An identification method with direct acquisition of reduced order model from a step response

We propose a deterministic off-line identification method, which is performed by using input and output data with a constant steady state output response. The method can directly acquire any order of reduced model without knowing the real order of a plant, in such a way that the intermediate parameters, from which the coefficients of a rational transfer function are calculated, are determined uniquely being irrelevant to the unmodelled dynamics omitted, in other words, orthogonally with respect to 0/spl sim/N-tuple integral values of output error.