| Popis: |
Following the philosophy of adaptive optimal control, a new technique is presented for robust optimal regulation of a class of nonlinear systems. First, accounting for a nominal system model, a single network adaptive critic (SNAC) based multi-layered neural network (called as NN 1 ) is synthesized offline for optimal regulation of the nominal system. However, another linear-in-weight neural network (called as NN 2 ) is trained online and augmented to NN1 in such a manner that their combined output represent the desired optimal costate for the actual plant. To do this, the nominal model needs to be updated online to adapt to the actual plant, which done by synthesizing yet another linear-in-weight neural network (called as NN3) online. Training of NN3 is done so that both the unmodelled part of the dynamics as well as its partial derivatives with respect to the states are captured. The overall architecture is named as 'Dynamically re-optimized single network adaptive critic (DR-SNAC)'. Numerical results for Van der Pol problem are presented, which demonstrate its effectiveness, and clearly bring out the potential of the proposed approach. |
