CN114737948A - Intelligent wellbore pressure control method and device based on physical constraint - Google Patents

Intelligent wellbore pressure control method and device based on physical constraint Download PDF

Info

Publication number
CN114737948A
CN114737948A CN202210222947.1A CN202210222947A CN114737948A CN 114737948 A CN114737948 A CN 114737948A CN 202210222947 A CN202210222947 A CN 202210222947A CN 114737948 A CN114737948 A CN 114737948A
Authority
CN
China
Prior art keywords
throttle valve
opening
parameters
pressure
bottom hole
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210222947.1A
Other languages
Chinese (zh)
Inventor
祝兆鹏
宋先知
姚学喆
李根生
黄中伟
段世明
胡晓丽
余簿文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Petroleum Beijing
Original Assignee
China University of Petroleum Beijing
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China University of Petroleum Beijing filed Critical China University of Petroleum Beijing
Priority to CN202210222947.1A priority Critical patent/CN114737948A/en
Publication of CN114737948A publication Critical patent/CN114737948A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E21—EARTH DRILLING; MINING
    • E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B47/00—Survey of boreholes or wells
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH DRILLING; MINING
    • E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
    • E21B43/12—Methods or apparatus for controlling the flow of the obtained fluid to or in wells
    • E21B43/121—Lifting well fluids
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH DRILLING; MINING
    • E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B47/00—Survey of boreholes or wells
    • E21B47/06—Measuring temperature or pressure
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Mining & Mineral Resources (AREA)
  • Geology (AREA)
  • Geochemistry & Mineralogy (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Fluid Mechanics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Geophysics (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Operation Control Of Excavators (AREA)

Abstract

The invention provides a physical constraint-based intelligent wellbore pressure control method and a physical constraint-based intelligent wellbore pressure control device, wherein the method comprises the following steps: acquiring pressure-controlled drilling data of a drilling well; constructing an input vector according to the pressure-controlled drilling data of the drilling well and the input parameters of a throttle valve opening adjusting model, wherein the throttle valve opening adjusting model is trained by utilizing constraint conditions, a neural network and historical pressure-controlled drilling data of a drilled reference well, and the constraint conditions are established by the incidence relation between the constraint parameters and the throttle valve opening; inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain the predicted calculated bottom hole pressure; and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector, returning to the execution of the prediction process, and if so, adjusting the throttle valve according to the predicted throttle valve opening. The stability and the generalization capability of the throttle opening adjusting model can be effectively improved.

Description

Intelligent wellbore pressure control method and device based on physical constraint
Technical Field
The invention relates to the technical field of oil and gas well drilling, in particular to a wellbore pressure intelligent control method and device based on physical constraint.
Background
With the continuous deepening of oil and gas exploration and development, the key points of the oil and gas exploration and development develop towards deep layers and ultra-deep layers. However, deep strata often have the characteristics of high temperature, large formation pressure and narrow window of safe drilling fluid density, and if the drilling process measures are improper, complicated underground conditions such as overflow, gas invasion and the like are easy to occur, so that accurately controlling the pressure of a shaft and making the pressure of the shaft slightly higher than the formation pressure is a key technology for realizing safe drilling in deep high-temperature and high-pressure strata.
The traditional shaft pressure control is realized based on algorithms such as a PID controller, the shaft pressure control method has the problems of low control precision, poor stability and low reliability under the condition of a complex stratum, and due to the fact that control parameters are relatively fixed, the shaft pressure control method cannot be adjusted in a self-adaptive mode, robustness is not strong, overshoot phenomenon is easy to generate, and well leakage risk is greatly increased.
In recent years, the advantages of the artificial intelligence technology in the field of oil and gas exploration and development are gradually highlighted, and the artificial intelligence technology is widely applied to aspects of working condition diagnosis, parameter optimization and the like and achieves good effects. But it is still deficient in stability and reliability due to the lack of constraints of mechanism models and conventional empirical knowledge.
Disclosure of Invention
The method is used for solving the problems that when the existing artificial intelligence is applied to the pressure control of the shaft, the constraint parameters related to the opening of the throttle valve in the pressure control drilling data are not analyzed, and the constraint conditions are not established, so that the stability and the reliability of the pressure control of the shaft are poor.
In order to solve the technical problem, a first aspect of the present disclosure provides a method for intelligent wellbore pressure control based on physical constraints, including:
acquiring pressure-controlled drilling data of a drilling well;
constructing an input vector according to the pressure-controlled drilling data of the drilling well and input parameters of a throttle valve opening adjusting model, wherein the input parameters comprise constrained parameters and unconstrained parameters of the throttle valve opening, the unconstrained parameters at least comprise a target bottom hole pressure and a calculated bottom hole pressure, the throttle valve opening adjusting model is obtained by utilizing constrained conditions, a neural network and historical pressure-controlled drilling data of a drilling completion reference well, and the constrained conditions are established by the incidence relation between the constrained parameters and the throttle valve opening;
the following prediction process is performed: inputting the input vector into a throttle opening regulating model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain predicted calculated bottom hole pressure;
and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector, continuing to execute the prediction process, and if so, adjusting the throttle valve according to the predicted throttle valve opening.
As a further embodiment herein, the determination process of the input parameters of the throttle opening adjustment model includes:
acquiring historical pressure control drilling data and throttle valve opening of the reference well after drilling;
processing abnormal values and missing values of historical pressure control drilling data and the opening degree of a throttle valve;
calculating the correlation between each parameter in the pressure-controlled drilling data and the opening of the throttle valve according to the processed pressure-controlled drilling data and the opening of the throttle valve;
screening out parameters with the correlation larger than a preset value;
analyzing and screening out the change rule of the parameters and the opening degree of the throttle valve;
and taking the parameter with the change rule of following the change of the bottom hole pressure as a constraint parameter, and taking the parameter with the change rule of not following the change as a non-constraint parameter.
As a further embodiment herein, the throttle opening adjustment model training process comprises:
constructing a plurality of groups of sample data according to the historical pressure-controlled drilling data of the drilled reference well, wherein each group of sample data comprises an input parameter value and a real value of the opening degree of the throttle valve after corresponding regulation and control;
taking the constrained parameters and the unconstrained parameters of the throttle valve opening as inputs, taking the regulated throttle valve opening as an output, and establishing a neural network model;
constructing an error loss function according to the sample data and the neural network model;
establishing a constraint condition according to the incidence relation between the constraint parameters of the throttle valve opening and the throttle valve opening;
and solving parameters in the neural network model according to the error loss function and the constraint condition.
As a further embodiment herein, establishing the constraint condition according to the correlation of the constraint parameter of the throttle opening degree and the throttle opening degree includes:
determining the incidence relation between the constraint parameters of the throttle valve openings and the throttle valve openings based on a shaft annulus multiphase flow mechanism and/or the constraint parameters of the throttle valve openings and the change rule of the throttle valve openings;
and converting the incidence relation between the constraint parameters of the throttle opening and the throttle opening into inequality constraint conditions by using the throttle opening expression of the neural network model.
As a further embodiment herein, the constraint parameters of the throttle opening include: bottom hole pressure error, drilling fluid flow rate and drilling fluid density;
the unconstrained parameters of the throttle opening further comprise: sag and drilling fluid viscosity.
As a further embodiment herein, converting the association of the constraint parameter of each throttle opening with the throttle opening into an inequality constraint condition using the mathematical expression of the throttle opening of the neural network model comprises:
the inequality constraints are established using the following formula:
Figure BDA0003534423590000031
Figure BDA0003534423590000032
Figure BDA0003534423590000033
Figure BDA0003534423590000034
wherein A isi、Bi、Ci、DiAs a constraint condition for each sample data, u ═ F (W)1,...,Wj,...,Wm,b1,...,bj,...,bm) A throttle valve opening expression output by the neural network model, rho is the drilling fluid density, m is the layer number of the neural network model, W1,...,Wj,...,WmFor the weights of the layers in the neural network model, b1,...,bj,...,bmFor the bias of each layer in each neural network model, q is the drilling fluid flow, and e is the bottom hole pressure error.
As a further embodiment herein, solving parameters in the neural network model according to the error loss function and constraints comprises:
converting an equation set consisting of the error loss function and the constraint condition into an unconstrained equation;
using an intelligent optimization algorithm, solving unconstrained equations to determine parameters in the neural network model.
A second aspect herein provides a wellbore pressure intelligent control device based on physical constraints, comprising:
the acquiring unit is used for acquiring the pressure-controlled drilling data of the drilling well;
the processing unit is used for constructing an input vector according to the pressure-controlled drilling data of the drilling well and input parameters of a throttle valve opening adjusting model, wherein the input parameters comprise constrained parameters and unconstrained parameters of the throttle valve opening, the unconstrained parameters at least comprise target bottom hole pressure and calculated bottom hole pressure, the throttle valve opening adjusting model is obtained by utilizing constrained conditions, a neural network and historical pressure-controlled drilling data of a drilled reference well, and the constrained conditions are established by the incidence relation between the constrained parameters and the throttle valve opening;
a prediction unit for performing a prediction process of: inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain predicted calculated bottom hole pressure;
and the execution unit is used for judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector, and continuing to execute the prediction process by the prediction unit, and if so, adjusting the throttle valve according to the predicted throttle valve opening.
A third aspect herein provides a computer apparatus comprising a memory, a processor, and a computer program stored on the memory, the computer program when executed by the processor, performing the instructions of the method according to any of the preceding embodiments.
A fourth aspect herein provides a computer storage medium having stored thereon a computer program which, when executed by a processor of a computer device, executes instructions of a method according to any of the preceding embodiments.
According to the physical constraint-based wellbore pressure intelligent control method and device, historical pressure control drilling data of a drilled reference well are analyzed, input parameters related to the opening of the throttle valve are determined, dimensionality of the input data can be reduced, input of irrelevant data is reduced, and training efficiency of a throttle valve opening adjusting model is improved. The input parameters are divided into the constraint parameters and the non-constraint parameters of the throttle opening, the constraint parameters are used for constructing constraint conditions, the neural network and the historical pressure-controlled drilling data of the drilled reference well are used for training the throttle opening adjusting model, so that the throttle opening adjusting model has certain interpretability, and the stability and the generalization capability of the throttle opening adjusting model are effectively improved. Applying the throttle opening adjusting model to a wellbore pressure test of a drilling well, and constructing an input vector according to pressure control drilling data of the drilling well and input parameters of the throttle opening adjusting model; executing the process of throttle valve opening prediction and bottom hole pressure prediction; and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is within a preset range, if not, updating the input vector, returning to the execution of the prediction process, if so, adjusting the throttle valve by using the predicted throttle valve opening, and accurately predicting to obtain the throttle valve opening by using a throttle valve opening adjusting model established by the drilled reference well, so that the high-efficiency and accurate control of the wellbore pressure under the complex stratum condition is realized, and the method has important guiding significance for reducing the drilling risk and realizing safe drilling.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram illustrating a wellbore pressure intelligent control system based on physical constraints in accordance with embodiments herein;
FIG. 2 illustrates a flow chart of a method of determining a throttle opening adjustment model according to embodiments herein;
FIG. 3 is a block diagram illustrating a neural network model according to an embodiment herein;
FIG. 4 shows a flow diagram of a neural network model parameter solution process according to an embodiment herein;
FIG. 5 is a flow chart illustrating a process for determining input parameters for a throttle opening adjustment model in accordance with an embodiment herein;
FIG. 6 illustrates a flow chart of a method of intelligent control of wellbore pressure based on physical constraints according to embodiments herein;
FIG. 7 illustrates a flow chart of a wellbore pressure intelligent control device based on physical constraints according to embodiments herein;
fig. 8 shows a block diagram of a computer device according to an embodiment of the present disclosure.
Description of the figures the symbols:
100. a first computing device;
110. a client;
120. a database;
130. a second computing device;
310. an input layer;
320. a first hidden layer;
330. a second hidden layer;
340. an output layer;
710. an acquisition unit;
720. a processing unit;
730. a prediction unit;
740. an execution unit;
802. a computer device;
804. a processor;
806. a memory;
808. a drive mechanism;
810. an input/output module;
812. an input device;
814. an output device;
816. a presentation device;
818. a graphical user interface;
820. a network interface;
822. a communication link;
824. a communication bus.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the scope of protection given herein.
It should be noted that the terms "first," "second," and the like in the description and claims herein and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments herein described are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.
The present specification provides method steps as described in the examples or flowcharts, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual system or apparatus product executes, it can execute sequentially or in parallel according to the method shown in the embodiment or the figures.
It should be noted that the managed pressure drilling data referred to herein are all information and data authorized by the user or sufficiently authorized by each party.
In an embodiment herein, there is provided an intelligent wellbore pressure control system based on physical constraints, as shown in fig. 1, the intelligent wellbore pressure control system based on physical constraints comprising: a first computing device 100, a client 110, a database 120, and a second computing device 130.
The first computing device 100 is configured to analyze historical pressure-controlled drilling data of a drilled reference well, and determine input parameters related to the opening of the throttle valve, where the input parameters include constrained parameters and unconstrained parameters of the opening of the throttle valve, and the unconstrained parameters at least include a target bottom hole pressure and a calculated bottom hole pressure; according to the historical pressure-controlled drilling data of the drilled reference well, constructing a plurality of groups of sample data, wherein each group of sample data comprises an input parameter value and a true value of the opening of the throttle valve after corresponding regulation; taking a constraint parameter and a non-constraint parameter of the opening of the throttle valve as input, taking the regulated opening of the throttle valve as output, and establishing a neural network model; adjusting the structure of the neural network model by using a grid search algorithm or a random search algorithm; constructing an error loss function according to the sample data and the neural network model; establishing a constraint condition according to the incidence relation between the constraint parameter of the throttle opening and the throttle opening; and solving parameters in the neural network model according to the error loss function and the constraint condition, wherein the neural network model with fixed parameter values is a throttle opening degree adjusting model.
The constraint parameters of the throttle opening refer to parameters having a certain response rule with the throttle opening, and include, for example, a bottom hole pressure error (target bottom hole pressure — calculated bottom hole pressure), a drilling fluid flow rate, and a drilling fluid density. The unconstrained parameters of the throttle opening refer to that the relationship between the unconstrained parameters and the throttle opening is correlated with the throttle opening but irregular, and comprise a target bottom hole pressure, a calculated bottom hole pressure, a vertical depth and a drilling fluid viscosity, for example.
The correlation between the constraint parameter and the throttle opening is a following relationship, wherein the following relationship comprises a direct proportion relationship and an inverse proportion relationship. The proportional relation means that the restriction parameter is increased, the opening of the throttle valve is increased, the restriction parameter is decreased, and the opening of the throttle valve is decreased. The inverse ratio relation means that the restriction parameter is decreased, the throttle opening is increased, the restriction parameter is increased, and the throttle opening is decreased. In specific implementation, the incidence relation between the constraint parameters and the throttle opening can be represented by the deviation of the constraint parameters calculated by a throttle opening expression, the deviation of the constraint parameters calculated by the throttle opening expression is greater than 0, the constraint parameters and the throttle opening are in direct proportion, the deviation of the constraint parameters calculated by the throttle opening expression is less than 0, and the constraint parameters and the throttle opening are in inverse proportion.
The client 110 is configured to obtain the managed pressure drilling data while drilling and send it to the second computing device 130.
In specific implementation, the client 110 may be a field dedicated device or a software program installed in an intelligent terminal, and the user may input the drilling data under controlled pressure in the client 110, or the client may automatically obtain the drilling data under controlled pressure from a database storing the drilling data under controlled pressure, and the manner in which the client 110 obtains the drilling data under controlled pressure is not limited herein.
The managed pressure drilling data includes, but is not limited to, target bottom hole pressure, calculated bottom hole pressure, conventional logging data, measurement while drilling data, drilling fluid performance parameters, and the like. The target bottom hole pressure is earthquake real pressure, the calculated bottom hole pressure is bottom hole pressure calculated after the current throttle opening is input into a bottom hole pressure calculation model, pressure-controlled drilling data can be obtained from drilling and logging equipment and measurement-while-drilling equipment, the table 1 specifically shows that the pressure-controlled drilling data shown in the table 1 is only partial data, and parameters specifically included in the pressure-controlled drilling data are not limited. In a specific implementation, the client 110 may also directly obtain parameters according to the input vector of the throttle opening scheduling model and send the parameters to the second computing device 130.
TABLE 1
Figure BDA0003534423590000081
Figure BDA0003534423590000091
The database 120 stores a throttle opening adjustment model and its parameters, and a bottom hole pressure calculation model and its parameters.
The throttle opening adjusting model can adopt the structure of the existing neural network model, and the concrete network structure is not limited in the text.
The downhole pressure calculation model is an annular multiphase flow mechanism model, and is not detailed in detail in the text with specific reference to the prior art.
The second computing device 130 receives the controlled pressure drilling data sent by the client 110 during drilling; constructing an input vector according to the pressure-controlled drilling data of the drilling well and the input parameters of the throttle valve opening degree adjusting model; the following prediction process is performed: calling a throttle opening adjusting model from the database 120, and inputting an input vector into the throttle opening adjusting model to obtain a predicted throttle opening; calling a bottom hole pressure calculation model from the database 120, and inputting the opening of the predicted throttle valve into the bottom hole pressure calculation model to obtain predicted calculated bottom hole pressure; and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector (namely, replacing the original calculated bottom hole pressure with the current predicted and calculated bottom hole pressure, updating parameters related to the calculated bottom hole pressure in the input vector, such as the calculated bottom hole pressure and a bottom hole pressure error), returning to execute the prediction process, and if so, adjusting the throttle valve by using the current predicted throttle valve opening.
In particular, the first computing device 100 and the second computing device 130 may be the same device, including but not limited to a smart terminal, a tablet computer, a desktop computer, a server, and the like.
The client 110 may be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device, and the like. Wherein, wearable equipment of intelligence can include intelligent bracelet, intelligent wrist-watch, intelligent glasses, intelligent helmet etc.. Of course, the client is not limited to the electronic device with a certain entity, and may also be software running in the electronic device.
The database 120 may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the database 120 may be at least one storage device located remotely from the aforementioned computing device.
According to the embodiment, the historical pressure control drilling data of the drilled reference well are analyzed, the input parameters related to the opening of the throttle valve are determined, the dimensionality of the input data can be reduced, the input of irrelevant data is reduced, and the training efficiency of the throttle valve opening adjusting model is improved. The input parameters are divided into the constraint parameters and the non-constraint parameters of the throttle opening, the constraint parameters are used for constructing constraint conditions, the neural network and the historical pressure-controlled drilling data of the drilled reference well are used for training the throttle opening adjusting model, so that the throttle opening adjusting model has certain interpretability, and the stability and the generalization capability of the throttle opening adjusting model are effectively improved. Applying the throttle opening adjusting model to a wellbore pressure test of a drilling well, and constructing an input vector according to pressure-controlled drilling data of the drilling well and input parameters of the throttle opening adjusting model; executing the process of throttle valve opening prediction and bottom hole pressure prediction; and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is within a preset range, if not, updating the input vector, returning to the execution of the prediction process, if so, adjusting the throttle valve by using the predicted throttle valve opening, and accurately predicting to obtain the throttle valve opening by using a throttle valve opening adjusting model established by the drilled reference well, so that the high-efficiency and accurate control of the wellbore pressure under the complex stratum condition is realized, and the method has important guiding significance for reducing the drilling risk and realizing safe drilling.
In an embodiment herein, there is provided a method for determining a throttle opening adjustment model, as shown in fig. 2, including:
and step 210, analyzing historical pressure control drilling data of the reference well after drilling at a plurality of sampling moments, and determining input parameters of a throttle valve opening adjusting model.
The input parameters comprise constrained parameters and unconstrained parameters related to the opening degree of the throttle valve, and the unconstrained parameters at least comprise a target bottom hole pressure and a calculated bottom hole pressure. In one embodiment, the constraint parameters of the throttle opening include a bottom hole pressure error, a drilling fluid flow rate and a drilling fluid density, and the non-constraint parameters of the throttle opening further include a vertical depth and a drilling fluid viscosity.
And step 220, constructing multiple groups of sample data according to the historical pressure control drilling data of the drilled reference well, wherein each group of sample data comprises an input parameter value and a real value of the opening degree of the throttle valve after corresponding regulation.
Wherein the drilling completion reference well is a drilling completion well with similar geological conditions with the well to be analyzed. Historical managed pressure drilling data is shown with reference to table 1 above. The real value of the opening degree of the regulated throttle valve in each group of sample data is the opening degree of the throttle valve corresponding to the regulation of the well bottom pressure to the target well bottom pressure in the input parameters, and can be determined according to historical regulation.
And step 230, taking the constrained parameters and the unconstrained parameters of the opening of the throttle valve as input, taking the regulated and controlled opening of the throttle valve as output, and establishing a neural network model.
The neural network model can be an existing CNN neural network model, wherein the input of the input layer comprises a constraint parameter and an unconstrained parameter of the throttle valve opening, and the number of layers of the hidden layer can be selected according to requirements. In the specific implementation, the structure of the neural network model may be adjusted by using a grid search algorithm or a random search algorithm, and the specific implementation process of the grid search algorithm and the random search algorithm may refer to the prior art, which is not described in detail herein.
In one embodiment, as shown in fig. 3, the neural network model includes an input layer 310, a first hidden layer 320, a second hidden layer 330 and an output layer 340, and if the activation function of each layer of nodes may be the same or different. Assuming that the activation functions of each layer of nodes are the same and are all f, the neural network model corresponds to the mathematical expression:
upred＝f(W3×f(W2×f(W1×X+b1)+b2)+b3)；
wherein u ispredIs the predicted throttle opening; f is an activation function; w1、W2、W3Is the weight between layers; b1、b2、b3Is an offset.
Step 240, constructing an error loss function according to the sample data and the neural network model, as shown in the following formula:
Figure BDA0003534423590000111
wherein MAE is the mean absolute error; n is the data volume; u. ofi,predIs the predicted ith throttle opening; u. ui,trueThe ith real throttle opening.
And 250, establishing a constraint condition according to the incidence relation between the constraint parameter of the throttle opening and the throttle opening.
When the method is implemented, firstly, determining the incidence relation between the constraint parameters of the opening of each throttle valve and the opening of the throttle valve based on a shaft annulus multiphase flow mechanism and/or the constraint parameters of the opening of the throttle valve and the change rule of the opening of the throttle valve; and then, converting the association relation between the constraint parameters of the throttle valve opening and the throttle valve opening into inequality constraint conditions by using a mathematical expression of the throttle valve opening of the neural network model.
The well bore annulus multiphase flow mechanism can refer to the prior art, and is not detailed here. The constraint parameters of the throttle opening and the change rule of the throttle opening can determine the change rule by fitting the constraint parameters of the historical throttle opening of the drilling reference well and the curve of the throttle opening.
Taking the constraint parameters including bottom hole pressure error, drilling fluid flow rate, and drilling fluid density as examples, the constraint conditions established in step 250 include the constraint conditions expressed by the following equations:
Figure BDA0003534423590000112
Figure BDA0003534423590000113
Figure BDA0003534423590000114
Figure BDA0003534423590000115
wherein A isi、Bi、Ci、DiAs a constraint condition under each sample data, AiIndicating that the throttle opening increases with increasing drilling fluid density p, B, at a given bottom hole pressureiIndicating that the bottom hole pressure is constant, the throttle opening increases as the drilling fluid flow q increases, CiIndicating that the bottom hole pressure error e is negative and the absolute value increases, the throttle opening increases, DiIndicating that the bottom hole pressure error e is positive and the absolute value increases the throttle opening decreases.
u＝F(W1,...,Wj,...,Wm,b1,...,bj,...,bm) A throttle valve opening expression output by the neural network model, m is the number of layers of the neural network model, W1,...,Wj,...,WmFor the weights of the layers in the neural network model, b1,...,bj,...,bmFor the bias of each layer in each neural network model, e is the bottom hole pressure error.
And step 260, solving parameters in the neural network model according to the error loss function and the constraint condition.
Specifically, as shown in fig. 4, the implementation process of this step includes:
step 410, converting the equation set composed of the error loss function and the constraint condition into an unconstrained equation, specifically, converting the equation set composed of the error loss function and the constraint condition into an unconstrained equation represented by the following formula by using a penalty function interior point method:
Figure BDA0003534423590000121
wherein, W, b and lambda are weight matrix, bias matrix and constraint term weight matrix in the neural network model respectively, n is sample data size, ui,predFor predicted throttle opening value, ui,trueTrue value of throttle opening, λ1、λ2、λ3And lambda4To constrain the weights in the term weight matrix, Ai、Bi、CiAnd DiFor the constraint terms under the ith sample data, the respective constraint term calculation formulas refer to the foregoing embodiments.
And step 420, solving an unconstrained equation by using an intelligent optimization algorithm to determine parameters in the neural network model, wherein the parameters in the neural network model comprise weights and offsets, namely W and b. During implementation, parameters in the neural network model can be determined by using intelligent optimization algorithms such as a genetic algorithm and the like.
The embodiment converts the constrained problem into the unconstrained problem, so that the solving complexity can be reduced, and the solving efficiency can be improved.
In an embodiment, as shown in fig. 5, the step 210 of analyzing the historical managed pressure drilling data at a plurality of sampling times of the reference well after drilling, and determining the input parameters of the throttle opening adjustment model includes:
and step 510, obtaining historical pressure control drilling data and throttle opening of the drilled reference well.
The pressure control drilling data at each moment correspond to a throttle opening, namely the throttle opening at the moment.
And step 520, processing abnormal values and missing values of the historical pressure-controlled drilling data and the opening degree of the throttle valve.
The abnormal value processing is, for example, analyzing whether an abnormal value exists in each parameter in the managed pressure drilling data, and if the abnormal value exists, deleting the corresponding value or limiting the corresponding value within a predetermined range. The missing value processing is, for example, a filling processing of missing parameter values.
And step 530, calculating the correlation between each parameter in the pressure-controlled drilling data and the opening of the throttle valve according to the processed pressure-controlled drilling data and the opening of the throttle valve.
In practice, correlation between each parameter in the pressure control drilling data and the opening degree of the throttle valve can be calculated by utilizing the Pearson correlation coefficient shown in the following formula:
Figure BDA0003534423590000131
where ρ isXYIs Pearson correlation coefficient; cov (X, Y) is the covariance between each parameter and the output; d (X), D (Y) are the input parameters and the output variance of the throttle valve opening degree adjusting model respectively.
And 540, screening out parameters with the correlation larger than a preset value.
The predetermined value may be selected according to an actual situation, for example, 0.5, and a specific value thereof is not limited herein.
And 550, analyzing and screening out the change rule of the parameters and the opening of the throttle valve.
In implementation, the parameter can be selected as the horizontal coordinate, the throttle opening is the vertical coordinate, a curve is drawn, and then the change rule between the parameter and the throttle opening is determined.
And 560, taking the parameter with the change rule of following the change of the bottom hole pressure as a constraint parameter, and taking the parameter with the change rule of not following the change as a non-constraint parameter.
In the training stage and the application stage of the throttle valve opening adjusting model, input parameters of the throttle valve opening adjusting model are standardized and normalized data, and the method can be implemented according to the following standardized formula and normalized formula:
a normalized formula:
Figure BDA0003534423590000132
normalization formula:
Figure BDA0003534423590000133
in the formula, XstandardizationIs a normalized feature; xiIs an original characteristic; mu is the mean value of the original features; sigma is the standard deviation of the original characteristics; xnormalizationIs a normalized feature; xminIs the minimum of the original features; xmaxIs the maximum of the original features.
According to the embodiment, the dimensionality of input parameters can be reduced, the input of useless irrelevant data is reduced, the training efficiency of the throttle valve opening degree adjusting model is improved, and the input parameters are optimized through correlation analysis. In order to reduce the influence of dimension units and magnitude on the training effect, the parameters are subjected to non-dimensionalization processing by standardization or normalization.
Based on the establishment of the throttle opening adjustment model, the method can be used for intelligent wellbore pressure control based on physical constraints, and in an embodiment herein, there is also provided a method for intelligent wellbore pressure control based on physical constraints, as shown in fig. 6, including:
step 610, acquiring pressure-controlled drilling data of the drilling.
Wherein the well drilling is the well under excavation within a certain distance range from the completion reference well or the well under excavation with similar geological conditions to the completion reference well.
And step 620, constructing an input vector according to the pressure-controlled drilling data of the drilling well and the input parameters of the throttle valve opening adjusting model.
The arrangement sequence of the input vectors is the same as the input parameter sequence during the training of the throttle opening regulating model.
Step 630, the following prediction process is performed: inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; and inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain the predicted and calculated bottom hole pressure.
Step 640, determining whether the difference between the predicted calculated bottom hole pressure and the target bottom hole pressure is within a preset range, if not, executing step 650, and if so, executing step 660.
Step 650, updating the input vector, and returning to execute the prediction process.
Step 660, the throttle is adjusted using the resulting predicted throttle opening.
The preset range can be determined according to the control precision, and specific values of the preset range are not limited in the text.
Taking the input parameters including bottom hole pressure error, calculated bottom hole pressure, target bottom hole pressure, drilling fluid flow, drilling fluid density, vertical depth and drilling fluid viscosity as examples, updating the input vector, namely recalculating the bottom hole pressure error according to the predicted calculated bottom hole pressure and the target bottom hole pressure, replacing the original bottom hole pressure error with the recalculated bottom hole pressure error, and replacing the original bottom hole pressure error with the predicted calculated bottom hole pressure.
According to the embodiment, the pressure-controlled drilling data, the pressure-controlled drilling experience knowledge (converted into constraint conditions) and the artificial intelligence algorithm are combined, and the self-adaptive accurate regulation and control of the wellbore pressure can be realized, so that the drilling risk is avoided, the non-production time is shortened, and the drilling cost is reduced.
Based on the same inventive concept, an intelligent wellbore pressure control device based on physical constraints is also provided, as described in the following embodiments. Because the principle of solving the problems of the intelligent wellbore pressure control device based on the physical constraint is similar to that of the intelligent wellbore pressure control method based on the physical constraint, the implementation of the intelligent wellbore pressure control device based on the physical constraint can refer to the intelligent wellbore pressure control method based on the physical constraint, and repeated parts are not described again. Specifically, as shown in fig. 7, the intelligent wellbore pressure control device based on physical constraints includes:
an obtaining unit 710 for obtaining managed pressure drilling data in drilling;
the processing unit 720 is configured to construct an input vector according to the pressure-controlled drilling data of the drilling well and input parameters of a throttle opening adjustment model, where the input parameters include constrained parameters and unconstrained parameters of the throttle opening, the unconstrained parameters at least include a target bottom-hole pressure and a calculated bottom-hole pressure, the throttle opening adjustment model is trained by using constrained conditions, a neural network and historical pressure-controlled drilling data of a drilled reference well, and the constrained conditions are established by an association relationship between the constrained parameters and the throttle opening;
a prediction unit 730, configured to perform the following prediction process: inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain the predicted calculated bottom hole pressure;
and the execution unit 740 is configured to determine whether a difference between the predicted calculated bottom hole pressure and the target bottom hole pressure is within a preset range, update the input vector if the difference is not within the preset range, return to the execution of the prediction process, and adjust the throttle valve according to the finally obtained predicted throttle opening if the difference is within the preset range.
According to the embodiment, the historical pressure control drilling data of the drilled reference well is analyzed, the input parameters related to the opening of the throttle valve are determined, the dimensionality of the input data can be reduced, the input of irrelevant data is reduced, and the training efficiency of the throttle valve opening adjusting model is improved. The input parameters are divided into the constraint parameters and the non-constraint parameters of the throttle opening, the constraint parameters are used for constructing constraint conditions, the neural network and the historical pressure-controlled drilling data of the drilled reference well are used for training the throttle opening adjusting model, so that the throttle opening adjusting model has certain interpretability, and the stability and the generalization capability of the throttle opening adjusting model are effectively improved. Applying the throttle opening adjusting model to a wellbore pressure test of a drilling well, and constructing an input vector according to pressure control drilling data of the drilling well and input parameters of the throttle opening adjusting model; executing the process of throttle valve opening prediction and bottom hole pressure prediction; and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is within a preset range, if not, updating the input vector, returning to the execution of the prediction process, if so, adjusting the throttle valve by using the predicted throttle valve opening, and accurately predicting to obtain the throttle valve opening by using a throttle valve opening adjusting model established by the drilled reference well, so that the high-efficiency and accurate control of the wellbore pressure under the complex stratum condition is realized, and the method has important guiding significance for reducing the drilling risk and realizing safe drilling.
In an embodiment herein, there is also provided a computer device, as shown in fig. 8, the computer device 802 may include one or more processors 804, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any memory 806 for storing information such as code and associated settings, data, etc., for any of the methods described in any of the preceding embodiments. For example, and without limitation, memory 806 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 802. In one case, when the processor 804 executes the associated instructions, which are stored in any memory or combination of memories, the computer device 802 can perform any of the operations of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808, such as a hard disk drive mechanism, an optical disk drive mechanism, etc., for interacting with any memory.
Computer device 802 may also include an input/output module 810(I/O) for receiving various inputs (via input device 812) and for providing various outputs (via output device 814)). One particular output mechanism may include a presentation device 816 and an associated graphical user interface 818 (GUI). In other embodiments, input/output module 810(I/O), input device 812, and output device 814 may also be excluded, as just one computer device in a network. Computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the above-described components together.
Communication link 822 may be implemented in any manner, such as over a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.
Corresponding to the methods in fig. 2, 5-6, the embodiments herein also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the above-described method.
Embodiments herein also provide computer readable instructions, wherein when executed by a processor, a program thereof causes the processor to perform the methods as shown in fig. 2, 5-6.
It should be understood that, in various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments herein.
It should also be understood that, in the embodiments herein, the term "and/or" is only one kind of association relation describing an associated object, meaning that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided herein, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments herein.
In addition, functional units in the embodiments herein may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The principles and embodiments of this document are explained herein using specific examples, which are presented only to aid in understanding the methods and their core concepts; meanwhile, for the general technical personnel in the field, according to the idea of this document, there may be changes in the concrete implementation and the application scope, in summary, this description should not be understood as the limitation of this document.

Claims (10)

1. A wellbore pressure intelligent control method based on physical constraints is characterized by comprising the following steps:
acquiring pressure-controlled drilling data of a drilling well;
constructing an input vector according to the pressure-controlled drilling data of the drilling well and input parameters of a throttle valve opening adjusting model, wherein the input parameters comprise constrained parameters and unconstrained parameters of the throttle valve opening, the unconstrained parameters at least comprise a target bottom hole pressure and a calculated bottom hole pressure, the throttle valve opening adjusting model is obtained by utilizing constrained conditions, a neural network and historical pressure-controlled drilling data of a drilling completion reference well, and the constrained conditions are established by the incidence relation between the constrained parameters and the throttle valve opening;
the following prediction process is performed: inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain predicted calculated bottom hole pressure;
and judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector, continuing to execute the prediction process, and if so, adjusting the throttle valve according to the predicted throttle valve opening.
2. The method of claim 1, wherein the determining of the input parameters of the throttle opening adjustment model comprises:
acquiring historical pressure control drilling data and throttle valve opening of the reference well after drilling;
processing abnormal values and missing values of historical pressure control drilling data and the opening degree of a throttle valve;
calculating the correlation between each parameter in the pressure-controlled drilling data and the opening of the throttle valve according to the processed pressure-controlled drilling data and the opening of the throttle valve;
screening out parameters with the correlation larger than a preset value;
analyzing and screening out the change rule of the parameters and the opening degree of the throttle valve;
and taking the parameter with the change rule of following the change of the bottom hole pressure as a constraint parameter, and taking the parameter with the change rule of not following the change as a non-constraint parameter.
3. The method of claim 2, wherein the throttle opening adjustment model training process comprises:
constructing a plurality of groups of sample data according to the historical pressure-controlled drilling data of the drilled reference well, wherein each group of sample data comprises an input parameter value and a real value of the opening degree of the throttle valve after corresponding regulation and control;
taking the constrained parameter and the unconstrained parameter of the opening of the throttle valve as input, taking the regulated and controlled opening of the throttle valve as output, and establishing a neural network model;
constructing an error loss function according to the sample data and the neural network model;
establishing a constraint condition according to the incidence relation between the constraint parameters of the throttle valve opening and the throttle valve opening;
and solving parameters in the neural network model according to the error loss function and the constraint condition.
4. The method of claim 3, wherein establishing the constraint condition based on the correlation of the constraint parameter of the throttle opening and the throttle opening comprises:
determining the incidence relation between the constraint parameters of the opening of each throttle valve and the opening of the throttle valve based on a wellbore annulus multiphase flow mechanism and/or the constraint parameters of the opening of the throttle valve and the change rule of the opening of the throttle valve;
and converting the incidence relation between the constraint parameters of the throttle valve opening and the throttle valve opening into inequality constraint conditions by using the mathematical expression of the throttle valve opening of the neural network model.
5. The method of claim 4, wherein the constraint parameter for the throttle opening comprises: bottom hole pressure error, drilling fluid flow rate and drilling fluid density;
the unconstrained parameters of the throttle opening further comprise: sag and drilling fluid viscosity.
6. The method of claim 5, wherein converting the correlation of the constraint parameter for each throttle opening to the throttle opening into an inequality constraint using the data expression for the throttle opening for the neural network model comprises:
the inequality constraints are established using the following formula:
Figure FDA0003534423580000021
Figure FDA0003534423580000022
Figure FDA0003534423580000023
Figure FDA0003534423580000031
wherein A isi、Bi、Ci、DiAs a constraint condition for each sample data, u ═ F (W)1,...,Wj,...,Wm,b1,...,bj,...,bm) A throttle valve opening expression output by the neural network model, rho is the drilling fluid density, m is the layer number of the neural network model, W1,...,Wj,...,WmFor the weights of the layers in the neural network model, b1,...,bj,...,bmFor the offsets of each layer in each neural network model, q is the drilling fluid flow, and e is the bottom hole pressure error.
7. The method of claim 3, wherein solving parameters in the neural network model based on the error loss function and constraints comprises:
converting an equation set consisting of the error loss function and the constraint condition into an unconstrained equation;
using an intelligent optimization algorithm, solving unconstrained equations to determine parameters in the neural network model.
8. An intelligent wellbore pressure control device based on physical constraints, comprising:
the acquiring unit is used for acquiring the pressure control drilling data of the drilling;
the processing unit is used for constructing an input vector according to the pressure-controlled drilling data of the drilling well and input parameters of a throttle valve opening adjusting model, wherein the input parameters comprise constrained parameters and unconstrained parameters of the throttle valve opening, the unconstrained parameters at least comprise target bottom hole pressure and calculated bottom hole pressure, the throttle valve opening adjusting model is obtained by utilizing constrained conditions, a neural network and historical pressure-controlled drilling data of a drilled reference well, and the constrained conditions are established by the incidence relation between the constrained parameters and the throttle valve opening;
a prediction unit for performing a prediction process of: inputting the input vector into a throttle opening adjusting model to obtain a predicted throttle opening; inputting the opening of the predicted throttle valve into a bottom hole pressure calculation model to obtain predicted calculated bottom hole pressure;
and the execution unit is used for judging whether the difference between the predicted and calculated bottom hole pressure and the target bottom hole pressure is in a preset range, if not, updating the input vector, and continuing to execute the prediction process by the prediction unit, and if so, adjusting the throttle valve according to the predicted throttle valve opening.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, performs the instructions of the method of any one of claims 1-7.
10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor of a computer device, executes instructions of a method according to any one of claims 1-7.
CN202210222947.1A 2022-03-07 2022-03-07 Intelligent wellbore pressure control method and device based on physical constraint Pending CN114737948A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210222947.1A CN114737948A (en) 2022-03-07 2022-03-07 Intelligent wellbore pressure control method and device based on physical constraint

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210222947.1A CN114737948A (en) 2022-03-07 2022-03-07 Intelligent wellbore pressure control method and device based on physical constraint

Publications (1)

Publication Number Publication Date
CN114737948A true CN114737948A (en) 2022-07-12

Family

ID=82275864

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210222947.1A Pending CN114737948A (en) 2022-03-07 2022-03-07 Intelligent wellbore pressure control method and device based on physical constraint

Country Status (1)

Country Link
CN (1) CN114737948A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117888841A (en) * 2024-03-15 2024-04-16 江苏卫东机械有限公司 Intelligent feedback control electric drilling valve
CN117888841B (en) * 2024-03-15 2024-05-17 江苏卫东机械有限公司 Intelligent feedback control electric drilling valve

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117888841A (en) * 2024-03-15 2024-04-16 江苏卫东机械有限公司 Intelligent feedback control electric drilling valve
CN117888841B (en) * 2024-03-15 2024-05-17 江苏卫东机械有限公司 Intelligent feedback control electric drilling valve

Similar Documents

Publication Publication Date Title
EP1982046B1 (en) Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator
EP1984860B1 (en) Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators
US8504341B2 (en) Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators
AU2012370482B2 (en) Determining optimal parameters for a downhole operation
WO2016205158A1 (en) Flow balancing for a well
US20200242497A1 (en) Intelligent optimization of flow control devices
CA2971706C (en) Method to optimize oilfield operations based on large and complex data sets
US20180052903A1 (en) Transforming historical well production data for predictive modeling
WO2018236238A1 (en) Predicting wellbore flow performance
CN110991079A (en) Oil and gas reservoir parameter interpretation method and device based on neural network and electronic equipment
US20220307357A1 (en) Reservoir fluid property modeling using machine learning
NO20200978A1 (en) Optimized methodology for automatic history matching of a petroleum reservoir model with ensemble kalman filter
CN114737948A (en) Intelligent wellbore pressure control method and device based on physical constraint
WO2023133213A1 (en) Method for automated ensemble machine learning using hyperparameter optimization
US20240068325A1 (en) Autonomous integrated system to maximize oil recovery
US20230316152A1 (en) Method to predict aggregate caliper logs using logging-while-drilling data
WO2024077538A1 (en) Methods and systems for predicting lithology and formation boundary ahead of the bit
US20230367290A1 (en) Online data-driven optimizer of rotating control device used in closed loop drilling
US20230383633A1 (en) Machine-learned based real-time virtual gas metering
US20230306164A1 (en) Method for predicting sand production in a formation
MX2008009776A (en) Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator
MX2008009775A (en) Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination