Documentation for systemID

systemID is an open source Python package consisting of a collection of functions useful for linear, bilinear and nonlinear system identification, focusing on time-domain methods. It provides a complete and robust API and implements most of the latest system identification techniques.

Specifically, it handles
  • Eigensystem Realization Algorithm (ERA), from initial condition response (ERA/IC)

  • Observer Kalman Identification Algorithm (OKID)

  • Eigensystem Realization Algorithm with Data Correlations (ERA/DC), from initial condition response (ERA/DCIC)

  • Time-varying Eigensystem Realization Algorithm (TVERA), from initial condition response (TVERA/IC)

  • Time-varying Observer Kalman Identification Algorithm (TVOKID)

  • Time-varying Eigensystem Realization Algorithm with Data Correlations (TVERA/DC), from initial condition response (TVERA/DCIC)

  • Bilinear System Identification Algorithm

  • Koopman Operator, general embeddings

  • Sparse Approximation

  • Higher-order state-transition tensor propagation (up to order 4)

Find Github code source: systemID.