Multiple-model estimation with variable structure Part V: Likely-model setalgorithm

A multiple-model (MM) estimator with a variable structure, called likely-mo del set (LMS) algorithm, is presented, which is generally applicable to mos t hybrid estimation problems and is easily implementable. It uses a set of models that are not unlikely to match the system mode in effect at any give n time. Different versions of the algorithm are discussed. The model set is made adaptive in the simplest version by deleting all unlikely models and activating all models to which a principal model may Jump so as to anticipa te the possible system made transitions. The generality, simplicity, and ea se in the design and implementation of the LMS estimator are illustrated vi a an example of tracking a maneuvering target and an example of fault detec tion and identification. Comparison of its cost-effectiveness with other fi xed- and variable-structure MM estimators is given.