Data Driven Descaling

This disclosure relates to descaling operations.

Scale may be caused by precipitation due to chemical reactions, such as a chemical reaction with the surface, precipitation due to a change in pressure or temperature, or precipitation due to a change in the composition of a solution. In some cases, scale may occur on well tubing and components as the saturation of produced water is affected by changing temperature and pressure conditions during production.

Scale forms in pipelines, on wellbores, on surface instruments, and on other equipment and the like due to thermodynamic, kinetic, and chemical interchange among hydrocarbons. Scale can form in, for example, hydrocarbon and water producing wells. Scale can reduce hydrocarbon flow, overpower production, and cause the collapse of downhole equipment such as electrical submersible pumps, chokes, and valves.

Descaling operations are executed to remove scale from pipelines, wellbores, surface instruments, equipment and the like used in oil and gas exploration, production, refining, and transportation. In examples, descaling operations use milling, chemicals, or gelling agents with coiled tubing that is equipped with a motor and drill bit to apply the selected descaling modality. Coiled tubing is used to place fluid and mechanical tools accurately and precisely at specific depths where scale occurs. In examples, chemical descaling refers to the use of chemicals or gelling agents to remove scale, and mechanical descaling refers to the use of physical tools to remove scale, such as milling.

The present techniques are directed to data driven descaling. In some embodiments, data associated with a descaling target is obtained, and feature engineering is used to derive features from the data associated with a descaling target. A machine learning model is selected and trained to predict the use of chemical descaling operations or mechanical descaling operations using the engineered features for a relevant descaling area, such as a drilled interval.

Some advantages of the present techniques include using a combination of features to robustly predict a descaling operation. The features are developed based on the data associated with the descaling target, thereby harnessing the power of historical data from past descaling operations executed at the descaling target to make informed decisions on the most suitable solution, such as mechanical descaling operations or chemical operations, while also determining an optimal number of coiled tubing runs associated with the drilling interval. Through this comprehensive approach, the present techniques increase the overall success rate of descaling operations by engineering features for each respective descaling target, and ensure enhanced efficiency and performance of descaling operations.

shows a workflowthat enables data driven descaling. The data driven descaling predicts an optimal solution for descaling based on data associated with a descaling target. At data collection, data associated with a descaling target is obtained. For ease of description, the descaling target is described as a well. However, the present techniques can be used to remove scale from pipelines, wells, surface instruments, equipment, pumps, chokes, valves and the like as used in oil and gas exploration, production, refining, and transportation. In examples, the data obtained includes a previous descaling operation (if any), oil rate, water cut, reservoir, geochemical analysis, well intervention history, temperature, pressure, scale composition, and tag depth. The data associated with the previous descaling operation describes if the candidate well was previously subjected to descaling. Wells that are previously descaled are more likely to be subjected to subsequent descaling operations. Reservoir data includes a name of the reservoir associated with each respective well. In fields, one or more reservoirs can be found. In some embodiments, wells associated with the same reservoir are analyzed for consistency. Geochemical analysis data shows the chemical concentrations for substances such as Cl, Na, K, Ca, and Mg. Well intervention history data includes a written report associated with respective wells. The report is completed after each major operation on a well. In examples, when a well is subjected to descaling, a well intervention history item is reported. The well intervention history provides information on the sequence and events that occur in wells similar to the candidate well. In examples, scale composition refers to the chemical composition of the scale that is collected, and then analyzed in the lab. By including the chemical composition in the model, the model can optimize the approach of removing this specific scale. Additionally, tag depth refers to a depth that usually cannot be passed with coiled tubing due to the obstruction of scale that is formed in the well. Tag depth is found out through the deployment of a gauge cutter on slickline.

At data pre-processing, the obtained data is preprocessed. In examples, preprocessing the data includes removing outliers and handling missing data. In the data preprocessing stage, missing data is filled using various techniques, such as mean imputation, and outliers are identified and subsequently removed to avoid their adverse impact on the model performance.

At feature engineering, the most important features are selected. In examples, the most important features include previous descaling operation, water cut, and scale composition. The most important features that have a significant impact on model accuracy are selected to train a machine learning model. In some embodiments, the most important features are selected based on their respective importance and correlating impact on the model accuracy. However, selection of other features can be performed on the fly so that other features deemed important can be used to build the model.

In some embodiments, the most important features are selected from features that are engineered from the input data. Underlying patterns are detected in the input data and used to create engineered features. In examples, the most important features are selected from the engineered features. Using engineered features further improves predictive capabilities of the trained machine learning model.

At modeling and evaluation, a best machine learning model is selected. In some embodiments, multiple machine learning models are trained using the most important features selected from the engineered features. In examples, the best machine learning model is a K-Nearest Neighbors (KNN) classifier. In examples, the machine learning model is iteratively updated by continuously evaluating the trained model's performance and validating its predictions to identify areas of improvement. One effective approach to enhance model accuracy is by incorporating new descaling operations data into the model. The inclusion of descaling operation data enables the model to learn from the latest information and adapt to evolving patterns and trends. As the model encounters new data, it can refine its understanding of the underlying patterns and improve its predictive capabilities. Through ongoing evaluation and validation, model performance is assessed on the new descaling operations data. This process helps identify any limitations or areas where the model may be underperforming. Consequently, corrective measures are implemented, such as fine-tuning the model's parameters or adjusting the feature engineering techniques, to further enhance its accuracy. By regularly updating the model with new data and leveraging the insights gained through evaluation and validation, the model remains effective and accurate in its predictions. This iterative approach enables continuous improvement and ensures that the model aligns with the evolving dynamics of the descaling operations domain.

At applications, the model will select an intervention type where an output of 1 corresponds to for mechanical descaling operations and an output of 2 corresponds to chemical descaling operations. To output an intervention type, the trained machine learning model is executed. In examples, a visualization platform renders the model output as shown at reference numberFor ease of illustration, the output is shown in text form. However, the present techniques can render the output using images, video, text, or any combinations thereof. In examples, the rendered output includes the input variables and the predicted descaling operations. For example, a drilled interval corresponds to inputs of Oil rate=0.5 mbod; Scale composition=4; Pressure=922; and WC=15%; a trained machine learning model predicts 2 for chemical descaling at the subject interval. In examples, the rendered output is an image of a well with descaling operations predicted for one or more intervals.

is a process flow diagram of a processthat enables data driven descaling. At block, data associated with the descaling target is obtained. At block, features are selected from the data associated with the descaling target. In some examples, feature engineering is performed on the data associated with the descaling target to derive features based on patterns found in the historical data. In examples, the most significant features are extracted from the data associated with the descaling target to create a training dataset.

At block, a selected machine learning model is trained using the training dataset. In examples, the machine learning model is selected based on trials of different machine learning models. In some embodiments, a visualization is rendered that shows predicted descaling operations associated with at least one drilled interval and the predicted number of coiled tubes used in the interval. For example, the visualization can show the predicted descaling operations for multiple intervals of a drilled well.

illustrates hydrocarbon production operationsthat include both one or more field operationsand one or more computational operations, which exchange information and control exploration for the production of hydrocarbons. In some implementations, outputs of techniques of the present disclosure can be performed before, during, or in combination with the hydrocarbon production operations, specifically, for example, either as field operationsor computational operations, or both.

Examples of field operationsinclude forming/drilling a wellbore, hydraulic fracturing, producing through the wellbore, injecting fluids (such as water) through the wellbore, to name a few. In some implementations, methods of the present disclosure can trigger or control the field operations. For example, the methods of the present disclosure can generate data from hardware/software including sensors and physical data gathering equipment (e.g., seismic sensors, well logging tools, flow meters, and temperature and pressure sensors). The methods of the present disclosure can include transmitting the data from the hardware/software to the field operationsand responsively triggering the field operationsincluding, for example, generating plans and signals that provide feedback to and control physical components of the field operations. Alternatively or in addition, the field operationscan trigger the methods of the present disclosure. For example, implementing physical components (including, for example, hardware, such as sensors) deployed in the field operationscan generate plans and signals that can be provided as input or feedback (or both) to the methods of the present disclosure.

Examples of computational operationsinclude one or more computer systemsthat include one or more processors and computer-readable media (e.g., non-transitory computer-readable media) operatively coupled to the one or more processors to execute computer operations to perform the methods of the present disclosure. The computational operationscan be implemented using one or more databases, which store data received from the field operationsand/or generated internally within the computational operations(e.g., by implementing the methods of the present disclosure) or both. For example, the one or more computer systemsprocess inputs from the field operationsto assess conditions in the physical world, the outputs of which are stored in the databases. For example, seismic sensors of the field operationscan be used to perform a seismic survey to map subterranean features, such as facies and faults. In performing a seismic survey, seismic sources (e.g., seismic vibrators or explosions) generate seismic waves that propagate in the earth and seismic receivers (e.g., geophones) measure reflections generated as the seismic waves interact with boundaries between layers of a subsurface formation. The source and received signals are provided to the computational operationswhere they are stored in the databasesand analyzed by the one or more computer systems.

In some implementations, one or more outputsgenerated by the one or more computer systemscan be provided as feedback/input to the field operations(either as direct input or stored in the databases). The field operationscan use the feedback/input to control physical components used to perform the field operationsin the real world.

For example, the computational operationscan process the seismic data to generate three-dimensional (3D) maps of the subsurface formation. The computational operationscan use these 3D maps to provide plans for locating and drilling exploratory wells. In some operations, the exploratory wells are drilled using logging-while-drilling (LWD) techniques which incorporate logging tools into the drill string. LWD techniques can enable the computational operationsto process new information about the formation and control the drilling to adjust to the observed conditions in real-time.

The one or more computer systemscan update the 3D maps of the subsurface formation as information from one exploration well is received and the computational operationscan adjust the location of the next exploration well based on the updated 3D maps. Similarly, the data received from production operations can be used by the computational operationsto control components of the production operations. For example, production well and pipeline data can be analyzed to predict slugging in pipelines leading to a refinery and the computational operationscan control machine operated valves upstream of the refinery to reduce the likelihood of plant disruptions that run the risk of taking the plant offline.

In some implementations of the computational operations, customized user interfaces can present intermediate or final results of the above-described processes to a user. Information can be presented in one or more textual, tabular, or graphical formats, such as through a dashboard. The information can be presented at one or more on-site locations (such as at an oil well or other facility), on the Internet (such as on a webpage), on a mobile application (or app), or at a central processing facility.

The presented information can include feedback, such as changes in parameters or processing inputs, that the user can select to improve a production environment, such as in the exploration, production, and/or testing of petrochemical processes or facilities. For example, the feedback can include parameters that, when selected by the user, can cause a change to, or an improvement in, drilling parameters (including drill bit speed and direction) or overall production of a gas or oil well. The feedback, when implemented by the user, can improve the speed and accuracy of calculations, streamline processes, improve models, and solve problems related to efficiency, performance, safety, reliability, costs, downtime, and the need for human interaction.

In some implementations, the feedback can be implemented in real-time, such as to provide an immediate or near-immediate change in operations or in a model. The term real-time (or similar terms as understood by one of ordinary skill in the art) means that an action and a response are temporally proximate such that an individual perceives the action and the response occurring substantially simultaneously. For example, the time difference for a response to display (or for an initiation of a display) of data following the individual's action to access the data can be less than 1 millisecond (ms), less than 1 second (s), or less than 5 s. While the requested data need not be displayed (or initiated for display) instantaneously, it is displayed (or initiated for display) without any intentional delay, taking into account processing limitations of a described computing system and time required to, for example, gather, accurately measure, analyze, process, store, or transmit the data.

Events can include readings or measurements captured by downhole equipment such as sensors, pumps, bottom hole assemblies, or other equipment. The readings or measurements can be analyzed at the surface, such as by using applications that can include modeling applications and machine learning. The analysis can be used to generate changes to settings of downhole equipment, such as drilling equipment. In some implementations, values of parameters or other variables that are determined can be used automatically (such as through using rules) to implement changes in oil or gas well exploration, production/drilling, or testing. For example, outputs of the present disclosure can be used as inputs to other equipment and/or systems at a facility. This can be especially useful for systems or various pieces of equipment that are located several meters or several miles apart, or are located in different countries or other jurisdictions.

is a schematic illustration of an example controller(or control system) for that enables data driven descaling. For example, the controllermay be operable according to the workflowofor the processof. In some embodiments, the controlleris the same as or similar to the computer systemsof. The controlleris intended to include various forms of digital computers, such as printed circuit boards (PCB), processors, digital circuitry, or otherwise parts of a system for supply chain alert management. Additionally the system can include portable storage media, such as, Universal Serial Bus (USB) flash drives. For example, the USB flash drives may store operating systems and other applications. The USB flash drives can include input/output components, such as a wireless transmitter or USB connector that may be inserted into a USB port of another computing device.

The controllerincludes a processor, a memory, a storage device, and an input/output interfacecommunicatively coupled with input/output devices(for example, displays, keyboards, measurement devices, sensors, valves, pumps). Each of the components,,, andare interconnected using a system bus. The processoris capable of processing instructions for execution within the controller. The processor may be designed using any of a number of architectures. For example, the processormay be a CISC (Complex Instruction Set Computers) processor, a RISC (Reduced Instruction Set Computer) processor, or a MISC (Minimal Instruction Set Computer) processor.

In one implementation, the processoris a single-threaded processor. In another implementation, the processoris a multi-threaded processor. The processoris capable of processing instructions stored in the memoryor on the storage deviceto display graphical information for a user interface on the input/output interface.

The memorystores information within the controller. In one implementation, the memoryis a computer-readable medium. In one implementation, the memoryis a volatile memory unit. In another implementation, the memoryis a nonvolatile memory unit.

The storage deviceis capable of providing mass storage for the controller. In one implementation, the storage deviceis a computer-readable medium. In various different implementations, the storage devicemay be a floppy disk device, a hard disk device, an optical disk device, or a tape device.

The input/output interfaceprovides input/output operations for the controller. In one implementation, the input/output devicesincludes a keyboard and/or pointing device. In another implementation, the input/output devicesincludes a display unit for displaying graphical user interfaces.

There can be any number of controllersassociated with, or external to, a computer system containing controller, with each controllercommunicating over a network. Further, the terms “client,” “user,” and other appropriate terminology can be used interchangeably, as appropriate, without departing from the scope of the present disclosure. Moreover, the present disclosure contemplates that many users can use one controllerand one user can use multiple controllers.

According to some non-limiting embodiments or examples, provided is a computer-implemented method that enables data driven descaling, including: obtaining, using at least one hardware processor, data associated with a descaling target; deriving, using the at least one hardware processor, engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training, using the at least one hardware processor, a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.

According to some non-limiting embodiments or examples, provided is an apparatus including a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations including: obtaining data associated with a descaling target; deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.

According to some non-limiting embodiments or examples, provided is a system, including: one or more memory modules; one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory modules to perform operations including: obtaining data associated with a descaling target; deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.

Further non-limiting aspects or embodiments are set forth in the following numbered embodiments:

Embodiment 1: A computer-implemented method that enables data driven descaling, including: obtaining, using at least one hardware processor, data associated with a descaling target; deriving, using the at least one hardware processor, engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training, using the at least one hardware processor, a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.

Embodiment 2: The computer implemented method of any preceding embodiment, wherein the selected machine learning model is trained to predict a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations.

Embodiment 3: The computer implemented method of any preceding embodiment, wherein the descaling target is a well and the selected machine learning model is trained to predict the use of chemical descaling operations or mechanical descaling operations for a drilled interval of the well using the engineered features and a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations.

Embodiment 4: The computer implemented method of any preceding embodiment, pre-processing the data associated with the descaling target to removing outliers and insert missing data.

Embodiment 5: The computer implemented method of any preceding embodiment, iteratively training the trained, selected machine learning model to enhance model accuracy.

Embodiment 6: The computer implemented method of any preceding embodiment, rendering a visualization that shows output of the trained, selected machine learning model that shows predicted descaling operations for at least one interval of a drilled well.

Embodiment 7: The computer implemented method of any preceding embodiment, wherein the selected machine learning model is selected from machine learning models trained to predict the use of chemical descaling operations or mechanical descaling operations.

Embodiment 8: An apparatus including a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations including: obtaining data associated with a descaling target; deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.

Embodiment 9: The apparatus of any preceding embodiment, wherein the selected machine learning model is trained to predict a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations.

Embodiment 10: The apparatus of any preceding embodiment, wherein the descaling target is a well and the selected machine learning model is trained to predict the use of chemical descaling operations or mechanical descaling operations for a drilled interval of the well using the engineered features and a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations.

Embodiment 11: The apparatus of any preceding embodiment, pre-processing the data associated with the descaling target to removing outliers and insert missing data.

Embodiment 12: The apparatus of any preceding embodiment, iteratively training the trained, selected machine learning model to enhance model accuracy.

Embodiment 13: The apparatus of any preceding embodiment, rendering a visualization that shows output of the trained, selected machine learning model that shows predicted descaling operations for at least one interval of a drilled well.

Embodiment 14: The apparatus of any preceding embodiment, wherein the selected machine learning model is selected from machine learning models trained to predict the use of chemical descaling operations or mechanical descaling operations.

Embodiment 15: A system, including: one or more memory modules; one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory modules to perform operations including: obtaining data associated with a descaling target; deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.