Considering the stability and safety of industrial production, the open-loop system cannot meet the requirements of industrial production, so more and more attention has been paid to multivariable closed-loop system identification. This study focuses on the identification of a multivariate closed-loop system with spike noise in which the model order of the feedback channel is lower than that of the forward channel. Combining principal component analysis (PCA), which is used to eliminate the correlation between the data matrix elements, and the derivable approximate least absolute criterion function, partial approximate least absolute deviation (PALAD) for multivariable closed-loop system identification is proposed. By introducing a deterministic function to replace the absolute value in partial approximate least absolute deviation, the non-differentiable problem of the least absolute deviation function can be solved, and the identifiability of the multivariable closed-loop system in the case mentioned above is theoretically verified. Simulation experiments show the validity of the PALAD algorithm. Compared with the partial least squares (PLS) method, PALAD can effectively restrain the spike noise that follows an distribution and shows stronger robustness when white and spike noises exist simultaneously.
Chemical industrial processes involve numerous multivariable nonlinear systems. Nonlinear Muli-Input Muli-Output (MIMO) models seem more suitable to represent most systems and control problems in industrial processes. Furthermore, the outputs of the real systems might be corrupted with the colored noises, which do not satisfy the assumption of the white noises. In order to solve the impact of the colored noises, an Amplitude-Limiting Variational Bayesian (ALVB) method combined with multivariable nonlinear model (Hammerstein model) working in over-sampling closed-loop structure is proposed in this paper. This method is the improvement of the Variational Bayesian (VB) method combining Hammerstein model and over-sampling closed-loop structure. Simulation experiments show that for the nonlinear model (Hammerstein model), the proposed algorithm not only overcomes the unidentifiable disadvantage of the traditional structure but also contributes to a higher identification accuracy. Furthermore, even under situation that the processes output noise is a colored noise, the proposed algorithm still maintains and converges to the achieved accuracy.