A self-learning fuzzy stabilizer for a synchronous machine

A fuzzy logic Power System Stabilizer (PSS) with self-learning capability is presented in this paper. This approach combines the advantages of Artificial Neural Networks (ANNs) and Fuzzy Logic Control (FLC). Two multi-layer adaptive networks are employed, one functions as power plant model, another one functions as controller. Propagating errors between the actual and the desired plant outputs back through the model is used to train the fuzzy controller. Without resetting to another existing controller, the proposed stabilizer enables the power system to be stable over a wide range of operating conditions.