Identification of nonlinear black-box systems based on universal learning networks

Abstract

Presents a modeling scheme for nonlinear black-box systems based on universal learning networks (ULN). The ULN, a superset of all kinds of neural networks, consists of two kinds of elements: nodes and branches corresponding to equations and their relations in a traditional description of dynamic systems. Following the idea of ULN, a nonlinear black-box system is first represented by a set of related unknown equations, and then treated as the ULN with nodes and branches. Each unknown node function in the ULN is re-parameterized by using an adaptive fuzzy model. One of distinctive features of the black-box model constructed in this way is that it can incorporate prior knowledge obtained from input-output data into its modeling and thus its parameters to be trained have explicit meanings useful for estimation and application.