Prediction of thermal conductivity of alumina water-based nanofluids by artificial neural networks

Ariana, Mohammad Amin; Vaferi, Behzad; Karimi, Gholamreza

doi:10.1016/j.powtec.2015.03.005

Cited by 140 publications

(45 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ÇKA'da aynı katmanın nöronları arasında herhangi bir bağlantı yoktur. Girdi ve çıktı nöronlarının sayısı sırasıyla bağımsız (girdi) ve bağımlı (çıktı) değişkenlerin sayısına eşittir [29]. Ancak, gizli katmanın ve nöronlarının sayıları ile ilgili özel bir kural yoktur.…”

Section: Yapay Si̇ni̇r Ağlari (Artificial Neuralunclassified

Odunun Yüzey Pürüzlülüğünün ve Adezyon Direncinin Yapay Sinir Ağları ile Tahmini

Özşahin

Singer

2019

Politeknik Dergisi

View full text Add to dashboard Cite

ÖZMobilya ve dekorasyon elemanlarının üretiminde kullanılan ağaç malzemelerin yüzey pürüzlülüğünün ve adezyon direncinin belirlenmesi, nihai ürünün kalitesinin değerlendirilmesi bakımından çok önemlidir. Bu makalede ilk olarak, odun türü, kesme yönü ve zımpara kağıdı türünün yüzey pürüzlülüğü üzerine etkilerini incelemek için yapay sinir ağı (YSA) ile yüzey pürüzlülüğü tahmin modeli geliştirilmiştir. Daha sonra, vernik türü, odun türü, kesme yönü ve yüzey pürüzlülüğünün adezyon direnci üzerine etkileri YSA ile geliştirilen adezyon direnci tahmin modeliyle araştırılmıştır. En iyi performansa sahip tahmin modelleri istatistiksel ve grafiksel karşılaştırmalar yoluyla belirlenmiştir. YSA modellerinin kabul edilebilir sapmalarla oldukça tatmin edici neticeler elde ettiği görülmüştür. Sonuç olarak bu çalışmanın bulguları, deneysel araştırmalar için zaman, enerji ve maliyeti azaltmak amacıyla mobilya ve dekorasyon endüstrisinde etkili bir şekilde uygulanabilir. ABSTRACTDetermining the surface roughness and adhesion strength of wood materials used in the manufacturing of furniture and decoration elements is very crucial in terms of evaluating the quality of the final product. In this article, firstly, the surface roughness prediction model was developed with the artificial neural network (ANN) to examine the effects of wood species, cutting direction and sandpaper type on surface roughness. Then, the effects of varnish type, wood species, cutting direction and surface roughness on adhesion strength were investigated with the adhesion strength prediction model developed with ANN. The prediction models with the best performance were determined by statistical and graphical comparisons. It has been observed that ANN models yielded very satisfactory results with acceptable deviations. As a result, the findings of this study could be employed effectively into the furniture and decoration industry to reduce time, energy and cost for empirical investigations.

show abstract

Section: Yapay Si̇ni̇r Ağlari (Artificial Neuralunclassified

Odunun Yüzey Pürüzlülüğünün ve Adezyon Direncinin Yapay Sinir Ağları ile Tahmini

Özşahin

Singer

2019

Politeknik Dergisi

View full text Add to dashboard Cite

show abstract

“…Among various types of ANN approaches, the multi-layer perceptron (MLP) networks have found high popularity for function approximation. 41,42 MLP neural network have proved itself through approximation of any unknown nonlinear function without prior knowledge of the distribution of the input data. 43,44 In the present work, the MLP neural network, with strictly feed-forward flow of signals, as shown in Fig.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Toward artificial intelligence-based modeling of vapor liquid equilibria of carbon dioxide and refrigerant binary systems

et al. 2018

View full text Add to dashboard Cite

The objective of this study is to design and validate a highly accurate approach based on an artificial neural network (ANN) to predict both bubble and dew point pressures of various CO 2-refrigerant binary systems in the temperature range of 263.15-367.30 K and pressure of 0.18-9.09 MPa. 503 Experimental vapour-liquid equilibria (VLE) data of nine different CO 2-refrigerant binary mixtures were used for preparation, validation and testing of ANN model. The developed ANN model correlates bubble and dew point pressure to reduced temperature, critical pressure, acentric factor of refrigerant, and distibution of CO 2 between the vapour and liquid phases. Trial and error procedure reveals that a three-layer neural network with fourteen neurons in the hidden layer is able to predict the pressure with mean square error (MSE), average absolute relative deviation (AARD), root mean square error (RMSE), and correlation coefficient (R 2) of 0.0133, 2.79 %, 0.1153 and 0.99836, respectively. The results confirmed that the ANN model can accurately apply for predicting the VLE data of different binary CO 2-refrigerant systems.

show abstract

“…Fifteen nanofluids with different types of nanoparticles and base fluids were used to develop the MLP model using experimental data reported in the literature. Ariana et al [40] presented a study to develop and validate MLP model to estimate the TCR of alumina/water nanofluids as a function of volume fraction, temperature and diameter of the nanoparticle. Papari et al [41] employed MLP model to estimate TCR of nanofluids consisting of multi-walled carbon nanotubes suspended in different base fluids.…”

Section: Introductionmentioning

confidence: 99%

An artificial neural network based approach for prediction the thermal conductivity of nanofluids

et al. 2020

View full text Add to dashboard Cite

Thermal conductivity is an important thermophysical property of nanofluids in many practical heat transfer applications. In this study, a novel approach is proposed to predict the thermal conductivity of nanofluids under multiple operating parameters. The proposed approach may be extended to be used to other thermophysical properties of nanofluids. The Kohonen's self-organizing maps (SOM), as an unsupervised artificial neural network (ANN), is used to provide an accurate prediction tool for the problem in hand. Furthermore, SOM, similar to any ANN-based approach, can handle nonlinear and complex input-output relationships with high generalization ability. Comparison of the SOM predicted values with corresponding available theoretical results as well as experimental data implies high prediction capability of the developed approach. The proposed approach was utilized to predict thermal conductivity ratio of oxide (Al 2 O 3 , CuO and TiO 2)/ water nanofluids under various operating conditions (nanoparticle size, temperature, and nanoparticle volume fraction). Keywords Nanofluids • Thermal conductivity • Artificial neural networks • Self-organizing maps List of symbols k Thermal conductivity (W/(m K)) T Temperature (°C) x Input vector w j Synaptic weight vector h ki Topological neighborhood d ik Euclidean distance r Thermal conductivity ratio Effective width of the topological neighborhood r Position vector Time constant P Projection matrix I g Identity matrix Volume fraction (%)

show abstract

Prediction of thermal conductivity of alumina water-based nanofluids by artificial neural networks

Cited by 140 publications

References 44 publications

Odunun Yüzey Pürüzlülüğünün ve Adezyon Direncinin Yapay Sinir Ağları ile Tahmini

Odunun Yüzey Pürüzlülüğünün ve Adezyon Direncinin Yapay Sinir Ağları ile Tahmini

Toward artificial intelligence-based modeling of vapor liquid equilibria of carbon dioxide and refrigerant binary systems

An artificial neural network based approach for prediction the thermal conductivity of nanofluids

Contact Info

Product

Resources

About