Gradient-Based Parameter Identification Algorithms for Observer Canonical State Space Systems Using State Estimates

摘要

This paper considers the parameter identification problem of the state space observer canonical model for linear stochastic systems, and proposes a Kalman filter-based gradient iterative algorithm and an observer-based multi-innovation stochastic gradient algorithm. The fundamental idea is to replace the unmeasurable states in the information vector with the estimated states and to compute the states of the systems through the Kalman filter or the state observer using the previous parameter estimates. Examples are provided to confirm the effectiveness of the proposed algorithms.