Hybrid identification of time-varying parameter with particle filtering and expectation maximization

The problem of time-varying parameter identification is considered on a class of nonlinear hybrid systems. It is assumed that inputs and outputs are directly measured, and a subset of system parameters can take different values from a finite set at each time instance. An offline (batch) algorithm that combines particle filtering and the expectation maximization is introduced for the identification of such systems. The efficiency of the proposed method is illustrated through simulated examples.