A Tutorial on Multiple Model Least-squares and Augmented Ud Identiication

The augmented UD identi cation (AUDI) is a family of new identi cation algorithms that are based on some well-known matrix decomposition and updating techniques. Compared with conventional least-squares methods, the AUDI methods are conceptually more concise, computationally more e cient, numerically more robust and application-wise more complete. As a result, AUDI is recommended as a complete replacements for conventional recursive least-squares in all parameter estimation and system identi cation applications. This tutorial paper presents an overview of the AUDI concept, implementation and applications. The multiple model least-squares (MMLS) method, which is a fundamental reformulation and an e cient implementation of the basic least-squares method, is discussed rst. Some application examples of the MMLS/AUDI are presented to demonstrate the versatility and reliability of this type of algorithms.