Experimental measurement and modeling of saturated reservoir oil viscosity

Hemmati-Sarapardeh, Abdolhossein; Majidi, Seyed-Mohammad-Javad; Mahmoudi, Behnam; Ramazani, Ahmad; Mohammadi, Amir H.

doi:10.1007/s11814-014-0033-3

Cited by 44 publications

(19 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The dataset should be divided randomly into three aforementioned subsets (training, validation and testing) such that data points are distributed homogeneously and different operating conditions are covered in each subset [25,26]. Then, the optimal configuration should be found by changing the number of neurons in the single hidden layer.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Using an artificial neural network to predict carbon dioxide compressibility factor at high pressure and temperature

Mohagheghian

Zafarian-Rigaki

Motamedi-Ghahfarrokhi

et al. 2015

Korean J. Chem. Eng.

Self Cite

View full text Add to dashboard Cite

Carbon dioxide injection, which is widely used as an enhanced oil recovery (EOR) method, has the potential of being coupled with CO 2 sequestration and reducing the emission of greenhouse gas. Hence, knowing the compressibility factor of carbon dioxide is of a vital significance. Compressibility factor (Z-factor) is traditionally measured through time consuming, expensive and cumbersome experiments. Hence, developing a fast, robust and accurate model for its estimation is necessary. In this study, a new reliable model on the basis of feed forward artificial neural networks is presented to predict CO 2 compressibility factor. Reduced temperature and pressure were selected as the input parameters of the proposed model. To evaluate and compare the results of the developed model with pre-existing models, both statistical and graphical error analyses were employed. The results indicated that the proposed model is more reliable and accurate compared to pre-existing models in a wide range of temperature (up to 1,273.15 K) and pressure (up to 140 MPa). Furthermore, by employing the relevancy factor, the effect of pressure and temprature on the Z-factor of CO 2 was compared for below and above the critical pressure of CO 2 , and the physcially expected trends were observed. Finally, to identify the probable outliers and applicability domain of the proposed ANN model, both numerical and graphical techniques based on Leverage approach were performed. The results illustrated that only 1.75% of the experimental data points were located out of the applicability domain of the proposed model. As a result, the developed model is reliable for the prediction of CO 2 compressibility factor.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Using an artificial neural network to predict carbon dioxide compressibility factor at high pressure and temperature

Mohagheghian

Zafarian-Rigaki

Motamedi-Ghahfarrokhi

et al. 2015

Korean J. Chem. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The neural networks developed had a correlation coefficient of 0.99 and performed better than existing empirical correlations [3], [4]. Similar studies with neural networks to predict viscosity of Iranian oils [5]- [7] and Omani oils [8] have shown to perform better than existing correlations. Besides this the entire viscosity curves have also been shown to be accurately predicted for Canadian oilfields using neural networks and SVM [9] thereby establishing the reliable use of data mining techniques to predict crude oil viscosity.…”

Section: Literature Reviewmentioning

confidence: 99%

Bagging Ensemble Model for Prediction of Dead Oil Viscosity

Gulyani¹,

Kumar²,

Fathima³

2017

IJCEA

View full text Add to dashboard Cite

Abstract-Dead oil viscosity is a critical design factor for oilfields and refineries. From available literature, crude oil viscosity is found to be a strong function of pressure, temperature, bubble-point pressure, gas-oil ratio, gas gravity, and oil gravity. Oil viscosity is generally determined from laboratory experiments and empirically derived correlations.Reliable measurements of dead oil viscosity are difficult to obtain due to lack of lab equipment or liquid samples. Based on API oil gravity & temperature, various correlations have been used to predict dead oil viscosity. In addition to correlations, recently data mining techniques like Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been used to predict petroleum viscosity. The aim of this paper is to introduce the ensemble model of bagging as an important data mining technique to predict dead oil viscosity. The ensemble model predicted the viscosity accurately with a correlation coefficient of 0.99, an accuracy that is comparable to that of ANN as found in literature. It was also observed that bagging lowered the relative error of the base classifier (ANN) from 10% to about 8%, thereby stabilizing the ANN while retaining its accuracy.

show abstract

“…In fact, viscosity plays a key role in simulation and prediction of different oil production operations. [15][16][17] Therefore, it is necessary to have a better understanding of the viscosity of water-in-oil or oil-in-water emulsions which contain fine solids.…”

Section: Introductionmentioning

confidence: 99%

Towards a mechanistic understanding of rheological behaviour of water-in-oil emulsion: Roles of nanoparticles, water volume fraction and aging time

Pajouhandeh¹,

Kavousi²,

Schaffie³

et al. 2016

S.Afr.j.chem.

View full text Add to dashboard Cite

The viscosity of water-oil emulsions plays an important role in oil production and transportation. The objective of this study was to improve the basic understanding of the influence of nanoparticles on the viscosity of water-in-oil emulsions. Using crude oil and different industrial nanomaterials, the droplet size distribution, droplet mean size, and rheological models of emulsions were investigated. Experimental results show that the addition of nanoparticles increases the crude oil viscosity; however, the Newtonian flow behaviour of oil is not affected by nanoparticles. It is observed that the viscosity of crude oil increased from 36.5 to 49 cP when the nanoparticle concentration was elevated from 0 to 0.1 wt%. From the results of rheological experiments, it can be concluded that the influence of nanoparticles on the emulsion viscosity is mainly affected by the type and amount of nanoparticles, water/oil-ratio and aging time. Mean droplet diameter decreased from 5.68 to 4.11 micrometre when 0.1 wt% nanoparticles were added to emulsion. The results also suggest that the properties of stabilized water-in-oil emulsions are significantly time-dependent, and the droplet size and viscosity of emulsions is reduced by time. Most of previously published correlations have huge errors and could not precisely predict the apparent viscosities of non-solid stabilized and solid-stabilized emulsions. None of the previously utilized equations did ever consider the effect of added solids to the emulsion.

show abstract

Experimental measurement and modeling of saturated reservoir oil viscosity

Cited by 44 publications

References 42 publications

Using an artificial neural network to predict carbon dioxide compressibility factor at high pressure and temperature

Using an artificial neural network to predict carbon dioxide compressibility factor at high pressure and temperature

Bagging Ensemble Model for Prediction of Dead Oil Viscosity

Towards a mechanistic understanding of rheological behaviour of water-in-oil emulsion: Roles of nanoparticles, water volume fraction and aging time

Contact Info

Product

Resources

About