← Physics-Informed Neural ODEs for IBR Dynamics

Physics-Informed Neural ODEs for IBR Dynamics

Continuous-Time PINNs and Neural ODEs

C3-06 · Module outline

Distinguish learning a solution function from learning a dynamic law.

Learning objectives

  • Write the ODE residual for a trajectory-network PINN.
  • Compare prediction interfaces and initial-condition handling.

Concept outline

  1. Time-to-state solution networks
  2. Collocation, initial conditions, and residual losses
  3. State-to-derivative NODE and solver rollout

Experiment direction · Planned

Simulation and code experiment

Train both formulations on the same simple ODE with a declared data budget.

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

Practice and discussion

Explain which formulation directly supplies a reusable vector field.

Worked solutions and feedback will accompany the full lesson.

Material preparation

A dedicated teaching experiment needs to be developed.

Develop a dedicated trajectory-network PINN example and a fair NODE comparison.

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