CN112330038B - Method, device and equipment for determining stress condition of tubular column - Google Patents

Method, device and equipment for determining stress condition of tubular column Download PDF

Info

Publication number
CN112330038B
CN112330038B CN202011258628.3A CN202011258628A CN112330038B CN 112330038 B CN112330038 B CN 112330038B CN 202011258628 A CN202011258628 A CN 202011258628A CN 112330038 B CN112330038 B CN 112330038B
Authority
CN
China
Prior art keywords
target
drilling
moment
well
torque
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.)
Active
Application number
CN202011258628.3A
Other languages
Chinese (zh)
Other versions
CN112330038A (en
Inventor
宋先知
朱硕
李根生
黄中伟
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 CN202011258628.3A priority Critical patent/CN112330038B/en
Publication of CN112330038A publication Critical patent/CN112330038A/en
Application granted granted Critical
Publication of CN112330038B publication Critical patent/CN112330038B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Animal Husbandry (AREA)
  • Earth Drilling (AREA)

Abstract

The embodiment of the specification provides a method, a device and equipment for determining the stress condition of a pipe column, wherein the method comprises the following steps: acquiring friction coefficients of a target well at a plurality of moments before a target moment; acquiring a first drilling dataset of a target well; determining a hook load and a turntable torque of the target well at a target moment according to friction coefficients at a plurality of moments before the target moment, the first drilling data set and a first prediction model; and determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment. In the embodiment of the specification, the stress condition of the tubular column in the target well at the target moment can be accurately determined at the moment before the target moment, and then the abnormal drilling condition such as drilling sticking and the like at the target moment can be subjected to early warning analysis at the moment before the target moment so as to ensure that the drilling is safely and efficiently carried out.

Description

Method, device and equipment for determining stress condition of tubular column
Technical Field
The embodiment of the specification relates to the technical field of geological exploration, in particular to a method, a device and equipment for determining the stress condition of a tubular column.
Background
Along with the advance of oil and gas exploration and development towards deep and complex stratum, drilling tool working conditions are severe, drilling pipe column stress is complex, friction torque is increased sharply, drilling sticking accidents occur frequently, and drilling efficiency is reduced. Therefore, it is very important to timely determine the stress condition of the underground pipe column at the next moment, and the drilling stuck risk can be avoided, and the mechanical drilling speed can be improved, so that the drilling is ensured to be carried out safely and efficiently.
In the prior art, theoretical analysis is generally performed by utilizing pipe column mechanics, and a pipe column overall stress model is established, so that parameters such as friction coefficient, axial force and the like of the current pipe column are calculated according to parameters such as hook load, turntable torque and the like which can be measured in real time at the current moment, and the stress condition of the underground pipe column at the current moment is analyzed and determined. Therefore, the method for determining the stress condition of the tubular column in the prior art can only determine the stress condition of the tubular column under the well at the current moment, and cannot accurately determine the stress condition of the tubular column under the well at the next moment at the current moment.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for determining the stress condition of a tubular column, which are used for solving the problem that the stress condition of a tubular column in a well at the next moment at the current moment cannot be accurately determined in the prior art.
The embodiment of the specification provides a method for determining the stress condition of a tubular column, which comprises the following steps: acquiring friction coefficients of a target well at a plurality of moments before a target moment; acquiring a first drilling dataset of a target well; wherein the first drilling dataset comprises drilling design parameter values for the target well and drilling regime data at a plurality of times prior to the target time; determining a hook load and a turntable torque of the target well at a target moment according to friction coefficients at a plurality of moments before the target moment, the first drilling data set and a first prediction model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set; and determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment.
The embodiment of the specification also provides a device for determining the stress condition of the pipe column, which comprises the following steps: the first acquisition module is used for acquiring friction coefficients of the target well at a plurality of moments before the target moment; a second acquisition module for acquiring a first drilling dataset of the target well; wherein the first drilling dataset comprises drilling design parameter values for the target well and drilling regime data at a plurality of times prior to the target time; a first determination module for determining a hook load and a carousel torque of the target well at a target time based on friction coefficients at a plurality of times prior to the target time, the first drilling data set, and a first predictive model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set; and the second determining module is used for determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment.
The embodiment of the specification also provides a device for determining the stress condition of the pipe column, which comprises a processor and a memory for storing instructions executable by the processor, wherein the processor realizes the steps of the method for determining the stress condition of the pipe column when executing the instructions.
Embodiments of the present disclosure also provide a computer readable storage medium having stored thereon computer instructions that when executed perform the steps of a method for determining a stress condition of a pipe string.
The embodiment of the specification provides a method for determining the stress condition of a tubular column, which can be used for predicting hook load and rotary table torque of a target well at target moment by using a first prediction model according to friction coefficients of the target well at a plurality of moments before the target moment and a first drilling data set of the target well. The first drilling data set may include drilling design parameter values of the target well and drilling condition data at a plurality of times prior to the target time. Further, the force loading condition of the tubular string in the target well at the target time can be determined based on the hook load and the turntable torque at the target time and the friction coefficient at a time immediately before the target time. Therefore, the stress condition of the tubular column in the target well at the target moment can be accurately determined at the moment before the target moment, and further, the abnormal drilling condition such as drilling sticking and the like at the target moment can be subjected to early warning analysis at the moment before the target moment, so that risks such as drilling sticking and the like are avoided, the mechanical drilling speed can be improved, and the safe and efficient drilling can be ensured.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the present specification, are incorporated in and constitute a part of this specification and do not limit the embodiments of the present specification. In the drawings:
FIG. 1 is a schematic diagram of steps of a method for determining a stress condition of a pipe string according to an embodiment of the present disclosure;
FIG. 2 is a schematic illustration of string segmentation results for a target well provided in accordance with an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a structure of a first target network provided according to an embodiment of the present disclosure;
FIG. 4 is a schematic illustration of a predicted outcome of predicting weight-on-bottom-hole using a second predictive model, provided in accordance with an embodiment of the present disclosure;
FIG. 5 is a schematic illustration of a predicted outcome of predicting downhole torque using a second predictive model, provided in accordance with an embodiment of the present disclosure;
fig. 6 is a schematic diagram of a prediction result of predicting a hook load using a first prediction model provided according to an embodiment of the present specification;
FIG. 7 is a schematic diagram of a predicted outcome of predicting turntable torque using a first predictive model provided in accordance with an embodiment of the present disclosure;
FIG. 8 is a schematic diagram of a stress situation and an early warning result of a pipe column according to an embodiment of the present disclosure;
FIG. 9 is a schematic structural view of a device for determining stress conditions of a pipe string according to an embodiment of the present disclosure;
Fig. 10 is a schematic structural view of a determining apparatus for determining a stress condition of a pipe string according to an embodiment of the present specification.
Detailed Description
The principles and spirit of the embodiments of the present specification will be described below with reference to several exemplary implementations. It should be understood that these embodiments are presented merely to enable one skilled in the art to better understand and implement the present description embodiments and are not intended to limit the scope of the present description embodiments in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Those skilled in the art will appreciate that the implementations of the embodiments of the present description may be implemented as a system, apparatus, method, or computer program product. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
While the flow described below includes a number of operations occurring in a particular order, it should be apparent that these processes may include more or fewer operations, which may be performed sequentially or in parallel (e.g., using a parallel processor or a multi-threaded environment).
Referring to fig. 1, the present embodiment may provide a method for determining a stress situation of a pipe string. The method for determining the stress situation of the pipe column in the target well at the target moment can be used for determining the hook load and the rotary table torque of the target well at the target moment by utilizing the first prediction model according to the drilling design parameter value of the target well, drilling condition data at a plurality of moments before the target moment and friction coefficient at a plurality of moments before the target moment, and determining the stress situation of the pipe column in the target well at the target moment on the basis of the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment, so that the drilling situation of the target well can be predicted according to the predicted stress situation of the pipe column in the target well at the target moment at the moment before the target moment, the drilling jamming risk is avoided, the mechanical drilling speed is improved, and the drilling safety and the high efficiency are ensured. The method for determining the stress condition of the pipe column can comprise the following steps.
S101: the friction coefficients of the target well at a plurality of times before the target time are obtained.
In this embodiment, the friction coefficient of the target well at a plurality of times before the target time can be obtained, where the friction coefficient can be used not only to characterize the surface conditions of the drill string and the well wall, but also to characterize the effects of mud viscosity and abnormal conditions of the well (such as cuttings bed, shrinkage, keyways, etc.).
In this embodiment, the target time may be the time next to the current drilling time, but the target time may be any other time, specifically, may be determined according to actual requirements, and the present application is not limited thereto. Further, the above-mentioned times before the target time may be: t-1, t-2 … … t-n, where t is the target time, n may be a preset time step, and n is a positive integer greater than 0, for example, if the preset time step is 6, the friction coefficient of the target well needs to be obtained 6 times before the target time. Of course, the foregoing description is merely an example, and other modifications may be made by those skilled in the art in light of the technical spirit of the embodiments of the present disclosure, so long as the functions and effects implemented are the same or similar to those of the embodiments of the present disclosure, all of which are included in the protection scope of the embodiments of the present disclosure.
In some embodiments, the friction coefficient may include: axial friction coefficient and circumferential friction coefficient, wherein axial refers to along the cylinder axis direction, and circumferential refers to around the cylinder axis direction.
In this embodiment, the method for obtaining the friction coefficient of the target well at a plurality of times before the target time may include: the friction coefficient of the target well is obtained from a preset database or input by a user at a plurality of moments before the target moment. It will be understood that, of course, other possible ways may be used to obtain the friction coefficient of the target well at a plurality of times before the target time, for example, searching in a web page according to a certain search condition, which may be specifically determined according to the actual situation, and the embodiment of the present disclosure is not limited to this.
S102: acquiring a first drilling dataset of a target well; wherein the first set of drilling data includes drilling design parameter values for the target well and drilling regime data at a plurality of times prior to the target time.
In this embodiment, a first drilling data set of the target well may be obtained, where the first drilling data set may include drilling design parameter values of the target well and drilling condition data at a plurality of times prior to the target time. The well design parameters for the target well may be static parameters, i.e., they may be constant for the target well regardless of the stage of the well being drilled. The drilling condition data may be time series data, that is, the drilling condition data is data generated in the drilling process of the target well, and may change in real time according to the drilling of the target well.
In one embodiment, the drilling design parameters of the target well may include: drilling tool combination, drill bit type, drilling fluid type and the like, wherein parameter values corresponding to the drilling tool combination can comprise: full eye, pendulum, tower, etc.; the parameter values corresponding to the drill bit types may include: PDC (Polycrystalline Diamond Compact ), roller cone drill bits, and the like; the parameter values corresponding to the types of drilling fluid can include: water-based, oil-based, gas-based, etc. It will be appreciated that the values of the drilling design parameters corresponding to the same well may be the same.
In this embodiment, the drilling design parameter may be designed before drilling, and thus, the method for obtaining the first drilling data set may include: the drilling design parameters input by the user are received, or can be obtained according to a preset path query. It will be understood that other possible ways of obtaining the drilling design parameters may be used, for example, searching the web page for the target drilling design parameters according to a certain search condition, and specifically may be determined according to the actual situation, which is not limited by the present application.
In one embodiment, since the drilling conditions data is time series data, drilling conditions data at a plurality of times before the target time may be acquired. The drilling condition data at a plurality of times prior to the target time may include at least one of: well depth, well inclination, azimuth, predicted value of weight on bit at bottom of well, predicted value of torque on bottom of well, hook load, surface torque, pump pressure, rotary table rotational speed, pump stroke, riser pressure, casing pressure, inlet density, outlet density, inlet temperature, outlet temperature, inlet conductance, outlet conductance, inlet flow, outlet flow, displacement, equivalent density, total pool volume, etc. at each time prior to the target time.
In the embodiment, in the drilling process, a proper drill bit type can be selected according to different stratum conditions and drilling depths, and the rotating speed, the weight on bit, the displacement and the mud performance are in an optimal combination state, so that the fastest drilling speed is obtained. As normal drilling proceeds, the wellbore will continue to deepen. Thus, drilling regime data at multiple times consecutive before the target time may be in real time. The bottom-hole weight and the bottom-hole torque can be measured by the underground sensor during drilling, but cannot be transmitted in real time, so that the bottom-hole weight and the bottom-hole torque cannot be acquired in real time, and therefore, the bottom-hole weight and the bottom-hole torque in the first drilling data set are predicted values.
In this embodiment, the above drilling condition data may be obtained by measuring the sensors disposed on the surface and downhole in real time, which is of course understood that the above drilling condition data may also be obtained by other possible manners, and may be specifically determined according to actual situations, which is not limited in this embodiment of the present disclosure.
S103: determining hook load and turntable torque of a target well at a target moment according to friction coefficients at a plurality of moments before the target moment, a first drilling data set and a first prediction model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set.
In this embodiment, the hook load and the turntable torque of the target well at the target time may be determined based on the friction coefficient, the first drilling data set, and the first predictive model at a plurality of times before the target time. The hook load and the rotary table torque at the target moment may be predicted values, the first prediction model may be pre-trained by using a neural network, and the first prediction model may be used to predict the hook load and the rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set.
In the present embodiment, since the hook load and the turntable torque at the target time cannot be accurately measured at the previous time of the target time, the hook load and the turntable torque at the target time can be predicted using the friction coefficient, the drilling condition data, and the drilling design parameters at a plurality of times before the target time.
S104: and determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment.
In the present embodiment, since the change between the friction coefficient at the target time and the friction coefficient at the time immediately before the target time is minute, the accuracy is higher than that in a manner employing an empirical value. Thus, the loading of the tubular string in the target well at the target time may be determined based on the predicted hook load and reel torque at the target time and the friction coefficient at a time immediately prior to the target time. The whole stress model of the pipe column takes the pipe column with a certain length underground as a research object to investigate the distribution of axial force and torque transmission, bending moment, contact force and buckling state. The tubular string may include, in a wellbore of a target well: drill string, casing string, test string, sucker rod string, coiled tubing, etc.
In this embodiment, the pipe column stress condition may include, but is not limited to, at least one of the following: tubular column axial force, torque, bending moment, contact force, buckling state, etc. According to the pipe column stress condition at the target moment determined by analysis, whether the target well is abnormal in the drilling process at the target moment can be determined, so that early warning analysis can be carried out on drilling abnormal conditions such as stuck drilling and the like at the target moment at the moment before the target moment, and the drilling safety is improved. Of course, the stress situation of the pipe column is not limited to the above examples, and other modifications are possible by those skilled in the art in light of the technical spirit of the embodiments of the present disclosure, but all the functions and effects achieved by the present disclosure are included in the protection scope of the embodiments of the present disclosure as long as they are the same or similar to the embodiments of the present disclosure.
In one embodiment, the tubular strings of the target well may be partitioned at preset intervals to obtain a plurality of tubular strings, and characteristic parameters of each tubular string in the plurality of tubular strings may be obtained. Furthermore, the bottom-hole bit pressure, bottom-hole torque and axial force of the pipe column can be determined by utilizing the pipe column integral stress model according to the characteristic parameters of each pipe column section, the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment.
In this embodiment, the preset interval may be a value greater than 0, for example: 10 meters, 13.5 meters, etc., and may be specifically determined according to practical situations, which is not limited by the present application. The characteristic parameters of each section of tubing string described above may be used to characterize the state of the tubing string, and in some embodiments may include at least one of the following: curvature, deflection, bending stiffness, inner diameter, wall thickness, etc. of each section of tubing string.
In this embodiment, after the string of the target well is divided into N sections according to the preset interval, the strings may be sorted downward from the surface, that is, each section of string from the surface to the drill bit may have a serial number of [0,1,2,3, …, i, i+1, …, N-1], and the length of each corresponding section is [ d s0,ds1,ds2,…,dsi,…dsN-1 ]. If the tubular string of the target well can be divided into N equal parts, d s0＝ds1＝ds2＝…＝dsi＝…dsN-1 =intervals. Otherwise, d s0＝L-(N-1)×intervals,ds1＝ds2＝…＝dsi＝…dsN-1 = interfaces. Further, the well depths corresponding to the two ends (the end close to the ground and the end close to the drill bit) of the N unit sections may be ：(0,ds0)、(ds0,1×intervals+ds0)、(1×intervals+ds0,2×intervals+ds0)、……、((i-1)×intervals+ds0,i×intervals+ds0)、……、((N-1-1)×intervals+ds0,(N-1)×intervals+ds0),, and the segmentation result may be shown in fig. 2, where the characteristic parameter of each section of the tubular string corresponds to the initialization parameter.
In one embodiment, where interval=10m, the string length 316m, the string may be divided into 32 sections, corresponding to the string number [0,1,2,3,4,5 …,31] from the surface to the bit, corresponding to the length of the ith cell section [6,10,10,10 … ], corresponding to the well depth [ (0, 6), (6, 16), (16, 26), (26, 36), … (306,316) ] from the surface to the two ends of the string (near the surface, bit).
In one embodiment, the stress condition of the pipe column in the target well at the target moment can be determined by using a pipe column integral stress model, and a transfer equation of the pipe column integral stress model can be shown in the following formula, and the pressure is positive:
Wherein: f i is the axial force of the ith section of pipe column close to the wellhead, N (cattle); f i+1 is the axial force of the ith section of pipe column close to the drill bit, and the unit is N; m Ti is torque of the ith section of pipe column near the wellhead, and N.m; m Ti+1 is torque of the ith section of pipe column near the drill bit, and N.m; EI i is the bending stiffness of the ith section of tubing string; m -1, which is the curvature of the well hole of the ith section of pipe column near the well mouth; The curvature of the well bore of the ith section of pipe column near the drill bit, and m -1;qi is the line weight of the ith section of pipe column and N/m; alpha i is the well inclination angle, degree of the ith section of tubing string; n ti is the contact force between the ith section of pipe column and the well wall, N/m; Δs i is the length of the unit section corresponding to the ith section of pipe column, m; d bi is the outer diameter of the ith section of pipe column, m; mu 1 and mu 2 are the axial friction coefficient and the circumferential friction coefficient, respectively, of the current pipe string.
In this embodiment, the torque at the bottom of the string near the drill bit is the bottom hole torque, and the torque at the top of the string near the wellhead is the rotary table torque. The hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment can be brought into the formula, and the stress analysis result of the tubular column in the target well at the target moment can be obtained from the iterative calculation of the wellhead section by section to the drill bit. Specifically, the axial force of each section of pipe column in the target well at the target moment can be calculated from the iterative calculation of the wellhead section by section to the position of the drill bit, and the different axial force values correspond to different buckling states.
In one embodiment, the bending moment may be calculated according to the following formula:
Mb＝EI×kb
Wherein M b is the bending moment on the pipe column, and the unit is N.m; EI is the bending stiffness of the tubing string, and the unit N.m 2;kb is the borehole axis curvature, the unit m -1.
In one embodiment, the contact force may be calculated according to the following formula:
wherein N t is the contact force between the pipe column and the well wall (casing), and the unit is N/m; parameters A, B may be calculated; mu 2 is the circumferential friction coefficient, dimensionless.
In one embodiment, the column buckling state may be determined as follows, with F sin being a sinusoidal buckling critical load; f hel_inter is low-order helical buckling and F hel_intra is high-order helical buckling. F is the axial force of the pipe column, and when F is smaller than F sin, the pipe column is not buckled; when F is larger than F sin and smaller than F hel_inter, the tubular column is buckled in a sinusoidal way; when F is greater than F hel_inter and less than F hel_intra, the pipe column is in low-order helical buckling; when F is greater than F hel_intra, the string is in high-order helical buckling.
From the above description, it can be seen that the following technical effects are achieved in the embodiments of the present specification: the hook load and the rotary table torque of the target well at the target time can be predicted by using the first prediction model according to the friction coefficient and the first drilling data set at a plurality of times before the target time by acquiring the friction coefficient of the target well at a plurality of times before the target time and the first drilling data set of the target well. The first drilling data set may include drilling design parameter values of the target well and drilling condition data at a plurality of times prior to the target time. Further, the force loading condition of the tubular string in the target well at the target time can be determined based on the hook load and the turntable torque at the target time and the friction coefficient at a time immediately before the target time. Therefore, the stress condition of the tubular column in the target well at the target moment can be accurately determined at the moment before the target moment, and further, the abnormal drilling condition such as drilling sticking and the like at the target moment can be subjected to early warning analysis at the moment before the target moment, so that risks such as drilling sticking and the like are avoided, the mechanical drilling speed can be improved, and the safe and efficient drilling can be ensured.
In one embodiment, before acquiring the friction coefficient of the target well at a plurality of times before the target time, the method may further include: a second drilling data set of the target well is acquired, wherein the second drilling data set includes drilling design parameter values of the target well and drilling regime data at a plurality of times prior to a time prior to the target time. And determining predicted values of the bottom hole weight and the bottom hole torque of the target well at a moment before the target moment according to the second drilling data set and a second prediction model, wherein the second prediction model is used for predicting the bottom hole weight and the bottom hole torque at the moment before according to the data in the second drilling data set. Further, the actual measurement values of the hook load and the turntable torque of the target well at the moment before the target moment can be obtained, and the friction coefficient of the target well at the moment before the target moment is determined by utilizing the whole tubular column stress model according to the predicted values of the bottom drilling pressure and the bottom torque at the moment before the target moment and the actual measurement values of the hook load and the turntable torque.
In this embodiment, since drilling is completed at a time before the target time, the hook load and the turntable torque of the target well at a time before the target time can be obtained in real time by the ground sensor, and the accuracy of determining the friction coefficient can be improved by using the actually measured hook load and turntable torque.
In this embodiment, the equation of transmission of the force model of the whole tubular column may be shown in the following formula, and the pressure is positive:
Wherein: f i is the axial force of the ith section of pipe column close to the wellhead, N (cattle); f i+1 is the axial force of the ith section of pipe column close to the drill bit, and the unit is N; m Ti is torque of the ith section of pipe column near the wellhead, and N.m; m Ti+1 is torque of the ith section of pipe column near the drill bit, and N.m; EI i is the bending stiffness of the ith section of tubing string; m -1, which is the curvature of the well hole of the ith section of pipe column near the well mouth; The curvature of the well bore of the ith section of pipe column near the drill bit, and m -1;qi is the line weight of the ith section of pipe column and N/m; n ti is the contact force between the ith section of pipe column and the well wall, N/m; Δs i is the length of the unit section corresponding to the ith section of pipe column, m; d bi is the outer diameter of the ith section of pipe column, m; mu 1 and mu 2 are the axial friction coefficient and the circumferential friction coefficient, respectively, of the current pipe string.
In this embodiment, the friction coefficient may be inverted by a dichotomy, and the calculation process may be: firstly, initializing and generating a friction coefficient between 0 and 1, bringing predicted values of the bottom drilling pressure and the bottom torque at the moment before the target moment into a whole stress model of the pipe column, and iteratively calculating the axial force and the torque at the upper end (close to the ground) of each section of pipe column from a drill bit section by utilizing a transmission equation of the axial force and the torque until the pipe column section closest to the ground is calculated, so as to obtain the axial force and the torque value at the uppermost end (close to the ground) of the whole pipe column, wherein the calculated value of the hook load is obtained by adding a minus sign to the axial force, and the calculated value of the torque value is the calculated value of the turntable torque.
In this embodiment, the calculated value of the hook load and the calculated value of the turntable torque may be compared with the actually measured hook load and turntable torque, and an error between the calculated value and the actually measured value is within a preset range, which indicates that the friction resistance factor is accurate, and the cycle is ended. Otherwise, a new friction factor is reinitialized, the friction factor is calculated from the drill bit to the ground section by section, the errors of the calculated value and the measured value are compared again, and the calculation is continuously circulated until the errors between the calculated value and the measured value of the hook load and the turntable torque are within a preset range, so that the friction factor at the moment before the target moment can be obtained.
In the embodiment, the real-time inversion of the friction coefficient can be realized by utilizing the actually measured hook load and the turntable torque in the drilling process and combining the predicted values of the bottom-hole bit pressure and the bottom-hole torque with the whole stress model of the tubular column, so that the blindness problem existing in the prior art by directly adopting the empirical value of the friction coefficient is solved.
In one embodiment, before determining predicted values of the weight-on-bit and the torque-on-bottom for the target well at a time prior to the target time based on the second drilling dataset and the second predictive model, the method may further include: and acquiring a drilling data set of at least one adjacent well of the target well, and preprocessing the drilling data set of the at least one adjacent well to obtain a preprocessed drilling data set. Furthermore, the drilling working condition data in the preprocessed drilling data set can be converted into a supervised learning format according to a preset time step to obtain a first training set, wherein the drilling working condition data is time sequence data. The drilling design parameters in the preprocessed drilling data set may be used as a second training set, wherein the drilling design parameters are non-time series data. The first training set can be used as input training data of a long-short-period memory network in a first target network, and the second training set can be used as input training data of a multi-layer feedforward neural network in the target network; the target network is constructed according to the long-term memory network and the multi-layer feedforward neural network, and the first target network is trained by utilizing the first training set and the second training set to obtain a second prediction model.
In this embodiment, in order to enable the data for training to better represent the target well, a drilling data set of at least one adjacent well of the target well may be acquired in advance, and further, the drilling data set of the at least one adjacent well may be preprocessed. Wherein preprocessing the drilling data set of the at least one adjacent well may include: and performing operations such as data well-dividing storage, data splicing, data cleaning, time sequencing and the like on the drilling data set of at least one adjacent well, so as to obtain a preprocessed drilling data set. The preprocessed drilling dataset may include drilling regime data and drilling design parameters. The drilling engineering parameters may include well depth, well inclination angle, azimuth angle, predicted value of bottom hole weight, predicted value of bottom hole torque, hook load, surface torque, pump pressure, rotary table rotation speed, pump stroke, riser pressure, casing pressure, inlet density, outlet density, inlet temperature, outlet temperature, inlet conductance, outlet conductance, inlet flow, outlet flow, displacement, equivalent density, total cell volume, etc.; the drilling design parameters include drilling fluid system, drilling tool assembly type, drill bit type, etc.
In this embodiment, because the drilling condition data is generated in real time along with time change in the drilling process, the drilling condition data has a time series property, and the drilling design parameters are designed parameters before drilling, do not change along with time, but are different from well to well. Aiming at the characteristics of time sequence and non-time sequence of data in the drilling data set. Therefore, the above-described first target network can be preferably constructed by processing LSTM (long short-term memory neural network) and BP neural network (multi-layer feedforward neural network) with good time-series data effects. The LSTM is designed to solve the long-term dependence problem in the traditional circulating neural network, can memorize information in a long time period, and is very suitable for processing the dynamic change problem in the drilling process.
In this embodiment, the long-short-term memory neural network and the multi-layer feedforward neural network may be configured to obtain a dual-input network structure, i.e., a first target network, by means of a parallel connection design. In one embodiment, the first target network may have a structure as shown in fig. 3, where the first target network has two inputs, and the time-sequential data is an LSTM input and the non-time-sequential data is a BP neural network input. Correspondingly, the first target network may have two output data, training the first target network using the first training set and the second training set, and the obtained output data of the second prediction model may include: bottom hole weight and bottom hole torque.
In this embodiment, before training the first target network, the drilling condition data in the preprocessed drilling data set may be converted into a format for supervised learning according to a preset time step according to structural features of the LSTM, so as to obtain the first training set. The preset time step may be any value greater than 0, for example: the time sequence data of preset time step timesteps =5, namely t-5, t-4, t-3, t-2 and t-1 can be selected as the input data for predicting the bottom hole weight and bottom hole torque at the moment t. It will be understood, of course, that the value of the above-mentioned preset time step may be adjusted according to the computational effort of the computer and the merits of the model prediction result, and specifically may be determined according to the actual situation, which is not limited by the present application.
In this embodiment, the well design parameters in the preprocessed well data set may be digitized using One-Hot encoding prior to training the first target network. The One-Hot code is also called One-bit valid code, and mainly uses an N-bit status register to code N states, each of which is defined by its independent register bit, and only One bit is valid at any time. One-Hot encoding is a representation of the classification variables as binary vectors. This first requires mapping the classification value to an integer value. Each integer value is then represented as a binary vector, which is zero except for the index of the integer, which is labeled 1.
In the embodiment, the second prediction model can accurately predict the bottom-hole weight and bottom-hole torque at the next moment, and the problems that the weight-on-bit read by the weight indicator in the prior art is often distorted due to influences of well deviation, well wall friction, mud performance and the like, and the bottom-hole weight and bottom-hole torque cannot be acquired in real time are effectively solved.
In one embodiment, before determining the hook load and the carousel torque of the target well at the target time based on the friction coefficient, the first drilling data set, and the first predictive model at a plurality of times prior to the target time, the method may further include: a drilling data set and a friction data set of at least one adjacent well of the target well are obtained, wherein the friction data set may include friction coefficients of the at least one adjacent well at each moment in time of drilling. The drilling data set for at least one adjacent well may be preprocessed to obtain a preprocessed drilling data set.
In this embodiment, since the preprocessed drilling data set includes time-series data and non-time-series data, the drilling condition data in the preprocessed drilling data set as time-series data and the friction coefficient in the friction data set may be converted into the format of supervised learning according to a preset time step, so as to obtain the third training set. And drilling design parameters in the preprocessed drilling data set as non-time series data may be used as a fourth training set. Further, the third training set may be used as input training data of a long-short-term memory network in the target network, and the fourth training set may be used as input training data of a multi-layer feedforward neural network in the target network, where the target network is constructed according to the long-short-term memory network and the multi-layer feedforward neural network. And training the target network by using the third training set and the fourth training set to obtain a first prediction model.
In this embodiment, because the drilling condition data and the friction coefficient are generated in real time as time changes in the drilling process, the drilling system has a time series property, and the drilling design parameters are designed parameters before drilling, do not change as time, but are different from each well. Aiming at the characteristics of time sequence and non-time sequence of data in the drilling data set. Therefore, the above-described second target network can be preferably constructed by processing LSTM (long short-term memory neural network) and BP neural network (multi-layer feedforward neural network) with good time-series data effects. The LSTM is designed to solve the long-term dependence problem in the traditional circulating neural network, can memorize information in a long time period, and is very suitable for processing the dynamic change problem in the drilling process.
In this embodiment, the long-short-term memory neural network and the multi-layer feedforward neural network may be configured to obtain a dual-input network structure, that is, a second target network, by means of a parallel connection design. In one embodiment, the second target network has two inputs, wherein the time-series data is used as an input of the LSTM and the non-time-series data is used as an input of the BP neural network. Correspondingly, the second target network may have two output data, training the target network using the third training set and the fourth training set, and the obtained output data of the first prediction model may include: hook load and turntable torque.
In this embodiment, before training the first target network, according to the structural feature of the LSTM, the drilling condition data in the preprocessed drilling data set and the friction coefficient in the friction data set may be converted into a format for supervised learning according to a preset time step, so as to obtain the third training set. The preset time step may be any value greater than 0, for example: the time sequence data of preset time step timesteps =5, namely t-5, t-4, t-3, t-2 and t-1 can be selected as the input data for predicting the hook load and the rotating disc torque at the t moment. It will be understood, of course, that the value of the above-mentioned preset time step may be adjusted according to the computational effort of the computer and the merits of the model prediction result, and specifically may be determined according to the actual situation, which is not limited by the present application.
In the embodiment, the friction coefficient, the drilling design parameter value of the target well and the drilling working condition data of the target well at a plurality of times before the target time obtained by real-time inversion are used as the input of the first prediction model to predict the hook load and the turntable torque at the target time, so that the prediction precision of the hook load and the turntable torque at the next time can be effectively improved.
In one embodiment, after determining the stress condition of the tubular string in the target well at the target time using the tubular string integral stress model based on the hook load and the turntable torque at the target time and the friction coefficient at a time immediately before the target time, the method may further include: determining whether the stress condition of the tubular column in the target well at the target moment is abnormal, and generating prompt information according to the stress condition of the tubular column in the target well at the target moment under the condition that the abnormality is determined to exist. Further, the hint information may be sent to the target processing object.
In this embodiment, whether there is an abnormality in the stress condition of the tubular string in the target well at the target time may be determined according to the buckling state. The normal condition is that buckling does not occur, when sinusoidal buckling and spiral buckling occur, the pipe column is stressed seriously, and prompt information is sent at the moment. The corresponding treatment mode can be to properly lift the pipe column, reduce the weight on bit and improve the stress state of the pipe column under the condition of ensuring certain rock breaking capacity.
In this embodiment, the prompt information may include, but is not limited to: the current time, the type of anomaly, etc., may of course also include other information, such as: the data about the target well at the target time, the suggested processing manner, etc. may be specifically determined according to the actual situation, which is not limited in the embodiment of the present specification. The target processing object may be a worker of the target well, and of course, may be other preset management personnel, and may specifically be determined according to actual situations, which is not limited in the embodiment of the present disclosure.
In one example scenario, taking a bid 322 well as an example, a drilling dataset for an adjacent well to the bid 322 well may include: bottom hole weight, bottom hole torque, hook load, rotary table torque, well depth, well inclination, azimuth, rotational speed, riser pressure, inlet density, outlet density, inlet temperature, outlet temperature, inlet conductance, outlet conductance, inlet flow, outlet flow, displacement, equivalent density, 1# pump, 2# pump, total sump volume, drilling fluid type, drilling tool assembly type, bit type, 3355 data samples total, 70% or 2348 data samples for training, and 30% or 1007 data samples for validation.
In one example scenario, well bore structure design parameters for a target well are shown in table 1, and string structure and parameters for a target well are shown in table 2.
TABLE 1
Opening time Well depth/m Diameter of well (inside diameter of casing)/m
One open 301 0.3397
Two-way opening 1500 0.2445
Three-way valve 3361 0.1778
Four-way switch 3649 0.1978
TABLE 2
Type of pipe string Well depth/m Inner diameter/m Outer diameter/m Joint diameter/m Line weight (kg/m)
Drill rod of first kind 2720 0.08829 01016 0.1116 19.45
Second kind drill rod 3170 0.06985 0.1143 0.1243 61.01
Third kind drill rod 3540 0.09718 0.1016 0.1116 27.00
Fourth drill rod 3649 0.06510 0.1143 0.1243 44.20
In one example scenario, a first target network may be trained from training samples in the drilling dataset of adjacent wells of the inch 322 well described above to obtain a second predictive model. Further, the accuracy of the second predictive model prediction may be verified using verification samples in the drilling dataset of adjacent wells of the inch 322 well. Wherein, the predicted result of predicting the bottom hole weight by using the second prediction model is shown in fig. 4; as shown in fig. 5, the prediction result of predicting the bottom hole torque by using the second prediction model is that the accuracy of predicting the bottom hole weight and the bottom hole torque by using the second prediction model is high as can be seen from fig. 4 and 5.
In one example of a scenario, the prediction result of predicting the hook load using the first prediction model is shown in fig. 6; as a result of predicting the turntable torque using the first prediction model, as shown in fig. 7, it can be found that the error between the predicted value and the true value of the hook load and the turntable torque is small according to fig. 6 and 7.
In a scenario example, according to the technical solutions in the embodiments of the present disclosure, the stress situation of the tubular string in the target well at the target moment may be determined according to the data in tables 1 and 2, where the stress situation of the tubular string and the early warning result are shown in fig. 8. The line graph in fig. 8 is a schematic diagram of the axial force change with well Depth at the target moment, where Resistance is friction and Depth is Depth. As can be seen from fig. 8, when the axial force is abnormal at a well depth of 3542 m, it can be determined that the buckling state of the english-buying 322 well is low-order helical buckling, and early warning is required.
Based on the same inventive concept, the embodiment of the present specification also provides a device for determining the stress condition of the pipe column, as in the following embodiment. Because the principle of the pipe column stress condition determining device for solving the problem is similar to that of the pipe column stress condition determining method, the implementation of the pipe column stress condition determining device can refer to the implementation of the pipe column stress condition determining method, and repeated parts are not repeated. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated. Fig. 9 is a block diagram of a device for determining a stress condition of a pipe column according to an embodiment of the present disclosure, and as shown in fig. 9, may include: the first acquisition module 901, the second acquisition module 902, the first determination module 903, and the second determination module 904 are explained below.
A first obtaining module 901, configured to obtain friction coefficients of a target well at a plurality of times before a target time;
A second acquisition module 902, which may be used to acquire a first drilling dataset of a target well; wherein the first drilling data set includes drilling design parameter values for the target well and drilling condition data for a plurality of times prior to the target time;
A first determination module 903 operable to determine a hook load and a turret torque for the target well at the target time based on the friction coefficient, the first drilling data set, and the first predictive model at a plurality of times prior to the target time; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set;
A second determination module 904 may be configured to determine a force profile of the tubular string in the target well at the target time based on the hook load and the turret torque at the target time, the friction coefficient at a time prior to the target time.
The embodiment of the present disclosure further provides an electronic device, which may specifically refer to a schematic structural diagram of an electronic device shown in fig. 10 and based on the method for determining the stress condition of the pipe string provided in the embodiment of the present disclosure, where the electronic device may specifically include an input device 41, a processor 42, and a memory 43. Wherein the input device 41 may be specifically adapted to input the friction coefficient of the target well at a plurality of moments before the target moment, the first drilling data set of the target well. The processor 42 may be specifically configured to obtain friction coefficients for the target well at a plurality of times prior to the target time; acquiring a first drilling dataset of a target well; wherein the first drilling data set includes drilling design parameter values for the target well and drilling condition data for a plurality of times prior to the target time; determining hook load and turntable torque of a target well at a target moment according to friction coefficients at a plurality of moments before the target moment, a first drilling data set and a first prediction model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set; and determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment. The memory 43 may be used to store parameters such as the stress condition of the target well string at a target time.
In this embodiment, the input device may specifically be one of the main means for exchanging information between the user and the computer system. The input device may include a keyboard, mouse, camera, scanner, light pen, handwriting input board, voice input apparatus, etc.; the input device is used to input raw data and a program for processing these numbers into the computer. The input device may also obtain data transmitted from other modules, units, and devices. The processor may be implemented in any suitable manner. For example, a processor may take the form of, for example, a microprocessor or processor, and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application SPECIFIC INTEGRATED Circuits (ASICs), programmable logic controllers, and embedded microcontrollers, among others. The memory may in particular be a memory device for storing information in modern information technology. The memory may comprise a plurality of levels, and in a digital system, may be memory as long as binary data can be stored; in an integrated circuit, a circuit with a memory function without a physical form is also called a memory, such as a RAM, a FIFO, etc.; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card, and the like.
In this embodiment, the specific functions and effects of the electronic device may be explained in comparison with other embodiments, which are not described herein.
The embodiment of the specification also provides a computer storage medium of a determination method based on the stress condition of the pipe column, wherein the computer storage medium stores computer program instructions, and the computer program instructions can be implemented when executed: acquiring friction coefficients of a target well at a plurality of moments before a target moment; acquiring a first drilling dataset of a target well; wherein the first drilling data set includes drilling design parameter values for the target well and drilling condition data for a plurality of times prior to the target time; determining hook load and turntable torque of a target well at a target moment according to friction coefficients at a plurality of moments before the target moment, a first drilling data set and a first prediction model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set; and determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment.
In the present embodiment, the storage medium includes, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read-Only Memory (ROM), a Cache (Cache), a hard disk (HARD DISK DRIVE, HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects of the program instructions stored in the computer storage medium may be explained in comparison with other embodiments, and are not described herein.
It will be apparent to those skilled in the art that the modules or steps of the embodiments described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, embodiments of the present specification are not limited to any specific combination of hardware and software.
Although the present description provides method operational steps as described in the above embodiments or flowcharts, more or fewer operational steps may be included in the method based on routine or non-inventive labor. In steps where there is logically no necessary causal relationship, the execution order of the steps is not limited to the execution order provided in the embodiments of the present specification. The described methods, when performed in an actual apparatus or an end product, may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment) as shown in the embodiments or figures.
It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the embodiments of the specification should, therefore, be determined not with reference to the above description, but instead should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above description is only of the preferred embodiments of the present embodiments and is not intended to limit the present embodiments, and various modifications and variations can be made to the present embodiments by those skilled in the art. Any modification, equivalent replacement, improvement, or the like made within the spirit and principles of the embodiments of the present specification should be included in the protection scope of the embodiments of the present specification.

Claims (8)

1. The method for determining the stress condition of the pipe column is characterized by comprising the following steps of:
Acquiring friction coefficients of a target well at a plurality of moments before a target moment;
acquiring a first drilling dataset of a target well; wherein the first drilling dataset comprises drilling design parameter values for the target well and drilling regime data at a plurality of times prior to the target time;
Determining a hook load and a turntable torque of the target well at a target moment according to friction coefficients at a plurality of moments before the target moment, the first drilling data set and a first prediction model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set;
Determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment;
wherein determining a force condition of the tubular string in the target well at the target time based on the hook load and the turntable torque at the target time, the friction coefficient at a time immediately before the target time, comprises:
substituting the hook load and the turntable torque at the target moment and the friction coefficient at the moment before the target moment into a whole pipe column stress model, and obtaining the stress condition of each section of pipe column in the target well at the target moment from the iterative calculation of a wellhead section by section to a drill bit; wherein the stress condition of each section of pipe column comprises at least one of the following: the axial force, torque, bending moment, contact force and buckling state of the pipe column;
wherein prior to determining the hook load and the rotary table torque of the target well at the target time based on the friction coefficient, the first drilling data set, and the first predictive model at a plurality of times prior to the target time, further comprising:
acquiring a drilling data set and a friction data set of at least one adjacent well of the target well; wherein the friction data set comprises friction coefficients of the at least one adjacent well at each moment in time of drilling;
preprocessing the drilling data set of at least one adjacent well to obtain a preprocessed drilling data set;
converting the drilling working condition data in the preprocessed drilling data set and the friction coefficient in the friction data set into a supervised learning format according to a preset time step to obtain a third training set; wherein the drilling condition data is time sequence data;
Taking the drilling design parameters in the preprocessed drilling data set as a fourth training set; wherein the well design parameters are non-time series data;
Taking the third training set as input training data of a long-term and short-term memory network in a target network, and taking the fourth training set as input training data of a multi-layer feedforward neural network in the target network; the target network is constructed according to the long-term memory network and the multi-layer feedforward neural network;
and training the target network by using the third training set and the fourth training set to obtain the first prediction model.
2. The method of claim 1, wherein the well design parameters comprise at least one of: drilling tool combination, drill bit type, drilling fluid type;
The drilling regime data at a plurality of times prior to the target time includes at least one of: well depth, well inclination, azimuth, predicted value of weight on bit at bottom of well, predicted value of torque on bottom of well, hook load, surface torque, pump pressure, rotary table rotation speed, pump stroke, riser pressure, casing pressure, inlet density, outlet density, inlet temperature, outlet temperature, inlet conductance, outlet conductance, inlet flow, outlet flow, displacement, equivalent density, total pool volume at each time before the target time.
3. The method of claim 1, further comprising, prior to obtaining the friction coefficient for the target well at a plurality of times prior to the target time:
Obtaining a second drilling data set of a target well, wherein the second drilling data set comprises drilling design parameter values of the target well and drilling condition data at a plurality of moments before a moment before the target moment;
Determining predicted values of bottom hole weight and bottom hole torque of the target well at a moment before the target moment according to the second drilling data set and a second prediction model; the second prediction model is used for predicting the bottom hole weight and the bottom hole torque at the previous moment according to the data in the second drilling data set;
Obtaining actual measurement values of hook load and turntable torque of the target well at a moment before the target moment;
And determining the friction coefficient of the target well at the moment before the target moment by utilizing the whole stress model of the pipe column according to the predicted value of the bottom drilling pressure and the bottom torque at the moment before the target moment and the actual measured value of the hook load and the turntable torque.
4. The method of claim 3, further comprising, prior to determining predicted values of weight-on-bottom and torque-on-bottom for the target well at a time prior to the target time based on the second drilling dataset and a second predictive model:
acquiring a drilling dataset of at least one adjacent well of the target well;
preprocessing the drilling data set of at least one adjacent well to obtain a preprocessed drilling data set;
The drilling working condition data in the preprocessed drilling data set are converted into a supervised learning format according to a preset time step, and a first training set is obtained; wherein the drilling condition data is time sequence data;
taking the drilling design parameters in the preprocessed drilling data set as a second training set; wherein the well design parameters are non-time series data;
the first training set is used as input training data of a long-short-period memory network in a first target network, and the second training set is used as input training data of a multi-layer feedforward neural network in the target network; the target network is constructed according to the long-term memory network and the multi-layer feedforward neural network;
And training the first target network by using the first training set and the second training set to obtain the second prediction model.
5. The method of claim 1, further comprising, after determining the force condition of the tubular string in the target well at the target time based on the hook load and the reel torque at the target time, the friction coefficient at a time immediately prior to the target time:
determining whether an abnormality exists in the stress condition of the tubular column in the target well at the target moment;
Generating prompt information according to the stress condition of the tubular column in the target well at the target moment under the condition that the abnormality exists;
and sending the prompt information to a target processing object.
6. A device for determining a force condition of a tubular string, comprising:
the first acquisition module is used for acquiring friction coefficients of the target well at a plurality of moments before the target moment;
A second acquisition module for acquiring a first drilling dataset of the target well; wherein the first drilling dataset comprises drilling design parameter values for the target well and drilling regime data at a plurality of times prior to the target time;
A first determination module for determining a hook load and a carousel torque of the target well at a target time based on friction coefficients at a plurality of times prior to the target time, the first drilling data set, and a first predictive model; the first prediction model is used for predicting hook load and rotary table torque at the target moment according to friction coefficients at a plurality of moments before the target moment and data in the first drilling data set;
The second determining module is used for determining the stress condition of the tubular column in the target well at the target moment based on the hook load and the rotary table torque at the target moment and the friction coefficient at the moment before the target moment;
wherein determining a force condition of the tubular string in the target well at the target time based on the hook load and the turntable torque at the target time, the friction coefficient at a time immediately before the target time, comprises:
substituting the hook load and the turntable torque at the target moment and the friction coefficient at the moment before the target moment into a whole pipe column stress model, and obtaining the stress condition of each section of pipe column in the target well at the target moment from the iterative calculation of a wellhead section by section to a drill bit; wherein the stress condition of each section of pipe column comprises at least one of the following: the axial force, torque, bending moment, contact force and buckling state of the pipe column;
wherein prior to determining the hook load and the rotary table torque of the target well at the target time based on the friction coefficient, the first drilling data set, and the first predictive model at a plurality of times prior to the target time, further comprising:
acquiring a drilling data set and a friction data set of at least one adjacent well of the target well; wherein the friction data set comprises friction coefficients of the at least one adjacent well at each moment in time of drilling;
preprocessing the drilling data set of at least one adjacent well to obtain a preprocessed drilling data set;
converting the drilling working condition data in the preprocessed drilling data set and the friction coefficient in the friction data set into a supervised learning format according to a preset time step to obtain a third training set; wherein the drilling condition data is time sequence data;
Taking the drilling design parameters in the preprocessed drilling data set as a fourth training set; wherein the well design parameters are non-time series data;
Taking the third training set as input training data of a long-term and short-term memory network in a target network, and taking the fourth training set as input training data of a multi-layer feedforward neural network in the target network; the target network is constructed according to the long-term memory network and the multi-layer feedforward neural network;
and training the target network by using the third training set and the fourth training set to obtain the first prediction model.
7. A device for determining the stress condition of a tubular string, comprising a processor and a memory for storing instructions executable by the processor, which processor, when executing the instructions, implements the steps of the method of any one of claims 1 to 5.
8. A computer readable storage medium having stored thereon computer instructions which when executed implement the steps of the method of any of claims 1 to 5.
CN202011258628.3A 2020-11-12 2020-11-12 Method, device and equipment for determining stress condition of tubular column Active CN112330038B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011258628.3A CN112330038B (en) 2020-11-12 2020-11-12 Method, device and equipment for determining stress condition of tubular column

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011258628.3A CN112330038B (en) 2020-11-12 2020-11-12 Method, device and equipment for determining stress condition of tubular column

Publications (2)

Publication Number Publication Date
CN112330038A CN112330038A (en) 2021-02-05
CN112330038B true CN112330038B (en) 2024-06-28

Family

ID=74317883

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011258628.3A Active CN112330038B (en) 2020-11-12 2020-11-12 Method, device and equipment for determining stress condition of tubular column

Country Status (1)

Country Link
CN (1) CN112330038B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113591239B (en) * 2021-07-28 2022-10-21 中国石油大学(北京) Method, device and equipment for determining stress condition of pipe column
CN114856540B (en) * 2022-05-11 2024-05-28 西南石油大学 Horizontal well mechanical drilling speed while drilling prediction method based on online learning
CN115841247A (en) * 2022-09-30 2023-03-24 中国石油天然气集团有限公司 Digital drilling risk monitoring method and device
CN116362143B (en) * 2023-06-02 2023-08-22 中国石油天然气集团有限公司 Drill string friction analysis method and device
CN117454561B (en) * 2023-12-19 2024-03-08 成都信息工程大学 Analysis method and system for ultimate extension distance of coiled tubing in horizontal well

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10590761B1 (en) * 2013-09-04 2020-03-17 Petrolink International Ltd. Systems and methods for real-time well surveillance
CN105825028B (en) * 2016-03-31 2018-10-09 中国石油集团川庆钻探工程有限公司工程技术研究院 A kind of computational methods of oil-well rig hook load
FR3054391B1 (en) * 2016-07-22 2024-01-19 Renault Sas ESTIMATION OF THE TORQUE OF A COIL ROTOR MACHINE USING A NEURAL NETWORK
CN108678725A (en) * 2018-04-27 2018-10-19 中国石油集团川庆钻探工程有限公司 Real-time monitoring and analyzing method for underground friction resistance and torque
CN109931048A (en) * 2019-03-27 2019-06-25 南智（重庆）能源技术有限公司 Oil/gas well tubing and casing integrality detection method and evaluation system
CN111734396B (en) * 2020-06-22 2023-06-20 中国石油天然气集团有限公司 Friction determination method, device and equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"基于BP-LSTM双输入网络的大钩载荷与转盘扭矩预测";宋先知等;《中国石油大学学报（自然科学版）》;20220430;第46卷(第2期);第76-84页 *
"钻柱模组扭矩智能实时分析与卡钻趋势预测";朱硕等;《石油钻采工艺》;20210831;第43卷(第4期);第428-435页 *

Also Published As

Publication number Publication date
CN112330038A (en) 2021-02-05

Similar Documents

Publication Publication Date Title
CN112330038B (en) Method, device and equipment for determining stress condition of tubular column
CN111734396B (en) Friction determination method, device and equipment
Li et al. Research advances and debates on tubular mechanics in oil and gas wells
CN111520123B (en) Mechanical drilling speed prediction method, device and equipment
RU2633006C1 (en) Automation of drilling with use of optimal control based on stochastic theory
US8504308B2 (en) System and method for fatigue analysis of a bottom hole assembly
CN109931048A (en) Oil/gas well tubing and casing integrality detection method and evaluation system
RU2663653C1 (en) Improved estimation of well bore logging based on results of measurements of tool bending moment
WO2016160005A1 (en) Model generation for real-time rate of penetration prediction
RU2638072C2 (en) Elimination of abrupt oscillations of drilling string
NO347143B1 (en) System and method for monitoring a life of a component in a wellbore, and a non-transitory computerreadable medium
EP3542236B1 (en) Optimal storage of load data for lifetime prediction for equipment used in a well operation
US20180112512A1 (en) Fatigue analysis procedure for drill string
CA2971712C (en) Optimizing sensor selection and operation for well monitoring and control
US20230212937A1 (en) Automated electric submersible pump (esp) failure analysis
Saadeldin et al. Intelligent model for predicting downhole vibrations using surface drilling data during horizontal drilling
CN115841247A (en) Digital drilling risk monitoring method and device
CN103883267B (en) Arrangement method and device of centralizer for drill rod
CN110847883A (en) Wellhead device lifting height prediction method
CN111622752A (en) Acceleration evaluation method of three-dimensional shaft system
CN111625916A (en) Method and system for calculating stability value of well wall
CN113591239B (en) Method, device and equipment for determining stress condition of pipe column
Guo et al. Mechanical characteristics of cluster perforation string under running process in horizontal wells with unconventional oil/gas reservoirs
CN116662849B (en) Intelligent stuck drill type identification method based on digital twinning and knowledge graph
CN110567623B (en) Method for determining installation position of hydraulic oscillator on drilling tool

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
GR01 Patent grant
GR01 Patent grant