A Bias-Corrected Method for Fractional Linear Parameter Varying Systems

Abstract

This paper proposes an identification algorithm for the fractional Linear Parameter Varying (LPV) system considering noisy scheduling and output measurements. A bias correction technique is provided in order to compensate for the bias caused by the least squares algorithm. This approach was created to estimate either coefficients or fractional-order differentiation, and it has been proven to produce unbiased and reliable results. The suggested method’s performance is assessed by the identification of two fractional models and was compared with Nelder–Mead Simplex method.