Search

Summary Decision making to optimize the drilling operation is based on a variety of factors, among them real-time interpretation of drilled lithology. Because logging while drilling (LWD) tools are placed some meters above the bit, mechanical drilling parameters are the earliest indicators, although they are difficult to interpret accurately. This paper presents a novel deep learning methodology using mechanical drilling parameters for lithology classification. A cascade of deep neural networks (DNNs) are trained on historical data from wells on a field operated by Equinor. Rather than an end-to-end approach, the drilling parameters are used to estimate LWD sensor readings in an intermediate step using the first DNNs. This allows continuous updates of the models during operation using delayed LWD data. The second DNN takes the virtual LWD estimates as input to predict currently drilled lithology, similar to manual expert interpretation of logs. This configuration takes into account case-dependent [mud, bottomhole assembly (BHA), wellbore geometry] and time-varying (bit wear, wellbore friction) relationships between drilling parameters and LWD readings while assuming a constant rule when using LWD data to classify lithology. Upon completion of training and validation, the system is tested on a separate, unseen wellbore, for which results are presented. Visualizations for true lithology alongside the estimates are given, along with confusion matrices and model accuracy. The system achieves high accuracy on the test set and presents low confusion between classes, meaning that it distinguishes well between the lithologies present in the wellbore. It can be seen that the borders between successive layers of lithology are detected rapidly, which is crucial seen from an optimization standpoint, so the driller may immediately adjust accordingly. It shows promise as an advisory system, capable of accurately classifying currently drilled lithology by continuously adapting to changing downhole conditions. Although we cannot expect perfect estimates of lithology purely based on drilling parameters, we can obtain a preliminary map of the subsurface this way. This novel configuration gives a real-time interpretation of the currently drilled lithology. Thus, the drilling operation can be improved through early information and prompt drilling parameter adjustments to accommodate the current drilling environment.

SummaryIn this paper, we describe measured and simulated downhole pressure variations (“surge and swab”) during drillpipe connections when drilling an ultradeepwater well offshore Brazil on Bacalhau (former Carcará) Field. Floating rig motion caused by waves and swell (“rig heave”) induces surge and swab when the drillstring is suspended in slips to make up or break a drillpipe connection and topside heave compensation is temporarily deactivated. This is a known issue in regions with harsh weather, such as the North Sea, where pressure oscillations of up to 20 bar have been reported during connections. Recorded downhole drilling data from Bacalhau Field reveals significant pressure oscillations downhole (in the same order of magnitude as in the North Sea) each time the drillstring was suspended in slips to make a connection in the subsalt 8½-in. section of the well. Mud losses were experienced around the same well depth, and they might have been caused by surge and swab.Measured surge and swab pressure variations have been reproduced in an advanced proprietary surge and swab simulator that considers rig heave, drillpipe elasticity, well friction, non-Newtonian drilling mud, well trajectory, and geometry. Moreover, findings in this paper suggest that surge and swab was in fact significantly higher than recorded by the measurement while drilling (MWD) tool. The true magnitude of surge and swab is not captured in the recorded MWD data due to low sampling frequency of the downhole pressure recording (one measurement every 6 seconds, a standard downhole pressure sampling rate used on many operations today).This work shows that surge and swab during drillpipe connections on floaters may challenge the available pressure window for some wells, even in regions with calm weather such as Brazil. Managed pressure drilling (MPD) is a technique that improves control of the downhole pressure. It is, however, not possible to compensate fast downhole pressure transients, such as heave-induced surge and swab, using MPD choke topside. This is due to the long distance between the choke and the bit, which translates into a time delay in the same order of magnitude as typical wave and heave periods. A downhole choke combined with continuous circulation is one of the potential solutions.Surge and swab during drillpipe connections can result in a loss or an influx and should be considered in the well planning phase when mud weight, section lengths, etc. are selected.

Neutron log is an important tool for lithology classification. In combination with the density log, it can be used to determine clay content, gas content and shaliness of a lithology. Combined with several logging while drilling (LWD) logs, a precise understanding of subsurface lithology can be achieved. However, logs are mounted some distance behind the bit. A deep neural network (DNN) architecture is used to estimate an at-bit virtual neutron log from drilling parameters. The DNN is trained on historical data from wells on a field operated by Equinor, resulting in a baseline model. Using delayed neutron log measurements, continuously supervising updates to the model is possible during operation. This configuration allows correcting for conditions that are different for every case, such as equipment used, bit wear, friction and well trajectory. The method is validated and tested on separate wellbores, unseen during training. Results are compared between the continuously updating model and the baseline model, where it can be seen that the updating model performs much better. The deviation from measured neutron log is significantly reduced using the updating system compared to the baseline model. Also, plots with true and estimated neutron log reveal that the updating model rapidly adapts to the case-specific conditions of the presented datasets and to a larger extent captures main trends. The system performance indicates that this approach could be used to give preliminary estimates of at-bit neutron, eliminating the delay due to the neutron log tool placement. To the best of our knowledge, a continuously updating system for at-bit neutron log estimation has not been presented before. This kind of approach is believed to increase generalizability, so that the model performs well on a wider range of cases.

Graphical abstract, In the streaming learning setting, an agent is presented with a data stream on which to learn from in an online fashion. A common problem is catastrophic forgetting of old knowledge due to updates to the model. Mitigating catastrophic forgetting has received a lot of attention, and a variety of methods exist to solve this problem. In this paper, we present a divided and prioritized experience replay approach for streaming regression, in which relevant observations are retained in the replay, and extra focus is added to poorly estimated observations through prioritization. Using a real-world dataset, the method is compared to the standard sliding window approach. A statistical power analysis is performed, showing how our approach improves performance on rare, important events at a trade-off in performance for more common observations. Close inspections of the dataset are provided, with emphasis on areas where the standard approach fails. A rephrasing of the problem to a binary classification problem is performed to separate common and rare, important events. These results provide an added perspective regarding the improvement made on rare events.•We divide the prediction space in a streaming regression setting•Observations in the experience replay are prioritized for further training by the model’s current error

The most important contributer to Improved Oil Recovery (IOR) on mature fields is drilling of infill wells. Managed Pressure Drilling (MPD) and Continuous Circulation System (CCS) techniques can be used for improved control of bottomhole pressure when drilling wells in depleted fields with narrow pressure windows, but rig heave is a challenge when drilling from floating drilling units. Rig heave, caused by sea waves, induces pressure oscillations downhole that may exceed the operational pressure window. These oscillations are called "surge & swab" and occur both during tripping in and out of hole as well as during drill pipe connections, when the topside heave compensation system used during drilling is disabled because the drill pipe is put in slips. Downhole choking was introduced as a method to reduce downhole pressure oscillations induced by the rig heave and the concept was tested in laboratory scale and using computer simulations (Kvernland et al., 2018). The simulations were perfomed using a purpose-developed software which utilizes such input variables as wave height, pump flow, drill pipe movements, rig characteristic (RAO), drilling fluid properties as well as well design, drill pipe and Bottom Hole Assembly (BHA) data to simulate downhole pressure, induced by rig heave. The simulator is designed to model dynamic interactions between the drilling fluid and the drill string in a rigorous manner, which gives it ability to accurately predict fast downhole changes, such as ones induced by ocean waves. This paper gives an overview of the surge & swab simulator, describing its capabilities and limitations. Data from drilling of a North Sea well is then used to validate the simulations made using the software. The well, used as example in this paper, was drilled conventionally from a floating rig. The downhole pressure variations recorded during three different drill pipe connections are compared with simulated downhole pressure. The simulations are based on the recorded rig heave as well as the actual drilling fluid, well design and drill pipe data. Results show that there is a good correlation between simulated and actual measured downhole pressure. The surge & swab simulation software is then used to simulate the same drilling pipe connections using three different techniques and combinations of techniques utilized for improved downhole pressure control: (1) Managed Pressure Drilling (MPD) (2) Managed Pressure Drilling combined with Continuous Circulation System (CCS) and (3) MPD combined with CCS and a downhole choke. Results show that rig heave-induced downhole pressure variations are reduced to a level which is considered acceptable for drilling a well with narrow pressure window for the last two cases, while utilization of backpressure MPD alone is not sufficient. The combination of MPD and CCS reduced surge & swab for two out of three connections. For the third and deepest connection, the surge & swab increased. The largest reduction in significant downhole pressure variations (43-68 % vs. conventional drilling for the three connections) occurs when MPD and CCS are combined with downhole choking. Future work will consist of further developing the surge & swab simulator so that it will be possible to utilize it in well planning and as real-time decision support during drilling operations. The simulator will also be developed to include possibility of simulating various well completion operations such as running casings and liners. A prototype of the downhole choke is currently being tested at the mud loop of the Ullrigg test rig facility in Stavanger, Norway, and the next development phase consists of designing and building a complete downhole tool for testing in a well.

We present a novel streaming learning approach, utilizing a deep neural network (DNN) to learn from data available during operation to estimate at-bit density using drilling parameters. Since every wellbore is different, the relationship between drilling parameters and at-bit density varies. Equipment used, well trajectory, friction and bit wear are examples of conditions that affect this relationship and makes a pre-trained model unable to represent an accurate input/output mapping applicable to all wells. However, using delayed density log measurements, continuously supervising updates to the model is possible during operation. The algorithm has been tested on drilling data from wells on a field operated by Equinor and compared to a standard deep learning approach, where results show that a streaming learning approach outperforms the traditional method. Statistical analyses have been performed to verify the statistical significance and effect size on the data sets. Data visualizations using a t-distributed Stochastic Neighbor Embedding (t-SNE) indicate that the relationship between drilling parameters and density log indeed vary between wellbores, making generalizability an issue for a traditional supervised learning approach to this problem, and motivating a streaming learning approach. Using the proposed method, more accurate at-bit estimates can be made, providing preliminary indications ahead of the tool placed 20–30 m behind the bit, which, dependent on rate of penetration (ROP), will be available 20–120min later.

During drilling operations, maintaining a desired downhole pressure between pressure margins is crucial to avoid damage to the formation and the well. The process is highly nonlinear, changing with depth, and every section in every well is different. Standard solutions with PID controllers are widely accepted for this purpose, although methods such as deep reinforcement learning (DRL) could be investigated as an alternative approach. A smooth update deep Q learning algorithm is used to train an agent embedded in a managed pressure drilling system. The aim is to control downhole pressure during pipe connections by use of a topside choke valve with nonlinear characteristics. The agent is trained on previously gathered data, from situations featuring step changes in pressure setpoint and changing mud flows, all at various well depths. After training, the agent is tasked with controlling BHP during connection, herein demonstrated by use of a numerically simulated low-order hydraulics model. Through episodic training, it becomes clear that the agent purely through interaction with the environment, and without any prerequisite knowledge of system dynamics and reward design, converges to an optimal control policy. The trained agent is then tested on pipe connections with well depths in the lower and upper bounds of the training data. The pipe connection scenario presents changes in operating conditions in terms of changing mud flows with changing conditions like increased frictional pressure losses due to increased depth. Still, the results presented show the agent's ability to track a pressure setpoint at various depths in the changing conditions present during connection, while seamlessly incorporating controller constraints. There are several advantages associated with this approach, among them eliminating the need for development of a complex dynamic model for the process. Also, the approach is applicable to both linear and nonlinear systems, deterministic and stochastic systems, and lower- and higher-level decision-making. These methods could possibly also be applied to other key challenges in drilling such as ROP optimization or autonomous directional drilling.

Summary This paper describes measured and simulated downhole pressure variations ("surge and swab") during drill pipe connections when drilling an ultra-deepwater well offshore Brazil on the Carcará field. Floating rig motion caused by waves and swell ("rig heave") induces surge and swab when the drill string is suspended in slips to make up or break a drill pipe connection and topside heave compensation is temporarily deactivated. This is a known issue in regions with harsh weather such as the North Sea, where pressure oscillations of up to 20 bar have been reported during connections. Recorded downhole drilling data from the Carcará field reveals significant pressure oscillations downhole (in the same order of magnitude as in the North Sea) each time the drill string was suspended in slips to make a connection in the sub-salt 8 ½" section of the well. Mud losses were experienced around the same well depth and they might have been caused by surge and swab. Measured surge and swab pressure variations have been reproduced in an advanced proprietary surge and swab simulator that considers rig heave, drill pipe elasticity, well friction, non-Newtonian drilling mud, well trajectory and geometry. Moreover, findings in this paper suggest that surge and swab was in fact significantly higher than recorded by the MWD (Measurement While Drilling) tool. The true magnitude of surge and swab is not captured in the recorded MWD data due to low sampling frequency of the downhole pressure recording (one measurement every six seconds, a standard downhole pressure sampling rate used on many operations today). This work shows that surge and swab during drill pipe connections on floaters may challenge the available pressure window for some wells even in regions with calm weather such as Brazil. Managed Pressure Drilling (MPD) is a technique that improves control of the downhole pressure. It is, however, not possible to compensate fast downhole pressure transients, such as heave-induced surge and swab, using MPD choke topside. This is due to the long distance between the choke and the bit, which translates into a time delay in the same order of magnitude as typical wave and heave periods. A downhole choke combined with continuous circulation is one of potential solutions. Surge and swab during drill pipe connections can result in a loss or an influx and should be considered in the well planning phase when mud weight, section lengths, etc. are selected.

This study investigated the effects of the Partners for Change Outcome Management System (PCOMS) in adult outpatient treatment at a hospital-based mental health clinic. It also investigated whether the effects differed with the timing of the treatment within a 4-year implementation period, with clients' initial distress levels, and between therapists. Adult clients (N = 170) were randomized to treatment as usual (TAU) or routine outcome monitoring (ROM). Twenty therapists provided therapy in both conditions. Therapy outcome was measured by the Behavior and Symptoms Identification Scale (BASIS-32). Data were analyzed in a series of multilevel models (MLMs). Clients in the ROM condition were 2.5 times more likely to demonstrate improvement than those in the TAU condition. Controlling for therapist variability, the overall effect size (ES) in favor of ROM was small (d = 0.26, p = .037). The superiority for ROM over TAU increased significantly over the duration of the study. ROM effects were not moderated by clients' initial distress levels. Differences between therapists accounted for 9%-10% of the variability in outcomes, and there were no significant differences in ROM effects between therapists. ROM was associated with better treatment outcomes independent of clients' initial distress levels. Clients treated later in the study benefitted more from ROM than those treated earlier. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Harsh weather conditions result in severe heave motion on floating drilling rigs. The drill string is heave-compensated during drilling ahead, however, when slips are set during drill pipe connections, the topside heave compensation system is disabled, and the drill string is then moving up and down together with the rig. Pressure oscillations below and around the drill bit, induced by such movement, are known as "surge & swab". These oscillations can be in the order of 20 bar or more during drill pipe connections in the North Sea and pose a serious challenge to drilling of wells with narrow pressure margins from floating rigs in harsh weather environment. A managed pressure drilling (MPD) choke at the surface cannot be used to control rig heave-induced surge & swab due to the fast nature of the pressure oscillations in question, stochastic character of the sea waves that cause them and long time-delay between topside choking and bottomhole response. Continuous Circulation System (CCS) might be able to reduce the pressure oscillations somewhat by maintaining constant mud flow during connections. Computer simulations and laboratory experiments were previously used to investigate a novel method for attenuating surge & swab by utilizing an autonomous choke to be installed in the bottom-hole assembly (BHA). The bottomhole pressure oscillations can be effectively reduced through dynamic in-situ control of the mud flow through BHA by a downhole choke. This paper presents the downhole choke system and the results from the first pilot trial conducted in a mud flow loop at Ullrigg test rig in Stavanger utilizing a full-scale version of the choke. The prototype was subjected to drilling mud with flow rates up to 2500 lpm and differential pressure up to 250 bar to investigate its ability to accurately control the flow while at the same time withstanding the demanding conditions. Satisfactory choke valve characteristics were obtained, indicating ability to control the flow with sufficient precision. Flow testing resulted in severe erosion of carbon steel components while wolfram carbide components were able to withstand the erosive nature of the flow. The test also uncovered challenges related to operation of the choke with high differential pressure and flow rates which could later be related to the motor, used to control the downhole choke assembly. The next phase of the project is to design a downhole prototype and test it in an onshore test well to achieve Technology Readyness Level (TRL) 4 qualification ("ready for first use offshore"). The final goal is to qualify the downhole choke together with MPD and a Continuous Circulation System (CCS) for use on floating drilling rigs in harsh weather environment.

Little is known about the mechanisms through which routine outcome monitoring (ROM) influences psychotherapy outcomes. In this secondary analysis of data from a randomized clinical trial (Brattland et al., 2018), we investigated whether the working alliance mediated the effect of the Partners for Change Outcome Monitoring System (PCOMS), a ROM system that provides session-by-session feedback on clients' well-being and the alliance. Adult individuals (N = 170) referred for hospital-based outpatient mental health treatment were randomized to individual psychotherapy either with the PCOMS ROM system, or without (treatment as usual [TAU]). Treatment was provided by the same therapists (N = 20) in both conditions. A multilevel mediation model was developed to test if there was a significant indirect effect of ROM on client impairment at posttreatment through the alliance at 2 months' treatment controlled for first-session alliance. Alliance ratings increased more from session 1 to 2 months' treatment in the ROM than TAU condition, and alliance increase was associated with less posttreatment impairment. A significant indirect effect of ROM on treatment outcomes through alliance increase (p = .043) explained an estimated 23.0% of the effect of ROM on outcomes. The results were consistent with a theory of the alliance as one mechanism through which ROM works. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

In this paper, a new tool to be placed in the bottomhole assembly (BHA) is introduced for the purpose of counteracting heave-induced down-hole pressure oscillations in offshore drilling. The tool contains a control choke, sensors and computing capability, and will operate autonomously with minimal implications for standard drilling procedures. A small-scale prototype is developed and successfully tested in laboratory experiments showing significant reduction in down-hole pressure oscillations. Realistic, full-scale cases investigated using computer simulations also show good performance. The paper gives a description of the small-scale lab as well as the mathematical model used for the computer simulations. A full-size autonomous choke prototype is currently being constructed for further testing under more realistic conditions. Design aspects of the prototype are presented in the paper.

As oil exploration and development costs rise, the oil industry increases its efforts to improve oil recovery (IOR) from existing fields. IOR is achieved mainly by drilling more wells, but drilling in partially depleted reservoirs is challenging due to narrow pressure margins. Offshore drilling in harsh environments, such as the North Sea, presents additional challenges, since the heaving motion from a floating rig induces large surge and swab pressures in the well. This brief suggests a remedy for this problem using automatic control of well pressure. Taking advantage of an experimental lab facility recently completed at NTNU, a model of the drilling system is developed using subspace identification methods. The model serves as a basis for state estimation and controller design using model predictive control. Applying the controller to the lab facility, pressure oscillations are suppressed by 70%-90% compared with the open-loop case, depending on the period of the heave motion. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works nb_NO