A Novel Correlation for Prediction of Gas Viscosity

Sanaei, Alireza; Yousefi, Seyed Hamidreza; Naseri, Ali; Khishvand, Mahdi

doi:10.1080/15567036.2011.601798

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental methods are typically not cost-effective and time-consuming. The emergence of artificial intelligence attracted several researchers since this approach is capable of dealing with prior challenges in gas viscosity determination. , Abooali and Khamehchi developed a method that was a function of pseudo-reduced temperature, pseudo-reduced pressure, apparent molecular weight, and gas density to predict natural gas dynamics viscosity by operating the genetic program on a database including 1938 data points. Deumah et al examined the efficiency of four different models, namely, multi-linear regression (MLR), decision tree (DT), random forest (RF), and K-nearest neighbors (KNN), to estimate the gas viscosity of a specific gas field.…”

Section: Introductionmentioning

confidence: 99%

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Zheng¹,

Mahmoudzadeh

Amiri-Ramsheh

et al. 2023

ACS Omega

View full text Add to dashboard Cite

Carbon dioxide (CO 2 ) has an essential role in most enhanced oil recovery (EOR) methods in the oil industry. Oil swelling and viscosity reduction are the dominant mechanisms in an immiscible CO 2 -EOR process. Besides numerous CO 2 applications in EOR, most oil reservoirs do not have access to natural CO 2 , and capturing it from flue gas and other sources is costly. Flue gases are available in huge quantities at a significantly lower price and can be considered economically viable agents for EOR operations. In this work, four powerful machine learning algorithms, namely, extra tree (ET), random forest (RF), gradient boosting (GBoost), and light gradient boosted machine (LightGBM) were utilized to accurately estimate the viscosity of CO 2 −N 2 mixtures. To this aim, a databank was employed, containing 3036 data points over wide ranges of pressures and temperatures. Temperature, pressure, and CO 2 mole fraction were applied as input parameters, and the viscosity of the CO 2 −N 2 mixture was the output. The RF smart model had the highest precision with the lowest average absolute percent relative error (AAPRE) of 1.58%, root mean square error (RMSE) of 2.221, and determination coefficient (R 2 ) of 0.9993. The trend analysis showed that the RF model could precisely predict the real physical behavior of the CO 2 −N 2 viscosity variation. Finally, the outlier detection was performed using the leverage approach to demonstrate the validity of the utilized databank and the applicability area of the developed RF model. Accordingly, nearly 96% of the data points seemed to be dependable and valid, and the rest of them were located in the suspected and out-of-leverage data zones. 22

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Zheng¹,

Mahmoudzadeh

Amiri-Ramsheh

et al. 2023

ACS Omega

View full text Add to dashboard Cite

show abstract

“…Although most of these analytical models have been developed for production of oil and gas, they can be adapted to investigate the thermal behavior of injection fluids. Several correlations have also been developed to predict CO 2 properties under different temperature and pressure conditions . If the temperature distribution of injected CO 2 from the wellhead to the reservoir is properly modeled, the effect of temperature changes around the wellbore injection inlet on CO 2 injectivity can be investigated.…”

Section: Introductionmentioning

confidence: 99%

“…Several correlations have also been developed to predict CO 2 properties under different temperature and pressure conditions. [38][39][40] If the temperature distribution of injected CO 2 from the wellhead to the reservoir is properly modeled, the effect of temperature changes around the wellbore injection inlet on CO 2 injectivity can be investigated.…”

Section: Introductionmentioning

confidence: 99%

Theoretical modeling of the effect of temperature on CO₂ injectivity in deep saline formations

et al. 2020

View full text Add to dashboard Cite

Well injectivity and storage capacity defines the storage potential of a CO2 capture, utilization, and storage (CCUS) facility. Formation temperature has high impact on the phase behavior and flow properties of CO2 such as density and viscosity. The effect of temperature on CO2 injectivity, especially in the wellbore injection inlet, is not well understood. We investigated the thermal behavior of CO2 from the wellhead to the reservoir using simple theoretical models that capture the major heat transfer mechanisms. The effect of CO2 injection flow rate and injection time on the temperature of CO2 were studied. We found that for the same initial CO2 injection temperature and formation intake temperature, the injected CO2 in the well is cooler than the surrounding formation from the wellhead to the bottomhole. The temperature difference increased with increasing injection flow rate and injection time. The results show that although CO2 may attain supercritical state at bottomhole, the temperature difference between CO2 in the wellbore and the reservoir could be significant. The results also suggest that CO2 could attain thermal equilibrium with the reservoir at a flow distance of about 600 ft into the formation depending on the injection flow rate and reservoir temperature. The thermal disequilibrium of CO2 in the wellbore vicinity where fluxes are also high could affect CO2 injectivity and the mobility of CO2 during CCUS and enhanced oil recovery (EOR) operations. The present findings provide vital understanding of the effect of thermal instability on CO2 injectivity especially in the wellbore injection inlet. © 2020 Society of Chemical Industry and John Wiley & Sons, Ltd.

show abstract

Hybrid approach for gas viscosity in Yemeni oil fields

Al-Gathe,

Baarimah,

Al-Khudafi

et al. 2023

Earth Sci Inform

View full text Add to dashboard Cite

The estimation of a gas viscosity experimentally is often difficult. So, accurate determination of gas viscosity has been the main challenge in a gas reservoir development. There are many correlations to estimate this property. Often time, the results of these correlations do not agree with experimental data, thereby causing a considerable amount of error. The difficulty of these correlations can be propagated simply by tuning against some experimental data using artificial intelligent model. Currently, the achievements of artificial neural networks (ANN) techniques alone to predict gas viscosity open the door to use the hybrid system. In this model, the Particle Swarm Optimization (PSO) algorithm is employed to search for optimal connection weighs and thresholds for the neural networks (NN), then the back-propagation learning rule and training algorithm is used to adjust the final weights. A total of about 868 data points obtained from the laboratory measurements of gas viscosity were used. The data include measured gas viscosity, specific gas gravity, temperature, pressure, molecular weight, pseudo-critical temperature and pressure and non-hydrocarbon components (H2S, CO2, and N2). The performance of the PSONN model is compared with performance of ANN and other empirical model to show the most general and accurate model for predicting gas viscosity. From the results of this study, we found that the PSONN model is more reliable and accurate with the absolute present relative (APRE) error and mean square error (RMS) of 2.76 and 5.49 respectively.

show abstract

A Novel Correlation for Prediction of Gas Viscosity

Cited by 6 publications

References 9 publications

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Theoretical modeling of the effect of temperature on CO₂ injectivity in deep saline formations

Hybrid approach for gas viscosity in Yemeni oil fields

Contact Info

Product

Resources

About

A Novel Correlation for Prediction of Gas Viscosity

Cited by 6 publications

References 9 publications

Modeling Viscosity of CO2–N2 Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Modeling Viscosity of CO2–N2 Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Theoretical modeling of the effect of temperature on CO2 injectivity in deep saline formations

Hybrid approach for gas viscosity in Yemeni oil fields

Contact Info

Product

Resources

About

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Theoretical modeling of the effect of temperature on CO₂ injectivity in deep saline formations