This paper highlights the challenges to drilling risers and running equipment for offshore drilling operations from dynamically positioned mobile offshore drilling units (MODUs) in extreme water depths. Whereas nearly all exploratory drilling has occurred in water depths shallower than 3,000-m, Total recently set the water depth record with its Raya-1 well (3,400-m water depth, offshore Uruguay) using the Maersk Valiant drillship. Petrobras has also set a new Brazilian record for exploratory drilling by reaching a water depth of nearly 3,000-m. The 3-BRSA-1296-SES well was drilled to a water depth of 2,988-m the Moita Bonita area, located in the Sergipe Alagoas basin off northeastern Brazil. Several operators have leases that extend into significantly deeper water depths. This paper discusses approaches and criteria to evaluate the suitability these systems for operations in such depths. As drilling water depths increase, candidate MODUs may require additional and/or upgraded subsea and running equipment to perform drilling operations. Some of the main concerns faced at these sites by the existing riser systems include but are not limited to: riser deployment and retrieval○challenges to handling and lift capacity caused by running weight and axial dynamic response,○diverter housing contactrerating / requalification of subsea BOP equipment (particularly control components);utilization of the riser system's rated capacity,riser recoil following planned or emergency riser disconnect,connected operability,collapse pressure rating,storm hangoff of the riser and LMRP,fatigue due to vortex-induced-vibration or wave loads. In such depths, longer and heavier riser equipment, rig motions, submerged weight to mass ratio, hydrostatic pressure, mud flow, stiffness, drag, waves, and current all play important roles on riser system integrity, from the wellhead to rig equipment. In addition, many of these wells are located in remote frontiers and are typically characterized by difficult logistics and harsh environment. These factors exacerbate the complexity and potential risk of already challenging operations. This paper provides general guidelines to evaluate and understand the performance and limitations of existing drilling riser systems on MODUs in moderate and harsh conditions in extreme water depths. The paper will discuss evaluation methods, typical findings and potential mitigations for these issues.
As risers are deployed into deeper water, they are subject to increasingly severe environmental loading due to ocean currents and surface weather. Analytical models of these risers often predict premature failure due to the required safety factors and conservative modeling assumptions. As the design boundaries are extended, field measurements become necessary to assess the accuracy and safety margins associated with these models. Additionally, such measurements are expected to play a prominent role as quantitative structural integrity management programs are formalized and mandated.We have developed a Riser Fatigue Monitoring System (RFMS) to provide field measurements of drilling riser stress and fatigue in real-time. To our knowledge, real-time fatigue monitoring of an entire drilling riser has not been accomplished previously.The RFMS calculates drilling riser stress states using measurements from accelerometers and angular rate sensors inside Subsea Vibration Data Logger (SVDL) modules installed at strategic locations along the riser length. This method is preferred to resistive or fiber optic strain gauges due to the measurement quality and reliability concerns associated with installing such devices subsea. The SVDL units are connected via fiber optic subsea cabling to a central data acquisition system, located topside.Data from each SVDL is displayed as it is acquired, and processed with a sophisticated online computer algorithm to synthesize stress estimates along the entire riser length using a database of riser dynamic modes. The estimates are then processed chronologically via rainflow counting, recording fatigue damage accumulated during the deployment. The fatigue estimates are updated at 15-minute intervals, thereby providing actionable information to the drilling crew in real-time. This enables the crew to make informed and timely responses to damaging events such as loop currents, wave action, or improper tensioner settings. Additionally, the accumulated fatigue damage estimates may be tracked on a per-joint basis as the riser joints are rotated among different well sites, thereby aiding decisions regarding the frequency of joint inspection intervals.Significantly, since the only required online inputs are the dynamic riser response, top tension (TT), and mud weight (MW), fatigue estimates may be calculated without knowledge of the impinging currents or other forcing events (although the fatigue response may be correlated to these data, if available). We deployed the system at two well sites off the coast of Japan at 1,180-and 1,939-meter water depths. It successfully collected and processed data from August to November 2012, recording a number of riser excitation events (and attending fatigue damage) due to operations, weather, and vortex-induced vibration (VIV) while connected to and disconnected from the wellhead.
A digital twin representing the drilling system of a dynamically positioned (DP) mobile offshore drilling unit (MODU) has been developed and deployed in offshore Brazil. The primary output of the digital twin is a set of dynamic watch circles which are generated based off the predicted drift-off behavior of the MODU under real-time environmental conditions. The watch circles, together with vessel and weather status information, are displayed to the crew on board and updated on an hourly basis. This paper describes the development of the software platform on which the digital twin is built, together with the underlying drilling system model and solution parameters, which uniquely include the effect of the marine riser restoring force. Integration with external data streams is presented, including vessel position and heading, riser tension, and environmental data (wind, wave, and current). The system outputs, including the local user interface on the vessel and the output data stream to the operator’s real-time data center via the WITSML protocol, are also described. The digital twin with dynamic watch circle output has been successfully utilized on a campaign of shallow-water wells for plug-and-abandonment (P&A) operations in concert with BOP tethering and subsea realtime monitoring systems. Together, these systems ensured safe operations and wellhead protection in a challenging environment for dynamically positioned MODUs. Additionally, the operator was able to gather correlated data streams monitoring the weather conditions, vessel status, dynamic watch circle estimation, subsea drilling system status, and tether loads. The digital twin and dynamic watch circle system enables drilling and completion operations to be performed under conditions judged to be untenable when evaluated via traditional operability analysis methods involving statistically predicted environmental conditions.
A variety of pumps are employed in all aspects of the oilfield life cycle, such as drilling, completion (including hydraulic fracturing), production, and intervention. There is no well-established method to monitor the pump fault states as they are operating based on sensor feedback. As a result, maintenance is performed either prematurely or reactively, both of which result in wasteful downtime and unnecessary expense. A machine learning based neural network model is used for identifying different fault states in a triplex pump from measured pressure sensor data. In a laboratory test, a triplex pump was seeded with eight different fault states (different combinations of damage in discharge valves, stuffing boxes, and suction valves). The time series data for suction and discharge pressures are recorded for 1500 different runs for a combination of eight different fault states and nominal condition. An efficient neural network model is trained on the observed data. This model is tested with multiple cross validation sets and is seen to have over 90% accuracy in predicting the correct fault class solely from the suction and discharge pressure data. In almost all cases, the model was able to correctly differentiate between the nominal response and response with different faults in the system. Different parameter transformation or feature engineering is performed to select optimal input features for the machine learning model. This work demonstrates that machine learning techniques can accurately predict different faults in pumps in operation from monitoring the suction and the discharge pressure. This work also demonstrates the importance using engineering domain knowledge for feature extraction and feature manipulation in creating insightful machine learning models.
Machine learning is gaining rapid popularity as a tool of choice for applications in almost every field. In the oil and gas industry, machine learning is used as a tool for solving problems which could not be solved by traditional methods or for providing a cost-effective and faster data driven solution. Engineering expertise and knowledge of fundamentals remain relevant and necessary to draw meaningful conclusions from the data-based models. Two case studies are presented in different applications that will illustrate the importance of using engineering domain knowledge for feature extraction and feature manipulation in creating insightful machine learning models. The first case study involves condition-based monitoring (CBM) of pumps. A variety of pumps are employed in all aspects of the oilfield life cycle, such as drilling, completion (including hydraulic fracturing), production, and intervention. There is no well-established method to monitor the pump fault states as they are operating based on sensor feedback. As a result, maintenance is performed either prematurely or reactively, both of which result in wasteful downtime and unnecessary expense. A machine learning based neural network model is used for identifying different fault states in a triplex pump from measured pressure sensor data. In the second case study, failures of mooring lines of an offshore floating production unit are predicted from the vessel position data. Identifying a damaged mooring line can be critical for the structural health of the floating production system. In offshore floating platforms, mooring line tension is highly correlated to a vessel’s motions. The vessel position data is created from running coupled analysis models. A K-Nearest-Neighbor (KNN) classifier model is trained to predict mooring line failures. In all the case studies, the importance of combining a deep understanding of the physics of the problem with machine learning tools is emphasized.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.