Rock Mechanics
Mahdi Bajolvand; Ahmad Ramezanzadeh; Amin Hekmatnejad; Mohammad Mehrad; Shadfar Davoodi; Mohammad Teimuri; Mohammad Reza Hajsaeedi; Mahya Safari
Abstract
Bit wear is one of the fundamental challenges affecting the performance and cost of drilling operations in oil, gas, and geothermal wells. Since identifying the factors influencing bit wear rate (BWR) is essential, and the ability to predict its variations during drilling operations is influenced by ...
Read More
Bit wear is one of the fundamental challenges affecting the performance and cost of drilling operations in oil, gas, and geothermal wells. Since identifying the factors influencing bit wear rate (BWR) is essential, and the ability to predict its variations during drilling operations is influenced by environmental and operational factors, this study aims to develop an Adaptive Bit Wear Rate Predictor (ABWRP) algorithm for estimating the BWR during drilling operations for new wells. The structure of this algorithm consists of a data transmitter, data processor, deep learning-based bit wear rate estimator, and a bit wear updating module. To develop a model for the BWR estimation module, data from two wells in an oil field in southwest Iran were collected and analyzed, including petrophysical data, drilling data, and bit wear and run records. Both studied wells were drilled using PDC bits with a diameter of 8.5 inches. After preprocessing the data, the key factors affecting the bit wear rate were identified using the Wrapper method, including depth, confined compressive strength, maximum horizontal stress, bit wear percentage, weight on bit, bit rotational speed, and pump flow rate. Subsequently, seven machine learning (ML) and deep learning (DL) algorithms were used to develop the bit wear rate estimation module within the ABWRP algorithm. Among them, the convolutional neural network (CNN) model demonstrated the best performance, with Root Mean Square Error (RMSE) values of 0.0011 and 0.0017 and R-square (R²) values of 0.96 and 0.92 for the training and testing datasets, respectively. Therefore, the CNN model was selected as the most efficient model among the evaluated models. Finally, a simulation-based experiment was designed to evaluate the performance of the ABWRP algorithm. In this experiment, unseen data from one of the studied wells were used as data from a newly drilled well. The results demonstrated that the ABWRP algorithm could estimate final bit wear with a 14% error. Thus, the algorithm developed in this study can play a significant role in the design and planning of new wells, particularly in optimizing drilling parameters while considering bit wear effects.
Exploration
Mahdi Bajolvand; Ahmad Ramezanzadeh; Amin Hekmatnejad; Mohammad Mehrad; Shadfar Davoodi; Mohammad Teimuri
Abstract
Shear Wave Slowness Log (DTSM) is one of the most important petrophysical logs applicable for studying reservoirs, especially geomechanical studying of the oil and gas fields. However, lack of this parameter in wellbore logging can import great sources of uncertainty into geomechanical studies. This ...
Read More
Shear Wave Slowness Log (DTSM) is one of the most important petrophysical logs applicable for studying reservoirs, especially geomechanical studying of the oil and gas fields. However, lack of this parameter in wellbore logging can import great sources of uncertainty into geomechanical studies. This study aims to provide solutions for decreasing the uncertainty of geomechanical models with estimation of the DTSM log using the high accurate deep machine learning models. The main idea is using data from offset fields for extending the range of training data and improving the estimation ability and generalizability of machine learning models. For this purpose, petrophysical data from 8 wells of 4 Iranian oil fields were collected. In the first stage, data preprocessing was performed for reducing the effects of wrong data, missing value, noises, and outliers. Then, machine learning (regression learning-based and deep neural network-based) and analytical models implemented for estimating DTSM. The results indicated that the Gated Recurrent Unit (GRU) model with the values of 1.9 and 2.14 for RMSE and 0.99 for R-square had the most exact answers, for training and test data, respectively. Meanwhile, evaluation of the accuracy of the models on the validation well data indicated that GRU model with the values of 2.43 and 0.93 had been the most accurate model for RMSE and R-square, respectively. Accordingly, using a multi-field comprehensive data bank and applying machine learning methods are strongly recommended to estimate the DTSM, for the cases where limited offset data is available.
Rock Mechanics
A. Asgari; A. Ramezanzadeh; Seyed M. E. Jalali; B. Brouard
Abstract
Ensuring the stability and integrity of underground gas storage salt caverns is a very complicated subject due to the non-linear and time-dependent behavior of rock salts under complicated thermal and mechanical loading conditions. For this reason, pressure and temperature fluctuations in the caverns ...
Read More
Ensuring the stability and integrity of underground gas storage salt caverns is a very complicated subject due to the non-linear and time-dependent behavior of rock salts under complicated thermal and mechanical loading conditions. For this reason, pressure and temperature fluctuations in the caverns and their surrounding strata must be integrated into the analysis and the numerical tools that are used for this purpose. LOCAS, a 2D axisymmetric finite-element code, dedicated to the stability analysis of underground salt spaces, was applied to assess the effects of various operating and geometrical parameters on the cavern behavior. In this paper, we aimed to give an overall assessment of the behavior of the salt caverns used for natural gas storage. In this work, some specific loading scenarios were considered first, followed by thorough parametric and sensitivity analyses to reveal the impacts of the geometrical parameters and operational parameters involved on the behavior of salt caverns using the modern stability criteria. The findings showed that the onset of dilation was more likely to happen within the first cavern life cycle when pressure dropped to the minimum level. As for the potential of tension occurrence in the surrounding rock, this is more likely to happen by increasing the number of operation cycles, especially in the upper one-third of the cavern wall. Finally, it was seen that the cavern depth and minimum cavern internal pressure had even more important influences than the others on the salt cavern behavior.
Rock Mechanics
S. Moshrefi; K. Shahriar; A. Ramezanzadeh; K. Goshtasbi
Abstract
A new failure criterion was presented to predict the ultimate strength of shale under the triaxial and polyaxial state of stress. A database containing 93 datasets was obtained from the results of the uniaxial, triaxial, polyaxial compressive tests, an indirect tensile test was collected from reliable ...
Read More
A new failure criterion was presented to predict the ultimate strength of shale under the triaxial and polyaxial state of stress. A database containing 93 datasets was obtained from the results of the uniaxial, triaxial, polyaxial compressive tests, an indirect tensile test was collected from reliable references, and this test was carried out on the shale samples taken from the southwestern oilfields in Iran. The database was used to evaluate the proposed criterion, and its accuracy was compared against the popular failure criteria in rock mechanics, particularly those used for stability analysis such as the Hoek-Brown, Mohr-Coulomb, Drucker-Prager, and Mogi-Coulomb failure criteria. In order to evaluate the model, seven important statistical indices were selected. Subsequently, curves from various failure criteria were fitted to the triaxial and polyaxial data, and the corresponding coefficients and statistical indices were determined. The results obtained indicated that, in all cases, compared to the other failure criteria, the proposed criterion succeeded to predict the ultimate strength at a higher accuracy. Also the proposed criterion was used calculate the uniaxial compressive and tensile strengths with a minimum error. For a further examination of the proposed criterion, a series of results from the triaxial test including the ductile failure data were utilized for evaluation of the applicability of the proposed criterion to the ductile zone. It showed that the criterion could predict the ultimate strength of shale over a wide range of stresses.
Rock Mechanics
M. B. Eslami Andargoli; K. Shahriar; A. Ramezanzadeh; K. Goshtasbi
Abstract
During the recent decades, the design and construction of underground spaces into rock salt have been particularly regarded for storing petroleum fluids, natural gas, and compressed air energy, and also for disposing nuclear and chemical wastes. The rock salt hosting such spaces will be subjected to ...
Read More
During the recent decades, the design and construction of underground spaces into rock salt have been particularly regarded for storing petroleum fluids, natural gas, and compressed air energy, and also for disposing nuclear and chemical wastes. The rock salt hosting such spaces will be subjected to various types of monotonic/cyclic, short-term/long-term stresses during the construction and/or operation phases. On this basis, it is necessary to investigate the mechanical behavior of the rock salt under the effects of various monotonic short-term/long-term stresses. Out of the most important factors affecting the creep behavior of rock salt are the composition of minerals and size of the crystals comprising the rock salt, humidity, temperature, time, loading scheme, loading rate, strain rate, and loading period. In the present research work, a loading scheme and a loading period were considered. On this basis, in order to achieve a true understanding of the creep behavior of rock salt, it is necessary to determine the creeping coefficients via laboratory tests. Thus, twenty cylindrical (length to diameter ratio > 2) specimens of rock salt were prepared for conducting the creep tests. Two stepwise short-term creep tests (each at three stress levels, namely 4.4, 10.1, and 11.9 MPa, and 7.5, 12, and 17 MPa, respectively) and eighteen long-term creep tests (at six stress levels, namely 5.5, 7.5, 10, 12, 14, and 18 MPa) were conducted. Then, first, the creep coefficients were determined according to the Lubby 2 constitutive model. These coefficients were adjusted using the results of the creep tests. Afterwards, a creep experimental model was presented using linear and nonlinear regression of the creep test data. For validation of the results obtained, both the adjusted Lubby 2 constitutive model and the proposed experimental model were compared with the results obtained for the creep tests. Both models had fairly good agreements with the data for the creep tests at a determination factor of about 93%.
Rock Mechanics
S. Moshrefi; K. Shahriar; A. Ramezanzadeh; K. Goshtasbi
Abstract
A rock failure criterion is very important for prediction of the ultimate strength in rock mechanics and geotechnics; it is determined for rock mechanics studies in mining, civil, and oil wellborn drilling operations. Also shales are among the most difficult to treat formations. Therefore, in this research ...
Read More
A rock failure criterion is very important for prediction of the ultimate strength in rock mechanics and geotechnics; it is determined for rock mechanics studies in mining, civil, and oil wellborn drilling operations. Also shales are among the most difficult to treat formations. Therefore, in this research work, using the artificial neural network (ANN), a model was built to predict the ultimate strength of shale, and comparison was made with support vector machine (SVM), multiple linear regression models, and the widely used conventional polyaxial failure criteria in the stability analysis of rock structures, Drucker-Prager, and Mogi-Coulomb. For building the model, the corresponding results of triaxial and polyaxial tests have been performed on shales by various researchers. They were collected from reliable published articles. The results obtained showed that a feed forward back propagation multi-layer perceptron (MLP) was used and trained using the Levenberg–Marquardt algorithm, and the 2-4-1 architecture with root-mean-square-error (RMSE) of 24.41 exhibits a better performance in predicting the ultimate strength of shale in comparison with the investigated models. Also for further validation, triaxial tests were performed on the deep shale specimens. They were prepared from the Ramshire oilfield in SW Iran. The results obtained were compared with ANN, SVM, multiple linear regression models, and the conventional failure criterion prediction. They showed that the ANN model predicted ultimate strength with a minimum error and RMSE being equal to 43.81. Then the model was used for prediction of the threshold broken pressure shale layer in the Gachsaran oilfield in Iran. For this, a vertical and horizontal stress was calculated based on a depth of shale layer. The threshold broken pressure was calculated for the beginning and ending of a shale layer to be 154.21 and 167.98 Mpa, respectively.
M. Mohammadi Behboud; A. Ramezanzadeh; B. Tokhmechi
Abstract
Multiplicity of the effective factors in drilling reflects the complexity of the interaction between rock mass and drilling bit, which is followed by the dependence of parameters and non-linear relationships between them. Rock mass or, in other words, the formation intended for drilling, as the drilling ...
Read More
Multiplicity of the effective factors in drilling reflects the complexity of the interaction between rock mass and drilling bit, which is followed by the dependence of parameters and non-linear relationships between them. Rock mass or, in other words, the formation intended for drilling, as the drilling environment, plays a very essential role in the drilling speed, depreciation of drilling bit, machines, and overall drilling costs. Therefore, understanding the drilling environment and the characteristics of the in-situ rock mass contributes a lot to the selection of the machines. In this work, a 1D geo-mechanical model of different studied wells is built by collecting the geological data, well logs, drilling data, core data, and pressure measurements of the formation fluid pressure in various wells. Having the drilling parameters of each part of the formation, its specific energy is calculated. The specific energy index can be used for predicting the amount of energy consumed for drilling. In order to find the relationship between the drilling specific energy (DSE) and its effective parameters, the multivariate regression model is used. Modeling DSE is done using the multivariate regression, which contains the parameters rock characteristics, well logs, and a combination of these two features. 70% and 30% of the data are, respectively, selected as the training and test for validation. After analyzing the model, the correlation coefficients obtained for the training and test data were, respectively, found to be 0.79 and 0.83. The parameters uniaxial compressive strength (UCS), internal friction angle, and fluid flow are among the most important factors found to affect DSE.
A. Ramezanzadeh; M. Hood
Abstract
The first step in mining activities is rock excavation in both mine development and production. Constant pressure for cost reduction and creating an improved/safe work environment for personnel has naturally resulted in increased use of mechanical excavation systems in many mining operations. Also, mechanical ...
Read More
The first step in mining activities is rock excavation in both mine development and production. Constant pressure for cost reduction and creating an improved/safe work environment for personnel has naturally resulted in increased use of mechanical excavation systems in many mining operations. Also, mechanical excavation and mining is more compatible with automation, meaning possibility of reduction in number of people in the active underground mines. This factor plays a major role in selection of mining systems especially considering the dire shortage of skilled labour in the industry. While these systems are an integral part of mining activities in underground soft rock mining (coal, salt, potash, trona etc.), there is a need for developing new approaches and machinery for use in the underground hard rock mining. This paper will offer a review of current and emerging technologies for mechanical hard rock excavation, including disc cutting technology, drag picks, mini-disc, and activated/oscillating disc cutter. A review of general guidelines for assessment of the potentials of new research and development on this topic and evaluation of emerging technologies for a specific mining application will also be offered.
