The control of a plant that is a process or critical part of

The control of a plant that is a process or critical part of a system that is to be maintained in a controlled condition, is another learning task that is well suited for neural network. Figure 2 shows the feedback control system that involves the use of unity feedback around a plant to be controlled. How do the learning tasks performed in this system? What are the approaches used? Explain.

Solution

The given system consisting of a plant which is to be controlled with the help of a controller in order to get a desired output. The approach for solving the system is first we have to find out the what the plant is referred to, what should be the desired output (that should be taken as a reference signal) and the controller which is to be used for controlling the system.

The parts of the given figure are explained as below:

Plant

\"Plant\" is a term which refers to the main system process. The given specifications are not meet by the given existing system. The given plants are not changeable so in order to control the plant we use controller.

Controller

The operation of the plant is controlled by an additional system called \"compensator\" which is added to the plant. The system can have multiple compensators, and they can appear anywhere in the system: A feedback loop is added to the plant at the summer or at the summing point.

Summer

A summer or a summing point which is used for adding of two or more signals and gives a single output which is the sum of the two signals. Here in the given figure the output after the summing point is error of the system with respective to the given reference signal

Forward Path

The forward path in the given figure shows the path after the error output from the summing point and then to the controller and then to the plant, after that it gives the output.

Feedback Path

The Feedback path or reverse path which refers as the output taken from the plant and it is given back to the summing point for finding out for any error in the system.

Unity feedback

For the unity feedback system the output is multiplied by a unity gain which is given to the summing point for finding out of the error.