A new identification method for non-uniformly sampled-data systems

Non- uniformly multi-rate sampling scheme is introduced, and the state space model of non-uniformly multi-rate sampling system is derived. The combined state and parameter identification algorithm with singular value decomposition is proposed and the hierarchical identification of state space models for multivariable systems is studied. For systems whose states are measurable, the parameter matrices of state space models are directly identified using the least squares principle. For systems whose states are un-measurable, according to the hierarchical identification principle, a hierarchical state space model identification method with singular value decomposition is presented to estimate unknown parameters and states by using input-output data. The simulation results show that the proposed algorithm has fast convergence rates and high estimation accuracy.