Signal processing method to inform maintenance of machine or alteration of environment
The signal processing method addresses inefficiencies in machine operation by analyzing signal variability and similarity to detect malfunctions and environmental changes, enabling adaptive maintenance and configuration adjustments.
Patent Information
- Application Number
- PCT/CN2024/071567
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-01-10
- Publication Date
- 2025-07-17
AI Technical Summary
Existing methods fail to effectively identify and respond to malfunctions or environmental changes in machines operating within environments by analyzing emitted signals for variability and similarity, leading to inefficiencies in maintenance and operation.
A signal processing method that organizes signals into windows, determines variability and similarity measures, and identifies outlier windows to inform maintenance or configuration adjustments based on machine function or environmental properties, using sensors and processing systems to detect and analyze sound and vibration data.
Enables timely maintenance and adaptive operation of machines by identifying malfunctions or environmental changes, improving efficiency and reliability through targeted maintenance and configuration adjustments.
Smart Images

Figure CN2024071567_17072025_PF_FP_ABST
Abstract
Description
SIGNAL PROCESSING METHOD TO INFORM MAINTENANCE OF MACHINE OR ALTERATION OF ENVIRONMENTBACKGROUND
[0001] When a machine is operating within an environment, the machine may emit sound and / or vibrations over time. The sound and / or vibrations may be recorded as a signal. When the machine functionally changes, malfunctions, and / or the environment changes, the signal may also change. As such, the signal may contain information about how the machine is functioning, such as if the machine is malfunctioning, and / or about the environment the machine is operating within.SUMMARY
[0002] This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.
[0003] In general, in one aspect, embodiments relate to a method. The method includes obtaining, from a sensor, a signal associated with a machine operating within an environment, organizing, using a signal processing system, the signal into windows, and determining, using the signal processing system, a measure of variability for each of the windows using the signal within each of the windows. The signal includes a first amplitude at each time sample. The method further includes identifying, using the signal processing system, one or more outlier windows among the windows based, at least in part, on the measure of variability for each of the windows and, for each outlier window among the one or more outlier windows, determining, using the signal processing system, a measure of similarity between the signal within each outlier window and each reference signal. Each of the reference signals is characteristic of a function of the machine, a property of the environment, or a noise. The method still further includes at least one of maintaining, using a machine maintenance system, the machine based, at least in part, on the measure of similarity and the function, where the function includes a malfunction, altering, using a planning system, a configuration of the machine based, at least in part, on the measure of similarity and the property, altering the environment based, at least in part, on the measure of similarity and the property, and updating, using the signal processing system, the signal by removing the signal within each outlier window based, at least in part, on the measure of similarity and the noise.
[0004] In general, in one aspect, embodiments relate to a system. The system includes a sensor and signal processing system. The sensor is configured to collect a signal associated with a machine operating within an environment. The signal includes a first amplitude at each time sample. The signal processing system is configured to organize the signal into windows, determine a measure of variability for each of the windows using the signal within each of the windows, and identify one or more outlier windows among the windows based, at least in part, on the measure of variability for each of the windows. The signal processing system is further configured, for each outlier window among the one or more outlier windows, to determine a measure of similarity between the signal within each outlier window and each reference signal. Each reference signal is characteristic of a function of the machine, a property of the environment, or a noise. At least one of the following is performed. The signal processing system is still further configured to cause a machine maintenance system to maintain the machine based, at least in part, on the measure of similarity and the function, where the function includes a malfunction. The signal processing system is still further configured to cause a planning system to alter a configuration of the machine based, at least in part, on the measure of similarity and the property. The signal processing system is still further configured to cause an altered environment for the machine to operate within based, at least in part, on the measure of similarity and the property. The signal processing system is further still configured to update the signal by removing the signal within each outlier window based, at least in part, on the measure of similarity and the noise.
[0005] Other aspects and advantages of the claimed subject matter will be apparent from the following description and the appended claims.BRIEF DESCRIPTION OF DRAWINGS
[0006] Specific embodiments of the disclosed technology will now be described in detail with reference to the accompanying figures. Like elements in the various figures are denoted by like reference numerals for consistency.
[0007] FIG. 1 illustrates a machine operating within an environment in accordance with one or more embodiments.
[0008] FIGs. 2A and 2B display a signal in accordance with one or more embodiments.
[0009] FIGs. 3A and 3B display a transformed signal in accordance with one or more embodiments.
[0010] FIGs. 4A and 4B display measures of variability in accordance with one or more embodiments.
[0011] FIG. 5 describes a method in accordance with one or more embodiments.
[0012] FIG. 6 illustrates a signal processing system in accordance with one or more embodiments.
[0013] FIG. 7 describes systems in accordance with one or more embodiments.DETAILED DESCRIPTION
[0014] In the following detailed description of embodiments of the disclosure, numerous specific details are set forth in order to provide a more thorough understanding of the disclosure. However, it will be apparent to one of ordinary skill in the art that the 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.
[0015] Throughout the application, ordinal numbers (e.g., first, second, third, etc. ) may be used as an adjective for an element (i.e., any noun in the application) . The use of ordinal numbers is not to imply or create any particular ordering of the elements nor to limit any element to being only a single element unless expressly disclosed, such as using the terms “before, ” “after, ” “single, ” and other such terminology. Rather, the use of ordinal numbers is to distinguish between the elements. By way of an example, a first element is distinct from a second element, and the first element may encompass more than one element and succeed (or precede) the second element in an ordering of elements.
[0016] It is to be understood that the singular forms “a, ” “an, ” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a signal” includes reference to one or more of such signals.
[0017] Terms such as “approximately, ” “substantially, ” etc., mean that the recited characteristic, parameter, or value need not be achieved exactly, but that deviations or variations, including for example, tolerances, measurement error, measurement accuracy limitations and other factors known to those of skill in the art, may occur in amounts that do not preclude the effect the characteristic was intended to provide.
[0018] It is to be understood that one or more of the steps shown in the flowcharts may be omitted, repeated, and / or performed in a different order than the order shown. Accordingly, the scope disclosed herein should not be considered limited to the specific arrangement of steps shown in the flowcharts.
[0019] Although multiple dependent claims are not introduced, it would be apparent to one of ordinary skill that the subject matter of the dependent claims of one or more embodiments may be combined with other dependent claims.
[0020] In the following description of FIGs. 1-7, any component described regarding a figure, in various embodiments disclosed herein, may be equivalent to one or more like-named components described regarding any other figure. For brevity, descriptions of these components will not be repeated regarding each figure. Thus, each and every embodiment of the components of each figure is incorporated by reference and assumed to be optionally present within every other figure having one or more like-named components. Additionally, in accordance with various embodiments disclosed herein, any description of the components of a figure is to be interpreted as an optional embodiment which may be implemented in addition to, in conjunction with, or in place of the embodiments described regarding a corresponding like-named component in any other figure.
[0021] Signal processing methods and associated systems are disclosed to identify and characterize one or more outlier windows within a signal. The signal is associated with a machine operating within an environment. A measure of variability, measure of similarity, and reference signals may be used, at least in part, to identify and characterize the signal within the one or more outlier windows. The signal within each outlier window may be characteristic of a function of the machine, property of the environment, or noise. In turn, in some embodiments, the machine may be maintained based on the characterized function of the machine, such as if the machine is malfunctioning, or a configuration of the machine may be altered based on the characterized property of the environment.
[0022] The machine may be any system configured to perform one or more functions and associated with any signal. The machine may be composed of one or more combinations, subcombinations, and / or elements. As such, the machine may not be associated with a specific field of endeavor. Thus, an exhaustive list of possible machines is not provided herein due to the extensive number of machines that are associated with a signal. Each, though not all, of the one or more combinations, subcombinations, and / or elements of the machine may be associated with the signal or portion thereof. For example, in some embodiments, each of two or more combinations, subcombinations, and / or elements of the machine may be associated with a portion of the signal at a unique frequency. As such, in these embodiments, the signal associated with the machine may be a blend of each portion of the signal associated with each of the two or more combinations, subcombinations, and / or elements of the machine where the signal has a bandwidth that includes the unique frequencies. Hereinafter, the discussion of the machine is posed either broadly as a machine or narrowly as a drilling system or element of the drilling system, such as a drill bit.
[0023] The signal may be any signal associated with the machine while operating within an environment. In some embodiments, the signal may be emitted from the machine over time or a measurement of the machine over time. In some embodiments, the signal may be a record of a measure of a sound and / or measure of a vibration that the machine emits while operating within an environment over time. In other embodiments, the signal may be a record of a measure of velocity or acceleration of the machine while operating within the environment over time.
[0024] The sensor that detects and records the signal may be any sensor. Further, the sensor may be an element of the machine, configured to attach to the machine, configured to attach to the environment, or external to the machine and / or environment. In some embodiments, the sensor may be an acoustic sensor configured to detect and record a measure of a sound or measure of a vibration emitted from the machine while operating within the environment. Thus, an exhaustive list of possible sensors is not provided herein. Hereinafter, the discussion of the sensor is posed either broadly as a sensor or narrowly as an acoustic sensor.
[0025] The environment may be any environment that the machine is configured to operate within. As such, the environment may not be associated with a specific field of endeavor. Further, the environment need not be the primary environment or field the machine is primarily designed to operate within. For example, the environment may be the environment used to test the machine and / or troubleshoot issues with the machine. As such, the environment may include, without limitation, a manufacturing environment, laboratory environment, neighboring primary environment, or primary environment. Thus, an exhaustive list of possible environments is not provided herein due to the extensive number of environments the machine may be configured to operate within. Hereinafter, the discussion of the environment is posed either broadly as an environment or narrowly as a formation (i.e., primary environment) , where a drilling system (i.e., machine) is configured to drill a wellbore within the formation.
[0026] Turning to FIG. 1, FIG. 1 illustrates a machine 100 operating within an environment 105 in accordance with one or more embodiments. Specifically, the machine 100 is illustrated as a drilling system 100a and the environment 105, as a formation 105a. In some embodiments, the drilling system 100a may be configured to drill a wellbore 110 within the formation 105a guided by a wellbore path. Although the drilling system 100a illustrated in FIG. 1 is configured to drill the wellbore 110 on land, the drilling system 100a may be a marine wellbore drilling system configured to drill the wellbore 110 below water. Further, although the drilling system 100a illustrated in FIG. 1 is used to drill a new wellbore 110, the wellbore 110 being drilled may be a sidetrack wellbore or offset wellbore. As such, the example of the drilling system 100a configured to operate within a formation 105a illustrated in FIG. 1 is not meant to limit the present disclosure but provide an example of a machine 100 operating within an environment 105.
[0027] Subcombinations of the drilling system 100a may include, without limitation, a drill rig 115, drillstring 120, and bottom hole assembly (BHA) 125. Each subcombination may include one or more elements. For example, the drill rig 115 may include a derrick 130, top drive 135, and drive shaft 140. The drillstring 120 may include one or more drill pipes connected to form conduit. The BHA 125 may include a drill bit 145 and mud motor 150. In some embodiments, one or more subcombinations or elements of the drilling system 100a, such as the drill bit 145, may be the machine 100.
[0028] The drill rig 115 may be situated on a land drill site, offshore platform, or drill ship. The drill rig 115 may be equipped with a hoisting system, such as the derrick 130, configured to raise or lower the drillstring 120. The drill rig 115 may be further equipped with the top drive 135 and drive shaft 140 configured to rotate the drillstring 120. In some embodiments, a sensor 155 may be attached to the drillstring 120 or drive shaft 140 above the surface of the earth 175 as illustrated in FIG. 1. In other embodiments, the sensor 155 may be attached to the drillstring 120 downhole. In some embodiments, the sensor 155 may be communicably coupled to a data acquisition system (DAQ) 160 that is communicably coupled to a signal processing system 165.
[0029] The BHA 125 may be disposed at the distal end of the drillstring 120. The BHA 125 may include the drill bit 145 along with measurement tools, such as a measurement-while-drilling (MWD) tool and logging-while-drilling (LWD) tool (not shown) . The MWD tools may include logging sensors and hardware to measure downhole drilling parameters, such as the azimuth and inclination of the drill bit 145, weight-on-bit, and torque. The LWD measurements may include logging sensors, such as resistivity, gamma ray, and neutron density sensors, to characterize the rock 170 surrounding the wellbore 110. Both MWD and LWD measurements may be transmitted to the surface of the earth 175 using any suitable telemetry system known in the art, such as a mud pulse or by wired drill pipe. In still other embodiments, the sensor 155 may be attached to the BHA 125. Further, in some embodiments, a logging sensor may be a sensor 155.
[0030] To start drilling, or “spudding in, ” the wellbore 110, the hoisting system lowers the drillstring 120 suspended from the derrick 130 of the drill rig 115 towards the planned surface location of the wellbore 110. In some embodiments, an engine, such as a diesel engine, may be used to supply power to the top drive 135 to rotate the drillstring 120 via the drive shaft 140. The weight of the drillstring 120 combined with the rotational motion enables the drill bit 145 to bore the wellbore 110. In other embodiments, the mud motor 150 and drilling mud 180 may enable the drill bit 145 to rotate and drill the wellbore 110.
[0031] The near-surface rock 170 of the formation 105a is typically made up of loose or soft sediment or rock, so large diameter casing (e.g., “base pipe” or “conductor casing” ) is often put in place while drilling to stabilize and isolate the wellbore 110. At the top of the base pipe is the wellhead, which serves to provide pressure control through a series of spools, valves, or adapters (not shown) . Once near-surface drilling has begun, water or drilling mud 180 may be used to force the base pipe into place using a pumping system until the wellhead is situated just above the surface of the earth 175.
[0032] Drilling may continue without any casing once deeper and / or more compact rock 170 is reached. While drilling, a drilling mud system may pump drilling mud 180 from a mud tank (not shown) on the surface of the earth 175 through the drillstring 120. Drilling mud 180 serves various purposes, including pressure equalization, removal of rock cuttings, and cooling and lubrication of the drill bit 145.
[0033] At planned depth intervals, drilling may be paused and the drillstring 120 withdrawn or retrieved from the wellbore 110. Sections of casing may be connected, inserted, and cemented into the wellbore 110. Casing string may be cemented in place by pumping cement and drilling mud 180, separated by a “cementing plug, ” from the surface of the earth 175 through the drillstring 120. The cementing plug and drilling mud 180 force the cement through the drillstring 120 and into the annular space between the casing and the wall of the wellbore 110. Once the cement cures, drilling may recommence. The drilling process is often performed in several stages. Therefore, a drilling and casing cycle may be repeated more than once, depending on the depth of the wellbore 110 and the pressure on the walls of the wellbore 110 from surrounding rock 170.
[0034] Due to the high pressures experienced by deep wellbores 110, a blowout preventer (BOP) may be installed at the wellhead to protect the drill rig 115 and wellbore environment from unplanned oil or gas releases. As the wellbore 110 becomes deeper, both successively smaller drill bits 145 and casing may be used. Drilling deviated or horizontal wellbores 110 may require specialized drill bits 145 and / or drill assemblies.
[0035] The drilling system 100a may be disposed at and communicate with other systems in the wellbore environment. The drilling system 100a may be configured to control at least a portion of a drilling operation by providing controls to various components of the drilling operation. In one or more embodiments, the drilling system 100a may receive data from one or more drilling sensors arranged to measure controllable parameters of the drilling operation. As a non-limiting example, drilling sensors may be arranged to measure weight-on-bit, drill rotational speed (RPM) , flow rate of the mud pumps (GPM) , and rate of penetration of the drilling operation (ROP) . Each drilling sensor may be positioned or configured to measure a desired physical stimulus. Drilling may be considered complete when a drilling target with a hydrocarbon reservoir (not shown) is reached or the presence of hydrocarbons is established. In some embodiments, a drilling sensor may be a sensor 155.
[0036] FIG. 2A displays a signal 200a associated with a machine 100 operating within an environment 105 in accordance with one or more embodiments. The signal 200a is a time series where the signal 200a includes a first amplitude 205 at each time sample 210 among the time series. In FIG. 2A, the abscissa 215 denotes recording time (hereinafter also “time” ) and the ordinate 220 denotes first amplitude 205.
[0037] In some embodiments, the signal 200a displayed in FIG. 2A may be emitted from the drill bit 145 drilling the wellbore 110 within the formation 105a over a period of time and detected and recorded by the sensor 155. In some embodiments, the signal 200a displayed in FIG. 2A may be organized into a window 225 of a pre-defined recording time length.
[0038] FIG. 2B displays a signal 200b associated with a machine 100 operating within an environment 105 in accordance with one or more embodiments. In some embodiments, the signal 200b displayed in FIG. 2B may be emitted from the drill bit 145 drilling the wellbore 110 within the formation 105a over a period of time and detected and recorded by the sensor 155. In some embodiments, the signal 200b displayed in FIG. 2B may be organized into hundreds of windows 225 of a pre-defined recording time length. In FIG. 2B, the signal 200b within each window 225 is stacked one on top of each other for viewing ease. In FIG. 2B, the ordinate 230 may denote any measure associated with the machine 100 or environment 105. For example, in some embodiments, the ordinate 230 may be depth of the drill bit 145 (i.e., the machine 100) along the wellbore 110 or true depth of the drill bit 145 within the formation 105a. In other embodiments, the ordinate 230 may denote recording time or recording time interval. The abscissa 235 denotes recording time. The grayscale bar denotes first amplitude 205 at each time sample 210.
[0039] In some embodiments, a transformed signal may be determined from the signal 200a, b. To do so, a transform may be applied to the signal 200a, b. The transform may be any type of Fourier transform, such as a fast Fourier transform (FFT) . However, any transform known to a person of ordinary skill in the art may be used. In some embodiments, the transform may transform the signal 200a, b from a time domain to a frequency domain.
[0040] FIG. 3A displays a transformed signal 300a associated with a machine 100 operating within an environment 105 in accordance with one or more embodiments. The transformed signal 300a is determined by applying an FFT to the signal 200a displayed in FIG. 2A. The transformed signal 300a is in a frequency domain as displayed along the abscissa 305. Each second amplitude 310 is displayed along the ordinate 315 at each sample 320.
[0041] FIG. 3B displays a transformed signal 300b associated with a machine 100 operating within an environment 105 in accordance with one or more embodiments. The transformed signal 300b is determined by applying an FFT to the signal 200b displayed in FIG. 2B along the time domain. In other embodiments, a transform may alternatively or additionally be applied to the domain along the ordinate 325. For example, a transform may be applied to the signal 200b to transform a depth domain to a wavenumber domain. The second amplitude 310 of the transformed signal 300b changes as shown by the scale bar.
[0042] In some embodiments, a measure of variability of the signal 200a, b or transformed signal 300a, b may be determined for each window 225. The measure of variability may include, without limitation, standard deviation, variance, standard error of the mean, and a probability distribution. The probability distribution may take the form of a discrete distribution or continuous distribution.
[0043] In some embodiments, if the measure of variability is variance, variance Vmay be determined for each window 225 by:
[0044] where Ai is the first amplitude 205 at the ith time sample 210 or second amplitude 310 at the ith sample 320, respectively, μ is the mean first amplitude or mean second amplitude, and N is the total number time samples 210 or samples 320. In some embodiments, a weighting scheme may be included with any measure of variability. For example, Equations (1) and (2) may be weighted as:
[0045] FIGs. 4A and 4B display measures of variability 400 in accordance with one or more embodiments. Each measure of variability 400 is determined by applying Equations (1) and (2) to the transformed signal 300b in each window 225 displayed in FIG. 3B. FIG. 4A specifically displays a zoomed-out version of the measures of variability 400. In some embodiments, each of one or more outlier windows 405 may be clearly identified as a large measure of variability 400 compared to other measures of variability 400 within FIG. 4A. FIG. 4B specifically displays a zoomed-in version of the measures of variability 400. Each of the one or more outlier windows 405 identified in FIG. 4A continue to be displayed but are now cut off as the abscissa 410 is truncated relate to FIG. 4A. In some embodiments, each of one or more additional outlier windows 405 may be clearly identified in FIG. 4B as a small measure of variability 400 compared to other measures of variability 400 within FIG. 4B. Each of the one or more additional outlier windows 405 may even be zero or nearly zero.
[0046] In some embodiments, the one or more outlier windows 405 may be identified by applying one or more thresholds 415a, b to the measures of variability 400. For example, FIG. 4B displays two thresholds: a lower threshold 415a and upper threshold 415b. In some embodiments, a measure of variability 400 below the lower threshold 415a may be identified as an outlier window 405. In some embodiments, a measure of variability 400 above the upper threshold 415b may be identified as an outlier window 405.
[0047] In some embodiments, each of the one or more thresholds 415a, b may be a percentile threshold. For example, the lower threshold 415a may be defined as the 0.1%percentile and the upper threshold 415b may be defined as the 99.9%threshold.
[0048] A measure of similarity (i.e., coherence) may be determined between the signal 200a, b or transformed signal 300a, b within each outlier window 405 and reference signals. The measure of similarity may be, without limitation, semblance, cross correction, and multiple signal classification (MUSIC) measures.
[0049] In some embodiments, each reference signal may be the signal 200a, b or transformed signal 300a, b within a window 225. In other embodiments, each reference signal may be a signal external to the signal 200a, b and transformed signal 300a, b. In these embodiments, each reference signal may be a synthetic signal or a previously-recorded signal. Each reference signal may be characteristic of a function of the machine 100, property of the environment 105, or noise. Relative to the function of the machine 100, a reference signal may characterize that the machine 100 is functioning adequately, malfunctioning, or changed functions. Each reference signal may be compared to the signal 200a, b or transformed signal 300a, b within each outlier window 405 to determine a measure of similarity.
[0050] If a reference signal is characteristic of the machine 100 functioning adequately and the machine 100 is functioning adequately, the outlier window 405 may include a large measure of similarity. If a reference signal is characteristic of the machine 100 functioning adequately and the machine 100 is malfunctioning, the outlier window 405 may include a small measure of similarity. Vice versa, if a reference signal is characteristic of the machine 100 malfunctioning and the machine 100 is functioning adequately, the outlier window 405 may include a small measure of similarity. If a reference signal is characteristic of the machine 100 malfunctioning and the machine 100 is malfunctioning, the outlier window 405 may include a large measure of similarity. Further, if a reference signal is characteristic of a property of the environment 105 and the machine 100 is operating within the environment 105 with that property, the outlier window 405 may include a large measure of similarity. Further still, if a reference signal is characteristic of noise and the signal 200a, b or transformed signal 300a, b includes noise, the outlier window 405 may include a large measure of similarity. Note that if the measures of similarity are normalized, a small measure of similarity may be zero or near zero while a large measure of similarity may be one or near one.
[0051] Once one or more measures of similarity are determined for each outlier window 405, at least one of the following may be performed. If the measure of similarity indicates that the machine 100 is malfunctioning, the machine 100 may be maintained. The machine 100 may be maintained by a machine maintenance system to bring the machine 100 back to functioning adequately. If the measure of similarity indicates that the machine 100 is operating within the environment 105 with a known property, the configuration of the machine 100 may be altered to accommodate the environment 105 with that property or the environment 105 may be altered. If the measure of similarity indicates that there is noise in the signal 200a, b or transformed signal 300a, b, the signal 200a, b or transformed signal 300a, b within the outlier window 405 may be removed.
[0052] FIG. 5 describes a method in accordance with one or more embodiments. In step 500, a signal 200a, b is obtained. The signal 200a, b is associated with a machine 100 operating within an environment 105. In some embodiments, the machine 100 may be a drilling system 100a or one or more subcombinations or elements thereof, such as a drill bit 145, as illustrated in FIG. 1. In some embodiments, the environment 105 may be a formation 105a as illustrated in FIG. 1. However, the machine 100 need not be limited to a specific field of endeavor. Further, the environment 105 need not be limited to the primary environment or field that the machine 100 is primarily designed to operate within.
[0053] The signal 200a, b is obtained from a sensor 155. In some embodiments, the sensor 155 may be an acoustic sensor configured to detect and record a measure of sound and / or measure of a vibration emitted from the machine 100 while operating within the environment 105. In other embodiments, the sensor 155 may be configured to detect and record the velocity or acceleration of the machine 100 while operating within the environment 105. The sensor 155 may be an element of the machine 100, configured to attach to the machine 100, configured to attach to the environment 105, or external to the machine 100 and / or environment 105. The signal 200a, b includes a first amplitude 205 at each time sample 210 as displayed in FIGs. 2A and 2B. As such, the signal 200a, b is a time series.
[0054] In step 505, the signal 200a, b is organized into windows 225. Each window 225 includes a portion of the signal 200a, b. In some embodiments, as displayed in FIGs. 3A and 3B, organizing the signal 200a, b may include determining a transformed signal 300a, b from the signal 200a, b using a transform as previously described. In some embodiments, the transform may transform the signal 200a, b from a time domain to a frequency domain. In other embodiments, a second transform may be applied to the signal 200a, b or transformed signal 300a, b to transform another domain of the signal 200a, b or transformed signal 300a, b. For example, in some embodiments, a transform may be applied along a depth domain as displayed in FIG. 3B to transform the depth domain to a wavenumber domain.
[0055] In step 510, a measure of variability 400 is determined for each of the windows 225. The measure of variability 400 may include, without limitation, standard deviation, variance, standard error of the mean, and a probability distribution. FIGs. 4A and 4B display a measure of variability 400 for each window 225 of the transformed signal 300b displayed in FIG. 3B. The measure of variability 400 is determined using the signal 200a, b or transformed signal 300a, b within each window 225. For example, in some embodiments, the measure of variability 400 may be variance and is determined for each window 225 using Equations (1) and (2) .
[0056] In step 515, one or more outlier windows 405 are identified among the windows 225 using the measure of variability 400. In some embodiments, an outlier window 405 may include a measure of variability 400 within a window 225 that may be smaller or larger than other measures of variability 400 of the signal 200a, b or transformed signal 300a, b within other windows 225. In other embodiments, an outlier window 405 may include a measure of variability 400 that is above an upper threshold 415b as illustrated in FIG. 4B. In still other embodiments, an outlier window 405 may include a measure of variability 400 that is below a lower threshold 415a as illustrated in FIG. 4B.
[0057] In step 520, a measure of similarity is determined for each outlier window 405. The measure of similarity is determined between the signal 200a, b or transformed signal 200a, b within the outlier window 405 and reference signals. In some embodiments, the reference signals are a portion of the signal 200a, b or transformed signal 200a, b. In other embodiments, the reference signals may be external to the signal 200a, b or transformed signal 200a, b. In these embodiments, the reference signals may be synthetic signals or previously-recorded signals. Each reference signal may be characteristic of a function of the machine 100, property of the environment 105, or noise as previously described.
[0058] In step 525, at least one of the following is performed.
[0059] If the measure of similarity indicates a malfunction of the machine 100, the machine 100 may be maintained. In some embodiments, a drill bit 145 of the drilling system 100a may have malfunctioned. In these embodiments, the drilling system 100a may be maintained by stopping the drilling system 100a, retrieving the drilling system 100a from the wellbore 110 within the formation 105a, replacing the drill bit 145 of the drilling system 100a with a new drill bit, deploying the drilling system 100a that includes the new drill bit within the wellbore 110, and starting the drilling system 100a.
[0060] If the measure of similarity indicates a property of the environment 105, the configuration of the machine 100 and / or the environment 105 may be altered. In some embodiments, the property of the environment 105 is a lithology of the formation 105a. In these embodiments, for example, the configuration of the drilling system 100a may be altered. The configuration may be altered such that the drilling system 100a can drill through the lithology of the formation 105a or such that the drilling system 100a is guided by an updated wellbore path that goes around the lithology of the formation 105a. In other embodiments, the environment 105 that the machine 100 operates within is altered.
[0061] If the measure of similarity indicates noise, the signal 200a, b or transformed signal 300a, b is updated by removing the signal 200a, b or transformed signal 300a, b within the outlier window 405. In some embodiments, the signal 200a, b or transformed signal 300a, b is updated until all noise within the signal 200a, b or transformed signal 300a, b is removed.
[0062] FIG. 6 illustrates a signal processing system 165 in accordance with one or more embodiments. The signal processing system 165 may be used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures as described in this disclosure, according to one or more embodiments. The illustrated signal processing system 165 is intended to encompass any computing device such as a server, desktop computer, laptop / notebook computer, wireless data port, smart phone, personal data assistant (PDA) , tablet computing device, one or more processors within these devices, or any other suitable processing device, including both physical or virtual instances (or both) of the computing device. Additionally, the signal processing system 165 may include a computer that includes an input device, such as a keypad, keyboard, touch screen, or other device that can accept user information, and an output device that conveys information associated with the operation of the signal processing system 165, including digital data, visual, or audio information (or a combination of information) , or a GUI.
[0063] The signal processing system 165 can serve in a role as a client, network component, a server, a database or other persistency, or any other component (or a combination of roles) of a computer system for performing the subject matter described in the instant disclosure. The illustrated signal processing system 165 is communicably coupled with a network 605. In some implementations, one or more components of the signal processing system 165 may be configured to operate within environments, including cloud-computing-based, local, global, or other environment (or a combination of environments) . Further, in some embodiments, the signal processing system 165 may be communicably coupled to the DAQ 160 and / or sensor 155.
[0064] At a high level, the signal processing system 165 is an electronic computing device operable to receive, transmit, process, store, or manage data and information associated with the described subject matter. According to some implementations, the signal processing system 165 may also include or be communicably coupled with an application server, e-mail server, web server, caching server, streaming data server, business intelligence (BI) server, or other server (or a combination of servers) .
[0065] The signal processing system 165 can receive requests over network 605 from a client application (for example, executing on another signal processing system 165) and responding to the received requests by processing the said requests in an appropriate software application. In addition, requests may also be sent to the signal processing system 165 from internal users (for example, from a command console or by other appropriate access method) , external or third-parties, other automated applications, as well as any other appropriate entities, individuals, systems, or computers.
[0066] Each of the components of the signal processing system 165 can communicate using a system bus 610. In some implementations, any or all of the components of the signal processing system 165, both hardware or software (or a combination of hardware and software) , may interface with each other or the interface 615 (or a combination of both) over the system bus 610 using an application programming interface (API) 620 or a service layer 625 (or a combination of the API 620 and service layer 625. The API 620 may include specifications for routines, data structures, and object classes. The API 620 may be either computer-language independent or dependent and refer to a complete interface, a single function, or even a set of APIs. The service layer 625 provides software services to the signal processing system 165 or other components (whether or not illustrated) that are communicably coupled to the signal processing system 165. The functionality of the signal processing system 165 may be accessible for all service consumers using this service layer. Software services, such as those provided by the service layer 625, provide reusable, defined business functionalities through a defined interface. For example, the interface may be software written in JAVA, C++, or other suitable language providing data in extensible markup language (XML) format or another suitable format. While illustrated as an integrated component of the signal processing system 165, alternative implementations may illustrate the API 620 or the service layer 625 as stand-alone components in relation to other components of the signal processing system 165 or other components (whether or not illustrated) that are communicably coupled to the signal processing system 165. Moreover, any or all parts of the API 620 or the service layer 625 may be implemented as child or sub-modules of another software module, enterprise application, or hardware module without departing from the scope of this disclosure.
[0067] The signal processing system 165 includes an interface 615. Although illustrated as a single interface 615 in FIG. 6, two or more interfaces 615 may be used according to particular needs, desires, or particular implementations of the signal processing system 165. The interface 615 is used by the signal processing system 165 for communicating with other systems in a distributed environment that are connected to the network 605. Generally, the interface 615 includes logic encoded in software or hardware (or a combination of software and hardware) and operable to communicate with the network 605. More specifically, the interface 615 may include software supporting one or more communication protocols associated with communications such that the network 605 or interface's hardware is operable to communicate physical signals within and outside of the illustrated signal processing system 165.
[0068] The signal processing system 165 includes at least one computer processor 630. Although illustrated as a single computer processor 630 in FIG. 6, two or more processors may be used according to particular needs, desires, or particular implementations of the signal processing system 165. Generally, the computer processor 630 executes instructions and manipulates data to perform the operations of the signal processing system 165 and any algorithms, methods, functions, processes, flows, and procedures as described in the instant disclosure.
[0069] The signal processing system 165 also includes a memory 635 that holds data for the signal processing system 165 or other components (or a combination of both) that can be connected to the network 605. For example, the memory 635 may store a planning system 640 further described relative to FIG. 7. Although illustrated as a single memory 635 in FIG. 6, two or more memories 635 may be used according to particular needs, desires, or particular implementations of the signal processing system 165 and the described functionality. While memory 635 is illustrated as an integral component of the signal processing system 165, in alternative implementations, memory 635 can be external to the signal processing system 165.
[0070] The application 645 is an algorithmic software engine providing functionality according to particular needs, desires, or particular implementations of the signal processing system 165, particularly with respect to functionality described in this disclosure. For example, application 645 can serve as one or more components, modules, applications, etc. Further, although illustrated as a single application 645, the application 645 may be implemented as multiple applications 645 on the signal processing system 165. In addition, although illustrated as integral to the signal processing system 165, in alternative implementations, the application 645 can be external to the signal processing system 165.
[0071] There may be any number of signal processing systems 165 associated with, or external to, a computer system containing a signal processing system 165, wherein each signal processing system 165 communicates over network 605. Further, the term “client, ” “user, ” and other appropriate terminology may be used interchangeably as appropriate without departing from the scope of this disclosure. Moreover, this disclosure contemplates that many users may use one signal processing system 165, or that one user may use multiple signal processing systems 165.
[0072] FIG. 7 describes a system 700 in accordance with one or more embodiments. In some embodiments, the system 700 may include the machine 100 that the signal 200a, b is associated with. In some embodiments, the system 700 may include the sensor 155 configured to collect (i.e., detect and record) the signal 200a, b associated with the machine 100 operating within the environment 105. The sensor 155 may be an element of the machine 100, configured to attach to the machine 100, configured to attach to the environment 105, or external to the machine 100 and / or environment 105. In some embodiments, the signal 200a, b may be transferred to, stored on, and / or processed by the signal processing system 165 previously described relative to FIG. 6. In some embodiments, the signal 200a, b may be transferred from the sensor 155 to the signal processing system 165 via the network 605. The signal processing system 165 may perform steps 500, 505, 510, 515, and 520 previously described relative to FIG. 5.
[0073] If the measure of similarity determined in step 520 indicates a malfunction of the machine 100, the signal processing system 165 may be configured to cause a machine maintenance system 705 to maintain the machine 100. The machine maintenance system 705 is configured to maintain the machine 100 based, at least in part, on the malfunction. For example, assume the machine 100 is a drill bit 145 and the drill bit 145 malfunctions. In these embodiments, the machine maintenance system 705 may include subcombinations of the drilling system 100a, such as the drill rig 115 and drillstring 120, configured to retrieve the BHA 125 from downhole within the wellbore 110 within the formation 105a. Further, the machine maintenance system 705 may include a new drill bit. Further still, the machine maintenance system 705 may include any tools necessary to remove the malfunctioning drill bit 145 from the BHA 125 and attach the new drill bit to the BHA 125. The drill rig 115 and drillstring 120 of the drilling system 100a may then deploy the BHA 125 with the new drill bit downhole within the wellbore 110 within the formation 105a.
[0074] If the measure of similarity determined in step 520 indicates a property of the environment 105, the signal processing system 165 may be configured to cause a planning system 640 to alter a configuration of the machine 100. The planning system 640 is configured to alter a configuration of the machine 100 based, at least in part, on the property. For example, assume the machine 100 is a drilling system 100a and the property of the environment 105 is a change in lithology that indicates a fault within the formation 105a. In these embodiments, the planning system 640 may be a wellbore planning system configured to update a wellbore path such that the drilling system 100a is guided by an altered wellbore path that avoids the fault. In other embodiments, the planning system 640 may be a wellbore planning system configured to update the weight-on-bit or rotational speed of a drill bit 145 to accommodate the change in lithology.
[0075] If the measure of similarity determined in step 520 indicates a property of the environment 105, the signal processing system 165 may be configured to cause the environment 105 may be altered. For example, assume the environment 105 is a formation 105a and the property of the environment 105 is sandstone. In these embodiments, a hydraulic fracturing system may be configured to alter the environment 105 by inducing hydraulic fractures within the sandstone of the formation 105a.
[0076] If the measure of similarity determined in step 520 indicates noise, the signal processing system 165 may be further configured to update the signal 200a, b or transformed signal 300a, b by removing the signal 200a, b or transformed signal 300a, b within each outlier window 405 that contains the noise.
[0077] Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications are possible in the example embodiments without materially departing from this invention. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims.
Claims
1.A method comprising:obtaining, from a sensor, a signal associated with a machine operating within an environment,wherein the signal comprises a first amplitude at each of a plurality of time samples;organizing, using a signal processing system, the signal into a plurality of windows;determining, using the signal processing system, a measure of variability for each of the plurality of windows using the signal within each of the plurality of windows;identifying, using the signal processing system, one or more outlier windows among the plurality of windows based, at least in part, on the measure of variability for each of the plurality of windows; andfor each outlier window among the one or more outlier windows:determining, using the signal processing system, a measure of similarity between the signal within each outlier window and each of a plurality of reference signals,wherein each of the plurality of reference signals is characteristic of a function of the machine, a property of the environment, or a noise, andat least one of:maintaining, using a machine maintenance system, the machine based, at least in part, on the measure of similarity and the function, wherein the function comprises a malfunction;altering, using a planning system, a configuration of the machine based, at least in part, on the measure of similarity and the property;altering the environment based, at least in part, on the measure of similarity and the property; andupdating, using the signal processing system, the signal by removing the signal within each outlier window based, at least in part, on the measure of similarity and the noise.2.The method of claim 1, wherein the signal comprises a measure of a vibration of the machine.3.The method of claim 1, wherein the machine operating within the environment comprises a drilling system drilling a wellbore within a formation guided by a wellbore path.4.The method of claim 3, wherein the drilling system comprises a drill bit.5.The method of claim 3, wherein the property of the environment comprises a lithology of the formation.6.The method of claim 4, wherein the function of the machine comprises the malfunction of the drill bit.7.The method of claim 6, wherein maintaining the machine comprises:stopping the drilling system;retrieving the drilling system, at least in part, from the wellbore;replacing the drill bit of the drilling system with a new drill bit;deploying the drilling system comprising the new drill bit within the wellbore; andstarting the drilling system.8.The method of claim 3, wherein updating the configuration of the machine comprises updating, using a wellbore planning system, the wellbore path based, at least in part, on a lithology of the formation.9.The method of claim 1, wherein the measure of variability comprises variance.10.The method of claim 1, wherein identifying the one or more outlier windows is further based on a threshold.11.The method of claim 10, wherein the threshold comprises a percentile threshold.12.The method of claim 1, wherein the measure of similarity comprises cross correlation.13.The method of claim 1, wherein organizing the signal comprises determining, using a transform, a transformed signal from the signal.14.A system comprising:a sensor configured to collect a signal associated with a machine operating within an environment,wherein the signal comprises a first amplitude at each of a plurality of time samples; anda signal processing system configured to:organize the signal into a plurality of windows,determine a measure of variability for each of the plurality of windows using the signal within each of the plurality of windows,identify one or more outlier windows among the plurality of windows based, at least in part, on the measure of variability for each of the plurality of windows, andfor each outlier window among the one or more outlier windows:determine a measure of similarity between the signal within each outlier window and each of a plurality of reference signals,wherein each of the plurality of reference signals is characteristic of a function of the machine, a property of the environment, or a noise; andat least one of:cause a machine maintenance system to maintain the machine based, at least in part, on the measure of similarity and the function, wherein the function comprises a malfunction,cause a planning system to alter a configuration of the machine based, at least in part, on the measure of similarity and the property,cause an altered environment for the machine to operate within based, at least in part, on the measure of similarity and the property, andupdate the signal by removing the signal within each outlier window based, at least in part, on the measure of similarity and the noise.15.The system of claim 14, further comprising the machine configured to operate within the environment.16.The system of claim 14, wherein the machine operating within the environment comprises a drilling system drilling a wellbore within a formation guided by a wellbore path.17.The system of claim 16, wherein the drilling system comprises a drill bit.18.The system of claim 14, further comprising the machine maintenance system.19.The system of claim 14, further comprising the planning system.20.The system of claim 16, wherein the planning system comprises a wellbore planning system configured to update the wellbore path based, at least in part, on a lithology of the formation.
Citation Information
Patent Citations
Method and system for identifying impact feature based on sound or vibration signal
CN110160765A
Instability Detection and Correction in Sinusoidal Active Noise Reduction System
US20150055787A1
Devices and Methods for Transmitting and Receiving in an Optical Communications System
US20180145762A1
Method for measuring surface torque oscillation performance index
US20190187012A1
Machine learning to predict bolt tension
WO2023168371A2