Patent Application
20250075572
Generally, the invention relates to drilling operations. More specifically, the invention relates to a system and method for classifying events during drilling operations.
In a drilling rig, well control events (for example, losses and kick events) are dangerous as well as costly experience for any company. To avoid this, companies in their Research and Development (R&D) facilities try their best to come up with systems that may detect these events immediately. Thus, when such situations occur, a respective team may take corrective actions.
For example, when a kick hits a well bore and begins to move towards a surface, this manifests as an increase in volume of mud at the surface and an increase in mud flow rate out of the well. Conversely, circulation may be reduced (i.e., a loss of circulation) when a part of drilling mud is lost in formations. These increases and decreases may be subtle when compared to the normal fluctuations in a mud system during drilling operations. The mud system undergoes significant changes in volume and flow rate as connections are made, as pipe is moved in and out of a hole, as pump rates change, and even as more depth is drilled.
Conventional alarm systems triggered by simple changes in mud volume and flow rate may generate many false alarms. The conventional alarm systems are not effective at detecting these dangerous events. Further, in the conventional alarm systems event signatures may be lost in normal data variance. Moreover, using traditional alarm sounds generated by the conventional alarm systems, it is difficult for drilling team members to take the generated alarm sound seriously as the large number of false alarms may have been encountered prior to an event. Further, the conventional alarm systems adjust thresholds on various attributes and in many cases do not consider different operations going on during the event.
In one embodiment, a method for classifying events during drilling operations is disclosed. The method may include determining a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells. The volve drilling data may be associated with one or more drilling events. The method may further include determining a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data. The method may further include selecting a set of drilling attributes from the plurality of drilling attributes based on the determined correlation value. The method may further include generating a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes. Generating the labelled dataset may further include determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes. The method may further include training a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.
In another embodiment, a system for classifying events during drilling operations is disclosed. The system may include a processor and a memory communicatively coupled to the processor. The memory may store processor-executable instructions, which on execution, may further cause the processor to determine a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells. The volve drilling data may be associated with one or more drilling events. The processor-executable instructions, on execution, may further cause the processor to determine a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data. The processor-executable instructions, on execution, may further cause the processor to select a set of drilling attributes from the plurality of drilling attributes based the determined correlation value. The processor-executable instructions, on execution, may further cause the processor to generate a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes. Generating the labelled dataset may further include determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes. The processor-executable instructions, on execution, may further cause the processor to train a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.
In yet another embodiment, a non-transitory computer-readable medium storing computer-executable instructions for classifying events during drilling operations is disclosed. The stored instructions, when executed by a processor, may cause the processor to perform operations including determining a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells. The volve drilling data may be associated with one or more drilling events. The operations may further include determining a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data. The operations may further include selecting a set of drilling attributes from the plurality of drilling attributes based on the determined correlation value. The operations may further include generating a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes. Generating the labelled dataset may include determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes. The operations may further include training a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
The present application can be best understood by reference to the following description taken in conjunction with the accompanying drawing figures, in which like parts may be referred to by like numerals:
The following description is presented to enable a person of ordinary skill in the art to make and use the invention and is provided in the context of particular applications and their requirements. Various modifications to the embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the invention. Moreover, in the following description, numerous details are set forth for the purpose of explanation. However, one of ordinary skill in the art will realize that the invention might be practiced without the use of these specific details. In other instances, well-known structures and devices are shown in block diagram form in order not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
While the invention is described in terms of particular examples and illustrative figures, those of ordinary skill in the art will recognize that the invention is not limited to the examples or figures described. Those skilled in the art will recognize that the operations of the various embodiments may be implemented using hardware, software, firmware, or combinations thereof, as appropriate. For example, some processes can be carried out using processors or other digital circuitry under the control of software, firmware, or hard-wired logic. (The term “logic” herein refers to fixed hardware, programmable logic and/or an appropriate combination thereof, as would be recognized by one skilled in the art to carry out the recited functions). Software and firmware can be stored on computer-readable storage media. Some other processes can be implemented using analog circuitry, as is well known to one of ordinary skill in the art. Additionally, memory or other storage, as well as communication components, may be employed in embodiments of the invention.
Referring now to
The attribute determination module 102 may be configured to determine a plurality of drilling attributes corresponding to volve drilling data 114 in a predefined format and associated with one or more wells (for example, a Norway-StatoilHydro-15_$47$_9-F-4″ well). The volve drilling data 114 may be associated with one or more drilling operations. In an embodiment, the volve drilling data 114 corresponding to the plurality of drilling operations may be obtained from an open-source database. In some embodiments, the volve drilling data 114 associated with the one or more wells may be extracted, in a current format. By way of an example, the current format be a format in which the volve drilling data 114 may be available on the open-source database. Further, the volve drilling data may be pre-processed to convert the current format into the predefined format. It should be noted that a data pre-processing technique may be used for this purpose. The predefined format may be a Comma Separated Values (CSV) format.
In detail, in some embodiments, a superset of attributes (useful in event classification) may be generated using the volve drilling data 114 in the predefined format. For example, the superset of attributes, for the Norway-StatoilHydro-15_$47$_9-F-4″ well, may include, but is not limited to, Mud Temperature Out (MTOA), Running speed-down (max) (RSOX), Mud Flow Out % (MFOP), Pump 2 Stroke Rate (SPM2), Casing (Choke) Pressure (CHKP), Pump 3 Stroke Rate (SPM3), Active Tank Volume Change (TVCA), Bit Depth (MD) (DBTM), Mud Flow Out (MFOA), Hole depth (MD) (DMEA), Maximum Surface Torque (TQX), Mud Density Out (MDOA), Gas (GASA), Mud Flow In (TFLO), Average Standpipe Pressure (SPPA), Total Strokes (TSTK), Hole Depth (TVD) (OVER), Mud Temperature (TDH), In Trip number (TNUM), Fill/gain volume obs. (cum) (FVOC), Average Hook load (HKLD), Active Tank Volume (TVA), Block Position (BPOS), Pump 1 Stroke Rate (SPM1), Maximum Hook load Lag Depth (MD) (HKLX), Average Surface Torque (DRTM), and Rate of Penetration (TQA).
Further, a subset of attributes may be selected from the superset set of attributes. The subset of attributes may correspond to the plurality of drilling attributes determined by the attribute determination module 102. The subset of attributes may include Mud Flow In (TFLO), Mud Flow Out % (MFOP), Mud Density In (MWTI), Mud Density Out (MDOA), Fill/gain volume obs. (cum) (FVOC), Active Tank Volume (TVA), Active Tank Volume Change (TVCA), Gas (GASA), Average Standpipe Pressure (SPPA), Average Hook load (HKLD), Average Rotary Speed (RPM), Weight on Bit (SWOB), Pump 1 Stroke Rate (SPM1), Pump 2 Stroke Rate (SPM2), Pump 3 Stroke Rate (SPM3), and Rate of Penetration (TQA).
In some embodiments, during progression of the volve drilling data 114 to select the subset of attributes, the volve drilling data 114 may be sorted to get time series data for the well (i.e., the “Norway-StatoilHydro-15_$47$_9-F-4” well). Further, based on the sorting, progression of data with time may be checked. After sorting the volve drilling data 114 according to timestamps to generate the time series data, it may be noted that there might be discontinuity, but a curve may be increasing. However, on examining the time series data using a graph, the curve was not increasing, so indexes with respect to the volve drilling data 114 may be reset based on which an increasing curve was obtained. Further, the attribute determination module 102 may be communicatively coupled to the correlation determination module 104 and the data store 112.
The correlation determination module 104 may be configured to determine a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data 114. In some embodiments, to determine the correlation, exploratory data analysis may be performed by generating a correlation heatmap. Further, in some embodiments, a pair plot may be plotted that may show a scatterplot of all the plurality of drilling attributes with each other. This may be used to check for multicollinearity in the volve drilling data 114 corresponding to the plurality of drilling attributes. With regards to the correlation heatmap, attribute pairs (i.e., each two attributes) with the correlation value more than a threshold value may be extracted from a correlation matrix using a “picking function”. Further, the correlation determination module 104 may be communicatively coupled to the attribute selection module 106 and the data store 112.
The attribute selection module 106 may select a set of drilling attributes from the plurality of drilling attributes based the determined correlation value. The set of drilling attributes may include a bit depth, a hole depth, a mud flow rate out, an average hook load, an average rate of penetration, an average weight on bit, a total pump stroke rate, and a rig activity code. In some embodiments the attribute selection module 106 may eliminate one or more drilling attributes with high correlation values based on a predefined correlation threshold value. The high correlation values may include one of a high positive correlation value or a high negative correlation value. It should be noted that the set of drilling attributes may be High Accuracy Well Kick Detection (HAWK) attributes with low correlation values and selected from Well-site Information Transfer Standard Markup Language (WITSML) data.
In detail, after analysing the correlation heatmap and the pair plot, some attributes from the plurality of drilling attributes may be dropped taking inference from the pair plots to select the set of drilling attributes. In order to drop some attributes, filtration technique may be used to make data values of the plurality of drilling attributes more physically viable. Further, attributes from the plurality of drilling attributes with missing data values may be removed using techniques like filling mean, median, mode values or taking an average of the data value in previous and next timestamp. For example, attributes, such as, SPPA and TFLO may have negative data value which have no significance. Therefore, these attributes with the negative data value may be removed.
In some embodiments, in order to select the set of drilling attributes, standard scaling technique may be used for normalization the volve drilling data 114 using a z-normalization method given by:
[(observation−mean)/standard deviation] equation (1)
Further, a Principal Component Analysis (PCA) may be applied, where principal components may be computed and used to perform a change of basis, dimensionality reduction, on the volve drilling data 114. Further in some embodiments, clusters may be formed from the volve drilling data 114 corresponding to the plurality of drilling attributes using an unsupervised learning technique (for example, using K-Means clustering). The attribute selection module 106 may be communicatively coupled to the labelling module 108 and the data store 112.
The labelling module 108 may be configured to generate a labelled dataset corresponding to the volve drilling data 114 based on the set of drilling attributes. In some embodiments, a value of one or more additional drilling attributes associated with the volve drilling data 114 may also be determined based on the set of drilling attributes, by the labelling module 108, to generate the labelled dataset. It should be noted that, the one or more additional drilling attributes may include a mud weight, and a pore pressure. In some embodiments, Equivalent Circulation Density (ECD) may also be determined. For example, when the mud weight is less than the pore pressure a corresponding label may be a kick, and when the mud weight is greater than the pore pressure the label may be a non-kick. The labelling module 108 may be operatively coupled to the training module 110 and the data store 112. In some embodiments, a function to search for strings like “kick”, “lost circulation”, and “influx” in the volve drilling data 114 may be used.
The training module 110 may be configured to train a supervised ML model 116 based on the labelled dataset and real-time drilling data. In some embodiments, the supervised ML model 116 may be referred to as the ML model. The supervised ML model 116 may be a Random Forest Classifier (RFC) model. The supervised ML model 116 may be trained for classifying each of the one or more drillings events in one of a set of pre-defined categories. Further, the set of pre-defined categories may be a kick category and a non-kick category.
The trained supervised ML model 116 may determine at least one of the kick category or the non-kick category when receives real-time data corresponding a drilling operation. The least one of the kick category or the non-kick category may be determined for each of a set of drilling events associated with the drilling operation based on the real-time data and historical data. To determine the kick category or the non-kick category for each of the set of drilling events, a value of the one or more additional drilling attributes corresponding to the real-time data may be calculated based on the set of drilling attributes.
It may be known to a person skilled in the art that use of the one type of data, for training the ML model, may result in generating a biased model trained with some attributes. For example, in case if drilling data of only well F-4 is used, then an ML model trained using this data may be biased to a specific-lithological parameters, or bit used etc. Therefore, in the present disclosure drilling data from various wells (for example, F-10, F-11, F-14, F-15) may be used. And, for all the wells, the superset may be created in order to cover different attributes which may be useful for marking out labels via external features.
For example, it is observed that the superset obtained from the drilling data collected for the well F-15 may include different attributes from the superset obtained from the drilling data collected for well F-14, when the superset of F-15 is matched with the superset of F-14. For example, different attributes may be Pore Pressure (POR_EQMD), Fracture Pressure (FRAC_EQMD), Bit MD (BITDEP), Hole MD (MDEPTH), and hole TVD (VDEPTH). Therefore, the supervised ML model 116 may be trained based on the drilling data collected for various wells.
Various relevant attributes may be checked, and attributes with less count may be replaced with other similar attributes. For example, replacement for HKLD may be HKLD AVG, MDEPTH may be Depth, VDEPTH may be Depth, ECDTD may be ECDCS or ECDBIT, and TRIPC may be TRIPCFILL or TRIPCEXPFILL.
It should be noted that, to make the supervised ML model 116 adaptive to various drilling operations carried out during process of extraction of oil from wells, a RigActivityCode attribute may be added which represents different operations using numerical codes. Both hot encoding and label encoding may be used to deal with this attribute. For example, rig activity codes “0”, “1”, “2”, “3”, “4”, “5”, “6”, “7”, “8”, “9”, “10”, “100”, “112”, and “13”, respectively represent operations “No Monitor”, “Drilling”, “Reaming”, “OffBottom”, “InSlips”, “Connection”, “TrippingIn”, “TrippingOut”, “TripInSlips”, “ShutIn”, “Circulating”, “Rotating”, “Rotating, Circulating, Reaming”, “means not Rotating, Circulating, and OffBottom”.
To deal with imbalance datasets, for training the supervised ML model 116, oversampling and under sampling Synthetic Minority Oversampling Technique (SMOTE) and Condensed Nearest Neighbours may be used.
It should be noted that, the system 100 and the associated event determination device 100a may be implemented in programmable hardware devices such as programmable gate arrays, programmable array logic, programmable logic devices, or the like. Alternatively, the event determination device 100a may be implemented in software for execution by various types of processors. An identified engine/module of executable code may, for instance, include one or more physical or logical blocks of computer instructions which may, for instance, be organized as a component, module, procedure, function, or other construct. Nevertheless, the executables of an identified engine/module need not be physically located together but may include disparate instructions stored in different locations which, when joined logically together, comprise the identified engine/module and achieve the stated purpose of the identified engine/module. Indeed, an engine or a module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
As will be appreciated by one skilled in the art, a variety of processes may be employed for classifying events during drilling operations. For example, the exemplary system 100 and associated event determination device 100a may classify events, by the process discussed herein. In particular, as will be appreciated by those of ordinary skill in the art, control logic and/or automated routines for performing the techniques and steps described herein may be implemented by the system 100 and associated event determination device 100a either by hardware, software, or combinations of hardware and software. For example, suitable code may be accessed and executed by the one or more processors on the toolpath computation device to perform some or all of the techniques described herein. Similarly, application specific integrated circuits (ASICs) configured to perform some, or all the processes described herein may be included in the one or more processors on the system 100 and associated event determination device 100a.
Referring now to
At step 202, a plurality of drilling attributes corresponding to volve drilling data may be determined using an attribute determination module 102. The volve drilling data may be in a predefined format and is associated with one or more wells. Also, the volve drilling data is associated with one or more drilling operations. This is further explained in detail in conjunction with
In some embodiments, the plurality of drilling attributes may include, but is not limited to, Mud Temperature Out (MTOA), Running speed-down (max) (RSOX), Mud Flow Out % (MFOP), Pump 2 Stroke Rate (SPM2), Casing (Choke) Pressure (CHKP), Pump 3 Stroke Rate (SPM3), Active Tank Volume Change (TVCA), Bit Depth (MD) (DBTM), Mud Flow Out (MFOA), Hole depth (MD) (DMEA), Maximum Surface Torque (TQX), Mud Density Out (MDOA), Gas (GASA), Mud Flow In (TFLO), Average Standpipe Pressure (SPPA), Total Strokes (TSTK), Hole Depth (TVD) (OVER), Mud Temperature (TDH), In Trip number (TNUM), Fill/gain volume obs. (cum) (FVOC), Average Hook load (HKLD), Active Tank Volume (TVA), Block Position (BPOS), Pump 1 Stroke Rate (SPM1), Maximum Hook load Lag Depth (MD) (HKLX), Average Surface Torque (DRTM), and Rate of Penetration (TQA).
In some other embodiments, the plurality of drilling attributes may be determined from these attributes. In that case, the plurality of drilling attributes may include Mud Flow In (TFLO), Mud Flow Out % (MFOP), Mud Density In (MWTI), Mud Density Out (MDOA), Fill/gain volume obs. (cum) (FVOC), Active Tank Volume (TVA), Active Tank Volume Change (TVCA), Gas (GASA), Average Standpipe Pressure (SPPA), Average Hook load (HKLD), Average Rotary Speed (RPM), Weight on Bit (SWOB), Pump 1 Stroke Rate (SPM1), Pump 2 Stroke Rate (SPM2), Pump 3 Stroke Rate (SPM3), and Rate of Penetration (TQA).
At step 204, a correlation value may be determined using the correlation determination module 104. The correlation value may be determined between each two attributes of the plurality of drilling attributes associated with the volve drilling data. It should be noted that heat map and pair plot may be generated for determining correlation between each two attributes. For example, from the plurality of drilling attributes, some pair of attributes may have high correlation values and some may have low correlation values.
Further, at step 206, a set of drilling attributes from the plurality of drilling attributes may be selected based the determined correlation value. This step may be performed by the attribute selection module 106. The set of drilling attributes may include a bit depth, a hole depth, a mud flow rate out, an average hook load, an average rate of penetration, an average weight on bit, a total pump stroke rate, and a rig activity code. It should be noted that one or more drilling attributes from the plurality of drilling attributes with high correlation values may be eliminated based on a predefined correlation threshold value. For example, the high correlation values may include one of a high positive correlation value or a high negative correlation value.
At step 208, a labelled dataset corresponding to the volve drilling data may be generated based on the set of drilling attributes. The labelling module 108 may be employed to perform this step. The labelled dataset may be generated by determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes. The one or more additional drilling attributes may include a mud weight, and a pore pressure.
Thereafter, at step 210, a supervised ML model may be trained. The supervised ML model may be trained using the training module 110. The training may be performed based on the labelled dataset and real-time drilling data. The supervised ML model (same as the supervised ML model 116) may be trained to classify each of the one or more drillings events in one of a set of pre-defined categories. The supervised ML model may be a Random Forest Classifier (RFC) model and the set of pre-defined categories may include a kick category and a non-kick category. In other words, once the supervised ML model may be trained based on the selected set of drilling attributes and the volve drilling data, then the trained supervised ML model may be able to categories each of the one or more drilling events associated with the drilling event as a kick event (i.e., the kick category) or a non-kick event (i.e., the non-kick category).
In short, the supervised ML model (i.e., the RFC model) may be trained on dataset labelled using external dependent features including pore pressure and mud weight in to detect well control events. In particular, the supervised ML model may be trained using eight different independent parameters including bit depth, hole depth, mud flow rate out, average hook load, average rate of penetration, average weight on bit, total pump stroke rate, and rig activity code as independent variables. These parameters may be essential for detecting events and providing accurate and reliable results. Therefore, false alarms which are generated usually due to false detection of kick events may be reduced.
Referring now to
Referring now to
At step 402, real-time data corresponding a drilling operation may be received by the trained supervised ML model 116. Further, at step 404, at least one of the kick category or the non-kick category may be determined for each of a set of drilling events associated with the drilling operation by the trained supervised ML model 116. In other words, each event that occurs while performing the drilling operation may be categorized by the trained supervised ML model 116 as a kick event (i.e., in the kick category) or a non-kick event (i.e., the non-kick category). The at least one of the kick category or the non-kick category may be determined based on the real-time data and historical data. At step 404a, a value of the one or more additional drilling attributes corresponding to the real-time data may be calculated based on the set of drilling attributes, to determine the kick category or the non-kick category for each of the set of drilling events.
Referring now to
These subsets may be transferred further for exploratory data analysis 504. During the exploratory data analysis 504, correlations between attributes of a subset may be determined. In other words, a correlation value between each two attributes present within a subset (e.g., the set of seventeen attributes in the subset of well F-14). Further, based on the determined correlation value, attributes with high correlation values may be discarded to determine a set of drilling attributes with low correlation values. The set of drilling attributes may include a bit depth, a hole depth, a mud flow rate out, an average hook load, an average rate of penetration, an average weight on bit, a total pump stroke rate, and a rig activity code.
The high correlation values may be high positive correlation values or high negative correlation values. Also, during the exploratory data analysis 504, missing values are handled, data corresponding to the attributes of the subsets may be filtered to remove outliers, and data types of some attributes may be changed to prepare physically viable data. Thereafter, dataset labelling 506 may be performed based on the set of drilling attributes. During the dataset labelling 506, additional drilling attributes may be determined based on the set of drilling attributes. Further, a labelled dataset corresponding to the volve drilling data based on the additional drilling attributes may be generated. The additional drilling attributes may include a mud weight, and a pore pressure. For example, a label ‘kick’ may be given when the mud weight is lesser than the pore pressure, and a label ‘non-kick’ may be given when mud weight is higher than the pore pressure.
Thereafter, a supervised ML model 508 (for example, the RFC model) may be trained based on the labelled dataset for classifying one or more events in a kick category or a non-kick category. In an embodiment, the one or more events may be associated with the volve drilling data captured corresponding to various wells. Thereafter, the supervised ML model 508 (i.e., the trained supervised ML model) may receive real-time data 510 corresponding to a drilling operation. The supervised ML model 508 may perform kick/non-kick/Equivalent Circulation Density (ECD) determination 512, for each event in the drilling operation, based on real-time data 510 and historical data. The kick category or the non-kick category for each event may be determined by calculating values of the additional drilling attributes (i.e., the mud weight and the pore pressure) corresponding to the real-time data 510 based on the set of drilling attributes. Further, dynamic dashboarding for data visualization 514 may be performed, where kick event, i.e., an event classified in the kick category, may be dynamically rendered. An exemplary dashboard rendering occurrence of kick event during the drilling operation is depicted and explained further in conjunction with
Referring now to
By way of an example, a correlation value between “Label” and “BITDEP”, or between “BITDEP” and “Label” is “−0.2”. The value “−0.2” is a low negative correlation value. Therefore, features corresponding to the attribute pair of “Label” and “BITDEP” may be considered while determining the set of drilling attributes. By way of another example, correlation values between attributes “MWIN and MWOUT”, “FLOWIN and STRATESUM”, and “MWOUT and Label” are respectively “1”, “1”, and “−0.84”. The value “1” is a high positive correlation value and the value “−0.84” is a high negative correlation value. Therefore, features corresponding to the attribute pairs “MWIN and MWOUT”, “FLOWIN and STRATESUM”, and “MWOUT and Label”, may not be considered and dropped out.
Referring now to
The disclosed methods and systems may be implemented on a conventional or a general-purpose computer system, such as a personal computer (PC) or server computer. Referring now to
The computing system 800 may also include a memory 806 (main memory), for example, Random Access Memory (RAM) or other dynamic memory, for storing information and instructions to be executed by the processor 802. The memory 806 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor 802. The computing system 800 may likewise include a read only memory (“ROM”) or other static storage device coupled to bus 804 for storing static information and instructions for the processor 802.
The computing system 800 may also include a storage device 808, which may include, for example, a media drives 810 and a removable storage interface. The media drive 810 may include a drive or other mechanism to support fixed or removable storage media, such as a hard disk drive, a floppy disk drive, a magnetic tape drive, an SD card port, a USB port, a micro USB, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive. A storage media 812 may include, for example, a hard disk, magnetic tape, flash drive, or other fixed or removable medium that is read by and written to by the media drive 810. As these examples illustrate, the storage media 812 may include a computer-readable storage medium having stored there in particular computer software or data.
In alternative embodiments, the storage devices 808 may include other similar instrumentalities for allowing computer programs or other instructions or data to be loaded into the computing system 800. Such instrumentalities may include, for example, a removable storage unit 814 and a storage unit interface 816, such as a program cartridge and cartridge interface, a removable memory (for example, a flash memory or other removable memory module) and memory slot, and other removable storage units and interfaces that allow software and data to be transferred from the removable storage unit 814 to the computing system 800.
The computing system 800 may also include a communications interface 818. The communications interface 818 may be used to allow software and data to be transferred between the computing system 800 and external devices. Examples of the communications interface 818 may include a network interface (such as an Ethernet or other NIC card), a communications port (such as for example, a USB port, a micro USB port), Near field Communication (NFC), etc. Software and data transferred via the communications interface 818 are in the form of signals which may be electronic, electromagnetic, optical, or other signals capable of being received by the communications interface 818. These signals are provided to the communications interface 818 via a channel 820. The channel 820 may carry signals and may be implemented using a wireless medium, wire or cable, fiber optics, or other communications medium. Some examples of the channel 820 may include a phone line, a cellular phone link, an RF link, a Bluetooth link, a network interface, a local or wide area network, and other communications channels.
The computing system 800 may further include Input/Output (I/O) devices 822. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The I/O devices 822 may receive input from a user and also display an output of the computation performed by the processor 802. In this document, the terms “computer program product” and “computer-readable medium” may be used generally to refer to media such as, for example, the memory 806, the storage devices 808, the removable storage unit 814, or signal(s) on the channel 820. These and other forms of computer-readable media may be involved in providing one or more sequences of one or more instructions to the processor 802 for execution. Such instructions, generally referred to as “computer program code” (which may be grouped in the form of computer programs or other groupings), when executed, enable the computing system 800 to perform features or functions of embodiments of the present invention.
In an embodiment where the elements are implemented using software, the software may be stored in a computer-readable medium and loaded into the computing system 800 using, for example, the removable storage unit 814, the media drive 810 or the communications interface 818. The control logic (in this example, software instructions or computer program code), when executed by the processor 802, causes the processor 802 to perform the functions of the invention as described herein.
Thus, the present disclosure may overcome drawbacks of traditional systems discussed before. Open-source real-time WITSML drilling volve dataset is used to train the supervised ML model. For example, parameters including bit depth, depth, mud flow rate out, average hook load, average rate of penetration, average weight on bit, total pump stroke rate, rig activity code may be used as independent variables, and parameters including pore pressure and mud flow rate may be used as dependent variables.
The system and associated event determination device disclosed in the present disclosure may be deployed on drilling rigs for detection of well control events and a better monitoring of different parameters associated with wells. The disclosure helps in determining probability of a well control event occurrence at any point of drilling. Further, the disclosure provides additional features corresponding to the well which may help in keeping a check on well parameters such as Equivalent Circulation Density (ECD), Rig Activity Code. Additionally, the disclosure discloses a dashboard which may show Non-productive time (NPT). Further, as the supervised ML model is trained and used for determination of kick and non-kick events, better results may be obtained than the results that might be obtained with other models. Also, the disclosure helps in reducing false alarm generation as the results of kick event determination are accurate.
It will be appreciated that, for clarity purposes, the above description has described embodiments of the invention with reference to different functional units and processors. However, it will be apparent that any suitable distribution of functionality between different functional units, processors or domains may be used without detracting from the invention. For example, functionality illustrated to be performed by separate processors or controllers may be performed by the same processor or controller. Hence, references to specific functional units are only to be seen as references to suitable means for providing the described functionality, rather than indicative of a strict logical or physical structure or organization.
Although the present invention has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Rather, the scope of the present invention is limited only by the claims. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognize that various features of the described embodiments may be combined in accordance with the invention. Furthermore, although individually listed, a plurality of means, elements or process steps may be implemented by, for example, a single unit or processor. Additionally, although individual features may be included in different claims, these may possibly be advantageously combined, and the inclusion in different claims does not imply that a combination of features is not feasible and/or advantageous. Also, the inclusion of a feature in one category of claims does not imply a limitation to this category, but rather the feature may be equally applicable to other claim categories, as appropriate.
| Number | Date | Country | Kind |
|---|---|---|---|
| 202311057956 | Aug 2023 | IN | national |
