Shut-in Stabilization Time Optimization for Better Reservoir Pressure Monitoring Harnessing Neural Network Modeling

Stabilization time is an essential key for pressure measurement accuracy. Obtaining representative pressure points in build-up tests for pressure-sensitive reservoirs is driven by optimizing stabilization time. An artificial intelligence technique was used in the study for testing pressure-sensitive reservoirs using measuring gauges. The stabilization time function of reservoir characteristics is generally calculated using the diffusivity equation where rock and fluid properties are honored. The artificial neural network (ANN) technique will be used to predict the stabilization time and optimize it using readily available and known inputs or parameters. The values obtained from the formula known as the diffusion formula and the ANN technique are then compared against the actual values measured from pressure gauges in the reservoirs. The optimization of the number of datasets required to be fed to the network to allow for coverage over the whole range is essential as opposed to the clustering of the datasets. A total of about 3000 pressure derivative samples from the wells were used in the testing, training, and validation of the ANN. The datasets are optimized by dividing them into three fractional parts, and the number optimized through monitoring the ANN performance. The optimization of the stabilization time is essential and leads to the improvement of the ANN learning process. The sensitivity analysis proves that the use of the formula and ANN technique, compared to actual datasets, is better since, in the formula and ANN technique, the time was optimized with an average absolute relative error of 3.67%. The results are near the same, especially when the ANN technique undergoes testing using known and easily available parameters. Time optimization is essential since discreet points or datasets in the ANN technique and formula would not work, allowing ANN to work in situations of optimization. The study was expected to provide additional data and information, considering that stabilization time is essential in obtaining the pressure map representation. ANN is a superior technique and, through its superiority, allows for proper optimization of time as a parameter. Thus it can predict reservoir log data almost accurately. The method used in the study shows the importance of optimizing pressure stabilization time through reduction. The study results can, therefore, be applied in reservoir testing to achieve optimal results.

Constitutive modelling with a novel two-step optimization for an Al-Zn-Mg-Cu alloy and its application in FEA

The modified Johnson-Cook constitutive model was developed for describing the flow behavior of Al-7.8Zn-1.65Mg-2.0Cu (wt.%) alloy based on the flow curves in the temperature range of 300℃~450℃ and strain rate range of 0.01s-1~10s-1 which were obtained by isothermal compression tests conducted on a Gleeble-3500 isothermal simulator. A two-step optimization method was proposed to optimize the prediction precision according to the evaluation of average absolute relative error (AARE). By using a traversal procedure for calculating the model under different reference conditions, this evaluator was found varying in the range of 4.1837%~11.105%, revealing the great influence of reference condition on the precision, then the reference condition optimization (RCO) was conducted. Genetic algorithm (GA) was introduced as the second step of the two-step optimization (TSO) to optimize the material constants of the model, which furtherly improved the precision by reducing the AARE-value to 3.801%. The models before and after optimization were written into subroutines for the software DEFORM and the compression tests were investigated through finite element analysis (FEA). The simulated results (forming load and temperature rise) revealed that the model after TSO has the highest agreement with the experimental.

Prediction of Flow Stress of Annealed 7075 Al Alloy in Hot Deformation Using Strain-Compensated Arrhenius and Neural Network Models

Hot compression experiments of annealed 7075 Al alloy were performed on TA DIL805D at different temperatures (733, 693, 653, 613 and 573 K) with different strain rates (1.0, 0.1, 0.01 and 0.001 s−1.) Based on experimental data, the strain-compensated Arrhenius model (SCAM) and the back-propagation artificial neural network model (BP-ANN) were constructed for the prediction of the flow stress. The predictive power of the two models was estimated by residual analysis, correlation coefficient (R) and average absolute relative error (AARE). The results reveal that the deformation parameters including strain, strain rate, and temperature have a significant effect on the flow stress of the alloy. Compared with the SCAM model, the flow stress predicted by the BP-ANN model is in better agreement with experimental values. For the BP-ANN model, the maximum residual is only 1 MPa, while it is as high as 8 MPa for the SCAM model. The R and AARE for the SCAM model are 0.9967 and 3.26%, while their values for the BP-ANN model are 0.99998 and 0.18%, respectively. All these reflect that the BP-ANN model has more accurate prediction ability than the SCAM model, which can be applied to predict the flow stress of the alloy under high temperature deformation.

Predicting the flow zone indicator of carbonate reservoirs using NMR echo transforms, and routine open-hole log measurements: Insights from a field case study spanning extreme micro-structure properties

Predicting the flow zone indicator is essential for identifying the hydraulic flow units of hydrocarbon reservoirs. Delineation of hydraulic flow units is crucial for mapping petrophysical and rock mechanical properties. Precise prediction of the flow zone indicator (FZI) of carbonate rocks using well log measurements in un-cored intervals is still a daunting challenge for petrophysicists. This study presents a data mining methodology for predicting the rock FZI using NMR echo transforms, and conventional open-hole log measurements. The methodology is applied on a carbonate reservoir with extreme microstructure properties, from an oil “M” field characterized by a relatively high-permeability with a median of approximately 167 mD, and a maximum of 3480 mD. The reservoir from the M field features detritic, or vuggy structure, covering a wide range of rock fabrics varying from microcrystalline mudstones to coarse-grained grainstones. Porosity has a median of approximately 22%. Dimensional analysis and regression analysis are applied for the derivation of four transforms that appear to capture approximately 80% of the FZI variance. These four transforms are formulated using the geometric mean of the transverse NMR relaxation time (T2lm), the ratio of the free fluid index (FFI) to the bulk volume irreducible (BVI), the bulk density, the sonic compressional travel time, the true resistivity, the photo-electric absorption, and the effective porosity. Non-linear regression models have been developed for predicting the FZI using the derived transforms, for the carbonate reservoir from the M field. The average relative error for the estimated FZI values is approximately 52%. The same transforms are used as input for training a developed general regression neural network (GRNN), built for the purpose of predicting rock FZI. The constructed GRNN predicts FZI with a notable precision. The average absolute relative error on FZI for the training set is approximately 3.1%. The average absolute relative error on FZI for the blind testing set is approximately 22.0 %. The data mining approach presented in this study appears to suggest that (i) the relationship between the flow zone indicator and open-hole log attributes is highly non-linear, (ii) the FZI is highly affected by parameters that reflect rock texture, rock micro-structure geometry, and diagenetic alterations, and (iii) the derived transforms provide a means for further enhancement of the flow zone indicator prediction in carbonate reservoirs.

Machine Learning Modeling of Water Use Patterns in Small Disadvantaged Communities

Water use patterns were explored for three small communities that are located in proximity to agricultural fields and rely on their local wells for potable water supply. High-resolution water use data, collected over a four-year period, revealed significant temporal variability. Monthly, daily, and hourly water use patterns were well described by autoregressive moving average (ARMA) models. Model development was supported by unsupervised clustering analysis via self-organizing maps (SOMs) that revealed similarities of water use patterns and confirmed the time-series water use model attributes. The inclusion of ambient temperature and rainfall as model attributes improved ARMA model performance for daily and hourly water use from R2 ~0.86–0.87 to 0.94–0.97 and from R2 ~0.85–0.89 to 0.92–0.98, respectively. Water use predictions for an entire year forward in time was feasible demonstrating ARMA models’ performance of (i) R2 ~0.90–0.94 and average absolute relative error (AARE) of ~2.9–4.9% for daily water use, and (ii) R2 ~0.81–0.95 and AARE ~1.9–3.8% for hourly water use. The study suggests that ARMA modeling should be useful for analysis of temporally variable water use in support of water source management, as well as assessing capacity building for small water systems including water treatment needs and wastewater handling.

COMPARATIVE STUDY OF EMPIRICAL CORRELATIONS AND EQUATIONS OF STATE EFFECTIVENESS FOR COMPRESSIBILITY FACTOR OF NATURAL GAS DETERMINATION

Introduction: Today, there are four main groups of methods for calculating the compressibility factor of natural gas: experimental measurements, equations of state, empirical correlations, modern methods based on genetic algorithms, neural networks, atomistic modeling (Monte Carlo method and molecular dynamics). A correctly chosen method can improve the accuracy of calculating gas reserves and predicting its production and processing. Aim: To find the optimal methods for calculating the z-factor following the characteristic thermobaric conditions. Methods: To determine the best method for calculating the compressibility factor, the effectiveness of using various empirical correlations and equations of state to predict the compressibility factor of hydrocarbon systems (reservoir gases and separation gases) of various compositions were evaluated by comparing numerical results with experimental data. Results and Discussion: Based on 824 experimental values of the compressibility factor for 235 various gas mixtures in the pressure range from 0.1 to 94 MPa and temperatures from 273 to 437 K, the optimal equation of state and empirical correlation dependence for accurate z-factor prediction was found. It is shown that for all gas mixtures the Peng-Robinson equation of state with the shift parameter and Brusilovsky equation of state allow achieving best results. For these methods, the average absolute relative error does not exceed 2%. Among the correlation dependences, the best results are shown by the Sanjari and Nemati Lay; Heidaryan, Moghadasi and Rahimi correlations with an error not exceeding 3%. Conclusions: It was found that for the proposed methods, the reduced pressure has a more significant effect on the accuracy of the calculated values than the reduced temperature. It is shown that when studying acid gas mixtures with a carbon dioxide content of more than 10%, the equations of state better describe the phase behavior of the system in comparison with empirical correlations.

Support Vector Machine Model for Predicting Gas Saturated and Undersaturated Crude Oil Viscosity of Niger Delta Oil Reservoir

Oil viscosity is one of the most important physical and thermodynamic property used when considering reservoir simulation, production forecasting and enhanced oil recovery. Traditional experimental procedure is expensive and time consuming while correlations are replete however they are limited in precision, hence need for a new Machine Learning (ML) models to accurately quantify oil viscosity of Niger Delta crude oil. This work presents use of ML model to predict gas-saturated and undersaturated oil viscosities. The ML used is the Support Vector Machine (SVM), it is applicable for linear and non-linear problems, the algorithm creates a hyperplane that separates data into two classes. The model was developed using data sets collected from the Niger Delta oil field. The data set was used to train, cross-validate, and test the models for reliability and accuracy. Correlation of Coefficient, Average Absolute Relative Error (AARE) and Root Mean Square Error (RMSE) were used to evaluate the developed model and compared with other correlations. Result indicated that SVM model outperformed other empirical models revealing the accuracy and advantage SVM a ML technique over expensive empirical correlations.

Hot Deformation Behavior of Ultralight Dual-Phase Mg-6li Alloy: Constitutive Model and Hot Processing Maps

High-temperature compression tests with dual-phase Mg-6Li alloy were conducted on the Gleeble-3500 thermal-mechanical simulator. Flow stress and micro-structure evolution were analyzed for temperatures (T = 423, 473,523 and 573 K) and strain rates (ε˙= 0.001, 0.01, 0.1 and 1 s−1). On this basis, the constitutive model and hot processing maps were established. Besides, the dynamic re-crystallization (DRX) of α-Mg phase, grain orientation and texture composition under different deformation conditions were analyzed by EBSD technology. The experimental results show that the flow stress of Mg-6Li alloy increased with decreasing deformation temperature and increasing strain rate. In addition, the range of instability zone expanded with the increase of strain. The optimal thermal processing temperature was found to be in the range of 500 K–573 K, and the optimal strain rates were between 0.01 s−1–1 s−1. Model-predicted stress values were compared with experimental values for model verification. The 0.9954 correlation coefficient and the 5.48% average absolute relative error shown by the calculation indicate an acceptable accuracy of the model in predicting thermal deformation behavior of Mg-6Li alloy. Moreover, based on our EBSD data and maps analysis, the DRX proportion of α-Mg phase in Mg-6Li alloy was relatively low, and α-Mg phase formed <0001>//CD basal texture.

A user-friendly finite element model for radial mode abrasive waterjet turning

This paper aims to develop a finite element (FE) model precisely simulating the multi-particle impact in the radial mode abrasive waterjet turning (AWJT). An explicit dynamic analysis was carried out to predict the crater profile resulting from the impact of the abrasive particles along a limited segment of the jet pass over the workpiece surface. The effect of both momentum transfer loss and abrasive load ratio was taken into consideration while calculating the impact velocity of the abrasive particles. To build a user-friendly model, the scripting feature of ABAQUS was involved to automatically perform all the repetitive modeling procedures. The presented FE model considers four variable turning parameters tested at five levels each, including impact velocity, abrasive mass flow rate, traverse rate, and workpiece speed. The obtained crater profile from the simulation process was utilized to calculate the depth of cut (DOC) at different parameter combinations. A comparison between the numerical and experimental results shows a good agreement with an average absolute relative error of 9.74%.

Application of the Strain Compensation Model and Processing Maps for Description of Hot Deformation Behavior of Metastable β Titanium Alloy

The flow behavior of metastable β titanium alloy was investigated basing on isothermal hot compression tests performed on Gleeble 3800 thermomechanical simulator at near and above β transus temperatures. The flow stress curves were obtained for deformation temperature range of 800–1100 °C and strain rate range of 0.01–100 s−1. The strain compensated constitutive model was developed using the Arrhenius-type equation. The high correlation coefficient (R) as well as low average absolute relative error (AARE) between the experimental and the calculated data confirmed a high accuracy of the developed model. The dynamic material modeling in combination with the Prasad stability criterion made it possible to generate processing maps for the investigated processing temperature, strain and strain rate ranges. The high material flow stability under investigated deformation conditions was revealed. The microstructural analysis provided additional information regarding the flow behavior and predominant deformation mechanism. It was found that dynamic recovery (DRV) was the main mechanism operating during the deformation of the investigated β titanium alloy.