الملخص
This work proposes a latent Lagrangian-based framework for reduced-order modelling of forced nonlinear dynamical systems. In contrast with conventional Lagrangian or Hamiltonian neural networks, our approach learns a set of latent coordinates sufficient to capture the dynamics conjointly with two neural networks for the latent kinetic and latent potential energies, and leverages force supervision to eliminate the need for an ODE solver during training. Consistency of physical laws in the latent space is ensured through the principle of virtual work. Results show that the model effectively learns the subtle dynamics induced by the system's nonlinearity and non-convex potential energy, and generalizes well to unseen forces and initial conditions. These observations confirm the physical relevance of the proposed approach, and its interest for model reduction.
الكلمات المفتاحية
بيانات النشر
- المعرّف الرقمي
- 10.1016/j.jmps.2026.106633
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Agrawal, A. K., & Thorin, A. (2026). Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems. https://doi.org/10.1016/j.jmps.2026.106633
MLA 9
Agrawal, Anand Kumar, and Anders Thorin. "Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems." https://doi.org/10.1016/j.jmps.2026.106633.
شيكاغو (المؤلف–التاريخ)
Agrawal, Anand Kumar, and Anders Thorin. 2026. "Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems." https://doi.org/10.1016/j.jmps.2026.106633.
هارفارد
Agrawal, A. K. and Thorin, A. (2026) 'Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems', doi:10.1016/j.jmps.2026.106633.
فانكوفر
Agrawal AK, Thorin A. Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems. doi:10.1016/j.jmps.2026.106633
IEEE
A. K. Agrawal, and A. Thorin, "Latent-Lagrangian Neural Networks for Reduced Order Modeling of Non-autonomous Nonlinear Dynamical Systems," doi: 10.1016/j.jmps.2026.106633.