Methods and systems for improving effective data rates for telemetry of wellbore configurations

Abstract

Methods and systems for predicting downhole measurement data at the earth surface include predicting, using a first processor in a downhole tool, a first estimate of an attribute of interest using a first predictor; and predicting, using a second processor of the terrestrial unit and using a second predictor, a second estimate of the attribute of interest, the second predictor including the same data processing as the first predictor. Measurements of the attribute of interest are obtained using sensors disposed in the downhole tool. The first processor compares the measurement value to the first estimate value and determines whether the measurement value is within a predetermined threshold value relative to the first estimate value. In response to the measurement being within the predetermined threshold of the first estimate, a wellbore operation based on the second estimate is performed using the second processor.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. Application Serial No. 63 / 392,286, filed on July 26, 2022, the entire disclosure of which is incorporated herein by reference. Background Technology

[0003] This disclosure relates to telemetry systems, and more specifically to telemetry systems for communicating from a downhole location (e.g., inside the wellbore) to another location inside the wellbore or on the surface and for estimating and / or processing data obtained using downhole sensors.

[0004] Telemetry in downhole operations is used for communication of downhole location (e.g., downhole tools) with other downhole tools and / or the surface, providing data and / or commands. Telemetry and data transmission can occur via mud pulse telemetry, wired data communication, wired pipeline systems, electromagnetic transmission (e.g., through formation), etc. However, due to the nature of downhole operations, bandwidth is limited, resulting in low bandwidth for uplink and downlink communication. This is particularly true for, but not limited to, drilling operations. The quantity and quality of drilling service data transmission can be limited due to low data density and / or bandwidth constraints. For example, avoiding directional downlinks for faster drilling operations may affect wellbore quality (e.g., formation assessment may be affected due to potentially lower data rates for multiple rock physics measurements). That is, the transmission of control or commands from the surface can be limited due to limited bandwidth to avoid delays in drilling operations. Such delays can be affected by limited uplink transmission when data collected downhole is transmitted to the surface. One solution to this limited bandwidth is the use of wired pipeline systems, but the associated costs can be prohibitive due to the nature of wired pipelines. Therefore, improved systems or methods for telemetry are likely desirable. Summary of the Invention

[0005] According to some embodiments, methods for predicting downhole measurement data at the Earth's surface are provided. These methods include: using a first processor disposed in a downhole tool within a wellbore to predict a first estimate of an attribute of interest, the first processor executing a first predictor; using a second processor disposed in a surface unit located at the Earth's surface and outside the wellbore to predict a second estimate of the attribute of interest, the second processor executing a second predictor including the same data processing as the first predictor, such that when the same input is provided to each of the first and second predictors, the first estimate predicted at the first processor is equal to the second estimate predicted at the second processor; obtaining a measurement of the attribute of interest via a sensor disposed in the downhole tool; comparing the measurement at the first processor with the first estimate predicted by the first predictor; determining whether the measurement is within a predetermined threshold relative to the first estimate; and, in response to the measurement being within the predetermined threshold of the first estimate, using the second processor to perform wellbore operations based on the second estimate of the attribute of interest.

[0006] According to some embodiments, a data prediction system for use with downhole operations is provided. These data prediction systems include: a sensor configured to acquire a measurement of an attribute of interest, the sensor being disposed on a downhole tool located in the wellbore; a first processor disposed in the downhole tool and configured to receive the measurement from the sensor; and a second processor disposed in a surface unit located at the Earth's surface and outside the wellbore. The first processor is configured to: execute a first predictor; receive the measurement of interest from the sensor; predict a first estimate of the attribute of interest by executing the first predictor; compare the first estimate with the measurement; and determine whether the measurement is within a predetermined threshold relative to the first estimate. The second processor is configured to: execute a second predictor; predict a second estimate of the attribute of interest by executing the second predictor; and perform wellbore operations based on the second estimate when the measurement is within the predetermined threshold relative to the first estimate. The first predictor and the second predictor are configured to perform the same data processing such that when the same input is provided to each of the first predictor and the second predictor, the predicted first estimate is equal to the predicted second estimate. Attached Figure Description

[0007] The following description should not be considered as limiting in any way. Referring to the accompanying drawings, the same elements are indicated by the same reference numerals:

[0008] Figure 1 A schematic diagram of a wellbore operation system that can be incorporated into an embodiment of this disclosure is depicted;

[0009] Figure 2 A block diagram of a processing system that can be used to implement further embodiments of this disclosure is depicted;

[0010] Figure 3 It is a schematic diagram of a system according to an embodiment of this disclosure;

[0011] Figure 4 This is a schematic diagram of an example process according to an embodiment of this disclosure;

[0012] Figure 5 It is a schematic diagram of a system according to an embodiment of this disclosure; and

[0013] Figure 6 This is the process according to the implementation scheme of this disclosure. Detailed Implementation

[0014] A detailed description of one or more embodiments of the devices and methods disclosed herein is presented by way of example rather than limitation with reference to the accompanying drawings. A modern bottom-of-the-hole assembly (BHA) consists of several distributed components such as sensors and tools, each performing data acquisition and / or processing for a specific purpose. During drilling operations, sensors and detectors can be used to determine the properties of the surrounding formation and / or to determine whether the wellbore is traversing the intended formation and / or within the specified formation (e.g., for production purposes). Such sensors and detectors can also, or alternatively, be used to determine physical properties relevant to the drilling operation, such as, but not limited to, pressure, temperature, mechanical loads (e.g., acceleration, bending moment, torsional moment, axial force, etc.) or directional information such as drift / inclination or direction / azimuth.

[0015] Figure 1 An embodiment of a system 100 for performing energy industry operations (e.g., underground drilling, measurement, stimulation, and / or production) is illustrated. System 100 includes a wellbore string 102, shown as being disposed in a well or wellbore 104 that penetrates at least one geological formation 106 during drilling or other downhole operations. As used herein, “wellbore” or “well casing” refers to a hole that forms all or part of a drilled well. It should be noted that wellbore 104 may include vertical, skew, and / or horizontal sections and may follow any suitable or desired path. As used herein, “formation” refers to the various features and materials (e.g., geological materials) that may be encountered in the subsurface environment and surround wellbore 104.

[0016] The wellbore string 102 is operatively connected to a surface structure or surface equipment such as a drilling rig 108, which includes or is connected to various components such as a surface drive unit 110 (also referred to as a top drive unit) and / or a rotary table 112 for supporting the wellbore string 102, rotating the wellbore string 102, and lowering string sections or other downhole components into the wellbore 104. In one embodiment, the wellbore string 102 is a drill string comprising one or more drill pipe sections 114 extending downward into the wellbore 104 and connected to one or more bottomhole components (bottomhole tools), which may be configured as a bottomhole assembly (BHA) 116. The BHA 116 may be fixedly connected to the wellbore string 102 such that rotation of the wellbore string 102 causes rotation of the BHA 116.

[0017] BHA 116 includes a disintegration device 118 (e.g., a drill bit), which in this embodiment is surface-driven but may also be downhole-driven (e.g., via a downhole mud motor or turbine). System 100 may include components that facilitate the circulation of fluid 120, such as drilling mud, through the inner bore of wellbore string 102 and the ring between wellbore string 102 and the wall of wellbore 104. For example, in this exemplary embodiment, a pumping device 122 is located at the surface to circulate fluid 120 from a mud pit or other fluid source 124 into wellbore 104 when the disintegration device 118 is rotated (e.g., by rotation of wellbore string 102 and / or downhole motor).

[0018] exist Figure 1 In the exemplary embodiment shown, system 100 may include a guide assembly 126 configured to guide or direct a portion of the wellbore string 102 and the disintegration device 118 along a selected path. Guide assembly 126 may have any configuration suitable for guiding or directing the drill string 102. Examples of guide assemblies include, but are not limited to, guideable motor assemblies (e.g., bending housing motor assemblies), turbines, and rotary guideable assemblies or systems.

[0019] In one non-limiting embodiment, the guide assembly 126 is configured as a rotary guide assembly forming part of or forming part of the BHA 116. The guide assembly 126 includes a non-rotating or slowly rotating sleeve 128, which includes one or more radially extending pads 130 (extending in a direction perpendicular to the longitudinal axis of the sleeve). The pads 130 may be located at different circumferential positions on the sleeve 128 and may be adjusted individually or in combination to deflect the disintegration device 118 by engaging the wall of the wellbore 104.

[0020] System 100 may also include a controller configured to operate or control the operation of pad 130 based on orientation information derived from orientation sensors located in BHA 116 and / or wellbore string 102. Orientation sensors may be disposed at, within, or near the guidance assembly 126. Orientation sensors may include one or more gyroscopes (e.g., gyroscope sensors or earth rate sensors) and one or more magnetometers (i.e., magnetic field sensors) and / or one or more accelerometers (e.g., acceleration sensors and / or gravity sensors).

[0021] In one embodiment, system 100 includes one or more sensor assemblies 132 configured to perform measurements of parameters relating to the position and / or orientation of the wellbore string 102, the disintegration device 118, and / or the guiding assembly 126. Figure 1 As shown, sensor assembly 132 may be located at one or more of various locations, such as on sleeve 128, at or near disintegration device 118, and / or on other components of wellbore string 102 and / or BHA 116. For example, sensor assembly 132 may be located on one or more stabilizer sections 134 of guide assembly 126. Sleeve 128 may be coupled to wellbore string 102 via bearing assembly or other mechanism that allows sleeve to rotate independently of rotation of wellbore string, as those skilled in the art will appreciate.

[0022] System 100 may include one or more of various tools or components configured to perform selected downhole functions such as: performing downhole surveying / exploration (e.g., formation assessment surveying, directional surveying, etc.), facilitating communication (e.g., mud pulser, wired communication sub-assembly, etc.), providing power, and other functions (e.g., mud turbine, generator, battery, data storage device, processor device, modem device, hydraulic device, etc.). For example, guidance assembly 126 may be connected to one or more sensor devices, such as gamma-ray imaging tool 136. Such gamma-ray imaging tool 136 can be used to measure, for example, formation density.

[0023] In one embodiment, system 100 includes measuring devices, such as logging-while-drilling (LWD) tools (e.g., for formation assessment measurements) or measurement-while-drilling (MWD) tools (e.g., for directional measurements), collectively referred to as drilling tool 138. Examples of LWD tools include nuclear magnetic resonance (NMR) tools, resistivity tools, gamma (density) tools, pulsed neutron tools, acoustic tools, and various other tools. Examples of MWD tools include tools that measure pressure, temperature, or directional data (e.g., magnetometers, accelerometers, gyroscopes, etc.). Guiding assembly 126 or system 100 may include other components, such as telemetry assemblies (e.g., mud pulsers, wired communication subassemblies, etc.) or other downhole and / or surface components, systems, or assemblies.

[0024] In one non-limiting embodiment, during drilling, the sleeve 128 does not rotate, or rotates at a rate less than that of the disintegration device 118 and other components of the guide assembly 126 and rotary table 112 or surface drive unit 110. The rotational rate of the sleeve 128 may be referred to herein as “slow rotation.” It should be noted that “slow” rotation is intended to indicate a rotational rate less than the drilling rotational rate and is not intended to be limited to any specific rate. A “slow-rotating” sleeve is a sleeve that rotates at a slow rate.

[0025] The sleeve 128 can rotate at any suitable slow rotation rate less than the drilling rotation rate. In one embodiment, the slow rotation of the sleeve 128 is between about 1 revolution per hour (RPH) and 10 revolutions per hour. In another embodiment, the slow rotation is between about 10 RPH and 50 RPH (60° / min to 300° / min). In yet another embodiment, the slow rotation is between about 1 RPH and 50 RPH (6° / min and 300° / min).

[0026] One or more downhole components and / or one or more surface components may communicate with and / or be controlled by a processor, such as downhole processing unit 140 and / or surface processing unit 142. Downhole processing unit 140 may be part of BHA 116, or may be otherwise arranged on or as part of the wellbore string 102. Surface processing unit 142 (and / or downhole processing unit 140) may be configured to perform functions such as: controlling drilling and steering, controlling the flow rate and pressure of fluid 120, controlling bit pressure (WOB), controlling the rotational speed (RPM) of rotary table 112 or surface drive unit 110, transmitting and receiving data, processing measurement data, and / or monitoring the operation of system 100. In some embodiments, surface processing unit 142 includes input / output (I / O) devices 144 (such as a keyboard and monitor), a processor 146, and data storage devices 148 (e.g., memory, computer-readable medium, etc.) for storing data, models, and / or computer programs or software that enable the processor to perform aspects of the methods and processes described herein.

[0027] In one non-limiting embodiment, the surface processing unit 142 is configured as a surface control unit that controls wellbore operations and / or various parameters, such as rotational speed (RPM), drilling pressure, fluid flow parameters (e.g., pressure and flow rate), directional control of the rotary steering assembly, and / or other parameters or aspects of system 100 such as data processing and / or data logging generation. Wellbore operations may involve a human operator or may be performed automatically without human operator intervention. In some embodiments, the downhole processing unit 140 may be a directional measurement controller or other processing means that controls the operation of the sensor assembly 132, acquires measurement data, and / or estimates various aspects of the directional parameters. The downhole processing unit 140 may also include functionality for controlling the operation of the steering assembly 126 and / or other downhole components, assemblies, or systems. In one non-limiting embodiment, the methods and processes described herein may be performed in the downhole processing unit 140 located within the wellbore string 102 or BHA 116.

[0028] exist Figure 1 In one embodiment, system 100 is configured to perform drilling and downhole measurement operations, and wellbore string 102 is a drill string. However, the embodiments described herein are not limited to this and may have any configuration suitable for performing energy industry operations that include or may benefit from directional measurement (e.g., well completion, fracturing, production, reentry, etc.).

[0029] It should be understood that the embodiments of this disclosure can be implemented in conjunction with any other suitable type of computing environment now known or developed in the future. For example, Figure 2A processing system 200 (e.g., [missing information]) that can be used to implement the techniques described herein is depicted. Figure 1 A block diagram of the surface processing unit 142 and / or the downhole processing unit 140. In the example, the processing system 200 has one or more central processing units 202a, 202b, 202c, etc. (collectively or generally referred to as processor 202 and / or processing device 202). In various aspects of this disclosure, each processor 202 may include a Reduced Instruction Set Computer (RISC) microprocessor. As shown, the processor 202 is connected to system memory (e.g., random access memory (RAM) 204) and various other components via a system bus 206. Read-only memory (ROM) 208 is connected to the system bus 206 and may include a Basic Input / Output System (BIOS) that controls certain basic functions of the processing system 200.

[0030] Figure 2 Further examples illustrate input / output (I / O) adapter 210 and network adapter 212 connected to system bus 206. I / O adapter 210 may be a Small Computer System Interface (SCSI) adapter that communicates with memory such as hard disk 214 and / or tape storage drive 216 or any other similar component. I / O adapter 210 and associated memory such as hard disk 214 and / or tape storage drive 216 may be collectively referred to herein as mass storage device 218. Operating system 220 for execution on processing system 200 may be stored in mass storage device 218. Network adapter 212 may be configured to interconnect system bus 206 with external network 222, enabling processing system 200 to communicate with other systems and / or remote systems (e.g., the Internet, extranets, and / or cloud-based systems).

[0031] A display (e.g., a display monitor) 224 is connected to the system bus 206 via a display adapter 226, which may include, for example, a graphics adapter for improving the performance of graphics-intensive applications and a video controller. In one aspect of this disclosure, adapters 210, 212, and / or 226 may be connected to one or more I / O buses connected to the system bus 206 via an intermediate bus bridge (not shown), as those skilled in the art will appreciate. Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include common protocols such as Peripheral Component Interconnect (PCI). Additional input / output devices are shown connected to the system bus 206 via a user interface adapter 228 and the display adapter 226. For example, as shown, a keyboard 230, a mouse 232, and a speaker 234 may be interconnected to the system bus 206 via a user interface adapter 228, which may include, for example, a super I / O chip integrating multiple device adapters into a single integrated circuit.

[0032] In some aspects of this disclosure and as shown in the figures, the processing system 200 includes a graphics processing unit 236. The graphics processing unit 236 may be specialized electronic circuitry designed to manipulate and modify memory to accelerate the creation of images in a frame buffer intended for output to a display (e.g., display 224). Generally, the graphics processing unit 236 is highly efficient in manipulating computer graphics and image processing, and has a highly parallel architecture, making it more efficient than a general-purpose CPU for algorithms that perform parallel processing of large data blocks.

[0033] Therefore, as configured herein, the processing system 200 includes processing power in the form of a processor 202, storage capacity including system memory (e.g., RAM 204 and mass storage device 218), input components such as a keyboard 230 and a mouse 232, and output capacity including a speaker 234 and a display 224. In some aspects of this disclosure, a portion of the system memory (e.g., RAM 204 and mass storage device 218) may be configured to co-store an operating system (e.g., operating system 220) to coordinate the functions of the various components shown in the processing system 200.

[0034] Will understand, Figure 2 The processing system 200 is currently described as a ground system (e.g., Figure 1 (Surface processing unit 142). However, it will be understood that similar electronic components may be employed in downhole systems (e.g., as part of the BHA and / or downhole processing unit 140). In such configurations, certain features of the processing system may be omitted. For example, in a downhole BHA system, user interface components may be omitted. Furthermore, the system bus may be arranged to span multiple different downhole components, and network connections may be communication components (e.g., telemetry, wired connections, wireless connections, etc.) configured to enable communication between the surface system and the downhole BHA system.

[0035] The processing system 200 can communicate with one or more downhole components via communication connections such as mud pulse telemetry. In some configurations, as mentioned, wired connections can be used, but the use of wired connections can be prohibitively expensive. Thus, a lower bandwidth solution is still relied upon for communication between downhole components and other downhole components or with surface components. It will be understood that communication between two downhole components can be achieved via a wired connection and may not require telemetry. However, a significant portion of downhole communication relies on telemetry transmission, and the bandwidth of telemetry-based communication is limited. Low uplink and / or downlink bandwidth can cause delays during drilling operations. For example, due to low bandwidth, transmitting information (including data and / or commands) between surface and downhole components is difficult (e.g., time-consuming). Thus, during active drilling operations, it is undesirable to delay drilling for data transmission purposes, especially if the data being transmitted only confirms that the drilling trajectory or drilling plan is being maintained (e.g., no problems exist).

[0036] Due to the high cost of wired solutions, the latency associated with telemetry, the bandwidth limitations associated with telemetry, and other considerations, embodiments of this disclosure relate to providing improved telemetry communication. For example, according to some embodiments, two similar or identical systems are deployed at two separate locations (e.g., one downhole and one on the surface) and configured to analyze data and make determinations regarding data transmission. In a non-limiting example, the downhole unit may be configured to estimate the next data point to be collected. When the next data point is collected, such as by a tool or sensor, the downhole unit may check to see if the collected data matches the estimate, and if a match exists, the downhole unit may not initiate data transmission. Simultaneously, the surface unit, having the same processing (and the same initialization information) as the downhole unit, may check to see if data has been received within a given time period, and if no data has been received, the surface unit may assume that the collected data matches the estimate and update the information stored at the surface unit based on this missing received signal.

[0037] Now for reference Figure 3A schematic diagram of a system 300 for performing energy industry operations (e.g., underground drilling, measurement, stimulation, and / or production) is shown. System 300 may be similar to the systems shown and described above, and therefore certain features need not be illustrated or described again. System 300 includes a surface system 302 and a downhole system 304. Surface system 302 includes a surface control unit 306 and a pump system 308 coupled to a mud pit 310, etc., and configured to generate mud pulses for telemetry purposes based on control from the surface control unit 306. Downhole system 304 is disposed in a wellbore 312 formed in earth 314. Downhole system 304 includes a column 316, at the end of which a bottom hole assembly (“BHA”) 318 is arranged. BHA 318 includes a drill bit 320 (e.g., a drill bit, a disintegration device, etc.) located at the end of the BHA and configured to cut, break, or disintegrate the material of the earth 314 to drill and form a wellbore 312.

[0038] BHA 318 includes one or more downhole tools 322, 324 and a downhole control unit 326. Although Figure 3 A specific arrangement of components is illustrated, but those skilled in the art will understand that the order and arrangement of components may vary depending on the specific needs of the system and / or the BHA itself. Therefore, the illustrative configuration is for illustrative purposes only and is not intended to be limiting. Downhole tools 322, 324 may be formation assessment tools, BHA monitoring tools, directional or geoguided tools, etc., as those skilled in the art will understand. Downhole control unit 326 may be configured to communicate with downhole tools 322, 324 and / or drill bit 320 and is configured to receive information for processing and / or information transmitted to the surface (e.g., to surface control unit 306). Downhole control unit 326 may include (or communicate with) a pulse generator, etc., configured to generate mud pulses in the drilling fluid (e.g., provided from mud pit 310 and pump system 308) to transmit data from BHA 318 to surface control unit 306.

[0039] Each of the surface control unit 306 and the downhole control unit 326 can be configured to process data received from external sources, such as downhole tools 322, 324, sensors at the surface or downhole, etc. Data collected downhole is typically transmitted from the downhole control unit 326 to the surface control unit 306 via telemetry. As discussed above, such telemetry can be subject to bandwidth limitations. Bandwidth limitations can limit the amount of data (e.g., collected data, commands, feedback information, etc.) that can be transmitted from the downhole control unit 326 to the surface control unit 306 (or vice versa). For a given downhole instrument or operation, certain data can be collected and processed. This data may include instructions or commands transmitted from the surface control unit 306 and / or may include information collected by the tool (which may be part of the downhole operation). Before transmitting data from the surface or downhole, some amount of preprocessing, such as pre-filtering, organizing, tagging, or packaging, or other methods of processing, may be performed on the data. Therefore, each of the surface control unit 306 and the downhole control unit 326 may include one or more processors and associated memory, as well as other electronic components that perform such processing.

[0040] According to embodiments of this disclosure, each of the surface control unit 306 and the downhole control unit 326 is programmed with a predictor (e.g., a surface predictor, a downhole predictor, etc.). As used herein, a predictor is a piece of software code that may be stored on memory, within a processor, or otherwise stored and associated with control logic, a processor, a general-purpose computer, a PCB, etc. The predictor described herein may be a process executed by an associated processor. These processors may be configured to perform other tasks such as control telemetry, or may be dedicated processors configured to perform the processes described herein. According to some embodiments and without limitation, the predictor may include one or more of linear regression, logistic regression, decision tree algorithms, gradient boosting models, neural networks, and / or combinations thereof.

[0041] For example, and according to embodiments of this disclosure, the predictor may be executed by one or more processors, such as the processor in the surface control unit 306 and / or the processor in the downhole control unit 326. The predictors in each of the surface control unit 306 and the downhole control unit 326 are substantially identical, such that when the same input value or data is input to the respective control unit 306, 326, the output or result is the same. Therefore, given a single piece of information input to each of the control units 306, 326, the same output will be produced. In this way, given the same starting conditions, each predictor can make an estimate of what the next data point should be (assuming the estimate is the same at each control unit 306, 326). As used herein, the predictor is software code or firmware code stored in the associated memory of the surface control unit 306 or the downhole control unit 326.

[0042] Each control unit 306, 326 has a predictor configured to receive, acquire, or provide data (e.g., preliminary data) and to predict subsequent values ​​based on the received data. That is, the predictor is configured to predict or estimate future data values ​​based on initial condition information (e.g., such as preliminary data or previously acquired data) and current (or past) data values. For example, during drilling operations, measurements are taken regarding formation assessment and drilling performance. Typically, this information is processed and transmitted from the downhole control unit 306 to the surface to update information at the surface control unit 326. The surface control unit 326 can then process the received information to determine whether adjustments to the drilling operation should be changed or whether other actions should be taken. This information is typically transmitted via mud pulse telemetry at specific intervals or as requested by the operator. It will be understood that other telemetry operations and mechanisms may be employed without departing from the scope of this disclosure. For example, alternatives to mud pulse telemetry may include, but are not limited to, acoustic and electromagnetic telemetry, which can be used to transmit data from the downhole control unit 326 to the surface control unit 306. It will be understood that there may be no cable or wiring connecting the downhole processor executing the downhole predictor in the downhole control unit 326 and the processor executing the surface predictor in the surface control unit 306, and therefore one or more telemetry devices may be required to transmit data from the downhole control unit 326 to the surface control unit 306.

[0043] However, according to embodiments of this disclosure, when data intended to be transmitted to the other of control units 306, 326 is received at one of the control units 306, 326, the predictor can be used to determine whether such transmission is necessary. If transmission is not necessary, as explained herein, transmission is not performed, and therefore telemetry bandwidth is not used to transmit such data. If transmission is determined to be necessary, telemetry communication is performed. Due to the large and diverse amount of data collected at both the surface and downhole, each predictor may include multiple different mathematical algorithms or processes for estimating values ​​associated with different aspects of drilling. In other embodiments, multiple different predictors may be provided. For example, in some embodiments, each different measurement may be assigned or have a separate and different (e.g., dedicated) predictor associated with it. Furthermore, it will be understood that any number of predictors (e.g., single-threaded versions, multi-threaded versions, etc.) may be implemented without departing from the scope of this disclosure. As used herein, the term "thread" refers to a processing algorithm that takes known data points (and, where appropriate, preliminary data, baseline data, basic conditions, or information) and predicts what the next data point will be.

[0044] Single-threaded versions can use data from a single attribute, such as formation density. In contrast, multi-threaded versions can use data from more than one attribute, such as formation density and resistivity. Threads can be designed to process operational data (e.g., operational attributes), such as drill string configuration (e.g., tool configuration), wellbore size, rate of penetration (ROP), revolutions per minute (RPM), weight on the drill string (WOB), wellbore depth or bit depth (e.g., measured depth (MD) or true vertical depth (TVD)), wellbore inclination or azimuth, and drilling fluid flow rate. Threads may optionally use formation assessment data (e.g., geomorphic properties) such as formation density, formation resistivity, formation porosity, formation permeability, and formation lithology, and / or may use dynamic data (e.g., dynamic attributes) such as drill string acceleration (e.g., vibration), drill string bending, and strain acting on the drill string. The predictor can combine multiple threads (multi-threaded version of the predictor) or use only one thread (single-threaded version of the predictor).

[0045] According to embodiments of this disclosure, the control unit will not transmit predictable data. At the surface and outside the wellbore (e.g., surface control unit 306), a surface predictor executed by a surface processor can be used to estimate future values ​​based on preliminary data, data received from downhole, and initial or known conditions that can affect specific measurements (such as, for example, temperature, wellbore orientation, depth, drill string acceleration, drill string bending, drill string rotation, drilling fluid flow rate, wellbore size, formation properties, penetration rate, etc.). Simultaneously, downhole and within the wellbore (e.g., downhole control unit 326), the downhole control unit will know what data has been sent to the surface unit (i.e., data transmitted from downhole to the surface). Furthermore, because the downhole control unit has the same downhole predictor executed by the downhole processor as the surface predictor of the surface control unit, the downhole control unit will know how the surface control unit will predict and make decisions. Therefore, the downhole control unit will know what the predicted values ​​made at the surface are. Therefore, if the predicted value (calculated at both the surface and downhole) is within an acceptable range relative to the actual measurement (for a specific measurement), the downhole control unit will not transmit the actual measurement data. Then, if no measurement data is received at the surface (when expected, i.e., within a specific time window), the surface control unit will assume the missing transmission was intentional and the prediction was correct. The surface control unit will then update its information using the predicted value as the next data point. If data is received at the surface control unit, the surface control unit will update its information based on the received data, not the predicted value.

[0046] According to some embodiments of this disclosure, the time window can be predetermined. For example, in a non-limiting embodiment, the width or length of the time window can depend on various factors. For example, and not limited to, the width or length of the time window can depend on the type of attribute of interest to be predicted, the telemetry data rate, the drill string penetration rate, the sampling rate of the downhole measurement of the attribute of interest (e.g., the sensor sampling rate), the duration of information transmitted in the telemetry stream (e.g., the number of bits and bit rate per message), the available bandwidth of the telemetry, etc. According to some embodiments of this disclosure, the time window can be from a few seconds to a few minutes. For example, and not limited to, the time window can have a width or length of 1 second (s) to 10 s, 10 s to 30 s, 20 s to 40 s, 30 s to 1 minute (min), 1 min to 10 min, or 5 min to 30 min.

[0047] Now for reference Figure 4 A schematic diagram of an example process according to an embodiment of this disclosure is shown. Figure 4 In the diagram, graph 400a represents data values ​​or data points recorded at a surface control unit (e.g., surface control unit 306) including a surface processor, and graph 400b represents data values ​​or data points recorded at a downhole control unit (e.g., downhole control unit 326) including a downhole processor. In each of graphs 400a and 400b, the horizontal axis represents time, and the vertical axis is an arbitrary scale of the data values. On each of graphs 400a and 400b, a series of data points 402 and 404 are plotted, indicating measured data point 402 and estimated data point 404.

[0048] Measurement data point 402 and estimated data point 404 represent attributes of interest (e.g., formation attributes, drilling characteristics (including dynamic and operational attributes), etc.). Measurement data point 402 represents the actual value obtained by downhole tools, downhole sensors, downhole systems, etc., located inside the wellbore and below the Earth's surface. Estimated data point 404 represents the predicted value generated by processing information to estimate or guess what future measurement data points will be. Thus, when the estimated data point is 100% accurate, a given estimated data point and the corresponding given measurement data point will be identical. However, it will be understood that due to real-world influences, the estimated data point may deviate from the measurement data point, as the estimate is only based on previous data and / or synthetic data.

[0049] like Figure 4As shown, at time t1, the downhole system acquires a first measurement 4021. In this example, the first measurement 4021 is the first collected data point of the monitored property of interest, such as a formation measurement, and is shown in graph 400b. In this example, no preliminary data is available, such as earlier transmitted measurements, data known from the offset well, or data generated from simulations performed before acquiring the first measurement 4021. The only pre-existing information associated with the collected data is, for example, information related to tool configuration. This information does not allow for the derivation of information about the measurement data collected by the downhole sensors. Thus, prediction of the first measurement 4021 is impossible because there is no preliminary data or information about the initial collection (e.g., earlier measurement data transmitted to the surface unit). Therefore, at time t1, the downhole control unit will telemetry the first data point 4021 to the surface via a first telemetry transmission 4061. As shown in graph 400a, the surface control unit will receive the first data point 4021. In this example, a single data point may not be sufficient to predict subsequent data points, and therefore at time t2, the downhole control unit obtains a second measurement 4022. Since no prediction has been made, the downhole control unit transmits the second measurement 4022 to the surface control unit via a second telemetry transmission 4062. The number of data points necessary to perform a reliable prediction of the attribute of interest can depend on a variety of factors. For example, and not limited to, the number of data points can depend on the type of attribute of interest, operating conditions, and / or formation (including the wellbore, etc.). In some non-limiting configurations, a single (i.e., one) data point may be sufficient to perform a reliable prediction. In other embodiments, more than a single (one) data point may be required, such as two or more data points.

[0050] In the downhole control unit with the first measurement 4021 and the second measurement 4022, the downhole processor executing the downhole predictor can predict the next measurement based on these initial measurements. As shown in graph 400b, the downhole control unit can predict a third measurement, indicated as the third estimate 4043. It should be noted that the nomenclature used herein labels the first estimate as the "third" estimate to align with a series of obtained points; in this example, there is no "first" estimate or "second" estimate because the first and second measurements cannot be predicted or estimated. Simultaneously, the surface control unit also predicts the third estimate 4043 using the surface processor and the surface predictor, as indicated on graph 400a. The third estimate 4043 is assigned to time t3. Then, at time t3 (actual time), the downhole control unit will obtain the third measurement 4023, as indicated on graph 400b. The downhole control unit will determine that the third telemetry transmission 4063 is sufficiently close to the third estimate 4043, and therefore determines that no transmission is necessary. Therefore, the third telemetry transmission 4063 will not occur (indicated by the "X" on the telemetry arrow), and the ground control unit will not receive information about the third measurement value 4023. Consequently, the third measurement value 4023 will not appear on graph 400a; instead, the third estimate value 4043 will fill the point. The measurement value used by the downhole predictor for comparison with the predicted estimate can be the raw measurement value provided by the sensor, or it can be a pre-processed raw measurement value (e.g., pre-processed for noise reduction, amplification, filtering, etc.).

[0051] Based on the first three data points (measurements 4021, 4022, and the third estimate 4043), the surface control unit predicts the next value as the fourth estimate 4044, as shown in graph 400a. The downhole control unit knows that the surface control unit has made a prediction based on these three data points (e.g., has information about them) and therefore knows the value of the fourth estimate 4044, which is plotted on graph 400b. The downhole control unit knows that the surface control unit has made a prediction based on the three data points because the downhole control unit did not transmit the third measurement 4023 to the surface unit. In the absence of data received at the surface control unit, the third measurement 4023 indicates to the surface control unit that the predicted third estimate 4043 matches the third measurement 4023 accurately enough and can be used for subsequent predictions. At time t4, the fourth measurement 4024 is obtained downhole within the wellbore. The downhole control unit plots the fourth measurement 4024 and compares it with the fourth estimate 4044. As illustrated in graph 400b, the fourth measured value 4024 does not match the fourth estimated value 4044. This mismatch can be based on various criteria, such as, but not limited to, comparison with a threshold deviation, checks to confirm that the value is above or below a certain absolute value, within a predetermined error limit, based on a percentage deviation associated with a particular measurement, etc.

[0052] It will be understood that the comparison between the measured value and the estimated value may depend on the specific data associated with it. In this case, because the fourth measured value 4024 deviates from the fourth estimated value 4044, the downhole control unit will transmit the fourth measured value 4024 to the surface unit via the fourth telemetry transmission 4064. The surface control unit will receive the fourth measured value 4024 and plot this data point. Furthermore, because the surface control unit has received the fourth measured value 4024, it will delete the fourth estimated value 4044 (as determined by...). Figure 4 (This is indicated by an "X" on the data point) and the fourth measurement 4024 is entered into the ground control unit's memory, processing, or data log. The percentage deviation may be, for example, but not limited to, within the range of 0.5% to 1%, 0.5% to 5%, or 1% to 10%.

[0053] Based on the data points up to that point (values ​​4021, 4022, 4043, 4024), the surface control unit will predict the next data point indicated by the fifth estimate 4045, as indicated on graph 400a for time t5. Similarly, the downhole control unit will make the same estimate based on the same information, as indicated on graph 400b. Then, at time t5, the downhole control unit will obtain the fifth measurement 4025. In this case, the fifth measurement 4025 matches the fifth estimate 4045 within a threshold deviation. Thus, in some embodiments, the fifth telemetry transmission 4065 may not be performed, and the surface control unit can use the fifth estimate 4045 to fill the entry for t5. However, in this exemplary embodiment, even if the fifth measurement 4025 is within the acceptable limits of the fifth estimate 4045, the downhole control unit will send the fifth measurement 4025 to the surface control unit, which will plot the fifth measurement 4025. In some such implementations, the additional transmission (telemetry transmission 4065) can be used for synchronization purposes, based on a previous point (at time t4) where there is a mismatch between the fourth estimate 4044 and the fourth measurement 4024, to confirm that the two systems are operating correctly.

[0054] although Figure 4 Described as having only five data points in total, this is merely exemplary, and the number of data points used to establish the baseline (e.g., first measurement 4021 and second measurement 4022) may be greater than two, or possibly fewer. For example, in some embodiments, a prediction or estimate may be provided for the first data point based on the specific metric or attribute under consideration and pre-existing data that can be used to establish the first estimate. For instance, if the current well is drilling through a formation near other previously drilled wells, it is possible to have a first estimate to estimate the first measurement based on previously drilled wells (e.g., offset wells). In this specific example, the baseline data serves as preliminary data that enables the surface predictor to predict the first measurement.

[0055] As discussed above, the process described herein is achieved by using identical predictors located in two separate locations. In the disclosed and discussed example, the first predictor is located downhole within the wellbore and below the Earth's surface as it appears in the wellbore fluid, while the second predictor is located at the surface, outside the wellbore, outside the bottomhole assembly, and above the Earth's surface and surrounded by air. Both predictors are configured such that they receive the same information as input and perform the same processing, analysis, or other operations on it to produce the same output. Thus, the first predictor will know what the second predictor will predict / estimate, and therefore can make a determination regarding whether to transmit information via telemetry.

[0056] A predictor can be software or a processing element as part of a control unit, or it can be a dedicated component configured to receive and process information. Predictors can be based on various types of logic or prediction algorithms, as known in the art. For example, depending on the specific characteristics or properties considered, predictions for the next data point can be performed using models, extrapolation algorithms, based on offset well data, historical data, laboratory or synthetic modeling and testing, etc. As discussed, each predictor will have the same logic or prediction algorithm and the same data, and therefore the outputs of the two predictors will always be the same. Because the output is known, it can be determined whether the measured value is equal to or within a predefined metric (e.g., a threshold). When the measured value is equal to or within a predefined metric (e.g., a threshold) relative to the estimate, the predictor or an associated processor can determine that a telemetry transmission is not required. Another predictor (or an associated processor) can monitor for received signals or telemetry transmissions associated with the next estimate. If no such telemetry transmission is received, the second predictor (or associated processor) can determine that the absence of transmission is intentional and can therefore replace the expected received data with the estimate. In this way, telemetry can be avoided for this type of data, and bandwidth is not consumed by its transmission. This reduced bandwidth consumption allows for the transmission of additional and / or alternative data that would otherwise be impossible to telemetry in a system that must transmit measurement data due to the lack of the described predictor. Therefore, some embodiments of this disclosure may allow the transmission to the ground of additional or alternative data that was previously impossible to transmit due to bandwidth limitations.

[0057] According to embodiments of this disclosure, the predictor makes a prediction of the next estimate and then compares the received measurement with the estimate. This comparison may be based on error tolerance, a threshold, the maximum deviation from a previous or expected value, a comparison relative to an absolute value, etc., depending on the specific characteristic or attribute considered. That is, according to embodiments of this disclosure, one or more predictors can be used for one or more corresponding characteristics or attributes, and each prediction (or each process within a single predictor) can be executed independently, allowing multiple parallel processes to be executed to determine what information needs to be transmitted to another predictor or system. Thus, the amount of data transmitted via telemetry can be reduced by using the predictors and systems described herein. Consequently, greater bandwidth can be used for telemetry because less information will need to be transmitted at any given time.

[0058] As noted above, different attributes or characteristics can be monitored through corresponding predictors, logic, or predictor algorithms. Attributes and characteristics may include, for example, but not limited to, gamma-ray data, neutron data, ROP data, WOB data, rotational velocity data, formation information, directional data such as tilt and azimuth measurements, dynamic data such as acceleration, vibration (e.g., torsional, lateral, axial), and bending, steering data, or other downhole data related to formation, drilling operations, and / or BHA / column component performance. It should be noted that these attributes are obtained downhole and have the potential to be transmitted to the surface. However, the opposite can also be true. That is, information can be transmitted from the surface to the downhole control unit. For example, drilling commands, etc., can be transmitted from the surface to the downhole via a downlink, which is similarly bandwidth-limited to the uplink from downhole to the surface. In this configuration, both predictors are configured identically, and therefore the lack of transmission reception can indicate that the next estimate is correct and therefore the downhole control unit should proceed as planned. This thus avoids additional downlink transmissions, similar to the avoidance of uplink transmissions described above.

[0059] As described above, two processors and two predictors are provided, wherein a first processor executes a first predictor located downhole inside the wellbore, and a second processor executes a second predictor located at the surface outside the wellbore. However, this configuration is not intended to be limiting. In other embodiments, both predictors may be located downhole. For example, now refer to… Figure 5 A schematic diagram of a system 500 according to an embodiment of the present disclosure is shown. System 500 can be configured to drill a wellbore 502 through geological formations 504. System 500 includes, for example, Figure 1 and Figure 3 The surface assembly shown and described includes a surface control unit 506. A column 508 is disposed within a wellbore 502 and configured to cut through the geological formation 504 using a disintegration device 510. As described above, the disintegration device 510 may be part of a BHA (Boiler Harness).

[0060] Adjacent to the disintegration device 510 may be a first processor 522 associated with and configured to execute the first predictor 512 (e.g., a first downhole processor and a first downhole predictor), and a third processor 524 associated with and configured to execute the third predictor 514 (e.g., a second downhole processor and a second downhole predictor). As described above, the predictor of this disclosure is a software process, instruction, or code executable by the associated processor. The third predictor 514 and the associated processor 524 may be arranged along post 508 between the first processor 522 and the associated first predictor 512 and the surface. Both the first predictor 512 and the third predictor 514 are downhole predictors. The surface control unit may include a second (or surface) processor 526 associated with and configured to execute the second (or surface) predictor 516. As shown, the second processor 526 executing the second predictor 516 is located outside post 508 and may be located at or part of the surface control unit 506. According to some implementation schemes, there may be no cable or wiring connecting the first processor 522 executing the first predictor 512 in the downhole control unit and the second processor 526 executing the second predictor 516 in the surface control unit 506.

[0061] At each processor 522, 524, 526, a pulse generator, pressure transducer, etc., may be associated with it for generating and / or detecting pulses in the fluid for telemetry purposes. Each of the predictors 512, 514, 516 may be configured identically such that each predictor 512, 514, 516 will output the same result given the same input. In some embodiments, an additional processor associated with and configured to execute the additional predictor may be provided along post 508, or one of the illustrated predictors 512, 514, 516 may be omitted, such that in some embodiments, both predictors are arranged downhole (e.g., a system with only a first predictor 512 and a second predictor 514).

[0062] In another embodiment, two or three of processors 522, 524, and 526 are configured to each execute more than one predictor. In such a configuration, each of these predictors executed by a single (or identical) processor is different from the others. For example, in this configuration, the first processor 522 may execute a first predictor 512 and a fifth predictor 532, the second processor 526 may execute a second predictor 516 and a fourth predictor 536, and the third processor 524 may execute a third predictor 514 and a sixth predictor 534. In this configuration, the first predictor 512 and the second predictor 516 may be the same, the third predictor 514 and the fourth predictor 536 may be the same, and the fifth predictor 532 and the sixth predictor 534 may be the same. Thus, the estimated value predicted by the first predictor 512 is equal to the estimated value predicted by the second predictor 516, the estimated value predicted by the third predictor 514 is equal to the estimated value predicted by the fourth predictor 536, and the estimated value predicted by the fifth predictor 532 is equal to the estimated value predicted by the sixth predictor 534. In this configuration, the second predictor 516 is configured to use the associated first sensor 542 to predict what the first processor 522 measures. The fourth predictor 536 is configured to use the associated second sensor 544 to predict what the third processor 524 measures. The sixth predictor 534 is configured to use the associated first sensor 542 to predict what the first processor 522 measures, or alternatively, the fifth predictor 532 is configured to use the associated second sensor 544 to predict what the third processor 524 measures. According to some embodiments, the first processor 522 and the third processor 524 may be arranged at the same location or approximately at the same location along the longitudinal axis of the column 508, or they may be arranged at different locations along the longitudinal axis of the column.

[0063] Now for reference Figure 6 This document illustrates a process 600 for performing operations according to an embodiment of the present disclosure. Process 600 can be performed using a system as shown and described herein. Such a system may include a first predictor at a first location and a second predictor at a second location separate from the first location. In some embodiments, the first predictor may be located in a downhole control unit that may be part of the BHA, and the second predictor may be arranged along the system column or at the surface above the well of the first predictor. As described above, the two predictors are identical, such that they will output the same result given the same input. Thus, each predictor will respond to the same information / data in the same manner, thereby allowing for reduced telemetry transmission.

[0064] The system for executing process 600 includes predictors implemented in corresponding controllers and / or control units, and includes a telemetry system for communication between a first predictor and a second predictor (or other components associated therewith). The telemetry system may be a mud pulse telemetry system (e.g., a pulse generator) configured to generate pressure waves within the fluid. As those skilled in the art will appreciate, each of the first and second predictors may be associated with a corresponding pulse generator for transmitting information and a system for receiving pulses from another system.

[0065] At operation 602, preliminary data is established at each of the first and second predictors. In some embodiments, operation 602 includes, for example, acquiring downhole measurements during drilling operations. Operation 602 may acquire one or more preliminary data points associated with the monitored characteristic or attribute. In some embodiments, operation 602 may include preset initial conditions, such as based on offset wells, experimental data, synthetic data, modeling, etc., and therefore preliminary data (e.g., baseline data) may be established independently of measurement data. The preliminary data may be stored in memory associated with the respective predictor.

[0066] At operation 604, each of the first and second predictors will generate an estimate. The estimate is a prediction based on preliminary data from operation 602. Because the first and second predictors are identical and provide the same preliminary data, the estimates generated at each of the first and second predictors will be identical. The estimate can be stored in the memory associated with each corresponding predictor. The estimate is a forward-looking prediction of the expected value of a measurement or observation performed by tools, devices, systems, etc., associated with the downhole operation.

[0067] At operation 606, the measured value is provided to the first predictor. The measured value can be obtained using a tool or other system configured to acquire data associated with the operation or component.

[0068] At operation 608, the first predictor compares the received measurement with the estimated value, and at operation 610 determines whether the measurement is within a predetermined threshold of the estimated value. The predetermined threshold may be specific to the type of data or measurement. For example, in some embodiments, at operation 608, the threshold may be an error tolerance (±) for a percentage, an absolute range, etc. In some embodiments, the threshold comparison may be a check to see if the measurement exceeds or falls below a specific absolute value associated with an attribute or characteristic. It will be understood that operation 608 and its comparison are specific to the data type or the measurement performed to obtain the measurement. The purpose of this comparison at operations 608 through 610 is to determine whether the measurement is substantially similar to the estimated value, such that the estimated value can be used as a valid data point.

[0069] Operations 606 to 610 are performed only at the first predictor. Operation 610 provides a "yes / no" output.

[0070] If the comparison at operations 608 to 610 indicates that the measured value is within the threshold (“Yes”), the first predictor will save the measured value and the estimated value. Furthermore, the first predictor will determine that it is not necessary to transmit the measured value to the second predictor because the estimated value is valid as a substitute. Therefore, at operation 612, the first predictor (or the associated controller / control unit) will not transmit the measured value to the second predictor. Thus, no telemetry transmission is performed. It will be understood that in some embodiments and operating modes, telemetry can be performed for purposes such as synchronization, even if the information matches (i.e., the estimated value is a valid substitute for the actual value). For example, in some embodiments, preset data transmission may always occur for synchronization purposes (e.g., every third value may be transmitted). That is, in some embodiments, a preset (or on-demand request from the ground) may prompt transmission even when the estimated value is valid.

[0071] The transmission of synchronization information may include measured values, predicted estimates, or another type of information. Other information may include, but is not limited to, indicators indicating how well the predicted estimates match the measured values, such as indicators for the difference between the measured values ​​and the predicted estimates (e.g., percentages or absolute values). In some embodiments, synchronization may include the number of predicted estimates and / or measured values ​​used by the downhole predictor or surface predictor since the prediction began. Synchronization may also include the ratio of the number of measured values ​​used in the downhole predictor or surface predictor to the number of predicted estimates since the prediction began. The transmission of synchronization information may be from the downhole control unit (e.g., downhole control unit 326) to the surface control unit (e.g., surface control unit 306) (i.e., uplink) or from the surface control unit to the downhole control unit (i.e., downlink). In some embodiments, the downhole control unit may be configured to transmit an acknowledgment to the surface control unit indicating that no measured values ​​have been transmitted to the surface control unit, and wherein the acknowledgment notifies the surface control unit that the predicted estimates at the surface predictor at the Earth's surface match the measured values ​​collected downhole in the wellbore within a predefined threshold. In this way, the ground control unit can check or confirm that it has not missed any measurements (e.g., through poor decoding or distorted data transmission via telemetry). The indicator can be a check, such as a 1-bit information or data element within a time window, or it can be some other coded information (e.g., two or more bits).

[0072] At operation 614, the second predictor will monitor received data that is reachable via telemetry signals and is associated with the estimated value. Because the first predictor prevents the system from transmitting the measured value, the second predictor will not receive the measured value associated with the estimated value. The absence of reception will indicate to the second predictor that the estimated value is a valid data entry, and the estimated value will be saved in the system as a valid entry for an expected measured value that has never arrived. It will be understood that the second processor or associated component / system executing the second predictor will monitor the received telemetry signals. Typically, telemetry is transmitted continuously or at predefined intervals, and therefore the second predictor knows when transmission is expected. Thus, the second predictor will know when (time window) telemetry signals have not arrived, because such signals are expected at known intervals, etc. Therefore, the second predictor is configured to detect when expected telemetry has not arrived. Thus, when no expected telemetry arrives at the second predictor, the second predictor will update the current entry with the estimated value as a substitute for the unarrived measured value.

[0073] Next, the operation returns to operation 604, where both the first and second predictors generate the next estimate. This subsequent estimate will be based on preliminary data combined with the updated value of the last entry (e.g., the generated final estimate). The process then continues in a loop through operations 606 to 610, and if the result of operation 610 is "yes," the process continues through operations 612-614, and again loops back to operation 604, with each iteration based on the last updated entry. If the predictor's prediction model (including threads) is accurate or within a threshold, it is possible to not send telemetry transmissions related to specific operations / attributes / characteristics for a period of time. In this way, the bandwidth (data / time) in the telemetry system will not be consumed by such data, and thus the throughput of information can be increased.

[0074] If, at operation 610, at any point in the loop (e.g., when the first operation 610 occurs or at any subsequent time), it is determined that the measured value is outside the threshold ("No" at operation 610), then process 600 proceeds to operation 616. At operation 616, the first processor (or associated component / system / controller / control unit) executing the first predictor will cause the measured value to be transmitted to the second predictor via telemetry.

[0075] At operation 618, the second predictor receives the measurement value received via telemetry and updates the next entry (e.g., the current entry) with the measurement value. That is, when process 600 returns to operation 604, the estimate generated at operation 604 (at the second predictor) is deleted (or stored in backup memory), and the second predictor uses the received measurement value to generate the next estimate.

[0076] In process 600, and according to embodiments of this disclosure, the first predictor (whether downhole or on the surface) is the predictor that will receive or generate initial measurements. The second predictor only receives this information / value when necessary, such as when the measured value does not adequately match the estimated value. In some embodiments, the first predictor is located downhole inside the wellbore and surrounded by drilling fluid, and the telemetry transmission is an uplink, wherein the second predictor is located above the first predictor or on the surface. In other embodiments or configurations, the first predictor is located on the surface or above the wellbore and surrounded by air, and the telemetry transmission is a downlink to the second predictor located downhole thereunder, such as in a BHA. It will be understood that each predictor can be both a first predictor and a second predictor, depending on the specific direction of the transmission and the location where the measurement is first obtained. That is, regardless of the location, the first predictor will be the predictor that receives the measurement, and the second predictor may or may not receive such measurement based on a comparison performed at the first predictor.

[0077] Furthermore, as noted above, in some implementations, more than two predictors may be employed in the system. In such implementations, there will typically be a single first predictor, and the other predictors will each be second predictors, with each second predictor receiving or not receiving measurements from the first predictor. In other implementations, the process may be chained. For example, and not limitingly, the first predictor may be located in the BHA. The first predictor may transmit to (or not to) a second predictor located on the wellbore but not on the surface. The second predictor, after receiving (or not receiving) from the BHA predictor, may become the first predictor and transmit from this intermediate predictor to (or not to) another second predictor, which may be located on the wellbore or on the surface. The reverse can also be true for downlink communication.

[0078] Advantageously, embodiments of this disclosure allow for improved data management and bandwidth usage for telemetry communications. By using at least two identical predictors, a determination can be made as to whether data should be transmitted via telemetry. Because the predictors are identical, identical inputs result in identical outputs, and therefore each predictor will know the value and state of the other predictor. Thus, when a predicted (estimated) value is determined to fairly represent a measurement, the measurement value may not be transmitted, and an estimated value may be input instead of the measurement value, thereby eliminating the need for data transmission.

[0079] Because telemetry in downhole environments is bandwidth / packet size limited, improved efficiency in data transmission from downhole to the surface (or from the surface to downhole), as described herein, can enhance this data transfer. By not transmitting certain data, the available bandwidth is increased to transmit other data that might be necessary for such transmission, and unnecessary data is not transmitted. According to some embodiments, a first predictor (processor) at a first location and a second predictor (processor) at a second location are provided, wherein at least one predictor is located downhole. The predictors are configured to perform the same algorithms, processes, methods, models, etc., such that the data received at each predictor is processed in the same manner. Each predictor acquires initial data (or previously acquired data) such as preliminary data and predicts the next data for a particular downhole measurement. Because the predictors are identical, the “next data” (forward-looking estimate) will be identical at each predictor. When new data is collected at the first predictor, if the new data is within a predefined error tolerance (i.e., matches the prediction), the data is not transmitted. When the second predictor does not receive the expected data, it will assume that the measurement data at the first predictor equals the predicted value, and therefore will continue based on the estimate. Conversely, if the measurement data at the first predictor does not match the prediction, the measurement data will be transmitted to the second predictor.

[0080] Advantageously, embodiments of this disclosure allow for the selective transmission of data based on predictions of expected measurements. That is, if a measurement matches an estimate, no data is transmitted, thus freeing up bandwidth that would otherwise be used for telemetry transmission. Each type of data, measurement, etc., will have an associated error limit that defines what is acceptable or unacceptable (i.e., how much deviation from the prediction should trigger or not trigger transmission).

[0081] The following are some of the aforementioned publicly disclosed implementation schemes:

[0082] Implementation Scheme 1: A method for predicting downhole measurement data at the Earth's surface, the method comprising: predicting a first estimate of an attribute of interest using a first processor disposed in a downhole tool disposed in a wellbore, the first processor executing a first predictor; predicting a second estimate of the attribute of interest using a second processor disposed in a surface unit located at the Earth's surface and outside the wellbore, the second processor executing a second predictor, the second predictor including the same data processing as the first predictor such that when the same input is provided to each of the first predictor and the second predictor, the first estimate predicted at the first processor is equal to the second estimate predicted at the second processor; obtaining a measurement of the attribute of interest by means of a sensor disposed in the downhole tool; comparing the measurement with the first estimate predicted by the first predictor at the first processor; determining whether the measurement is within the predetermined threshold relative to the first estimate; and, in response to the measurement being within the predetermined threshold of the first estimate, performing wellbore operations based on the second estimate of the attribute of interest using the second processor.

[0083] Implementation Scheme 2: The method according to any of the foregoing implementation schemes, the method further comprising: in response to the measured value being outside the predetermined threshold, using the first processor to transmit the measured value from the downhole tool to the surface unit; in response to receiving the transmitted measured value at the surface unit, replacing the second estimated value with the transmitted measured value by the second processor; and predicting a subsequent second estimated value using the second predictor based on the transmitted measured value.

[0084] Implementation Scheme 3: The method according to any of the preceding implementation schemes, wherein in response to the measured value being within the predetermined threshold of the first estimated value, the downhole tool is configured not to transmit the measured value to the surface unit.

[0085] Implementation Scheme 4: The method according to any of the foregoing implementation schemes, wherein the attribute of interest is one of the characteristics of the drilling operation and the properties of the Earth's formation.

[0086] Implementation Scheme 5: The method according to any of the preceding implementation schemes, the method further comprising: establishing a preliminary dataset used by each of the first predictor and the second predictor to predict the first estimate and the second estimate.

[0087] Implementation Scheme 6: The method according to any of the preceding implementation schemes, wherein the first predictor is configured to use the preliminary data, and the preliminary data includes data from two attributes, wherein one of the two attributes is the attribute of interest, and the other of the two attributes is one of a drilling operation characteristic and a geological formation attribute, and wherein the two attributes are different attributes.

[0088] Implementation Scheme 7: The method according to any of the preceding implementation schemes, wherein the predetermined threshold is one of a predetermined percentage deviation between the first estimate and the measured value and a predetermined absolute deviation between the first estimate and the measured value.

[0089] Implementation Scheme 8: The method according to any of the preceding embodiments, the method further comprising: using a third processor disposed in the downhole tool to predict a third estimate of the attribute of interest; and using a fourth predictor to predict a fourth estimate of the attribute of interest, wherein the third predictor includes the same data processing as the fourth predictor, such that when the same input is provided to each of the third predictor and the fourth predictor, the predicted third estimate is equal to the predicted fourth estimate, and wherein the fourth estimate is predicted using one of (i) the first processor or (ii) the second processor.

[0090] Implementation Scheme 9: The method according to any of the preceding implementation schemes, wherein the first predictor comprises one of linear regression, logistic regression, decision tree algorithm, gradient boosting model and neural network.

[0091] Implementation Scheme 10: The method according to any of the foregoing implementation schemes, the method further comprising: a predetermined time window, the predetermined time window being used by the second processor to wait for the measurement value to be transmitted from the downhole tool to the surface unit, and when the measurement value is not received at the surface unit within the predetermined time window, using the second estimate to perform the wellbore operation.

[0092] Implementation Scheme 11: The method according to any of the foregoing implementation schemes, the method further comprising: using the first processor to transmit an indicator from the downhole tool to the surface unit, the indicator instructing the second processor to perform the wellbore operation using the second estimate.

[0093] Implementation Scheme 12: The method according to any of the foregoing implementation schemes further includes: transmitting synchronization information from the downhole tool to the surface unit.

[0094] Implementation Scheme 13: A data prediction system for use with downhole operations, the data prediction system comprising: a sensor configured to acquire measurements of an attribute of interest, the sensor being disposed on a downhole tool located in a wellbore; a first processor disposed in the downhole tool; and a second processor disposed in a surface unit located at the Earth's surface and outside the wellbore; wherein the first processor is configured to: receive the measurements of the attribute of interest from the sensor; predict a first estimate of the attribute of interest by executing a first predictor; and compare the first estimate with the measurements. The first processor is configured to: compare the measured value with a predetermined threshold relative to the first estimated value; and determine whether the measured value is within a predetermined threshold relative to the first estimated value; and wherein the second processor is configured to: predict a second estimated value of the attribute of interest by executing a second predictor; and perform wellbore operations based on the second estimated value when the measured value is within the predetermined threshold relative to the first estimated value; wherein the first predictor and the second predictor are configured to perform the same data processing such that when the same input is provided to each of the first predictor and the second predictor, the first estimated value predicted at the first predictor is equal to the second estimated value predicted at the second predictor.

[0095] Implementation Scheme 14: A system according to any of the foregoing embodiments, wherein the first processor is configured to transmit the measured value from the downhole tool to the surface unit in response to the measured value being outside the predetermined threshold.

[0096] Implementation Scheme 15: The system according to any of the preceding embodiments further includes at least one of a mud pulse generator, an electromagnetic telemetry device, and an acoustic telemetry device configured to transmit the measurement value from the downhole tool to the surface unit in response to a command received from the first processor.

[0097] Implementation Scheme 16: A system according to any of the foregoing embodiments, wherein the second processor is configured to replace the second estimate with the transmitted measurement in the second predictor and to predict a subsequent second estimate using the second predictor based on the transmitted measurement.

[0098] Implementation Scheme 17: The system according to any of the foregoing implementation schemes, wherein there is no cable connection between the first processor and the second processor.

[0099] Implementation Scheme 18: A system according to any of the foregoing implementation schemes, wherein each of the first predictor and the second predictor uses preliminary data to predict the first estimate and the second estimate, respectively.

[0100] Implementation Scheme 19: The system according to any of the foregoing implementation schemes, wherein the predetermined threshold is one of a predetermined percentage deviation between the first estimate and the measured value or a predetermined absolute deviation between the first estimate and the measured value.

[0101] Implementation Scheme 20: The system according to any of the preceding embodiments further includes: a third processor disposed in the downhole tool and configured to predict a third estimate; and a fourth predictor executed by (i) the first processor or (ii) the second processor and configured to predict a fourth estimate, wherein the third predictor includes the same data processing as the fourth predictor, such that when the same input is provided to each of the third predictor and the fourth predictor, the predicted third estimate is equal to the predicted fourth estimate.

[0102] In the context of describing the invention (particularly in the context of the appended claims), the terms “an,” “a,” and “the,” and similar designations, should be interpreted to cover both the singular and plural, unless otherwise specified herein or clearly contradicted by the context. Furthermore, it should be noted that the terms “first,” “second,” etc., used herein do not indicate any order, quantity, or importance, but are used to distinguish one element from another. The terms “about,” “substantially,” and “generally” are intended to include, based on the equipment available at the time of filing, the degree of error associated with a particular number of measurements. For example, “about” and / or “substantially” and / or “generally” can include a range of ±8%, 5%, or 2% of a given value.

[0103] The teachings of this disclosure can be applied to a variety of well operations. These operations may involve treating a formation, fluids residing in the formation, the wellbore, and / or equipment within the wellbore, such as production tubing, with one or more treatment agents. Treatment agents can be in the form of liquids, gases, solids, semi-solids, and mixtures thereof. Exemplary treatment agents include, but are not limited to, fracturing fluids, acids, steam, water, brine, corrosion inhibitors, cementing agents, permeability modifiers, drilling mud, emulsifiers, demulsifiers, tracers, flow improvers, etc. Exemplary well operations include, but are not limited to, hydraulic fracturing, production enhancement, tracer injection, cleaning, acidizing, steam injection, water injection, cementing, etc.

[0104] Although the invention has been described with reference to one or more exemplary embodiments, those skilled in the art will understand that various changes can be made and equivalents can be substituted for elements therein without departing from the scope of the invention. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of the invention without departing from the basic scope of the invention. Therefore, it is contemplated that the invention is not limited to the specific embodiments disclosed as the best mode contemplated for carrying out the invention, but rather that the invention will encompass all embodiments falling within the scope of the claims. Additionally, exemplary embodiments of the invention have been disclosed in the drawings and detailed descriptions, and although specific terminology has been used, it is used in a general and descriptive sense only, and not for limiting purposes, unless otherwise specified, and therefore the scope of the invention is not limited thereto.

Claims

1. A method for predicting downhole measurement data at the surface of the earth, the method comprising: predicting (604) a first estimate (404) of a property of interest using a first processor (522) in a downhole tool (116, 318) disposed in a wellbore (104, 312, 502), the first processor executing a first predictor (512); predicting (604) a second estimate (404) of the property of interest using a second processor (526) disposed in a surface unit (506) located at the surface of the earth and outside of the wellbore, the second processor executing a second predictor (516), the second predictor including the same data processing as the first predictor such that the first estimate predicted at the first processor is equal to the second estimate predicted at the second processor when the same input is provided to each of the first predictor and the second predictor; obtaining (606) a measurement (402) of the property of interest via a sensor (132, 542, 544), wherein the sensor is disposed in the downhole tool; comparing, at the first processor, the measured value with the first estimated value predicted by the first predictor (608); determining (610) whether the measurement is within a predetermined threshold relative to the first estimate; as well as In response to the measured value being within the predetermined threshold of the first estimate, using the second processor to perform a wellbore operation based on the second estimate of the attribute of interest.

2. The method according to claim 1, further comprising: in response to the measurement being outside the predetermined threshold, transmitting (616) the measurement from the downhole tool to the surface unit using the first processor; in response to receiving the transmitted measurement at the ground unit, replacing (618), by the second processor, the second estimate with the transmitted measurement; as well as A subsequent second estimate is predicted (604) using the second predictor based on the transmitted measurement value.

3. The method of any preceding claim, wherein in response to the measurement being within the predetermined threshold from the first estimate, the downhole tool is configured to not transmit the measurement to the surface unit (612).

4. A method according to any preceding claim, wherein the property of interest is one of a characteristic of the drilling operation and a property of the Earth formation.

5. The method according to any preceding claim, further comprising: Establish (602) a preliminary data set used by each of the first predictor and the second predictor to predict the first estimate and the second estimate, preferably wherein the first predictor is configured to use the preliminary data and the preliminary data includes data from two attributes, wherein one of the two attributes is the attribute of interest and the other of the two attributes is one of a characteristic of the drilling operation and an attribute of the earth formation, and wherein the two attributes are different attributes.

6. A method according to any preceding claim, wherein the predetermined threshold is one of a predetermined percentage deviation between the first estimate and the measured value and a predetermined absolute value deviation between the first estimate and the measured value.

7. The method according to any preceding claim, further comprising: predicting (604) a third estimate of the property of interest using a third processor (524) disposed in the downhole tool; as well as predicting (604) a fourth estimate of the attribute of interest using a fourth predictor (536), wherein the third predictor includes the same data processing as the fourth predictor such that when the same input is provided to each of the third predictor and the fourth predictor, the predicted third estimate is equal to the predicted fourth estimate, and Wherein the fourth estimate is predicted using one of (i) the first processor or (ii) the second processor.

8. The method of any preceding claim, wherein the first predictor comprises one of a linear regression, a logistic regression, a decision tree algorithm, a gradient boosting model, and a neural network.

9. The method according to any preceding claim, further comprising: A predetermined time window is used by the second processor to wait for the measurement value to be transmitted from the downhole tool to the surface unit, and when the measurement value is not received at the surface unit within the predetermined time window, using the second estimate to perform the wellbore operation.

10. The method according to any preceding claim, further comprising: An indicator is transmitted from the downhole tool to the surface unit using the first processor, the indicator instructing the second processor to perform the wellbore operation using the second estimate.

11. The method according to any preceding claim, further comprising: Synchronization information is transmitted from the downhole tool to the surface unit.

12. A data prediction system for use with downhole operations, the data prediction system comprising: a sensor (132, 542, 544) configured to obtain a measurement of a property of interest, the sensor being disposed on a downhole tool (116, 318) located in a wellbore (104, 312, 502); a first processor (522) disposed in the downhole tool; and a second processor (526) disposed in a surface unit located at the earth's surface and outside the wellbore; The first processor is configured to: receiving the measured value of the property of interest from the sensor (402); predicting a first estimated value (404) of the attribute of interest by executing a first predictor (512); comparing the first estimate to the measured value; and determining whether the measured value is within a predetermined threshold with the first estimate; and The second processor is configured as follows: predicting a second estimated value (404) of the attribute of interest by executing a second predictor (516); and When the measured value is within the predetermined threshold with the first estimated value, performing a wellbore operation based on the second estimated value; wherein the first predictor and the second predictor are configured to perform the same data processing such that when the same input is provided to each of the first predictor and the second predictor, the first estimate predicted at the first predictor is equal to the second estimate predicted at the second predictor.

13. The system according to claim 12, further comprising: at least one of a mud pulse generator, an electromagnetic telemetry device and an acoustic telemetry device configured to transmit the measurement value from the downhole tool to the surface unit in response to a command received from the first processor, preferably wherein the second processor is configured to replace the second estimate value with the transmitted measurement value in the second predictor and to predict a subsequent second estimate value with the second predictor based on the transmitted measurement value.

14. The system of any one of claims 12-13, wherein there is no cable connection between the first processor and the second processor.

15. The system according to any one of claims 12 to 14, further comprising: a third processor (524) disposed in the downhole tool and configured to predict a third estimate; and a fourth predictor (536) executed by one of (i) the first processor or (ii) the second processor and configured to predict a fourth estimate, Wherein the third predictor includes the same data processing as the fourth predictor, such that when the same input is provided to each of the third predictor and the fourth predictor, the predicted third estimate is equal to the predicted fourth estimate.

Images