Surface Drilling Parameters Research Articles

Fracture Pressure Prediction Using Surface Drilling Parameters by Artificial Intelligence Techniques

AbstractSeveral correlations are available to determine the fracture pressure, a vital property of a well, which is essential in the design of the drilling operations and preventing problems. Some of these correlations are based on the rock and formation characteristics, and others are based on log data. In this study, five artificial intelligence (AI) techniques predicting fracture pressure were developed and compared with the existing empirical correlations to select the optimal model. Real-time data of surface drilling parameters from one well were obtained using real-time drilling sensors. The five employed methods of AI are functional networks (FN), artificial neural networks (ANN), support vector machine (SVM), radial basis function (RBF), and fuzzy logic (FL). More than 3990 datasets were used to build the five AI models by dividing the data into training and testing sets. A comparison between the results of the five AI techniques and the empirical fracture correlations, such as the Eaton model, Matthews and Kelly model, and Pennebaker model, was also performed. The results reveal that AI techniques outperform the three fracture pressure correlations based on their high accuracy, represented by the low average absolute percentage error (AAPE) and a high coefficient of determination (R2). Compared with empirical models, the AI techniques have the advantage of requiring less data, only surface drilling parameters, which can be conveniently obtained from any well. Additionally, a new fracture pressure correlation was developed based on ANN, which predicts the fracture pressure with high precision (R2 = 0.99 and AAPE = 0.094%).

Application of Artificial Intelligence Techniques in Predicting the Lost Circulation Zones Using Drilling Sensors

Drilling a high-pressure, high-temperature (HPHT) well involves many difficulties and challenges. One of the greatest difficulties is the loss of circulation. Almost 40% of the drilling cost is attributed to the drilling fluid, so the loss of the fluid considerably increases the total drilling cost. There are several approaches to avoid loss of return; one of these approaches is preventing the occurrence of the losses by identifying the lost circulation zones. Most of these approaches are difficult to apply due to some constraints in the field. The purpose of this work is to apply three artificial intelligence (AI) techniques, namely, functional networks (FN), artificial neural networks (ANN), and fuzzy logic (FL), to identify the lost circulation zones. Real-time surface drilling parameters of three wells were obtained using real-time drilling sensors. Well A was utilized for training and testing the three developed AI models, whereas Well B and Well C were utilized to validate them. High accuracy was achieved by the three AI models based on the root mean square error (RMSE), confusion matrix, and correlation coefficient (R). All the AI models identified the lost circulation zones in Well A with high accuracy where the R is more than 0.98 and RMSE is less than 0.09. ANN is the most accurate model with R=0.99 and RMSE=0.05. An ANN was able to predict the lost circulation zones in the unseen Well B and Well C with R=0.946 and RMSE=0.165 and R=0.952 and RMSE=0.155, respectively.

Coupling rate of penetration and mechanical specific energy to Improve the efficiency of drilling gas wells

Drilling operations for oil or gas wells are very expensive. Optimizing the drilling efficiency and increasing the rate of penetration (ROP) will reduce the overall cost of the drilling operation. Different approaches are utilized to increase the drilling performance including analytical and empirical methods. However, most of the available models have some limitations once they applied for real-time drilling operations. This study presents a new approach for evaluating and improving the drilling operations for real-time applications. Seven ROP models were developed using artificial neural network (ANN) technique. The ANN models were developed using real field data (20,000 data sets) which includes the real-time recording of the surface drilling parameters such as rate of penetration (ROP), weight on bit (WOB), torque, rotation speed (RPM) and mud flow rate (Q). The ANN-based models are able to provide an accurate estimation for the full ROP profile. Thereafter, the predicted ROP was coupled with the calculated MSE in order to optimize the drilling performance. Moreover, and for the first time, a new (ROP/MSE) ratio is suggested, which can be used to assess the drilling operations in a real-time. A new profile of ROP/MSE ratio can be displayed along with the drilling parameter in order to provide a quick and more reliable evaluation for the ongoing drilling operation. The suggested ratio incorporates the impacts of the primary drilling factors which are the drilling speed (ROP) and the required drilling energy (MSE). Also, the seven ANN-based models, developed in this work, can predict the full profile of ROP with an average absolute percentage error (AAPE) of around 7.9% and a correlation coefficient of around 0.92.

Deep Illustration for Loss of Circulation While Drilling

One of the most severe, costly, and time-consuming problems in the drilling operation is the loss of circulation. The drilling fluid accounts for 25–40% of the total cost of the drilling operation. Loss of the drilling fluid will increase the total cost of the drilling operation. Uncontrolled lost circulation of the drilling fluid may result in dangerous well control problem and in some cases the loss of the well. Fluid losses can occur in different formations such as natural fracture, induced fracture, unconsolidated, and cavernous and vugular. The objective of this paper is to deeply understand and illustrate different types of loss of circulation, techniques used to determine the loss rate, and detection of loss zones. In addition, losses mitigation techniques, different lost circulation materials (LCM), and the apparatus used to evaluate the available LCM will be explained in detail. The deep literature review illustrated that lost circulation costs 10–20% of the cost of drilling high-pressure high-temperature wells and 90% of these losses occur in fractured formations. The loss rate depends on the drilling fluid types, and it is generally higher in the case of water-based drilling fluid than in the case of oil-based drilling fluid. It is important to utilize an advanced measurement for losses with high frequency to detect the occurrences of lost circulation quickly and correctly. The measurements of flow rate (flow in and flow out) should be supported by additional data such as logging data, lost circulation information (loss rate and depth), mud properties, and surface drilling parameters. The preventive approach is the most efficient to mitigate the loss of circulation since the use of conventional LCM is not successful in most of the cases because of their limitations. It is vital to consider the size of different fractures encountered while drilling and modify the laboratory equipment to simulate this problem. Loss of circulation is affected by many parameters that are related to formation characterization, drilling parameters, fluid properties, and a lot of other known and unknown factors. Therefore, it is a challenge to predict the loss of circulation. To overcome such challenge, it is recommended to develop a new technique such as artificial intelligence to predict the thief zones and the loss rate by capturing the changes in the drilling mechanical parameters and the fluid properties.

New approach to evaluate the equivalent circulating density (ECD) using artificial intelligence techniques

The equivalent circulation density (ECD) is a very important parameter in drilling high-pressure high-temperature and deepwater wells. ECD is a key parameter during drilling through formations where the margin between the pore pressure and the fracture pressure (FP) is narrow. In these critical formations, the ECD is used to control the formation pressure and prevent kicks. Recent approaches in oilfields to determine ECD depend mainly on using expensive downhole sensors for providing real-time values of ECD. Most of these tools have operational limitations such as high pressure and high temperature which may prevent using these tools in downhole conditions. The objective of this paper is to develop a new approach for predicting ECD using artificial intelligence (AI) techniques from surface drilling parameters [mud weight, drill pipe pressure, and rate of penetration (ROP)]. 2376 data points were used to develop the AI models. The data were collected during the drilling of an 8.5″ vertical hole section. Two AI models were used to estimate the ECD: artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). An empirical correlation for ECD was derived from the optimized ANN model by extracting the weights and biases. The developed ANN and ANFIS models were able to calculate ECD with a correlation coefficient (R) of 0.99 and average absolute percentage error of 0.22% for ANN and ANFIS models, respectively. The developed empirical correlation for the ANN model can be used during well design to choose a correct mud weight to safely drill the well based on the expected drilling parameters. It will also minimize the drilling problems related to ECD such as losses or gains especially in critical situations where the margin between the pore and fracture pressure is very narrow. In addition, using this technique will save cost and time by reducing the need for expensive, complicated downhole tools.

Equivalent formation strength as a proxy tool for exploring for the location and distribution of gas hydrates

Abstract Gas hydrate-bearing layers are normally identified by a seismic imaged bottom simulating reflectors (BSR) or by downhole log responses because of their high acoustic velocity and electric resistivity compared to surrounding formations. These gas hydrate characteristics can also result in contrasting in-situ formation compressive strengths. Here, we describe gas hydrate-bearing layers based on equivalent strength (EST), which relates to in-situ compressive strength, in five exploration boreholes drilled during the Indian National Gas Hydrate Program Expedition 02 (NGHP-02). For Site NGHP-02-23, a representative site for those that were established during NGHP-02, the EST evaluated from drilling parameters shows a constant trend of ∼2 MPa, with some strong peak values in the 0–271.4 m-below-seafloor (mbsf) interval, and a sudden increase up to 4 MPa above the BSR depth (271.4–290.0 mbsf). Below the BSR, the EST stays at ∼2 MPa to the bottom of the hole (378 mbsf). Comparing the EST with logging data and a core sample description suggests that the EST depth profiles reflect the formation lithology and gas hydrate content. The EST increases in sand-rich and gas hydrate-bearing zone. In the lower gas hydrate layers in particular, the EST curve shows the same approximate trend with that of P-wave velocity and resistivity measured during downhole logging. Similar relationships between EST, hydrate layer, and log responses are confirmed in other four sites drilled nearby in NGHP-02 Area B. These results suggest that the EST, as a proxy for in-situ formation strength, can indicate the location and extent of the gas hydrate as well as borehole logging. Although the EST was calculated after drilling, utilizing the recorded surface drilling parameters (weight on bit, top drive torque, RPM and rate of penetration) in this study, the EST can be acquired during drilling using real-time drilling parameters. In addition, the EST only requires drilling performance data without any additional tools or measurements, making it a simple and economical tool for the exploration of gas hydrates.

Bit feed principles and operations of slide drilling

Slide bit feed is often used in the drilling of directional and horizontal wells. How the surface intermittently feeding of drill pipe into the well transfers to down hole drill bit pushing? How to reduce the WOB error due to slide friction between the drill string and the borehole wall? What are the advantages and disadvantages of the existing sliding drilling bit feed technologies? In order to answer these questions, this paper first introduces bit feed principles of the down hole drill string elasticity, the hydraulic oscillator and the hydraulic thruster. Then, introduces the relationships between surface drilling parameters and bottom hole drilling parameters for slide feeding technology of the BHA only with motor, and it also with hydraulic oscillator or it also with hydraulic thruster. Finally, these three technologies are compared. The best is the slide feeding technology of BHA with the hydraulic thruster, WOB is smooth and adjustable, the hydraulic thrusters can be used in tandem and the upper part of the drill string can make short trip while the bit is drilling. Two potential devices facilitating slide feeding are introduced.

A comparative review of modelling and controlling torsional vibrations and experimentation using laboratory setups

Improved drilling performance enables us to drill a high quality well at less cost per foot in the lowest time possible. Drillstring vibration is one of the limiting factors maximizing drilling performance. Also, it has become necessary for drilling oil/gas/geothermal wells in order to optimize surface drilling parameters and to reduce downhole dynamics while drilling. Operating a drillstring above or below the critical speed will definitely reduce vibrations and the probability of premature catastrophic failure of downhole components. Hence, it is necessary to carry out pre-drilling analysis as well as real time analysis of drillstring dynamics. The complexity of the drilling phenomenon makes it impractical to derive models having worldwide acceptability. Modeling the entire drillstring system and validating the results using the laboratory experiments or the field data have been the best practice. Most of the times, the parameters affecting the model's sensitivity are either unknown or insufficiently studied during the modeling which makes the study more challenging. The first part of the current review article summarizes the work carried out by the researcher in the field of modeling and controlling torsional vibrations. The second part highlights the experimental studies carried out in laboratories in order to reproduce modes of vibrations in the laboratory. Based on the past development, further efforts can be outlined in this field in order to improve the quality of reproduction of torsional vibrations in the laboratory. The present article reviews the information which needs to be considered while modeling a complete drilling system and developing a laboratory model to reproduce torsional vibrations.

Model Development of Torsional Drillstring and Investigating Parametrically the Stick-Slips Influencing Factors

Drillstring vibration is one of the limiting factors maximizing drilling performance. Torsional vibrations/oscillations while drilling is one of the sever types of drillstring vibration which deteriorates the overall drilling performance, causing damaged bit, failure of bottom-hole assembly, overtorqued tool joints, torsional fatigue of drillstring, etc. It has been identified that the wellbore-drillstring interaction and well face-drill bit interaction are the sources of excitation of torsional oscillations. Predrilling analysis and real time analysis of drillstring dynamics is becoming a necessity for drilling oil/gas or geothermal wells in order to optimize surface drilling parameters and to reduce vibration related problems. It is very challenging to derive the drillstring model considering all modes of vibrations together due to the complexity of the phenomenon. This paper presents the mathematical model of a torsional drillstring based on nonlinear differential equations which are formulated considering drillpipes and bottom-hole assembly separately. The bit–rock interaction is represented by a nonlinear friction forces. Parametric study has been carried out analyzing the influence of drilling parameters such as surface rotations per minute (RPM) and weight-on-bit (WOB) on torsional oscillations. Influences of properties of drillstring like stiffness and inertia, which are most of the times either unknown or insufficiently studied during modeling, on torsional oscillation/stick-slip is also studied. The influences of different rock strength on rate of penetration (ROP) considering the drilling parameters have also been studied. The results show the same trend as observed in fields.

Multidisciplinary Collaborative Concept Aids Challenging Deepwater Operations in Brazil

This article, written by Editorial Manager Adam Wilson, contains highlights of paper SPE 151186, ’Upgrading the Real-Time Drilling-Optimization Culture in Brazil's Challenging Deepwater Operations: The Utilization of a Remote and Rigsite Multidisciplinary Collaborative Concept,’ by Augusto Borella Hougaz, Danilo S. Gozzi, Isao Fujishima, and Klaus L. Vello, Petrobras, and Sandro Alves, Ian Thomson, Raul Krasuk, SPE, and Frank Buzzerio, Baker Hughes, prepared for the 2012 SPE/IADC Drilling Conference and Exhibition, San Diego, California, 6-8 March. The paper has not been peer reviewed. In Brazil, deepwater well-construction activity has increased significantly since the first major presalt discovery in the Santos basin in 2006. The creation of a multidisciplinary drilling-optimization group, integrated with the operator’s drilling team in 2008, and the introduction of a highly specialized downhole-drilling-dynamics measurement-while-drilling (MWD) tool changed the drilling-optimization concept in Brazil. This new optimization concept pioneered the remote (off-the-rig) downhole drilling-parameters surveillance in deepwater operations. Introduction A novel real-time optimization drilling service was implemented in 2008 with the major deepwater operator in Brazil in the Santos basin. Throughout the implementation and execution of the real-time optimization service, the importance of not only knowing where (wellbore placement) and what (formation evaluation) you are drilling but also how you are drilling, which is mainly driven by the integration between operator and service company, became apparent. After 3 years, it was clearly observed that the higher the integration between service company and operator was in a proactive and collaborative environment, the higher the drilling performance was. Today, in the deepwater Santos basin presalt environment, the real-time optimization drilling service is already part of the drilling program in almost every well, from the top hole section to the reservoir section. Real-Time Drilling-Optimization Team In 2008, to answer the “how” questions in the Santos basin, a new culture of real-time optimization arose with the concept of a multidisciplinary optimization team from the service company acting in collaboration with the major operator in Brazil in an integrated manner to achieve superior performance. To accomplish effective remote and rigsite real-time drilling optimization, it is important to use a highly specialized downhole drilling-dynamics MWD tool that records and transmits real-time dynamics data (e.g., stick/slip, lateral vibration, whirl, and axial vibration) and downhole drilling parameters (e.g., weight on bit, torque, revolutions per minute, and bending moment), which allows for a better judgment of the down-hole conditions while drilling and better support for adjusting the surface drilling parameters to optimize operations, in a continuous feedback cycle (Fig. 1).