scholarly journals Validation and Optimization of Thermophysical Properties for Thermal Conductivity and Viscosity of Nanofluid Engine Oil using Neural Network

2020 ◽  
Vol 3 (1) ◽  
pp. 53-60
Author(s):  
Amin Moslemi Petrudi ◽  
Masoud Rahmani
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Thermal Conductivity ◽  
Optimization Algorithm ◽  
Thermophysical Properties ◽  
Volume Fraction ◽  
Engine Oil ◽  
Coefficient Of Determination ◽  
Neural Network Modeling ◽  
Nsga Ii

In this study, the thermophysical properties of thermal conductivity and viscosity of a motor oil nanofluid were investigated using experimental data and artificial neural network. NSGA II optimization algorithm was used to maximize thermal conductivity and minimum viscosity with changes in temperature and volume fraction of nanofluids. Also, to obtain the viscosity and thermal conductivity values in terms of nanofluid temperature and volume fraction with 174 experimental data, neural network modeling was performed. Input data include temperature and volume fraction, and output is viscosity and thermal conductivity. Various indices such as R squared and Mean Square Error (MSE) have been used to evaluate the accuracy of modeling in the prediction of viscosity and thermal conductivity of nanofluids. The coefficient of determination R squared is 0.9989 indicating acceptable agreement with the experimental data. In order to optimize and finally results as an objective function, the optimization algorithm is presented and the Parto front and its corresponding optimum points are presented where the maximum optimization results of thermal conductivity and viscosity occur at 1% volume fraction.

scholarly journals Multilayer method for solving a problem of metals rupture under creep conditions

2019 ◽  
Vol 23 (Suppl. 2) ◽  
pp. 575-582 ◽  
Author(s):  
Evgenii Kuznetsov ◽  
Sergey Leonov ◽  
Dmitry Tarkhov ◽  
Alexander Vasilyev
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Parameter Identification ◽  
Uniaxial Tension ◽  
Network Modeling ◽  
Identification Problem ◽  
Neural Network Modeling ◽  
Creep Theory ◽  
Parameter Identification Problem ◽  
Kinetic Creep

The paper deals with a parameter identification problem for creep and fracture model. The system of ordinary differential equations of kinetic creep theory is applied for describing this model. As for solving the parameter identification problem, we proposed to use the technique of neural network modeling, as well as the multilayer approach. The procedures of neural network modeling and multilayer approximation constructing application is demonstrated by the example of finding parameters for uniaxial tension model for isotropic steel 45 specimens at creep conditions. The solution corresponding to the obtained parameters agrees well with theoretical strain-damage characteristics, experimental data, and results of other authors.

Experimental and Theoretical Studies of Thermophysical Properties of MgO-Water Nanofluid

2020 ◽  
Vol 1008 ◽  
pp. 47-52
Author(s):  
Abdallah Yousef Mohammed Ali ◽  
Ahmed Hassan El-Shazly ◽  
Marwa Farouk El-Kady ◽  
Hesham Ibrahim Elqady ◽  
Kholoud Madih ◽  
...  
Keyword(s):  
Thermal Conductivity ◽  
Thermophysical Properties ◽  
Volume Fraction ◽  
Sol Gel ◽  
Solid Volume Fraction ◽  
Ammonium Bromide ◽  
Distilled Water ◽  
Step Method ◽  
Mgo Nanoparticles ◽  
Cetyl Trimethyl Ammonium

Magnesium oxide (MgO) nanoparticles were synthesized using the sol-gel technique then characterized. Cetyl Trimethyl Ammonium Bromide (CTAB) surfactant was added to reduce Van der Waal forces among MgO nanoparticles and distilled water forming a stable nanofluid using two-step method with aid of ultrasound sonication. Pure distilled water and nanofluids with different volume fractions of 0.25, 0.5, 0.75, and 1% are used as working fluids. Thermophysical properties of prepared nanofluids were measured experimentally and determined theoretically. Effect of solid volume fraction on the thermophysical properties; including thermal conductivity, heat capacity, viscosity, and density of MgO-water nanofluids are discussed. Moreover, experimental results have been compared with the suitable correlations for MgO-water nanofluid. The findings show that thermal conductivity, viscosity, and density of nanofluid increases with increasing solid volume fraction.

Designing artificial neural network on thermal conductivity of Al2O3–water–EG (60–40 %) nanofluid using experimental data

2016 ◽  
Vol 126 (2) ◽  
pp. 837-843 ◽  
Author(s):  
Mohammad Hemmat Esfe ◽  
Mohammad Reza Hassani Ahangar ◽  
Davood Toghraie ◽  
Mohammad Hadi Hajmohammad ◽  
Hadi Rostamian ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Thermal Conductivity ◽  
Artificial Neural Network ◽  
Artificial Neural

scholarly journals Investigation of the Efficiency of Small-Scale NF/RO Seawater Desalination by Using Artificial Neural Network Modeling

2021 ◽  
Vol 16 (3) ◽  
pp. 239-299
Author(s):  
Asma Adda ◽  
Salah Bezari ◽  
Mohamed Salmi ◽  
Giulio Lorenzini ◽  
Maamar Laidi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Flow Rate ◽  
Coefficient Of Determination ◽  
Neural Network Modeling ◽  
Small Scale ◽  
Water Recovery ◽  
Seawater Desalination ◽  
Feed Forward Back Propagation ◽  
Artificial Neural

An attempt is conducted in this paper to develop an artificial neural network (ANN) model for predicting the efficiency of small-scale NF/RO seawater desalination, then applied to the simulation of permeate flow rate and water recovery. A feed-forward back-propagation neural network with the Levenberg-Marquardt learning algorithm is considered. The performance of ANN compared to the multiple linear regression (MLR) is based on the calculated value of the coefficient of determination (R2). For ANN, R2 permeate flow rate was 0.997, and R2 permeate water recovery was 0.999, and for MLR, R2 permeate flow rate was 0.508, and R2 permeate water recovery was 0.713. It was observed that ANN performed better than the MLR.

Application of artificial intelligence neural network modeling to predict the generation of domestic, commercial and construction wastes

2020 ◽  
pp. 0734242X2093518 ◽  
Author(s):  
Gulnur Coskuner ◽  
Majeed S Jassim ◽  
Metin Zontul ◽  
Seda Karateke
Keyword(s):  
Neural Network ◽  
Solid Waste ◽  
Mean Squared Error ◽  
Solid Waste Management ◽  
Management Strategies ◽  
Cost Effective ◽  
Coefficient Of Determination ◽  
Neural Network Modeling ◽  
Msw Management ◽  
Ann Models

Reliable prediction of municipal solid waste (MSW) generation rates is a significant element of planning and implementation of sustainable solid waste management strategies. In this study, the multi-layer perceptron artificial neural network (MLP-ANN) is applied to verify the prediction of annual generation rates of domestic, commercial and construction and demolition (C&D) wastes from the year 1997 to 2016 in Askar Landfill site in the Kingdom of Bahrain. The proposed robust predictive models incorporated selected explanatory variables to reflect the influence of social, demographical, economic, geographical and touristic factors upon waste generation rates (WGRs). The Mean Squared Error (MSE) and coefficient of determination ( R2) are used as performance indicators to evaluate effectiveness of the developed models. MLP-ANN models exhibited strong accuracy in predictions with high R2 and low MSE values. The R2 values for domestic, commercial and C&D wastes are 0.95, 0.99 and 0.91, respectively. Our results show that the developed MLP-ANN models are effective for the prediction of WGRs from different sources and could be considered as a cost-effective approach for planning integrated MSW management systems.

Sign in / Sign up

Export Citation Format

Share Document