FREQUENCY-DOMAIN IDENTIFICATION OF CONTINUOUS-TIME ARMA MODELS FROM SAMPLED DATA

Frequency-domain identification of continuous-time ARMA models from sampled data

This paper treats direct identification of continuous-time autoregressive moving average (CARMA) noise models. The approach has its point of origin in the frequency domain Whittle likelihood estimator. The discreteor continuoustime spectral densities are estimated from equidistant samples of the output. For low sampling rates the discrete-time spectral density is modeled directly by its continu...

Frequency-Domain Identification of Continuous-Time Output Error Models from Non-Uniformly Sampled Data

This paper treats the identification of continuous-time output error (OE) models based on sampled data. The exact method for doing this is well known both for data given in the time domains, but this approach becomes somewhat complex, especially for non-uniformly sampled data. In this paper we assume that the system is fed with a zero order hold input signal and that the sampling rate is so hig...

Frequency-Domain Identification of Continuous-Time Output Error Models from Sampled Data

This paper treats identification of continuous-time output error (OE) models based on sampled data. The exact method for doing this is well known both for data given in the time and frequency domains. This approach becomes somewhat complex, especially for non-uniformly sampled data. We study various ways to approximate the exact method for reasonably fast sampling. While an objective is to gain...

Identification of Continuous-time Models from Sampled Data

Frequency Domain Identification of Continuous-Time ARMA Models: Interpolation and Non-uniform Sampling

In this paper is discussed how to estimate irregularly sampled continuous-time ARMA models in the frequency domain. In the process, the model output signal is assumed to be piecewise constant or piecewise linear, and an approximation of the continuous-time Fourier transform is calculated. ML-estimation in the frequency domain is then used to obtain parameter estimates.