Search

Abstract Shear wave velocity (VS) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such data by analyzing finite reservoir rock cores is very costly and limited. The high cost of sonic dipole advanced wellbore logging service and its implementation in a few wells of a field has placed many limitations on geomechanical modeling. On the other hand, shear wave velocity VS tends to be nonlinearly related to many of its influencing variables, making empirical correlations unreliable for its prediction. Hybrid machine learning (HML) algorithms are well suited to improving predictions of such variables. Recent advances in deep learning (DL) algorithms suggest that they too should be useful for predicting VS for large gas and oil field datasets but this has yet to be verified. In this study, 6622 data records from two wells in the giant Iranian Marun oil field (MN#163 and MN#225) are used to train HML and DL algorithms. 2072 independent data records from another well (MN#179) are used to verify the VS prediction performance based on eight well-log-derived influencing variables. Input variables are standard full-set recorded parameters in conventional oil and gas well logging data available in most older wells. DL predicts VS for the supervised validation subset with a root mean squared error (RMSE) of 0.055 km/s and coefficient of determination (R2) of 0.9729. It achieves similar prediction accuracy when applied to an unseen dataset. By comparing the VS prediction performance results, it is apparent that the DL convolutional neural network model slightly outperforms the HML algorithms tested. Both DL and HLM models substantially outperform five commonly used empirical relationships for calculating VS from Vp relationships when applied to the Marun Field dataset. Concerns regarding the model's integrity and reproducibility were also addressed by evaluating it on data from another well in the field. The findings of this study can lead to the development of knowledge of production patterns and sustainability of oil reservoirs and the prevention of enormous damage related to geomechanics through a better understanding of wellbore instability and casing collapse problems. Graphical abstract

One of the challenges in reservoir management is determining the fracture density (FVDC) in reservoir rock. Given the high cost of coring operations and image logs, the ability to predict FVDC from various petrophysical input variables using a supervised learning basis calibrated to the standard well is extremely useful. In this study, a novel machine learning approach is developed to predict FVDC from 12-input variable well-log based on feature selection. To predict the FVDC, combination of two networks of multiple extreme learning machines (MELM) and multi-layer perceptron (MLP) hybrid algorithm with a combination of genetic algorithm (GA) and particle swarm optimizer (PSO) has been used. We use a novel MELM-PSO/GA combination that has never been used before, and the best comparison result between MELM-PSO-related models with performance test data is RMSE = 0.0047 1/m; R2 = 0.9931. According to the performance accuracy analysis, the models are MLP-PSO

Two-phase flow rate estimation of liquid and gas flow through wellhead chokes is essential for determining and monitoring production performance from oil and gas reservoirs at specific well locations. Liquid flow rate (QL) tends to be nonlinearly related to these influencing variables, making empirical correlations unreliable for predictions applied to different reservoir conditions and favoring machine learning (ML) algorithms for that purpose. Recent advances in deep learning (DL) algorithms make them useful for predicting wellhead choke flow rates for large field datasets and suitable for wider application once trained. DL has not previously been applied to predict QL from a large oil field. In this study, 7245 multi-well data records from Sorush oil field are used to compare the QL prediction performance of traditional empirical, ML and DL algorithms based on four influencing variables: choke size (D64), wellhead pressure (Pwh), oil specific gravity (γo) and gas–liquid ratio (GLR). The prevailing flow regime for the wells evaluated is critical flow. The DL algorithm substantially outperforms the other algorithms considered in terms of QL prediction accuracy. The DL algorithm predicts QL for the testing subset with a root-mean-squared error (RMSE) of 196 STB/day and coefficient of determination (R2) of 0.9969 for Sorush dataset. The QL prediction accuracy of the models evaluated for this dataset can be arranged in the descending order: DL > DT > RF > ANN > SVR > Pilehvari > Baxendell > Ros > Glbert > Achong. Analysis reveals that input variable GLR has the greatest, whereas input variable D64 has the least relative influence on dependent variable QL.

Fluid-flow measurements of petroleum can be performed using a variety of equipment such as orifice meters and wellhead chokes. It is useful to understand the relationship between flow rate through orifice meters (Qv) and the five fluid-flow influencing input variables: pressure (P), temperature (T), viscosity (μ), square root of differential pressure (ΔP^0.5), and oil specific gravity (SG). Here we evaluate these relationships using a range of machine-learning algorithms applied to orifice meter data from a pipeline flowing from the Cheshmeh Khosh Iranian oil field. Correlation coefficients indicate that (Qv) has weak to moderate positive correlations with T, P, and μ, a strong positive correlation with the ΔP^0.5, and a weak negative correlation with oil specific gravity. In order to predict the flow rate with reliable accuracy, five machine-learning algorithms are applied to a dataset of 1037 data records (830 used for algorithm training; 207 used for testing) with the full input variable values for the data set provided. The algorithms evaluated are: Adaptive Neuro Fuzzy Inference System (ANFIS), Least Squares Support Vector Machine (LSSVM), Radial Basis Function (RBF), Multilayer Perceptron (MLP), and Gene expression programming (GEP). The prediction performance analysis reveals that all of the applied methods provide predictions at acceptable levels of accuracy. The MLP algorithm achieves the most accurate predictions of orifice meter flow rates for the dataset studied. GEP and RBF also achieve high levels of accuracy. ANFIS and LSSVM perform less well, particularly in the lower flow rate range (i.e.

The wellbore stability of a vertical well through the sandstone reservoir layers of the Asmari oil-bearing formation in south-west Iran is investigated. The safe drilling-fluid density range for maintaining wellbore stability is determined and simulated using FLAC3D software and a finite volume model established with drilled strata geomechanical features. The initiation of plastic condition is used to determine the safe mud weight window (SMWW) in specific sandstone layers. The effects of rock strength parameters, major stresses around the wellbore and pore pressure on the SMWW are investigated for this wellbore. Sensitivity analysis reveals that a reduction in cohesion and internal friction angle values leads to a significant narrowing of the SMWW. On the other hand, the reduction of pore pressure and the ratio between maximum and minimum horizontal stresses causes the SMWW to widen significantly. The ability to readily quantify changes in SMWW indicates that the developed model is suitable as a well planning and monitoring tool. Key words: wellbore stability, wellbore geomechanical property, safe mud weight window, wellbore instability risk factors, drilling stress simulation

None of the various published models used to predict oil production rates through wellhead chokes from fluid composition and pressures can be considered as a universal model for all regions. Here, a model is provided to predict liquid production-flow rates for the Reshadat oil field offshore southwest Iran, applying a customized genetic optimization algorithm (GA) and standard Excel Solver non-linear and evolutionary optimization algorithms. The dataset of 182 records of wellhead choke measurements spans liquid flow rates from

An important requirement of reservoir management is to understand the properties of reservoir fluids and dependent phase behaviors. This makes it possible to determine the properties of reservoir fluids in laboratory pressure-volume-temperature (PVT) tests. Such laboratory tests are costly and time consuming, and reservoir data are sometimes not available. When estimating the in-place fluid volumes and/or designing enhanced recovery processes information on bubble point pressure (BPP) and oil formation volume factor (OFVF) is required. Predicting these two parameters is therefore one of the priorities of reservoir engineers. It is becoming increasingly beneficial to be able to predict BPP and OFVF with efficient machine-learning algorithms based on underlying variables that are more easily measured directly in the field. In this study, a dataset of 638 data records of published crude oil fluid samples from around the world is evaluated. After filtering the dataset for outliers, 591 data records for BPP and 599 datasets for OFVF are evaluated with efficient hybrid machine-learning algorithms (multi-layer extreme learning machine --MELM-- and least squares support vector machine -- LSSVM) optimized using a genetic algorithm –GA-- and a particle swarm optimizer –PSO-- to improve their prediction performance. Four underlying variables are considered for each data record: temperature (T), solution gas oil ratio (Rs), gas specific gravity (γg) and oil gravity (API). The PSO- MELM-PSO hybrid algorithm achieved the highest prediction accuracy measured in terms of root mean square errors (RMSE) of 33.5 psi for BPP and 0.0199 for OFVF. The four-hybrid machine-learning-optimization algorithms evaluated all outperform the empirical relationships used for many decades in the oil industry to predict BPP and OFVF.

Numerous empirical correlation models for predicting wellhead flow rates have been proposed. Here we apply a recently developed model based upon extensive data from the Ghawar Field (Saudi Arabia) to the Pazanan 1 retrograde gas-condensate field (Aghajari, Iran). A firefly optimization algorithm is applied to select the optimum coefficient values for that model by minimizing the mean square error between measured and predicted gas flow rates from a wellhead-test data set. The input data to calculate gas flow rate includes choke diameter, gas specific gravity, flowing fluid temperature, upstream and downstream pressure. The models prediction accuracy depends upon the coefficient values applied in its formula. The firefly optimization model was tested with various sensitivity cases applying different values to the key control variables γ and N (number of fireflies in the population). Optimum results in terms of minimum mean square error and rapid convergence was achieved with the control variable values γ = 2 and N = 40. The optimum case achieved with low error values and a level of accuracy that is significantly better than the predictions for dataset using the coefficient values applied to the Ghawar field, suggesting that such model coefficients need to be optimized on a field-by-field basis.

The casing-collapse hazard is one that drilling engineers seek to mitigate with careful well design and operating procedures. However, certain rock formations and their fluid pressure and stress conditions are more prone to casing-collapse risks than others. The Gachsaran Formation in south west Iran, is one such formation, central to oil and gas resource exploration and development in the Zagros region and consisting of complex alternations of anhydrite, marl and salt. The casing-collapse incidents in this formation have resulted over decades in substantial lost production and remedial costs to mitigate the issues surrounding wells with failed casing string. High and vertically-varying horizontal stresses across the Gachsaran formation are the challenge to predict and overcome. This study investigates casing collapse in wellbores from an established petroleum geomechanics perspective to develop and compare two hybrid neural-network models, multilayer perceptron's tuned, respectively, with a genetic algorithm (MLP-GA) and a particle swarm algorithm (MLP-PSO). These machine-learning algorithms are configured to predict Poisson's ratio ( ϑ ) and maximum horizontal stress ( σ H ) from available well-log input data. A large dataset from three wellbores drilled though the Gachsaran Formation in the Marun oil field, the second largest in Iran, is used to construct and validate the hybrid MLP models. In the first step, 22323 data records from a collapsed wellbore are divided into training (15626 records; 70%) and independent testing subsets (6697 records; 30%). In the next step, in order to test whether the suggested algorithms could be generalized, the data sets of the other two wells in the field were tested. Those tests confirmed that the algorithms achieved high prediction accuracy for Poisson's ratio and maximum horizontal stress in other wellbores.