MATLAB® and Its Applications in Engineering: [Based on MATLAB 7.5 (R2007b)]

13.11. Implementation of Ann Controller

One of the simplest approaches for the implementation of neuro-control is the direct inverse control approach. In this approach, the neural network is first trained offline using Error-Backpropagation algorithm to learn the inverse dynamics of the plant and then configured as direct controller to the plant. It has been shown that delayed plant output signals as input vector elements of neural network model in the training stage have definite effect on the neuro-controller in faster learning of the true inverse plant model. Because the neural network is connected in series with the plant for control purposes the direct inverse control scheme is also called Series Neuro-Control Scheme.

There are generally ...