Designing a neural network for closed thermosyphon with nanofluid using a genetic algorithm

Salehi, H.; Heris, Saeed Zeinali; Salooki, Mahdi Koolivand; Noei, S H

doi:10.1590/s0104-66322011000100017

Cited by 50 publications

(17 citation statements)

References 27 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analyzes of variance of means were conducted using Duncan multiple tests. The feed-forward neural networks are the most popular architectures due to their structural flexibility and good representational capabilities (Salehi et al, 2011). Any ANN model contains an input layer, an output layer and one or more hidden layers.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Modelling and analysis of compressive strength properties of parboiled paddy and milled rice

Nasirahmadi¹,

Abbaspour‐Fard²,

Emadi³

et al. 2014

International Agrophysics

View full text Add to dashboard Cite

A b s t r a c t. The present investigation deals with analyzing the compressive strength properties of two varieties (Tarom and Fajr) of parboiled paddy and milled rice including: ultimate stress, modulus of elasticity, rupture force and rupture energy. Combined artificial neural network and genetic algorithm were also applied to model these properties. The parboiled samples were prepared with three soaking temperatures (25, 50 and 75°C) and three steaming times (10, 15 and 20 min). The samples were then dried to final moisture contents of 8, 10 and 12% (w.b.). In general, Tarom variety had higher compressive strength properties for paddy and milled rice than Fajr variety. With increase in steaming time from 10 to 20 min, all mentioned properties increased significantly, whereas these properties were decreased with increasing moisture content from 8 to 12% (w.b.). Coupled artificial neural network and genetic algorithm model with one hidden layer, three inputs (soaking temperature, steaming time and moisture content), was developed to predict the compressive strength properties as model outputs. Results indicated that this model could predict these properties with high correlation and low mean squared error.K e y w o r d s: artificial neural network, genetic algorithm, paddy, milled rice INTRODUCTION Rice (Oryza sativa L.) is the principal food cereal in the world and it is the main food of over half of the world population (Razavi and Farahmandfar, 2008). The majority of Iranian rice (75%) is grown in Mazandaran and Guilan provinces (Zareiforoush et al., 2010). The production rate is still far from the country rice self-sufficiency. Increasing the grain severity and hence reducing the processing losses could be a possible way of compenzation for the increasing demand. The primary step in rice processing is dehusking of paddy, which results in brown rice. Polishing or removing of bran to yield white rice is the second step. Knowledge of the compressive strength properties of rice is important in the design of milling equipment to predict their cracking behaviour and to minimize the losses during handling, drying, cleaning and milling processes. For this reason, extensive studies have been done in this area, that would be reviewed here. Shitanda et al. (2001) explored the physical and mechanical properties of paddy and rice. They showed that shortgrain rice was harder than long-grain variety and had less broken grain. They noted that husking characteristics of rice are related to shape and size of rice. Cao et al. (2004) explored the effect of moisture content on some mechanical properties of brown rice. They showed that moisture content has a significant effect on mechanical properties ie compressive strength and tensile strength decreased with increasing moisture content. Corrêa et al. (2007) explored mechanical behaviour of grains in rice processing. They showed that compressive force was significantly affected by processing. Zareiforoush et al. (2010) investigated the mechanical properties of two rice varieti...

show abstract

Section: Methodsmentioning

confidence: 99%

“…Recently the GA method has been widely used for finding the best topology and initial parameters of ANN to obtain good training process (Goni et al, 2008;Salehi et al, 2011). Consequently, GA was employed for initializing of mass and bias.…”

Section: Methodsmentioning

confidence: 99%

Modelling and analysis of compressive strength properties of parboiled paddy and milled rice

Nasirahmadi¹,

Abbaspour‐Fard²,

Emadi³

et al. 2014

International Agrophysics

View full text Add to dashboard Cite

show abstract

“…GA has been used to optimize the ANN parameters namely: learning rate, momentum coefficient, Activation function, Number of hidden layers and number of nodes for worker assignment into Virtual Manufacturing Cells(VMC) application [17]. GA-ANN model has been experimented for of study of the heat transport characteristics of a nanofluid thermosyphon in a magnetic field where, GA is used to optimize the number of neurons in the hidden layer, the coefficient of the learning rate and the momentumof ANN [18].…”

Section: The Hybrid Model Of Ga and Bpnmentioning

confidence: 99%

Application of Genetic Algorithm Optimized Neural Network Connection Weights for Medical Diagnosis of PIMA Indians Diabetes

Karegowda¹,

Manjunath²,

Jayaram³

2011

IJSC

144

View full text Add to dashboard Cite

Neural Networks are one of many data mining analytical tools that can be utilized to make predictions for medical data. Model selection for a neural network entails various factors such as selection of the optimal number of hidden nodes, selection of the relevant input variables and selection of optimal connection weights. This paper presents the application of hybrid model that integrates Genetic Algorithm and Back

show abstract

“…The nanofluids are expected to have better thermophysical properties compared to conventional heat transfer fluids (Zeinali Heris et al, 2007;Das et al, 2008;Kazemi-Beydokhti et al, 2013). Long-term stability and thermal conductivity of nanofluids are important factors that have been widely investigated by many researchers for copper, aluminum, and titania nanoparticles with their oxides and carbon nanotubes (Murshed et al, 2005;Eastman, 2001;Hwang, 2006;Das et al, 2003a;Jiang and Wang, 2010;Lee et al, 1999;Salehi et al, 2011;Wang and Mujumdar, 2008(a,b); Molana and Banooni, 2013).…”

Section: Introductionmentioning

confidence: 99%

PREDICTION OF STABILITY AND THERMAL CONDUCTIVITY OF SnO2NANOFLUID VIA STATISTICAL METHOD AND AN ARTIFICIAL NEURAL NETWORK

Kazemi‐Beydokhti

Namaghi

Asgarkhani

et al. 2015

Braz. J. Chem. Eng.

Self Cite

View full text Add to dashboard Cite

-Central composite rotatable design (CCRD) and artificial neural networks (ANN) have been applied to optimize the performance of nanofluid systems. In this regard, the performance was evaluated by measuring the stability and thermal conductivity ratio based on the critical independent variables such as temperature, particle volume fraction and the pH of the solution. A total of 20 experiments were accomplished for the construction of second-order polynomial equations for both target outputs. All the influential factors, their mutual effects and their quadratic terms were statistically validated by analysis of variance (ANOVA). According to the results, the predicted values were in reasonable agreement with the experimental data as more than 96% and 95% of the variation could be predicted by the respective models for zeta potential and thermal conductivity ratio. Also, ANN proved to be a very promising method in comparison with CCD for the purpose of process simulation due to the complexity involved in generalization of the nanofluid system.

show abstract

Designing a neural network for closed thermosyphon with nanofluid using a genetic algorithm

Cited by 50 publications

References 27 publications

Modelling and analysis of compressive strength properties of parboiled paddy and milled rice

Modelling and analysis of compressive strength properties of parboiled paddy and milled rice

Application of Genetic Algorithm Optimized Neural Network Connection Weights for Medical Diagnosis of PIMA Indians Diabetes

PREDICTION OF STABILITY AND THERMAL CONDUCTIVITY OF SnO2NANOFLUID VIA STATISTICAL METHOD AND AN ARTIFICIAL NEURAL NETWORK

Contact Info

Product

Resources

About