Consistent Subspace Identification of Errors-in-Variables Hammerstein Systems
针对含噪声的Hammerstein系统，提出一种一致子空间辨识方法，通过估计无噪声Hankel矩阵和噪声方差，得到无偏参数估计，并用仿真验证了有效性。
In this article, a consistent subspace identification method (SIM) is proposed for block-oriented errors-in-variables Hammerstein systems. Due to that the existing SIMs using parity subspace based on noisy measurements may result in biased parameter estimates, we propose a scheme for the consistent system parameter estimation, which estimates the noise-free Hankel matrix using available noisy measurements and noise variances. A 2-D search method is proposed to estimate the unknown noise variances from available noisy measurements. After that consistent estimations of the Hammerstein system parameters can be then retrieved from the estimated noise-free Hankel matrix following the same algorithm framework of the existing SIMs using parity subspace. Two simulation examples are included to support the effectiveness and merits of the proposed method.