Development of classification and prediction methods of critical heat flux using fuzzy theory and artificial neural networks = 퍼지이론과 인공신경회로망을 이용한 임계 열유속의 분류와 예측방법의 개발

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 328
  • Download : 0
This thesis applies new information techniques, artificial neural networks, (ANNs) and fuzzy theory, to the investigation of the critical heat flux (CHF) phenomenon for water flow in vertical round tubes. The work performed are (a) classification and prediction of CHF based on fuzzy clustering and ANN, (b) prediction and parametric trends analysis of CHF using ANN with the introduction of dimensionless parameters, and (c) detection of CHF occurrence using fuzzy rule and spatiotemporal neural network (STN). Fuzzy clustering and ANN are used for classification and prediction of the CHF using primary system parameters. The fuzzy clustering classifies the experimental CHF data into a few data clusters (data groups) according to the data characteristics. After classification of the experimental data, the characteristics of the resulted clusters are discussed with emphasis on the distribution of the experimental conditions and physical mechanisms. The CHF data in each group are trained in an artificial neural network to predict the CHF. The artificial neural network adjusts the weight so as to minimize the prediction error within the corresponding cluster. Application of the proposed method to the KAIST CHF data bank shows good prediction capability of the CHF, better than other existing methods. Parametric trends of the CHF are analyzed by applying artificial neural networks to a CHF data base for water flow in uniformly heated vertical round tubes. The analyses are performed from three viewpoints, i.e., for fixed inlet conditions, for fixed exit conditions, and based on local conditions hypothesis. In order to remove the necessity of data classification, Katto and Groeneveld et al.``s dimensionless parameters are introduced in training the ANNs with the experimental CHF data. The trained ANNs predict the CHF better than any other conventional correlations, showing RMS error of 8.9%, 13.1%, and 19.3% for fixed inlet conditions, for fixed exit conditions, and for l...
Chang, Soon-Heungresearcher장순홍researcher
한국과학기술원 : 원자력공학과,
Issue Date
101880/325007 / 000895150

학위논문(박사) - 한국과학기술원 : 원자력공학과, 1995.8, [ xiii, 152 p. ]


Prediction; Classification; Fuzzy and ANN; Critical Heat Flux; Parametric Trends; 변수 경향; 예측; 분류; 퍼지와 인공신경회로망; 임계 열유속

Appears in Collection
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0