A general regression artificial neural network for two-phase flow regime identification

Tambouratzis, Tatiana; Pázsit, Imre

doi:10.1016/j.anucene.2010.02.004

Cited by 38 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, application of ANNs in the data treatment is especially important where systems present nonlinearities and complex behavior. So ANNs have been applied successfully in different areas such as function approximation and pattern recognition [25][26][27][28]. These artificial networks can be trained in such a way as to learn sophisticated experimental relations and detect patterns that are related independently to their corresponding dependent variables.…”

Section: Design Of Neural Networkmentioning

confidence: 99%

Prediction of Two-Phase Heat Transfer Coefficients in a Horizontal Pipe for Different Inclined Positions With Artificial Neural Networks

Sobhanifar

Ahmadloo

Azizi

2015

Journal of Heat Transfer

View full text Add to dashboard Cite

This paper presents the application of artificial neural network (ANN) in prediction of heat transfer coefficients (HTCs) of two-phase flow of air-water in a pipe in the horizontal and slightly upward inclined (2, 5, and 7 deg) positions. For this purpose, the superficial liquid and gas Reynolds numbers and the inclination of the pipe were used as input parameters, while the HTCs of two-phase flow were used as output parameters in training and testing of the multilayered, feedforward, backpropagation neural networks. In this present study, experimental data were taken from literature and then used for the ANN model. The superficial liquid and gas Reynolds numbers ranged from 740 to 26,100 and 560 to 47,600 for water and air, respectively. The mean deviations against experimental data were determined for the model. Results showed that the network predictions were in very good agreement with the experimental HTC data, whereas the correlation showed more deviations. Finally, results showed that the accuracy between the neural network predictions and experimental data was achieved with mean relative error (MRE) of 2.92% and correlation coefficient (R) that was 0.997 for all datasets, which suggests the reliability of the ANNs as a strong tool for predicting HTCs with two-phase flows.

show abstract

Section: Design Of Neural Networkmentioning

confidence: 99%

Prediction of Two-Phase Heat Transfer Coefficients in a Horizontal Pipe for Different Inclined Positions With Artificial Neural Networks

Sobhanifar

Ahmadloo

Azizi

2015

Journal of Heat Transfer

View full text Add to dashboard Cite

show abstract

“…counter-clustering [23]) combined with pattern selection (e.g. [24][25][26]) may be needed (the interested reader is referred to [25][26][27] for examples of classification tasks implemented via PNN's and GR ANN's).…”

Section: Correlation Coefficients Between Pairs Of Continuous/categormentioning

confidence: 99%

Combining probabilistic neural networks and decision trees for maximally accurate and efficient accident prediction

Tambouratzis

Souliou

Chalikias

et al. 2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

The extent to which accident severity can be predicted from accident-related data collected at a variety of locations is investigated. The 2005 accident dataset brought together by the Republic of Cyprus Police is employed; this dataset comprises 1407 records of 43 continuous and categorical input parameters and a single categorical output parameter representing accident severity. No transformation of the database has been opted for, either by extracting the parameters that are significant for the prediction task or by modifying the records in any way (e.g. via record selection or transformation). Aiming at maximally accurate and efficient prediction, a combination of probabilistic neural networks (PNN's) and decision trees (DT's) is implemented: the simple training and direct operation of the PNN is complemented by the hierarchical, exhaustive and recursive construction of the DT. By training pairs of PNN's on data from the partitions derived from the minimal necessary number of top DT nodes, both efficiency and accident prediction accuracy are maximized.

show abstract

“…(9) The most well-defined number of individuals (elitism) are stored for the next generation. (10) To fix the increased number of population to the initially defined number, individuals with high fitness values (poor individuals) are removed from the population randomly. (11) And the individual with the lowest fitness value (best individual) is assigned as the global best.…”

Section: Calculation Procedures For the Genetic Algorithm (Ga)mentioning

confidence: 99%

“…Tambouratzis and Pazsit [10] proposed a general regression ANN for the identification of the two-phase flow in the coolant channels of boiling water reactors. In conclusion, their cross validation tests validated accurate on-line flow regime identification.…”

Section: Introductionmentioning

confidence: 99%

Investigation of empirical correlations on the determination of condensation heat transfer characteristics during downward annular flow of R134a inside a vertical smooth tube using artificial intelligence algorithms

2011

View full text Add to dashboard Cite

The heat transfer characteristics of R134a during downward condensation are investigated experimentally and numerically. While the convective heat transfer coefficient, two-phase multiplier and frictional pressure drop are considered to be the significant variables as output for the analysis, inputs of the computational numerical techniques include the important two-phase flow parameters such as equivalent Reynolds number, Prandtl number, Bond number, Froude number, Lockhart and Martinelli number. Genetic algorithm technique (GA), unconstrained nonlinear minimization algorithm-Nelder-Mead method (NM) and non-linear least squares error method (NLS) are applied for the optimization of these significant variables in this study. Regression analysis gave convincing correlations on the prediction of condensation heat transfer characteristics using ±30% deviation band for practical applications. The most suitable coefficients of the proposed correlations are depicted to be compatible with the large number of experimental data by means of the computational numerical methods. Validation process of the proposed correlations is accomplished by means of the comparison between the various correlations reported in the literature.

show abstract

A general regression artificial neural network for two-phase flow regime identification

Cited by 38 publications

References 25 publications

Prediction of Two-Phase Heat Transfer Coefficients in a Horizontal Pipe for Different Inclined Positions With Artificial Neural Networks

Prediction of Two-Phase Heat Transfer Coefficients in a Horizontal Pipe for Different Inclined Positions With Artificial Neural Networks

Combining probabilistic neural networks and decision trees for maximally accurate and efficient accident prediction

Investigation of empirical correlations on the determination of condensation heat transfer characteristics during downward annular flow of R134a inside a vertical smooth tube using artificial intelligence algorithms

Contact Info

Product

Resources

About