US20230114088A1

US20230114088A1 - Data-driven model for control and optimization of hydrocarbon production

Info

Publication number: US20230114088A1
Application number: US17/497,492
Authority: US
Inventors: Anton Gryzlov; Sergey SAFONOV; Muqbil Alkhalaf; Muhammad ARSALAN
Original assignee: Aramco Innovations LLC; Saudi Arabian Oil Co
Current assignee: Saudi Arabian Oil Co
Priority date: 2021-10-08
Filing date: 2021-10-08
Publication date: 2023-04-13
Also published as: WO2023059895A1; CN118339357A; EP4413234A1

Abstract

A system for controlling and optimizing hydrocarbon production may include sensors that capture sensor data pertaining to wellhead pressure values in a well. The system may also include a multiphase flow meter that captures production data pertaining to multiphase production flow rates of the well. The system may include an access module to access an estimated parameter value associated with a second time and a parameter that pertains to production. The estimated parameter value is predicted by a data-driven model for describing production fluid dynamics of the well, based on the sensor data and the production data obtained at a first time. The system includes a processor to update the data-driven model using a data assimilation algorithm and the production data received at the second time. The processor generates, using the updated data-driven model, an optimal control setting of a control tool for causing an adjustment to a production system.

Description

BACKGROUND

In the petroleum industry, the production of hydrocarbons is a complex process that is governed by complex dynamics of a coupled wellbore-reservoir system. The uncontrolled operation of a well does not guarantee maximized production. Moreover, the uncontrolled operation of a well may lead to serious danger to the health and life of the people working on the well, to the environment, and to the equipment of the well.
Accordingly, there is a need for an intelligent production control system for improving the production of hydrocarbon fluid from oil and gas wells.

SUMMARY

This summary is provided to introduce concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.
In general, in one aspect, embodiments disclosed herein relate to a system for controlling and optimizing hydrocarbon production. The system includes one or more sensors arranged to capture sensor data pertaining to one or more wellhead pressure values in a well. The system includes a multiphase flow meter arranged to capture production data pertaining to multiphase production flow rates of the well. The system includes an access module configured to access an estimated parameter value associated with a second time and a parameter. The parameter pertains to production from the well. The estimated parameter value is predicted by a data-driven model for describing production fluid dynamics of the well, based on the sensor data and the production data obtained at a first time. The system includes one or more hardware processors configured to update the data-driven model using a data assimilation algorithm and the production data received during a production process at the second time. The one or more hardware processors are further configured to generate, using the updated data-driven model, an optimal control setting of a control tool for causing an adjustment to a production system.
In general, in one aspect, embodiments disclosed herein relate to a method for controlling and optimizing hydrocarbon production. The method includes accessing an estimated parameter value associated with a second time and a parameter. The parameter pertains to production from a well. The estimated parameter value is predicted by a data-driven model for describing production fluid dynamics of the well, based on sensor data and production data obtained at a first time. The method includes updating the data-driven model using a data assimilation algorithm and the production data obtained during a production process at the second time. The updating is performed using one or more hardware processors. The method includes generating, using the updated data-driven model, an optimal control setting of a control tool for causing an adjustment to a production system.
In general, in one aspect, embodiments disclosed herein relate to a non-transitory machine-readable storage medium. The non-transitory machine-readable storage medium includes instructions that, when executed by one or more processors of a machine, cause the machine to perform operations. The operations include accessing an estimated parameter value associated with a second time and a parameter. The parameter pertains to production from a well. The estimated parameter value is predicted by a data-driven model for describing production fluid dynamics of the well, based on sensor data and production data obtained at a first time. The operations include updating the data-driven model using a data assimilation algorithm and the production data obtained during a production process at the second time. The operations include generating, using the updated data-driven model, an optimal control setting of a control tool for causing an adjustment to a production system.
Other aspects and advantages of the claimed subject matter will be apparent from the following description and the appended claims.

BRIEF DESCRIPTION OF DRAWINGS

Some embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings.

FIG. 1 illustrates a system, according to one or more example embodiments.

FIG. 2 is a block diagram that illustrates a production control system, according to one or more example embodiments.

FIG. 3 is a flow diagram that illustrates an algorithm for data assimilation using the production control system, according to one or more example embodiments.

FIG. 4 illustrates a graphical representation of optimal control settings, according to one or more example embodiments.

FIG. 5 is a flowchart illustrating operations of the production control system in performing a method for controlling and optimizing hydrocarbon production, according to one or more example embodiments.

FIGS. 6A and 6B illustrate a computing system, according to one or more example embodiments.

DETAILED DESCRIPTION

Example systems and methods for controlling and optimizing hydrocarbon production using a data-driven model are described. Unless explicitly stated otherwise, components and functions are optional and may be combined or subdivided. Similarly, operations may be combined or subdivided, and their sequence may vary.
In the following detailed description of embodiments of the disclosure, numerous specific details are set forth in order to provide a more thorough understanding of the disclosure. However, it will be apparent to one of ordinary skill in the art that the disclosure may be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description.
Throughout the application, ordinal numbers (e.g., first, second, or third) may be used as an adjective for an element (that is, any noun in the application). The use of ordinal numbers is not to imply or create any particular ordering of the elements nor to limit any element to being only a single element unless expressly disclosed, such as using the terms “before,” “after,” “single,” and other such terminology. Rather, the use of ordinal numbers is to distinguish between the elements. By way of an example, a first element is distinct from a second element, and the first element may encompass more than one element and succeed (or precede) the second element in an ordering of elements.
According to some example embodiments, a production control system may be used to optimize the hydrocarbon production from a well using a non-linear, data-driven Artificial Intelligence (AI) model. An analysis of the relationship between the dynamics of flow variables (e.g., multiphase flow rates at the wellhead, wellbore pressures, and temperatures) associated with the hydrocarbon production from a well and of wellhead pressure values at various times may facilitate a more accurate prediction of future multiphase flow rates form the well. Such analysis may be represented in the data-driven model that may be used, by the production control system, to generate optimal control settings for a choke valve for improved control of the production from the well. The data-driven model may be defined based on available production data and sensor data using system identification techniques, such as a dynamic mode decomposition (DMD) algorithm. In addition, the data-driven model may be corrected using data assimilation methods.
The production control system provides improvements over existing methods by incorporating the data-driven model generated (hereinafter also “trained” or “established”) based on a DMD algorithm that uses measurements taken by wellbore instrumentation, such as sensors, gauges, and three-phase separators. The data-driven model excludes unobservable (unmeasured) components, such as reservoir-based variables, from consideration. The production control system, using the DMD algorithm, extracts dynamically-relevant process features from time-resolved experimental data associated with a well. Then, the production control system generates a low-dimensional, data-driven model for predicting future multiphase flow rates for the well, based on the dynamically-relevant process features. Unlike the existing conventional models, the low-dimensional, data-driven model predicts optimal control settings (e.g., rate and pressure at which production fluids progress through a pipeline) for the control of production from the well more accurately and over a longer forecast horizon. In addition, the use of a low-dimensional model improves the computation speed of the production control system as compared to existing control systems.
In some example embodiments, the data-driven model is generated based on sensor data obtained using downhole temperature and pressure sensors (or gauges) and based on available production data pertaining to multiphase flow rates (i.e., oil, gas, and water) determined using a multiphase flow meter or test separator. The sensor data and the production data may be matched based on time stamps associated with the sensor data and the production data. The production control system initializes the data-driven model with the dynamically relevant process features extracted from the sensor data and the production data.
In some example embodiments, the data-driven model explains the relationship between the control of the well and the dynamics of flow variables in the following pseudo—-pseudo-linear way:
$X_{t + 1} = A_{D M D} \cdot X_{t} + B_{D M D} \cdot u_{t},$
where X is a state vector, which includes multiphase rates at the wellhead, wellbore pressures, and temperatures, t refers to a time step index, and u is a control vector, which includes values of wellhead pressure adjustable through the topside choke. A and B are the matrices defining the system dynamics, which are extracted from the data using the DMD algorithm.
Upon extracting the dynamically relevant process data from the sensor data and the production data, the production control system trains the data-driven model, based on the extracted dynamically relevant process data, to predict the estimated parameter value associated with a future time. The training process can be formulated in the following paradigm. All the dynamic information is considered as time series x_i(t) and u_i(t), where x is the vector of the target parameters (e.g., the flow rates of oil, gas, and water) and u represents the control vector of wellhead pressures. Mathematical formulation of the prediction process can be given as follows: it is necessary to estimate the output value of x_i at the time t given a time series of input features with temporal length of l, which in case the measurements are equally spaced in time corresponds to the shifted time window of [t - l, t]. Given the set of training data, where the target flow rates are known, the training data is split into a finite number of overlapping sequences of length l shifted by one time step from each other. The resulting training input matrix can be represented as follows:
$X = [\begin{matrix} x_{0} & \dots & x_{T R - l} \\ x \\ _{1} & \dots & x_{T R - l + 1} \\ ⋮ & ⋱ & ⋮ \\ x_{l} & \dots & x_{T R} \end{matrix}] .$
Similarly, the array of control inputs u is defined. Here, the subscript TR corresponds to the number of data points in the training sequence. The data-driven model defines a numerical operator, which maps every column of X(t) and u(t) to the entries of vector X(t+1).
$X (t), u (t) \to X (t +) (1) .$
In one or more embodiments, this mapping is defined by DMD, i.e., a DMD operator (also hereinafter “DMD model”) is introduced which relates X(t) and u(t) to X(t+1). Once the DMD operator is trained, the following equation can be used to estimate the values of multiphase flow rates, wellbore pressures, and temperatures at time t+1:
$X_{t + 1} = A_{D M D} \cdot X_{t} + B_{D M D} \cdot u_{t}$
Since the measured data is used to prepare a data-driven model according to X(t), u(t) → X(t + 1), then any measurement uncertainty would propagate to matrices A_DMD and B_DMD defining the DMD operator and eventually would cause a deviation of the predicted variables from the measured values. The typical sources of uncertainty are related to the quality of the sensor used, whether the information from the sensors is continuously supplied, or there are any gaps in the received data.
The data-driven model can be used to predict multiphase flow rates, such as the flow rates of oil, gas, and water, from a well when the associated uncertainty is minimal. For highly non-linear, time-varying dynamics, the data-driven model may eventually diverge from actual measured production values due to accumulated changes in system conditions. To mitigate this, data assimilation techniques based on the Kalman Filter may be used. Such data assimilation techniques enable online correction of the structure of the data-driven model by integrating newly acquired measurements into the data-driven model. For example, the components of matrices A and B for model predictions may be adjusted to match actual production measurement values.
Once the data-driven model is generated, the data-driven model may be used to maximize the production of the well by solving an optimization problem to compute a new control input vector u to be applied to the data-driven model. The result of the application of the new control vector u is the new vector of state variables X. The control input vector may be used, by the production control system, to control the amount of opening of a choke valve (e.g., a topside choke valve) associated with the well. The values in the control vector correspond to the choke opening. Hence, by computing a new value of a control vector, the choke opening can be defined and set. The production control system may control the production of the well by adjusting the position of the choke valve to allow the flow of an optimal level of hydrocarbon production.
FIG. 1 shows a schematic diagram of a system, in accordance with one or more embodiments. FIG. 1 illustrates a well environment 100 that includes a hydrocarbon reservoir (“reservoir”) 102 located in a subsurface hydrocarbon-bearing formation (“formation”) 104 and a well system 106. The hydrocarbon-bearing formation 104 may include a porous or fractured rock formation that resides underground, beneath the earth’s surface (“surface”) 108. In the case of the well system 106 being a hydrocarbon well, the reservoir 102 may include a portion of the hydrocarbon-bearing formation 104. The hydrocarbon-bearing formation 104 and the reservoir 102 may include different layers of rock having varying characteristics, such as varying degrees of permeability, porosity, capillary pressure, and resistivity. In the case of the well system 106 being operated as a production well, the well system 106 may facilitate the extraction (or “production”) of hydrocarbons from the reservoir 102.
In some embodiments disclosed herein, the well system 106 includes a rig 101, a wellbore 120, a well sub-surface system 122, a well surface system 124, and an operation system 126. The operation system 126 may control various operations of the well system 106, such as well production operations, well completion operations, well maintenance operations, and reservoir monitoring, assessment and development operations. In some embodiments, the operation system 126 includes a computer system that is the same as or similar to computing system 500 or 514 described below in FIGS. 5A and 5B, and the accompanying descriptions.
The rig 101 is the machine used to drill a borehole to form the wellbore 120. Major components of the rig 101 include the mud tanks, the mud pumps, the derrick or mast, the drawworks, the rotary table or topdrive, the drillstring, the power generation equipment, and auxiliary equipment.
The wellbore 120 includes a bored hole (i.e., borehole) that extends from the surface 108 into a target zone of the hydrocarbon-bearing formation 104, such as the reservoir 102. An upper end of the wellbore 120, terminating at or near the surface 108, may be referred to as the “up-hole” end of the wellbore 120, and a lower end of the wellbore, terminating in the hydrocarbon-bearing formation 104, may be referred to as the “downhole” end of the wellbore 120. The wellbore 120 may facilitate the circulation of drilling fluids during drilling operations, the flow of hydrocarbon production (“production”) 121 (e.g., oil, gas, or both) from the reservoir 102 to the surface 108 during production operations, the injection of substances (e.g., water) into the hydrocarbon-bearing formation 104 or the reservoir 102 during injection operations, or the communication of monitoring devices (e.g., logging tools) into the hydrocarbon-bearing formation 104 or the reservoir 102 during monitoring operations (e.g., during in situ logging operations).
In some embodiments, during operation of the well system 106, the operation system 126 collects and records wellhead data 140 for the well system 106. The wellhead data 140 may include, for example, a record of measurements of wellhead pressure values (P_wh) (e.g., including flowing wellhead pressure values), wellhead temperature values (T_wh) (e.g., including flowing wellhead temperature values), wellhead multiphase production rates (Q_wh) over some or all of the life of the well (106), and water cut data. In some embodiments, the measurement values are recorded in real-time, and are available for review or use within seconds, minutes, or hours of the condition being sensed (e.g., the measurements are available within 1 hour of the condition being sensed). In such an embodiment, the wellhead data 140 may be referred to as “real-time” wellhead data 140. Real-time wellhead data 140 may enable an operator of the well 106 to assess a relatively current state of the well system 106, and make real-time decisions regarding development or management of the well system 106 and the reservoir 102, such as on-demand adjustments in regulation of production flow from the well.
In some embodiments, the well sub-surface system 122 includes casing installed in the wellbore 120. For example, the wellbore 120 may have a cased portion and an uncased (or “open-hole”) portion. The cased portion may include a portion of the wellbore having casing (e.g., casing pipe and casing cement) disposed therein. The uncased portion may include a portion of the wellbore not having casing disposed therein. In some embodiments, the casing includes an annular casing that lines the wall of the wellbore 120 to define a central passage that provides a conduit for the transport of tools and substances through the wellbore 120. For example, the central passage may provide a conduit for lowering logging tools into the wellbore 120, a conduit for the flow of production 121 (e.g., oil and gas) from the reservoir 102 to the surface 108, or a conduit for the flow of injection substances (e.g., water) from the surface 108 into the hydrocarbon-bearing formation 104. In some embodiments, the well sub-surface system 122 includes production tubing installed in the wellbore 120. The production tubing may provide a conduit for the transport of tools and substances through the wellbore 120. The production tubing may, for example, be disposed inside casing. In such an embodiment, the production tubing may provide a conduit for some or all of the production 121 (e.g., oil and gas) passing through the wellbore 120 and the casing.
In some embodiments, the well surface system 124 includes a wellhead 130. The wellhead 130 may include a rigid structure installed at the “up-hole” end of the wellbore 120, at or near where the wellbore 120 terminates at the Earth’s surface 108. The wellhead 130 may include structures for supporting (or “hanging”) casing and production tubing extending into the wellbore 120. Production 121 may flow through the wellhead 130, after exiting the wellbore 120 and the well sub-surface system 122, including, for example, the casing and the production tubing. In some embodiments, the well surface system 124 includes flow regulating devices that are operable to control the flow of substances into and out of the wellbore 120. For example, the well surface system 124 may include one or more production valves 132 that are operable to control the flow of production 134. A production valve 132 may be fully opened to enable unrestricted flow of production 121 from the wellbore 120. Further, the production valve 132 may be partially opened to partially restrict (or “throttle”) the flow of production 121 from the wellbore 120. In addition, the production valve 132 may be fully closed to fully restrict (or “block”) the flow of production 121 from the wellbore 120, and through the well surface system 124.
In some embodiments, the wellhead 130 includes a choke assembly. For example, the choke assembly may include hardware with functionality for opening and closing the fluid flow through pipes in the well system 106. Likewise, the choke assembly may include a pipe manifold that may lower the pressure of fluid traversing the wellhead. As such, the choke assembly may include a set of high-pressure valves and at least two chokes. These chokes may be fixed or adjustable or a mix of both. Redundancy may be provided so that if one choke is taken out of service, the flow can be directed through another choke. In some embodiments, pressure valves and chokes are communicatively coupled to the operation system 126. Accordingly, the operation system 126 may obtain wellhead data regarding the choke assembly as well as transmit one or more commands to components within the choke assembly in order to adjust one or more choke assembly parameters.
Keeping with FIG. 1 , in some embodiments, the well surface system 124 includes a surface sensing system 134. The surface sensing system 134 may include sensors for sensing characteristics of substances, including production 121, passing through or otherwise located in the well surface system 124. The characteristics may include, for example, pressure, temperature and flow rate of production 121 flowing through the wellhead 130, or other conduits of the well surface system 124, after exiting the wellbore 120. The surface sensing system 134 may also include sensors for sensing characteristics of the rig 101, such as bit depth, hole depth, drilling mudflow, hook load, rotary speed, etc.
In some embodiments, the surface sensing system 134 includes a surface pressure sensor 136 operable to sense the pressure of production 151 flowing through the well surface system 124, after it exits the wellbore 120. The surface pressure sensor 136 may include, for example, a wellhead pressure sensor that senses a pressure of production 121 flowing through or otherwise located in the wellhead 130. In some embodiments, the surface sensing system 134 includes a surface temperature sensor 138 operable to sense the temperature of production 151 flowing through the well surface system 124, after it exits the wellbore 120. The surface temperature sensor 138 may include, for example, a wellhead temperature sensor that senses a temperature of production 121 flowing through or otherwise located in the wellhead 130, referred to as “wellhead temperature” (T_wh). In some embodiments, the surface sensing system 134 includes a flow rate sensor 139 operable to sense the flow rate of production 151 flowing through the well surface system 124, after it exits the wellbore 120. The flow rate sensor 139 may include hardware that senses a flow rate of production 121 (Q_wh) passing through the wellhead 130. In some embodiments, downhole sensors and gauges are operable to capture production-related data (e.g., pressures, temperatures, etc.).
While FIG. 1 illustrates a configuration of components, other configurations may be used without departing from the scope of the disclosure. For example, various components in FIG. 1 may be combined to create a single component. As another example, the functionality performed by a single component may be performed by two or more components.
FIG. 2 is a block diagram that illustrates a production control system 214, and other parts of a system that interact with the production control system 214, according to one or more example embodiments. The production control system 214 is shown as including one or more sensors 216 (shown as the pressure sensor 136, the temperature sensor 138, and the flow rate sensor 139 in FIG. 1 ), a multiphase flow meter 218, an access module 220, and one or more processors 222 (shown as the operation system 126 in FIG. 1 ). The components of the production control system 214 are operatively connected and are configured to communicate with each other (e.g., via a bus, shared memory, a switch, wirelessly, etc.). In addition, the production control system 214 is configured to communicate with a data repository 202 and a control tool 212.
The one or more sensors 216 are arranged to capture data associated with a parameter (e.g., a pressure or a temperature) over a certain production period. The multiphase flow meter 218 is arranged to capture data pertaining to multiphase (e.g., gas, oil, and water components) production flow rates. The data captured by the one or more sensors 216 may be stored as sensor data 204 in the data repository 202. The data captured by the multiphase flow meter 218 may be stored as production data 206 in the data repository 202. The access module 218 may access the sensor data 204 and the production data 206 and may use this data as input for a system identification algorithm to generate a lower-order data-driven model that describes the multiphase flow production from a well. The lower-order model may be stored as data-driven model 208 in the data repository 202.
The one or more processors 222 are configured, in some example embodiments, to extract dynamically-relevant process data from the sensor data 204 and the production data 206 using a dynamic mode decomposition (DMD) algorithm. The one or more processors 222 are further configured to train the data-driven model 208 based on the extracted dynamically-relevant process data.
In addition, the one or more processors 222 update the data-driven model 208 using a data assimilation algorithm and production data received during a production process. Further, a processor 222 generates, using the updated data-driven model 208, an optimal control setting of the control tool 212 for causing an adjustment to a production system. The processor 222 may generate an instruction 210 for the control tool 212 to make an adjustment to the production system based on the optimal control setting. The processor 222 may execute the instruction 210 during the production process. The executing of the instruction causes the control tool 212 to perform the adjustment to the production system. In some embodiments, the control tool 212 is a production valve. In certain embodiments, the control tool 212 is a choke assembly. As shown in FIG. 2 , the control tool instructions 210 may be stored in the data repository 202.
FIG. 3 is a flow diagram that illustrates an algorithm for data assimilation using the production control system, according to one or more example embodiments. According to certain example embodiments, one or more steps shown in flow diagram 300 are performed by the production control system 214, which may also be executed on a computing system as shown in FIGS. 6A and 6B below.
In some example embodiments, at Step 302, sensor data 204 and production data 206 are utilized to initialize the data-driven model 208. Specifically, the production control system 214 calculates matrices A_DMD and B_DMD which define the data-driven model 208.
After the data-driven model 208 is initialized, the production control system 214 (e.g., the processor 222) predicts, at Step 304, an estimated value of a parameter. The estimated value is associated with a particular future time. Depending on the formulation of the objective function, the target criteria for optimization could be maximizing the oil recovery, minimizing the water cut, maximizing the net present value (NPV), etc.
Next, at Step 306, Kalman filter equations may be applied to the data-driven model 208 to increase the accuracy of estimation of parameter values. In some example embodiments, the production control system 214 updates the data-driven model 208 with an actual measurement for the parameter, that was obtained at the next time, t+1, and the covariance matrix is minimized. The covariance matrix represents the relationship between a pair of different states and parameters. By minimizing the covariance matrix, the uncertainty of a data-driven model is reduced. The production control system 214 then transitions to a new state, X(t + 1), after which the cycle starts over.
At each control step t, a Model Predictive Control (MPC) controller measures the current state of the system, X(t). The MPC controller is an advanced mathematical method of system optimization, which is used to control a process while satisfying a set of constraints. In this example, the control is performed by the control vector, and the constraints are defined by a data-driven model. Then, to predict the parameter value for the particular time t+1, the production control system 214 uses the data-driven model 208 to derive, at time t, an a priori state estimate for the next time step, t+1.
FIG. 4 illustrates a graphical representation of optimal control settings, according to one or more example embodiments. Upon updating the data-driven model 208 using the data assimilation algorithm and actual production data received during a production process, the production control system 214 generates, using the updated data-driven model 208, an optimal control setting of a control tool for causing an adjustment to a production system. FIG. 4 shows the output the data-driven model 208 as a series of constant choke settings in a predicted control input graph 406. The series is defined over a future control period (“prediction horizon”), and includes a number of sample times, t, t+1, t+2, ... , t+n.
In addition, FIG. 4 shows a required target graph 402 and a predicted target graph 404. The target graph 402 illustrates the expected results for a target criterion, such as maximized oil recovery, minimized water cut, or maximized NPV. The predicted target graph 404 illustrates the results of the MPC operation. In some instances, the predictions should converge to expected values.
FIG. 5 is a flowchart illustrating operations of the production control system 214 in performing a method for controlling and optimizing hydrocarbon production, according to one or more example embodiments. Steps of the method 500 may be performed using the components described above with respect to FIG. 2 . One or more blocks in FIG. 5 may be performed by a computing system such as that shown and described below in FIGS. 6A and 6B. While the various blocks in FIG. 5 are presented and described sequentially, one of ordinary skill in the art will appreciate that some or all of the blocks may be executed in different orders, may be combined or omitted, and some or all of the blocks may be executed in parallel. Furthermore, the blocks may be performed actively or passively.
At Step 502, the access module 220 accesses sensor data 204 captured by one or more sensors 216 from the well at the first time, and production data 206 for the well at the first time. The sensor data and the production data may be accessed from a database or may be received from sensors in real-time.
At Step 504, the one or more processors 222 extract dynamically-relevant process data from the sensor data 204 and the production data 206 obtained at the first time, using a dynamic mode decomposition (DMD) algorithm. In some example embodiments, the dynamically-relevant process data characterizes a temporal change in a system state. In some instances, the dynamically-relevant information is extracted from the collected data.
At Step 506, the one or more processors 222 train a data-driven model 208 for describing production fluid dynamics of the well, based on the extracted dynamically-relevant process data, to predict, for a parameter, an estimated parameter value associated with a second time and a parameter. The parameter pertains to hydrocarbon production from the well. In some example embodiments, the data-driven model 208 is a lower-order, non-linear data-driven model. In various example embodiments, the parameter is at least one of a multiphase (e.g., oil, gas, or water) production flow rate, a wellbore pressure, or a temperature.
At Step 508, the access module 220 accesses the estimated parameter value associated with the second time. The parameter value may be accessed from a database (e.g., the data repository 202).
At Step 510, the one or more hardware processors 222 update the data-driven model 208 using a data assimilation algorithm and the production data 206 received during a production process at the second time. In some example embodiments, the updating of the data-driven model 208 using the data assimilation algorithm and the production data 206 captured during a production process includes adjusting the estimated parameter value to match an actual measurement value obtained during the production process.
At Step 512, the one or more hardware processors 222 generate, using the updated data-driven model 208, an optimal control setting of a control tool 212 for causing an adjustment to a production system. In some example embodiments, the control tool 212 is a production valve. In certain example embodiments, the control tool 212 is a choke assembly. In various example embodiments, the optimal control setting is generated using an optimization algorithm to maximize hydrocarbon recovery over a particular period of production.
At Step 514, the one or more hardware processors 222 generate an instruction for the control tool 212 to make the adjustment to the production system based on the optimal control setting.
At Step 516, the one or more hardware processors 222 execute the instruction during the production process. The executing of the instruction causes the adjustment, by the control tool 212, to the production system.
Example embodiments may be implemented on a computing system. Any combination of mobile, desktop, server, router, switch, embedded device, or other types of hardware may be used. For example, as shown in FIG. 6A, the computing system 600 may include one or more computer processors 602, non-persistent storage 604 (e.g., volatile memory, such as random access memory (RAM) or cache memory), persistent storage 606 (e.g., a hard disk, an optical drive such as a compact disk (CD) drive or digital versatile disk (DVD) drive, or a flash memory), a communication interface 612 (e.g., Bluetooth interface, infrared interface, network interface, or optical interface), and numerous other elements and functionalities.
The computer processor(s) 602 may be an integrated circuit for processing instructions. For example, the computer processor(s) 602 may be one or more cores or micro-cores of a processor. The computing system 600 may also include one or more input devices 610, such as a touchscreen, keyboard, mouse, microphone, touchpad, or electronic pen.
The communication interface 612 may include an integrated circuit for connecting the computing system 600 to a network (not shown) (e.g., a local area network (LAN), a wide area network (WAN), such as the Internet, mobile network, or any other type of network) or to another device, such as another computing device.
Further, the computing system 600 may include one or more output devices 608, such as a screen (e.g., a liquid crystal display (LCD), a plasma display, touchscreen, cathode ray tube (CRT) monitor, or projector), a printer, external storage, or any other output device. One or more of the output devices may be the same or different from the input device(s). The input and output device(s) may be locally or remotely connected to the computer processor(s) 602, non-persistent storage 604, and persistent storage 606. Many different types of computing systems exist, and the aforementioned input and output device(s) may take other forms.
Software instructions in the form of computer readable program code to perform embodiments of the disclosure may be stored, in whole or in part, temporarily or permanently, on a non-transitory computer readable medium such as a CD, DVD, storage device, a diskette, a tape, flash memory, physical memory, or any other computer readable storage medium. Specifically, the software instructions may correspond to computer readable program code that when executed by a processor(s) is configured to perform one or more embodiments of the disclosure.
The computing system 600 in FIG. 6A may be connected to or be a part of a network. For example, as shown in FIG. 6B, the network 616 may include multiple nodes (e.g., node X 618 or node Y 620). Each node may correspond to a computing system, such as the computing system shown in FIG. 6B, or a group of nodes combined may correspond to the computing system shown in FIG. 6B. By way of an example, embodiments of the disclosure may be implemented on a node of a distributed system that is connected to other nodes. By way of another example, embodiments of the disclosure may be implemented on a distributed computing system having multiple nodes, where each portion of the disclosure may be located on a different node within the distributed computing system. Further, one or more elements of the aforementioned computing system 614 may be located at a remote location and connected to the other elements over a network.
Although not shown in FIG. 6B, the node may correspond to a blade in a server chassis that is connected to other nodes via a backplane. By way of another example, the node may correspond to a server in a data center. By way of another example, the node may correspond to a computer processor or micro-core of a computer processor with shared memory or resources.
The nodes (e.g., node X 618 or node Y 620) in the network 616 may be configured to provide services for a client device 622. For example, the nodes may be part of a cloud computing system. The nodes may include functionality to receive requests from the client device 622 and transmit responses to the client device 622. The client device 622 may be a computing system, such as the computing system shown in FIG. 6B. Further, the client device 622 may include or perform all or a portion of one or more embodiments of the disclosure.
The previous description of functions presents only a few examples of functions performed by the computing system of FIG. 6A and the nodes or client device in FIG. 6B. Other functions may be performed using one or more embodiments of the disclosure.
While the disclosure has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this disclosure, will appreciate that other embodiments can be devised which do not depart from the scope of the disclosure as disclosed. Accordingly, the scope of the disclosure should be limited only by the attached claims.
Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications are possible in the example embodiments without materially departing from this invention. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims. In the claims, means-plus-function clauses are intended to cover the structures described herein as performing the recited function and not only structural equivalents, but also equivalent structures. Thus, although a nail and a screw may not be structural equivalents in that a nail employs a cylindrical surface to secure wooden parts together, whereas a screw employs a helical surface, in the environment of fastening wooden parts, a nail and a screw may be equivalent structures. It is the express intention of the applicant not to invoke 35 U.S.C. § 112, paragraph 6 for any limitations of any of the claims herein, except for those in which the claim expressly uses the words ‘means for’ together with an associated function.

Claims

What is claimed:

1. A method comprising:

accessing an estimated parameter value associated with a second time and a parameter, the parameter pertaining to production from a well, the estimated parameter value being predicted by a data-driven model for describing production fluid dynamics of the well, based on sensor data and production data obtained at a first time;

updating the data-driven model using a data assimilation algorithm and the production data obtained during a production process at the second time, the updating being performed using one or more hardware processors; and

generating, using the updated data-driven model, an optimal control setting of a control tool for causing an adjustment to a production system.

2. The method of claim 1, further comprising:

accessing the sensor data captured by one or more sensors from the well at the first time, and production data for the well at the first time;

extracting dynamically relevant process data from the sensor data and the production data using a dynamic mode decomposition (DMD) algorithm; and

training the data-driven model, based on the extracted dynamically relevant process data, to predict the estimated parameter value associated with the second time.

3. The method of claim 2, wherein the dynamically relevant process data characterizes a temporal change in a system state.

4. The method of claim 1, further comprising:

generating an instruction for the control tool to make the adjustment to the production system based on the optimal control setting.

5. The method of claim 4, further comprising:

executing the instruction during the production process, the executing of the instruction causing the adjustment, by the control tool, to the production system.

6. The method of claim 1, wherein the control tool is a production valve.

7. The method of claim 1, wherein the control tool is a choke assembly.

8. The method of claim 1, wherein the data-driven model is a lower-order, non-linear data-driven model.

9. The method of claim 1, wherein the optimal control setting is generated using an optimization algorithm to maximize hydrocarbon recovery over a particular period of production.

10. The method of claim 1, wherein the parameter is at least one of a multiphase production flow rate, a wellbore pressure, or a temperature.

11. The method of claim 1, wherein the updating of the data-driven model using the data assimilation algorithm and production data obtained during the production process includes:

adjusting the estimated parameter value to match an actual measurement value obtained during the production process.

12. A system comprising:

one or more sensors arranged to capture sensor data pertaining to one or more wellhead pressure values in a well;

a multiphase flow meter arranged to capture production data pertaining to multiphase production flow rates of the well;

an access module configured to access an estimated parameter value associated with a second time and a parameter, the parameter pertaining to production from the well, the estimated parameter value being predicted by a data-driven model for describing production fluid dynamics of the well, based on the sensor data and the production data obtained at a first time; and

one or more hardware processors configured to:

update the data-driven model using a data assimilation algorithm and the production data received during a production process at the second time; and

13. The system of claim 12, further comprising:

an access module configured to access the sensor data captured by one or more sensors from the well at the first time, and production data for the well at the first time;

wherein the one or more hardware processors are further configured to:

extract dynamically relevant process data from the sensor data and the production data using a dynamic mode decomposition (DMD) algorithm; and

train the data-driven model, based on the extracted dynamically relevant process data, to predict the estimated parameter value associated with the second time.

14. The system of claim 12, wherein the one or more hardware processors are further configured to generate an instruction for the control tool to make the adjustment to the production system based on the optimal control setting.

15. The system of claim 14, wherein the one or more hardware processors are further configured to execute the instruction during the production process, the executing of the instruction causing the adjustment, by the control tool, to the production system.

16. The system of claim 12, wherein the optimal control setting is generated using an optimization algorithm to maximize hydrocarbon recovery over a particular period of production.

17. The system of claim 12, wherein the parameter is at least one of a multiphase production flow rate, a wellbore pressure, or a temperature.

18. The system of claim 12, wherein the updating of the data-driven model using the data assimilation algorithm and production data obtained during the production process includes:

19. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

updating the data-driven model using a data assimilation algorithm and the production data obtained during a production process at the second time; and

20. The non-transitory machine-readable storage medium of claim 19, wherein the operations further comprise: