A First Course in FUZZY and NEURAL CONTROL

216 CHAPTER 6. NEURAL CONTROL

Figure 6.20. Variation in proportional gain to test pattern

Figure 6.21. Variation in integral gain to test function

From this example, we can see the benefits of using neural control in com-
parison with conventional PID control. Both proportional and integral gains are
variable and can be scaled externally toprovide the desired response. We leave
as an exercise the development of a single neural network that can provide both
proportional and integral control. Choose an appropriate feedforward neural
network topology in which two output neurons can each provide proportional
and integral gain control.

6.5 Neural networks in indirect neural control

Indirect neural control designis based on a neural network model of the
system to be controlled. In this case, the controller itself may not be a neural
network, but it is derived from a plant that is modeled by a neural network.