文档介绍：Expert Systems with Applications 37 (2010) 5454–5460
Contents lists available at ScienceDirect
Expert Systems with Applications
journal homepage: ate/eswa
An adaptive neuro-fuzzy inference system approach for prediction of tip speed
ratio in wind turbines
R. Ata a, Y. Kocyigit b,*
a Celal Bayar University, Department of Electrics, 45700 Kırkag˘aç, Manisa, Turkey
b Celal Bayar University, Department of Electrical and Electronics Engineering, Muradiye, Manisa, Turkey
article info abstract
Keywords: This paper introduces an adaptive neuro-fuzzy inference system (ANFIS) model to predict the tip speed
Wind turbines ratio (TSR) and the power factor of a wind turbine. This model is based on the parameters for LS-1 and
Tip speed ratio NACA4415 profile types with 3 and 4 blades. In model development, profile type, blade number, Schmitz
Adaptive neuro-fuzzy inference system coefficient, end loss, profile type loss, and blade number loss were taken as input variables, while the TSR
(ANFIS)
and power factor were taken as output variables. After a essful learning and training process, the pro-
Artificial works (ANN)
posed model produced reasonable mean errors. The results indicate that the errors of ANFIS models in
Prediction
predicting TSR and power factor are less than those of the ANN method.
Ó 2010 Elsevier Ltd. All rights reserved.
1. Introduction depends on seve