Bài báo khoa học

NONLINEAR SYSTEM IDENTIFICATION USING GENERALIZED EXPONENTIAL FUNCTION LINK NETWORK MODEL Extension functions based on the model of trigonometric functional link networks (TFLN) and adaptive exponential functional link networks (AEFLN) have been widely applied in nonlinear system identification. However, these models lack crossover terms (product of the input sample and its past color). This degrades their performance, especially in nonlinear systems containing strong nonlinear distortion. In this study, we propose a generalized AEFLN model (GAEFLN- Generalized AEFLN) for identifying nonlinear systems. Since GAEFLN contains sine, exponential, and cross-term expansion functions, the performance of của will be improved. Simulation results based on nonlinear system identification show that the characteristics of GAEFLN are superior to those of TFLN and AEFLN.