Fuzzy identification based on fuzzy clustering and decomposition of matrices (Q2785114)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Fuzzy identification based on fuzzy clustering and decomposition of matrices |
scientific article; zbMATH DE number 1733325
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Fuzzy identification based on fuzzy clustering and decomposition of matrices |
scientific article; zbMATH DE number 1733325 |
Statements
16 November 2002
0 references
fuzzy modeling
0 references
matrix QR decomposition
0 references
matrix UD decomposition
0 references
fuzzy clustering
0 references
identification
0 references
gas furnace system
0 references
Fuzzy identification based on fuzzy clustering and decomposition of matrices (English)
0 references
The authors present a method for identifying fuzzy systems. The method consists of five steps: (1) the premise structure of a fuzzy model is obtained by an improved fuzzy clustering; (2) the inference matrices are a decomposition on the basis of a matrix QR decomposition; (3) the validity of clustering is acquired according to an analysis of the ranks of the matrices; (4) a recursive least squares method based on the matrix UD decomposition is used to estimate the conclusion parameters of the fuzzy model; (5) the structure and the parameters of the fuzzy model are optimized. The above method is successfully used to model the gas furnace system that comes from Box-Jenkins' famous book of 1970.
0 references
