Nonlinear identification and adaptive control based on self-structuring fuzzy systems

This paper presents a nonlinear identification and indirect control algorithm based on a self-structuring fuzzy system (SFS) with guaranteed stability. The overall controller consists of two parts: the indirect adaptive controller based on the self-structuring fuzzy system (IACSFS) is the dominant controller which maintains the closed-loop stability when the fuzzy system is a good approximation of the nonlinear plant. A supervisory controller is an auxiliary controller which is activated when the tracking error reaches the boundary of a predefined constraint set. The supervisory controller helps generate useful data and allows enough time for the fuzzy system to learn and improve through online adding new rules, replacing or deleting old rules and tune the parameters of rules according the latest on-line data. When the fuzzy system regains good approximation through learning and the model based main controller is capable of maintain system stability, the supervisory controller is idle. It is proven that the overall adaptive control scheme with the IACSFS and the supervisory controller guarantees the global stability in the sense that all the closed-loop signals are bounded. The effectiveness of the proposed control scheme is demonstrated through simulation.