DocumentCode :
3606815
Title :
Comprehensive Modeling of U-Tube Steam Generators Using Extreme Learning Machines
Author :
Beyhan, Selami ; Kavaklioglu, Kadir
Author_Institution :
Electr. & Electron. Eng., Pamukkale Univ., Denizli, Turkey
Volume :
62
Issue :
5
fYear :
2015
Firstpage :
2245
Lastpage :
2254
Abstract :
This paper proposes artificial neural network and fuzzy system-based extreme learning machines (ELM) for offline and online modeling of U-tube steam generators (UTSG). Water level of UTSG systems is predicted in a one-step-ahead fashion using nonlinear autoregressive with exogenous input (NARX) topology. Modeling data are generated using a well-known and widely accepted dynamic model reported in the literature. Model performances are analyzed with different number of neurons for the neural network and with different number of rules for the fuzzy system. UTSG models are built at different reactor power levels as well as full range that corresponds to all reactor operating powers. A quantitative comparison of the models are made using the root-mean-squared error (RMSE) and the minimum-descriptive-length (MDL) criteria. Furthermore, conventional back propagation learning-based neural and fuzzy models are also designed for comparing ELMs to classical artificial models. The advantages and disadvantages of the designed models are discussed.
Keywords :
autoregressive processes; backpropagation; boilers; fission reactor cooling; fuzzy neural nets; fuzzy set theory; mean square error methods; nuclear engineering computing; U-tube steam generators; UTSG system water level; artificial neural network; back propagation learning-based neural models; classical artificial models; dynamic model performances; fuzzy system; fuzzy system-based extreme learning machines; minimum-descriptive-length criteria; nonlinear autoregressive with exogenous input topology; offline modeling; one-step-ahead fashion; online modeling; reactor operating powers; reactor power levels; root-mean-squared error; Adaptation models; Computational modeling; Data models; Fuzzy systems; Generators; Mathematical model; Numerical models; Extreme learning machine; U-tube steam generator (UTSG); fuzzy system; minimum-descriptive-length (MDL); neural-network; online and offline identification; root-mean-squared error (RMSE);
fLanguage :
English
Journal_Title :
Nuclear Science, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9499
Type :
jour
DOI :
10.1109/TNS.2015.2462126
Filename :
7274493
Link To Document :
بازگشت