Modeling and identification of parallel and feedback nonlinear systems

Structural classification and parameter estimation (SCPE) methods have been used for studying single-input single-output (SISO) parallel and feedback nonlinear system models from input-output (I-O) measurements. The uniqueness of the I-O mappings of different models and parameter uniqueness of the I-O mapping of a given structural model are evaluated. The former aids in defining the conditions under which different model structures may be differentiated from one another. The latter defines the conditions under which a given model parameter can be uniquely estimated from I-O measurements. SCPE methods presented in this paper can be further developed to study more complicated multi-input multi-output (MIMO) block-structured models which will provide useful techniques for modeling and identifying highly complex nonlinear systems