scholarly journals Evaluates A PVT Correlation to Estimate Dead Oil Viscosity for Libyan Crudes Using 104 Samples from Different Reservoirs

2021 ◽  
Author(s):  
Mohammed A. Samba ◽  
◽  
Li Yiqiang ◽  
Wannees A. Alkhyyali A. Alkhyyali ◽  
Yousef A. Altaher ◽  
...  
Keyword(s):  
Crude Oil ◽  
Oil And Gas ◽  
Surface Condition ◽  
Petroleum Engineering ◽  
Ann Model ◽  
Empirical Correlations ◽  
Oil Viscosity ◽  
The Dead ◽  
Artificial Neural Network Ann ◽  
Measured Viscosity

Viscosity is defined as the resistance of the fluid to flow. It plays a very significant role in most oil and gas engineering applications. The measured viscosity for any crude oil at surface condition is called by the dead oil viscosity, where the dead oil viscosity is a function in any correlation to calculate the viscosity of the crude oil. Thus, the dead oil viscosity is important in most applications related to the petroleum engineering. Accordingly, a new mathematical and artificial neural network (ANN) dead oil viscosity correlations were developed for Libyan crudes and compared with renowned dead oil viscosity correlations using 104 samples from different reservoirs. The evaluation in this study has been done by statistical and graphical error analysis. The results shown that the ANN model has proven to be a useful tool for predicting where the ANN model has given the best result with low error AAD was 14.40509 % and R^2 was 95.91%. The ANN model and mathematical model gave the lowest error when they compared with different empirical correlations.

scholarly journals Analisis Jaringan Syaraf Tiruan untuk prediksi volume ekspor dan impor migas di Indonesia

2018 ◽  
Vol 4 (1) ◽  
pp. 30
Author(s):  
Yuli Andriani ◽  
Hotmalina Silitonga ◽  
Anjar Wanto
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Crude Oil ◽  
Oil And Gas ◽  
Oil Products ◽  
Oil Exports ◽  
Directorate General ◽  
Architectural Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Analisis pada penelitian penting dilakukan untuk tujuan mengetahui ketepatan dan keakuratan dari penelitian itu sendiri. Begitu juga dalam prediksi volume ekspor dan impor migas di Indonesia. Dilakukannya penelitian ini untuk mengetahui seberapa besar perkembangan ekspor dan impor Indonesia di bidang migas di masa yang akan datang. Penelitian ini menggunakan Jaringan Syaraf Tiruan (JST) atau Artificial Neural Network (ANN) dengan algoritma Backpropagation. Data penelitian ini bersumber dari dokumen kepabeanan Ditjen Bea dan Cukai yaitu Pemberitahuan Ekspor Barang (PEB) dan Pemberitahuan Impor Barang (PIB). Berdasarkan data ini, variabel yang digunakan ada 7, antara lain: Tahun, ekspor minyak mentah, impor minyak mentah, ekspor hasil minyak, impor hasil minyak, ekspor gas dan impor gas. Ada 5 model arsitektur yang digunakan pada penelitian ini, 12-5-1, 12-7-1, 12-8-1, 12-10-1 dan 12-14-1. Dari ke 5 model yang digunakan, yang terbaik adalah 12-5-1 dengan menghasilkan tingkat akurasi 83%, MSE 0,0281641257 dengan tingkat error yang digunakan 0,001-0,05. Sehingga model ini bagus untuk memprediksi volume ekspor dan impor migas di Indonesia, karena akurasianya antara 80% hingga 90%.   Analysis of the research is Imporant used to know precision and accuracy of the research itself. It is also in the prediction of Volume Exports and Impors of Oil and Gas in Indonesia. This research is conducted to find out how much the development of Indonesia's exports and Impors in the field of oil and gas in the future. This research used Artificial Neural Network with Backpropagation algorithm. The data of this research have as a source from custom documents of the Directorate General of Customs and Excise (Declaration Form/PEB and Impor Export Declaration/PIB). Based on this data, there are 7 variables used, among others: Year, Crude oil exports, Crude oil Impors, Exports of oil products, Impored oil products, Gas exports and Gas Impors. There are 5 architectural models used in this study, 12-5-1, 12-7-1, 12-8-1, 12-10-1 and 12-14-1. Of the 5 models has used, the best models is 12-5-1 with an accuracy 83%, MSE 0.0281641257 with error rate 0.001-0.05. So this model is good to predict the Volume of Exports and Impors of Oil and Gas in Indonesia, because its accuracy between 80% to 90%.

Development of Neural Network Models for a Crude Oil Distillation Column

2012 ◽  
Author(s):  
Khairiyah Mohd. Yusof ◽  
Fakhri Karray ◽  
Peter L. Douglas
Keyword(s):  
Neural Network ◽  
Steady State ◽  
Crude Oil ◽  
Distillation Column ◽  
Network Models ◽  
Ann Model ◽  
Neural Network Models ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Crude Oil Distillation

This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the model is developed for real time optimisation (RTO) applications they are steady state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO.

scholarly journals Prediction of Rate of Penetration for wells at Nam Con Son basin using Artificial Neural Networks models

10.29007/4sdt ◽  
2022 ◽  
Author(s):  
Vu Khanh Phat Ong ◽  
Quang Khanh Do ◽  
Thang Nguyen ◽  
Hoang Long Vo ◽  
Ngoc Anh Thy Nguyen ◽  
...  
Keyword(s):  
Network Model ◽  
Oil And Gas ◽  
Research Approach ◽  
Ann Model ◽  
Rate Of Penetration ◽  
Drilling Parameters ◽  
Drilling Operations ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The rate of penetration (ROP) is an important parameter that affects the success of a drilling operation. In this paper, the research approach is based on different artificial neural network (ANN) models to predict ROP for oil and gas wells in Nam Con Son basin. The first is the process of collecting and evaluating drilling parameters as input data of the model. Next is to find the network model capable of predicting ROP most accurately. After that, the study will evaluate the number of input parameters of the network model. The ROP prediction results obtained from different ANN models are also compared with traditional models such as the Bingham model, Bourgoyne & Young model. These results have shown the competitiveness of the ANN model and its high applicability to actual drilling operations.

Machine Learning-Based Improved Pressure–Volume–Temperature Correlations for Black Oil Reservoirs

2021 ◽  
Vol 143 (11) ◽  
Author(s):  
Zeeshan Tariq ◽  
Mohamed Mahmoud ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Mathematical Models ◽  
Petroleum Engineering ◽  
Support Vector ◽  
Pvt Properties ◽  
Empirical Correlations ◽  
Oil Viscosity ◽  
Engineering Applications ◽  
Wide Range ◽  
Black Oil

Abstract Pressure–volume–temperature (PVT) properties of crude oil are considered the most important properties in petroleum engineering applications as they are virtually used in every reservoir and production engineering calculation. Determination of these properties in the laboratory is the most accurate way to obtain a representative value, at the same time, it is very expensive. However, in the absence of such facilities, other approaches such as analytical solutions and empirical correlations are used to estimate the PVT properties. This study demonstrates the combined use of two machine learning (ML) technique, viz., functional network (FN) coupled with particle swarm optimization (PSO) in predicting the black oil PVT properties such as bubble point pressure (Pb), oil formation volume factor at Pb, and oil viscosity at Pb. This study also proposes new mathematical models derived from the coupled FN-PSO model to estimate these properties. The use of proposed mathematical models does not need any ML engine for the execution. A total of 760 data points collected from the different sources were preprocessed and utilized to build and train the machine learning models. The data utilized covered a wide range of values that are quite reasonable in petroleum engineering applications. The performances of the developed models were tested against the most used empirical correlations. The results showed that the proposed PVT models outperformed previous models by demonstrating an error of up to 2%. The proposed FN-PSO models were also compared with other ML techniques such as an artificial neural network, support vector regression, and adaptive neuro-fuzzy inference system, and the results showed that proposed FN-PSO models outperformed other ML techniques.

scholarly journals A Study of Asphaltene Precipitation Problem in some wells in Kurdistan Region

2020 ◽  
Vol 4 (6) ◽  
pp. 27-36
Author(s):  
akram Humoodi ◽  
Baroz Aziz ◽  
Dana Khidhir
Keyword(s):  
Crude Oil ◽  
Phase Behavior ◽  
Oil And Gas ◽  
Surface Condition ◽  
Oil And Gas Industry ◽  
Kurdistan Region ◽  
Asphaltene Precipitation ◽  
Oil Composition ◽  
Reservoir Conditions ◽  
Point Pressure

Throughout the production and reservoir lifecycle, the asphaltene precipitation is an ever existing problem through changing the porosity, permeability and wettability leading to decline in production. The conditions that govern Asphaltene precipitation varies from well to well and from reservoir conditions of high pressure and temperature to surface conditions and need to be studied case by case. The modeling and predicting the phase behavior and precipitation of Asphaltene is paramount for wells in Kurdistan region as it is developing its oil and gas industry. Crude oil samples from three wells in Kurdistan Region-Iraq were selected for this study. Experimental data such as crude oil composition using Gas Chromatography, PVT analysis and reservoir pressure and temperature were used as input data into Computer Modeling Group CMG simulator and a model of Asphaltene phase behavior was suggested. The model suggests that the maximum precipitation occurs near the bubble point pressure at reservoir conditions. This is validated and compared with results in literature indicating similar behavior of crude oil. To predict the Asphaltene precipitation at surface condition a modified Colloidal Instability Index CII were used and the results were validated by De Bore plot

scholarly journals An Efficient Approach for Real-Time Prediction of Rate of Penetration in Offshore Drilling

2016 ◽  
Vol 2016 ◽  
pp. 1-13 ◽  
Author(s):  
Xian Shi ◽  
Gang Liu ◽  
Xiaoling Gong ◽  
Jialin Zhang ◽  
Jian Wang ◽  
...  
Keyword(s):  
Oil And Gas ◽  
Bohai Bay ◽  
Ann Model ◽  
Rate Of Penetration ◽  
Oil And Gas Exploration ◽  
Formation Type ◽  
Artificial Neural Network Ann ◽  
Learning Machine ◽  
Efficient Learning ◽  
Rock Mechanical Properties

Predicting the rate of penetration (ROP) is critical for drilling optimization because maximization of ROP can greatly reduce expensive drilling costs. In this work, the typical extreme learning machine (ELM) and an efficient learning model, upper-layer-solution-aware (USA), have been used in ROP prediction. Because formation type, rock mechanical properties, hydraulics, bit type and properties (weight on the bit and rotary speed), and mud properties are the most important parameters that affect ROP, they have been considered to be the input parameters to predict ROP. The prediction model has been constructed using industrial reservoir data sets that are collected from an oil reservoir at the Bohai Bay, China. The prediction accuracy of the model has been evaluated and compared with the commonly used conventional artificial neural network (ANN). The results indicate that ANN, ELM, and USA models are all competent for ROP prediction, while both of the ELM and USA models have the advantage of faster learning speed and better generalization performance. The simulation results have shown a promising prospect for ELM and USA in the field of ROP prediction in new oil and gas exploration in general, as they outperform the ANN model. Meanwhile, this work provides drilling engineers with more choices for ROP prediction according to their computation and accuracy demand.

scholarly journals A Study of Asphaltene Precipitation Problem in some wells in Kurdistan Region

2020 ◽  
Vol 4 (6) ◽  
pp. 27-36
Author(s):  
akram Humoodi Abdulwahab ◽  
Baroz Aziz ◽  
Dana Khidhir
Keyword(s):  
Crude Oil ◽  
Phase Behavior ◽  
Oil And Gas ◽  
Surface Condition ◽  
Oil And Gas Industry ◽  
Kurdistan Region ◽  
Asphaltene Precipitation ◽  
Oil Composition ◽  
Reservoir Conditions ◽  
Point Pressure

Throughout the production and reservoir lifecycle, the asphaltene precipitation is an ever existing problem through changing the porosity, permeability and wettability leading to decline in production. The conditions that govern Asphaltene precipitation varies from well to well and from reservoir conditions of high pressure and temperature to surface conditions and need to be studied case by case. The modeling and predicting the phase behavior and precipitation of Asphaltene is paramount for wells in Kurdistan region as it is developing its oil and gas industry. Crude oil samples from three wells in Kurdistan Region-Iraq were selected for this study. Experimental data such as crude oil composition using Gas Chromatography, PVT analysis and reservoir pressure and temperature were used as input data into Computer Modeling Group CMG simulator and a model of Asphaltene phase behavior was suggested. The model suggests that the maximum precipitation occurs near the bubble point pressure at reservoir conditions. This is validated and compared with results in literature indicating similar behavior of crude oil. To predict the Asphaltene precipitation at surface condition a modified Colloidal Instability Index CII were used and the results were validated by De Bore plot

scholarly journals NEW DERIVED CORRELATIONS FOR LIBYAN CRUDE OIL TO ESTIMATE BUBBLE-POINT PRESSURE

2019 ◽  
Vol 2 (1) ◽  
pp. 1-13
Author(s):  
Mustafa Sharrad ◽  
Hamid Hakim Abd-Alrahman
Keyword(s):  
Crude Oil ◽  
Oil Recovery ◽  
Production Performance ◽  
Petroleum Engineering ◽  
Empirical Correlations ◽  
Bubble Point ◽  
Bubble Point Pressure ◽  
New Correlation ◽  
Future Production ◽  
Point Pressure

The key factor of all petroleum engineering calculation is the knowledge of the PVT (Pressure, Volume, Temperature) parameters, such as determination of oil and gas flowing properties, predicting production performance in the future, production facilities designing and enhanced oil recovery planning methods. Those PVT properties are ideally determined experimentally in the laboratory. However, some of these experimental data is not always available; consequently, empirical correlations are used to estimate them. Many researchers have been focusing on models for predicting reservoir fluid properties from the available experimental PVT data, such as reservoir pressure, temperature, crude oil API gravity, gas oil ratio, formation volume factor, and gas gravity. The present study compares between some of the available empirical PVT correlations for estimating the bubble point pressure of some Libyan crude oils based on 35 data point samples from different Libyan oil fields. In the second part of this study, a new correlation has been derived to predict the bubble point pressure using Eviews software and compares the output results of this new correlation with some derived correlations found in the literature using statistical analysis such as the Average Absolute Error (AARE). The results showed an AARE as low as 8.7%, for bubble point pressure estimated by this new derived correlation. These results are valid to compare to other driven empirical correlations that have been evaluated. 

Effects of Sonication Time on the Stability and Viscosity of Functionalized MWCNT-Based Nanolubricants

2020 ◽  
Vol 16 (4) ◽  
pp. 639-654
Author(s):  
Ahmet Selim Dalkilic ◽  
Bedri Onur Küçükyıldırım ◽  
Ayşegül Akdoğan Eker ◽  
Faruk Yıldız ◽  
Altuğ Akpinar ◽  
...  
Keyword(s):  
Effective Viscosity ◽  
Mass Concentration ◽  
Measured Data ◽  
Sonication Time ◽  
Empirical Correlations ◽  
Thermal Systems ◽  
The Stability ◽  
Rotary Viscometer ◽  
Functionalized Mwcnts ◽  
Measured Viscosity

Background: Active scholars in the nanofluid field have continuously attempted to remove the associated challenge of the stability of nanofluids via various approaches, such as functionalization and adding a surfactant. After preparing a stable nanofluid, one must measure the properties, as this is vital in the design of thermal systems. Objective: Authors aimed to investigate the stability and viscosity of refrigeration lubrication oilbased nanofluids containing functionalized MWCNTs. The effects of concentration and temperature on viscosity were studied. Furthermore, the present study focused on the effect of sonication time on the stability and viscosity of the prepared samples. Methods: After the preparation of chemically functionalized MWCNTs, solutions were dispersed with an ultrasonic homogenizer for 2, 4 and 8 hours sonication at maximum power. Viscosity measurements for all samples were made 10 minutes after sonication by adjusting the proper spinning velocity using a digital rotary viscometer. Results: The first part deals with the stability of the nanofluid as a nanolubricant, and the second one investigates the viscosity of the nanofluid and the effects of various parameters on it. The last one is related to the validation of the measured viscosity values by means of well-known empirical correlations. The measured data are given for validation issues. Conclusion: The samples will have higher stability by increasing the time of sonication. The viscosity of a nanofluid does not change with the increase of sonication time to two hours and higher. Up to mass concentration of 0.1%, the effective viscosity increases with adding nanotubes linearly.

Sign in / Sign up

Export Citation Format

Share Document