In this paper, an optimized neuro-fuzzy power-system stabilizer (NF PSS) is
proposed to improve the transient and dynamic stability of synchronous mac
hines. The NF PSS employs a five-layer fuzzy-neural network (FNN). The lear
ning scheme of this FNN is composed of three phases. The first phase uses a
clustering algorithm for coarse identification of the initial membership f
unctions of the fuzzy controller (FC). The second phase extracts the lingui
stic-fuzzy rules from the available training data. In the third phase, a mu
lti-resolutional dynamic genetic algorithm (MRD-GA) is used to fine-tune an
d optimize the membership functions of the FC. Extensive simulation studies
have been carried out to show the performance of the NF PSS and to compare
it with a Conventional PSS (CPSS) in a multi-machine power-system environm
ent. (C) 1999 Published by Elsevier Science B.V. All rights reserved.