Physics-Informed Neural ODEs for IBR Dynamics
Parameter Identification and Generalization
C3-07 · Module outline
Separate unknown-parameter estimation from prediction at supplied parameters.
Learning objectives
- Recognize compensation between parameters and residuals.
- Evaluate interpolation and extrapolation separately.
Concept outline
- Grey-box derivative matching
- Joint and staged fitting assumptions
- Held-out trajectories and parameter cases
Experiment direction · Planned
Simulation and code experiment
Compare physical-parameter estimates and held-out predictions across model forms.
Model explanations, parameter settings, runnable code, and result interpretation will be developed here.
Practice and discussion
Explain why a small loss need not identify the true parameters.
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.