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.


Fundamentally-Guided Empirical Modeling


R. Pearson

Norweigian University of Science and Technology, Department of Engineering Cybernetics

Many authors have noted that "pure empirical modeling" is an essentially ill-posed problem. Conversely, fundamental models tend to be extremely complex, making them unsuitable for many model-based control problems. This talk begins with a brief discussion of both of these problems, making the case for "intermediate" or "gray-box" approaches and the rest of the talk is devoted to discussions of some of the key issues that must be addressed in turning this appealing idea into a practical modeling methodology. An extremely important issue is that of initial model structure selection and much of the talk will be concerned with various aspects of this problem: what model structures are available for nonlinear empirical modeling? what are the consequences of different choices, particularly in terms of the possible qualitative behavior of the resulting model? how can fundamental knowledge of qualitative process behavior be used in selecting good empirical model structures and avoiding bad ones? In addition, questions of input sequence design for model identification, parameter estimation, and model validation/invalidation/ refinement will also be discussed.


Type of Publication:

(05)Plenary/Invited/Honorary Lecture

No Files for download available.
% No recipe for automatically generating a BibTex entry for (05)Plenary/Invited/Honorary Lecture
Permanent link