Subspace-based Continuous-time Identification

摘要: The last few years have witnessed a strong interest in system identification using realisation-based algorithms. use of Markov parameters as suggested by Ho and Kalman [18] Akaike [1], Kung [28], can be effectively applied to the problem state-space identification; see Verhaegen et al. [43, 44], van Overschee de Moor [41], Juang Pappa [26], Moonen [36], Bayard [3, 4, 33, 34]. Suitable background for discrete-time theory supporting stochastic subspace model is found [1,14,41]. As structures realisation theory, important contributions [12, 31]. these subspace-model algorithms deal with case fitting model, it remains an open how extend methods continuous-time (CT) systems. A great modelling natural sciences technology made means models such require suitable [19]. To this end, theoretical framework statistical validation needed. In particular, experimental data are usually provided time series, relevant provide that permit application data.