Simplified LQG Control with Neural Networks

A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce a minimum variance controller for the non-linear process. After training, tuning possibilities for the observer as well as for the controller are introduced to improve the closed loop robustness and noise suppression. The advantage of this method is that tuning takes place after the time consuming training session. The method is illustrated by a simple, multivariable example.