Realization of a database-driven PID control system using a CMAC memory

As a nonlinear control approach, a database-driven PID (DD-PID) controller has been proposed that uses distance calculations of an initial database to tune PID parameters. However, sorting operations are required in extracting neighborhood data from the database, which imposes a large computational load. Therefore, it is impossible to finish this computation within a restricted sampling period in control systems with fast response time and insufficient memory capacity. On the other hand, the cerebellar model articulation controller (CMAC) has advantages for these problems and has similar constructs to the DD approach. Therefore, this paper combines advantages of these two approaches, and proposes a CMAC-PID controller design based on off-line optimization of a database. Finally, a comparison with conventional off-line CMAC-PID controller and DD-PID controller through simulations are considered.