← Physics-Informed Neural ODEs for IBR Dynamics

Physics-Informed Neural ODEs for IBR Dynamics

From Swing Models to Converter Dynamics

C3-09 · Module outline

Plan a learning experiment with converter states, terminal outputs, and events.

Learning objectives

  • Separate observed channels from hidden states.
  • Respect algebraic constraints and hybrid event boundaries.

Concept outline

  1. A1/B1/C1 datasets and declared observation channels
  2. ODE residuals, KCL, and active sets
  3. Fair NODE, grey-box, and PI-NODE protocols

Experiment direction · Planned

Simulation and code experiment

Start with one fixed converter configuration and hold out complete disturbances.

Model explanations, parameter settings, runnable code, and result interpretation will be developed here.

Practice and discussion

Propose separate baseline and advanced project acceptance criteria.

Worked solutions and feedback will accompany the full lesson.

Material preparation

Physical models and data-generation material are available; the learning pipeline and training validation need development.

Implement and validate the converter learning pipeline; available datasets are not completed training evidence.

All modules in this course
  1. Dynamical Systems and Trajectory Data
  2. Neural Network Foundations
  3. Neural ODEs and Learned Vector Fields
  4. Derivative and Trajectory Matching
  5. Physics Constraints and Residual Backbones
  6. Continuous-Time PINNs and Neural ODEs
  7. Parameter Identification and Generalization
  8. Stability Diagnostics for Learned Models
  9. From Swing Models to Converter Dynamics