DIAGONAL RECURRENT NEURAL NETWORKS FOR DYNAMIC-SYSTEMS CONTROL

A new neural paradigm called diagonal recurrent neural network (DRNN) is presented. The architecture of DRNN is a modified model of the full y connected recurrent neural network with one hidden layer, and the hi dden layer is comprised of self-recurrent neurons. Two DRNN's are util ized in a control system, one as an identifier called diagonal recurre nt neuroidentifier (DRNI) and the other as a controller called diagona l recurrent neurocontroller (DRNC). A controlled plant is identified b y the DRNI, which then provides the sensitivity information of the pla nt to the DRNC. A generalized dynamic backpropagation algorithm (DBP) is developed and used to train both DRNC and DRNI. Due to the recurren ce, the DRNN can capture the dynamic behavior of a system. To guarante e convergence and for faster learning, an approach that uses adaptive learning rates is developed by introducing a Lyapunov function. Conver gence theorems for the adaptive backpropagation algorithms are develop ed for both DRNI and DRNC. The proposed DRNN paradigm is applied to nu merical problems and the simulation results are included.