Automated interpretation of deposition volumes

Abstract

Disclosed are systems, apparatuses, methods, and computer readable medium for modeling depositions within a pipe. A method includes: building a predictive model of an interior of a pipe based on legacy data observations; receiving flowline data from a sensor indicating a flow profile within the pipe; analyzing the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and rendering a representation of the data representing the change in the flow profile.

Description

TECHNICAL FIELD

[0001] The present technology pertains to a well system for extracting materials, and more particularly, to automating the interpretation of diameter changes in the flowline for well or flowline facilities.BACKGROUND

[0002] A well or flowline system comprises a well-drilling or pipe laying system to form the well or flowline and a pumping system to move materials in the well or flowline. These systems include equipment and machinery designed to extract and transport natural resources, such as water, oil, or gas, from the ground. The system typically includes a drilling rig, which is used to bore a hole into the earth's crust, and a casing, which is a steel pipe that lines the well and prevents the walls from collapsing. The drilling process begins with the placement of a drill bit at the end of a drill string. The drill bit is then rotated, using a motor or a manual mechanism, to create a hole in the ground. As the hole is drilled, the drill string is gradually lengthened by adding more sections of pipe. The process continues until the desired depth is reached. When this fluid is produced, it is transported along a flowline for processing and distribution at gathering stations and refineries.

[0003] Once the drilling is complete, a casing is installed into the well to protect it from collapse and prevent contamination of the extracted resources. The casing is typically cemented into place to seal off any potential pathways for groundwater to enter the well. Once the well is prepared, a well-pumping system is installed to extract the resources from the well. The type of pump used depends on the type of resource being extracted, as well as the depth and diameter of the well. For example, a submersible pump may be used for a water well, while a reciprocating pump may be used for an oil well.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] In order to describe the manner in which the various advantages and features of the disclosure may be obtained, a more particular description of the principles described herein will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Understanding that these drawings depict only example embodiments of the disclosure and are not to be considered to limit its scope, the principles herein are described and explained with additional specificity and detail through the use of the drawings in which:

[0005] FIG. 1A is a schematic diagram of an example logging while drilling (LWD) wellbore operating environment in accordance with various aspects of the disclosure;

[0006] FIG. 1B is a diagram of an example downhole environment having tubulars, in accordance with various aspects of the disclosure;

[0007] FIG. 1C is a diagram of an example downhole environment having a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0008] FIG. 1D is diagram of an example of a non-intrusive deposition measurement system for identifying deposits in a fluidic channel;

[0009] FIG. 2 is a diagram of a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0010] FIG. 3 is an example output from a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0011] FIG. 4 is an example method for capturing data using a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure; and

[0012] FIG. 5 illustrates an example of computing system in accordance with some aspects of the present technology.DETAILED DESCRIPTION

[0013] Certain aspects of this disclosure are provided below. Some of these aspects may be applied independently and some of them may be applied in combination as would be apparent to those of skill in the art. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of aspects of the application. However, it will be apparent that various aspects may be practiced without these specific details. The figures and descriptions are not intended to be restrictive.

[0014] The ensuing description provides example aspects only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the example aspects will provide those skilled in the art with an enabling description for implementing an example aspect. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the application as set forth in the appended claims.

[0015] The terms “exemplary” and / or “example” are used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” and / or “example” is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term “aspects of the disclosure” does not require that all aspects of the disclosure include the discussed feature, advantage or mode of operation.

[0016] As previously described, well and flowline systems (or a well site) include a large number of interoperating components, and many of these components experience wear and tear, failure, adverse conditions, and other general issues that may affect operation of the well site. In one illustrative aspect, an electric submersible pump system, which is also referred to as an artificial lift pumping system, can be deployed into the downhole environment (e.g., into the well) and experiences high temperature, immense pressure, fluid-borne abrasives, excessive gas, scale, and variable flow rate environments. In some cases, operators of the well site may implement a records system to document the operation of the various components, adverse conditions, and data related to the adverse conditions. One type of data tracked and recorded is the pressure profiles of pipelines which can be undertaken by various equipment, including non-invasive equipment. The pressure profiles can be used to determine the contours of the inner diameter of a pipeline, providing a profile of potential deposits that take place while operating a well system. During the operation of the well or flowline system, including oil exploration, production, transportation, refining, and chemical processing, surfaces may become contaminated with deposits from crude oils. Some chemical species such as asphaltenes, paraffins, and mineral scales, for example, may be naturally present in crude oils. These chemical species, among others, may deposit on surfaces such as tubulars in the case of oil exploration, or on surfaces of pipelines during oil transport. Identification of these deposits, as well as their rate of change, allows for the operators to avoid failure and blockages of the pipelines while maintaining operations.

[0017] Operators are able to clean-out deposits found in a fluidic channel. After the fluidic channel is inspected at certain points and deposits are identified, a portion of the fluidic channel with deposits can be cleaned and / or replaced by any suitable method. For example, the operator can determine a cleaning process to remove the deposit from the fluidic channel based on the properties of the deposit. In some examples, the operator can initiate the cleaning process to remove the deposit from the fluidic channel. In some examples, the operator can initiate the cleaning process automatically without human assistance. In some examples, a user can begin the cleaning process by providing instructions to a controller. As the location and the identification and / or properties of each deposit in the fluidic channel is known, a more precise and targeted approach to address the deposits can be performed. Cleaning can take place via the use of pipeline inspection gauges (PIG) that operate within the fluidic channel to clean out deposits. The present disclosure allows an operator to identify the location of a deposit and the characteristics of the deposit and flowline to better implement cleaning out the deposit.

[0018] The use of off-site computing systems to undertake the interrogation of flowlines and identify depositions present can be intensive and time-consuming, which can lead to reduced measurements and time-delayed identification of deposits. Such off-site methods can also be expensive to operate and impractical to deploy in the field. What is needed is a process that is cost-effective, timely, easy to deploy, and avoids the use of memory and processing power only available with access to a full off-site facility. Accordingly, the present disclosure discusses a new method using an updated and improved model to determine deposition levels, the model incorporates regression analysis and neural networks to create a quick and efficient output that calculates depositions in a pipeline using the model in combination with previous measured data.

[0019] The disclosed technology addresses the foregoing by using a neural network and multivariate regression analysis to quickly and efficiently update the calculation of depositions in a pipe using the known state of the pipe from previous measurements, the current measurements, and the regression model. In various embodiments, a system may include one or more processors and at least one computer-readable storage medium storing instructions which, when executed by the one or more processors, cause the one or more processors to receive flowline data from a pressure sensor, determine, via analysis of the flowline data, the presence of a deposition, and build a predictive model based on legacy data observations and the presence of the deposition.

[0020] This disclosure includes tools and systems that allow for non-intrusive methodologies that, given a deposit's location in a fluidic channel such as a pipeline, wellbore, flowline, or well, can determine the basic properties of the deposit based on its physical attributes without the deployment of intrusive devices. Non-intrusive methodologies can enable better decisions to be made based on an understanding of deposit location using cost-effective equipment that can be deployed and maintained on-site for periodic inspections and reviews. By non-intrusively determining the properties of the deposits, delays that can result in loss of revenue from reduced or halted product flows, cost multiple millions of dollars per pipeline segment, or are well-treated with ineffective chemical or physical treatments can be avoided. Quick identification of deposits without costly deployment of multiple resources can enable a shorter delay in decisions regarding effective treatments and enable superior maintenance of targeted flow rates.

[0021] The ability to identify deposits without requiring deployment of equipment or sensors along the pipeline or wellbore length represents a major step forward and will support application of subsequent treatments in a manual or automated methodology.

[0022] The system can utilize acoustic or pressure waves induced by one or more pressure devices and measured by one or more sensors to characterize a variety of potential deposit properties which will be required for identification of various deposit types. The properties can include, for example: Porosity, Permeability, Elasticity, Darcy-Weisbach friction factor, Reynolds number, Surface roughness, etc. Analysis of these properties in conjunction with knowledge of the deposit's location and an ideal simulated model can provide identification of deposit material for support of treatment decisions.

[0023] Additional details and aspects of the present disclosure are described in more detail below with respect to the figures. The method can be employed using a pressure transducer, e.g., sensor 150, utilized in an exemplary system shown, for example, in FIGS. 1A-1D.

[0024] FIG. 1A is a schematic diagram of an example system for logging while drilling (LWD) operating environment of a well site, in accordance with various aspects of the disclosure.

[0025] In some aspects, the system 100 can be a drilling arrangement as shown in FIG. 1A, that exemplifies an LWD configuration in a wellbore drilling scenario. The LWD typically incorporates sensors that acquire formation data. The drilling arrangement of FIG. 1A also exemplifies measurement while drilling (MWD) and utilizes sensors to acquire data from which the wellbore's path and position in three-dimensional space may be determined. FIG. 1A shows a drilling platform 102 equipped with a derrick 104 that supports a hoist 106 for raising and lowering a drill string 108. The hoist 106 suspends a top drive 110 suitable for rotating and lowering the drill string 108 through a well head 112. A drill bit 114 may be connected to the lower end of the drill string 108. As the drill bit 114 rotates, the drill bit 114 creates a wellbore 116 that passes through at least one subterranean formation 118. A pump 120 circulates drilling fluid through a supply pipe 122 to top drive 110, down through the interior of the drill string 108, and out orifices in the drill bit 114 into the wellbore. The drilling fluid returns to the surface via the annulus around the drill string 108, and into a retention pit 124. The drilling fluid transports cuttings from the wellbore 116 into the retention pit 124 and the drilling fluid's presence in the annulus aids in maintaining the integrity of the wellbore 116. Various materials may be used for drilling fluid, including oil-based fluids and water-based fluids.

[0026] In some aspects, at least one logging tool 126 may be integrated into the bottom-hole assembly 125 near the drill bit 114. As the drill bit 114 extends the wellbore 116 through the subterranean formation 118, logging tool 126 collect measurements relating to various formation properties as well as the orientation of the tool and various other drilling conditions. In some cases, the logging tools interface with various sensors and equipment. The bottom-hole assembly 125 may also include a telemetry sub 128 to transfer measurement data to a surface receiver 132 and to receive commands from the surface. In at least some cases, the telemetry sub 128 communicates with a surface receiver 132 using mud pulse telemetry. In some instances, the telemetry sub 128 does not communicate with the surface, but rather stores logging data for later retrieval at the surface when the logging assembly is recovered.

[0027] Each logging tool 126 may include one or more tool components spaced apart from each other and communicatively coupled by one or more wires and / or another communication arrangement. The logging tool 126 may also include one or more computing devices communicatively coupled with one or more of the tool components. The one or more computing devices may be configured to control or monitor the performance of the tool, process logging data, and / or carry out one or more aspects of the methods and processes of the present disclosure.

[0028] In at least some instances, the at least one logging tool 126 may communicate with a surface receiver 132 by a wire, such as a wired drill pipe. In other cases, the at least one logging tool 126 may communicate with a surface receiver 132 by wireless signal transmission, such as ground penetrating radar. In at least some cases, one or more of the logging tools 126 may receive electrical power from a wire that extends to the surface, including wires extending through a wired drill pipe.

[0029] In some aspects, a collar 134 is a frequent component of a drill string 108 and generally resembles a very thick-walled cylindrical pipe, typically with threaded ends and a hollow core for the conveyance of drilling fluid. In some cases, more than one collar 134 may be included in the drill string 108 and are constructed and intended to be heavy to apply weight on the drill bit 114 to assist the drilling process. Because of the thickness of the collar's wall, pocket-type cutouts or other type recesses may be provided into the collar's wall without negatively impacting the integrity (strength, rigidity, and the like) of the collar 134 as a component of the drill string 108.

[0030] FIG. 1B is a diagram of an example downhole environment having tubulars in accordance with various aspects of the disclosure. In some aspects, an example system 140 is depicted for conducting downhole measurements after at least a portion of a wellbore has been drilled and the drill string removed from the well. A downhole tool is shown having a tool body 146 to perform logging, measurements, and / or other operations. For example, instead of using the drill string 108 of FIG. 1A to lower a tool body 146, which may contain sensors and / or other instrumentation for detecting and logging nearby characteristics and conditions of the wellbore 116 and surrounding formations, a wireline conveyance 144 may be used.

[0031] The tool body 146 may be lowered into the wellbore 116 by wireline conveyance 144. The wireline conveyance 144 may be anchored in the drill rig 142 or by a portable device such as a truck 145. The wireline conveyance 144 may include one or more wires, slicklines, cables, and / or the like, as well as tubular conveyances such as coiled tubing, joint tubing, or other tubulars.

[0032] The wireline conveyance 144 provides power and support for the tool, as well as enabling communication between processing systems 148 on the surface. In some examples, the wireline conveyance 144 may include electrical and / or fiber optic cabling for performing any communications. The wireline conveyance 144 is sufficiently strong and flexible to tether the tool body 146 through the wellbore 116, while also permitting communication through the wireline conveyance 144 to one or more of the processing systems 148, which may include local and / or remote processors. In some cases, power may be supplied via the wireline conveyance 144 to meet the power requirements of the tool. For slickline or coiled tubing configurations, power may be supplied downhole with a battery or via a downhole generator.

[0033] In other examples, as illustrated in FIG. 1C, the system 100 can be employed in an exemplary wellbore environment. The environment includes a derrick 104 extending over and around a fluidic channel 135, such as a wellbore 116 in FIG. 1C.

[0034] A conduit 137 can be disposed within the wellbore 116. In at least one example, the fluidic channel 135 can include the conduit 137. The conduit 137 can include, for example, wireline conveyance 144 (shown in FIG. 1B), tubing-conveyed, wireline, slickline, work string, joint tubing, jointed pipe, pipeline, coiled tubing, and / or any other suitable means for conveying a downhole device, e.g., tool body 146 in FIG. 1B, into a fluidic channel 135, such as a wellbore 116. In some examples, the conduit 137 can include electrical and / or fiber optic cabling for carrying out communications. The conduit 137 can be sufficiently strong and flexible to tether the downhole device, e.g., tool body 146 in FIG. 1B, through the wellbore 116, while also permitting communication through the conduit 137 to one or more of processors, which can include local and / or remote processors. Moreover, power can be supplied via the conduit 137 to meet power requirements of the downhole device, e.g., tool body 146 in FIG. 1B. For slickline or coiled tubing configurations, power can be supplied downhole with a battery or via a downhole generator.

[0035] The system of FIG. 1C includes a data acquisition system 195. Data acquisition system 195 includes at least one sensor 150 communicatively coupled with the controller 190 which can receive and / or process the data received from the sensors 150. While FIG. 1C illustrates one sensor 150, in other examples, more than one sensor 150 may be utilized. In at least one example, as illustrated in FIG. 1C, at least one sensor 150 can be disposed within the wellbore 116 at predetermined locations. The sensor 150 is positioned to measure pressure in the wellbore 116. Additionally, the sensor 150 may measure parameters related to the wellbore 116 and / or fluid in the wellbore 116, such as flow rate, temperature, and / or composition. In some examples, additional sensors 150 may measure additional parameters related to the wellbore 116 and / or the fluid in the wellbore 116 such as flow rate, temperature, and / or composition. In at least one example, sensor 150 can be disposed within the wellbore 116, for example it may be coupled with or disposed in a casing of the wellbore 116. Similarly, if the configuration included fluid transportation between two storage and refinery, for example, the at least one 150 can be along the flowline transporting the fluid.

[0036] It should be noted that while FIG. 1C generally depicts a land-based operation, the principles described herein are equally applicable to operations that employ floating or sea-based platforms and rigs, without departing from the scope of the disclosure. Also, even though FIG. 1C depicts a vertical wellbore, the present disclosure is equally well-suited for use in wellbores having other orientations, including horizontal wellbores, slanted wellbores, multilateral wellbores, or the like.

[0037] The fluidic channel 135 can include open ends such that each end is accessible by an operator and fluid can flow through the open ends. In other examples, the fluidic channel 135 can include a closed end such that fluid cannot flow through closed end. In at least one example, the open and / or closed ends can be located along any point of the fluidic channel 135. For example, an open and / or closed end may be located in the middle of the fluidic channel 135, and may be an entry point to gain access to the fluidic channel 135. While FIG. 1C shows a vertically oriented fluidic channel 135, the fluidic channel 135 can include multiple orientations, for example a vertical section, a diagonal section, and / or a horizontal section. In other examples, the fluidic channel 135 can extend only in one direction or multiple directions along any axis.

[0038] The fluidic channel 135 has walls which form an interior passage through which fluid can be contained in and flow. The fluid can be one fluid or more than one fluid. The fluid can include, for example, water and / or oil. The fluid can also substantially fill the entire fluidic channel 135 or, in other examples, the fluid can partially fill the fluidic channel 135. The fluidic channel 135 can be substantially circular, ovoid, rectangular, or any other suitable shape. The walls of the fluidic channel 135 can be made of any combination of plastics or metals, suitable to withstand fluid flow without corrosion and with minimal deformation. The fluidic channel 135 can also include at least one port 159 of FIG. 1D. The port159 of FIG. 1D can extend through the walls of the fluidic channel 135 and permit communication across the walls of the fluidic channel 135.

[0039] One example of a device that can be inserted and removed from the fluidic channel 135, through a port 159 of FIG. 1D or an open end of a pipe is a PIG device, either automated or manual. PIG devices are particularly useful with the substance of this disclosure as the predictive model identified hereinbelow is able to identify the location of the deposit and track its build-up over time. The operators of the system are then able to more easily determine when a cleanout is needed and the closest port or opening to the deposit for easy insertion of the PIG device. The predictive model can also provide a quick and meaningful test to determine if the clean-out was successful and to track how often successful clean-outs are needed.

[0040] The system 100 includes a data acquisition system 195 which receives and processes data such that the data can be used and interpreted by a user. The data acquisition system 195 can be located on-site and can share data with a data center, which can be proximate to the end of the fluidic channel 135. The data center may be above ground, under water, underground, or located at any point to collect data. For example, the data center may be an underwater vehicle or on a platform.

[0041] To obtain the measured profile and inspect the fluidic channel 135 in a non-intrusive manner, at least one pressure pulse can be induced. Referring to FIGS. 1D, to induce the pressure pulses, a pressure device 160 can be used. The pressure device 160 can be actuated to create a pressure pulse that travels through the fluidic channel 135 at the local speed of sound in the medium. In at least one example, the pressure device 160 is not a permanent fixture or attachment. As such, the pressure device 160 can be coupled to the fluidic channel 135 only when needed to create pressure pulses. In other examples, the pressure device 160 can be a permanent fixture in the fluidic channel 135. In at least one example, the pressure device 160 can include a valve which can close to create a pressure pulse, an injector to inject fluid into a fluidic channel, and / or a hydrophone projector. The type of mechanism for the pressure device 160 to create the pressure pulse can be determined based on the type of fluid and / or the type of fluidic channel 135.

[0042] For example, as illustrated in FIG. 1D, a pipeline or flowline system 170 can include a pressure device 160, and the pressure device 160 can include a hydrophone projector, and can include at least one hammer 162 and a collar 164 coupled with the hammer 162. The collar 164 can be configured to couple externally with the walls of the fluidic channel 135. The collar 164, for example, can wrap around the walls of the fluidic channel 135 to secure the pressure device 160 to be in contact with and external of the fluidic channel 135. As such, to actuate a pressure pulse with the pressure device 160, the pressure device 160 is not deposited within the interior passage of the fluidic channel 135. The pressure device 160 is non-intrusive, as the pressure device 160 is positioned external to the fluidic channel 135.

[0043] The pressure device 160 can be actuated and create the pressure pulse by the at least one hammer 162 striking and impacting the external surface of walls 157 of the fluidic channel 135. The hammer 162 can be electrical, mechanical, pneumatic, and / or hydraulic hammers. The hammer 162 can be any suitable object which can strike and impact the external surface of the walls 157, thereby creating a pressure pulse within the fluidic channel 135. For example, the hammer 162 can be any blunt object which does not damage the walls 157 of the fluidic channel 135 as the hammer 162 impact the walls 157. When the hammer 162 strike the walls 157, an acoustic pressure pulse is generated that travels upstream of the pressure device 160. The pressure device 160 can be electrically programmed, such that different pressures can be induced based on the strikes of the hammer 162. The harder the impact of the hammer 162 against the walls 157, the greater, or sharper, the pressure pulse. The striking of the hammer 162 against the walls 157 provides for a pulse with a higher resolution.

[0044] As the pressure pulse travels along the fluidic channel 135, any encountered obstructions or deposits 139 generate a reflected signal which is reflected back toward the pressure device 160. The system 100 includes a sensor 150 to receive the reflected pressure pulse signals. The sensor 150 can be a known distance from the pressure device 160. The sensor 150 can be a pressure transducer. In other examples, the sensor 150 can be any suitable sensor that measures pressure or stress of the fluid, for example a string gauge or an optical fiber transducer. The sensor 150 can be disposed within the interior passage of the fluidic channel 135. For example, the sensor 150, as illustrated in FIG. 1D, can be mounted to and / or inserted through a port 159 of the fluidic channel 135. The port 159 may be pre-existing, so the fluidic channel 135 does not need to be modified or disrupted to position the sensor 150. In other examples, the sensor 150 can be disposed external to the fluidic channel 135.

[0045] The reflected signals received by the sensor 150 are passed through a transmission system 115 to a data acquisition system 195 to be interpreted to map out and quantify any deposits 139 in the fluidic channel 135. The data acquisition system 195 can be located at the surface, within a vehicle, or any other suitable location such that the data can be interpreted by an operator. The transmission system 115 can be wireline, optical fiber, wirelessly such as through the cloud or Bluetooth, or any other suitable method to transmit data. In at least one example, the transmission system 115 can additionally be coupled with the pressure device 160 to send / receive instructions and / or data from the pressure device 160.

[0046] FIG. 2 illustrates a non-intrusive deposition measurement system 200, which measures the aforementioned results of drilling, wireline, or pumping operations. Non-intrusive deposition measurement system 200, shown in FIG. 2, can be a part of a pipeline, a producing wellbore, flowlines, or any pipeline where it is useful to measure depositions in a non-intrusive manner, e.g., single-phase and multi-phase fluids in the petroleum industry or any related industry, as shown in FIGS. 1A-1D. Further, while FIG. 2, places all the components on site, the components are capable of being separate and connected through a network. The non-intrusive deposition measurement system 200 works via the principle that a sensor can measure pressure profiles which can be compared with expected or predicted pressure profiles. Expected pressure profiles have normal distribution about the inner diameter of a pipe, but if there are any deposits within the pipe, the pressure profile will change based on the impact of the deposition. This pressure profile change is measured by sensor 250 and can be analyzed by the predictive model 220, which identifies the differences between the expected pressure profile and the measured pressure profile. This difference allows the system to identify the presence of depositions.

[0047] FIG. 2 includes sensor 250 that, in one embodiment, can be connected to a pipeline that is fluidically connected to a source of hydrocarbons such as a producing well or hydrocarbon storage area such as a tank farm or other hydrocarbon storage media. Sensor 250 measures the pressure profile provided by a signal based on a signal generator disposed on or within pipeline. Signal generator may be operable to produce an acoustical or pressure signal within pipeline which may propagate through pipeline and the signal produced can be received by sensor 250. Acoustical or pressure signals may interact with deposits which may alter acoustical or pressure signal by altering the amplitude, phase, frequency, or any combination thereof of acoustical or pressure signal created by the signal generator. In smooth conduits with no deposits, returning signals may be relatively unchanged. Conversely, when deposits are present, returning signals may exhibit additional characteristics different from the generated signal. Friction factors associated with deposits may determine how and to what degree acoustical or pressure signals are altered when encountering deposits. Reflected signals may be used to determine the location and magnitude of a deposit, for example.

[0048] Sensor 250 may be disposed on or within a pipeline at an upstream or downstream location from a signal generator. Sensor 250, and / or sensor 150 in FIGS. 1C and 1D, may be operable to detect acoustical or pressure signals produced by the signal generator or returning signals. Returning signals may be reflected acoustical or pressure waves reflected by deposits or other features within pipeline. Signals collected by Sensor 250 may be converted to a data file or data stream and transmitted to predictive model 220 via the analog-to-digital converter 240. The analog-to-digital converter 240 may be any module or program capable of converting the raw data received by the sensor 250 into a digital signal that is compatible with predictive model 220. Transmission of the raw data to analog-to-digital converter 240 and the data file or data stream from the analog-to-digital converter 240 to the predictive model 220 may be wired or wireless, for example.

[0049] The sensor 250 will typically encounter a pressure pulse traveling in a wellbore created by, e.g., a water hammer or valve closing. In principle, it can be assumed that when the pressure pulse has reached the bottom of the well or end of the pipe, the fluid velocity in the wellbore will be effectively reduced to zero. The frictional pressure drop will propagate continuously to the wellhead and can be measured and is often called line-packing.

[0050] One method of calculating the effects of the pressure pulse is using the Darcy-Weisbach equation, an empirical formula used to calculate the pressure drop in a fluid flowing through a pipe or duct. This equation is commonly used in fluid mechanics and engineering, particularly in fluid flow analysis in pipelines. The Darcy-Weisbach equation can be expressed as follows:Δ⁢p=f⁡(Ld)⁢(ρ⁢v22)Where Δp is the pressure drop (head loss) in the pipe, f is the Darcy friction factor, a dimensionless parameter that depends on the pipe's roughness and the Reynolds number (Re) of the flow, L is the length of the pipe, d is the diameter of the pipe, ρ is the density of the fluid, and v is the velocity of the fluid flow. This equation can be used to estimate the pressure drop due to friction as a fluid flows through a pipe, and it is particularly valuable in designing and analyzing pipelines for various applications, including water supply, oil and gas transportation, and industrial processes. The Darcy-Weisbach equation can also be written in terms of the pressure gradient if desired.The friction factor in single-phase and multiphase flows can be obtained from semi-empirical relationships such as the Blasius equation for laminar flow or the Colebrook-White equation, depending on the smoothness of the pipe. These equations show that the flow in land-based and offshore wellbores, flowlines, and pipelines depends on many factors. Additional factors are the pressure, volume, and temperature behavior of the fluid mixtures involved.

[0052] Sensor 250 can be used to collect and / or analyze multiple types of data, including:

[0053] an initial pressure, which can refer to the starting pressure at a specific point in the pipeline or system before any flow begins or any changes occur,

[0054] a mass flow rate (“MFR”), which can refer to the amount of mass passing through a given point in the system per unit of time, usually expressed in kilograms per second (kg / s) or pounds per hour (lb / h),

[0055] an incremental MFR, which can refer to the change in mass flow rate over a small segment of the system or over a small period of time, and it can represent how the mass flow rate varies incrementally,

[0056] a start time, which can refer to when a measurement or modeling process begins,

[0057] an end time, which can refer to when a measurement or modeling process ends,

[0058] a Haaland's factor, which can refer to a friction factor calculated using the Haaland equation, which is a formula used to determine the Darcy-Weisbach friction factor for fluid flow through pipes,

[0059] a friction factor, which can refer to a dimensionless number commonly found in fluid dynamics to quantify the resistance or friction losses in a pipe due to the flow of fluid, and it can be used in calculations involving the Darcy-Weisbach equation,

[0060] a pipe diameter, which can refer to the interior diameter of the pipe,

[0061] an incremental distance, which can refer to a segment of a pipeline or flowline,

[0062] an incremental diameter, which can refer to the change in diameter over time or over a distance,

[0063] an incremental acoustic velocity, which can refer to the change in the speed at which sound waves travel through the fluid in a pipe over a distance or period of time,

[0064] an incremental density, which can refer to the change in the density of a fluid in a pipeline or flowline over a segment of the pipeline or flowline or over a period of time,

[0065] an incremental viscosity, which can refer to the change in the viscosity of a fluid in a pipeline or flowline over a segment of the pipeline or flowline or over a period of time,

[0066] an incremental simulated pressure, which can refer to the change in pressure predicted by a model over a segment of the pipeline or flowline or over a period of time, and can be used to compare against observed or measured pressures as part of a model,

[0067] an incremental observed pressure, which can refer to the observed or measured change in pressure over a segment of the pipeline or flowline or over a period of time, and can be used to compare against modeled pressures, and

[0068] an incremental calculated deposition, which can refer to the change in the amount of material deposited inside a segment of a pipeline or a flowline over a period of time.

[0069] The multiple types of data referenced above can be captured using a single pressure transducer or multiple pressure transducers, can include the flowline geometry, and can include the fluid properties known to the system or collected by the sensor 250. Also, some of the data collected by the sensor 250 is used to calculate the above data, and all of the data collected or calculated can be stored in a dataset.

[0070] For example, the pressure transducer measures the pressure of the fluid within a pipeline or flowline. By capturing pressure data at different points or continuously, the system is able to collect data associated with various aspects of the fluid flow within the pipeline or flowline, such as flow rate, velocity, and pressure drops along the pipeline.

[0071] The flowline geometry is either modeled or known to the system operator and addresses the physical dimensions and shape of the pipeline or flowline, including data that addresses pipe diameter, pipe length, and any bends and / or fittings encountered in the pipeline or flowline. With the flowline geometry, the system is able to calculate flow rates and measure the fluid dynamics changes along the flowline that can be caused by, for example, changes in pipe diameter or the presence of deposits or other obstacles.

[0072] Fluid properties include such parameters as fluid density, fluid viscosity, fluid temperature, and other characteristics of the fluid within the pipeline or flowline. Fluid properties allow for the system to calculate and model fluid behavior under various conditions encountered during the transportation of the fluid through the pipeline or flowline. For example, when the system has data related to the fluid's viscosity, the system can better predict how the fluid will resist flow, and having data related to density can allow the system to convert between volumetric flow rates and mass flow rates. In one exemplary environment, the system 200 is able to use each of these measurements alone and / or in combination to model different aspects of the fluid flow through the pipeline or flowline.

[0073] These measurements and model outputs can all be stored in a dataset and used with the predictive model 220. Similarly, the legacy data is also capable of including any or all of these measurements in a dataset for use as a baseline for the predictive model. The non-intrusive deposition measurement system 200 is also able to determine segments of the pipeline or flowline based on the behavior of the measurements and models through the pipeline or flowline. When there are behavior changes within the pipeline or flowline, it can be advantageous to segment the pipeline or flowline into different segments so that the predictive model is better able to fit, as described with respect to FIG. 3 below, the predictive model to the pipeline or flowline, thereby providing improved outcomes for that segment of the pipeline or flowline.

[0074] Once the sensor receives the data from the pipeline, the predictive model 220 can receive the data from the analog-to-digital converter 240. Within the predictive model 220, calculation service 210 can create and store a data set based on models and previously collected data. The calculation service 210 is able to use the stored outputs from known theoretical fluid flow equations, e.g., Darcy-Weisbach, Blasius, Colebrook-White, amongst other known fluid flow equations, created off-site based on known data sets. These legacy data observations provide theoretically ideal models for the given pipeline, e.g., when there are no depositions, leaks, or obstructions and known baselines for depositions in the flowline. While these fluid flow calculations can be applied to the measured data sets collected via sensor 250, those calculations may be undertaken offsite because the process of applying these fluid flow equations to new data sets is computationally intensive and time-consuming. The off-site calculations require the use of large compute capacity along with significant power consumption.

[0075] Typically, on-site or in the field, any collection or calculation system will run on a programable logic controller (“PLC”), which may not be capable of running the fluid flow calculations to create a full model of pipe depositions. For this reason, the fluid flow calculations are typically undertaken off-site at a facility. The calculation service is capable of using the fluid flow calculations based on theoretical models created at an off-site facility and use those calculations to create a baseline model of a clean pipe and a baseline model based on the most recent fluid flow calculations. The models used by the calculation service 210 are updated when the fluid flow calculations are undertaken off-site and relayed to the calculation service 210, thereby updating the underlying basis of the models. By updating the underlying data, the system can iterate and improve the understanding of the system operations and create better fitting models for the current state of the pipe.

[0076] The predictive model 220 can be a linear or non-linear regression model based on the off-site calculations of the theoretical model and the raw data received from the analog-to-digital converter 240. The predictive model 220 can use a convergence value of the regression model that compares the ideal or theoretical flow through a pipeline and the last known state of flow through the pipeline with the observed characteristics of the pipeline. Using a regression model is fast, using a small computing load compared to solving the fluid flow equations related to the physics within the pipe. There are tradeoffs when using a regression model instead of using the fluid flow equations. For example, using a regression model sacrifices precision but takes orders of magnitude less time when compared to the time it takes to compute the fluid flow equations using collected data from a pipe. When a user needs basic information about the fluid flow instead of a full physical assessment, a regression analysis can provide sufficient information to the user. The regression analysis provides the basic information about whether fluid flow has changed significantly between tests. Based on this preliminary information, when significant changes are discovered or additional data is needed, a user can schedule for the data collected by sensor 250 to be sent off-site where fluid flow equations can be analyzed and assessed. However, if the regression analysis shows that the system has remained unchanged or the change is within expected parameters, no updated off-site calculations may be necessary. Instead of having to run the full models off-site on a regular basis to analyze the flow through a pipeline, using the predictive model 220 will quickly provide feedback on-site, which allows the user to determine if further assessment is needed.

[0077] Predictive model 220 can be a linear regression model. Linear regression models are a statistical model for the relationship between a dependent variable and one or more independent variables by fitting a linear equation to observed data. For example, based on the previous physics calculations of fluid flow, as well as the theoretical maximum flow, the predictive model 220 can provide a convergence factor that allows the predictive model 220 to determine the difference between the known, calculated profile of the flowline of the pipe and the measured data received from the sensor 250.

[0078] The goal of the linear regression algorithm applied by predictive model 220, is to find the best-fitting line through the data points that represent the measured data from sensor 250 and the previously calculated model of the profile of the flowline of the pipe, thereby minimizing the difference between the observed data and the expected data. One method that is used for linear regression minimizes the sum of the squared differences between the observed data and the expected data, also known as the least squares method. Linear regression is a method chosen when the relationship between the variables is approximately linear. However, when there is a non-linear relationship, non-linear regression algorithms can be used.

[0079] Non-linear regression models are statistical methods that model the relationship between dependent and independent variables when a linear equation does not effectively describe that relationship. Non-linear regression allows for more complex and curved relationships between the observed data and expected data. In non-linear regression, the goal is to estimate the parameters that best fit the observed data. The non-linear function can take various forms, such as exponential, logarithmic, polynomial, sigmoid, or any other non-linear shape that can better capture the underlying pattern in the data. Estimating parameters in non-linear regression models is typically performed using optimization techniques to minimize the difference between the observed data and predicted data. Unlike linear regression, there is no closed-form solution for estimating parameters, so numerical methods are often used. Oftentimes, non-linear regression can benefit from the application of machine learning, neural networks, and / or artificial intelligence to increase the speed of identifying and fitting the relationships between the legacy data and the observed data.

[0080] As addressed herein, a neural network constitutes an artificial mathematical construct designed to approximate nonlinear functions. Neurons within an artificial neural network are typically organized into a sequence of layers. Information traverses from the initial layer (the input layer), through one or more intermediate layers (hidden layers), and culminates in the final layer (the output layer). The input to each neuron is a scalar quantity, specifically a linear combination of the outputs from neurons in the preceding layer, weighted by the synaptic strengths (weights). The output signal of each neuron is derived from this input via its activation function, introducing nonlinearity into the network's computation. The functional behavior of the neural network is dictated by the synaptic weights between neurons. The training process involves adjusting these weights through methods such as empirical risk minimization and backpropagation, aiming to optimize the network's performance against a given dataset. These can be used in the present system with non-linear regression models to create a better analysis of the observed data and expected data.

[0081] In one example, predictive model 220 may apply an algorithm based on the following equation:y=β0+β1⁢x1+…+βr⁢xr+εThis may be the basis of a model that is built using regression, multivariate regression, neural networks, and / or machine learning, where the values of x are shown to have a linear relationship. βr are the regression coefficients and ε is the random error. By implementing a regression model using these relationships, the predictive model 220 can quickly model the expected deposition level within a pipeline. It is also possible to provide different weights to the model of legacy data, to impact the error and residuals, thereby targeting a minimization of the coefficient of determination, e.g., R2.The predictive model 220 can also undertake deposition analysis. Deposition analysis may include calculating a location and amount of deposition, for example. Acoustical and pressure waves generated and recorded enable monitoring of acoustical or pressure variations in a pipeline or wellbore. Generally, the data collected from the sensor 250 will be processed via predictive model 220 which can identify the location and size of the deposit.

[0083] The signal generated and received by sensor 250 may be created by any suitable signal generator configured to be operable to generate a pressure wave or an acoustic wave through a pipeline monitored by sensor 250. The signal generator may include a diaphragm, a fast-closing valve capable of generating a detectable pressure signal, injecting or removing mass from the pipeline, linear-actuator, electroacoustic transducers, or any combinations thereof. The signal generator may produce a recognized acoustical or pressure signal generated within a defined timeframe such that a distortion in the acoustical or pressure signal may be detected by sensor 250. Sensor 250 may include any suitable sensor operable to detect the generated signal within a pipeline. Sensor 250 may include a transducer configured to detect the generated signal and generate an output usable by the predictive model 220.

[0084] In some examples, depositions may be continuously monitored, and the analysis can be conducted continuously to account for deposits in real-time. The predictive model 220 can operate on a data set that identifies certain inputs, e.g., length of the flow line, diameter of the pipe, regression coefficients, and known random error, as well as any other inputs available from sensor 250. For example, the magnitude of the pressure pulse generated can be measured up-stream by using a sensor 250 (e.g., pressure transducer). In flow systems where the up-stream and down-stream pipes (wellbore, flowline, pipeline) are sufficiently long, the pressure increase immediately up-stream of the signal generator will be the same as given by the water-hammer equation.

[0085] The non-intrusive deposition measurement system 200 also includes an interface module 230. The interface module translates the data output from the predictive model 220 so that the device 260 is capable of receiving and rendering an output consistent with the predictive model output. The interface module 230 can be a hardware, software, or a combination of hardware and software. For example, it can be an API, an SDK, or any suitable hardware connection to allow the predictive model 220 to communicate with the device 260. Device 260 can be any output device available at the well site. For example, monitors, projectors, or any suitable audio / video device or software capable of providing appropriate outputs from the predictive model 220 to the user.

[0086] The non-intrusive deposition measurement system 200, in this example, can take place on an Internet of Things (“IoT”) edge device 270. This allows for distributed and scalable architecture to be used at a drill or pump site, for example, without needing to access or rely on the centralized cloud-based resources available. By using the IoT edge device 270 to implement the system 200, the system is able to provide on-site feedback using the sensor 250 data that is processed via the predictive model 220. As discussed above, the typical computing software for an edge device is a PLC that provides limited compute capacity but is capable of running the regression analysis of the predictive model 220. It is also capable of operating the remaining functions of the system 200, as described above. While a PLC is the primary edge device, the current disclosure is not limited to a PLC. The IoT edge device 270 can be any computing device capable of running the predictive model 220 and the other functions of the system 200, e.g., microcontrollers and microprocessors, software-based control systems (SCADA, etc.), or custom computing devices capable of operating on-site while running the predictive model and outputting results for the end user.

[0087] The non-intrusive deposition measurement system 200, can generate and output results based on inputting the data from the sensor 250 into the predictive model 220. The output, in one example, can resemble the output shown in FIG. 3. FIG. 3 shows an approximation of the output from a predictive model. As can be seen with reference to the figure, the left or “y” axis is labeled “diameter” and the bottom or “x” axis is labeled distance. This is an exemplary representation of the diameter of a pipe over a set distance. The measurements are taken downstream of the pressure pulse, where the pressure in the pipe is altered based on the deposits 320. deposits 320 are represented by the area under the curve 330, which are based on the previous off-site calculations based on legacy data, as discussed above. The predictive model 220 can provide an output that shows a change in the depositions, as represented by the modeled line 335. The predictive model 220 provides the output that is a regression analysis of the change in data measured by the sensor 250, and it is compared to the known state of the pipe, e.g., curve 330, modeled off of the legacy data. Based on the difference between curve 330 and modeled line 335, reflects the approximate change in deposition level within the pipe 310. As shown in FIG. 3, the change in deposition level is fairly modest and would most likely not necessitate further action by a user. However, if the modeled line 335 had a dramatic change that resulted in a large area present between curve 330 and modeled line 335, the end user may decide to undertake further action, and have the data from sensor 250 sent off-site for further analysis with the full computing power of the remote systems that can accurately analyze the data using the fluid flow and physics equations identified above.

[0088] Referring to FIG. 3, the fluidic channel 135 may include pipe 310, deposits 320 in the pipe 310 may form. The deposits 320 can be any material disposed in the pipe 310 of any amount and in any shape and form to at least partially impede flow of the fluid. For example, in some areas, the deposits 320 may completely block the interior of the pipe 310. Additionally, the deposits 320 may be to such an extent as to cause structural damage such as cracks in the top wall 340 and bottom wall 350 of the pipe 310. Deposits can be, for example, wax deposits, clay deposits, or any other possible deposits that can adhere to the top wall 340 and bottom wall 350 of the pipe 310 such that the fluid flow is at least partly impeded. For example, the deposits can include wax, precipitant such as asphaltenes, and / or scale.

[0089] In some areas, the pipe 310 may not have any deposits 320. For example, the cross-sectional shape of the pipe 310 can be substantially circular or any other desired shape as discussed with respect to the fluidic channel 135, above. In yet other areas, the pipe 310 may have deposits 320. The change in shape of the pipe 310 by the deposits 320 can cause the cross-sectional shape of the pipe 310 to be substantially ovoid, rectangular, diamond, triangular, irregular, or any other possible shape other than the original shape of the pipe 310. As illustrated in FIG. 3, the illustrated portion of the pipe 310 has one portion with deposits 320. In other examples, the fluidic channel 135 can include the pipe 310 which can be more than one portion with deposits 320. In yet other examples, the pipe 310 may not have any portions with deposits 320.

[0090] As the fluid flows through the pipe 310, from a portion without deposits 320 through a portion with deposits 320, the fluid may experience turbulent flow. In at least one example, the fluid may be prevented from flowing across the portion of the pipe 310 with deposits 320. The predictive model 220 is able to identify these deposits 320 based on the data collected by sensor 150 and / or 250.

[0091] The predictive model 220, can predict deposit 320 is present either on the top wall 340 of the pipe 310, the bottom wall 350 of the pipe 310, or both. The example FIG. 3 shows a deposit 320 that is at the bottom wall 350 of the pipe 310, but the model can also detect and include obstructions from the top wall 340 of the pipe 310. The predictive model 220 can incorporate the base case, a clean pipe with no deposits, the fluid flow calculations based on legacy data, and the regression model based on the difference between the models and the currently acquired data from sensor 250. The regression analysis predicts the difference between the models based on legacy data and current data, and outputs an approximation of the current state of the pipe which is represented in 300.

[0092] FIG. 4 illustrates an example method 400 for modeling the deposition changes within the flowline of a pipe. Although the example method 400 depicts a particular sequence of operations, the sequence may be altered without departing from the scope of the present disclosure. For example, some of the operations depicted may be performed in parallel or in a different sequence that does not materially affect the function of the method 400. In other examples, different components of an example device or system that implements the method 400 may perform functions at substantially the same time or in a specific sequence.

[0093] According to some embodiments, the method includes building a predictive model of an interior of a pipe based on legacy data observations at step 410. For example, the data from sensor 250 can be collected and sent off-site where the data can be assessed via the fluid flow equations. Off-site assessment can form the basis of the current state of the pipe that the predictive model 220 uses to determine if there are changes to the depositions in a pipe. The predictive model 220 is built using the calculation service 210, the previous assessments of fluid flow through a pipe based on legacy data, and the regression analysis applied to the data collected by the sensor 250. Using these inputs, the predictive model 220 can assess the data from the sensor 250 and provide an analysis on changes to the deposition level in a pipe.

[0094] According to some embodiments, the method includes receiving flowline data from a sensor indicating a flow profile within the pipe at step 420. For example, after a change in pressure is introduced to a pipe, the sensor 250 can detect how the pressure waves travel through the pipe and collect that data. The data from the sensor 250 can then be transmitted to the analog-to-digital converter 240, which translates the analog data into a digital signal. The digital signal from the analog-to-digital converter 240 can then be transmitted to the predictive model 220, where the predictive model 220 can assess the data from the sensor 250.

[0095] According to some embodiments, the method includes analyzing the flowline data using the predictive model at step 430. For example, after the data from the sensor 250 is received in step 420, the predictive model is able to assess the data using a regression analysis between what is expected based on the legacy data observations and the currently received data from sensor 250. This regression analysis can be linear or non-linear, and applies the equations discussed above with respect to predictive model 220.

[0096] According to some embodiments, the method includes outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data at step 440. For example, after analyzing the flowline data in step 440, the predictive model 220 will output the data reflecting the regression analysis undertaken by the model. This data will, in some examples, include the change between the data received from sensor 250 and the previous baseline of the pipe depositions based on legacy data. These differences are then able to be, for example, in a graph or similar representation to facilitate review by the end user.

[0097] According to some embodiments, the method includes rendering a representation of the data representing the change in the flow profile at step 450. For example, system 200, after the data is output from the predictive model 220, can transmit the data to an interface module that translates the data for presentation on device 260. In one example, the data can be rendered as shown in FIG. 3, with the expected curve 330, based on legacy data, and the modeled line 335 based on the regression analysis undertaken by the predictive model 220 based on the data collected by sensor 250.

[0098] FIG. 5 shows an example of computing system 500, which can be for example any computing device making up the IoT edge device 270, or any component thereof in which the components of the system are in communication with each other using connection 505. Connection 505 can be a physical connection via a bus, or a direct connection into processor 510, such as in a chipset architecture. Connection 505 can also be a virtual connection, networked connection, or logical connection.

[0099] In some embodiments, computing system 500 is a distributed system in which the functions described in this disclosure can be distributed within a datacenter, multiple data centers, a peer network, etc. In some embodiments, one or more of the described system components represents many such components each performing some or all of the function for which the component is described. In some embodiments, the components can be physical or virtual devices.

[0100] Example system 500 includes at least one processing unit (CPU or processor) 510 and connection 505 that couples various system components including system memory 515, such as read-only memory (ROM) 520 and random access memory (RAM) 525 to processor 510. Computing system 500 can include a cache of high-speed memory 512 connected directly with, in close proximity to, or integrated as part of processor 510.

[0101] Processor 510 can include any general purpose processor and a hardware service or software service, such as services 532, 534, and 536 stored in storage device 530, configured to control processor 510 as well as a special-purpose processor where software instructions are incorporated into the actual processor design. Processor 510 may essentially be a completely self-contained computing system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

[0102] To enable user interaction, computing system 500 includes an input device 545, which can represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech, etc. Computing system 500 can also include output device 535, which can be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems can enable a user to provide multiple types of input / output to communicate with computing system 500. Computing system 500 can include communications interface 540, which can generally govern and manage the user input and system output. There is no restriction on operating on any particular hardware arrangement, and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

[0103] Storage device 530 can be a non-volatile memory device and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, cartridges, random access memories (RAMs), read-only memory (ROM), and / or some combination of these devices.

[0104] The storage device 530 can include software services, servers, services, etc., that when the code that defines such software is executed by the processor 510, it causes the system to perform a function. In some embodiments, a hardware service that performs a particular function can include the software component stored in a computer-readable medium in connection with the necessary hardware components, such as processor 510, connection 505, output device 535, etc., to carry out the function.

[0105] For clarity of explanation, in some instances, the present technology may be presented as including individual functional blocks including functional blocks comprising devices, device components, steps or routines in a method embodied in software, or combinations of hardware and software.

[0106] Any of the steps, operations, functions, or processes described herein may be performed or implemented by a combination of hardware and software services or services, alone or in combination with other devices. In some embodiments, a service can be software that resides in memory of a client device and / or one or more servers of a content management system and perform one or more functions when a processor executes the software associated with the service. In some embodiments, a service is a program or a collection of programs that carry out a specific function. In some embodiments, a service can be considered a server. The memory can be a non-transitory computer-readable medium.

[0107] In some embodiments, the computer-readable storage devices, mediums, and memories can include a cable or wireless signal containing a bit stream and the like. However, when mentioned, non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals per se.

[0108] Methods according to the above-described examples can be implemented using computer-executable instructions that are stored or otherwise available from computer-readable media. Such instructions can comprise, for example, instructions and data which cause or otherwise configure a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Portions of computer resources used can be accessible over a network. The executable computer instructions may be, for example, binaries, intermediate format instructions such as assembly language, firmware, or source code. Examples of computer-readable media that may be used to store instructions, information used, and / or information created during methods according to described examples include magnetic or optical disks, solid-state memory devices, flash memory, USB devices provided with non-volatile memory, networked storage devices, and so on.

[0109] Devices implementing methods according to these disclosures can comprise hardware, firmware and / or software, and can take any of a variety of form factors. Typical examples of such form factors include servers, laptops, smartphones, small form factor personal computers, personal digital assistants, and so on. The functionality described herein also can be embodied in peripherals or add-in cards. Such functionality can also be implemented on a circuit board among different chips or different processes executing in a single device, by way of further example.

[0110] The instructions, media for conveying such instructions, computing resources for executing them, and other structures for supporting such computing resources are means for providing the functions described in these disclosures.

[0111] One of ordinary skill will appreciate that the less than (“<”) and greater than (“>”) symbols or terminology used herein may be replaced with less than or equal to (“≤”) and greater than or equal to (“≥”) symbols, respectively, without departing from the scope of this description.

[0112] Where components are described as being “configured to” perform certain operations, such configuration may be accomplished, for example, by designing electronic circuits or other hardware to perform the operation, by programming programmable electronic circuits (e.g., microprocessors, or other suitable electronic circuits) to perform the operation, or any combination thereof.

[0113] The phrase “coupled to” refers to any component that is physically connected to another component either directly or indirectly, and / or any component that is in communication with another component (e.g., connected to the other component over a wired or wireless connection, and / or other suitable communication interface) either directly or indirectly.

[0114] Claim language or other language reciting “at least one of” a set and / or “one or more” of a set indicates that one member of the set or multiple members of the set (in any combination) satisfy the claim. For example, claim language reciting “at least one of A and B” or “at least one of A or B” means A, B, or A and B. In another example, claim language reciting “at least one of A, B, and C” or “at least one of A, B, or C” means A, B, C, or A and B, or A and C, or B and C, or A and B and C. The language “at least one of” a set and / or “one or more” of a set does not limit the set to the items listed in the set. For example, claim language reciting “at least one of A and B” or “at least one of A or B” may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0115] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the aspects disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0116] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices such as general purposes computers, wireless communication device handsets, or integrated circuit devices having multiple uses including application in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized at least in part by a computer-readable data storage medium comprising program code including instructions that, when executed, performs one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may comprise memory or data storage media, such as RAM such as synchronous dynamic random access memory (SDRAM), ROM, non-volatile random access memory (NVRAM), EEPROM, flash memory, magnetic or optical data storage media, and the like. The techniques additionally, or alternatively, may be realized at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that may be accessed, read, and / or executed by a computer, such as propagated signals or waves.

[0117] The program code may be executed by a processor, which may include one or more processors, such as one or more DSPs, general purpose microprocessors, an application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Such a processor may be configured to perform any of the techniques described in this disclosure. A general purpose processor may be a microprocessor; but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Accordingly, the term “processor,” as used herein may refer to any of the foregoing structure, any combination of the foregoing structure, or any other structure or apparatus suitable for implementation of the techniques described herein.

[0118] Illustrative aspects of the disclosure include:

[0119] Aspect 1. A method comprising: building a predictive model of an interior of a flowline based on legacy data observations; receiving flowline data from a sensor indicating a flow profile within the pipe; analyzing the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and rendering a representation of the data representing the change in the flow profile.

[0120] Aspect 2. The method of Aspect 1, wherein the flowline data is collected using a pressure transducer.

[0121] Aspect 3. The method of any of Aspects 1 to 2, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0122] Aspect 4. The method of any of Aspects 1 to 3, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0123] Aspect 5. The method of any of Aspects 1 to 4, further comprising: collecting at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0124] Aspect 6. The method of any of Aspects 1 to 5, further comprising: initiating a pressure pulse within the flowline; and measuring the pressure pulse with the pressure sensor.

[0125] Aspect 7. The method of any of Aspects 1 to 6, wherein the pressure pulse is created through injecting mass, removing mass, or actuating a valve.

[0126] Aspect 8. The method of any of Aspects 1 to 7, wherein the predictive model includes a linear or non-linear regression model.

[0127] Aspect 9. The method of any of Aspects 1 to 8, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . βrxr+ε. β0, β1, . . . . βr, where X=x1 . . . , xr have a linear relationship, β are regression coefficients, and ε is the random error.

[0128] Aspect 10. The method of any of Aspects 1 to 9 wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

[0129] Aspect 11. A system includes a storage (implemented in circuitry) configured to store instructions and a processor. The processor configured to execute the instructions and cause the processor to: build a predictive model of an interior of a pipe based on legacy data observations; receive flowline data from a sensor indicating a flow profile within the pipe; analyze the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and render a representation of the data representing the change in the flow profile.

[0130] Aspect 12. The system of Aspect 11, wherein the flowline data is collected using a pressure transducer.

[0131] Aspect 13. The system of any of Aspects 11 to 12, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0132] Aspect 14. The system of any of Aspects 11 to 13, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0133] Aspect 15. The system of any of Aspects 11 to 14, wherein the processor is configured to execute the instructions and cause the processor to: collect at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0134] Aspect 16. The system of any of Aspects 11 to 15, wherein the processor is configured to execute the instructions and cause the processor to: initiate a pressure pulse within the flowline; and measure the pressure pulse with the pressure sensor.

[0135] Aspect 17. The system of any of Aspects 11 to 16, wherein the pressure pulse is created through injecting mass, remove mass, or actuate a valve.

[0136] Aspect 18. The system of any of Aspects 11 to 17, wherein the predictive model includes a linear or non-linear regression model.

[0137] Aspect 19. The system of any of Aspects 11 to 18, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . βrxr+ε . . . β0, β1, . . . . βr, where x=x1 . . . , xr have a linear relationship, B are regression coefficients, and ε is the random error.

[0138] Aspect 20. The system of any of Aspects 11 to 19, wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

[0139] Aspect 21. A computer readable medium comprising instructions using a computer system. The computer includes a memory (e.g., implemented in circuitry) and a processor (or multiple processors) coupled to the memory. The processor (or processors) is configured to execute the computer readable medium and cause the processor to: build a predictive model of an interior of a pipe based on legacy data observations; receive flowline data from a sensor indicating a flow profile within the pipe; analyze the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and render a representation of the data representing the change in the flow profile.

[0140] Aspect 22. The computer readable medium of Aspect 21, wherein the flowline data is collected using a pressure transducer.

[0141] Aspect 23. The computer readable medium of any of Aspects 21 to 22, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0142] Aspect 24. The computer readable medium of any of Aspects 21 to 23, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0143] Aspect 25. The computer readable medium of any of Aspects 21 to 24, wherein the processor is configured to execute the computer readable medium and cause the processor to: collect at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0144] Aspect 26. The computer readable medium of any of Aspects 21 to 25, wherein the processor is configured to execute the computer readable medium and cause the processor to: initiate a pressure pulse within the flowline; and measure the pressure pulse with the pressure sensor.

[0145] Aspect 27. The computer readable medium of any of Aspects 21 to 26, wherein the pressure pulse is created through injecting mass, remove mass, or actuate a valve.

[0146] Aspect 28. The computer readable medium of any of Aspects 21 to 27, wherein the predictive model includes a linear or non-linear regression model.

[0147] Aspect 29. The computer readable medium of any of Aspects 21 to 28, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . . βrxr+ε. β0, β1, . . . . βr, where x=x1 . . . , xr have a linear relationship, β are regression coefficients, and ε is the random error.

[0148] Aspect 30. The computer readable medium of any of Aspects 21 to 29, wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

Examples

Embodiment Construction

[0013]Certain aspects of this disclosure are provided below. Some of these aspects may be applied independently and some of them may be applied in combination as would be apparent to those of skill in the art. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of aspects of the application. However, it will be apparent that various aspects may be practiced without these specific details. The figures and descriptions are not intended to be restrictive.

[0014]The ensuing description provides example aspects only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the example aspects will provide those skilled in the art with an enabling description for implementing an example aspect. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope ...

TECHNICAL FIELD

[0001] The present technology pertains to a well system for extracting materials, and more particularly, to automating the interpretation of diameter changes in the flowline for well or flowline facilities.BACKGROUND

[0002] A well or flowline system comprises a well-drilling or pipe laying system to form the well or flowline and a pumping system to move materials in the well or flowline. These systems include equipment and machinery designed to extract and transport natural resources, such as water, oil, or gas, from the ground. The system typically includes a drilling rig, which is used to bore a hole into the earth's crust, and a casing, which is a steel pipe that lines the well and prevents the walls from collapsing. The drilling process begins with the placement of a drill bit at the end of a drill string. The drill bit is then rotated, using a motor or a manual mechanism, to create a hole in the ground. As the hole is drilled, the drill string is gradually lengthened by adding more sections of pipe. The process continues until the desired depth is reached. When this fluid is produced, it is transported along a flowline for processing and distribution at gathering stations and refineries.

[0003] Once the drilling is complete, a casing is installed into the well to protect it from collapse and prevent contamination of the extracted resources. The casing is typically cemented into place to seal off any potential pathways for groundwater to enter the well. Once the well is prepared, a well-pumping system is installed to extract the resources from the well. The type of pump used depends on the type of resource being extracted, as well as the depth and diameter of the well. For example, a submersible pump may be used for a water well, while a reciprocating pump may be used for an oil well.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] In order to describe the manner in which the various advantages and features of the disclosure may be obtained, a more particular description of the principles described herein will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Understanding that these drawings depict only example embodiments of the disclosure and are not to be considered to limit its scope, the principles herein are described and explained with additional specificity and detail through the use of the drawings in which:

[0005] FIG. 1A is a schematic diagram of an example logging while drilling (LWD) wellbore operating environment in accordance with various aspects of the disclosure;

[0006] FIG. 1B is a diagram of an example downhole environment having tubulars, in accordance with various aspects of the disclosure;

[0007] FIG. 1C is a diagram of an example downhole environment having a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0008] FIG. 1D is diagram of an example of a non-intrusive deposition measurement system for identifying deposits in a fluidic channel;

[0009] FIG. 2 is a diagram of a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0010] FIG. 3 is an example output from a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure;

[0011] FIG. 4 is an example method for capturing data using a non-intrusive deposition measurement system, in accordance with various aspects of the disclosure; and

[0012] FIG. 5 illustrates an example of computing system in accordance with some aspects of the present technology.DETAILED DESCRIPTION

[0013] Certain aspects of this disclosure are provided below. Some of these aspects may be applied independently and some of them may be applied in combination as would be apparent to those of skill in the art. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of aspects of the application. However, it will be apparent that various aspects may be practiced without these specific details. The figures and descriptions are not intended to be restrictive.

[0014] The ensuing description provides example aspects only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the example aspects will provide those skilled in the art with an enabling description for implementing an example aspect. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the application as set forth in the appended claims.

[0015] The terms “exemplary” and / or “example” are used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” and / or “example” is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term “aspects of the disclosure” does not require that all aspects of the disclosure include the discussed feature, advantage or mode of operation.

[0016] As previously described, well and flowline systems (or a well site) include a large number of interoperating components, and many of these components experience wear and tear, failure, adverse conditions, and other general issues that may affect operation of the well site. In one illustrative aspect, an electric submersible pump system, which is also referred to as an artificial lift pumping system, can be deployed into the downhole environment (e.g., into the well) and experiences high temperature, immense pressure, fluid-borne abrasives, excessive gas, scale, and variable flow rate environments. In some cases, operators of the well site may implement a records system to document the operation of the various components, adverse conditions, and data related to the adverse conditions. One type of data tracked and recorded is the pressure profiles of pipelines which can be undertaken by various equipment, including non-invasive equipment. The pressure profiles can be used to determine the contours of the inner diameter of a pipeline, providing a profile of potential deposits that take place while operating a well system. During the operation of the well or flowline system, including oil exploration, production, transportation, refining, and chemical processing, surfaces may become contaminated with deposits from crude oils. Some chemical species such as asphaltenes, paraffins, and mineral scales, for example, may be naturally present in crude oils. These chemical species, among others, may deposit on surfaces such as tubulars in the case of oil exploration, or on surfaces of pipelines during oil transport. Identification of these deposits, as well as their rate of change, allows for the operators to avoid failure and blockages of the pipelines while maintaining operations.

[0017] Operators are able to clean-out deposits found in a fluidic channel. After the fluidic channel is inspected at certain points and deposits are identified, a portion of the fluidic channel with deposits can be cleaned and / or replaced by any suitable method. For example, the operator can determine a cleaning process to remove the deposit from the fluidic channel based on the properties of the deposit. In some examples, the operator can initiate the cleaning process to remove the deposit from the fluidic channel. In some examples, the operator can initiate the cleaning process automatically without human assistance. In some examples, a user can begin the cleaning process by providing instructions to a controller. As the location and the identification and / or properties of each deposit in the fluidic channel is known, a more precise and targeted approach to address the deposits can be performed. Cleaning can take place via the use of pipeline inspection gauges (PIG) that operate within the fluidic channel to clean out deposits. The present disclosure allows an operator to identify the location of a deposit and the characteristics of the deposit and flowline to better implement cleaning out the deposit.

[0018] The use of off-site computing systems to undertake the interrogation of flowlines and identify depositions present can be intensive and time-consuming, which can lead to reduced measurements and time-delayed identification of deposits. Such off-site methods can also be expensive to operate and impractical to deploy in the field. What is needed is a process that is cost-effective, timely, easy to deploy, and avoids the use of memory and processing power only available with access to a full off-site facility. Accordingly, the present disclosure discusses a new method using an updated and improved model to determine deposition levels, the model incorporates regression analysis and neural networks to create a quick and efficient output that calculates depositions in a pipeline using the model in combination with previous measured data.

[0019] The disclosed technology addresses the foregoing by using a neural network and multivariate regression analysis to quickly and efficiently update the calculation of depositions in a pipe using the known state of the pipe from previous measurements, the current measurements, and the regression model. In various embodiments, a system may include one or more processors and at least one computer-readable storage medium storing instructions which, when executed by the one or more processors, cause the one or more processors to receive flowline data from a pressure sensor, determine, via analysis of the flowline data, the presence of a deposition, and build a predictive model based on legacy data observations and the presence of the deposition.

[0020] This disclosure includes tools and systems that allow for non-intrusive methodologies that, given a deposit's location in a fluidic channel such as a pipeline, wellbore, flowline, or well, can determine the basic properties of the deposit based on its physical attributes without the deployment of intrusive devices. Non-intrusive methodologies can enable better decisions to be made based on an understanding of deposit location using cost-effective equipment that can be deployed and maintained on-site for periodic inspections and reviews. By non-intrusively determining the properties of the deposits, delays that can result in loss of revenue from reduced or halted product flows, cost multiple millions of dollars per pipeline segment, or are well-treated with ineffective chemical or physical treatments can be avoided. Quick identification of deposits without costly deployment of multiple resources can enable a shorter delay in decisions regarding effective treatments and enable superior maintenance of targeted flow rates.

[0021] The ability to identify deposits without requiring deployment of equipment or sensors along the pipeline or wellbore length represents a major step forward and will support application of subsequent treatments in a manual or automated methodology.

[0022] The system can utilize acoustic or pressure waves induced by one or more pressure devices and measured by one or more sensors to characterize a variety of potential deposit properties which will be required for identification of various deposit types. The properties can include, for example: Porosity, Permeability, Elasticity, Darcy-Weisbach friction factor, Reynolds number, Surface roughness, etc. Analysis of these properties in conjunction with knowledge of the deposit's location and an ideal simulated model can provide identification of deposit material for support of treatment decisions.

[0023] Additional details and aspects of the present disclosure are described in more detail below with respect to the figures. The method can be employed using a pressure transducer, e.g., sensor 150, utilized in an exemplary system shown, for example, in FIGS. 1A-1D.

[0024] FIG. 1A is a schematic diagram of an example system for logging while drilling (LWD) operating environment of a well site, in accordance with various aspects of the disclosure.

[0025] In some aspects, the system 100 can be a drilling arrangement as shown in FIG. 1A, that exemplifies an LWD configuration in a wellbore drilling scenario. The LWD typically incorporates sensors that acquire formation data. The drilling arrangement of FIG. 1A also exemplifies measurement while drilling (MWD) and utilizes sensors to acquire data from which the wellbore's path and position in three-dimensional space may be determined. FIG. 1A shows a drilling platform 102 equipped with a derrick 104 that supports a hoist 106 for raising and lowering a drill string 108. The hoist 106 suspends a top drive 110 suitable for rotating and lowering the drill string 108 through a well head 112. A drill bit 114 may be connected to the lower end of the drill string 108. As the drill bit 114 rotates, the drill bit 114 creates a wellbore 116 that passes through at least one subterranean formation 118. A pump 120 circulates drilling fluid through a supply pipe 122 to top drive 110, down through the interior of the drill string 108, and out orifices in the drill bit 114 into the wellbore. The drilling fluid returns to the surface via the annulus around the drill string 108, and into a retention pit 124. The drilling fluid transports cuttings from the wellbore 116 into the retention pit 124 and the drilling fluid's presence in the annulus aids in maintaining the integrity of the wellbore 116. Various materials may be used for drilling fluid, including oil-based fluids and water-based fluids.

[0026] In some aspects, at least one logging tool 126 may be integrated into the bottom-hole assembly 125 near the drill bit 114. As the drill bit 114 extends the wellbore 116 through the subterranean formation 118, logging tool 126 collect measurements relating to various formation properties as well as the orientation of the tool and various other drilling conditions. In some cases, the logging tools interface with various sensors and equipment. The bottom-hole assembly 125 may also include a telemetry sub 128 to transfer measurement data to a surface receiver 132 and to receive commands from the surface. In at least some cases, the telemetry sub 128 communicates with a surface receiver 132 using mud pulse telemetry. In some instances, the telemetry sub 128 does not communicate with the surface, but rather stores logging data for later retrieval at the surface when the logging assembly is recovered.

[0027] Each logging tool 126 may include one or more tool components spaced apart from each other and communicatively coupled by one or more wires and / or another communication arrangement. The logging tool 126 may also include one or more computing devices communicatively coupled with one or more of the tool components. The one or more computing devices may be configured to control or monitor the performance of the tool, process logging data, and / or carry out one or more aspects of the methods and processes of the present disclosure.

[0028] In at least some instances, the at least one logging tool 126 may communicate with a surface receiver 132 by a wire, such as a wired drill pipe. In other cases, the at least one logging tool 126 may communicate with a surface receiver 132 by wireless signal transmission, such as ground penetrating radar. In at least some cases, one or more of the logging tools 126 may receive electrical power from a wire that extends to the surface, including wires extending through a wired drill pipe.

[0029] In some aspects, a collar 134 is a frequent component of a drill string 108 and generally resembles a very thick-walled cylindrical pipe, typically with threaded ends and a hollow core for the conveyance of drilling fluid. In some cases, more than one collar 134 may be included in the drill string 108 and are constructed and intended to be heavy to apply weight on the drill bit 114 to assist the drilling process. Because of the thickness of the collar's wall, pocket-type cutouts or other type recesses may be provided into the collar's wall without negatively impacting the integrity (strength, rigidity, and the like) of the collar 134 as a component of the drill string 108.

[0030] FIG. 1B is a diagram of an example downhole environment having tubulars in accordance with various aspects of the disclosure. In some aspects, an example system 140 is depicted for conducting downhole measurements after at least a portion of a wellbore has been drilled and the drill string removed from the well. A downhole tool is shown having a tool body 146 to perform logging, measurements, and / or other operations. For example, instead of using the drill string 108 of FIG. 1A to lower a tool body 146, which may contain sensors and / or other instrumentation for detecting and logging nearby characteristics and conditions of the wellbore 116 and surrounding formations, a wireline conveyance 144 may be used.

[0031] The tool body 146 may be lowered into the wellbore 116 by wireline conveyance 144. The wireline conveyance 144 may be anchored in the drill rig 142 or by a portable device such as a truck 145. The wireline conveyance 144 may include one or more wires, slicklines, cables, and / or the like, as well as tubular conveyances such as coiled tubing, joint tubing, or other tubulars.

[0032] The wireline conveyance 144 provides power and support for the tool, as well as enabling communication between processing systems 148 on the surface. In some examples, the wireline conveyance 144 may include electrical and / or fiber optic cabling for performing any communications. The wireline conveyance 144 is sufficiently strong and flexible to tether the tool body 146 through the wellbore 116, while also permitting communication through the wireline conveyance 144 to one or more of the processing systems 148, which may include local and / or remote processors. In some cases, power may be supplied via the wireline conveyance 144 to meet the power requirements of the tool. For slickline or coiled tubing configurations, power may be supplied downhole with a battery or via a downhole generator.

[0033] In other examples, as illustrated in FIG. 1C, the system 100 can be employed in an exemplary wellbore environment. The environment includes a derrick 104 extending over and around a fluidic channel 135, such as a wellbore 116 in FIG. 1C.

[0034] A conduit 137 can be disposed within the wellbore 116. In at least one example, the fluidic channel 135 can include the conduit 137. The conduit 137 can include, for example, wireline conveyance 144 (shown in FIG. 1B), tubing-conveyed, wireline, slickline, work string, joint tubing, jointed pipe, pipeline, coiled tubing, and / or any other suitable means for conveying a downhole device, e.g., tool body 146 in FIG. 1B, into a fluidic channel 135, such as a wellbore 116. In some examples, the conduit 137 can include electrical and / or fiber optic cabling for carrying out communications. The conduit 137 can be sufficiently strong and flexible to tether the downhole device, e.g., tool body 146 in FIG. 1B, through the wellbore 116, while also permitting communication through the conduit 137 to one or more of processors, which can include local and / or remote processors. Moreover, power can be supplied via the conduit 137 to meet power requirements of the downhole device, e.g., tool body 146 in FIG. 1B. For slickline or coiled tubing configurations, power can be supplied downhole with a battery or via a downhole generator.

[0035] The system of FIG. 1C includes a data acquisition system 195. Data acquisition system 195 includes at least one sensor 150 communicatively coupled with the controller 190 which can receive and / or process the data received from the sensors 150. While FIG. 1C illustrates one sensor 150, in other examples, more than one sensor 150 may be utilized. In at least one example, as illustrated in FIG. 1C, at least one sensor 150 can be disposed within the wellbore 116 at predetermined locations. The sensor 150 is positioned to measure pressure in the wellbore 116. Additionally, the sensor 150 may measure parameters related to the wellbore 116 and / or fluid in the wellbore 116, such as flow rate, temperature, and / or composition. In some examples, additional sensors 150 may measure additional parameters related to the wellbore 116 and / or the fluid in the wellbore 116 such as flow rate, temperature, and / or composition. In at least one example, sensor 150 can be disposed within the wellbore 116, for example it may be coupled with or disposed in a casing of the wellbore 116. Similarly, if the configuration included fluid transportation between two storage and refinery, for example, the at least one 150 can be along the flowline transporting the fluid.

[0036] It should be noted that while FIG. 1C generally depicts a land-based operation, the principles described herein are equally applicable to operations that employ floating or sea-based platforms and rigs, without departing from the scope of the disclosure. Also, even though FIG. 1C depicts a vertical wellbore, the present disclosure is equally well-suited for use in wellbores having other orientations, including horizontal wellbores, slanted wellbores, multilateral wellbores, or the like.

[0037] The fluidic channel 135 can include open ends such that each end is accessible by an operator and fluid can flow through the open ends. In other examples, the fluidic channel 135 can include a closed end such that fluid cannot flow through closed end. In at least one example, the open and / or closed ends can be located along any point of the fluidic channel 135. For example, an open and / or closed end may be located in the middle of the fluidic channel 135, and may be an entry point to gain access to the fluidic channel 135. While FIG. 1C shows a vertically oriented fluidic channel 135, the fluidic channel 135 can include multiple orientations, for example a vertical section, a diagonal section, and / or a horizontal section. In other examples, the fluidic channel 135 can extend only in one direction or multiple directions along any axis.

[0038] The fluidic channel 135 has walls which form an interior passage through which fluid can be contained in and flow. The fluid can be one fluid or more than one fluid. The fluid can include, for example, water and / or oil. The fluid can also substantially fill the entire fluidic channel 135 or, in other examples, the fluid can partially fill the fluidic channel 135. The fluidic channel 135 can be substantially circular, ovoid, rectangular, or any other suitable shape. The walls of the fluidic channel 135 can be made of any combination of plastics or metals, suitable to withstand fluid flow without corrosion and with minimal deformation. The fluidic channel 135 can also include at least one port 159 of FIG. 1D. The port159 of FIG. 1D can extend through the walls of the fluidic channel 135 and permit communication across the walls of the fluidic channel 135.

[0039] One example of a device that can be inserted and removed from the fluidic channel 135, through a port 159 of FIG. 1D or an open end of a pipe is a PIG device, either automated or manual. PIG devices are particularly useful with the substance of this disclosure as the predictive model identified hereinbelow is able to identify the location of the deposit and track its build-up over time. The operators of the system are then able to more easily determine when a cleanout is needed and the closest port or opening to the deposit for easy insertion of the PIG device. The predictive model can also provide a quick and meaningful test to determine if the clean-out was successful and to track how often successful clean-outs are needed.

[0040] The system 100 includes a data acquisition system 195 which receives and processes data such that the data can be used and interpreted by a user. The data acquisition system 195 can be located on-site and can share data with a data center, which can be proximate to the end of the fluidic channel 135. The data center may be above ground, under water, underground, or located at any point to collect data. For example, the data center may be an underwater vehicle or on a platform.

[0041] To obtain the measured profile and inspect the fluidic channel 135 in a non-intrusive manner, at least one pressure pulse can be induced. Referring to FIGS. 1D, to induce the pressure pulses, a pressure device 160 can be used. The pressure device 160 can be actuated to create a pressure pulse that travels through the fluidic channel 135 at the local speed of sound in the medium. In at least one example, the pressure device 160 is not a permanent fixture or attachment. As such, the pressure device 160 can be coupled to the fluidic channel 135 only when needed to create pressure pulses. In other examples, the pressure device 160 can be a permanent fixture in the fluidic channel 135. In at least one example, the pressure device 160 can include a valve which can close to create a pressure pulse, an injector to inject fluid into a fluidic channel, and / or a hydrophone projector. The type of mechanism for the pressure device 160 to create the pressure pulse can be determined based on the type of fluid and / or the type of fluidic channel 135.

[0042] For example, as illustrated in FIG. 1D, a pipeline or flowline system 170 can include a pressure device 160, and the pressure device 160 can include a hydrophone projector, and can include at least one hammer 162 and a collar 164 coupled with the hammer 162. The collar 164 can be configured to couple externally with the walls of the fluidic channel 135. The collar 164, for example, can wrap around the walls of the fluidic channel 135 to secure the pressure device 160 to be in contact with and external of the fluidic channel 135. As such, to actuate a pressure pulse with the pressure device 160, the pressure device 160 is not deposited within the interior passage of the fluidic channel 135. The pressure device 160 is non-intrusive, as the pressure device 160 is positioned external to the fluidic channel 135.

[0043] The pressure device 160 can be actuated and create the pressure pulse by the at least one hammer 162 striking and impacting the external surface of walls 157 of the fluidic channel 135. The hammer 162 can be electrical, mechanical, pneumatic, and / or hydraulic hammers. The hammer 162 can be any suitable object which can strike and impact the external surface of the walls 157, thereby creating a pressure pulse within the fluidic channel 135. For example, the hammer 162 can be any blunt object which does not damage the walls 157 of the fluidic channel 135 as the hammer 162 impact the walls 157. When the hammer 162 strike the walls 157, an acoustic pressure pulse is generated that travels upstream of the pressure device 160. The pressure device 160 can be electrically programmed, such that different pressures can be induced based on the strikes of the hammer 162. The harder the impact of the hammer 162 against the walls 157, the greater, or sharper, the pressure pulse. The striking of the hammer 162 against the walls 157 provides for a pulse with a higher resolution.

[0044] As the pressure pulse travels along the fluidic channel 135, any encountered obstructions or deposits 139 generate a reflected signal which is reflected back toward the pressure device 160. The system 100 includes a sensor 150 to receive the reflected pressure pulse signals. The sensor 150 can be a known distance from the pressure device 160. The sensor 150 can be a pressure transducer. In other examples, the sensor 150 can be any suitable sensor that measures pressure or stress of the fluid, for example a string gauge or an optical fiber transducer. The sensor 150 can be disposed within the interior passage of the fluidic channel 135. For example, the sensor 150, as illustrated in FIG. 1D, can be mounted to and / or inserted through a port 159 of the fluidic channel 135. The port 159 may be pre-existing, so the fluidic channel 135 does not need to be modified or disrupted to position the sensor 150. In other examples, the sensor 150 can be disposed external to the fluidic channel 135.

[0045] The reflected signals received by the sensor 150 are passed through a transmission system 115 to a data acquisition system 195 to be interpreted to map out and quantify any deposits 139 in the fluidic channel 135. The data acquisition system 195 can be located at the surface, within a vehicle, or any other suitable location such that the data can be interpreted by an operator. The transmission system 115 can be wireline, optical fiber, wirelessly such as through the cloud or Bluetooth, or any other suitable method to transmit data. In at least one example, the transmission system 115 can additionally be coupled with the pressure device 160 to send / receive instructions and / or data from the pressure device 160.

[0046] FIG. 2 illustrates a non-intrusive deposition measurement system 200, which measures the aforementioned results of drilling, wireline, or pumping operations. Non-intrusive deposition measurement system 200, shown in FIG. 2, can be a part of a pipeline, a producing wellbore, flowlines, or any pipeline where it is useful to measure depositions in a non-intrusive manner, e.g., single-phase and multi-phase fluids in the petroleum industry or any related industry, as shown in FIGS. 1A-1D. Further, while FIG. 2, places all the components on site, the components are capable of being separate and connected through a network. The non-intrusive deposition measurement system 200 works via the principle that a sensor can measure pressure profiles which can be compared with expected or predicted pressure profiles. Expected pressure profiles have normal distribution about the inner diameter of a pipe, but if there are any deposits within the pipe, the pressure profile will change based on the impact of the deposition. This pressure profile change is measured by sensor 250 and can be analyzed by the predictive model 220, which identifies the differences between the expected pressure profile and the measured pressure profile. This difference allows the system to identify the presence of depositions.

[0047] FIG. 2 includes sensor 250 that, in one embodiment, can be connected to a pipeline that is fluidically connected to a source of hydrocarbons such as a producing well or hydrocarbon storage area such as a tank farm or other hydrocarbon storage media. Sensor 250 measures the pressure profile provided by a signal based on a signal generator disposed on or within pipeline. Signal generator may be operable to produce an acoustical or pressure signal within pipeline which may propagate through pipeline and the signal produced can be received by sensor 250. Acoustical or pressure signals may interact with deposits which may alter acoustical or pressure signal by altering the amplitude, phase, frequency, or any combination thereof of acoustical or pressure signal created by the signal generator. In smooth conduits with no deposits, returning signals may be relatively unchanged. Conversely, when deposits are present, returning signals may exhibit additional characteristics different from the generated signal. Friction factors associated with deposits may determine how and to what degree acoustical or pressure signals are altered when encountering deposits. Reflected signals may be used to determine the location and magnitude of a deposit, for example.

[0048] Sensor 250 may be disposed on or within a pipeline at an upstream or downstream location from a signal generator. Sensor 250, and / or sensor 150 in FIGS. 1C and 1D, may be operable to detect acoustical or pressure signals produced by the signal generator or returning signals. Returning signals may be reflected acoustical or pressure waves reflected by deposits or other features within pipeline. Signals collected by Sensor 250 may be converted to a data file or data stream and transmitted to predictive model 220 via the analog-to-digital converter 240. The analog-to-digital converter 240 may be any module or program capable of converting the raw data received by the sensor 250 into a digital signal that is compatible with predictive model 220. Transmission of the raw data to analog-to-digital converter 240 and the data file or data stream from the analog-to-digital converter 240 to the predictive model 220 may be wired or wireless, for example.

[0049] The sensor 250 will typically encounter a pressure pulse traveling in a wellbore created by, e.g., a water hammer or valve closing. In principle, it can be assumed that when the pressure pulse has reached the bottom of the well or end of the pipe, the fluid velocity in the wellbore will be effectively reduced to zero. The frictional pressure drop will propagate continuously to the wellhead and can be measured and is often called line-packing.

[0050] One method of calculating the effects of the pressure pulse is using the Darcy-Weisbach equation, an empirical formula used to calculate the pressure drop in a fluid flowing through a pipe or duct. This equation is commonly used in fluid mechanics and engineering, particularly in fluid flow analysis in pipelines. The Darcy-Weisbach equation can be expressed as follows:Δ⁢p=f⁡(Ld)⁢(ρ⁢v22)Where Δp is the pressure drop (head loss) in the pipe, f is the Darcy friction factor, a dimensionless parameter that depends on the pipe's roughness and the Reynolds number (Re) of the flow, L is the length of the pipe, d is the diameter of the pipe, ρ is the density of the fluid, and v is the velocity of the fluid flow. This equation can be used to estimate the pressure drop due to friction as a fluid flows through a pipe, and it is particularly valuable in designing and analyzing pipelines for various applications, including water supply, oil and gas transportation, and industrial processes. The Darcy-Weisbach equation can also be written in terms of the pressure gradient if desired.The friction factor in single-phase and multiphase flows can be obtained from semi-empirical relationships such as the Blasius equation for laminar flow or the Colebrook-White equation, depending on the smoothness of the pipe. These equations show that the flow in land-based and offshore wellbores, flowlines, and pipelines depends on many factors. Additional factors are the pressure, volume, and temperature behavior of the fluid mixtures involved.

[0052] Sensor 250 can be used to collect and / or analyze multiple types of data, including:

[0053] an initial pressure, which can refer to the starting pressure at a specific point in the pipeline or system before any flow begins or any changes occur,

[0054] a mass flow rate (“MFR”), which can refer to the amount of mass passing through a given point in the system per unit of time, usually expressed in kilograms per second (kg / s) or pounds per hour (lb / h),

[0055] an incremental MFR, which can refer to the change in mass flow rate over a small segment of the system or over a small period of time, and it can represent how the mass flow rate varies incrementally,

[0056] a start time, which can refer to when a measurement or modeling process begins,

[0057] an end time, which can refer to when a measurement or modeling process ends,

[0058] a Haaland's factor, which can refer to a friction factor calculated using the Haaland equation, which is a formula used to determine the Darcy-Weisbach friction factor for fluid flow through pipes,

[0059] a friction factor, which can refer to a dimensionless number commonly found in fluid dynamics to quantify the resistance or friction losses in a pipe due to the flow of fluid, and it can be used in calculations involving the Darcy-Weisbach equation,

[0060] a pipe diameter, which can refer to the interior diameter of the pipe,

[0061] an incremental distance, which can refer to a segment of a pipeline or flowline,

[0062] an incremental diameter, which can refer to the change in diameter over time or over a distance,

[0063] an incremental acoustic velocity, which can refer to the change in the speed at which sound waves travel through the fluid in a pipe over a distance or period of time,

[0064] an incremental density, which can refer to the change in the density of a fluid in a pipeline or flowline over a segment of the pipeline or flowline or over a period of time,

[0065] an incremental viscosity, which can refer to the change in the viscosity of a fluid in a pipeline or flowline over a segment of the pipeline or flowline or over a period of time,

[0066] an incremental simulated pressure, which can refer to the change in pressure predicted by a model over a segment of the pipeline or flowline or over a period of time, and can be used to compare against observed or measured pressures as part of a model,

[0067] an incremental observed pressure, which can refer to the observed or measured change in pressure over a segment of the pipeline or flowline or over a period of time, and can be used to compare against modeled pressures, and

[0068] an incremental calculated deposition, which can refer to the change in the amount of material deposited inside a segment of a pipeline or a flowline over a period of time.

[0069] The multiple types of data referenced above can be captured using a single pressure transducer or multiple pressure transducers, can include the flowline geometry, and can include the fluid properties known to the system or collected by the sensor 250. Also, some of the data collected by the sensor 250 is used to calculate the above data, and all of the data collected or calculated can be stored in a dataset.

[0070] For example, the pressure transducer measures the pressure of the fluid within a pipeline or flowline. By capturing pressure data at different points or continuously, the system is able to collect data associated with various aspects of the fluid flow within the pipeline or flowline, such as flow rate, velocity, and pressure drops along the pipeline.

[0071] The flowline geometry is either modeled or known to the system operator and addresses the physical dimensions and shape of the pipeline or flowline, including data that addresses pipe diameter, pipe length, and any bends and / or fittings encountered in the pipeline or flowline. With the flowline geometry, the system is able to calculate flow rates and measure the fluid dynamics changes along the flowline that can be caused by, for example, changes in pipe diameter or the presence of deposits or other obstacles.

[0072] Fluid properties include such parameters as fluid density, fluid viscosity, fluid temperature, and other characteristics of the fluid within the pipeline or flowline. Fluid properties allow for the system to calculate and model fluid behavior under various conditions encountered during the transportation of the fluid through the pipeline or flowline. For example, when the system has data related to the fluid's viscosity, the system can better predict how the fluid will resist flow, and having data related to density can allow the system to convert between volumetric flow rates and mass flow rates. In one exemplary environment, the system 200 is able to use each of these measurements alone and / or in combination to model different aspects of the fluid flow through the pipeline or flowline.

[0073] These measurements and model outputs can all be stored in a dataset and used with the predictive model 220. Similarly, the legacy data is also capable of including any or all of these measurements in a dataset for use as a baseline for the predictive model. The non-intrusive deposition measurement system 200 is also able to determine segments of the pipeline or flowline based on the behavior of the measurements and models through the pipeline or flowline. When there are behavior changes within the pipeline or flowline, it can be advantageous to segment the pipeline or flowline into different segments so that the predictive model is better able to fit, as described with respect to FIG. 3 below, the predictive model to the pipeline or flowline, thereby providing improved outcomes for that segment of the pipeline or flowline.

[0074] Once the sensor receives the data from the pipeline, the predictive model 220 can receive the data from the analog-to-digital converter 240. Within the predictive model 220, calculation service 210 can create and store a data set based on models and previously collected data. The calculation service 210 is able to use the stored outputs from known theoretical fluid flow equations, e.g., Darcy-Weisbach, Blasius, Colebrook-White, amongst other known fluid flow equations, created off-site based on known data sets. These legacy data observations provide theoretically ideal models for the given pipeline, e.g., when there are no depositions, leaks, or obstructions and known baselines for depositions in the flowline. While these fluid flow calculations can be applied to the measured data sets collected via sensor 250, those calculations may be undertaken offsite because the process of applying these fluid flow equations to new data sets is computationally intensive and time-consuming. The off-site calculations require the use of large compute capacity along with significant power consumption.

[0075] Typically, on-site or in the field, any collection or calculation system will run on a programable logic controller (“PLC”), which may not be capable of running the fluid flow calculations to create a full model of pipe depositions. For this reason, the fluid flow calculations are typically undertaken off-site at a facility. The calculation service is capable of using the fluid flow calculations based on theoretical models created at an off-site facility and use those calculations to create a baseline model of a clean pipe and a baseline model based on the most recent fluid flow calculations. The models used by the calculation service 210 are updated when the fluid flow calculations are undertaken off-site and relayed to the calculation service 210, thereby updating the underlying basis of the models. By updating the underlying data, the system can iterate and improve the understanding of the system operations and create better fitting models for the current state of the pipe.

[0076] The predictive model 220 can be a linear or non-linear regression model based on the off-site calculations of the theoretical model and the raw data received from the analog-to-digital converter 240. The predictive model 220 can use a convergence value of the regression model that compares the ideal or theoretical flow through a pipeline and the last known state of flow through the pipeline with the observed characteristics of the pipeline. Using a regression model is fast, using a small computing load compared to solving the fluid flow equations related to the physics within the pipe. There are tradeoffs when using a regression model instead of using the fluid flow equations. For example, using a regression model sacrifices precision but takes orders of magnitude less time when compared to the time it takes to compute the fluid flow equations using collected data from a pipe. When a user needs basic information about the fluid flow instead of a full physical assessment, a regression analysis can provide sufficient information to the user. The regression analysis provides the basic information about whether fluid flow has changed significantly between tests. Based on this preliminary information, when significant changes are discovered or additional data is needed, a user can schedule for the data collected by sensor 250 to be sent off-site where fluid flow equations can be analyzed and assessed. However, if the regression analysis shows that the system has remained unchanged or the change is within expected parameters, no updated off-site calculations may be necessary. Instead of having to run the full models off-site on a regular basis to analyze the flow through a pipeline, using the predictive model 220 will quickly provide feedback on-site, which allows the user to determine if further assessment is needed.

[0077] Predictive model 220 can be a linear regression model. Linear regression models are a statistical model for the relationship between a dependent variable and one or more independent variables by fitting a linear equation to observed data. For example, based on the previous physics calculations of fluid flow, as well as the theoretical maximum flow, the predictive model 220 can provide a convergence factor that allows the predictive model 220 to determine the difference between the known, calculated profile of the flowline of the pipe and the measured data received from the sensor 250.

[0078] The goal of the linear regression algorithm applied by predictive model 220, is to find the best-fitting line through the data points that represent the measured data from sensor 250 and the previously calculated model of the profile of the flowline of the pipe, thereby minimizing the difference between the observed data and the expected data. One method that is used for linear regression minimizes the sum of the squared differences between the observed data and the expected data, also known as the least squares method. Linear regression is a method chosen when the relationship between the variables is approximately linear. However, when there is a non-linear relationship, non-linear regression algorithms can be used.

[0079] Non-linear regression models are statistical methods that model the relationship between dependent and independent variables when a linear equation does not effectively describe that relationship. Non-linear regression allows for more complex and curved relationships between the observed data and expected data. In non-linear regression, the goal is to estimate the parameters that best fit the observed data. The non-linear function can take various forms, such as exponential, logarithmic, polynomial, sigmoid, or any other non-linear shape that can better capture the underlying pattern in the data. Estimating parameters in non-linear regression models is typically performed using optimization techniques to minimize the difference between the observed data and predicted data. Unlike linear regression, there is no closed-form solution for estimating parameters, so numerical methods are often used. Oftentimes, non-linear regression can benefit from the application of machine learning, neural networks, and / or artificial intelligence to increase the speed of identifying and fitting the relationships between the legacy data and the observed data.

[0080] As addressed herein, a neural network constitutes an artificial mathematical construct designed to approximate nonlinear functions. Neurons within an artificial neural network are typically organized into a sequence of layers. Information traverses from the initial layer (the input layer), through one or more intermediate layers (hidden layers), and culminates in the final layer (the output layer). The input to each neuron is a scalar quantity, specifically a linear combination of the outputs from neurons in the preceding layer, weighted by the synaptic strengths (weights). The output signal of each neuron is derived from this input via its activation function, introducing nonlinearity into the network's computation. The functional behavior of the neural network is dictated by the synaptic weights between neurons. The training process involves adjusting these weights through methods such as empirical risk minimization and backpropagation, aiming to optimize the network's performance against a given dataset. These can be used in the present system with non-linear regression models to create a better analysis of the observed data and expected data.

[0081] In one example, predictive model 220 may apply an algorithm based on the following equation:y=β0+β1⁢x1+…+βr⁢xr+εThis may be the basis of a model that is built using regression, multivariate regression, neural networks, and / or machine learning, where the values of x are shown to have a linear relationship. βr are the regression coefficients and ε is the random error. By implementing a regression model using these relationships, the predictive model 220 can quickly model the expected deposition level within a pipeline. It is also possible to provide different weights to the model of legacy data, to impact the error and residuals, thereby targeting a minimization of the coefficient of determination, e.g., R2.The predictive model 220 can also undertake deposition analysis. Deposition analysis may include calculating a location and amount of deposition, for example. Acoustical and pressure waves generated and recorded enable monitoring of acoustical or pressure variations in a pipeline or wellbore. Generally, the data collected from the sensor 250 will be processed via predictive model 220 which can identify the location and size of the deposit.

[0083] The signal generated and received by sensor 250 may be created by any suitable signal generator configured to be operable to generate a pressure wave or an acoustic wave through a pipeline monitored by sensor 250. The signal generator may include a diaphragm, a fast-closing valve capable of generating a detectable pressure signal, injecting or removing mass from the pipeline, linear-actuator, electroacoustic transducers, or any combinations thereof. The signal generator may produce a recognized acoustical or pressure signal generated within a defined timeframe such that a distortion in the acoustical or pressure signal may be detected by sensor 250. Sensor 250 may include any suitable sensor operable to detect the generated signal within a pipeline. Sensor 250 may include a transducer configured to detect the generated signal and generate an output usable by the predictive model 220.

[0084] In some examples, depositions may be continuously monitored, and the analysis can be conducted continuously to account for deposits in real-time. The predictive model 220 can operate on a data set that identifies certain inputs, e.g., length of the flow line, diameter of the pipe, regression coefficients, and known random error, as well as any other inputs available from sensor 250. For example, the magnitude of the pressure pulse generated can be measured up-stream by using a sensor 250 (e.g., pressure transducer). In flow systems where the up-stream and down-stream pipes (wellbore, flowline, pipeline) are sufficiently long, the pressure increase immediately up-stream of the signal generator will be the same as given by the water-hammer equation.

[0085] The non-intrusive deposition measurement system 200 also includes an interface module 230. The interface module translates the data output from the predictive model 220 so that the device 260 is capable of receiving and rendering an output consistent with the predictive model output. The interface module 230 can be a hardware, software, or a combination of hardware and software. For example, it can be an API, an SDK, or any suitable hardware connection to allow the predictive model 220 to communicate with the device 260. Device 260 can be any output device available at the well site. For example, monitors, projectors, or any suitable audio / video device or software capable of providing appropriate outputs from the predictive model 220 to the user.

[0086] The non-intrusive deposition measurement system 200, in this example, can take place on an Internet of Things (“IoT”) edge device 270. This allows for distributed and scalable architecture to be used at a drill or pump site, for example, without needing to access or rely on the centralized cloud-based resources available. By using the IoT edge device 270 to implement the system 200, the system is able to provide on-site feedback using the sensor 250 data that is processed via the predictive model 220. As discussed above, the typical computing software for an edge device is a PLC that provides limited compute capacity but is capable of running the regression analysis of the predictive model 220. It is also capable of operating the remaining functions of the system 200, as described above. While a PLC is the primary edge device, the current disclosure is not limited to a PLC. The IoT edge device 270 can be any computing device capable of running the predictive model 220 and the other functions of the system 200, e.g., microcontrollers and microprocessors, software-based control systems (SCADA, etc.), or custom computing devices capable of operating on-site while running the predictive model and outputting results for the end user.

[0087] The non-intrusive deposition measurement system 200, can generate and output results based on inputting the data from the sensor 250 into the predictive model 220. The output, in one example, can resemble the output shown in FIG. 3. FIG. 3 shows an approximation of the output from a predictive model. As can be seen with reference to the figure, the left or “y” axis is labeled “diameter” and the bottom or “x” axis is labeled distance. This is an exemplary representation of the diameter of a pipe over a set distance. The measurements are taken downstream of the pressure pulse, where the pressure in the pipe is altered based on the deposits 320. deposits 320 are represented by the area under the curve 330, which are based on the previous off-site calculations based on legacy data, as discussed above. The predictive model 220 can provide an output that shows a change in the depositions, as represented by the modeled line 335. The predictive model 220 provides the output that is a regression analysis of the change in data measured by the sensor 250, and it is compared to the known state of the pipe, e.g., curve 330, modeled off of the legacy data. Based on the difference between curve 330 and modeled line 335, reflects the approximate change in deposition level within the pipe 310. As shown in FIG. 3, the change in deposition level is fairly modest and would most likely not necessitate further action by a user. However, if the modeled line 335 had a dramatic change that resulted in a large area present between curve 330 and modeled line 335, the end user may decide to undertake further action, and have the data from sensor 250 sent off-site for further analysis with the full computing power of the remote systems that can accurately analyze the data using the fluid flow and physics equations identified above.

[0088] Referring to FIG. 3, the fluidic channel 135 may include pipe 310, deposits 320 in the pipe 310 may form. The deposits 320 can be any material disposed in the pipe 310 of any amount and in any shape and form to at least partially impede flow of the fluid. For example, in some areas, the deposits 320 may completely block the interior of the pipe 310. Additionally, the deposits 320 may be to such an extent as to cause structural damage such as cracks in the top wall 340 and bottom wall 350 of the pipe 310. Deposits can be, for example, wax deposits, clay deposits, or any other possible deposits that can adhere to the top wall 340 and bottom wall 350 of the pipe 310 such that the fluid flow is at least partly impeded. For example, the deposits can include wax, precipitant such as asphaltenes, and / or scale.

[0089] In some areas, the pipe 310 may not have any deposits 320. For example, the cross-sectional shape of the pipe 310 can be substantially circular or any other desired shape as discussed with respect to the fluidic channel 135, above. In yet other areas, the pipe 310 may have deposits 320. The change in shape of the pipe 310 by the deposits 320 can cause the cross-sectional shape of the pipe 310 to be substantially ovoid, rectangular, diamond, triangular, irregular, or any other possible shape other than the original shape of the pipe 310. As illustrated in FIG. 3, the illustrated portion of the pipe 310 has one portion with deposits 320. In other examples, the fluidic channel 135 can include the pipe 310 which can be more than one portion with deposits 320. In yet other examples, the pipe 310 may not have any portions with deposits 320.

[0090] As the fluid flows through the pipe 310, from a portion without deposits 320 through a portion with deposits 320, the fluid may experience turbulent flow. In at least one example, the fluid may be prevented from flowing across the portion of the pipe 310 with deposits 320. The predictive model 220 is able to identify these deposits 320 based on the data collected by sensor 150 and / or 250.

[0091] The predictive model 220, can predict deposit 320 is present either on the top wall 340 of the pipe 310, the bottom wall 350 of the pipe 310, or both. The example FIG. 3 shows a deposit 320 that is at the bottom wall 350 of the pipe 310, but the model can also detect and include obstructions from the top wall 340 of the pipe 310. The predictive model 220 can incorporate the base case, a clean pipe with no deposits, the fluid flow calculations based on legacy data, and the regression model based on the difference between the models and the currently acquired data from sensor 250. The regression analysis predicts the difference between the models based on legacy data and current data, and outputs an approximation of the current state of the pipe which is represented in 300.

[0092] FIG. 4 illustrates an example method 400 for modeling the deposition changes within the flowline of a pipe. Although the example method 400 depicts a particular sequence of operations, the sequence may be altered without departing from the scope of the present disclosure. For example, some of the operations depicted may be performed in parallel or in a different sequence that does not materially affect the function of the method 400. In other examples, different components of an example device or system that implements the method 400 may perform functions at substantially the same time or in a specific sequence.

[0093] According to some embodiments, the method includes building a predictive model of an interior of a pipe based on legacy data observations at step 410. For example, the data from sensor 250 can be collected and sent off-site where the data can be assessed via the fluid flow equations. Off-site assessment can form the basis of the current state of the pipe that the predictive model 220 uses to determine if there are changes to the depositions in a pipe. The predictive model 220 is built using the calculation service 210, the previous assessments of fluid flow through a pipe based on legacy data, and the regression analysis applied to the data collected by the sensor 250. Using these inputs, the predictive model 220 can assess the data from the sensor 250 and provide an analysis on changes to the deposition level in a pipe.

[0094] According to some embodiments, the method includes receiving flowline data from a sensor indicating a flow profile within the pipe at step 420. For example, after a change in pressure is introduced to a pipe, the sensor 250 can detect how the pressure waves travel through the pipe and collect that data. The data from the sensor 250 can then be transmitted to the analog-to-digital converter 240, which translates the analog data into a digital signal. The digital signal from the analog-to-digital converter 240 can then be transmitted to the predictive model 220, where the predictive model 220 can assess the data from the sensor 250.

[0095] According to some embodiments, the method includes analyzing the flowline data using the predictive model at step 430. For example, after the data from the sensor 250 is received in step 420, the predictive model is able to assess the data using a regression analysis between what is expected based on the legacy data observations and the currently received data from sensor 250. This regression analysis can be linear or non-linear, and applies the equations discussed above with respect to predictive model 220.

[0096] According to some embodiments, the method includes outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data at step 440. For example, after analyzing the flowline data in step 440, the predictive model 220 will output the data reflecting the regression analysis undertaken by the model. This data will, in some examples, include the change between the data received from sensor 250 and the previous baseline of the pipe depositions based on legacy data. These differences are then able to be, for example, in a graph or similar representation to facilitate review by the end user.

[0097] According to some embodiments, the method includes rendering a representation of the data representing the change in the flow profile at step 450. For example, system 200, after the data is output from the predictive model 220, can transmit the data to an interface module that translates the data for presentation on device 260. In one example, the data can be rendered as shown in FIG. 3, with the expected curve 330, based on legacy data, and the modeled line 335 based on the regression analysis undertaken by the predictive model 220 based on the data collected by sensor 250.

[0098] FIG. 5 shows an example of computing system 500, which can be for example any computing device making up the IoT edge device 270, or any component thereof in which the components of the system are in communication with each other using connection 505. Connection 505 can be a physical connection via a bus, or a direct connection into processor 510, such as in a chipset architecture. Connection 505 can also be a virtual connection, networked connection, or logical connection.

[0099] In some embodiments, computing system 500 is a distributed system in which the functions described in this disclosure can be distributed within a datacenter, multiple data centers, a peer network, etc. In some embodiments, one or more of the described system components represents many such components each performing some or all of the function for which the component is described. In some embodiments, the components can be physical or virtual devices.

[0100] Example system 500 includes at least one processing unit (CPU or processor) 510 and connection 505 that couples various system components including system memory 515, such as read-only memory (ROM) 520 and random access memory (RAM) 525 to processor 510. Computing system 500 can include a cache of high-speed memory 512 connected directly with, in close proximity to, or integrated as part of processor 510.

[0101] Processor 510 can include any general purpose processor and a hardware service or software service, such as services 532, 534, and 536 stored in storage device 530, configured to control processor 510 as well as a special-purpose processor where software instructions are incorporated into the actual processor design. Processor 510 may essentially be a completely self-contained computing system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

[0102] To enable user interaction, computing system 500 includes an input device 545, which can represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech, etc. Computing system 500 can also include output device 535, which can be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems can enable a user to provide multiple types of input / output to communicate with computing system 500. Computing system 500 can include communications interface 540, which can generally govern and manage the user input and system output. There is no restriction on operating on any particular hardware arrangement, and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

[0103] Storage device 530 can be a non-volatile memory device and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, cartridges, random access memories (RAMs), read-only memory (ROM), and / or some combination of these devices.

[0104] The storage device 530 can include software services, servers, services, etc., that when the code that defines such software is executed by the processor 510, it causes the system to perform a function. In some embodiments, a hardware service that performs a particular function can include the software component stored in a computer-readable medium in connection with the necessary hardware components, such as processor 510, connection 505, output device 535, etc., to carry out the function.

[0105] For clarity of explanation, in some instances, the present technology may be presented as including individual functional blocks including functional blocks comprising devices, device components, steps or routines in a method embodied in software, or combinations of hardware and software.

[0106] Any of the steps, operations, functions, or processes described herein may be performed or implemented by a combination of hardware and software services or services, alone or in combination with other devices. In some embodiments, a service can be software that resides in memory of a client device and / or one or more servers of a content management system and perform one or more functions when a processor executes the software associated with the service. In some embodiments, a service is a program or a collection of programs that carry out a specific function. In some embodiments, a service can be considered a server. The memory can be a non-transitory computer-readable medium.

[0107] In some embodiments, the computer-readable storage devices, mediums, and memories can include a cable or wireless signal containing a bit stream and the like. However, when mentioned, non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals per se.

[0108] Methods according to the above-described examples can be implemented using computer-executable instructions that are stored or otherwise available from computer-readable media. Such instructions can comprise, for example, instructions and data which cause or otherwise configure a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Portions of computer resources used can be accessible over a network. The executable computer instructions may be, for example, binaries, intermediate format instructions such as assembly language, firmware, or source code. Examples of computer-readable media that may be used to store instructions, information used, and / or information created during methods according to described examples include magnetic or optical disks, solid-state memory devices, flash memory, USB devices provided with non-volatile memory, networked storage devices, and so on.

[0109] Devices implementing methods according to these disclosures can comprise hardware, firmware and / or software, and can take any of a variety of form factors. Typical examples of such form factors include servers, laptops, smartphones, small form factor personal computers, personal digital assistants, and so on. The functionality described herein also can be embodied in peripherals or add-in cards. Such functionality can also be implemented on a circuit board among different chips or different processes executing in a single device, by way of further example.

[0110] The instructions, media for conveying such instructions, computing resources for executing them, and other structures for supporting such computing resources are means for providing the functions described in these disclosures.

[0111] One of ordinary skill will appreciate that the less than (“<”) and greater than (“>”) symbols or terminology used herein may be replaced with less than or equal to (“≤”) and greater than or equal to (“≥”) symbols, respectively, without departing from the scope of this description.

[0112] Where components are described as being “configured to” perform certain operations, such configuration may be accomplished, for example, by designing electronic circuits or other hardware to perform the operation, by programming programmable electronic circuits (e.g., microprocessors, or other suitable electronic circuits) to perform the operation, or any combination thereof.

[0113] The phrase “coupled to” refers to any component that is physically connected to another component either directly or indirectly, and / or any component that is in communication with another component (e.g., connected to the other component over a wired or wireless connection, and / or other suitable communication interface) either directly or indirectly.

[0114] Claim language or other language reciting “at least one of” a set and / or “one or more” of a set indicates that one member of the set or multiple members of the set (in any combination) satisfy the claim. For example, claim language reciting “at least one of A and B” or “at least one of A or B” means A, B, or A and B. In another example, claim language reciting “at least one of A, B, and C” or “at least one of A, B, or C” means A, B, C, or A and B, or A and C, or B and C, or A and B and C. The language “at least one of” a set and / or “one or more” of a set does not limit the set to the items listed in the set. For example, claim language reciting “at least one of A and B” or “at least one of A or B” may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0115] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the aspects disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0116] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices such as general purposes computers, wireless communication device handsets, or integrated circuit devices having multiple uses including application in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized at least in part by a computer-readable data storage medium comprising program code including instructions that, when executed, performs one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may comprise memory or data storage media, such as RAM such as synchronous dynamic random access memory (SDRAM), ROM, non-volatile random access memory (NVRAM), EEPROM, flash memory, magnetic or optical data storage media, and the like. The techniques additionally, or alternatively, may be realized at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that may be accessed, read, and / or executed by a computer, such as propagated signals or waves.

[0117] The program code may be executed by a processor, which may include one or more processors, such as one or more DSPs, general purpose microprocessors, an application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Such a processor may be configured to perform any of the techniques described in this disclosure. A general purpose processor may be a microprocessor; but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Accordingly, the term “processor,” as used herein may refer to any of the foregoing structure, any combination of the foregoing structure, or any other structure or apparatus suitable for implementation of the techniques described herein.

[0118] Illustrative aspects of the disclosure include:

[0119] Aspect 1. A method comprising: building a predictive model of an interior of a flowline based on legacy data observations; receiving flowline data from a sensor indicating a flow profile within the pipe; analyzing the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and rendering a representation of the data representing the change in the flow profile.

[0120] Aspect 2. The method of Aspect 1, wherein the flowline data is collected using a pressure transducer.

[0121] Aspect 3. The method of any of Aspects 1 to 2, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0122] Aspect 4. The method of any of Aspects 1 to 3, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0123] Aspect 5. The method of any of Aspects 1 to 4, further comprising: collecting at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0124] Aspect 6. The method of any of Aspects 1 to 5, further comprising: initiating a pressure pulse within the flowline; and measuring the pressure pulse with the pressure sensor.

[0125] Aspect 7. The method of any of Aspects 1 to 6, wherein the pressure pulse is created through injecting mass, removing mass, or actuating a valve.

[0126] Aspect 8. The method of any of Aspects 1 to 7, wherein the predictive model includes a linear or non-linear regression model.

[0127] Aspect 9. The method of any of Aspects 1 to 8, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . βrxr+ε. β0, β1, . . . . βr, where X=x1 . . . , xr have a linear relationship, β are regression coefficients, and ε is the random error.

[0128] Aspect 10. The method of any of Aspects 1 to 9 wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

[0129] Aspect 11. A system includes a storage (implemented in circuitry) configured to store instructions and a processor. The processor configured to execute the instructions and cause the processor to: build a predictive model of an interior of a pipe based on legacy data observations; receive flowline data from a sensor indicating a flow profile within the pipe; analyze the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and render a representation of the data representing the change in the flow profile.

[0130] Aspect 12. The system of Aspect 11, wherein the flowline data is collected using a pressure transducer.

[0131] Aspect 13. The system of any of Aspects 11 to 12, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0132] Aspect 14. The system of any of Aspects 11 to 13, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0133] Aspect 15. The system of any of Aspects 11 to 14, wherein the processor is configured to execute the instructions and cause the processor to: collect at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0134] Aspect 16. The system of any of Aspects 11 to 15, wherein the processor is configured to execute the instructions and cause the processor to: initiate a pressure pulse within the flowline; and measure the pressure pulse with the pressure sensor.

[0135] Aspect 17. The system of any of Aspects 11 to 16, wherein the pressure pulse is created through injecting mass, remove mass, or actuate a valve.

[0136] Aspect 18. The system of any of Aspects 11 to 17, wherein the predictive model includes a linear or non-linear regression model.

[0137] Aspect 19. The system of any of Aspects 11 to 18, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . βrxr+ε . . . β0, β1, . . . . βr, where x=x1 . . . , xr have a linear relationship, B are regression coefficients, and ε is the random error.

[0138] Aspect 20. The system of any of Aspects 11 to 19, wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

[0139] Aspect 21. A computer readable medium comprising instructions using a computer system. The computer includes a memory (e.g., implemented in circuitry) and a processor (or multiple processors) coupled to the memory. The processor (or processors) is configured to execute the computer readable medium and cause the processor to: build a predictive model of an interior of a pipe based on legacy data observations; receive flowline data from a sensor indicating a flow profile within the pipe; analyze the flowline data using the predictive model; outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; and render a representation of the data representing the change in the flow profile.

[0140] Aspect 22. The computer readable medium of Aspect 21, wherein the flowline data is collected using a pressure transducer.

[0141] Aspect 23. The computer readable medium of any of Aspects 21 to 22, wherein the legacy data observations include data previously captured using a single pressure transducer, flowline geometry, or fluid properties and stored in a database as a captured data set.

[0142] Aspect 24. The computer readable medium of any of Aspects 21 to 23, wherein the predictive model is segmented based on the single pressure transducer, flowline geometry, and fluid properties.

[0143] Aspect 25. The computer readable medium of any of Aspects 21 to 24, wherein the processor is configured to execute the computer readable medium and cause the processor to: collect at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

[0144] Aspect 26. The computer readable medium of any of Aspects 21 to 25, wherein the processor is configured to execute the computer readable medium and cause the processor to: initiate a pressure pulse within the flowline; and measure the pressure pulse with the pressure sensor.

[0145] Aspect 27. The computer readable medium of any of Aspects 21 to 26, wherein the pressure pulse is created through injecting mass, remove mass, or actuate a valve.

[0146] Aspect 28. The computer readable medium of any of Aspects 21 to 27, wherein the predictive model includes a linear or non-linear regression model.

[0147] Aspect 29. The computer readable medium of any of Aspects 21 to 28, wherein the predictive model is based at least on the following equations: γ=β0+β1x1 . . . . βrxr+ε. β0, β1, . . . . βr, where x=x1 . . . , xr have a linear relationship, β are regression coefficients, and ε is the random error.

[0148] Aspect 30. The computer readable medium of any of Aspects 21 to 29, wherein the predictive model is run on a programmable logical controller in communication with the pressure sensor.

Examples

Embodiment Construction

[0013]Certain aspects of this disclosure are provided below. Some of these aspects may be applied independently and some of them may be applied in combination as would be apparent to those of skill in the art. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of aspects of the application. However, it will be apparent that various aspects may be practiced without these specific details. The figures and descriptions are not intended to be restrictive.

[0014]The ensuing description provides example aspects only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the example aspects will provide those skilled in the art with an enabling description for implementing an example aspect. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope ...

Claims

1. A method comprising:building a predictive model of an interior of a pipe based on legacy data observations;receiving flowline data from a sensor indicating a flow profile within the pipe;analyzing the flowline data using the predictive model;outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; andrendering a representation of the data representing the change in the flow profile.

2. The method of claim 1, wherein the flowline data is collected using a pressure transducer.

3. The method of claim 1, wherein the legacy data observations include data previously captured using at least one pressure transducer, a flowline geometry, or at least one fluid property and storing the legacy data observations in a database as a captured data set.

4. The method of claim 3, wherein the predictive model is segmented based on the at least one pressure transducer, the flowline geometry, or the at least one fluid property.

5. The method of claim 1, further comprising:collecting at least one of an initial pressure, an MFR, and incremental MFR, a start time, an end time, a Halland's factor, a friction factor, a pipe diameter, an incremental distance, an incremental diameter, an incremental acoustic velocity, an incremental density, an incremental viscosity, an incremental simulated pressure, an incremental observed pressure, and an incremental calculated deposition.

6. The method of claim 1, further comprising:initiating a pressure pulse within a flowline of the pipe; andmeasuring the pressure pulse with the sensor.

7. The method of claim 6, wherein the pressure pulse is created through injecting mass, removing mass, or actuating a valve.

8. The method of claim 1, wherein the predictive model includes a linear or non-linear regression model.

9. The method of claim 8, wherein the predictive model is based at least on the following equations:y=β0+β1⁢x1⁢ …⁢ βr⁢xr+ε.β0,β1,…⁢ βrwhere x=x1, . . . , xr have a linear relationship, ε are regression coefficients, and & is random error.

10. The method of claim 1 wherein the predictive model is run on a programmable logical controller in communication with the sensor.

11. A system comprising:a storage configured to store instructions;a processor configured to execute the instructions and cause the processor to:build a predictive model of an interior of a pipe based on legacy data observations;receive flowline data from a sensor indicating a flow profile within the pipe;analyze the flowline data using the predictive model;outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; andrender a representation of the data representing the change in the flow profile.

12. The system of claim 11, wherein the flowline data is collected using a pressure transducer.

13. The system of claim 11, wherein the legacy data observations include data previously captured using at least one pressure transducer, a flowline geometry, or at least one fluid property and storing the legacy data observations in a database as a captured data set.

14. The system of claim 11, wherein the processor is configured to execute the instructions and cause the processor to:initiate a pressure pulse within a flowline; andmeasure the pressure pulse with the sensor.

15. The system of claim 11, wherein the predictive model includes a linear or non-linear regression model.

16. The system of claim 11, wherein the predictive model is run on a programmable logical controller in communication with the sensor.

17. A non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:build a predictive model of an interior of a pipe based on legacy data observations;receive flowline data from a sensor indicating a flow profile within the pipe;analyze the flowline data using the predictive model;outputting, from the predictive model, data representing a change in the flow profile, wherein the change in the flow profile indicates a difference between the legacy data observations and the flowline data; andrender a representation of the data representing the change in the flow profile.

18. The computer readable medium of claim 17, the flowline data is collected using a pressure transducer.

19. The computer readable medium of claim 17, wherein the computer readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:initiate a pressure pulse within a flowline; andmeasure the pressure pulse with the sensor.

20. The computer readable medium of claim 17, the predictive model includes a linear or non-linear regression model.

Images