A T-S type of rough fuzzy controller based on process input-output data

A new type of rough fuzzy controller is proposed. The design of the controller combines the rough logic with fuzzy inference. In this approach, rough set theory is used to find the minimal set of rules of input-output space, and by complementing the information of output control corresponding to the rough reduced rules, a T-S type of rough fuzzy control system is constructed, which can derive control rules from input-output data effectively and can solve the problem that the number of rules in a fuzzy controller increases exponentially with the number of variables involved. The simulation for controlling the inverted pendulum with a varying length of pole shows that a highly precise nonlinear control is achieved.