Physics-Informed Neural ODEs for IBR Dynamics
Dynamical Systems and Trajectory Data
C3-01 · Module outline
Build a simple reference system and construct meaningful training trajectories.
Learning objectives
- Interpret states, equilibria, and numerical trajectories.
- Design whole-trajectory splits before training.
Concept outline
- One-state ODE and two-state swing model
- Initial conditions, parameter families, and coverage
- Normalized teaching coordinates and measurement noise
Experiment direction · Planned
Simulation and code experiment
Generate swing-model trajectories from diverse initial conditions.
Model explanations, parameter settings, runnable code, and result interpretation will be developed here.
Practice and discussion
Explain why random time-row splitting can leak trajectory information.
Worked solutions and feedback will accompany the full lesson.
Material preparation
Related notes, models, or notebooks are available and need adaptation into a web lesson and experiment.
Adapt the existing material into a lesson, a reproducible experiment, and worked practice.