Dwc. Ho et al., ROBUST APPROXIMATE POLE ASSIGNMENT FOR 2ND-ORDER SYSTEMS - NEURAL-NETWORK COMPUTATION, Journal of guidance, control, and dynamics, 21(6), 1998, pp. 923-929
A recurrent neural network approach to robust approximate pole assignm
ent for second-order systems is proposed. The design is formulated as
an unconstrained optimization problem and solved via the gradient-flow
approach, which is ideally suited for neural network implementation.
Convergence of the gradient flow also is established. Simulation resul
ts are used to demonstrate the effectiveness of the proposed method.