Development of a laboratory module for intelligent and classical control classes

This paper demonstrates an educatuanal experimental setup called fluid testbed, which includes the use of CMAC neural networks and robust servomechanism controllers, in real world applications, for the system identification and control of nonlinear systems. This work is intended to serve as the foundation for a laboratory module that can be used in either an undergraduate or graduate course in electrical and computer engineering. The problem of regulating fluid height in a column is considered. A dynamic nonlinear model of the process is obtained using fundamental physical laws and by training a CMAC neural network using experimental input-output data. Based on the identified models, both control approaches are used to implement model reference control. Successful experimental results are obtained even in the presence of disturbances. Engineering students can use the developed testbed to implement intelligent control systems as well as classical methods and control the physical process using computer.