Nonlinear identification of a turbogenerator by local model networks

Local model (LM) networks are applied to the identification of the global nonlinear dynamics of a turbogenerator excitation loop. A hybrid algorithm is used to optimise the learning process. Extensive use of plant `a priori´ information is used to form an initial estimate for the nonlinear interpolation regions. The resulting model was found to describe the behaviour of the nonlinear generator-exciter system over its entire operating range