STFC-self-tuning fuzzy controller

A new type of self-tuning fuzzy controller (STFC) is presented which can emulate not only the control experience of a human expert, but also the strategies or thinking of the expert to be utilized in developing the fuzzy controller. The remarkable feature of the STFC is its dynamic knowledge base, which is constructed with a multilayer rule architecture. In this architecture, upper layer rules, called tuning rules, are used to adjust lower layer rules, called control rules, and the shape of membership functions. A floating object experiment is described to show the control performance compared with general fuzzy control without self-tuning function