查看文章

It is well known that, in some practical system identification situations, measuring both input and output signals can commonly be affected by additive noises. In this paper, we consider the problem of identifying continuous-time fractional systems from noisy input and output measurements. The bias correction scheme, which aims at eliminating the bias introduced by the fractional order ordinary least squares method, is presented, based on the estimation of variances of the input and output measured noises. The compensation method for the input and output noises is also studied by introducing an augmented high-order fractional-order system in the identification algorithm. The presented algorithm is established to perform unbiased coefficients and fractional orders estimation. The promising performances of the proposed method are assessed via the identification of a fractional model and a fractional real …