complete, open, and flexible approach that enables your digital transformation vision on your terms.

The physics based, simulation-driven digital twin leverages standardized, tool independent interfaces like the functional mock-up interface (FMI), co-simulation methods with geometry-based 3D CAE tools, and reduced order modeling approaches to derive low fidelity models from detailed simulations. The data-driven twin uses ML algorithms and data science to optimize product performance. Looking at the problem through this lens allows you to get fast, real-time insights about the status of the product then make the appropriate operational adjustments to improve the life of the product and avoid failures.