Implementation of Hyperelastic Physics-Augmented Neural Networks in the Explicit Finite Element Codes Simcenter Radioss and OpenRadioss with Applications to Impact Events
arXiv:2606.29874v1 Announce Type: cross Abstract: Data-driven material modeling techniques have gained significant attention due to their ability to capture complex constitutive behaviors beyond the limitations of classical material models. Physics-augmented neural networks (PANNs), which embed physical constraints directly into their architecture, combine the flexibility of machine learning with the reliability required for engineering simulations. This work presents an approach to integrate such network architectures into the explicit finite element solvers Simcenter Radioss and OpenRadioss
The increasing sophistication of neural networks and the demand for more accurate and efficient engineering simulations are driving the integration of AI with established physics-based modeling techniques.
This development allows for more accurate and faster material modeling in critical engineering applications, reducing development cycles and improving product reliability.
Material modeling in explicit finite element analysis becomes more flexible and robust through the integration of physics-augmented neural networks, potentially leading to more advanced design and simulation capabilities.
- · Engineering and Manufacturing Sectors
- · Simulation Software Providers
- · Material Science Researchers
- · AI/ML Developers
- · Traditional Material Modeling Techniques (potentially less competitive)
- · Companies reliant solely on empirical material testing
Improved material performance and structural integrity in engineered products, especially under extreme conditions like impact events.
Accelerated design and iteration cycles for complex mechanical systems, leading to faster innovation in industries like aerospace and automotive.
The potential for 'digital twin' fidelity to significantly increase, enabling predictive maintenance and performance optimization to a degree previously unachievable.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG