Results
Failure Forensics of Shaped PDC Cutters Using Image Analysis and Deep Learning
Liu, Wei (MOE Key Laboratory of Petroleum Engineering, China University of Petroleum (Beijing) / State Key Laboratory of Petroleum Resources and Engineering (Equal contributor)) | Li, Jianchao (MOE Key Laboratory of Petroleum Engineering, China University of Petroleum (Beijing) / State Key Laboratory of Petroleum Resources and Engineering (Equal contributor)) | Gao, Deli (MOE Key Laboratory of Petroleum Engineering, China University of Petroleum (Beijing) / State Key Laboratory of Petroleum Resources and Engineering (Corresponding author))
Summary One of the major advances in polycrystalline diamond compact (PDC) bits in the last 10 years is the global adoption of 3D-shaped PDC cutters. By manipulating the cutter shape based on the understandings of cutterโrock interaction mechanisms, the cutting efficiency and mechanical properties of PDC cutters have been greatly improved. Ongoing innovations in 3D-shaped PDC cutter technology are critical to overcoming the more and more challenging formations in ultradeep wells, such as the 10 000-m-deep wells being drilled in China. Such an important role for 3D-shaped PDC cutters in oil and gas drilling applications necessitates a complete and effective failure analysis method. However, the current International Association of Drilling Contractors (IADC) dull grading cannot fulfill this objective. It is out of date in judging the damages to PDC bits and exhibits more limitations in addressing the unique challenges presented by complicated cutter shapes. To address this issue, an intelligent recognition model for PDC bit damage identification was developed based on the image analysis technology and the YOLOv7 algorithm. More than 10,000 dull bit images were used to train and validate this intelligent recognition model, which were collected from 363 PDC bits that suffered different degrees of damage after being used to drill 185 wells in the Sinopec Shengli Oilfield. Compared to the existing models, the developed intelligent recognition model has several notable contributions. First, the developed model is capable of recognizing the damages of various shaped PDC cutters commonly used by the global bit manufacturers, enabling a more accurate assessment of the failure behaviors of shaped cutters and their bits. The detection accuracy of the developed model exceeds 80% based on the confusion matrix. The recognition results by the developed artificial intelligence (AI) model are consistent with the actual failure modes judged by experienced drilling engineers. Second, the developed AI model provides direct qualitative identification of the failure modes and failure reasons for both cutters and PDC bits rather than the quantitative evaluation of the missing diamond layer used by IADC dull grading. Furthermore, the developed model eliminates the effect of reclaimed cutters on the AI detection results based on the implicit use of spatial cues in the YOLOv7 algorithm. The intelligent recognition model developed in this work can provide reliable and valuable guidance for the post-run evaluation, the bit selection for the next run, and the iterative optimization of bit design.
- North America > United States > Texas (0.29)
- Asia > Middle East > UAE (0.28)
- Asia > China > Shandong Province (0.24)
- Well Drilling > Drill Bits > Bit design (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
- Information Technology > Sensing and Signal Processing > Image Processing (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.84)
Abstract When it comes to optimizing drilling, the focus is on running the bit into the well and performing the drilling efficiently. Included in this are methods for optimizing rate of penetration (ROP), determining the right time to change drilling bits, and managing bit run to reduce other drilling costs, such as tripping, hole conditioning, material consumption, and detecting drilling problems at the right time. The present study employs a new approach to drilling bit modeling that utilizes along-string measurement (ASM) data to continuously monitor the status of the drilling bit. A two-pronged approach is employed in the monitoring of drilling bit condition in addition to estimating rock drillability to keep track of change in lithology. First step involves developing a model for polycrystalline compact drilling (PDC) bits. It examines micro forces at the bit cutters and then upscales these forces to parameters applied to the drilling bits, such as weight and torque. Upscaling involves geometric remodeling of bits as equivalent cutters and equivalent blades. In the second part, a data-analytic approach is used to combine continuous measurement of downhole data with the developed experimental-based model. The real-time data is measured by using an along-string measurement system on the wired pipe. The results of this approach can be grouped into three categories. First, the drilling bit condition is estimated in real time in each equivalent cutter. A quantitative assessment could be undertaken based on model output, or a qualitative assessment could be carried out by analyzing specific energy. Having knowledge of the status of bit, the second conclusion is to monitor rock drillability according to variations in specific energy at the bit and publishing numerical value of rock drillability. In addition, the last corollary is to generate knowledge regarding drill string dynamics and the way to differentiate between vibration at the bit and at the drill string. In this paper, however, the first two outcomes are addressed. This approach is tested on a set of ASM data captured during drilling operations on the Norwegian continental shelf. The results are consistent with those reported from the field. Currently, the selection and evaluation of drilling bits requires knowledge of nearby well records. A drilling penetration rate model that requires calibration for a specific field may also be used to estimate bit condition in some cases. This research presents a new bit status simulator that overcomes the limitations of existing techniques by applying a delicate and intelligent application of ASM data to predict drilling events and mitigate them in real-time.
- North America > United States > Texas > Kleberg County (0.24)
- North America > United States > Texas > Chambers County (0.24)
- Geology > Geological Subdiscipline > Geomechanics (0.94)
- Geology > Rock Type (0.88)
- Well Drilling > Wellbore Design > Rock properties (1.00)
- Well Drilling > Drilling Operations (1.00)
- Well Drilling > Drill Bits > Bit design (1.00)
- (2 more...)
- Information Technology > Sensing and Signal Processing (1.00)
- Information Technology > Architecture > Real Time Systems (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Evolutionary Systems (0.46)
Drill Bit Failure Forensics Using 2D Bit Images Captured at the Rig Site
Chu, Jian (The University of Texas at Austin (Corresponding author)) | Ashok, Pradeepkumar (The University of Texas at Austin) | Witt-Doerring, Ysabel (The University of Texas at Austin) | Yan, Zeyu (The University of Texas at Austin) | van Oort, Eric (The University of Texas at Austin) | Chen, Dongmei (The University of Texas at Austin)
Summary Identifying the root cause of damage of a pulled bit as soon as possible will aid in preparation for future drilling operations. Today, bit damage analyses are often time-consuming, delayed, subjective, and error prone. A novel automated forensics approach is presented in this paper for polycrystalline diamond compact (PDC) bit damage root cause analysis using 2D bit photos that can be easily captured on a phone or camera at the rigsite. A labeled data set consisting of 125 actual bit images and 800 synthetic images was first created with the cutters appropriately identified and labeled. Using this data set, a convolutional neural network (CNN) along with other image processing techniques was applied to first identify the individual cutters and their positions on the bit and then to quantify the damage to the cutters. A cutter detection accuracy of over 97% and a damage quantification accuracy of 97% were achieved. A separate classifier was then trained to directly identify the root cause of failure from the bit images. This classifier utilized a separate data set that consisted of multiple bit images from 25 distinct bit runs. This data set was labeled into different types of failure mechanisms through analysis by a subject-matter expert. The trained classifier developed could properly identify the root causes of failure when the bit photo quality met certain minimum standards. One key observation was that bit images are not always captured appropriately, and this reduces the accuracy of the proposed methodology. By identifying the potential root causes of PDC damage through image processing, drilling parameters can be optimized to prolong future bit life.
- North America > United States > Texas > Permian Basin > Delaware Basin (0.99)
- North America > United States > New Mexico > Permian Basin > Delaware Basin (0.99)
- Well Drilling > Drill Bits > Bit design (1.00)
- Well Drilling > Drill Bits > Bit - rock interactions (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
- Information Technology > Sensing and Signal Processing > Image Processing (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.34)
In the absence of downhole sensors, the drill bit is one of the best indicators of downhole conditions. Quick evaluation of a drill bit after it has been pulled out, can help optimize drilling parameter and bit selection for subsequent bit runs. Traditionally the evaluation of drill bits is performed by the crew at the rig site and (or) drill bit subject matter experts who are typically off site. Such evaluations tend be to be subjective and are often biased depending on the background of the person doing the evaluation. AI applied to object recognition and image processing has developed to a level of sophistication whereby the task of drill bit forensics can be fully automated โ and a lot of the subjectivity removed from the process.
- Instructional Material > Course Syllabus & Notes (0.38)
- Instructional Material > Online (0.37)
- Energy > Oil & Gas > Upstream (1.00)
- Education > Educational Technology > Educational Software > Computer Based Training (0.89)
- Well Drilling > Drill Bits (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
- Information Technology > Artificial Intelligence > Applied AI (0.89)
- Information Technology > Sensing and Signal Processing > Image Processing (0.73)
- Information Technology > Enterprise Applications > Human Resources > Learning Management (0.42)
Abstract North America shale drilling is a fast-paced environment where downhole drilling equipment is pushed to the limits for maximum rate of penetration (ROP). Downhole mud motor power sections have rapidly evolved to deliver more horsepower and torque, resulting in different downhole dynamics, such as motor back-drive drilling dynamics. This paper investigates the root cause of the motor back-drive dynamics and the bit/BHA damage caused by this. High-frequency (HF) compact drilling dynamics recorders embedded in the mud motor bit box and top sub provide unique measurements to fully understand the reaction of the power section under load relative to the type of rock being drilled. 3-axis shock, gyro and temperature sensors placed above and below the power section measure the dynamic response of power transfer to the bit and associated losses caused by motor back-drive dynamics. Formations with high interfacial severity pose more of a challenge due to the rapid change in formation strength. The torsional energy stored and released in the drill string can be high due to surface rotation-speed/torque output and downhole mud-motor speed/torque. Torsional drill string energy wind-up and release results in variable power output at the bit, inconsistent ROP and rapid fatigue on downhole equipment. Detailed analysis of the high-frequency embedded downhole sensor data as well as Electronic Drilling Recorder (EDR) data provides an in-depth understanding of mud motor dynamics. In one of the "Delaware Basin" field examples from Loving County, Texas, the root cause of the motor back-drive dynamics was identified. A systematic photo documentation of drill bit forensics was performed to precisely document the bit damage from this type of drilling dynamics. The auto-driller weight-on-bit (WOB) and ROP setpoints were examined along with the downhole sensor data and EDR to pinpoint the root cause of drilling dysfunction. A drillstring analytical model was used to predict the torsional natural frequencies, which are compared against the sensor-observed torsional oscillation frequencies. This paper reports a unique case of motor back-drive drilling dynamics caused by auto-driller dysfunction and formation effects. Additionally, a systematic photo documentation of drill bit forensics was applied to thoroughly document motor driven bit damage.
- Overview (0.54)
- Research Report (0.48)
- North America > United States > Texas > Permian Basin > Delaware Basin > Wolfcamp Shale Formation (0.98)
- North America > United States > Texas > Permian Basin > Delaware Basin > Bone Springs Formation (0.98)
- North America > United States > New Mexico > Permian Basin > Delaware Basin > Wolfcamp Shale Formation (0.98)
- North America > United States > New Mexico > Permian Basin > Delaware Basin > Bone Springs Formation (0.98)
- Information Technology > Sensing and Signal Processing (0.68)
- Information Technology > Communications > Networks > Sensor Networks (0.68)
Abstract Over a three-well program the FORGE drill teams reduced well times by more than half, with instantaneous ROP increased over 400% in the thick granite pay zone. At the same time, record footage per bit was increased over 200%. The physics-based, limiter-redesign workflow utilized is described, along with specific changes in design and operational practices. Both are expected to yield similar results in any hard rock, geothermal or similar operations. In 2020, the U.S. Department of Energy (DOE) funded a group at Texas A&M University to develop physics-based practices for the geothermal industry, similar to those that have enabled large gains for many operators in the petroleum industry. Wells in the Frontier Observatory for Research in Geothermal Energy (FORGE) were used to develop and test the workflow and practices. The effort began with sixteen hours of training for all team members, including drilling management. Changes were made in the daily workflow, such as periodic parameter testing, real time recognition and response to the common drilling dysfunctions, limiter identification, and daily discussion of the physics of each limiter and the immediate response required that included remote support personnel. The continual daily emphasis on identification of limiters, combined with training in how each limiter physically worked, created an enabling environment for change Some of the key performance limiters addressed in these FORGE wells included previously held beliefs about limitations on WOB with PDCs, modifications to reduce BHA whirl, use of high WOB to suppress bit whirl, identification and avoidance of resonant RPM, BHA design and drilling practices to reduce the amplitude of borehole patterns to improve weight transfer, and the use of high spurt loss fluid (water) to achieve brittle rock failure. It was eventually possible to increase WOB to the structural limit of the bits (i.e., 68k lbs on 10-5/8" PDC). The bit vendor was engaged continually in daily analysis of digital data and dulls, and bits were redesigned to redistribute cutter wear, increase aggressiveness, and improve life through the increased use of shaped cutters. A significant finding was that contemporary PDC cutters remained relatively unworn for long distances in the FORGE granite regardless of WOB used, if the team is trained to manage dysfunction The mechanism through which the cutters eventually fail is discussed, along with operational and design practices to further extend the run lengths. This paper is intended to serve as a reference, with the basic concepts, science, and real-time practices an operator may consider in developing its physics-based, limiter-redesign workflows.
- Geology > Geological Subdiscipline > Geomechanics (0.47)
- Geology > Rock Type > Igneous Rock > Granite (0.46)
- Government > Regional Government > North America Government > United States Government (1.00)
- Energy > Renewable > Geothermal (1.00)
- Energy > Oil & Gas > Upstream (1.00)
- North America > United States > Texas > Permian Basin > Delaware Basin (0.99)
- North America > United States > New Mexico > Permian Basin > Delaware Basin (0.99)
- Asia > Middle East > Qatar > Arabian Gulf > Rub' al Khali Basin > North Field (0.99)
- Well Drilling > Drilling Operations (1.00)
- Well Drilling > Drill Bits (1.00)
- Reservoir Description and Dynamics > Non-Traditional Resources > Geothermal resources (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Architecture > Real Time Systems (1.00)
- Information Technology > Sensing and Signal Processing (0.93)
Abstract The challenging offshore drilling environment has increased the need for cost-effective operations to deliver accurate well placement, high borehole quality, and shoe-to-shoe drilling performance. As well construction complexity continues to develop, the need for an improved systems approach to delivering integrated performance is critical. Complex bottom hole assemblies (BHA) used in deepwater operations will include additional sensors and capabilities than in the past. These BHAs consist of multiple cutting structures (bit/reamer), gamma, resistivity, density, porosity, sonic, formation pressure testing/sampling capabilities, as well as drilling dynamics systems and onboard diagnostic sensors. Rock cutting structure design primarily relied on data capture at the surface. An instrumented sensor package within the drill bit provides dynamic measurements allowing for better understanding of BHA performance, creating a more efficient system for all drilling conditions. The addition of intelligent systems that monitor and control these complex BHAs, makes it possible to implement autonomous steering of directional drilling assemblies in the offshore environment. In the Deepwater Gulf of Mexico (GOM), this case study documents the introduction of a new automated drilling service and Intelligent Rotary Steerable System (iRSS) with an instrumented bit. Utilizing these complex BHAs, the system can provide real-time (RT) steering decisions automatically given the downhole tool configuration, planned well path, and RT sensor information received. The 6-3/4-inch nominal diameter system, coupled with the instrumented bit, successfully completed the first 5,400-foot (1,650m) section while enlarging the 8-1/2-inch (216mm) borehole to 9-7/8 inches (250mm). The system delivered a high-quality wellbore with low tortuosity and minimal vibration, while keeping to the planned well path. The system achieved all performance objectives and captured dynamic drilling responses for use in an additional applications. This fast sampling iRSS maintains continuous and faster steering control at high rates of penetration (ROP) providing accurate well path directional control. The system-matched polycrystalline diamond (PDC) bit is engineered to deliver greater side cutting efficiency with enhanced cutting structure improving the iRSS performance. Included within the bit is an instrumentation package that tracks drilling dynamics at the bit. The bit dynamics data is then used to improve bit designs and optimize drilling parameters.
- North America > United States > West Virginia > Appalachian Basin (0.99)
- North America > United States > Virginia > Appalachian Basin (0.99)
- North America > United States > Tennessee > Appalachian Basin (0.99)
- (7 more...)
- Information Technology > Architecture > Real Time Systems (0.71)
- Information Technology > Artificial Intelligence (0.50)
- Information Technology > Sensing and Signal Processing (0.47)
Abstract More than two decades have passed since the introduction of the scratch testing method for rock strength determination. The test method typically involves dragging a rigid-shaped cutter across the rock surface at a fixed cutting depth. This depth determines the failure mechanism of the rock, ductile for shallow depths and brittle for deeper. In the ductile mode, intrinsic specific energy is primarily a measure of the unconfined-compressive-strength (UCS), which is pivotal for rate of penetration (ROP) during drilling and for borehole stability analysis. On the contrary, brittle failure can lead to permanent core damage and is usually not desired as it impacts interpretation of the scratch testing results. Consequently, it is imperative to identify the critical depth, and at which transition from ductile to brittle failure occurs which will help optimize rock testing and tool designs. In this study, a novel methodology is proposed utilizing micro-computed tomography (CT) imaging to determine critical depth through morphological analysis of scratch test cuttings. Scratch tests are carried out on Indiana limestone core samples with the cutter-rock interaction geometry characterized by a cutter width of 10mm and a back-rake angle of 15ยฐ. The sample is scratched in the range of 0.05mm to 0.40mm with increments of 0.05mm. Scratch powder is carefully collected after each scratch increment and stored for further analysis. This powder is then loaded into slim rubber tubes and imaged at a high resolution of 1 ยตm with a helical micro-CT scanner. The scans are then reconstructed using a computer program to initiate the visualization of individual grains from each cutter depth including evaluation of grain morphologies. Finally, the results from this morphological analysis are corroborated and compared with three other methods: force response analysis, force inflection point analysis, and the size effect law (SEL). Based on shape analysis, it was found that the transition from ductile to brittle regime occurs at a depth of 0.25mm. Elongation and appearance of the enhanced degree of angularity of the grains as the depth of cut (DOC) increases past 0.25mm was observed. Moreover, large grain sizes were detected and are representative of formation of chips (typical brittle regime response). Furthermore, it is illustrated that the image analysis helps eliminate the ambiguity of force signal analysis and in combination can aid in the critical depth of cut determination. The other methods involving force alone and the SEL are not able to pin-point onset of brittle regime. Using a similar methodology, creation of a database for various rock types is recommended to develop a guide for the depth of cut selection during scratch testing. This novel methodology utilizing micro-CT analysis and comparative study with other techniques will put in place an accurate strategy to determine the critical depth of cut when designing rock scratch testing programs.
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Rock Type > Sedimentary Rock > Carbonate Rock (0.35)
- Well Drilling > Drill Bits (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (0.75)
- Reservoir Description and Dynamics > Reservoir Characterization > Reservoir geomechanics (0.67)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Core analysis (0.54)
- Information Technology > Sensing and Signal Processing > Image Processing (0.34)
- Information Technology > Artificial Intelligence > Vision (0.34)
Summary North American shale drilling is a fast-paced environment where downhole drilling equipment is pushed to the limits for the maximum rate of penetration (ROP). Downhole mud motor power sections have rapidly advanced to deliver more horsepower and torque, resulting in different downhole dynamics that have not been identified in the past. High-frequency (HF) compact drilling dynamics recorders embedded in the drill bit, mud motor bit box, and motor top subassembly (top-sub) provide unique measurements to fully understand the reaction of the steerable-motor power section under load relative to the type of rock being drilled. Three-axis shock, gyro, and temperature sensors placed above and below the power section measure the dynamic response of power transfer to the bit and associated losses caused by back-drive dynamics. Detection of back-drive from surface measurements is not possible, and many measurement-while-drilling (MWD) systems do not have the measurement capability to identify the problem. Motor back-drive dynamics severity is dependent on many factors, including formation type, bit type, power section, weight on bit, and drillpipe size. The torsional energy stored and released in the drillstring can be high because of the interaction between surface rotation speed/torque output and mud motor downhole rotation speed/torque. Torsional drillstring energy wind-up and release results in variable power output at the bit, inconsistent rate of penetration, rapid fatigue on downhole equipment, and motor or drillstring backoffs and twistoffs. A new mechanism of motor back-drive dynamics caused by the use of an MWD pulser above a steerable motor has been discovered. HF continuous gyro sensors and pressure sensors were deployed to capture the mechanism in which a positive mud pulser reduces as much as one-third of the mud flow in the motor and bit rotation speed, creating a propensity for a bit to come to a complete stop in certain conditions and for the motor to rotate the drillstring backward. We have observed the backward rotation of a polycrystalline diamond compact (PDC) drill bit during severe stick-slip and back-drive events (โ50 rev/min above the motor), confirming that the bit rotated backward for 9 milliseconds (ms) every 133.3 ms (at 7.5โHz), using a 1,000-Hz continuous sampling/recording in-bit gyro. In one field test, multiple drillstring dynamics recorders were used to measure the motor back-drive severity along the drillstring. It was discovered that the back-drive dynamics are worse at the drillstring, approximately 1,110โft behind the bit, than these measured at the motor top-sub position. These dynamics caused drillstring backoffs and twistoffs in a particular field. A motor back-drive mitigation tool was used in the field to compare the runs with and without the mitigation tool while keeping the surface drilling parameters nearly the same. The downhole drilling dynamics sensors were used to confirm that the mitigation tool significantly reduced stick-slip and eliminated the motor back-drive dynamics in the same depth interval. Detailed analysis of the HF embedded downhole sensor data provides an in-depth understanding of mud motor back-drive dynamics. The cause, severity, reduction in drilling performance and risk of incident can be identified, allowing performance and cost gains to be realized. This paper will detail the advantages to understanding and reducing motor back-drive dynamics, a topic that has not commonly been discussed in the past.
- North America > United States > Texas (1.00)
- Europe (0.94)
- North America > United States > Texas > Permian Basin > Midland Basin (0.99)
- North America > United States > Texas > Permian Basin > Delaware Basin (0.99)
- North America > United States > New Mexico > Permian Basin > Delaware Basin (0.99)
- Information Technology > Sensing and Signal Processing (1.00)
- Information Technology > Communications > Networks > Sensor Networks (1.00)
- Information Technology > Architecture > Real Time Systems (1.00)
Prediction of Penetration Rate for PDC Bits Using Indices of Rock Drillability, Cuttings Removal, and Bit Wear
Mazen, Ahmed Z. (University of Bradford) | Rahmanian, Nejat (University of Bradford (Corresponding author) | Mujtaba, Iqbal (e-mail: n.rahmanian@bradford.ac.uk)) | Hassanpour, Ali (University of Bradford)
Summary Predicting rate of penetration (ROP) has gained considerable interest in the drilling industry because it is the most-effective way to improve the efficiency of drilling and reduce the operating costs. One way to enhance the drilling performance is to optimize the drilling parameters using real-time data. The optimization of the drilling parameters stands on the fact that drilling parameters are interrelated; that is, corrections in one factor affect all the others, positively or negatively. Analysis of the available models in the literature showed that they did not take into account all factors, and therefore, they might underestimate the ROP. To improve the accuracy of predicting the bit efficiency, a new ROP model is developed to preplan and lower the drilling costs. This approach introduces three parts of the process that were developed to describe the challenge of predicting ROP: aggressiveness or drillability, hole cleaning, and cutters wear, which are interrelated to each other. The approach discusses each process individually, and then the influence of all three factors on ROP is assessed. Taking into account the drilling parameters and formation properties, ROP1 is estimated by use of a new equation. Then, lifting the produced cutting to the surface and evaluating how that affects the bit performance is proposed in the second part of the process (hole cleaning). Finally, wear index is introduced in the third part (wear condition) to predict the reduction of ROP2 caused by cutter/rock friction. The approach serves and could be considered as a baseline to identify all factors that can affect the bit performance. The developed model equations are applied to estimate ROP in three vertical oil wells with different bit sizes and lithology descriptions in Libya. The results indicate that the driven model provides an effective tool to predict the bit performance. The results are found in good agreement with the actual ROP values and achieve an enhancement of approximately 40% as compared to the previous models.
- Asia > Middle East (1.00)
- North America > United States > Texas (0.46)
- Europe > United Kingdom > England (0.28)
- Geology > Geological Subdiscipline > Geomechanics (1.00)
- Geology > Rock Type > Sedimentary Rock (0.69)
- Well Drilling > Wellbore Design > Rock properties (1.00)
- Well Drilling > Drilling Operations (1.00)
- Well Drilling > Drill Bits > Bit design (1.00)
- (2 more...)
- Information Technology > Artificial Intelligence (1.00)
- Information Technology > Architecture > Real Time Systems (1.00)
- Information Technology > Sensing and Signal Processing (0.88)