A Neural Fuzzy Controller Learning by Fuzzy Error Propagation
نویسندگان
چکیده
In this paper we describe a procedure to integrate techniques for the adaptation of membership functions in a linguistic variable based fuzzy control environment by using neural network learning principles. This is an extension to our work in 2]. We solve this problem by deenining a fuzzy error that is propagated back through the architecture of our fuzzy controller. According to this fuzzy error and the strength of its antecedent each fuzzy rule determines its amount of error. Depending on the current state of the controlled system and the control action derived from the conclusion, each rule tunes the membership functions of its antecedent and its conclusion. By this we get an unsupervised learning technique that enables a fuzzy controller to adapt to a control task by knowing just about the global state and the fuzzy error.
منابع مشابه
Maximum Power Point Tracking of the Photovoltaic System Based on Adaptive Fuzzy-Neural Method
The aim of this paper was to present an optimized method in order to use maximum capacity of the photovoltaic panels. In this regard, we presented a method for the maximum power point tracking in the photovoltaic systems by using the neural networks and adaptive controller. In the proposed system, we estimated an error by using neural network. If this error is lower than the allowable systems e...
متن کاملFast Transient Hybrid Neuro Fuzzy Controller for STATCOM During Unbalanced Voltage Sags
A static synchronous compensator (STATCOM) is generally used to regulate voltage and improve transient stability in transmission and distribution networks. This is achieved by controlling reactive power exchange between STATCOM and the grid. Unbalanced sags are the most common type of voltage sags in distribution networks. A static synchronous compensator (STATCOM) is generally used to maintain...
متن کاملInterpreting Changes in the Fuzzy Sets of a Self-adaptive Neural Fuzzy Controller
We describe a procedure for the adaptation of membership functions in a fuzzy control environment by using neural network learning principles. The changes in the fuzzy sets can be easily interpreted. By using a fuzzy error that is propagated back through the architecture of our fuzzy controller, we receive an unsupervised learning technique, where each rule tunes the membership functions of its...
متن کاملOutput Based Adaptive Iterative Learning Control Design for Nonaffine Nonlinear Systems
In this paper, an output based adaptive iterative learning controller using an output recurrent fuzzy neural network is proposed for a class of uncertain nonaffine nonlinear systems. It is assumed that the states are not measurable. Without state observer, a sliding window of measurement is introduced to design the iterative learning controller. The main structure of this controller is construc...
متن کاملA Controller Design with ANFIS Architecture Attendant Learning Ability for SSSC-Based Damping Controller Applied in Single Machine Infinite Bus System
Static Synchronous Series Compensator (SSSC) is a series compensating Flexible AC Transmission System (FACTS) controller for maintaining to the power flow control on a transmission line by injecting a voltage in quadrature with the line current and in series mode with the line. In this work, an Adaptive Network-based Fuzzy Inference System controller (ANFISC) has been proposed for controlling o...
متن کامل