Identification Methods Of The State Space Model Essay

1501 Words Nov 21st, 2016 7 Pages
Subspace identification methods (SIMs) identify system matrices of the state space model directly from the input and output data measurements. The advantage of SIM is that, it is based on reliable numerical algorithms of the QR decomposition and singular value decomposition (SVD). Furthermore, this method can be implemented for Multi Input Multi Output (MIMO) system identification. There are several algorithms commonly used for subspace identification which are Canonical Variate Analysis (CVA) proposed by [1], Multivariable Output Error State Space (MOESP) by [2] and Numerical Subspace State Space System Identification (N4SID) by [3]. Basically, subspace identification algorithms are based on the concepts from different branches which are system theory, numerical linear algebra and statistics.
Subspace identification methods for linear time invariant systems initially can be classified into two groups. The first group consists of methods that aim at obtaining the column space of the extended observability matrix and subsequently use the shift invariant structure of this matrix to estimate A and C matrices. The MOESP methods are considered in this group. Meanwhile, the second group consists of method that aim at approximating the state sequence of the system and use the approximate state in a second step to estimate the system matrices. The methods that consider in the second group are the N4SID methods [3], [4] and CVA methods.
The different in each subspace…

Related Documents