Eventos Anais de eventos
COBEM 2017
24th ABCM International Congress of Mechanical Engineering
A Neural Genetic Hybrid Model for Eigenstructure Allocation in the LQR Project in DFIG
Submission Author:
RILDENIR SILVA , MA
Co-Authors:
RILDENIR SILVA
Presenter: RILDENIR SILVA
doi://10.26678/ABCM.COBEM2017.COB17-0831
Abstract
A hybrid neuronal genetic model is proposed with the objective of solving the Riccati Algebraic Equation (RAE) that is associated to the restricted optimization structure of the Linear Quadratic Regulator (LQR) problem. The application of this hybrid model of artificial intelligence will be performed in a wind power generation system, in particular, the double fed induction generator (DFIG). For this, a recurrent neural network with is used where its performance is realized by metrics of the norm of infinity associated with RAE and energy surfaces as a function of the positive definite symmetric matrix.
Keywords
