Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


Author's Response to comments on


M. Pottmann, R. Pearson

AIChE Journal, vol. 45, pp. 1839-1840

In their discussion of our paper, Abonyi, Nagy, and Szeifert make a number of observations with which we agree and others with which we differ. Certainly, we agree with their final conclusion that ``care must be taken in the application of the feedback block- oriented model,'' a caution that we would extend to all approximate model classes. Conversely, we disagree with the suggestion that the process dynamics and the steady-state behavior can be specified independently for the more common Wiener and Hammerstein models. Several other points are discussed briefly, and we conclude by re-emphasizing that we approach empirical modeling as a process of approximation and, as a consequence, there can be no ``correct'' empirical model. Different choices of model structure and identification algorithm can be expected to yield different approximations, each with its own associated strengths and weaknesses. In our view, the greatest strengths of the feedback block-oriented model structure are, first, that it permits an exact match of known steady-state characteristics, second, that once these steady-state characteristics are fixed the subsequent parameter estimation problem is straightforward, and finally, that it is capable of exhibiting significantly different types of dynamic behavior than either Wiener or Hammerstein models.


Type of Publication:


File Download:

Request a copy of this publication.
(Uses JavaScript)
% Autogenerated BibTeX entry
@Article { PotPea:1999:IFA_1547,
    author={M. Pottmann and R. Pearson},
    title={{Author's Response to comments on}},
    journal={AIChE Journal},
Permanent link