Key‐Term Separation–Based Approach for Fractional Hammerstein System Using the Filtering Technique

ABSTRACT

This work studies the identification problem of fractional‐order Hammerstein–controlled autoregressive FOHCAR systems with ARMA noise using filtered input and output data. The system consists of a static nonlinear block in series with a fractional‐order dynamic subsystem. Two novel approaches are developed to estimate the parameters of the linear subsystem, the coefficients of the nonlinear block and the noise model parameters. First, an auxiliary model least‐square‐based iterative algorithm is proposed. Next, a key‐term separation least‐square‐based iterative algorithm is developed based on the decomposition technique. The auxiliary model principle is applied for both estimation methods to overcome the issue of unknown parameters and unmeasured intermediate signals. The experimental results demonstrate the efficiency of the proposed algorithms in offering consistent parameter estimates with high accuracy and fast convergence speed.