Patent Application
20240151141
Not applicable.
The disclosed embodiments relate generally to techniques for detecting fracture driven interactions in a hydrocarbon production field.
Unconventional hydrocarbon resource plays are maturing and operators are increasingly challenged with finding new ways to drive production in these wells. Near-wellbore damage resulting from fracturing and/or drilling can significantly impact the initial and subsequent productivity of a well. Interference between hydraulic fracture stages in nearby wells is one of the most common causes of near-wellbore damage. The impact of fracture driven interactions (FDI) varies depending on the location of the frac stage or well within a drainage volume and can range from reduced productivity to complete well damage (plugging). It is important for operators to understand the impact of FDI and the methods to mitigate it.
Horizontal wells (child wells) are fractured to increase oil and gas productivity. The process involves pumping solid proppants mixed with fluids at high pressure into a child “frac” well in order to create the lateral fractures. On many occasions, the child-well fractures extend to neighboring (parent) wells and interfere with the parent well's ongoing production efficiency. Legacy data such as well head pressure which are currently available can indicate when such interference occurs, but this data is of poor quality and insufficient to distinguish between a valid frac-event and operational noise.
The most common approach to address this issue is to shut neighboring (parent) wells in advance of a child well frac operation, and/or pressure the parent well to restrict fluid migration from child well. These methods are expensive operations that lead to losses related to the intervening fracturing procedure. There are also several attempts to model the propagation of fractures between child well and parent well. These modelling methods are based on heuristic models that require extensive computing resource and have not proven to be precise yet. Existing methods of utilizing machine learning methods utilize secondary effects such as long term (6 months) changes in parent well production due to the challenge of dealing with noisy primary data.
What all these methods lack is an effective strategy that is precise in predicting frac interference and prescriptive in identifying the best mitigative action. In general, current methods are broad and regional and unable to reference direct data related to the phenomenon that varies by region, reservoir zone, and historical production history.
There exists a need for detecting and characterizing fracture driven interactions.
In accordance with some embodiments, a method for detecting and characterizing fracture driven interactions including receiving well completion and production data for a plurality of wells; identifying parent-child well pairs in the plurality of wells; generating event labels based on dynamic pressure exceptions, fluid ratio behavior analysis, and anomaly detection for the parent-child well pairs; and training a model to identify and characterize fracture driven interactions using the event labels and the dynamic pressure exceptions and fluid ratio behavior is disclosed. The method may apply the model to a second set of well completion and production data to identify and characterize fracture driven interactions.
In another aspect of the present invention, to address the aforementioned problems, some embodiments provide a non-transitory computer readable storage medium storing one or more programs. The one or more programs comprise instructions, which when executed by a computer system with one or more processors and memory, cause the computer system to perform any of the methods provided herein.
In yet another aspect of the present invention, to address the aforementioned problems, some embodiments provide a computer system. The computer system includes one or more processors, memory, and one or more programs. The one or more programs are stored in memory and configured to be executed by the one or more processors. The one or more programs include an operating system and instructions that when executed by the one or more processors cause the computer system to perform any of the methods provided herein.
Like reference numerals refer to corresponding parts throughout the drawings.
Described below are methods, systems, and computer readable storage media that provide a manner of detecting fracture driven interactions (FDIs). The analytical techniques disclosed here are used to detect, analyze, and characterize FDI events in unconventional resources using production data from a well and its nearest neighbors. The method provides a rigorous statistical analysis of the production data of a well and its nearest neighbors, and utilizes a combination of signals including pressure, rate, water-oil ratio (WOR), and fluid production to identify and characterize FDI events. The method is designed to handle multiple wells with different collection frequencies and timestamps, and the tools are designed to be used on multiple wells in a field.
The problem objective is to predict when a child well frac operation will interfere and affect a neighbor parent well using data-driven Machine Learning (ML) algorithms. This solution requires extensive subject matter expert (SME) validated data to create a ML training data set that can represent fracture interference events that is very difficult and expensive to obtain. This solution provides an automated method to create a frac event training dataset using legacy data.
Reference will now be made in detail to various embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure and the embodiments described herein. However, embodiments described herein may be practiced without these specific details. In other instances, well-known methods, procedures, components, and mechanical apparatus have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.
The methods and systems of the present disclosure may, in part, use one or more models that are machine-learning algorithms. These models may be supervised. Supervised learning algorithms are trained using labeled data (i.e., training data) which consist of input and output pairs. By way of example and not limitation, supervised learning algorithms may include classification and/or regression algorithms such as neural networks, generative adversarial networks, linear regression, etc. Although the present disclosure may name specific models, those of skill in the art will appreciate that any model that may accomplish the goal may be used.
The methods and systems of the present disclosure may be implemented by a system and/or in a system, such as a system 10 shown in
The electronic storage 13 may be configured to include electronic storage medium that electronically stores information. The electronic storage 13 may store software algorithms, information determined by the processor 11, information received remotely, and/or other information that enables the system 10 to function properly. For example, the electronic storage 13 may store information relating to well production data, and/or other information. The electronic storage media of the electronic storage 13 may be provided integrally (i.e., substantially non-removable) with one or more components of the system 10 and/or as removable storage that is connectable to one or more components of the system 10 via, for example, a port (e.g., a USB port, a Firewire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage 13 may include one or more of optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, magnetic hard drive, floppy drive, etc.), electrical charge-based storage media (e.g., EPROM, EEPROM, RAM, etc.), solid-state storage media (e.g., flash drive, etc.), and/or other electronically readable storage media. The electronic storage 13 may be a separate component within the system 10, or the electronic storage 13 may be provided integrally with one or more other components of the system 10 (e.g., the processor 11). Although the electronic storage 13 is shown in
The graphical display 14 may refer to an electronic device that provides visual presentation of information. The graphical display 14 may include a color display and/or a non-color display. The graphical display 14 may be configured to visually present information. The graphical display 14 may present information using/within one or more graphical user interfaces. For example, the graphical display 14 may present information relating to production data, fracture interactions, and/or other information.
The processor 11 may be configured to provide information processing capabilities in the system 10. As such, the processor 11 may comprise one or more of a digital processor, an analog processor, a digital circuit designed to process information, a central processing unit, a graphics processing unit, a microcontroller, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information. The processor 11 may be configured to execute one or more machine-readable instructions 100 to facilitate detecting fracture driven interactions. The machine-readable instructions 100 may include one or more computer program components. The machine-readable instructions 100 may include a neighbor component 102, an event component 104, an AI model component 106, and/or other computer program components.
It should be appreciated that although computer program components are illustrated in
While computer program components are described herein as being implemented via processor 11 through machine-readable instructions 100, this is merely for ease of reference and is not meant to be limiting. In some implementations, one or more functions of computer program components described herein may be implemented via hardware (e.g., dedicated chip, field-programmable gate array) rather than software. One or more functions of computer program components described herein may be software-implemented, hardware-implemented, or software and hardware-implemented.
Referring again to machine-readable instructions 100, the neighbor component 102 may be configured to analyze well neighbors.
The event component 104 may be configured to generate event labels.
The Artificial Intelligence (AI) model component 106 may be configured to train an AI model to characterize potential fracture driven interaction events. It may also apply the AI model.
The description of the functionality provided by the different computer program components described herein is for illustrative purposes, and is not intended to be limiting, as any of computer program components may provide more or less functionality than is described. For example, one or more of computer program components may be eliminated, and some or all of its functionality may be provided by other computer program components. As another example, processor 11 may be configured to execute one or more additional computer program components that may perform some or all of the functionality attributed to one or more of computer program components described herein.
The analytical techniques disclosed here are used to detect, analyze, and characterize FDI events in unconventional resources using production data from a well and its nearest neighbors. The method provides a rigorous statistical analysis of the production data of a well and its nearest neighbors, and utilizes a combination of signals including pressure, rate, water-oil ratio (WOR), and fluid production to identify and characterize FDI events. The method is designed to handle multiple wells with different collection frequencies and timestamps, and the tools are designed to be used on multiple wells in a field.
This invention process uses field data that is directly representative of the frac interference phenomenon. This invention does not limit use of representative data to expensive field study data that is obtained specifically for the purpose of enabling such studies and is commonly limited to a small number of wells due to costs of data acquisition.
The process enables use of general purpose data commonly used in daily oil field operations. The process reduces the challenge of noise associated with such data use, by corelating a variety of data (surface operation readings and subsurface readings) to limit the effect of operational noise, such as surface activities. By enabling use of multi-purpose data, the process converts the problem target of using with high fidelity data on a few wells to a solution that can utilize low fidelity data on a large number of wells. The process provides a solution for dealing with large data sets. The solution involves use of machine learning algorithms to identify and detect signal patterns and then document the legacy occurrence of high probability events. Additional machine learning algorithms are used to curate the vast data set into a subset of high probability event identification. In doing so, the process lowers cost, increases accuracy and precision and is more effective in representing asset-specific data sets that can serve as a training data set for predicting the occurrences of frac dependent interference events.
At operation 21, the method 200 analyzes neighbors among the wells. One criteria is proximity: parent-child pairs are computed based on proximity vectors. Controls are provided for the FDI analyst to change the lateral and buffer distance to find the most optimum number of pairs. As seen in
Referring again to
The labeled events from operation 22 are used in combination with any known subsurface reservoir property information 24 by operation 23 to train an AI model to characterize potential FDI events based on the categories in operation 22. This could be done in the first round of training. If the subsurface reservoir property data isn't initially available, it's possible to progress with a model created without the data and improve the performance with a 2nd model created with the additional data when it's available. While a capable model can be created without the subsurface reservoir property data, the model performance should improve with it. For example, the production rates of a well may decrease in response to a well being shut-in. Or the flowing rates may increase due to an increase in the well choke that was executed for operational reasons. By using subsurface and auxiliary data, an SME is able to confirm that the label is correct and not mis-identified before such labelled data is fed to a supervised ML algorithm.
The AI model may be a supervised machine learning model, such as a neural network, decision tree, support vector machine, or random forest. The architecture of the model may include multiple layers, with each layer consisting of a set of nodes or neurons. The input layer receives the features extracted from the data, such as pressure, rate, water-oil ratio (WOR), and fluid production, as well as any available subsurface reservoir property information. The hidden layers perform various transformations on the input data, with each node applying an activation function to the weighted sum of its inputs. The output layer generates the predictions for the potential FDI events based on the categories defined in operation 22. The model may be trained using a combination of labeled events and subsurface reservoir property information to optimize its performance in identifying and characterizing FDI events.
During the training process, the AI model learns the relationships between the input features and the labeled events, adjusting the weights and biases within the network to minimize the prediction error. The model may be evaluated using a validation dataset, which is separate from the training dataset, to assess its performance in detecting and characterizing FDI events. Performance metrics such as accuracy, precision, recall, and F1 score can be used to determine the effectiveness of the model in predicting FDI events.
Once the AI model has been trained and its performance has been validated, it can be applied to a second set of well completion and production data to identify and characterize fracture driven interactions. The model may generate predictions for each parent-child well pair in the dataset, providing insights into the potential FDI events and enabling operators to take appropriate mitigative actions to optimize well productivity and minimize well damage.
The AI model utilized in this method is a supervised machine learning model that leverages labeled events and subsurface reservoir property information to accurately identify and characterize fracture driven interactions in hydrocarbon production fields. The model's architecture may include multiple layers, such as input, hidden, and output layers, to process the input features and generate predictions for potential FDI events. The model's performance is validated using a separate dataset and performance metrics, ensuring its effectiveness in detecting and characterizing FDI events in real-world applications.
Subsurface reservoir property features may include formation permeability, zone stress, porosity, Shmin direction, compass angle, Pclay, Psand, vclay, vsand, and distance from child stage and parent stage to natural fractures and frac conductivity properties and the like. Shmin direction refers to the orientation of the minimum horizontal stress in a subsurface reservoir. It is an important parameter in understanding the stress regime and fracture behavior in reservoirs. Compass angle is the angle measured in degrees from a reference direction (usually north) to another direction of interest. In the context of this method, it may refer to the angle between the Shmin direction and a reference direction. It is visualized as the angle created by drawing a line from the stage of the parent well to the stage of the child well that resulted in the interference event where true north is 0 degrees. Pclay and Psand are terms that refer to the pressure within clay and sand formations in the subsurface reservoir. Pressure in these formations can impact fluid flow and fracture behavior. Vclay and vsand are the velocities of seismic waves (such as P-wave or S-wave) in clay and sand formations. Seismic velocities can provide information about the mechanical properties and stress state of the subsurface formations. Frac conductivity refers to the ability of a hydraulic fracture to conduct fluids, such as oil, gas, or water. It is an important parameter in evaluating the effectiveness of hydraulic fracturing treatments and the productivity of the fractured reservoir. Frac conductivity depends on factors like fracture width, permeability, and proppant properties. In addition, stage distance from nearby faults is computed as a feature and included for evaluation as a FDI event cause. The FDI Data set is used to do an Exploratory Data analysis to evaluate correlation between different features and assess statistical distributions of data such as validation of Gaussian or Skewed distributions and valid ranges of data existence using outlier evaluation and NULL value correction Physical parameters are grouped using clustering algorithms such as K-means clustering are used to compare event descriptions between different assets to compare FDI model behavior similarity for improvement in events detection. These comparisons may provide insights into better event definitions for more standard interpretation and potential actionable interventions.
Referring again to
While particular embodiments are described above, it will be understood it is not intended to limit the invention to these particular embodiments. On the contrary, the invention includes alternatives, modifications and equivalents that are within the spirit and scope of the appended claims. Numerous specific details are set forth in order to provide a thorough understanding of the subject matter presented herein. But it will be apparent to one of ordinary skill in the art that the subject matter may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.
The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the description of the invention and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this specification, specify the presence of stated features, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, operations, elements, components, and/or groups thereof.
As used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in accordance with a determination” or “in response to detecting,” that a stated condition precedent is true, depending on the context. Similarly, the phrase “if it is determined [that a stated condition precedent is true]” or “if [a stated condition precedent is true]” or “when [a stated condition precedent is true]” may be construed to mean “upon determining” or “in response to determining” or “in accordance with a determination” or “upon detecting” or “in response to detecting” that the stated condition precedent is true, depending on the context.
Although some of the various drawings illustrate a number of logical stages in a particular order, stages that are not order dependent may be reordered and other stages may be combined or broken out. While some reordering or other groupings are specifically mentioned, others will be obvious to those of ordinary skill in the art and so do not present an exhaustive list of alternatives. Moreover, it should be recognized that the stages could be implemented in hardware, firmware, software or any combination thereof.
The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to best explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to best utilize the invention and various embodiments with various modifications as are suited to the particular use contemplated.
The present application claims priority to U.S. Provisional Patent Application No. 63/422618 filed Nov. 4, 2022, the entire content of which is incorporated herein by reference.
| Number | Date | Country | |
|---|---|---|---|
| 63422618 | Nov 2022 | US |
