arXiv:2603.28707v3 Announce Type: replace-cross Abstract: We present a physics-based neural network framework for the discovery of constitutive models in fully coupled thermomechanics. In contrast to classical formulations based on the Helmholtz energy, we adopt the internal energy and a dissipation potential as primary constitutive functions, expressed in terms of deformation and entropy. This choice avoids the need to enforce mixed convexity--concavity conditions and facilitates a consistent incorporation of thermodynamic principles. In this contribution, we focus on materials without prefer
The accelerating pace of AI research, particularly in physics-informed neural networks and material science, is enabling new approaches to complex engineering problems.
This development represents a significant step towards more accurate and efficient computational modeling of materials, which is critical for advanced manufacturing and design.
Traditional constitutive modeling in thermomechanics can be augmented or potentially superseded by AI-driven discovery, leading to more robust and predictive material simulations.
- · Material science researchers
- · Advanced manufacturing industries
- · AI/ML engineering firms
- · Aerospace and automotive sectors
- · Traditional empirical material testing labs (if slow to adapt)
- · Legacy simulation software providers
More accurate simulations of material behavior under extreme conditions become possible.
Accelerated discovery of novel materials with tailored thermomechanical properties could revolutionize engineering applications.
This could lead to a 'digital twin' approach for entire physical systems, predicting failure and optimizing performance with unprecedented precision.
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.AI