Estimation and neurocontrol in the presence of feedback

When feedforward adaptive control is applied to distributed parameter plants a feedback path often exists around the controller. This feedback path introduces a potential instability and greatly changes the behaviour of the controlled system, usually degrading performance with respect to the 'no feedback' case. The feedback induced effects present in feedforward neurocontrol are similar to those experienced in the context of simpler linear adaptive controllers. Strategies devised for feedback compensation of linear adaptive controllers are demonstrated to work in the context of nonlinear estimation by feedforward neural networks, in the presence of feedback.<
>