WO2019017977A1

WO2019017977A1 - Formation change detection with adaptive threshold based sta-lta method

Info

Publication number: WO2019017977A1
Application number: PCT/US2017/043404
Authority: WO
Inventors: Ravigopal Vennelakanti; Anshuman SAHU; Iwao TANUMA; Christophe LOTH
Original assignee: Hitachi, Ltd.
Priority date: 2017-07-21
Filing date: 2017-07-21
Publication date: 2019-01-24

Abstract

Example implementations of the present disclosure are directed to systems and methods for drilling analyses for upstream oil and gas operations, in particular, to determining formation change points of a well. Example implementations provided herein are directed to providing systems and methods for determining the formation change points in real time, thereby automating part of the drilling analysis and avoiding costly manual errors.

Description

FORMATION CHANGE DETECTION WITH ADAPTIVE THRESHOLD BASED

STA-LTA METHOD

BACKGROUND Field

[0001] The present disclosure relates generally to oil and gas data analytics, and more specifically, to detecting changes in formation features based on data collected during the drilling phase.

Related Art

[0002] In the related art, oil and gas rigs utilize computerized systems to assist the operators of the rigs throughout the different phases of the oil or gas rigs (e.g., exploration, drilling, production, completions). Such computer systems are deployed for the development of energy sources such as shale gas, oil sands, and deep water resources. In the related art, attention has shifted to the development of shale gas for supplying future energy needs. Related art advances in horizontal directional drilling and hydraulic fracturing technologies have unlocked the potential for recovering natural gas from shale to become a viable energy source.

[0003] However, maximizing output from an oil and gas reservoir, particularly shale gas reservoirs, can be difficult, even with the assistance from present computer systems. The process of making production decisions and sizing top-side facilities is oftentimes a manual process that depends on the judgment of the rig operator. Furthermore, operators often struggle with real-time performance of support for down-hole gauges, semi-submersible pumps, and other equipment. Non-Productive Time (NPT) for a rig may constitute over 30% of the cost of drilling operations.

[0004] One aspect of the issue of output maximization is the lack of effective data processing and data analytics, along with the sheer volume of data received from oil and gas wellsites. The data sets obtained from different upstream processes can be substantial in terms of number of available attributes. Manually developing applications that utilize these attributes can be very time-consuming. [0005] The identification of formation tops has been a well-known and long-standing problem in the oil and gas industry, and methods to identify formation tops have been often taught in universities for petroleum engineering (see, for example, J. Toro, Introduction to Petroleum Geology, University of West Virginia, Spring 2015, http://pages.geo.wvu.edu/~jtoro/Petroleum/). In particular, the detection of formation tops in a well during the drilling phase is oftentimes conducted manually by drilling experts in the oil and gas domain, or based on techniques involving log data as described, for example in J. Toro, Formation Evaluations: Well Logs, University of West Virginia, Spring 2015, as well as W.H. Fertl, Abnormal Formation Pressures, pgs. 102-112, 1976. Detecting changes in formation while drilling is critical for appropriate casing to avoid downtime which can cost time and resources. Further, accurate formation characterizations depend on determining the formation change points in an accurate and timely manner. Failure to detect such change points in a timely manner can cause the drilling operations to continue under erroneous drilling parameters, causing delay and possible mismanagement or unneeded wear of drilling equipment.

[0006] To remove the manual aspect of determining formation changes, several algorithmic related art implementations have been proposed. One example related art implementation involves a Bayesian online changepoint detection system as described, for example, in "Bayesian Online Changepoint Detection" by Ryan P. Adams and David J.C. MacKay, University of Cambridge 2007. Through the application of Bayesian online changepoint detection algorithm to well-log data such as nuclear magnetic response, changepoints can be provided for a given well with predictive error bars.

[0007] Another example related art implementation involves applying Hadoop based analytics, which involves consolidating datasets such as LAS files, production records, well header files, and auction histories into a modern data architecture, as described, for example, at The Adoption of Hadoop and Advanced Analytics Accelerates in Oil and Gas, K. Kohlleffel, May 15, 2015. Such related art implementations can facilitate streamlined access to the data, and also provide analytics to enable feature vectors and pick formation tops to compute the percentage of the zone that has the desired payload. SUMMARY

[0008] However, the aforementioned related art solutions are directed to determining formation changes based on processed log data or based on sensor measurements that are obtained while drilling is suspended, and do not provide any real time or automated solutions for determining formation changes while drilling is conducted. The present disclosure is directed to an automated system and method for detecting changes in formation given the data features collected while drilling in real time.

[0009] Aspects of the present disclosure can include a management server configured to manage one or more wells. The management server may include a memory, configured to store sensor data of the one or more wells; and a processor, configured to determine first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determine second values of the one or more wells from a selection of ones of the first values that meet a threshold; determine, from the second values, third values representative of formation change points of the one or more wells, and determine formation characterizations of the one or more wells based on the third values.

[0010] Aspects of the present disclosure can further include a method to manage one or more wells, which can include storing sensor data of the one or more wells; determining first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determining second values of the one or more wells from a selection of ones of the first values that meet a threshold; determining, from the second values, third values representative of formation change points of the one or more wells, and determining formation characterizations of the one or more wells based on the third values.

[0011] Aspects of the present disclosure can further include a computer program for managing one or more wells, the computer program having instructions which can include storing sensor data of the one or more wells; determining first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determining second values of the one or more wells from a selection of ones of the first values that meet a threshold; determining, from the second values, third values representative of formation change points of the one or more wells, and determining formation characterizations of the one or more wells based on the third values. The computer program may be stored in a non-transitory computer readable medium and executed by one or more processors.

BRIEF DESCRIPTION OF DRAWINGS

[0012] FIG. 1 illustrates a system involving a plurality of rig systems and a management server, in accordance with an example implementation.

[0013] FIG. 2 illustrates an example timeline for a rig system, in accordance with an example implementation.

[0014] FIG. 3 illustrates an example configuration of a rig system, in accordance with an example implementation.

[0015] FIG. 4 illustrates a configuration of a management server, in accordance with an example implementation.

[0016] FIG. 5 illustrates an example drilling system in accordance with an example implementation.

[0017] FIG. 6 illustrates an example screenshot for the User Interface (UI) layer, in accordance with an example implementation.

[0018] FIG. 7 illustrates a flow diagram for determining well formations, in accordance with an example implementation.

[0019] FIGS. 8(a) and 8(b) illustrate an example of utilization of gamma ray data for determining change points, in accordance with an example implementation.

[0020] FIG. 9 illustrates an example STA/LTA approach as applied to the well log data, in accordance with an example implementation.

[0021] FIG. 10 illustrates a flow diagram for determining change points, in accordance with an example implementation. [0022] FIG. 11 illustrates an example of change point capture, in accordance with an example implementation.

[0023] FIGS. 12(a) and 12(b) illustrate example threshold for STA/LTA ratio measurements, in accordance with an example implementation.

[0024] FIG. 13 illustrates an example threshold implementation, in accordance with an example implementation.

[0025] FIGS. 14(a) to 14(c) illustrate example management information in accordance with an example implementation.

[0026] FIG. 15 illustrates a flow diagram for rig management, in accordance with an example implementation.

DETAILED DESCRIPTION

[0027] The following detailed description provides further details of the figures and example implementations of the present application. Reference numerals and descriptions of redundant elements between figures are omitted for clarity. Terms used throughout the description are provided as examples and are not intended to be limiting. For example, the use of the term "automatic" may involve fully automatic or semi-automatic implementations involving user or administrator control over certain aspects of the implementation, depending on the desired implementation of one of ordinary skill in the art practicing implementations of the present application. The term "rig" and "well" may also be used interchangeably. "Rig systems" and "wellsites" may also be utilized interchangeably.

[0028] FIG. 1 illustrates a system involving a plurality of rig systems and a management server, in accordance with an example implementation. One or more rig systems 101-1, 101- 2, 101-3, 101-4, and 101-5 can each involve a corresponding rig 200-1, 200-2, 200-3, 200-4, 200-5 as illustrated in FIG. 5 along with a corresponding rig node 300-1, 300-2, 300-3, 300-4, and 300-5 as illustrated in FIG. 3. Each of the rig systems 101-1, 101-2, 101-3, 101-4, and 101-5 is connected to a network 100 which is connected to a management server 102. The management server 102 manages a database 103, which contains data aggregated from the rig systems in the network 100. In alternate example implementations, the data from the rig systems 101-1, 101-2, 101-3, 101-4, and 101-5 can be aggregated to a central repository or central database such as public databases that aggregate data from rigs or rig systems, such as for government compliance purposes, and the management server 102 can access or retrieve the data from the central repository or central database.

[0029] FIG. 2 illustrates an example timeline for a rig system, in accordance with an example implementation. The timeline for the rig system 101 may include multiple phases of rig operation. These phases can include (but are not limited to) an exploration phase, a drilling phase, a completions phase, a production phase, a processing phase and a pipeline phase. In the following description, the term "process" may also be used interchangeably with the term "phase". Example implementations may involve data or attributes associated with one or more of the phases of the timeline, depending on the desired implementation.

[0030] During the exploration phase, the well is initially drilled to determine whether reservoirs with oil or gas are present and the initial construction of the rig. In example implementations described herein, the rig node may be configured to assist the user in determining how to configure the rig and the parameters for the drilling during the exploration phase.

[0031] The drilling phase follows the exploration phase as determined in the exploration phase, e.g., if promising amounts of oil and gas are confirmed from the exploration phase. During the drilling phase, the size and characteristics of the discovery are determined and technical information is utilized to allow for more optimal methods for recovery of the oil and gas. An appraisal drilling can be performed and a rig is established. In example implementations described herein, the rig node may be configured to assist the user in determining appropriate parameters for the drilling and assist in the management and obtaining of desired characteristics for the rig.

[0032] The completions phase is directed to the determination as to whether the well should be completed as a well, or whether it should be abandoned as a dry hole. The completion phase transforms the drilled well into a producing well. During this phase, the casing of the rig may be constructed, along with the perforations. Various aspects of the construction of the rig, such as cementing, gravel packing and production tree installation may be employed. Sensors may be employed to determine various parameters for facilitating the completion of the rig, such as rate of flow, flow pressure and gas to oil ratio measurements, but not limited thereto. [0033] The production phase follows the completions phase and is directed to the facilitation of production of oil or gas. The production phase includes the operation of wells and compressor stations or pump stations, waste management, and maintenance and replacement of facility components. Sensors may be utilized to observe the above operations, as well as determining environmental impacts from parameters such as sludge waste accumulation, noise, and so on. Example implementations described herein may provide feedback to rig system operators to maximize the production of the rig based on the use of model signatures.

[0034] During the processing and pipelining phase, the produced oil or gas is processed and transferred to refineries through a pipeline.

[0035] Example implementations of the present disclosure are directed to aspects regarding the drilling phase for the rig system. In the example implementations described herein, change points of a drilling formation can be determined, which can be used to as a comparison to drilling parameters of the drilling system as described herein.

[0036] FIG. 3 illustrates an example configuration of a rig system 101, in accordance with an example implementation. The rig system 101 includes a rig 200 as illustrated in FIG. 5 which contains a plurality of sensors 210. The rig system 101 includes a rig node 300 which may be in the form of a server or other computer device and can contain a processor 301, a memory 302, a storage 303, a data interface (I/F) 304 and a network I/F 305. The data I/F 304 interacts with the one or more sensors 210 of the rig 200 and store raw data in the storage 303, which can be sent to a management server for processing, or to a central repository or central database. The network I/F 305 provides an interface to connect to the network 100.

[0037] FIG. 4 illustrates a configuration of a management server 102, in accordance with an example implementation. Although the example implementation for apparatuses is described as management server 102, other implementations are also possible depending on the desired implementation. Management server 102 may involve a processor 401, a memory 402, a storage I/F 404 and a network I/F 405. The processor 401 is configured to execute one or more programs in the memory 402, to process data and for calculating composite similarity scores. The storage I/F 404 is the interface to facilitate connections between the management server 102 and the database 103. The network I/F 405 facilitates interactions between the management server 102 and the plurality of rig systems. Data is aggregated to the management server by the network I/F and then subsequently stored in the database, for example, for future analytics. Alternatively, the plurality of rig systems may send the data to a central database or repository, which is then processed by the management server 102. Management server 102 may execute a process for managing the one or more wells by using programs stored in memory 402 and executed by processor 401, and transmitting or receiving information to or from the respective rig systems of the one or more wells to assist or affect the control or management of the well operations.

[0038] In an example implementation memory 402 is configured to store sensor data of the one or more wells; and processor 401 is configured to determine first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well. In example implementations the first window can represent a window over a range of sensor data that has been stored in memory 402, either as historical data from a database or as accumulated from previously live or streamed data that is stored for longer term analysis. The first window can have a first range of depth values which is set based on the desired implementation for a batch window of sensor values (e.g. historical sensor data accumulated over 1000 meters for one or more wells). The second window can represent a window over a range of sensor data that has been received by the management server 102 for live or stream processing. In an example implementation, the second window can have a second range that can be equal to or shorter than the first range of depth values which is set based on the desired implementation for a live or streaming window of sensor values (e.g. values accumulated as received from one or more wells or from the database up to a particular depth (e.g. 0.5 m)). In example implementation the first window of the sensor data is conducted as a batch process on the sensor data stored in the memory, and the second window of the sensor data is conducted as a streaming process on the sensor data streamed from the one or more wells.

[0039] The first values can involve any desired calculation involving the comparison of the sensor data in the first window with the second window, such as ratios of the sensor values directly, the ratios of the averages of the values within the respective windows, and so on. For example, the first window of the sensor data can be represented as first average of the sensor data across the first range of depth values, and the second window of the sensor data can be represented as a second average of the sensor data across the second range of depth values. In additional example implementations, the first range is larger than the second range in the case where the first window is used as a longer term snapshot of the sensor data, and the second window is used as the live or shorter term snapshot of the sensor data. Such an example implementation can include having the long term average being represented by the first window, and the short term average being the second window, and where the first values are the ratio between the short term average and the long term average as described, for example, in FIG. 10.

[0040] In example implementations, processor 401 can be configured to determine second values of the one or more wells from a selection of ones of the first values that meet a threshold. The threshold can be a static threshold set by the operator of the management server 102 in accordance with the desired implementation, or through algorithms as described, for example, in FIG. 12(b) and FIG. 13. In an example implementation as described in further detail in FIG. 12(b) and FIG. 13, the processor 401 is configured to adjust the threshold for a given depth based on a first maximum value within the first window of the sensor data up to the given depth and a second maximum value within the second window of the sensor data up to the given depth; and is configured to update the threshold upon a lesser of the first maximum value and the second maximum value exceeding the previous threshold. Further, the processor 401 can be configured to, for the lesser of the first maximum value and the second maximum value not exceeding the threshold, update the threshold based on an average of the threshold and a greater of the first maximum value and the second maximum value as described in FIG. 12(b) and FIG. 13.

[0041] In an example implementation as described in further detail in FIG. 12(b) and FIG. 13, the processor 401 is configured to adjust another threshold for a given depth based on a first minimum value within the first window of the sensor data up to the given depth and a second minimum value within the second window of the sensor data up to the given depth; and is configured to update the threshold upon a greater of the first minimum value and the second minimum value falling below the previous threshold. Further, the processor 401 can be configured to, for the greater of the first minimum value and the second minimum value not falling below the threshold, update the threshold based on an average of the threshold and a lesser of the first minimum value and the second minimum value as described in FIG. 12(b) and FIG. 13. The maximum and minimum thresholds can be used in singular or in combination with each other as illustrated in FIG. 13. [0042] When the second values are obtained, third values can be selected from the second values that are representative of the formation change points of the one or more wells. Third values can be determined from post-processing methods such as the methods as described in FIG. 10 and FIG. 15, or can include all the second values depending on the desired implementation. The corresponding depth values of the third values can then be used as the formation change points. Once the formation change points are determined, processor 401 can be configured to determine formation characterizations of the one or more wells based on the third values by referencing the corresponding depth values as the change points and then running any algorithm to determine the formation characterizations depending on the desired implementation. In example implementations the processor 401 can update formation change points of the one or more wells with the third values, thereby providing a more accurate map of the formation of the well.

[0043] In example implementations, the first window of the sensor data is conducted as a batch process on the sensor data stored in the memory, and the second window of the sensor data is conducted as a streaming process on the sensor data streamed from the one or more wells.

[0044] In example implementations, the sensor data includes gamma ray data streamed from the one or more wells or streamed from a centralized database as illustrated in FIG. 9. The first window can be configured to be measured as a batch process, wherein streamed data is subsequently stored for later analysis and processed once sufficient data to fall within the first range (e.g., across a depth of 100 meters) is accumulated. The second window can be determined through processing the streamed gamma ray data through a streaming process, which can involve a cache and processors for processing the data in real-time as it is received, or after sufficient data to fall within the range (e.g. across a depth of 0.5 meters) is accumulated. Data can be streamed directly from rig systems of the one or more wells or from the centralized database through an internet connection, a dedicated wired connection, or by other methods depending on the desired implementation. Although the examples provided herein are directed to gamma ray, the present disclosure is not limited thereto and other data can be utilized according to the desired implementation. For example, the method can extend to other sensor data such as acoustic impedance, reflection coefficient, resistivity, porosity, and so on. [0045] In example implementations, once the formation change points are determined, the change points of the rig node can be updated with the determined change points. Once the change points are determined or updated, the operator of the drilling operations can update the drilling operations based on the determined change points. For example, the table of FIG. 14(b) may be updated to reflect change points as determined from example implementations. Through the use of the updated change points, a more accurate characterization of the well formation can be achieved, and drilling parameters can be adjusted based on the update in change points while drilling operations are ongoing.

[0046] FIG. 5 illustrates an example drilling system in accordance with an example implementation. Specifically, FIG. 5 illustrates an example rig 200 in accordance with an example implementation. The example implementation depicted in FIG. 5 is directed to a shale gas rig. However, similar concepts can be employed at other types of rigs as well without departing from the inventive scope of the present disclosure, for example, example implementations described herein can also be applied to horizontal oil wells by integrating features from multiple upstream processes. The rig 200 may include a drilling system 201 which is configured to conduct drilling operations in accordance with parameters configured according to the change point of the formations of the well. Tubing 201-2 is configured to extract gas from the well 201. The rig 200 may include a case 202 which can involve a pipe constructed within the borehole of the well. One or more packers 204 can be employed to isolate sections of the well 201.

[0047] As illustrated in FIG. 5 various sensors may be applied throughout the rig to measure various data or attributes for a rig node, which are described in further detail below. The sensors are identified by an "S" in an octagon in FIG. 5, and are configured to provide sensor data for drilling operations (e.g., gamma ray, depth, etc.). These sensors provide feedback to the rig node which can interact with the system as illustrated in FIG. 1, and can be fed to the management server 102 for database storage 103, and/or supplied to a central repository or database such as a public database, which can then be harvested by management server 102.

[0048] FIG. 6 illustrates an example of the User Interface (UI) layer of a management server, in accordance with an example implementation. Example implementations facilitate a mechanism for visualization of well formations. In the example user interface of FIG. 6, there is a visualization pane that is configured to provide (e.g. display) visualization of a map showing the type of well formation over the depth of a well, in accordance with an example implementation. Each of the formations can be determined from data processed according to example implementations while rigs are conducting drilling. Each well visualization can be implemented in the form of a well file which can involve formation tops and other information in accordance with the desired implementation, as well as the actual readings from several variables. Such variables can be related to different characteristics such as mechanical (e.g., Rate of penetration, weight on bit); lithology (e.g., gamma ray reading, resistivity); and total gas content. Example implementations utilize the information about different process characteristics, and understand their relationship to the corresponding formation. In the example of FIG. 6, the formation composition is classified according to the detected type of formation (e.g., LI, L2, L3, L4, L5, L6, L7, L8) across the depth of the well, and a map of the formation is provided.

[0049] FIG. 7 illustrates a flow diagram for determining well formations, in accordance with an example implementation. At 701, well logs are processed for Gamma Ray readings over the depth of the well. At 702, the Gamma Ray readings from wells are processed to detect change points in well formations. In example implementations, the Gamma Ray readings are processed through a modified short term averaging (STA)/long term averaging (LTA) algorithm with adaptive thresholds to determine the change points in Gamma Ray readings. The change points are further processed using three post-processing techniques: index-based, depth-based, and cluster-based on nearest neighbors. The above approach can be utilized to provide faster analysis in near real-time, and serves as a baseline for further analysis for feedback into the drilling system to manage drilling operations. At 703, the well formation mapping is determined from the change points and the Gamma Ray readings to produce the visualization as illustrated in FIG. 6.

[0050] FIGS. 8(a) and 8(b) illustrate an example of utilization of gamma ray data for determining change points, in accordance with an example implementation. In the example of FIG. 8(a) and 8(b), gamma ray data is utilized to understand the relationship with formation change. Given the gamma ray readings, example implementations are configured to identify the change points. To determine the correspondence of the change points to the actual identified formation tops of the well, the actual formation tops of FIG. 8(a) are utilized as a baseline for comparison with the change points derived from the drilling information of FIG. 8(b). [0051] In example implementations, the change points are identified and evaluated by using the STA/LTA ratio approach. FIG. 9 illustrates an example STA/LTA ratio approach as applied to the well log data, in accordance with an example implementation. The STA is computed over a window of shorter duration while LTA is computed over a window of longer duration. In the example implementation of FIG. 9, localized changes are identified in the data using the ratio of STA and LTA (STA/LTA). The STA captures short-term behavior of the signal while LTA captures the longer-term behavior. When the signal changes, the example implementations can capture the changes through a comparison of the STA/LTA ratio with a threshold.

[0052] In example implementations, at each depth for the gamma ray data, two windows are taken, the short-term window and the long-term window. The ratio of the average value of the reading in the short term window (STA) and the long term window (LTA) are taken, and the lengths of the window are adjusted by the well operator according to the desired implementation.

[0053] FIG. 10 illustrates a flow diagram for determining change points, in accordance with an example implementation. At 1001, the ratio of STA and LTA values across the depth of the well are calculated. At 1002, the set of data points whose values are over/below the upper/lower threshold are collected for post-processing. An example of change point capturing is provided in FIG. 11 and its description below. Thresholds can be applied to the ratio of STA and LTA values as described in FIG. 12(a) and 12(b) and its description below.

[0054] At 1003, successive points in the set are placed into post-processing for determining the change point. In example implementations, various post-processing techniques can be considered for merging the set of successive points to determine the change point. In an example implementation, the post-processing technique can be index based wherein adjacent indices are merged together to form the change point. In another example implementation, the post-processing technique can be depth based, wherein a threshold depth is determined and the points within the given threshold depth are merged together to form the change point. In another example implementation, the points can be clustered based on the distance between the nearest neighbor points.

[0055] The lengths of the short term frame and the long term frame can be adjusted by the well operator according to the desired implementation. In an example implementation, the detected points can be compared with known historical formation change points as recorded by domain operators (e.g. geologists).

[0056] FIG. 11 illustrates an example of change point capture, in accordance with an example implementation. Specifically, FIG. 11 illustrates a graph plot of the ratio of STA and LTA over the depth of the well. The highlighted portion indicates the set of data points whose values exceed a threshold. In the example of FIG. 11, the set of data points collected are the values that exceed the upper threshold, however, other implementations may also involve collecting the set of data points that are below a lower threshold and/or above a higher threshold, depending on the desired implementation. Successive points in the set of collected data points are then post-processed in accordance with the flow at 1003 at FIG. 10. Thus, change points are obtained based on a threshold as applied to the STA/LTA ratio. As illustrated in FIG. 11, a threshold is applied to capture a set of points that exceed the threshold. In the example of FIG. 11, the first point to meet the threshold is used as the representative change point, wherein subsequent points beyond the threshold are captured by the flow at 1003.

[0057] FIGS. 12(a) and 12(b) illustrate example threshold for STA/LTA ratio measurements, in accordance with an example implementation. Specifically, FIG. 12(a) illustrates an example threshold configuration based on a single global threshold. As illustrated in FIG. 12(a), a single global threshold can be applied, wherein the STA/LTA ratio exceeding the single global threshold are captured to determine change points. However, as illustrated in FIG. 12(a), a single global threshold may fail to capture local peaks in the STA/LTA ratio measurements.

[0058] Thus, in example implementations, the threshold can also be derived through adaptive threshold configuration techniques for capturing local peaks. FIG. 12(b) illustrates an example threshold configuration based on an adaptive threshold approach, in accordance with an example implementation. The adaptive threshold approach adopts to the STA/LTA ratio measurements to determine local peaks. Thus, as illustrated in FIG. 12(b), the adaptive threshold approach captures the local peaks that a single global threshold may otherwise be unable to capture.

[0059] FIG. 13 illustrates an example threshold implementation, in accordance with an example implementation. Specifically, FIG. 13 illustrates an example of the minimum and maximum thresholds. To initialize the adaptive threshold, let the initialization begin with depth index i = LT + ST. That is, the depth index i is set to the length of the long term frame and the short term frame as defined by the operator in accordance with the desired implementation.

[0060] The threshold is then set as the average of the maximum values within the long term frame and the short term frame and is expressed as follows: threshold, = avg max(z^') ,

[0061] ^{1 ώ J} wherein

, max( LT frame , ) + max( ST frame , )

s.t. avg max( i) = — - — —

[0062] ²

[0063] Once the depth exceeds the aggregate of the long term frame and the short term frame (i > LT + ST), the threshold is updated according to the values received. A check is performed to determine if the lesser value of the maximum within the short term frame and the long term frame exceeds the previously set threshold. If so, then the threshold is updated to the lesser value, otherwise, the threshold is set to the average of the previous threshold, the maximum value within the short term frame and the maximum value within the long term frame. The expression is as follows:

[0064] If min(max(ST frame i), max (LT frame i)) > threshold^_! then threshold _i = avg max(z^')

[0065] threshold + max(STframe . + LTframe_i)

threshold . =

[0066] Else 2

[0067] As illustrated in FIG. 13, a minimum threshold may also be utilized. The threshold is set as the average of the minimum values within the long term frame and the short term frame and is expressed as follows:

[0068] threshold , = avg min( i) _wherein

. . .. min( LT frame , ) + min( ST frame , )

s.t. avg min( z) = — — —

[0069] 2 [0070] The minimum threshold may also be updated similarly to the maximum threshold, as follows:

[0071] If max (min(ST frame i) , mi n(LT frame ) < threshold^ then threshold _i = avg min(z^')

[0072]

[0073] Else, threshold _t__x + min( STframe _i + / frame _; )

threshold

[0074] 2

[0075] Through the implementations as described in FIG. 13, one or more thresholds can be utilized to track both when the STA/LTA window goes above a maximum threshold, and/or when the window falls below a minimum threshold.

[0076] FIGS. 14(a) to 14(c) illustrate example management information in accordance with an example implementation. FIG. 14(a) illustrates an example of sensor data that can be provided by sensors 210 from one or more connected wells. Such data can include gamma ray, resistivity, porosity and others depending on the desired implementation. FIG. 14(b) illustrates an example of a description of the formation of a well after processing of change points. In the example illustrated in FIG. 14(b), the depths of the well are correlated with the rock formation found within the indicated depth ranges of the well, and derived from FIG. 14(a). FIG. 14(b) provides a comparison between the depth range and the formation characterization found for a managed rig system. Each of the labels indicates formation characterizations which can involve rock compositions. For example, the rock compositions can include shale, salt, anhydride, and so on, that occur between the change points. The depth ranges as illustrated in FIG. 14(b) can be defined by the change points as determined by example implementations described above. FIG. 14(c) illustrates formation label definitions. Each of the formation labels may correspond to a definition as desired by the operator of the management server. Further, each of the formation labels may be associated with drilling parameters for adjusting the drilling processes of the rig. Thus in example implementations, based upon the determination of the formation characterizations, the drilling parameters for the present depth of the drill can be transmitted to the rig to configure the drilling accordingly. [0077] FIG. 15 illustrates a flow diagram for rig management, in accordance with an example implementation. At 1501, the sensor data for a well is received by the management server, which can either be streamed directly by a corresponding rig node or stored from the rig node to a management database for retrieval by the management server. At 1502, the management server is configured to determine change points of the well formation from the sensor data as illustrated, for example, in FIG. 10. At 1503, the formations between the change points are determined. The formations can be determined based on the data as illustrated in FIG. 14(a) through any desired implementation to produce the results as illustrated in FIG. 14(b). For example, a pre-trained classifier can be utilized to determine the formation composition after the change points are defined as illustrated in PCT Application No. PCT/US2016/016889, the disclosure of which is incorporated herein by reference in its entirety for all purposes. At 1504, well formation analytics are provided to the manager of the corresponding well, as illustrated in FIG. 6. Based on the well formation analytics, the manager can adjust the drilling of the rig in view of the well formation. In this manner, the well analytics can be provided in real time to the operator of the rig.

[0078] Some portions of the detailed description are presented in terms of algorithms and symbolic representations of operations within a computer. These algorithmic descriptions and symbolic representations are the means used by those skilled in the data processing arts to convey the essence of their innovations to others skilled in the art. An algorithm is a series of defined steps leading to a desired end state or result. In example implementations, the steps carried out require physical manipulations of tangible quantities for achieving a tangible result.

[0079] Unless specifically stated otherwise, as apparent from the discussion, it is appreciated that throughout the description, discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," or the like, can include the actions and processes of a computer system or other information processing device that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system's memories or registers or other information storage, transmission or display devices.

[0080] Example implementations may also relate to an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes, or it may include one or more general-purpose computers selectively activated or reconfigured by one or more computer programs. Such computer programs may be stored in a computer readable medium, such as a computer-readable storage medium or a computer-readable signal medium. A computer-readable storage medium may involve tangible mediums such as, but not limited to optical disks, magnetic disks, read-only memories, random access memories, solid state devices and drives, or any other types of tangible or non-transitory media suitable for storing electronic information. A computer readable signal medium may include mediums such as carrier waves. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Computer programs can involve pure software implementations that involve instructions that perform the operations of the desired implementation.

[0081] Various general-purpose systems may be used with programs and modules in accordance with the examples herein, or it may prove convenient to construct a more specialized apparatus to perform desired method steps. In addition, the example implementations are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the example implementations as described herein. The instructions of the programming language(s) may be executed by one or more processing devices, e.g., central processing units (CPUs), processors, or controllers.

[0082] As is known in the art, the operations described above can be performed by hardware, software, or some combination of software and hardware. Various aspects of the example implementations may be implemented using circuits and logic devices (hardware), while other aspects may be implemented using instructions stored on a machine-readable medium (software), which if executed by a processor, would cause the processor to perform a method to carry out implementations of the present application. Further, some example implementations of the present application may be performed solely in hardware, whereas other example implementations may be performed solely in software. Moreover, the various functions described can be performed in a single unit, or can be spread across a number of components in any number of ways. When performed by software, the methods may be executed by a processor, such as a general purpose computer, based on instructions stored on a computer-readable medium. If desired, the instructions can be stored on the medium in a compressed and/or encrypted format. [0083] Moreover, other implementations of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the teachings of the present application. Various aspects and/or components of the described example implementations may be used singly or in any combination. It is intended that the specification and example implementations be considered as examples only, with the true scope and spirit of the present application being indicated by the following claims.

Claims

CLAIMS s claimed is:

1. A management server configured to manage one or more wells, the management server comprising: a memory, configured to store sensor data of the one or more wells; and a processor, configured to: determine first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determine second values of the one or more wells from a selection of ones of the first values that meet a threshold; determine, from the second values, third values representative of formation change points of the one or more wells; and update change points of the one or more wells with the third values.

2. The management server of claim 1, wherein the first window of the sensor data comprises a first average of the sensor data across the first range of depth values, and the second window of the sensor data comprises a second average of the sensor data across the second range of depth values; wherein the first range is larger than the second range; and wherein the first values are based on a ratio between the first average and the second average.

3. The management server of claim 2, wherein the processor is configured to adjust the threshold for a given depth based on a first maximum value within the first window of the sensor data up to the given depth and a second maximum value within the second window of the sensor data up to the given depth; and wherein the processor is configured to update the threshold upon a lesser of the first maximum value and the second maximum value exceeding the threshold.

4. The management server of claim 3, wherein the first window of the sensor data is conducted as a batch process on the sensor data stored in the memory, and the second window of the sensor data is conducted as a streaming process on the sensor data streamed from the one or more wells.

5. The management server of claim 3, wherein the processor is configured to, for the lesser of the first maximum value and the second maximum value not exceeding the threshold, update the threshold based on an average of the threshold and a greater of the first maximum value and the second maximum value.

6. The management server of claim 3, wherein the sensor data comprises gamma ray data streamed from the one or more wells; wherein the processor is configured to: determine the second window through processing of the streamed gamma ray data through a streaming process; and determine the first window through storage of the streamed gamma ray data in the memory for processing through a batch process.

7. The management server of claim 2, wherein the processor is configured to adjust another threshold for a given depth based on a first minimum value within the first window of the sensor data up to the given depth and a second minimum value within the second window of the sensor data up to the given depth; and wherein the processor is configured to update the another threshold upon a greater of the first minimum value and the second minimum value being lower than the another threshold.

8. A method to manage one or more wells, the method comprising: storing sensor data of the one or more wells; determining first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determining second values of the one or more wells from a selection of ones of the first values that meet a threshold; determining, from the second values, third values representative of formation change points of the one or more wells; and update change points of the one or more wells with the third values.

9. The method of claim 8, wherein the first window of the sensor data comprises a first average of the sensor data across the first range of depth values, and the second window of the sensor data comprises a second average of the sensor data across the second range of depth values; wherein the first range is larger than the second range; and wherein the first values are based on a ratio between the first average and the second average.

10. The method of claim 9, further comprising adjusting the threshold for a given depth based on a first maximum value within the first window of the sensor data up to the given depth and a second maximum value within the second window of the sensor data up to the given depth; and updating the threshold upon a lesser of the first maximum value and the second maximum value exceeding the threshold.

11. The method of claim 10, wherein the first window of the sensor data is conducted as a batch process on the sensor data stored in the memory, and the second window of the sensor data is conducted as a streaming process on the sensor data streamed from the one or more wells.

12. The method of claim 10, further comprising, for the lesser of the first maximum value and the second maximum value not exceeding the threshold, update the threshold based on an average of the threshold and a greater of the first maximum value and the second maximum value.

13. The method of claim 10, wherein the sensor data comprises gamma ray data streamed from the one or more wells; wherein the method further comprises: determining the second window through processing of the streamed gamma ray data through a streaming process; and determining the first window through storage of the streamed gamma ray data in the memory for processing through a batch process.

14. The method of claim 10, further comprising adjusting another threshold for a given depth based on a first minimum value within the first window of the sensor data up to the given depth and a second minimum value within the second window of the sensor data up to the given depth; and updating the another threshold upon a greater of the first minimum value and the second minimum value being lower than the threshold.

15. A computer program for managing one or more wells, the computer program having instructions comprising: storing sensor data of the one or more wells; determining first values for the one or more wells based on a comparison of a first window of the sensor data across a first range of depth values of the well to a second window of the sensor data across a second range of depth values of the well; determining second values of the one or more wells from a selection of ones of the first values that meet a threshold; determining, from the second values, third values representative of formation change points of the one or more wells, and update change points of the one or more wells with the third values.