Answers are grounded in this paper and cite their sources.
This paper investigates some issues related to grey-box identification. In particular it is discussed how a priori information about the system static nonlinearity can be incorporated into the model. Also, it is shown that in some applications involving nonlinear systems, there must be a tradeoff between the accuracy of the estimated model static nonlinearity and the quality of forecasts. These concepts are applied in the identification of a real DC-DC buck converter operating in continuous mode. Improvement in model global stability was achieved by using simple a priori information that takes into account the steady-state voltage relation of the converter. Models that are valid over a wide operating range are included. Such models are compact and can be estimated directly from data obtained from the converter.
No takes yet. Share an insight, caveat, or question.
Aguirre et al. (2000) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: