Prediction of Bubble Point Pressure Using Artificial Intelligence AI Techniques

Alakbari, Fahd Saeed; Elkatatny, Salaheldin; Baarimah, Salem O.

doi:10.2118/184208-ms

Cited by 35 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2012, Al-Marhoun et al (2012) presented an AI model for predicting crude oil viscosity. Alakbari et al (2016) also used different artificial intelligence techniques for the prediction of bubble-point pressure (P bp -). Elkatatny et al (2016) used the ANN technique for real-time prediction of drilling fluid rheological properties.…”

Section: Applications Of Artificial Intelligence In Petroleum Industrymentioning

confidence: 99%

Cutting concentration prediction in horizontal and deviated wells using artificial intelligence techniques

Al-Azani

Elkatatny

Ali

et al. 2019

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

Improper hole cleaning or drilled-cutting transportation impacts drilling operations. To illustrate, inefficient cleaning of the wellbore can lead to many drilling problems such as low drilling rate (i.e. low ROP), early bit wear and, in the severe cases, a complete loss of the well due to stuck pipe. To understand efficiency in cutting transport in drilling and to provide solutions for the problem, many studies have been conducted. In all cases, they provide empirical models based on experimental data. In this study, different artificial intelligence (AI) techniques are employed to estimate the concentration of cuttings present in the wellbore. The purpose of this study is to indirectly measure the hole-cleaning efficiency in order to predict the cutting concentration from drilling parameters using artificial intelligence techniques. The study is based on 116 experimental data records from the studies. Two AI techniques were selected, namely artificial neural network (ANN) and support vector machine (SVM), to estimate the cutting concentration in the wellbore. The input parameters comprise mud density and mud rheological properties (yield point and plastic viscosity) in addition to drilling parameters including the hole inclination angle, pipe eccentricity (i.e. location of the drill pipe from the axis of the well), the rate of penetration (ROP), flow rate (GPM), drill pipe rotary speed (RPM) and temperature. The results obtained show the ability of the two employed techniques to accurately predict the cutting concentration in the wellbore with average absolute errors (AAE) less than 5% and correlation coefficients (R) higher than 0.9. Comparison of these results with a literature model showed that the AI techniques provide better predictions of cutting concentration and higher accuracy than that model. Applying the developed AI technique will help the drilling engineers to assess the hole cleaning in a real time.

show abstract

Section: Applications Of Artificial Intelligence In Petroleum Industrymentioning

confidence: 99%

Cutting concentration prediction in horizontal and deviated wells using artificial intelligence techniques

Al-Azani

Elkatatny

Ali

et al. 2019

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial neural network and fuzzy-logic approaches were utilized to estimate the P b . 29 Sharrad and Abd-Alrahman 30 showed the P b correlation with an AAE of 8.7% based on 35 Libyan datasets and using EViews software. An artificial neural network, an adaptive neuro-fuzzy inference system, and a support vector machine were operated to determine a P b .…”

Section: Introductionmentioning

confidence: 99%

An Accurate Reservoir’s Bubble Point Pressure Correlation

et al. 2022

View full text Add to dashboard Cite

Bubble point pressure ( P b ) is essential for determining petroleum production, simulation, and reservoir characterization calculations. The P b can be measured from the pressure–volume–temperature (PVT) experiments. Nonetheless, the PVT measurements have limitations, such as being costly and time-consuming. Therefore, some studies used alternative methods, namely, empirical correlations and machine learning techniques, to obtain the P b . However, the previously published methods have restrictions like accuracy, and some use specific data to build their models. In addition, most of the previously published models have not shown the proper relationships between the features and targets to indicate the correct physical behavior. Therefore, this study develops an accurate and robust correlation to obtain the P b applying the Group Method of Data Handling (GMDH). The GMDH combines neural networks and statistical methods that generate relationships among the feature and target parameters. A total of 760 global datasets were used to develop the GMDH model. The GMDH model is verified using trend analysis and indicates that the GMDH model follows all input parameters’ exact physical behavior. In addition, different statistical analyses were conducted to investigate the GMDH and the published models’ robustness. The GMDH model follows the correct trend for four input parameters (gas solubility, gas specific gravity, oil specific gravity, and reservoir temperature). The GMDH correlation has the lowest average percent relative error, root mean square error, and standard deviation of 8.51%, 12.70, and 0.09, respectively, and the highest correlation coefficient of 0.9883 compared to published models. The different statistical analyses indicated that the GMDH is the first rank model to accurately and robustly predict the P b .

show abstract

“…Gomaa 32 used the multiple nonlinear regression analysis, utilizing 441 data points from the Middle East crude oil, to build a P b correlation. 32 Alakbari et al 33 utilized an artificial neural network and the fuzzy logic method to obtain P b models. Sharrad and Abd-Alrahman 34 presented a P b correlation applying 35 data points from Libya crude oil, using linear regression analysis through EViews software.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approach for Robust Prediction of Reservoir Bubble Point Pressure

et al. 2021

View full text Add to dashboard Cite

The bubble point pressure ( P b ) is a crucial pressure–volume–temperature (PVT) property and a primary input needed for performing many petroleum engineering calculations, such as reservoir simulation. The industrial practice of determining P b is by direct measurement from PVT tests or prediction using empirical correlations. The main problems encountered with the published empirical correlations are their lack of accuracy and the noncomprehensive data set used to develop the model. In addition, most of the published correlations have not proven the relationships between the inputs and outputs as part of the validation process (i.e., no trend analysis was conducted). Nowadays, deep learning techniques such as long short-term memory (LSTM) networks have begun to replace the empirical correlations as they generate high accuracy. This study, therefore, presents a robust LSTM-based model for predicting P b using a global data set of 760 collected data points from different fields worldwide to build the model. The developed model was then validated by applying trend analysis to ensure that the model follows the correct relationships between the inputs and outputs and performing statistical analysis after comparing the most published correlations. The robustness and accuracy of the model have been verified by performing various statistical analyses and using additional data that was not part of the data set used to develop the model. The trend analysis results have proven that the proposed LSTM-based model follows the correct relationships, indicating the model’s reliability. Furthermore, the statistical analysis results have shown that the lowest average absolute percent relative error (AAPRE) is 8.422% and the highest correlation coefficient is 0.99. These values are much better than those given by the most accurate models in the literature.

show abstract

Prediction of Bubble Point Pressure Using Artificial Intelligence AI Techniques

Cited by 35 publications

References 18 publications

Cutting concentration prediction in horizontal and deviated wells using artificial intelligence techniques

Cutting concentration prediction in horizontal and deviated wells using artificial intelligence techniques

An Accurate Reservoir’s Bubble Point Pressure Correlation

Deep Learning Approach for Robust Prediction of Reservoir Bubble Point Pressure

Contact Info

Product

Resources

About