Neural regulator design.
Design of a neural-net-based regulator for nonlinear plants is considered. Both state and output feedback regulators with deterministic and stochastic disturbances have been investigated. A Multilayered Feedforward Neural Network (MFNN) has been employed as the nonlinear controller. The training of the MFNN utilizes the recently developed concept of Block Partial Derivatives (BPDs).
Journal Article↗