A Novel Empirical Correlation to Predict the Dew Point Pressure using Intelligent Algorithms

2019 ◽  
Author(s):  
Mohammad Rasheed Khan ◽  
Shams Kalam ◽  
Zeeshan Tariq ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Empirical Correlation ◽  
Dew Point ◽  
Intelligent Algorithms ◽  
Point Pressure ◽  
Dew Point Pressure

A Comparative Analysis of the Prediction of Gas Condensate Dew Point Pressure Using Advanced Machine Learning Algorithms

2021 ◽  
Author(s):  
Thitaree Lertliangchai ◽  
Birol Dindoruk ◽  
Ligang Lu ◽  
Xi Yang
Keyword(s):  
Machine Learning ◽  
Domain Knowledge ◽  
Compositional Data ◽  
Machine Learning Algorithms ◽  
Empirical Correlation ◽  
Dew Point ◽  
Pvt Data ◽  
Point Pressure ◽  
Input Variables ◽  
Dew Point Pressure

Abstract Dew point pressure (DPP) is a key variable that may be needed to predict the condensate to gas ratio behavior of a reservoir along with some production/completion related issues and calibrate/constrain the EOS models for integrated modeling. However, DPP is a challenging property in terms of its predictability. Recognizing the complexities, we present a state-of-the-art method for DPP prediction using advanced machine learning (ML) techniques. We compare the outcomes of our methodology with that of published empirical correlation-based approaches on two datasets with small sizes and different inputs. Our ML method noticeably outperforms the correlation-based predictors while also showing its flexibility and robustness even with small training datasets provided various classes of fluids are represented within the datasets. We have collected the condensate PVT data from public domain resources and GeoMark RFDBASE containing dew point pressure (the target variable), and the compositional data (mole percentage of each component), temperature, molecular weight (MW), MW and specific gravity (SG) of heptane plus as input variables. Using domain knowledge, before embarking the study, we have extensively checked the measurement quality and the outcomes using statistical techniques. We then apply advanced ML techniques to train predictive models with cross-validation to avoid overfitting the models to the small datasets. We compare our models against the best published DDP predictors with empirical correlation-based techniques. For fair comparisons, the correlation-based predictors are also trained using the underlying datasets. In order to improve the outcomes and using the generalized input data, pseudo-critical properties and artificial proxy features are also employed.

Determination of Bubble-Point and Dew-Point Pressure Without a Visual Cell

2014 ◽  
Author(s):  
R.. Hosein ◽  
R.. Mayrhoo ◽  
W. D. McCain
Keyword(s):  
Oil And Gas ◽  
Saturation Pressure ◽  
Volatile Oil ◽  
Phase Region ◽  
Gas Condensate ◽  
Dew Point ◽  
Bubble Point ◽  
Point Pressure ◽  
Dew Point Pressure

Abstract Bubble-point and dew-point pressures of oil and gas condensate reservoir fluids are used for planning the production profile of these reservoirs. Usually the best method for determination of these saturation pressures is by visual observation when a Constant Mass Expansion (CME) test is performed on a sample in a high pressure cell fitted with a glass window. In this test the cell pressure is reduced in steps and the pressure at which the first sign of gas bubbles is observed is recorded as bubble-point pressure for the oil samples and the first sign of liquid droplets is recorded as the dew-point pressure for the gas condensate samples. The experimental determination of saturation pressure especially for volatile oil and gas condensate require many small pressure reduction steps which make the observation method tedious, time consuming and expensive. In this study we have extended the Y-function which is often used to smooth out CME data for black oils below the bubble-point to determine saturation pressure of reservoir fluids. We started from the initial measured pressure and volume and by plotting log of the extended Y function which we call the YEXT function, with the corresponding pressure, two straight lines were obtained; one in the single phase region and the other in the two phase region. The point at which these two lines intersect is the saturation pressure. The differences between the saturation pressures determined by our proposed YEXT function method and the observation method was less than ± 4.0 % for the gas condensate, black oil and volatile oil samples studied. This extension of the Y function to determine dew-point and bubble-point pressures was not found elsewhere in the open literature. With this graphical method the determination of saturation pressures is less tedious and time consuming and expensive windowed cells are not required.

The Effect of Capillary Condensation on the Geomechanical and Acoustic Properties of Tight Formations: An Experimental Study

2021 ◽  
Author(s):  
Aamer Albannay ◽  
Binh Bui ◽  
Daisuke Katsuki
Keyword(s):  
Pore Pressure ◽  
Capillary Condensation ◽  
Pore Space ◽  
Dew Point ◽  
Acoustic Properties ◽  
Point Pressure ◽  
Tight Formations ◽  
Dew Point Pressure ◽  
Compressional Velocity

Abstract Capillary condensation is the condensation of the gas inside nano-pore space at a pressure lower than the bulk dew point pressure as the result of multilayer adsorption due to the high capillary pressure inside the small pore throat of unconventional rocks. The condensation of liquid in nano-pore space of rock changes its mechanical and acoustic properties. Acoustic properties variation due to capillary condensation provides us a tool to monitor phase change in reservoir as a result of nano-confinement as well as mapping the area where phase change occurs as well as characterize pore size distribution. This is particularly important for tight formations where confinement has a strong effect on phase behavior that is challenging to measure experimentally. Theoretical studies have examined the effects of capillary condensation; however, these findings have not been verified experimentally. The main objective of this study is to experimentally investigate the effect of capillary condensation on the mechanical and acoustic properties of shale samples. The mechanical and acoustic characterization of the samples was carried out experimentally using a state-of-the-art tri-axial facility at the Colorado School of Mines. The experimental set-up is capable of the simultaneous acquisition of coupled stress, strain, resistivity, acoustic and flow data. Carbon dioxide was used as the pore pressure fluid in these experiments. After a comprehensive characterization of shale samples, experiments were conducted by increasing the pore pressure until condensation occurs while monitoring the mechanical and acoustic properties of the sample to quantify the effect of capillary condensation on the mechanical and acoustic properties of the sample. Experimental data show a 5% increase in Young's Modulus as condensation occurs. This increase is attributed to the increase in pore stiffness as condensation occurs reinforcing the grain contact. An initial decrease in compressional velocity was observed as pore pressure increases before condensation occurs which is attributed to the expansion of the pore volume when pore pressure increases. After this initial decrease, compressional velocity slightly increases at a pressure around 750 - 800 psi which is close to the condensation pressure. We also observed a noticeable increase in shear velocity when capillary condensation occurs, this could be due to the immobility of the condensed liquid phase at the pore throats. The changes of geomechanical and acoustic signatures were observed at around 750 - 800 psi at 27°C, which is the dew point pressure of the fluid in the nano-pore space of the sample at this temperature. While the unconfined bulk dew point pressure of carbon dioxide at the same temperature is 977 psi. Hence, this study marks the first measurement of the dew point of fluid in nano-pore space and potentially leads to the construction of the phase envelope of fluid under confinement.

Predicting Dew Point Pressure: Using a Hybrid Intelligent Network

2014 ◽  
Vol 32 (24) ◽  
pp. 2969-2975 ◽  
Author(s):  
Sh. Ghassemzadeh ◽  
M. Schaffie ◽  
A. Sarrafi ◽  
M. Ranjbar
Keyword(s):  
Dew Point ◽  
Intelligent Network ◽  
Point Pressure ◽  
Dew Point Pressure

A New Correlation to Predict Dew Point Pressure in Wet Gas Reservoirs

2014 ◽  
Vol 39 (11) ◽  
pp. 8341-8346 ◽  
Author(s):  
Ehsan Ghanaatpisheh ◽  
Hosein Vahdani ◽  
Kamal Bolandparvaz Jahromi
Keyword(s):  
Dew Point ◽  
Gas Reservoirs ◽  
New Correlation ◽  
Wet Gas ◽  
Point Pressure ◽  
Dew Point Pressure
Sign in / Sign up

Export Citation Format

Share Document