Nonlinear System Identification Using Takagi-Sugeno-Kang Type Interval-valued Fuzzy Systems via Stable Learning Mechanism

摘要

In this paper, we propose a stable learning mechanism for novel Takagi-Sugeno-Kang type interval-valued neural fuzzy systems with asymmetric fuzzy membership functions (called TIVNFS-A). The TIVNFS-A consists of asymmetric fuzzy membership functions and Takagi-Sugeno-Kang type consequent part to enhance the performance. The corresponding type reduction procedure is simplified and integrated in the adaptive network layers to reduce the amount of computation in the system. Based on the Lyapunov stability theorem, the TIVNFS-A system is optimized by the back-propagation (BP) algorithm having an optimal learning rate (adaptive learning rate) to guarantee the stable and faster convergence. Finally, the TIVNFS-A with the optimal stable learning mechanism is applied in nonlinear system identification to demonstrate the effectiveness and performance.