Application of artificial neural networks for viscosity of crude oil-based nanofluids containing oxides nanoparticles

Derakhshanfard, Fahimeh; Mehralizadeh, Amir

doi:10.1016/j.petrol.2018.05.018

Cited by 22 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Templates are applied to inputs and a simple algorithm regulates the weight of combinations to get the desired result. After many exercises using a number of different templates, the neural network "learns" to recognize certain types of templates 29 . The programmer may not even know these templates precisely because the templates are analyzed by the neural network itself.…”

Section: Methodsmentioning

confidence: 99%

Intelligent modeling of rheological and thermophysical properties of nanoencapsulated PCM slurry

Jirandeh

Mohammadiun

et al. 2020

Heat Trans

View full text Add to dashboard Cite

Nanoencapsulated phase change material slurries (NPCMS) combine properties of carried fluid and phase change material (PCM). Usage of NPCMS instead of water as a working fluid has a lot of advantages in many industrial fields. The costly and time-consuming determination of thermophysical properties of NPCMS through the experimental analysis led the current investigations to use soft computing methods like correlating, artificial neural network (ANN), and ant colony optimization (ACO R ). In this study, the application of ANN, empirical correlations, and ACO R for modeling the thermophysical properties of NPCM slurry, which has been synthesized through a facile and eco-friendly procedure, has been investigated. PCM nanocapsules have been synthesized using a miniemulsion polymerization method. Nancapsules consist of AP-25 as core and a Styrene shell, which is modified with graphene oxide nanosheets as an extra protective screen.The morphology and thermal properties of nanocapsules were characterized and analyzed, respectively. Results revealed that minimum average particle-size values result in a melting latent heat of 146.8 J/g. In case of NPCM slurry, the results showed that the thermal conductivity of MPCS decreased with particle concentration for the temperatures below the melting point. The NPCMS can be considered a Newtonian fluid within the test region (shear rate > 200/seconds and mass fraction < 0.25). The ANN-ACO R model consists of two neurons in the input layer, six neurons in the hidden layer, and two neurons in the output layer. The input layer consists of two nodes (PCM concentration and temperature) that correspond to parameters found essential and sufficient for thermophysical properties prediction. Upon comparison, the results show that the presented model, which is a combination of the ACO R algorithm and an artificial neural network, is compatible with experimental work. K E Y W O R D SANN modeling, ant colony, phase change material, slurry, thermophysical properties

show abstract

Section: Methodsmentioning

confidence: 99%

Intelligent modeling of rheological and thermophysical properties of nanoencapsulated PCM slurry

Jirandeh

Mohammadiun

et al. 2020

Heat Trans

View full text Add to dashboard Cite

show abstract

“…The mean average relative error of the model was 2.48%. Since then, several other computer-aided data-driven models have been developed by considering different intelligent modeling approaches, including fuzzy C-means clustering-based adaptive neuro-fuzzy system (FCM-ANFIS), hybrid self-organizing polynomial neural networks (PNN) based on group method of data handling (GMDH), least-square support vector machine (LSSVM), radial basis function neural networks (RBF-NN), genetic algorithm-polynomial neural network (GA-PNN), multilayer perceptron neural networks (MLP-NNs), gene expression programming (GEP) [ 8 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ]. However, the most accurate model with a wide range of applicability for the prediction of viscosity of nanofluids was developed by Hemmati-Sarapardeh et al [ 1 ], based on a committee machine intelligent system (CMIS).…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment

et al. 2020

View full text Add to dashboard Cite

The process of selecting a nanofluid for a particular application requires determining the thermophysical properties of nanofluid, such as viscosity. However, the experimental measurement of nanofluid viscosity is expensive. Several closed-form formulas for calculating the viscosity have been proposed by scientists based on theoretical and empirical methods, but these methods produce inaccurate results. Recently, a machine learning model based on the combination of seven baselines, which is called the committee machine intelligent system (CMIS), was proposed to predict the viscosity of nanofluids. CMIS was applied on 3144 experimental data of relative viscosity of 42 different nanofluid systems based on five features (temperature, the viscosity of the base fluid, nanoparticle volume fraction, size, and density) and returned an average absolute relative error (AARE) of 4.036% on the test. In this work, eight models (on the same dataset as the one used in CMIS), including two multilayer perceptron (MLP), each with Nesterov accelerated adaptive moment (Nadam) optimizer; two MLP, each with three hidden layers and Adamax optimizer; a support vector regression (SVR) with radial basis function (RBF) kernel; a decision tree (DT); tree-based ensemble models, including random forest (RF) and extra tree (ET), were proposed. The performance of these models at different ranges of input variables was assessed and compared with the ones presented in the literature. Based on our result, all the eight suggested models outperformed the baselines used in the literature, and five of our presented models outperformed the CMIS, where two of them returned an AARE less than 3% on the test data. Besides, the physical validity of models was studied by examining the physically expected trends of nanofluid viscosity due to changing volume fraction.

show abstract

“…The GP has been used in many engineering applications due to its flexibility to model nonlinear complex patterns between dataset variables (MacKay 2005). The GP has been adopted in solving many engineering and real-life problems because of its ability to handle data in various forms and sizes (Akin et al 2008;Ali Ahmadi and Golshadi 2012;Asadisaghandi and Tahmasebi 2011;Ashoori et al 2010;Babakhani et al 2015;Derakhshanfard and Mehralizadeh 2018;Ebden 2008;Huang et al 2003;Iturrarán-Viveros and Molero 2013;Kelechukwu et al 2013;Riazi et al 2014;Sheremetov et al 2014;Vaferi et al 2014). A general sketch of the problem is presented in Fig.…”

Section: Introductionmentioning

confidence: 99%

Data-driven model for shear wave transit time prediction for formation evaluation

Onalo

Adedigba

Oloruntobi

et al. 2020

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Sonic well logs provide a cost-effective and efficient non-destructive tool for continuous dynamic evaluation of reservoir formations. In the exploration and production of oil and gas reservoirs, these sonic logs contain crucial information about the formation. However, shear sonic logs are not acquired in all oil and gas exploration wells. More so, many offset wells are not run with the most recent sonic logging tools capable of measuring both shear and compressional sonic transit times due to the relatively high costs of running such equipment. And in wells where they are deployed, they are run only over limited intervals of the formation. Such wells lack continuous shear wave transit time measurements along the formation. In this study, an exponential Gaussian process model is presented. The model accurately predicts the shear wave transit times in the formations which lack reliable shear wave transit time measurements. The proposed model is developed using an array of well logs, namely depth, density, porosity, gamma ray, and compressional transit time. A Monte Carlo simulation is used to quantify the proposed model uncertainty. The shear sonic transit time predictions are used to estimate some formation deformation properties, namely Young's modulus and Poisson's ratio of a reservoir formation. The results suggest that shear transit time can be represented and predicted by Gaussian-based process model with RMSE, R 2 , and MSE of 11.147, 0.99, and 124.6, respectively. The proposed model provides a reliable and cost-effective tool for oil and gas dynamic formation evaluation. The findings from this study can help for better understanding of shear transit times in formations which do not have multipole sonic logs or where data have been corrupted while logging in the Niger Delta. List of symbolsRHOB Bulk density log (g/cm 3 ) DTCO Compressional wave travel time (µs/ft) Δt c Compressional wave travel time (µs/ft) RESD Deep resistivity log (ohm m) PHIE Effective porosity log (m 3 /m 3 ) den Electron density porosity (g/cc) fl Fluid density (g/cc) , b Formation density (g/cc) Δt fl Formation fluid compressional wave travel time (µs/ft) Δt ma Formation matrix compressional wave travel time (µs/ft) GR min Gamma ray in clean sandstone GR min Gamma ray in shale GR Gamma ray log (gAPI) GR Gamma ray log reading ma Matrix density (g/cc) MAE Mean absolute error MPE Mean percentage error Δt log Measured compressional wave travel time (µs/ft) N Neutron porosity N,fl Neutron response of the matrix Poisson's Ratio Rock porosity Vsh Shale volume DTSM Shear wave travel time (µs/ft) Δt s Shear wave travel time (µs/ft) s Sonic porosity PHIT Total porosity log (m 3 /m 3 ) E Young's modulus (MPa)

show abstract

Application of artificial neural networks for viscosity of crude oil-based nanofluids containing oxides nanoparticles

Cited by 22 publications

References 27 publications

Intelligent modeling of rheological and thermophysical properties of nanoencapsulated PCM slurry

Intelligent modeling of rheological and thermophysical properties of nanoencapsulated PCM slurry

Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment

Data-driven model for shear wave transit time prediction for formation evaluation

Contact Info

Product

Resources

About