Patent Application
20240175344
Stick-slip is characterized by the absorption and release of energy as a function of a difference between static friction and dynamic friction. In the oilfield industry, stick-slip may occur to a drill string and/or a downhole tool in a wellbore. In one example, stick-slip may occur due to friction between the drill string and/or downhole tool and the side wall of the wellbore. In another example, stick-slip may occur due to friction between the drill bit and the formation through which the drill bit is cutting. The friction may cause a lower portion of the drill string and/or the downhole tool to slow down or stop rotating while an upper portion continues to be rotated by equipment at the surface. This may cause one or more turns or twists to develop in the drill string. As the turns/twists build, the rotational potential energy increases. When the rotational potential energy overcomes the friction force, the drill string and/or downhole tool slip(s), resulting in an uncontrolled rotational speed and/or rotational acceleration in the wellbore.
As will be appreciated, sticking and/or slipping may damage the drill string and/or the downhole tool (e.g., the drill bit), damage the wellbore, cause non-productive time, etc. Systems and methods exist to mitigate stick-slip after the stick-slip is detected. However, it would be desirable to have systems and methods that can predict stick-slip before it occurs.
A method for predicting a stick-slip event is disclosed. The method includes measuring one or more surface properties using a sensor at the surface. The method also includes measuring one or more downhole properties using a downhole tool in a wellbore. The method also includes determining that the one or more surface properties and the one or more downhole properties match a distribution (e.g., a pattern). The distribution occurs before two or more previously-detected stick-slip events. The method also includes determining a likelihood that a stick-slip event will occur based at least partially upon the distribution that the one or more surface properties and the one or more downhole properties match.
In another embodiment, the method includes measuring one or more first surface properties. The method also includes measuring one or more first downhole properties. The method also includes training a model. Training the model includes identifying a plurality of previously-detected stick-slip events. Training the model also includes determining the one or more first surface properties and the one or more first downhole properties that occur before each of the previously-detected stick-slip events. Training the model also includes determining a distribution in the one or more first surface properties and the one or more first downhole properties that occurs before two or more of the previously-detected stick-slip events. The method also includes measuring one or more second surface properties. The method also includes measuring one or more second downhole properties. The method also includes determining that the one or more second surface properties and the one or more second downhole properties match the distribution. The method also includes determining a likelihood that a stick-slip event will occur based at least partially upon the distribution that the one or more second surface properties and the one or more second downhole properties match.
A system for predicting a stick-slip event is also disclosed. The system includes a sensor configured to measure one or more surface properties. The system also includes a downhole tool configured to measure one or more downhole properties. The system also includes a computing system configured to receive the one or more surface properties and the one or more downhole properties. The computing system is also configured to determine that the one or more surface properties and the one or more downhole properties match a distribution. The distribution occurs before two or more previously-detected stick-slip events. The computing system is also configured to determine a likelihood that a stick-slip event will occur based at least partially upon the distribution that the one or more surface properties and the one or more downhole properties match.
It will be appreciated that this summary is intended merely to introduce some aspects of the present methods, systems, and media, which are more fully described and/or claimed below. Accordingly, this summary is not intended to be limiting.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures:
Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to one of ordinary skill in the art that the invention may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.
It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope of the present disclosure. The first object or step, and the second object or step, are both, objects or steps, respectively, but they are not to be considered the same object or step.
The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in this description and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Further, as used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.
Attention is now directed to processing procedures, methods, techniques, and workflows that are in accordance with some embodiments. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined and/or the order of some operations may be changed.
In the example of
In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 can include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114). An entity may be characterized by one or more properties (e.g., a geometrical pillar grid entity of an earth model may be characterized by a porosity property). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.
In an example embodiment, the simulation component 120 may operate in conjunction with a software framework such as an object-based framework. In such a framework, entities may include entities based on pre-defined classes to facilitate modeling and simulation. A commercially available example of an object-based framework is the MICROSOFT® .NET® framework (Redmond, Washington), which provides a set of extensible object classes. In the .NET® framework, an object class encapsulates a module of reusable code and associated data structures. Object classes can be used to instantiate object instances for use in by a program, script, etc. For example, borehole classes may define objects for representing boreholes based on well data.
In the example of
As an example, the simulation component 120 may include one or more features of a simulator such as the ECLIPSE™ reservoir simulator (Schlumberger Limited, Houston Texas), the INTERSECT™ reservoir simulator (Schlumberger Limited, Houston Texas), etc. As an example, a simulation component, a simulator, etc. may include features to implement one or more meshless techniques (e.g., to solve one or more equations, etc.). As an example, a reservoir or reservoirs may be simulated with respect to one or more enhanced recovery techniques (e.g., consider a thermal process such as SAGD, etc.).
In an example embodiment, the management components 110 may include features of a commercially available framework such as the PETREL® seismic to simulation software framework (Schlumberger Limited, Houston, Texas). The PETREL® framework provides components that allow for optimization of exploration and development operations. The PETREL® framework includes seismic to simulation software components that can output information for use in increasing reservoir performance, for example, by improving asset team productivity. Through use of such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes. Such a framework may be considered an application and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc.).
In an example embodiment, various aspects of the management components 110 may include add-ons or plug-ins that operate according to specifications of a framework environment. For example, a commercially available framework environment marketed as the OCEAN® framework environment (Schlumberger Limited, Houston, Texas) allows for integration of add-ons (or plug-ins) into a PETREL® framework workflow. The OCEAN® framework environment leverages .NET® tools (Microsoft Corporation, Redmond, Washington) and offers stable, user-friendly interfaces for efficient development. In an example embodiment, various components may be implemented as add-ons (or plug-ins) that conform to and operate according to specifications of a framework environment (e.g., according to application programming interface (API) specifications, etc.).
As an example, a framework may include features for implementing one or more mesh generation techniques. For example, a framework may include an input component for receipt of information from interpretation of seismic data, one or more attributes based at least in part on seismic data, log data, image data, etc. Such a framework may include a mesh generation component that processes input information, optionally in conjunction with other information, to generate a mesh.
In the example of
As an example, the domain objects 182 can include entity objects, property objects and optionally other objects. Entity objects may be used to geometrically represent wells, surfaces, bodies, reservoirs, etc., while property objects may be used to provide property values as well as data versions and display parameters. For example, an entity object may represent a well where a property object provides log information as well as version information and display information (e.g., to display the well as part of a model).
In the example of
In the example of
As mentioned, the system 100 may be used to perform one or more workflows. A workflow may be a process that includes a number of worksteps. A workstep may operate on data, for example, to create new data, to update existing data, etc. As an example, a may operate on one or more inputs and create one or more results, for example, based on one or more algorithms. As an example, a system may include a workflow editor for creation, editing, executing, etc. of a workflow. In such an example, the workflow editor may provide for selection of one or more pre-defined worksteps, one or more customized worksteps, etc. As an example, a workflow may be a workflow implementable in the PETREL® software, for example, that operates on seismic data, seismic attribute(s), etc. As an example, a workflow may be a process implementable in the OCEAN® framework. As an example, a workflow may include one or more worksteps that access a module such as a plug-in (e.g., external executable code, etc.).
One or more surface sensors (one is shown: 240) may be positioned at the surface (e.g., on the rig 210). The surface sensor 240 may be configured to measure surface physical properties, such as a rate of rotation (e.g., in RPM) of the tubular string 230 at the surface. More particularly, the surface sensor 240 may be configured to measure the rate of rotation imparted to an upper portion of the tubular string 230 by the rig 210 (e.g., by a rotary table and/or kelly of the rig 210). The surface physical properties measured by the surface sensor 240 may also include a torque exerted on the upper portion of the tubular string 230 by the rig 210 (e.g., by the rotary table and/or kelly). The surface physical properties may also include a weight on a drill bit 256 (WOB). The surface physical properties may also include a depth of the drill bit 256.
A downhole tool 250 may be coupled to an end of the tubular string 230 in the wellbore 220. The downhole tool 250 may be or include a measurement-while drilling (MWD) tool 252, a logging-while-drilling (LWD) tool 254, and the drill bit 256. The MWD 252 and/or the LWD 254 may be configured to measure downhole properties as the drill bit 256 drills the wellbore 220 farther into the subterranean formation 222. For example, the downhole tool 250 (e.g., the MWD 252) may be configured to measure downhole physical properties, such as pressure, temperature, and wellbore trajectory in three-dimensional space. The downhole physical properties may also include a rate of rotation of the downhole tool 250 (e.g., referred to as CRPM). As described above, the rate of rotation of a lower portion of the tubular string 230 in the wellbore 220 and/or a rate of rotation of the downhole tool 250 in the wellbore 220 may be different than the rate of rotation imparted to the upper portion of the tubular string 230 at the surface during stick-slip conditions. The downhole tool 250 (e.g., the LWD 254) may also be configured to measure downhole formation properties, such as resistivity, porosity, sonic velocity, and gamma ray data.
The training portion 310 of method 300 may include measuring one or more surface properties, as at 312. The surface properties may be measured at the surface. For example, the surface properties may include the surface physical properties measured by one of the surface sensors 240. An illustrative list of examples of the surface properties is provided above.
The training portion 310 of method 300 may also include measuring one or more downhole properties, as at 314. The downhole properties may be measured in the wellbore 220. For example, the downhole properties may include the downhole physical properties measured by the MWD tool 252 and/or downhole formation properties measured by the LWD tool 254. Illustrative lists of the downhole physical properties and the downhole formation properties are provided above.
The training portion 310 of method 300 may also include transmitting the one or more downhole properties to the surface, as at 316. For example, the downhole tool 250 may transmit encoded data representing the measured downhole properties to the surface using mud pulse telemetry or electromagnetic (EM) telemetry or other communication techniques.
The training portion 310 of method 300 may also include combining the surface properties and the downhole properties to produce combined properties, as at 318. For example, the surface properties and the downhole properties may be combined in a computing system 500 at the surface, which is described in greater detail below with respect to
The training portion 310 of method 300 may also include indexing the combined properties by time, as at 320. For example, a first of the properties (e.g., torque on the upper portion of the drill string 230 at the surface) may be measured every second, and a second of the properties (e.g., the rate of rotation of the downhole tool 250) may be measured every 30 seconds. Indexing these properties may include interpolating (e.g., averaging) the second property to predict values at the same time intervals as the first property (e.g., every second). It may also or instead include selecting one out of every 30 readings of the first property.
The training portion 310 of method 300 may also include extracting one or more features from the combined properties, as at 322. The one or more features may be extracted before or after the surface properties and the downhole properties are combined, and/or before or after the combined properties are indexed. As used herein, the term “features” may refer to an individual measurable property or characteristic of a phenomenon being observed. Thus, examples of features may include time series moment calculations, vertical stand extractions, sliding time windows, and the like.
The training portion 310 of method 300 may also include preparing the combined properties, as at 324. The combined properties may be prepared before or after the surface physical properties and the downhole properties are combined, before or after the combined properties are indexed, and/or before or after the features are extracted from the combined properties. In at least one embodiment, preparing the combined properties may include determining whether the combined properties are within a predetermined range. For example, the predetermined range for the rate of rotation of the downhole tool 250 may be from 0 RPM to about 200 RPM. Rates outside of this range may be identified as unrealistic, and thus erroneous, and may be discarded. In another embodiment, preparing the combined properties may be or include bit-on-bottom recordings, slips data, RPM data, or CRPM data.
The training portion 310 of method 300 may also include training a machine learning (ML) model to predict a stick-slip event (e.g., involving the drill string 230 and/or downhole tool 250) based at least partially upon the combined properties, as at 326. The model may be or include a neural network. The model may be trained before or after the surface physical properties and the downhole properties are combined, before or after the combined properties are indexed, before or after the features are extracted from the combined properties, and/or before or after the combined properties are prepared.
In at least one embodiment, training the model may include identifying a plurality of previously-detected stick-slip events, as at 328. For example, more than 100, more than 1000, or more than 10,000 previously-detected stick-slip events may be identified and used to train the model. A starting time and an ending time may be identified for each previously-detected stick-slip event.
Training the model may also include determining an amount of stick-slip during each previously-detected event, as at 330. The amount of stick-slip may be represented by a difference between a maximum number of rotations per minute (RPM) and a minimum number of RPM. The maximum and minimum number(s) of RPM may be determined at the surface (e.g., as part of the surface properties) and/or downhole (e.g., as part of the downhole properties).
Training the model may also include assigning each previously-detected stick-slip event to a level based at least partially upon the amount of stick-slip during each previously-detected event, as at 332. In an example, the levels may include:
Thus, in the example above, where the amount of stick-slip is 35 RPM, this particular stick-slip event may be classified as Level 4 (severe). Table 1 below shows data for a plurality of events.
In another embodiment, rather than quantifying the amount of stick-slip by a number of RPMs, as in Table 1 above, the amount may also or instead be quantified by a percentage of stick-slip. For example, the level may be light when the stick-slip is 0%-40%, the level may be medium when the stick-slip is 40%-80%, the level may be heavy when the stick-slip is 80%-100%, and the level may be sever when the stick-slip is 100+%.
Training the model may also include determining the surface properties and/or the downhole properties that occur before and/or during each previously-detected stick-slip event, as at 334. In at least one embodiment, the surface properties and the downhole properties may be determined during a predetermined time before each previously-detected stick-slip event begins (e.g., from 5 minutes before the stick-slip event begins until the stick-slip event begins). In another embodiment, the surface properties and the downhole properties may be determined during a predetermined distance/depth before each previously-detected stick-slip event begins (e.g., from 5 meters above where the stick-slip event begins until where the stick-slip event begins). The surface properties and the downhole properties may also or instead be determined while each previously-detected stick-slip event occurred (e.g., between the start time and end time of each previously-detected stick-slip event).
Training the model may also include determining one or more distributions (e.g., patterns or trends) in the surface properties and/or the downhole properties that occur before and/or during the previously-detected stick-slip events, as at 336. As used herein, a distribution may refer to a mathematical expression that describes the probability that a system will take on a specific value or set of values. For example, the distribution may be or include a plurality of surface properties and/or downhole properties that are common between two or more previously-detected stick-slip events.
For example, the computing system 500 may analyze the properties and determine that two or more of the previously-detected stick-slip events occurred when:
Training the model may also include determining a likelihood that a distribution occurs before and/or during the previously-detected stick-slip events, as at 338. In an example, the computing system 500 may determine that a previously-detected stick-slip event occurred 15% of the time when the above distribution is detected. Thus, in this example, no stick-slip event occurred 85% of the time that the above distribution is detected. In at least one embodiment, a plurality of different distribution may be determined, and each distribution may have a different likelihood that the stick-slip events occur.
Training the model may also include determining a likelihood that the stick-slip events that occurred in response to the distribution(s) are assigned to one or more of the levels, as at 340. For example, there may be 20 stick-slip events that occurred when the above distribution is detected, and 8 of the stick-slip events may be level 1 (light), 7 of the stick-slip events may be level 2 (medium), 3 of the stick-slip events may be level 4 (heavy), and 1 of the stick-slip events may be level 4 (severe). Thus, there may be a 15% chance that a stick-slip event occurs when the above distribution is detected, and if an event occurs when the above distribution is detected, there may be a 40% likelihood that the event is level 1 (light), a 35% likelihood that the event is level 2 (medium), a 20% likelihood that the event is level 3 (heavy), and a 5% likelihood that the event is level 4 (severe).
The predicting portion 350 of the method 300 may include measuring one or more surface properties, as at 352. The predicting portion 350 of the method 300 may also include measuring one or more downhole properties, as at 354. The predicting portion 350 of the method 300 may also include transmitting the one or more downhole properties to the surface, as at 356. The portions 352, 354, and/or 356 may be similar to the portions 312, 314, 316 described above; however, the portions 352, 354, and/or 356 may occur at a later time. For example, the portions 352, 354, and/or 356 may occur after the training portion 310 is at least partially complete. Thus, in one embodiment, the properties measured at 312, 314 may be referred to as first properties (e.g., first surface properties 312 and first downhole properties 314), and the properties measured at 352, 354 may be referred to as second properties (e.g., second surface properties 352 and second downhole properties 354).
The predicting portion 350 of the method 300 may also include predicting a stick-slip event based at least partially upon the surface properties (measured at 352), the downhole properties (measured at 354), and the model, as at 358.
Predicting the stick-slip may include determining whether the surface properties (measured at 352) and/or the downhole properties (measured at 354) match one or more of the distributions (determined at 336), as at 360. The determination may be based upon the model or using the model. In one embodiment, the model may identify relationships between the features and the outputs (e.g., stick-slip events). One or more models may be trained/used to identify different relationships. The model may not be a rule-based model. Thus, the model may not explicitly look at patterns. In other words, the model may be trained to learn distributions and not explicit patterns.
For example, the surface properties (measured at 352) and/or the downhole properties (measured at 354) may match the distribution above when the rate of rotation imparted to the upper portion of the tubular string 230 by the rig 210 is 7 RPM, the torque exerted on the upper portion of the tubular string 230 by the rig 210 is 110 N*m, the pressure measured by the downhole tool 250 is 34 kPa, and resistivity measured by the downhole tool 250 is 11 Ω*m. In at least one embodiment, the surface properties (measured at 352) and/or the downhole properties (measured at 354) may match two or more of the distributions.
If the surface properties (measured at 352) and/or the downhole properties (measured at 354) match one or more of the distributions, then a likelihood of the stick-slip event occurring may be determined, as at 362. The likelihood of the stick-slip event occurring may be determined based upon the model or using the model. More particularly, the likelihood of the stick-slip event occurring may be determined based upon the particular distribution(s) that is/are matched, and the likelihood of the particular distribution(s) leading to a stick-slip event (as determined above at 338). For example, if the surface properties (measured at 352) and/or the downhole properties (measured at 354) match the distribution described above (at 336), then it may be determined that there is a 15% chance that the stick-slip event will occur. More particularly, there is a 15% chance that the stick slip event will occur within the predetermined time (e.g., within the next 5 minutes) and/or with the predetermined distance/depth (e.g., within the next 5 meters).
In addition, if the surface properties (measured at 352) and/or the downhole properties (measured at 354) match one or more of the distributions, then a likelihood that the stick-slip event is assigned to one or more of the levels may be determined, as at 364. The likelihood that the stick-slip event is assigned to one or more of the levels may be determined based upon the model or using the model. More particularly, likelihood that the stick-slip event is assigned to one or more of the levels may be determined based upon the particular distribution(s) matched (as determined above at 340). For example, if the surface properties (measured at 352) and/or the downhole properties (measured at 354) match the distribution described above (at 336), then it may be determined that there is a 15% chance that the stick-slip event will occur, and if the stick-slip event occurs, there is a 40% likelihood that it will be level 1 (light), a 35% likelihood that it will be level 2 (medium), a 20% likelihood that it will be level 3 (heavy), and a 5% likelihood that it will be level 4 (severe).
The predicting portion 350 of the method 300 may also include performing a physical action in response to predicting the stick-slip event, as at 366. For example, the physical action may be performed in response to the surface properties (measured at 352) and/or the downhole properties (measured at 354) matching one or more of the distributions (as determined at 360). The physical action may also or instead be performed in response to the likelihood of the stick-slip event occurring (as determined at 362) being greater than a predetermined threshold (e.g., 20%). The physical action may also or instead be performed in response to the likelihood of the level of the stick-slip event (as determined at 364) being greater than or equal to a predetermined level (e.g., greater than or equal to level 2) being greater than a predetermined threshold (e.g., 50%). In the example above, there is a 60% chance that the stick-slip event will be level 2-level 4; thus, as 60% is greater than the predetermined threshold of 50%, the physical action may be performed.
The physical action may be or include varying (e.g., decreasing) the rate of rotation imparted to the upper portion of the tubular string 230 by the rig 210, varying (e.g., decreasing) the torque exerted on the upper portion of the tubular string 230 by the rig 210, varying (e.g., decreasing) the weight on the drill bit 256, varying a trajectory of the downhole tool 250 in the wellbore 220, or a combination thereof. For example, the physical action may be selected to change one or more of the physical properties (measured at 352) and/or the downhole properties (measured at 354) such that they no longer match any of the distributions.
In at least one embodiment, the prediction portion 350 of the method 300 may be used to further train (e.g., tune) the model in the training portion 310 of the method 300 to increase the accuracy of the model for future iterations.
In some embodiments, the methods of the present disclosure may be executed by a computing system.
A processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.
The storage media 506 may be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of
In some embodiments, computing system 500 contains one or more stick-slip prediction module(s) 508 configured to perform at least a portion of the method 300. It should be appreciated that computing system 500 is merely one example of a computing system, and that computing system 500 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of
Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in information processing apparatus such as general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or other appropriate devices. These modules, combinations of these modules, and/or their combination with general hardware are included within the scope of the present disclosure.
Computational interpretations, models, and/or other interpretation aids may be refined in an iterative fashion; this concept is applicable to the methods discussed herein. This may include use of feedback loops executed on an algorithmic basis, such as at a computing device (e.g., computing system 500,
The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or limiting to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. Moreover, the order in which the elements of the methods described herein are illustrate and described may be re-arranged, and/or two or more elements may occur simultaneously. The embodiments were chosen and described in order to best explain the principals of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosed embodiments and various embodiments with various modifications as are suited to the particular use contemplated.
This application is a continuation of U.S. patent application Ser. No. 17/756,822, filed Jun. 3, 2022, which is a National Stage Entry of International Application No. PCT/US2019/064753, filed Dec. 5, 2019.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 17756822 | Jun 2022 | US |
| Child | 18432202 | US |
