Real-Time Prediction of Mud Motor Failure Using Surface Sensor Data Features and Trends

2021 ◽  
Author(s):  
Tesleem Lawal ◽  
Pradeepkumar Ashok ◽  
Eric van Oort ◽  
Dandan Zheng ◽  
Matthew Isbell
Keyword(s):  
Real Time ◽  
Cost Optimization ◽  
Damage Index ◽  
Sensor Data ◽  
Drilling Parameters ◽  
Wear And Tear ◽  
Drilling Operations ◽  
Downhole Measurements ◽  
The Impact ◽  
Motor Failure

AbstractMud motor failure is a significant contributor to non-productive time in lower-cost land drilling operations, e.g. in North America. Typically, motor failure prevention methodologies range from re-designing or performing sophisticated analytical modeling of the motor power section, to modeling motor performance using high-frequency downhole measurements. In this paper, we present data analytics methods to detect and predict motor failures ahead of time using primarily surface drilling measurements.We studied critical drilling and non-drilling events as applicable to motor failure. The impacts of mud motor stalls and drill-off times were investigated during on-bottom drilling. For the off-bottom analysis, the impact of variations in connection practices (pick up practices, time spent backreaming, and time spent exposing the tools to damaging vibrations) was investigated. The relative importance of the various features found to be relevant was calculated and incorporated into a real-time mud motor damage index.A historical drilling dataset, consisting of surface data collected from 45 motor runs in lateral hole sections of unconventional shale wells drilled in early to mid-2019, was used in this study. These motor runs contained a mix of failure and non-failure cases. The model was found to accurately predict motor failure due to motor wear and tear. Generally, the higher the magnitude of the impact stalls experienced by the mud motor, the greater the probability of eventual failure. Variations in connection practices were found not to be a major wear-and-tear factor. However, it was found that connection practices varied significantly and were often driller-dependent.The overall result shows that simple surface drilling parameters can be used to predict mud motor failure. Hence, the value derived from surface sensor information for mud motor management can be maximized without the need to run more costly downhole sensors. In addition to this cost optimization, drillers can now monitor motor degradation in real-time using the new mud motor index described here.

Case Studies for the Successful Deployment of Wells Augmented Stuck Pipe Indicator in Wells Real Time Centre

2021 ◽  
Author(s):  
Meor M. Meor Hashim ◽  
M. Hazwan Yusoff ◽  
M. Faris Arriffin ◽  
Azlan Mohamad ◽  
Tengku Ezharuddin Tengku Bidin ◽  
...  
Keyword(s):  
Real Time ◽  
Case Studies ◽  
Drilling Fluid ◽  
Drill String ◽  
Drilling Operation ◽  
Cost Impact ◽  
Drilling Parameters ◽  
The Impact ◽  
Productive Time ◽  
Specific Challenge

Abstract The restriction or inability of the drill string to reciprocate or rotate while in the borehole is commonly known as a stuck pipe. This event is typically accompanied by constraints in drilling fluid flow, except for differential sticking. The stuck pipe can manifest based on three different mechanisms, i.e. pack-off, differential sticking, and wellbore geometry. Despite its infrequent occurrence, non-productive time (NPT) events have a massive cost impact. Nevertheless, stuck pipe incidents can be evaded with proper identification of its unique symptoms which allows an early intervention and remediation action. Over the decades, multiple analytical studies have been attempted to predict stuck pipe occurrences. The latest venture into this drilling operational challenge now utilizes Machine Learning (ML) algorithms in forecasting stuck pipe risk. An ML solution namely, Wells Augmented Stuck Pipe Indicator (WASP), is developed to tackle this specific challenge. The solution leverages on real-time drilling database and supplementary engineering design information to estimate proxy drilling parameters which provide active and impartial pattern recognition of prospective stuck pipe events. The solution is built to assist Wells Real Time Centre (WRTC) personnel in proactively providing a holistic perspective in anticipating potential anomalies and recommending remedial countermeasures before incidents happen. Several case studies are outlined to exhibit the impact of WASP in real-time drilling operation monitoring and intervention where WASP is capable to identify stuck pipe symptoms a few hours earlier and provide warnings for stuck pipe avoidance. The presented case studies were run on various live wells where restrictions are predicted stands ahead of the incidents. Warnings and alarms were generated, allowing further analysis by the personnel to verify and assess the situation before delivering a precautionary procedure to the rig site. The implementation of the WASP will reduce analysis time and provide timely prescriptive action in the proactive real-time drilling operation monitoring and intervention hub, subsequently creating value through cost containment and operational efficiency.

Valuable Cuttings-Based Petrophysic Analysis Successfully Reduces Drilling Risk in HPHT Formations

2021 ◽  
Author(s):  
Jianlin Chen ◽  
Yanhua Yao ◽  
Yingbiao Liu ◽  
Zhaofei Wang ◽  
Craig Collier ◽  
...  
Keyword(s):  
Real Time ◽  
Fluid Loss ◽  
Bottom Line ◽  
Rock Density ◽  
Drilling Parameters ◽  
Drilling Operations ◽  
Analysis Application ◽  
Time Basis ◽  
Compressional Strength ◽  
Drilling Conditions

Abstract Cuttings data has always been neglected or forgotten as a source of information by many operators. In some areas, it is even common practice to throw away cuttings in order to reduce cost. However, cuttings data can yield a great amout of information to provide great value and support to drilling operations, as well as reduce potential downhole risks. This was evident in wells drilled in remote Western regions of China, where wells typically have high temperature high pressure (HTHP) formations with a true vertical depth ranging between 4000-7000 meters and target formation temperature between 150-160 degrees Celcius. Due to severe drilling conditions, the measurement tools of Logging While Drilling (LWD) and Measured While Drilling (MWD) are at high risk of running into holes. Even due to the high formations’ temperatures is over the bottom line of LWD and MWD tools, the sensors of LWD and MWD cannot work efficiently in such circumstances, increasing the drilling risk and expense. Thus, "blind" drilling is the most reasonable economical choice for local operators. Without sufficient real-time formations’ information, the drilling uncertainties dramatically increase. The fluid loss, pipe stuck, as well as drilling bit damages frequently occur. Currently, there is no successful well that accesses to the target reservoir. The data from the wireline logs and cores cannot be available, as the well is the first exploration well in the block; however, during drilling, only drill cuttings are available for peoples. The creative cutting-based petrophysics models are built for the formation analysis that is able to provide rock density, cuttings gamma, Delta Time of Compressional Acoustic (DTC), Unconfined Compressional Strength (UCS) Index, Caliper Index, Brittleness Index, and Hydrocarbon Index from the cuttings samples at the wellsite on a near-real-time basis. This data can help people quantitatively and qualitatively evaluate the downhole formations on a near-real-time basis and can help people to make a more reasonable decision, and therefore, reduce the drilling risk within a controlled level. The authors provide the several cases to study the cutting models into drilling events, and proves the models are consistent with log and core data, and match the drilling parameters and like ROP, and pumping pressure, as well as torque, and bit performance. LWD and MWD are unable to run into the hole due to high formation pressure and extreme risky hole. The field portable XRF instrument is applied, and the mineralogy and elements input into the models. The cuttings petrophysics analysis application can provide the valuable information for drilling engineers to drill the wells to TD.

Improved Drilling Operations with Wired Drill Pipe and Along-String Measurements – Learnings and Highlights from Multiple North Sea Deployments

2021 ◽  
Author(s):  
Børge Engdal Nygård ◽  
Espen Andreassen ◽  
Jørn Andre Carlsen ◽  
Gunn Åshild Ulfsnes ◽  
Steinar Øksenvåg ◽  
...  
Keyword(s):  
Continental Shelf ◽  
Real Time ◽  
High Speed ◽  
Drill Pipe ◽  
Large Data ◽  
Drill String ◽  
Bottom Hole Assembly ◽  
Drilling Operations ◽  
Downhole Measurements ◽  
Remote Operations

Abstract Over the last few years, multiple wells have been drilled in the Norwegian Continental Shelf (NCS) and the United Kingdom Continental Shelf (UKCS) using wired drill pipe (WDP). This paper captures highlights from using real-time downhole measurements provided by WDP, for improved drilling operations. It presents learnings on how WDP measurements have been used in the operator's decision process. As part of WDP, along-string measurement subs (ASM) are equipped with temperature, annular/internal pressure, rotation and vibrations sensors. Data is transmitted to surface at high speed and is available in real-time, even when flow is off. The data provide great insight into the hole conditions along the drill string and at the bottom hole assembly (BHA). Based on this insight, drilling parameters at surface can be accurately adjusted, resulting in increased overall efficiency. Large data amounts can be communicated to and from surface with negligible time delay and independent from fluid circulation. Displaying the downhole measurements in real-time, both at the rig site and in remote operations centers has proven essential when optimising well construction activities. All parties need to access the same information in real-time. Moreover, the data need to be presented in an intuitive manner that enable improved operational decisions. To maximize WDP values, the Operator has learned that downhole data must be used to adjust drilling operations in real-time.

Fracture Pressure Prediction Using Surface Drilling Parameters by Artificial Intelligence Techniques

2020 ◽  
Vol 143 (3) ◽  
Author(s):  
Abdulmalek Ahmed ◽  
Salaheldin Elkatatny ◽  
Abdulwahab Ali
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Optimal Model ◽  
Time Data ◽  
Fracture Pressure ◽  
Drilling Parameters ◽  
Drilling Operations

Abstract Several 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%).

Seismic-while-drilling applications from the first DrillCAM trial with wireless geophones and instrumented top drive

2020 ◽  
Vol 39 (6) ◽  
pp. 422-429
Author(s):  
Andrey Bakulin ◽  
Ali Aldawood ◽  
Ilya Silvestrov ◽  
Emad Hemyari ◽  
Flavio Poletto
Keyword(s):  
Real Time ◽  
Polycrystalline Diamond ◽  
Drill String ◽  
Sensor Data ◽  
Continuous Data ◽  
Near Surface ◽  
Initial Application ◽  
Look Ahead ◽  
Drilling Operations ◽  
Single Sensor

Advanced geophysical sensing while drilling is being driven by trends to automate and optimize drilling and the desire to better characterize complex near surface and overburden in desert environments. We introduce the DrillCAM system, which combines a set of geophysical techniques from seismic while drilling (SWD), drill-string vibration health, estimation of formation properties at the bit, and imaging ahead of and around the bit. We present data acquisition, processing, and initial application results from the first field trial on an onshore well in a desert environment. In this study, we focus on SWD applications. For the first time, wireless geophones installed around a rig were used to acquire continuous data while drilling. We demonstrate the feasibility of such a system to provide flexible acquisition geometries that are easily expandable with increasing bit depth without interference from drilling operations. Using a top-drive sensor as a pilot, we transform the drill-bit noise into meaningful and reliable seismic signals. The data were used to retrieve a check shot while drilling, make kinematic look-ahead predictions, and obtain a vertical seismic profiling corridor stack matching surface seismic. Robust near-offset check-shot signals were received from roller-cone and polycrystalline diamond compact (PDC) bits above 7200 ft after limited preprocessing of challenging single-sensor data with supergrouping. Detecting signals from deeper sections drilled with PDC bits may require more advanced processing by using an entire 2D spread of wireless geophones and downhole pilots. The real-time capabilities of the system make the data available for continuous data processing and interpretation that will facilitate drilling automation and improve real-time decision making.

scholarly journals Digital Triplet Approach for Real-Time Monitoring and Control of an Elevator Security System

Designs ◽  
2020 ◽  
Vol 4 (2) ◽  
pp. 9 ◽  
Author(s):  
Michael M. Gichane ◽  
Jean B. Byiringiro ◽  
Andrew K. Chesang ◽  
Peterson M. Nyaga ◽  
Rogers K. Langat ◽  
...  
Keyword(s):  
Machine Learning ◽  
Object Recognition ◽  
Real Time ◽  
Learning Algorithm ◽  
Performance Testing ◽  
Sensor Data ◽  
Security Measures ◽  
Monitoring And Control ◽  
Digital Twin ◽  
The Impact

As Digital Twins gain more traction and their adoption in industry increases, there is a need to integrate such technology with machine learning features to enhance functionality and enable decision making tasks. This has lead to the emergence of a concept known as Digital Triplet; an enhancement of Digital Twin technology through the addition of an ’intelligent activity layer’. This is a relatively new technology in Industrie 4.0 and research efforts are geared towards exploring its applicability, development and testing of means for implementation and quick adoption. This paper presents the design and implementation of a Digital Triplet for a three-floor elevator system. It demonstrates the integration of a machine learning (ML) object detection model and the system Digital Twin. This was done to introduce an additional security feature that enabled the system to make a decision, based on objects detected and take preliminary security measures. The virtual model was designed in Siemens NX and programmed via Total Integrated Automation (TIA) portal software. The corresponding physical model was fabricated and controlled using a Programmable Logic Controller (PLC) S7 1200. A control program was developed to mimic the general operations of a typical elevator system used in a commercial building setting. Communication, between the physical and virtual models, was enabled using the OPC-Unified Architecture (OPC-UA) protocol. Object recognition using “You only look once” (YOLOV3) based machine learning algorithm was incorporated. The Digital Triplet’s functionality was tested, ensuring the virtual system duplicated actual operations of the physical counterpart through the use of sensor data. Performance testing was done to determine the impact of the ML module on the real-time functionality aspect of the system. Experiment results showed the object recognition contributed an average of 1.083 s to an overall signal travel time of 1.338 s.

STEP Change in Preventing Stuck Pipe and Tight Hole Events Using Machine Learning

2021 ◽  
Author(s):  
Salah Bahlany ◽  
Mohammed Maharbi ◽  
Saud Zakwani ◽  
Faisal Busaidi ◽  
Ferrante Benvenuti
Keyword(s):  
Oil And Gas ◽  
Wellbore Stability ◽  
Sensor Data ◽  
Pilot Phase ◽  
Stability Problems ◽  
Engineering Data ◽  
Execution Phase ◽  
Drilling Parameters ◽  
Drilling Operations ◽  
Productive Time

Abstract Wellbore stability problems, such as stuck pipe and tight spots, are one of the most critical risks that impact drilling operations. Over several years, Oil and Gas Operator in Middle East has been facing problems associated with stuck pipe and tight spot events, which have a major impact on drilling efficiency, well cost, and the carbon footprint of drilling operations. On average, the operator loses 200 days a year (Non-Productive Time) on stuck pipe and associated fishing operations. Wellbore stability problems are hard to predict due to the varying conditions of drilling operations: different lithology, drilling parameters, pressures, equipment, shifting crews, and multiple well designs. All these factors make the occurrence of a stuck pipe quite hard to mitigate only through human intervention. For this reason, The operator decided to develop an artificial intelligence tool that leverages the whole breadth and depth of operator data (reports, sensor data, well engineering data, lithology data, etc.) in order to predict and prevent wellbore stability problems. The tool informs well engineers and rig crews about possible risks both during the well planning and well execution phase, suggesting possible mitigation actions to avoid getting stuck. Since the alarms are given ahead of the bit, several hours before the possible occurrence of the event, the well engineers and rig crews have ample time to react to the alarms and prevent its occurrence. So far, the tool has been deployed in a pilot phase on 38 wells giving 44 true alarms with a recall of 94%. Since mid-2021 operator has been rolling out the tool scaling to the whole drilling operations (over 40 rigs).

Drilling in the Digital Age: Sensors in Bit and Underreamer Improves Future BHA Design Offshore Mexico

2021 ◽  
Author(s):  
Peter Batruny ◽  
Zuriel Aburto ◽  
Pete Slagel ◽  
M Razali Paimin ◽  
Mohamad Mahran ◽  
...  
Keyword(s):  
Sensor Data ◽  
Element Analysis ◽  
Stick Slip ◽  
High Data ◽  
Fea Model ◽  
Drilling Parameters ◽  
Bottom Hole Assembly ◽  
Drilling Operations ◽  
Drilling Parameter ◽  
The Individual

Abstract Downhole vibration is the primary cause of low Rate of Penetration (ROP), and severe vibration causes Bottom Hole Assembly (BHA) tool failure; it is especially apparent during Hole Enlargement While Drilling (HEWD) due to multiple points of cutter contact with the formation at the bit and the underreamer. Electronic, high data rate sensors, embedded in the 17-1/2 in. bit and the 22 in. underreamer, generated detailed insights on the location, mechanism, and magnitude of downhole vibration. Time-based downhole vibration logs from the sensors were plotted alongside mudlogging data. Finite Element Analysis (FEA) models were run using actual drilling parameters to simulate downhole conditions and provide a baseline model for further optimization. Sensor data was isolated for each of the bit and underreamer to better understand the individual and combined vibration mechanisms during hole enlargement while drilling operations. The FEA model was then used to optimize BHA configuration and underreamer placement that result in the largest drilling parameter window for future BHAs. The data from sensors showed that whirl occurred when the bit entered sandstone bodies and the underreamer was still in shale. The data also showed that when the bit was in shale and the underreamer in sandstone, the underreamer experienced stick slip which induced stick slip at the bit. The BHA dynamics model run with actual drilling parameters showed a narrow drilling window with multiple critical vibration points at the same rotation speed (RPM). A new BHA was developed for the next well with a wider drilling window and less critical vibration points for the same RPM. The analysis identified key operational mitigations when stick slip or whirl are encountered. This work leveraged technology and insights generated from data to shorten the learning curve and improve operations after just one well. In a drilling age where operations are becoming increasingly complex, relying on surface data is no longer enough.

Integrated Real-Time Simulation in an Earth Model – Automating Drilling and Driving Efficiency

2021 ◽  
Author(s):  
Pedro J. Arévalo ◽  
Olof Hummes ◽  
Matthew Forshaw
Keyword(s):  
Real Time ◽  
Sensor Data ◽  
Earth Model ◽  
Seamless Integration ◽  
The North ◽  
Time Simulation ◽  
Drilling Parameters ◽  
Related Risk ◽  
Drilling Engineering ◽  
The North Sea

Abstract Real-time while drilling simulations use an evergreen digital twin of the well, consisting of physics-based models in an earth model to constantly update boundary conditions and parameters while drilling. The approach actively contributes to prediction or early detection of specific drilling issues, thus reducing drilling-related risk, non-productive time (NPT), and invisible-lost time (ILT). The method also unlocks further drilling optimization opportunities, while staying within a safe operative envelope that protects the wellbore. In the planning phase, a run plan is prepared based on drilling engineering simulations – such as downhole hydraulics and Torque and Drag (T&D) – within the lithology and geomechanics of the earth model. While drilling, the run plan continuously evolves as automatic updates with actual drilling parameters refine the simulations. Smart triggering algorithms constantly monitor sensor data at surface and downhole, automatically updating the simulations. Drilling automation services consume the simulation results, shared across an aggregation layer, to predict drilling dysfunctions related to hole-cleaning, downhole pressure, tripping velocity (which might lead to fractured formations or formation fluids entering the wellbore), tight hole and pipe sticking. Drillers receive actionable information, and drilling automation applications are equipped to control specific drilling processes. Case studies from drilling runs in the North Sea and in Middle East confirm the effectiveness of the approach. Deployment on these runs used a modular and scalable system architecture to allow seamless integration of all components (surface data acquisition, drilling engineering simulations, and monitoring applications). As designed, the system allows the integration of new services, and different data providers and consumers.

Sign in / Sign up

Export Citation Format

Share Document