Germinal Center Optimization Applied to Recurrent High Order Neural Network Observer

摘要

In this work, a germinal center optimization (GCO) algorithm which implements temporal leadership through modeling a non-uniform competitive-based distribution for particle selection is used to find an optimal set of parameters for a recurrent high order neural network observer (RHONNO). The RHONNO is trained with an extended Kalman filter algorithm and it is capable of giving a model of the system besides of just giving state estimation. Furthermore, the RHONNO does not need previous knowledge of the system model, nor measurements, estimation or bounds of delays and disturbances. Applicability of the proposed methodology is presented using simulation results.