Search

Liquid metals play a central role in new generation liquid metal cooled nuclear reactors, for which numerical investigations require the use of appropriate thermal turbulence models for low Prandtl number fluids. Given the limitations of traditional modelling approaches and the increasing availability of high-fidelity data for this class of fluids, we propose a Machine Learning strategy for the modelling of the turbulent heat flux. A comprehensive algebraic mathematical structure is derived and physical constraints are imposed to ensure attractive properties promoting applicability, robustness and stability. The closure coefficients of the model are predicted by an Artificial Neural Network (ANN) which is trained with DNS data at different Prandtl numbers. The validity of the approach was verified through a priori and a posteriori validation for two and three-dimensional liquid metal flows. The model provides a complete vectorial representation of the turbulent heat flux and the predictions fit the DNS data in a wide range of Prandtl numbers (Pr=0.01-0.71). The comparison with other existing thermal models shows that the methodology is very promising.

One of the most important topics discussed in the area of financial management is investors’ ability to tell favourable investment opportunities from unfavourable ones. One way to help investors is to present firm’s financial distress prediction models. So far, different techniques have been used to design firm’s financial distress prediction models. Recent studies in the field of financial distress prediction have focused on creation and application of artificial intelligence and machine learning methods, AdaBoost algorithm and artificial neural networks are used in the present study as a comparative model to Companies’ financial distress prediction. 660 samples were selected from 112 financially distressed companies and 548 non-financially distressed over a 6-year period from 2007 to 2012 have been selected.Research Findings suggest that in Companies’ financial distress prediction, the model based on AdaBoost algorithm has a higher overall accuracy than the model based on artificial neural network.

One of the most important topics discussed in the area of financial management is investors’ ability to tell favourable investment opportunities from unfavourable ones. One way to help investors is to present firm’s financial distress prediction models. So far, different techniques have been used to design firm’s financial distress prediction models. Recent studies in the field of financial distress prediction have focused on creation and application of artificial intelligence and machine learning methods, AdaBoost algorithm and artificial neural networks are used in the present study as a comparative model to Companies’ financial distress prediction. 660 samples were selected from 112 financially distressed companies and 548 non-financially distressed over a 6-year period from 2007 to 2012 have been selected.Research Findings suggest that in Companies’ financial distress prediction, the model based on AdaBoost algorithm has a higher overall accuracy than the model based on artificial neural network.

Understanding the effect of soil parameters (pH, Eh and organic and inorganic ligands availability) on uranium mobility under different geochemical conditions is fundamental for reliable prediction of its behaviour and fate in the environment. In this study, the impact of total and available phosphorus content, humus and acidity of Serbian agricultural soils on the content of total and available uranium were evaluated by Response Surface Methodology (RSM), second order polynomial regression models (SOPs) and artificial neural networks (ANNs). The performance of ANNs was compared with the performance of SOPs and experimental results. SOPs showed high coefficients of determination (0.785-0.956), while ANN model performed high prediction accuracy: 0.8893-0.904. According to the results, total and available uranium content in the soil were mostly affected by pH, statistically significant at p LT 0.05 level. For the same responses the total phosphorus was found to be also very influential, statistically significant at p LT 0.05 and p LT 0.10 levels. The impact of available phosphourus and humus was much more influential on total and available uranium content, compared to total phosphorus content. Proposed chemometric approach will be very helpful in preserving the natural resources and practical application for risk assessment modeling of uranium environmental pathways.