Model-group switching algorithm for multiple-model estimation with variable structure

摘要

The general multiple-model estimator with variable structure (VSMM) presented, namely the model-group switching (MGS) algorithm, assumes that the total set of models can be covered by a number of model groups, each representing a cluster of closely related system behavior patterns or structures; a particular group is running at any given time determined by a hard decision. ^This algorithm is the first VSMM estimator generally applicable to a large class of problem with hybrid (continuous and discrete) uncertainties and easily implementable. ^The algorithm is implemented for a problem of tracking a maneuvering target using a time-varying set (group) of models. ^Simulation results show that the proposed MGS algorithm provides a substantial reduction in computation while having virtually identical performance with the fixed-structure interacting multiple-model estimator. ^(Author)