Method for automatically determining rock debris depth while drilling

Abstract

A method for depth determination of drilled cuttings is disclosed. Tracers are injected and transported downhole along the mud flow (204, 205) and adhere to cuttings. Cuttings impregnated with tracers are detected at the surface (108) based on molecular weight, emission wavelength or radio frequency features used to encode the tracers. When a specific batch of tracers is released into the mud, the identification code identifies the depth of the drill bit. In addition to mud properties, flow rate, drilled volume and rate of penetration, formation characteristics and well specifications, detection data is transmitted to and analyzed by a tracer analysis and control engine (202). The tracer analysis and control engine (202) controls an internet of things controller (203) that adjusts parameters of a tracer injection pump (206) to enable intelligent controlled release, thereby optimizing the depth characterization process.

Description

Background Technology

[0001] Drilling fluid (also known as "drilling mud" or simply "mud") is used to facilitate drilling wells in the earth, such as oil and gas wells. The main functions of drilling fluid include: providing hydrostatic pressure to prevent formation fluids from entering the wellbore; keeping the drill bit cool and clean during drilling; carrying drill cuttings; and suspending drill cuttings during drilling pauses and as drilling components are carried into and out of the wellbore. Drill cuttings, also known as "rock cuttings," are fragments of rock generated by the drill bit as it advances along the wellbore. Mud logging creates a logging log of the wellbore by examining the rock cuttings carried to the surface by circulating drilling mud.

[0002] Tracers are chemical or physical markers added to materials to allow for various forms of testing of the labeled materials. Tracer detectors can be used to detect them. Physical tracers can take many different forms, but are typically tiny in size, added to materials at low levels, and are easily detected. Tracers can be encoded based on specific characteristics (e.g., optical, chemical, electrical, or mechanical features) to act as virtual “fingerprints.” Examples of encoded tracers include metallic NanoTags, which are, for example, microscopic metallic tags between 0.3 mm and 1.0 mm. Each batch of NanoTags has a unique multi-digit alphanumeric identification code. For example, the identification code can be etched into an optically variable (holographic) substrate of the NanoTag. NanoTags can be suspended in a UV-sensitive transparent adhesive that is brushed or sprayed onto any item for authentication or other security purposes. Summary of the Invention

[0003] In general, in one aspect, the present invention relates to a method for determining cuttings depth during drilling operations in subsurface formations. The method includes: during a first time window of the drilling operation, releasing a first batch of tracer into drilling fluid using a tracer injection pump, wherein the first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings; detecting a first time-related signal from the first batch of tracer using a tracer detector at a surface location when the first batch of cuttings reaches the surface, wherein the first batch of tracer is delivered to the surface by the drilling fluid after impregnating the first batch of cuttings; and during a second time window of the drilling operation, releasing a second batch of tracer into the drilling fluid using the tracer injection pump, wherein the second batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings. When a second batch of cuttings is generated, the second batch of cuttings is impregnated; using the tracer detector at the surface location, a second time-correlation signal is detected from the second batch of tracer when the second batch of cuttings reaches the surface, wherein the second batch of tracer is delivered to the well by the drilling fluid after impregnation of the second batch of cuttings; using a tracer analysis and control engine, the overlap of the first time-correlation signal and the second time-correlation signal is analyzed for the injection parameters of the tracer injection pump during a first time period and a second time period to generate an injection distribution curve; and the injection parameters of the tracer injection pump are adjusted based on the injection distribution curve to improve the quality of cuttings depth determination, wherein mud logging is performed based on the improved quality of cuttings depth determination.

[0004] In one aspect, the present invention relates to a system for determining cuttings depth. The system includes a computer processor and a memory storing instructions. The instructions, when executed by the computer processor, include the following functions: During a first time window throughout the drilling operation, releasing a first batch of tracer into the drilling fluid using a tracer injection pump, wherein the first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings; using a tracer detector at the surface location to detect a first time-related signal from the first batch of tracer when the first batch of cuttings reaches the surface, wherein the first batch of tracer is delivered to the surface by the drilling fluid after impregnating the first batch of cuttings; and during a second time window throughout the drilling operation, releasing a second batch of tracer into the drilling fluid using the tracer injection pump, wherein the second batch of tracer is delivered downhole by the drilling fluid to the surface. The tracer is delivered downhole to impregnate the second batch of cuttings when the drill bit produces the second batch of cuttings; using the tracer detector at the surface location, a second time-correlation signal is detected from the second batch of tracer when the second batch of cuttings reaches the surface, wherein the second batch of tracer is delivered to the surface by the drilling fluid after impregnation of the second batch of cuttings; using a tracer analysis and control engine, the overlap of the first time-correlation signal and the second time-correlation signal is analyzed for the injection parameters of the tracer injection pump during a first time period and a second time period to generate an injection distribution curve; and the injection parameters of the tracer injection pump are adjusted based on the injection distribution curve to improve the quality of cuttings depth determination, wherein mud logging is performed based on the improved quality of cuttings depth determination.

[0005] In general, in one aspect, the present invention relates to a non-transitory computer-readable medium storing instructions executable by a computer processor for determining cuttings depth. The instructions, when executed, include the following functions: during a first time window of the drilling operation, releasing a first batch of tracer into the drilling fluid using a tracer injection pump, wherein the first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings; detecting a first time-related signal from the first batch of tracer using a tracer detector at the surface location when the first batch of cuttings reaches the surface, wherein the first batch of tracer is delivered to the surface by the drilling fluid after impregnating the first batch of cuttings; and during a second time window of the drilling operation, releasing a second batch of tracer into the drilling fluid using the tracer injection pump, wherein the second batch of tracer is delivered downhole by the drilling fluid. The drilling fluid is used to impregnate the second batch of cuttings when the drill bit produces the second batch of cuttings; using the tracer detector at the surface location, a second time-correlation signal is detected from the second batch of tracer when the second batch of cuttings reaches the surface, wherein the second batch of tracer is delivered to the well by the drilling fluid after impregnation of the second batch of cuttings; using a tracer analysis and control engine, the overlap of the first time-correlation signal and the second time-correlation signal is analyzed for the injection parameters of the tracer injection pump during a first time period and a second time period to generate an injection distribution curve; and the injection parameters of the tracer injection pump are adjusted based on the injection distribution curve to improve the quality of cuttings depth determination, wherein mud logging is performed based on the improved quality of cuttings depth determination.

[0006] Other aspects and advantages will become apparent from the following description and the appended claims. Attached Figure Description

[0007] Specific embodiments of the disclosed technology will now be described in detail with reference to the accompanying drawings. For consistency, similar elements in the drawings are indicated by similar reference numerals.

[0008] Figure 1 and Figure 2 A system according to one or more embodiments is shown.

[0009] Figure 3 A flowchart according to one or more embodiments is shown.

[0010] Figure 4A and Figure 4B Examples according to one or more embodiments are shown.

[0011] Figure 5A and Figure 5B A computing system according to one or more embodiments is shown. Detailed Implementation

[0012] Specific embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. For consistency, similar elements in the drawings are indicated by similar reference numerals.

[0013] Numerous specific details are set forth in the following detailed description of embodiments of the present disclosure in order to provide a more thorough understanding of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description.

[0014] Throughout the application, ordinal numbers (e.g., first, second, third, etc.) may be used as adjectives for elements (i.e., any noun in this application). Unless explicitly disclosed, such as by using the terms “before,” “after,” “single,” and other such terms, the use of ordinal numbers does not imply or create any particular order of elements, nor does it limit any element to a single element. Rather, the use of ordinal numbers is intended to distinguish between elements. As an example, a first element is distinct from a second element, and a first element may contain more than one element and be placed after (or before) the second element in the order of elements.

[0015] Embodiments of the present invention provide a method, system, and non-transitory computer-readable medium for determining the depth of drilling cuttings based on an impregnated tracer. In one or more embodiments of the invention, the tracer comprises polymer-based nanoparticles encoded based on barcodes or radio frequency characteristics. A tracer injection pump controls the release of the tracer into the drilling fluid to ensure that drilling cuttings are distinguishable at different stages of the drilling operation and generated at different depths. The tracer is injected and transported downhole along the mud flow and adheres to the cuttings when they are generated at the drill bit. Subsequently, the tracer-impregnated cuttings are detected at the surface to generate detection data. The detection data includes an identification code for the tracer, which is detected based on the molecular weight, emission wavelength, or radio frequency characteristics used to encode the tracer. When a particular batch of tracer is released into the mud, the identification code identifies the depth at the drill bit. In addition to mud properties, flow rate, drilling volume and penetration rate, formation characteristics, and well specifications (e.g., depth, diameter, geometry), the detection data is also transmitted to and analyzed by the tracer analysis and control engine. The tracer analysis and control engine controls an Internet of Things (IoT) controller, which adjusts the parameters of the tracer injection pump to achieve intelligent, controlled release, thereby optimizing the depth characterization process.

[0016] Figure 1 A schematic diagram according to one or more embodiments is shown. Figure 1As shown, well environment 100 includes a hydrocarbon reservoir (“reservoir”) 102 located in a subsurface hydrocarbon-bearing formation (“formation”) 104 and a well system 106. The hydrocarbon-bearing formation 104 may include porous or fractured rock formations located subsurface, below the Earth’s surface (“surface”) 108. In the case where well system 106 is a hydrocarbon well, reservoir 102 may include a portion of the hydrocarbon-bearing formation 104. The hydrocarbon-bearing formation 104 and reservoir 102 may include different rock formations with different characteristics (e.g., varying degrees of permeability, porosity, capillary pressure, and resistivity). When well system 106 is operated as a production well, well system 106 facilitates the extraction of hydrocarbons (or “products”) from reservoir 102.

[0017] In some embodiments of the invention, the well system 106 includes a drilling rig 101, a wellbore 120, a subsurface well system 122, a surface well system 124, and a well control system (“control system”) 126. The well control system 126 can control various operations of the well system 106, such as well production operations, drilling operations, well completion operations, well maintenance operations, and reservoir monitoring, assessment, and development operations. In some embodiments, the well control system 126 includes components related to the following... Figure 5A and Figure 5B And computer systems that are the same as or similar to the computer system 500 described in the accompanying instructions. For example, the following Figure 2 The tracer detector 201, IoT controller 203 and tracer injection pump 206 shown may be part of the well control system 126 and may be implemented as a combination of hardware and software components of the computer system 500.

[0018] Drilling rig 101 is a machine used to drill a wellbore to form a wellbore 120. The main components of drilling rig 101 include drilling fluid tank, drilling fluid pump (e.g., drilling rig mixing pump), derrick or turret, winch, rotary table or top drive, drill string, power generation equipment, and auxiliary equipment.

[0019] Wellbore 120 includes a borehole (i.e., a wellbore) extending from surface 108 into a target area (e.g., reservoir 102) of hydrocarbon-bearing formation 104. The upper end of wellbore 120 terminating at or near surface 108 may be referred to as the “upstream” end of wellbore 120, while the lower end of wellbore terminating in hydrocarbon-bearing formation 104 may be referred to as the “downstream” end of wellbore 120. Wellbore 120 facilitates the circulation of drilling fluid during drilling operations, the flow of hydrocarbon products (“products”) 121 (e.g., oil and gas) from reservoir 102 to surface 108 during production operations, the injection of substances (e.g., water) into hydrocarbon-bearing formation 104 or reservoir 102 during injection operations, or communication of monitoring equipment (e.g., logging tools) that have descended into formation 104 or reservoir 102 during monitoring operations (e.g., during in-situ logging operations).

[0020] In some embodiments, during the operation of the well system 106, the well control system 126 collects and records well data 140 for the well system 106. During drilling operations of the well 106, the well data 140 may include mud characteristics, flow rate, drilling volume and rate of penetration, formation characteristics, etc. The well data 140 may also include the following: Figure 2 The sensor data of the tracer detector 201 shown is illustrated. In some embodiments, well data 140 is recorded in real time and is available for viewing or use within seconds, minutes, or hours after a condition is sensed (e.g., measurements are available within one hour of a sensed condition). In such embodiments, well data 140 may be referred to as “real-time” well data 140. Real-time well data 140 enables the operator of well 106 to assess the relative current state of well system 106 and make real-time decisions regarding the development of well system 106 and reservoir 102, such as on-demand adjustments to drilling fluid and regulation of production flow from the well.

[0021] In some embodiments, the well surface system 124 includes a wellhead 130. The wellhead 130 may include a rigid structure mounted at or near the "upstream" end of the wellbore 120, where the wellbore 120 terminates at or near the Earth's surface 108. The wellhead 130 may include structures for supporting (or "suspending") the casing and production tubing extending into the wellbore 120. Product 121 may flow through the wellhead 130 after exiting the wellbore 120 and the well subsurface system 122 (including, for example, the casing and production tubing). In some embodiments, the well surface system 124 includes flow control devices operable to control the inflow and outflow of material into and out of the wellbore 120. For example, the well surface system 124 may include one or more production valves 132 operable to control the flow of product 134. For example, production valve 132 can be fully opened to allow product 121 to flow out of wellbore 120 without restriction, production valve 132 can be partially opened to partially restrict (or “throttle”) the flow of product 121 out of wellbore 120, and production valve 132 can be completely closed to completely restrict (or “block”) the flow of product 121 out of wellbore 120 and through well surface system 124.

[0022] In some embodiments, the wellhead 130 includes a choke assembly. For example, the choke assembly may include hardware having the function of opening and closing fluid flow through a conduit in the well system 106. Similarly, the choke assembly may include a manifold that can reduce the pressure of fluid flowing through the wellhead. Thus, the choke assembly may include a set of high-pressure valves and at least two chokes. These chokes may be fixed or adjustable, or a combination of both. Redundancy can be provided so that if one choke has to stop working, flow can be guided by another choke. In some embodiments, the pressure valves and chokes are communicatively coupled to the well control system 126. Therefore, the well control system 126 can obtain wellhead data regarding the choke assembly and transmit one or more commands to components within the choke assembly to adjust one or more choke assembly parameters.

[0023] Continue to refer to Figure 1 In some embodiments, the well surface system 124 includes a surface sensing system 134. The surface sensing system 134 may include sensors for sensing characteristics of substances (including product 121) passing through or otherwise located within the well surface system 124. These characteristics may include, for example, the pressure, temperature, and flow rate of product 121 flowing through the wellhead 130 or other conduits of the well surface system 124 after exiting the wellbore 120. The surface sensing system 134 may also include sensors for sensing characteristics of the drilling rig 101, such as bit depth, wellbore depth, drilling fluid flow rate, hook load, rotational speed, etc. Furthermore, the following... Figure 2 The tracer detector 201 shown may be included as part of the surface sensing system 134.

[0024] In some embodiments, the well system 106 is provided with an analysis engine 160. For example, in the following... Figure 2 The tracer analysis and control engine 202 shown may be part of an analysis engine 160, which includes hardware and / or software with the capability to analyze drilling fluid and tracer-impregnated cuttings to determine the bit depth at which cuttings are generated. The bit depth at which cuttings are generated is referred to as the cuttings origin depth. Accurately determining the cuttings origin depth for mud logging can improve the quality of geosteering, well placement, and petrophysical analysis through real-time formation assessment. The analysis engine 160 may also include a reservoir simulator, which includes hardware and / or software with the capability to generate one or more reservoir models for hydrocarbon-bearing formations 104 and / or perform one or more reservoir simulations. Reservoir models and simulations can be advantageously generated / executed based on the improved well placement and petrophysical analysis described above. Therefore, reservoir development plans and / or production operations can be improved based on the results generated by the analysis engine 160.

[0025] Although the analytics engine 160 is shown at the well site, in some embodiments, the analytics engine 160 is located at a location far from the well site, such as in the cloud on the Internet. In some embodiments, the analytics engine 160 may include a computer system similar to the one described below. Figure 5A and Figure 5B And the computer system 500 described in the corresponding description.

[0026] Turning Figure 2 , Figure 2 An exemplary system according to one or more embodiments of the present invention is illustrated. In one or more embodiments, omissions, repetitions, and / or substitutions may be made. Figure 2 The embodiments of the present invention should not be considered as limited to one or more modules and / or elements shown. Figure 2 The specific arrangement of the modules and / or elements shown.

[0027] The lack of accurate determination of the source depth of cuttings limits the effectiveness of conventional mud logging due to depth uncertainties of several feet (ft), especially in deviated and horizontal wells where cuttings flow can be delayed by gravity debris accumulation, hydraulic issues, and wellbore cleaning problems. Accurate determination of the source depth of cuttings depends on wellbore mud hydraulics, wellbore cleaning, a precise understanding of the return-trip delay time in the annulus, caving, and the identification of cuttings that may delay their return to the surface. Even under normal flow conditions, if the upward journey of cuttings lasts longer than 30 minutes, the depth uncertainty can exceed 20 feet. Any inaccuracies in marking the collected cuttings further increase these errors.

[0028] Figure 2 A system 200 is shown for automatically and accurately determining the source depth of rock cuttings carried to the surface in drilling mud flows. In one or more embodiments of the invention, system 200 is as described above. Figure 1 Part of the well system 106 shown. Figure 2 As shown, system 200 includes a tracer detector 201, a tracer analysis and control engine 202, an IoT controller 203, and a tracer injection pump 206, which together detect, analyze, and control the tracer released into the mud flows 204, 205 of the wellbore 120. For example, the tracer detector 201, IoT controller 203, and tracer injection pump 206 can be the aforementioned... Figure 1 This is part of the well control system 126 shown. The tracer analysis and control engine 202 may be the one described above. Figure 1 This is a portion of the analysis engine 160 shown, as based on Figure 250. Figure 2As shown, arrows indicate data communication between the various components of system 200, and shaded curves represent mud flow. Specifically, mud flow 204 proceeds downhole, while mud flow 205 returns to the surface. The lighter shaded portion 204a of mud flow 204 represents tracer released into the mud flow proceeding downhole. The lighter shaded portion 205a of mud flow 205 represents tracer impregnated onto cuttings carried by the returning mud flow. For example, the lighter shaded portion 205a corresponds to the first batch of tracer released into the mud flow, while the lighter shaded portion 204a of mud flow 204 corresponds to the second batch of tracer released after the first batch. In this disclosure, the lighter shaded portion 205a is referred to as tracer 205a or the first batch of tracer. Similarly, the lighter shaded portion 204a is referred to as tracer 204a or the second batch of tracer.

[0029] In one or more embodiments of the invention, tracer detector 201 detects and analyzes tracers impregnated on rock cuttings as the rock is carried to the surface in a mud flow. The detection data is then transmitted to tracer analysis and control engine 202, in addition to mud characteristics, flow rate, drilling volume and rate of penetration, formation properties, and well specifications (depth, diameter, geometry, etc.).

[0030] In one or more embodiments of the present invention, the tracer analysis and control engine 202 analyzes detection data from the tracer detector 201 and other information to generate an injection distribution curve. The injection distribution curve is sent to the IoT controller 203 and used by the IoT controller 203 to adjust the injection parameters of the tracer injection pump 206 to achieve intelligent and controlled release of the tracer. In one or more embodiments, the tracer analysis and control engine 202 uses artificial intelligence and machine learning algorithms to generate the injection distribution curve.

[0031] In one or more embodiments of the invention, the IoT controller 203 controls the tracer injection pump 206 to release tracer into the mud stream via a release controller 206a, thereby ensuring that different batches of tracer-impregnated cuttings generated during various stages of the drilling operation are distinguishable. As described above, the IoT controller 203 controls the tracer injection pump 206 by adjusting injection parameters based on the injection distribution curve received from the tracer analysis and control engine 202.

[0032] In one or more embodiments of the invention, the tracer injection pump 206 includes multiple injector valves connected to multiple different container chambers (for containing tracer), the multiple different container chambers having different sizes selectable based on injection distribution profiles. An IoT controller 203 engages with the tracer injection pump 206 to control the degree of closure and opening of the injector valves and the pressure at the injector valves for each container chamber. The tracer injection pump 206 is a metering pump that allows precise amounts of tracer to be injected into the drilling fluid. While the tracer injection pump 206 automatically adjusts the injector valves based on injection parameters from the IoT controller 203, the tracer injection pump 206 also allows for manual adjustment of the injector valves.

[0033] In one or more embodiments of the invention, the tracer comprises polymer nanoparticles dispersed in an aqueous fluid, which are added directly to the drilling fluid in small doses. The polymer nanoparticles are a type of tracer known as “NanoTag.” The term “NanoTag” can also refer to other types of tracers, such as metallic micro-dots with etched identification codes. Due to the small size and chemical properties of the NanoTag or polymer nanoparticles, the tracer permanently adheres to the cuttings when they are cut off at the drill bit face. When the cuttings return to the surface in the mud flow, the tracer impregnates the cuttings by remaining on them and embedding within the pores of the cuttings. Based on the coded identification code of the NanoTag or polymer nanoparticles, the depth determination of the tracer-impregnated cuttings has a depth uncertainty within 1 foot and is unaffected even if different batches of cuttings move or mix during storage and transportation prior to analysis. Therefore, System 200 improves the quality of rock physical analysis of cuttings based on improved mud logging depth accuracy.

[0034] Turning Figure 3 , Figure 3 A method flowchart according to one or more embodiments is shown. Figure 3 One or more boxes in the middle can be used as follows Figure 1 and Figure 2 The described one or more components are used to perform this. Although Figure 3 The boxes in the document are presented and described in sequence, but those skilled in the art will understand that some or all of these boxes may be executed in a different order, may be combined or omitted, and may be executed in parallel and / or iteratively. Furthermore, these boxes may be executed actively or passively.

[0035] First, within block 300, during the entire first time window of the drilling operation, the first batch of tracer is released into the drilling fluid using a tracer injection pump. The first batch of tracer is injected according to a first injection distribution profile. Generally, the injection distribution profile specifies various injection parameters, such as the amount of tracer, the injection pressure of the tracer injection pump, the degree of closure and opening of the individual injector valves, the injection time window, the time interval from the injection of the previous batch of tracer (i.e., the injection lag), etc. The first batch of tracer is delivered downhole via the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings. In one or more embodiments of the invention, the first batch of tracer comprises polymer nanoparticles, wherein each nanoparticle is encoded with a unique identification code for the first batch of tracer.

[0036] In block 301, a tracer detector at a surface location is used to detect a first-time correlation signal from the first batch of tracers when the first batch of cuttings reaches the surface. The tracer detector detects the first-time correlation signal from the first batch of tracers based on the optical, chemical, electrical, or mechanical characteristics of the nanoparticles in the tracer. The first batch of tracers is delivered to the surface by drilling fluid after impregnating the first batch of cuttings downhole. In one or more embodiments, the first-time correlation signal is identified as originating from the first batch of tracers based on the detection of a unique identification code. The amplitude of the first-time correlation signal is proportional to the amount or concentration of tracer (e.g., polymer nanoparticles) detected in the mud flow that carries the first batch of impregnated cuttings to the surface.

[0037] In block 302, during the entire second time window following the first time window of the drilling operation, a second batch of tracer is released into the drilling fluid using a tracer injection pump. The second batch of tracer is injected according to a second injection distribution profile. The second batch of tracer is delivered downhole via the drilling fluid to impregnate a second batch of cuttings when the drill bit produces a second batch of cuttings. In one or more embodiments of the invention, the second batch of tracer comprises polymer nanoparticles, wherein each nanoparticle is encoded with a unique identification code for the second batch of tracer.

[0038] In block 303, a tracer detector at a surface location is used to detect a second time-correlation signal from the second batch of tracer when the second batch of cuttings arrives at the surface. The tracer detector detects the second time-correlation signal from the second batch of tracer based on the optical, chemical, electrical, or mechanical characteristics of the nanoparticles in the tracer. The second batch of tracer is delivered to the surface by drilling fluid after impregnating the second batch of cuttings downhole. In one or more embodiments, the second time-correlation signal is identified as originating from the second batch of tracer based on the detection of a unique identification code. The amplitude of the second time-correlation signal is proportional to the amount or concentration of tracer (e.g., polymer nanoparticles) detected in the mud flow that carries the second batch of impregnated cuttings to the surface.

[0039] In block 304, a tracer analysis and control engine is used to analyze the overlap of the first and second time-correlated signals to generate a third injection distribution curve. In one or more embodiments of the invention, this analysis includes one or more of the following operations: determining the corresponding signal peaks and half-widths of the first and second time-correlated signals; determining the time gap between the two signal peaks and the signal floor within that time gap; and determining other timing waveform statistics. Overlap is defined as a measure based on the corresponding signal peaks and half-widths, the time gap, the signal floor, and other timing waveform statistics. For example, overlap can be defined as the ratio of the sum of the half-widths to the time gap. Overlap can be further defined or modified by the ratio of one or two signal peak amplitudes to the signal floor. If each corresponding signal peak is present and has an amplitude exceeding a predetermined threshold for the signal floor (e.g., 30% of the signal peak amplitude), then the first and second time-correlated signals are determined to be distinguishable from each other, i.e., have minimal overlap. If each corresponding signal peak is not present individually, or if the overlap of the two time-correlated signals exceeds a predetermined threshold, then the first and second time-correlated signals are determined to be indistinguishable from each other.

[0040] In one or more embodiments, if it is determined that the first time-correlation signal and the second time-correlation signal are distinguishable from each other, the third injection distribution curve is substantially the same as the first or second injection distribution curve. In one or more embodiments, if it is determined that the first time-correlation signal and the second time-correlation signal are not sufficiently distinguishable from each other, the third injection distribution curve is adjusted from the first or second injection distribution curve. For example, the tracer dose, injection pressure, and / or injection lag of the third injection distribution curve may be increased from the tracer dose, injection pressure, and / or injection lag of the first and / or second injection distribution curves. In particular, the third injection distribution curve is adjusted such that a third batch of tracer injected according to the third injection distribution curve produces a third time-correlation signal that is at least distinguishable from the second time-correlation signal. In particular, the amplitude of the third time-correlation signal is proportional to the amount or concentration of tracer (e.g., polymer nanoparticles) detected in the mud flow carrying the third batch of impregnated rock cuttings to the ground.

[0041] In one or more embodiments, a machine learning model generated by a tracer analysis and control engine is used to generate a third injection distribution curve. The machine learning model is trained using a training dataset comprising a large number of time-correlated signals with corresponding injection distribution curves and associated well site parameters used in the drilling operation, such as mud properties, bit depth, rate of penetration (RLP), formation characteristics, etc. For example, the training dataset may include a first and a second injection distribution curve that produce first and second time-correlated signals that are distinguishable from each other and are labeled as appropriate injection distribution curves. In another example, the training dataset may include a first and a second injection distribution curve that produce first and second time-correlated signals that are not sufficiently distinguishable from each other and are labeled as inappropriate injection distribution curves. Therefore, the third injection distribution curve is generated using a trained machine learning model with well site parameters as input. In other words, the third injection distribution curve depends on mud properties, bit depth, RLP, formation characteristics, etc., at the time of injection of the third batch of tracer. Specifically, such dependence is captured in and modeled by the machine learning model. As a result, the third batch of tracer injected according to the third injection distribution curve produced a distinguishable third time-correlation signal under the well site conditions at the time of injection. (See below for reference.) Figure 4A and Figure 4B Describe an example of generating a machine learning training dataset.

[0042] In block 305, based on the third injection distribution curve, the injection parameters of the tracer injection pump are adjusted to improve the quality of cuttings depth determination for mud logging. In one or more embodiments, the third injection distribution curve is sent from the tracer analysis and control engine to the IoT controller. Therefore, the IoT controller adjusts the injection parameters of the tracer injection pump based on this injection distribution curve. In one or more embodiments, the tracer analysis and control engine resides on a cloud server, and the IoT controller is located near the tracer injection pump at the well site. Specifically, the tracer analysis and control engine communicates with the IoT controller via a network connection (e.g., the Internet) to send the injection distribution curve.

[0043] In box 306, mud logging is performed based on the quality of improved cuttings depth determination. For example, mud logging is performed using first, second, and third time-correlation signals that are distinguishable from each other. During mud logging, depth measurements from the drill bit are used to label the rock characteristics of the first, second, and third batches of cuttings based on unique identifiers for the first, second, and third batches of tracers. See below. Figure 4A and Figure 4BThis section describes an example of performing mud logging operations based on the quality of improved cuttings depth determination.

[0044] Figure 4A and Figure 4B Examples according to one or more embodiments are shown. Figure 4A and Figure 4B The example shown is based on the above reference. Figures 1 to 3 The systems and methods described. In particular, Figure 4A and 4B The diagram illustrates time-correlation signals (401, 402, 403, 411, 412) detected from tracer-impregnated cuttings carried back to the surface in a mud flow. In a first exemplary application, the sequentially occurring time-correlation signals (401, 402, 403, 411, 412) are used to determine the cuttings depth (i.e., the source depth) during mud logging operations. In a second exemplary application, the time-correlation signals (401, 402, 403, 411, 412) and their corresponding injection parameters are part of a training dataset used to train a machine learning model employed by a tracer analysis and control engine. Following the training phase, the machine learning model is used to generate injection distribution curves by taking various well site parameters (e.g., mud properties, bit depth, rate of penetration, formation characteristics, etc.) as input. In the second exemplary application, these injection distribution curves generated by the machine learning model are used to determine the cuttings depth, thereby performing mud logging.

[0045] like Figure 4A As shown, the time-correlation signal 401 corresponds to the first batch of tracer injected into the drilling mud in a fixed amount over a certain period of time during drilling operations. This period of time depends on the flow rate, the outflow and inflow from the annulus and drill string, and the mud properties and drilling depth / velocity. The injection of the first batch of tracer continues until the impregnated cuttings are detected and analyzed at the surface. When the time-correlation signal 401 indicates that an appropriate percentage (e.g., 1 ppm) of the cuttings is impregnated with the first batch of tracer, the impregnated cuttings are collected as a first analytical sample for mud logging for a first exemplary application. Simultaneously, the drill bit depth is recorded as the cuttings origin depth. The first analytical sample is uniquely identified by an identification code encoded on each nanoparticle in the first batch of tracer. The rock properties of the first analytical sample are recorded relative to the cuttings origin depth, i.e., the drill bit depth at which an appropriate percentage of cuttings impregnated with the first batch of tracer is detected.

[0046] Subsequently, a second batch of tracer is injected into the drilling fluid to travel down the formation. For example, the injection of the second batch of tracer can begin when an appropriate percentage of cuttings impregnated with the first batch of tracer is detected. Time-correlation signal 402 corresponds to the cuttings impregnated with the second batch of tracer. Initially, the injection rate can be similar to that of the first batch of tracer; however, the injection rate of the second batch of tracer is automatically adjusted depending on the distinguishability between time-correlation signals 401 and 402. If time-correlation signals 401 and 402 are distinguishable from each other (i.e., have minimal overlap), the injection of the second batch of tracer is gradually reduced until time-correlation signal 402 reaches a certain threshold. Time-correlation signals 401 and 402 are considered distinguishable from each other, i.e., have minimal overlap, if each corresponding signal peak (represented as a solid triangle) is present and has an amplitude exceeding a predetermined threshold (e.g., 30% of the signal peak amplitude) of the signal background 404 (represented as a hollow square). In a first exemplary application, when the time-correlated timing signal 402 indicates that an appropriate percentage of cuttings has been impregnated with the second batch of tracer, the impregnated cuttings are collected as a second analytical sample for mud logging. The second analytical sample is uniquely identified by an identification code encoded on each nanoparticle in the second batch of tracer. The rock characteristics of the second analytical sample are recorded relative to the cuttings' origin depth, i.e., the drill bit depth at which the appropriate percentage of cuttings impregnated with the second batch of tracer is detected.

[0047] Subsequently, a third batch of tracer is injected into the drilling fluid to travel down the formation. For example, the injection of the third batch of tracer can begin when an appropriate percentage of cuttings impregnated with the second batch of tracer is detected. A time-correlation signal 403 corresponds to the cuttings impregnated with the third batch of tracer. In a first exemplary application, when the time-correlation signal 403 indicates that an appropriate percentage of cuttings is impregnated with the third batch of tracer, the impregnated cuttings are collected as a third analytical sample for mud logging. The third analytical sample is uniquely identified by an identification code encoded on each nanoparticle in the third batch of tracer. The rock characteristics of the third analytical sample are recorded relative to the cuttings source depth, i.e., the drill bit depth at which the appropriate percentage of cuttings impregnated with the third batch of tracer is detected.

[0048] For the second exemplary application, since the time-related signals (401, 402, 403) all have distinct peaks with minimal overlap with each other, the injection distribution curves associated with the first, second, and third batches of tracers are appropriately labeled in the machine learning training dataset.

[0049] Figure 4BThis illustrates the case where the time correlation signals of two consecutive batches of tracer are not sufficiently distinguishable. In other words, the time correlation signals of two consecutive batches of tracer cannot be adequately distinguished from each other. Two time correlation signals are considered indistinguishable if each corresponding signal peak does not exist independently, or if the overlap of the two time correlation signals exceeds a predetermined threshold. For example, time correlation signal 411 corresponds to a rock cuttings combination impregnated with two consecutive batches of tracer, while time correlation signal 412 corresponds to rock cuttings impregnated with a later batch of tracer after the injection of two consecutive batches. The rock cuttings combination associated with time correlation signal 411 is discovered and / or confirmed by simultaneously detecting the different identification codes of the first and second batches of tracer. In other words, the rock cuttings associated with time correlation signal 411 include rock cuttings impregnated with the first batch of tracer and rock cuttings impregnated with the second batch of tracer. Figure 4A The situation shown is different; the signal peak at time 7 does not appear as a separate signal peak. Regarding the first exemplary application, cuttings associated with time-correlation signal 411 are not collected as any mud logging sample. Instead, for subsequent batches of tracers, the injection volume and / or injection pressure are increased to generate a time-correlation signal 412 distinguishable from time-correlation signal 411. Therefore, cuttings associated with time-correlation signal 412 are collected as mud logging samples. During mud logging, the drill bit advances deeper into the formation, corresponding to the sequence of time-correlation signals (401, 402, 403, 411, 412) used to determine the depth of cuttings. The injection distribution curves remain substantially unchanged and suitable for the first, second, and third batches of tracers at the corresponding drilling stages. Due to variations in drilling parameters and / or formation parameters, when the drill bit advances beyond the first three recorded depths in the mud logging log, the injection distribution curve becomes unsuitable and is adjusted in real time (i.e., during drilling operations) based on the analysis results of time correlation signals 401, 402, 403, and 411, so that time correlation signal 412 can at least be distinguished from time correlation signal 411 to continue mud logging.

[0050] Regarding the second exemplary application, the cuttings depth cannot be uniquely determined for each of the two consecutive batches of tracer associated with time-correlation signal 411. Therefore, the injection distribution curves of the two consecutive batches of tracer associated with time-correlation signal 411 are inappropriately labeled in the machine learning training dataset.

[0051] Exemplary tracer injection parameters are listed in Table 1 below, which uses polybrominated styrene / bromostyrene nanoparticles (PBrST / BNP), polychlorostyrene chlorinated nanoparticles (PCIST / CNP), polymethylstyrene nanoparticles (MNP), sodium dodecyl sulfate (SDS), and oil-based mud (OBM). For example, each row in Table 1 can correspond to the above. Figure 4A One of the three batches of tracers described in the text or above Figure 4B One of the three batches of tracers described in the text.

[0052] Table 1

[0053]

[0054] The embodiments can be implemented on a computer system. Any combination of mobile devices, desktops, servers, routers, switches, embedded devices, or other types of hardware can be used. For example, such as... Figure 5A As shown, the computing system 500 may include one or more computer processors 502, non-persistent memory 504 (e.g., volatile memory, such as random access memory (RAM), cache memory), persistent memory 506 (e.g., hard disk, optical drive such as optical disc (CD) drive or digital multifunction disc (DVD) drive, flash memory, etc.), communication interface 512 (e.g., Bluetooth interface, infrared interface, network interface, fiber optic interface, etc.), and numerous other elements and functions.

[0055] The computer processor 502 may be an integrated circuit for processing instructions. For example, the computer processor may be one or more cores or microkernels of a processor. The computing system 500 may also include one or more input devices 510, such as a touch screen, keyboard, mouse, microphone, touchpad, electronic pen, or any other type of input device.

[0056] The communication interface 512 may include an integrated circuit for connecting the computing system 500 to a network (not shown) (e.g., a local area network (LAN), a wide area network (WAN) such as the Internet, a mobile network, or any other type of network) and / or to another device (e.g., another computing device).

[0057] In addition, the computing system 500 may include one or more output devices 508, such as a screen (e.g., a liquid crystal display (LCD), plasma display, touch screen, cathode ray tube (CRT) monitor, projector, or other display device), printer, external storage, or any other output device. One or more output devices may be the same as or different from input devices. Input and output devices may be connected locally or remotely to the computer processor 502, non-persistent storage 504, and persistent storage 506. Many different types of computing systems exist, and the aforementioned input and output devices may take other forms.

[0058] Software instructions in the form of computer-readable program code for performing embodiments of the present disclosure may be stored, in whole or in part, temporarily or permanently, on a non-transitory computer-readable medium (e.g., CD, DVD, storage device, disk, magnetic tape, flash memory, physical memory, or any other computer-readable storage medium). Specifically, the software instructions may correspond to computer-readable program code that, when executed by a processor, is configured to perform one or more embodiments of the present disclosure.

[0059] Figure 5A The computing system 500 can be connected to a network or act as part of a network. For example, such as... Figure 5B As shown, network 520 may include multiple nodes (e.g., node X 522, node Y 524). Each node may correspond to a computing system, for example... Figure 5A The computing system shown, or a group of nodes combined, can correspond to Figure 5A The computing system shown is illustrated. As an example, embodiments of this disclosure can be implemented on nodes of a distributed system connected to other nodes. As another example, embodiments of this disclosure can be implemented on a distributed computing system with multiple nodes, wherein each part of this disclosure can reside on a different node within the distributed computing system. Furthermore, one or more elements of the computing system 500 described above can be located in remote locations and connected to other elements via a network.

[0060] Despite Figure 5B Not shown, but a node can correspond to a blade in a server chassis connected to other nodes via a backplane. As another example, a node can correspond to a server in a data center. As yet another example, a node can correspond to a computer processor or a microkernel of a computer processor with shared memory and / or resources.

[0061] Nodes in network 520 (e.g., node X 522, node Y 524) can be configured to provide services to client device 526. For example, a node may be part of a cloud computing system. A node may include the ability to receive requests from client device 526 and transmit responses to client device 526. Client device 526 may be a computing system, such as... Figure 5A The computing system shown. Furthermore, client device 526 may include and / or perform all or part of one or more embodiments of this disclosure.

[0062] While this disclosure has been described with respect to a limited number of embodiments, those skilled in the art, who will benefit from this disclosure, will understand that other embodiments can be devised without departing from the scope of the disclosure as set forth herein. Therefore, the scope of this disclosure should be defined only by the appended claims.

[0063] Although this disclosure has been foregoing a description with reference to specific devices, materials, and embodiments, it is not intended to be limited to the details disclosed herein; rather, it extends to all functionally equivalent structures, methods, and uses, such as those within the scope of the appended claims. In the claims, the means-plus-function clause is intended to cover not only structural equivalents but also equivalent structures, as described in this disclosure for performing the enumerated functions. Thus, while nails and screws may not be structural equivalents, since nails have a cylindrical surface for securing wooden components together and screws have a helical surface, in the context of fastening wooden components, nails and screws may be equivalent structures. The applicant’s explicit intent is not to invoke Section 112(f) of the U.S. Patent Act to limit any claim in this specification, except those claims that expressly use the phrase “means for…” along with the associated function.

Claims

1. A method for determining the depth of cuttings during drilling operations in underground formations, the method comprising: During the entire first time window of the drilling operation, the first batch of tracer is released into the drilling fluid using a tracer injection pump, wherein the first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings; Using a tracer detector at a surface location, a first-time relevant signal is detected from the first batch of tracers when the first batch of cuttings reaches the surface, wherein the first batch of tracers is delivered to the well by the drilling fluid after impregnating the first batch of cuttings; During the entire second time window of the drilling operation, a second batch of tracer is released into the drilling fluid using the tracer injection pump, wherein the second batch of tracer is delivered downhole by the drilling fluid to impregnate the second batch of cuttings when the drill bit produces the second batch of cuttings; Using the tracer detector at the said ground location, a second time-related signal is detected from the second batch of tracer when the second batch of cuttings reaches the ground, wherein the second batch of tracer is delivered to the well by the drilling fluid after the second batch of cuttings has been impregnated; Using a tracer analysis and control engine, the overlap of the first time-related signals and the second time-related signals is analyzed for the injection parameters of the tracer injection pump during the first and second time windows to generate an injection distribution curve; and Based on the injection distribution curve, the injection parameters of the tracer injection pump are adjusted to improve the quality of the cuttings depth determination. Among them, mud logging is performed based on the quality determined by the improved cuttings depth.

2. The method according to claim 1, further comprising: The injection distribution curve is sent from the tracer analysis and control engine to the IoT controller. The IoT controller adjusts the injection parameters of the tracer injection pump based on the injection distribution curve.

3. The method according to claim 2, wherein, The tracer analysis and control engine is located on a cloud server, which communicates with the IoT controller via a network connection.

4. The method according to claim 1, in, The injection distribution curve specifies the time-dependent injection pressure over the entire injection period and the interval between adjacent injection periods. The injection parameters include the pressure of each injector valve connected to the corresponding container chamber of the tracer injection pump, as well as the degree to which they are closed and open.

5. The method according to claim 1, wherein, The first injection distribution curve of the first batch of tracers and the second injection distribution curve of the second batch of tracers are defined such that the first time-correlation signal and the second time-correlation signal are distinguishable from each other.

6. The method according to any one of claims 5, in, The tracer analysis and control engine generates the injection distribution curve based on a machine learning model. The machine learning model is trained using at least the first injection distribution curve and the second injection distribution curve, which produce mutually distinguishable first and second time-related signals. The inputs to the machine learning model include drilling fluid parameters, drilling parameters, and formation parameters.

7. The method according to any one of claims 1 to 6, wherein, The first and second batches of tracers comprise polymer nanoparticles encoded with corresponding identification codes.

8. A system for determining the depth of rock cuttings, the system comprising: The tracer injection pump is configured to: During the entire first time window of the drilling operation, the first batch of tracer is released into the drilling fluid, wherein the first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings, and During the entire second time window of the drilling operation, a second batch of tracer is released into the drilling fluid, wherein the second batch of tracer is delivered downhole by the drilling fluid to impregnate the second batch of cuttings when the drill bit produces the second batch of cuttings; A tracer detector at a ground location, the tracer detector being configured as follows: A first-time relevant signal is detected from the first batch of tracers when the first batch of cuttings reaches the surface, wherein the first batch of tracers is delivered to the wellhead by the drilling fluid after impregnating the first batch of cuttings. A second time-related signal is detected from the second batch of tracers when the second batch of cuttings reaches the surface, wherein the second batch of tracers is delivered to the well by the drilling fluid after the second batch of cuttings has been impregnated; The tracer analysis and control engine is configured as follows: The overlap of the first time-correlation signal and the second time-correlation signal is analyzed based on the injection parameters of the tracer injection pump during the first time window and the second time window to generate an injection distribution curve; and The IoT controller is configured as follows: Based on the injection distribution curve, the injection parameters of the tracer injection pump are adjusted to improve the quality of the cuttings depth determination. Among them, mud logging is performed based on the quality determined by the improved cuttings depth.

9. The system according to claim 8, wherein, The tracer analysis and control engine is located on a cloud server, which communicates with the IoT controller via a network connection.

10. The system according to claim 8, in, The injection distribution curve specifies the time-dependent injection pressure over the entire injection period and the interval between adjacent injection periods. The injection parameters include the pressure of each injector valve connected to the corresponding container chamber of the tracer injection pump, as well as the degree to which they are closed and open.

11. The system according to claim 8, wherein, The first injection distribution curve of the first batch of tracers and the second injection distribution curve of the second batch of tracers are defined such that the first time-correlation signal and the second time-correlation signal are distinguishable from each other.

12. The system according to claim 11, in, The tracer analysis and control engine is also configured to: The injection distribution curve is generated based on a machine learning model. The machine learning model is trained using at least the first injection distribution curve and the second injection distribution curve, which produce mutually distinguishable first and second time-related signals. The inputs to the machine learning model include drilling fluid parameters, drilling parameters, and formation parameters.

13. The system according to any one of claims 8 to 12, wherein, The first and second batches of tracers comprise polymer nanoparticles encoded with corresponding identification codes.

14. A non-transitory computer-readable medium storing instructions executable by a computer processor for determining cuttings depth, the instructions, when executed, causing the computer processor to perform steps including: Control the tracer injection pump so that the tracer injection pump: During the entire first time window of the drilling operation, the first batch of tracer was released into the drilling fluid, in which... The first batch of tracer is delivered downhole by the drilling fluid to impregnate the first batch of cuttings when the drill bit produces the first batch of cuttings, and During the entire second time window of the drilling operation, a second batch of tracer is released into the drilling fluid, wherein the second batch of tracer is delivered downhole by the drilling fluid to impregnate the second batch of cuttings when the drill bit produces the second batch of cuttings; Control the tracer detector at the ground location such that the tracer detector: A first-time relevant signal is detected from the first batch of tracers when the first batch of cuttings reaches the surface, wherein the first batch of tracers is delivered to the wellhead by the drilling fluid after impregnating the first batch of cuttings. A second time-related signal is detected from the second batch of tracers when the second batch of cuttings reaches the surface, wherein the second batch of tracers is delivered to the well by the drilling fluid after the second batch of cuttings has been impregnated; The overlap of the first time-correlation signal and the second time-correlation signal is analyzed based on the injection parameters of the tracer injection pump during the first time window and the second time window to generate an injection distribution curve; and Based on the injection distribution curve, the injection parameters of the tracer injection pump are adjusted to improve the quality of the cuttings depth determination. Among them, mud logging is performed based on the quality determined by the improved cuttings depth.

Images