Flow regime and volume fraction identification using nuclear techniques, artificial neural networks and computational fluid dynamics

2020 ◽  
Vol 159 ◽  
pp. 109103 ◽  
Author(s):  
Renato R.W. Affonso ◽  
Roos S.F. Dam ◽  
William L. Salgado ◽  
Ademir X. da Silva ◽  
César M. Salgado
Keyword(s):  
Fluid Dynamics ◽  
Neural Networks ◽  
Computational Fluid Dynamics ◽  
Artificial Neural Networks ◽  
Flow Regime ◽  
Volume Fraction ◽  
Nuclear Techniques ◽  
Artificial Neural

Optimization of the Impeller and Diffuser of Hydraulic Submersible Pump using Computational Fluid Dynamics and Artificial Neural Networks

2012 ◽  
pp. 456-474
Author(s):  
Juan Bernardo Sosa Coeto ◽  
Gustavo Urquiza Beltrán ◽  
Juan Carlos García Castrejon ◽  
Laura Lilia Castro Gómez ◽  
Marcelo Reggio
Keyword(s):  
Fluid Dynamics ◽  
Neural Networks ◽  
Computational Fluid Dynamics ◽  
Artificial Neural Networks ◽  
Impeller Speed ◽  
Design Stage ◽  
Submersible Pump ◽  
Pump Performance ◽  
Mathematical Relation ◽  
Artificial Neural

Overall performance of hydraulic submersible pump is strongly linked to its geometry, impeller speed and physical properties of the fluid to be pumped. During the design stage, given a fluid and an impeller speed, the pump blades profiles and the diffuser shape has to be determined in order to achieve maximum power and efficiency. Using Computational Fluid Dynamics (CFD) to calculate pressure and velocity fields, inside the diffuser and impeller of pump, represents a great advantage to find regions where the behavior of fluid dynamics could be adverse to the pump performance. Several trials can be run using CFD with different blade profiles and different shapes and dimensions of diffuser to calculate the effect of them over the pump performance, trying to find an optimum value. However the optimum impeller and diffuser would never be obtained using lonely CFD computations, by this means are necessary the application of Artificial Neural Networks, which was used to find a mathematical relation between these components (diffusers and blades) and the hydraulic head obtained by CFD calculations. In the present chapter artificial neural network algorithms are used in combinations with CFD computations to reach an optimum in the pumps performance.

scholarly journals Artificial Neural Networks Investigation of Indentation Force Effects on Nano- and Microhardness of Dual Phase Steels

2014 ◽  
Vol 2014 ◽  
pp. 1-11
Author(s):  
A. Fotovati ◽  
J. Kadkhodapour ◽  
S. Schmauder
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Volume Fraction ◽  
Nanoindentation Test ◽  
Dual Phase ◽  
Test Results ◽  
Indentation Force ◽  
Input Parameters ◽  
Artificial Neural ◽  
Selection Of

Nanoindentation test results on different grain sizes of dual phase (DP) steels are used to train artificial neural networks (ANNs). With selection of ferrite and martensite grain size, martensite volume fraction (MVF), and indentation force as input and microhardness, ferrite, and martensite nanohardness as outputs, six different ANNs are trained according to normalized datasets to predict hardness and their tolerances. A graphical user interface (GUI) is developed for a better investigation of the trained ANN prediction. The response of the ANN is analyzed in five case studies. In each case the variation of two input parameters on the output is analyzed when the other input parameters are kept constant. Reliable and reasonable results of ANN predictions are achieved in each case.

scholarly journals Fatigue Life Predictions of Metal Matrix Composites Using Artificial Neural Networks

2014 ◽  
Vol 59 (1) ◽  
pp. 97-103 ◽  
Author(s):  
I. Uygur ◽  
A. Cicek ◽  
E. Toklu ◽  
R. Kara ◽  
S. Saridemir
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Fatigue Life ◽  
Metal Matrix Composites ◽  
Metal Matrix ◽  
Volume Fraction ◽  
Matrix Composites ◽  
R Ratio ◽  
Artificial Neural ◽  
Life Predictions

Abstract In this study, fatigue life predictions for the various metal matrix composites, R ratios, notch geometries, and different temperatures have been performed by using artificial neural networks (ANN) approach. Input parameters of the model comprise various materials (M), such as particle size and volume fraction of reinforcement, stress concentration factor (Kt), R ratio (R), peak stress (S), temperatures (T), whereas, output of the ANN model consist of number of failure cycles. ANN controller was trained with Levenberg-Marquardt (LM) learning algorithm. The tested actual data and predicted data were simulated by a computer program developed on MATLAB platform. It is shown that the model provides intimate fatigue life estimations compared with actual tested data.

Sign in / Sign up

Export Citation Format

Share Document