Premium
A Quantitative Measure to Evaluate Competing Designs for Non‐linear Dynamic Process Identification
Author(s) -
Rollins Derrick K.,
Pacheco Liza,
Bhandari Nidhi,
Nguyen Justin
Publication year - 2006
Publication title -
the canadian journal of chemical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.404
H-Index - 67
eISSN - 1939-019X
pISSN - 0008-4034
DOI - 10.1002/cjce.5450840407
Subject(s) - identification (biology) , measure (data warehouse) , computer science , process (computing) , sampling (signal processing) , design of experiments , data mining , content (measure theory) , mathematical optimization , statistics , mathematics , mathematical analysis , botany , filter (signal processing) , computer vision , biology , operating system
The strategy for the collection of information (i.e., data) for model development is called experimental design. Optimal design seeks to maximize the information content under constraints of time and sampling. In the system identification literature the dominant strategy has been the method of pseudo random sequences (PRS). However, this work demonstrates that statistical design of experiments (SDOE) can provide greater information content as quantitatively measured by the D‐optimal criterion.