[go: up one dir, main page]

CN118297196A - Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium - Google Patents

Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium Download PDF

Info

Publication number
CN118297196A
CN118297196A CN202310003854.4A CN202310003854A CN118297196A CN 118297196 A CN118297196 A CN 118297196A CN 202310003854 A CN202310003854 A CN 202310003854A CN 118297196 A CN118297196 A CN 118297196A
Authority
CN
China
Prior art keywords
lost circulation
data
real
time sequence
similarity
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
CN202310003854.4A
Other languages
Chinese (zh)
Inventor
孙旭东
李昌盛
杨传书
沈希为
付宣
徐术国
黄历铭
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 Petroleum and Chemical Corp
Sinopec Petroleum Engineering Technology Research Institute Co Ltd
Original Assignee
China Petroleum and Chemical Corp
Sinopec Petroleum Engineering Technology Research Institute Co Ltd
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 Petroleum and Chemical Corp, Sinopec Petroleum Engineering Technology Research Institute Co Ltd filed Critical China Petroleum and Chemical Corp
Priority to CN202310003854.4A priority Critical patent/CN118297196A/en
Publication of CN118297196A publication Critical patent/CN118297196A/en
Pending legal-status Critical Current

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
    • 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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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

Landscapes

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

Abstract

The invention provides a lost circulation prediction method, a lost circulation prediction device, a computing device and a storage medium, wherein the method comprises the following steps: acquiring real-time sequence data of appointed parameters in the drilling process of the target well; comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; and when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process. According to the similarity between the real-time sequence data and the lost circulation model data in the drilling process, lost circulation in the drilling process is predicted, and accuracy and reliability of lost circulation prediction results are improved.

Description

Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium
Technical Field
The present invention relates to the field of drilling engineering, and in particular, to a lost circulation prediction method, a lost circulation prediction device, a computing device, and a storage medium.
Background
For a long time, the real-time prediction of well drilling lost circulation mainly aims at the lost circulation characteristics of different areas, a rule for identifying and judging the lost circulation is established, and whether the lost circulation occurs or not is determined through the rule. The mode is difficult to apply in a large area due to the problems of low judging success rate, large difference of judging rules in different areas and the like.
In recent years, a great deal of research has begun to shift to methods based on big data and machine learning. Although the method can save labor and has higher flexibility, the accuracy of predicting lost circulation by simply relying on machine learning is lower and the reliability is poor.
Both the above methods mechanically use "manual rules" and "machine learning" techniques to predict lost circulation with low accuracy, and therefore a new lost circulation prediction method is highly desirable.
Disclosure of Invention
The invention mainly aims to provide a lost circulation prediction method, a lost circulation prediction device, a computing device and a storage medium, so that the lost circulation prediction accuracy is improved.
The invention provides a lost circulation prediction method, which comprises the following steps: acquiring real-time sequence data of appointed parameters in the drilling process of the target well; comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; and when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process.
In one embodiment, comparing the real-time sequence data of the specified parameter with the corresponding lost circulation model data, determining the similarity between the real-time sequence data of the specified parameter and the corresponding lost circulation model data, comprises: comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, determining the time regular distance between the real-time sequence data of the specified parameters and the corresponding lost circulation model data through a DTW algorithm, and taking the time regular distance as the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process, including: and when the time warping distance is smaller than a preset distance threshold value, determining that lost circulation of the target drilling engineering occurs in the drilling process.
In one embodiment, the real-time timing data of the specified parameter includes real-time timing data of at least two specified parameters; comparing the real-time sequence data of the specified parameter with corresponding lost circulation model data, determining the similarity between the real-time sequence data of the specified parameter and the corresponding lost circulation model data, comprising: comparing the real-time sequence data of at least two specified parameters with the corresponding lost circulation model data respectively, and determining the similarity between the real-time sequence data of at least two specified parameters and the corresponding lost circulation model data respectively; when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process, including: when the number of the specified parameters of which the similarity meets the corresponding similarity threshold value condition reaches a preset number, determining that lost circulation of the target drilling engineering occurs in the drilling process.
In one embodiment, the at least two specified parameters include: outlet flow, surface fluid volume, and/or riser pressure.
In one embodiment, the step of generating lost circulation model data corresponding to the specified parameters comprises: acquiring historical logging data of specified parameters of a plurality of welltimes with preset time periods before and after the occurrence of the well leakage, and generating a plurality of well leakage sample time sequence data of the specified parameters corresponding to the plurality of welltimes one by one according to the historical logging data of the specified parameters; fitting the time sequence data of the plurality of lost circulation samples according to a preset fitting method to obtain lost circulation model data corresponding to the specified parameters.
In one embodiment, the preset fitting method includes: mean fitting and/or median fitting.
In one embodiment, the specified parameters are determined from a plurality of parameters of the drilling process using principal component analysis and/or multidimensional scaling analysis.
The invention provides a lost circulation prediction device, comprising: the data acquisition module is used for acquiring real-time sequence data of specified parameters in the drilling process of the target well; the data comparison module is used for comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; and the lost circulation prediction module is used for determining lost circulation of the target drilling engineering in the drilling process when the similarity meets the similarity threshold condition.
The invention provides a computing device comprising a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the lost circulation prediction method are realized.
The present invention provides a storage medium in which a computer program is stored which, when executed by a processor, implements the steps of the lost circulation prediction method described above.
According to the method, firstly, data samples of a specific area are collected and combed systematically, time sample sequences of TPIT, SPP, FLOWOUT key parameters of occurrence of lost circulation are screened out through expert experience, and lost circulation model data are constructed. And calculating the DTW regular distance between the real-time sequence data of the well site and the corresponding well leakage model data, so as to predict the well leakage working condition of the well drilling according to the DTW regular distance.
According to the method, the lost circulation model data is constructed by using the lost circulation historical logging data, the similarity between the real-time sequence data and the lost circulation model data in the drilling process is calculated through a DTW algorithm, lost circulation prediction is achieved according to the similarity, and high prediction accuracy is achieved.
Because the real-time data of the well drilling site has the characteristic of time sequence trend representation, the time sequence data analysis has good application prospect. The method of the embodiment fully utilizes expert experience to develop screening analysis of the lost circulation model data sample, and is favorable for obtaining extremely high lost circulation prediction accuracy by combining the time sequence of the data.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a undue limitation on the application, wherein:
FIG. 1 is a plot of total pool volume TPIT over time for a plurality of wellruns experiencing lost circulation;
FIG. 2 is a flow chart of a lost circulation prediction method according to an exemplary embodiment of the present application;
Fig. 3A-3F are timing data for a plurality of lost circulation samples of TPIT in accordance with one embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Drilling lost circulation refers to a complex downhole situation in which various working fluids (including drilling fluids, cement slurries, completion fluids, and other fluids, etc.) are introduced directly into the formation under differential pressure during downhole operations such as drilling, cementing, testing, or workover. Lost circulation includes permeability loss, fractured loss, and vuggy loss. The main reasons include: 1) The drilled stratum has natural leakage channels, such as high-permeability stratum, fractured stratum and karst cave stratum, and the leakage channels can be artificially generated due to poor drilling fluid performance or improper operation; 2) The pressure of the drilled stratum is not high, or the density of the drilling fluid is too high, so that a large pressure difference is generated; 3) The viscosity and shear force of the drilling fluid are too large, so that the pumping pressure is too large, and pressure agitation is generated to suppress the formation leakage; 4) The drilling fluid has poor sand carrying performance, unclean well wall or excessive water loss, thick filter cake, improper operations of drilling and discharging, pump opening and the like, and pressure agitation is generated. In the drilling construction process of a drilling well site, the identification and early warning of the occurrence of lost circulation through the real-time data of the well site are an extremely important ring in the risk prevention and control of the drilling engineering, and are also important factors for reducing the risk cost in the drilling engineering.
By analyzing historical logging data of a plurality of wellheads with lost circulation, the logging data have certain similarity among the plurality of wellheads for some logging parameters in the lost circulation process. For example, as shown in fig. 1, in which the horizontal axis represents the sampling point and the vertical axis represents the total cell volume (TPIT), for TPIT, the trend of TPIT of each well has a high similarity with time after occurrence of lost circulation (sampling points 151 to 261), and almost all trends gradually decrease after rapid increase. Thus, based on this similarity, a model curve for predicting lost circulation may be created using the lost circulation-sensitive logging parameters to predict lost circulation by the similarity between the measured curve and the model curve.
Example 1
The present embodiment provides a lost circulation prediction method, and fig. 2 is a flowchart of a lost circulation prediction method according to an exemplary embodiment of the present application. As shown in fig. 2, the method of the present embodiment may include:
s100: real-time sequence data of specified parameters in the drilling process of the target well is obtained.
S200: and comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data.
S300: and when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process.
By the lost circulation prediction method, real-time sequence data of specified parameters in the drilling process are compared with corresponding lost circulation model data, so that whether lost circulation of a target well is generated or not is predicted. By utilizing the time sequence data, the characteristic of time-varying specified parameters of the drilling engineering can be effectively combined to predict lost circulation. The lost circulation model data can be calibrated by an expert, so that accuracy and reliability of lost circulation prediction results are improved.
In an embodiment, comparing the real-time sequence data of the specified parameter with the corresponding lost circulation model data, determining the similarity between the real-time sequence data of the specified parameter and the corresponding lost circulation model data may include: comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, determining the time regular distance between the real-time sequence data of the specified parameters and the corresponding lost circulation model data through a DTW (DYNAMIC TIME WARPING, dynamic time-warping) algorithm, and taking the time regular distance as the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; when the similarity meets a similarity threshold condition, determining that the target drilling engineering is lost circulation during the drilling process may include: and when the time warping distance is smaller than a preset distance threshold value, determining that lost circulation of the target drilling engineering occurs in the drilling process.
The DTW algorithm performs linear scaling on a certain sequence so as to align with another time sequence data, thereby realizing the elasticity measurement of a complex time sequence, measuring the similarity of two time sequences with different lengths, and realizing the similarity comparison between physical events represented by two heterogeneous time sequences.
In other embodiments, other algorithms may be used to determine the similarity between the real-time timing data of the specified parameters and the corresponding lost circulation model data, such as euclidean distance, angle cosine, and the like.
In one embodiment, the real-time timing data of the specified parameter includes real-time timing data of at least two specified parameters; comparing the real-time sequence data of the specified parameter with the corresponding lost circulation model data, determining the similarity between the real-time sequence data of the specified parameter and the corresponding lost circulation model data may include: comparing the real-time sequence data of at least two specified parameters with the corresponding lost circulation model data respectively, and determining the similarity between the real-time sequence data of at least two specified parameters and the corresponding lost circulation model data respectively; when the similarity meets a similarity threshold condition, determining that the target drilling engineering is lost circulation during the drilling process may include: when the number of the specified parameters of which the similarity meets the corresponding similarity threshold value condition reaches a preset number, determining that lost circulation of the target drilling engineering occurs in the drilling process.
In this embodiment, the number of the specified parameters may be 2,3 or 4, which is not limited in the present application.
In one embodiment, the at least two specified parameters may include: outlet flow, surface fluid volume, and/or riser pressure.
For example, the real-time series data of the outlet flow may be compared with lost circulation model data of the outlet flow, a first similarity determined, and the first similarity compared with a first similarity threshold; comparing the real-time sequence data of the total volume of the ground liquid filling with the lost circulation model data of the total volume of the ground liquid filling, determining a second similarity, and comparing the second similarity with a second similarity threshold; comparing the real-time sequence data of the riser pressure with the lost circulation model data of the riser pressure, determining a third similarity, and comparing the third similarity with a third similarity threshold. Accordingly, the preset threshold condition may be that at least two similarities reach respective similarity thresholds, that is, the first and second similarities reach respective similarity thresholds, the second and third similarities reach respective similarity thresholds, or the first, second and third similarities reach respective similarity thresholds. In another example, the preset threshold condition may be that, in a case where the first similarity reaches the first similarity threshold, at least one of the second and third similarities reaches the corresponding similarity threshold.
Of course, in other embodiments, the at least two specified parameters may also include other parameters, for example, in the drilling arts, other weight on bit data, displacement data, etc., in the drilling fluids, viscosity, density, etc. of the drilling fluids. The number of specified parameters and the specific specified parameters including which and preset threshold conditions can be set as required, which is not particularly limited in the present application.
In one embodiment, the step of generating lost circulation model data corresponding to the specified parameters may comprise: acquiring historical logging data of specified parameters of a plurality of welltimes with preset time periods before and after the occurrence of the well leakage, and generating a plurality of well leakage sample time sequence data of the specified parameters corresponding to the plurality of welltimes one by one according to the historical logging data of the specified parameters; fitting the time sequence data of the plurality of lost circulation samples according to a preset fitting method to obtain lost circulation model data corresponding to the specified parameters.
In this embodiment, the preset time period before and after occurrence of the lost circulation may include a time period that is experienced by the overall process in which the lost circulation occurs. The preset duration may be determined empirically by an expert, or may be determined by determining a time-dependent change of the historical logging data of the specified parameter, for example, when a time-dependent change trend of the historical logging data of the specified parameter is mutated, the mutated time may be used as a start time of occurrence of lost circulation, and after the occurrence of lost circulation is determined, when the time-dependent change trend of the historical logging data of the specified parameter is smoothed, the smoothed time may be used as an end time of occurrence of lost circulation. Of course, the preset duration before and after occurrence of the lost circulation may be determined according to other methods as required, and the length of the preset duration may be set as required, which is not limited in the present application.
In this embodiment, for example, the plurality of wellbores includes 10 wellbores, and for each wellbore, the specified parameters include outlet flow, surface fluid filling volume, and riser pressure. Then, for the outlet flow, 10 groups of lost circulation sample time sequence data corresponding to 10 well orders one by one are included, and the 10 groups of lost circulation sample time sequence data are fitted to obtain lost circulation model data corresponding to the outlet flow; for the total volume of the ground liquid irrigation, 10 groups of lost circulation sample time sequence data corresponding to 10 well times one by one are included, and the 10 groups of lost circulation sample time sequence data are fitted to obtain lost circulation model data corresponding to the total volume of the ground liquid irrigation; and for the pressure of the vertical pipe, 10 groups of lost circulation sample time sequence data corresponding to 10 well times one by one are included, and the 10 groups of lost circulation sample time sequence data are fitted to obtain lost circulation model data corresponding to the pressure of the vertical pipe.
In an embodiment, the preset fitting method for obtaining lost circulation model data corresponding to the specified parameters may include: mean fitting and/or median fitting. Other fitting methods may be utilized as desired, as the application is not limited in this regard.
In one embodiment, the specified parameters may be determined from a plurality of parameters of the drilling process using principal component analysis and/or multidimensional scaling analysis.
According to the lost circulation prediction method, an expert can manually mark lost circulation model data to form standard lost circulation model data. According to the similarity between the real-time sequence data and the lost circulation model data in the drilling process, lost circulation in the drilling process is predicted, and accuracy and reliability of lost circulation prediction results are improved. And data similarity comparison is performed through time regularity of the DTW time sequence data, so that a similarity comparison result has higher accuracy. According to research, in lost circulation prediction, the real-time data of the drilling well site has the characteristic of time sequence trend, so that the accuracy of lost circulation prediction results is improved, and the method has good application prospect.
Example two
The embodiment provides a specific embodiment of a lost circulation prediction method. The lost circulation prediction method of the present embodiment may include the following steps (1) to (6).
(1) Lost circulation key index screening
Principal Component Analysis (PCA) or multidimensional scaling analysis can be performed on parameters included in the drilling flow data and the pressure data to screen three parameter indicators from which the relationship with lost circulation is more intimate, for example, the three parameter indicators can be: outlet flow (FLOWOUT, unit L/s), total surface tank volume (total tank volume TPIT, unit m 3), stand Pipe pressure (SPP, stand Pipe Pressrue, unit MPa).
(2) Well leakage sample curve calibration
1) And collecting historical logging data of various parameter indexes before and after the occurrence of lost circulation of an n (n > 10) wellhead. Taking TPIT as an example, historical logging data of the leakage amount before and after occurrence of lost circulation is shown in fig. 3A to 3F, wherein the horizontal axis in the figure represents sampling points, the vertical axis represents the leakage amount of the total pool volume, and it can be seen that the leakage amount gradually increases after occurrence of lost circulation, and correspondingly, TPIT gradually decreases.
2) The expert marks the time period of occurrence of the lost circulation according to the on-site record (drilling daily report-abnormal working condition), and generates lost circulation sample data, for example, the historical logging data of 30 minutes before and after occurrence of the lost circulation, namely the historical logging data of 60 minutes of total duration before and after occurrence of the lost circulation, can be marked. In one embodiment, the time period length of lost circulation sample data for each parameter indicator for each well is the same.
3) The expert marks the sampling points in the lost circulation sample data of each parameter index, for example, 50-200 sampling points in the lost circulation sample data of each parameter index of each well, for example, 150 sampling points can be marked. In one embodiment, the number of samples of lost circulation sample data for each parameter indicator for each well is the same. For the selection of specific sampling points, the determination can be carried out according to the lost circulation event of each well.
4) And connecting sampling points of lost circulation sample data of each parameter index of each well according to the time sequence to obtain a total of 3*n sample curves.
(3) Construction of lost circulation model data
And fitting a lost circulation sample data curve of n times for each parameter index to obtain lost circulation model data. Well leakage model data corresponding to the outlet flow, the total surface liquid filling volume and the pressure of the vertical pipe can be obtained.
(4) DTW algorithm
The DTW algorithm performs linear scaling on a certain sequence so as to align with another time sequence data, thereby realizing the elasticity measurement of a complex time sequence, measuring the similarity of two time sequences with different lengths, and realizing the similarity comparison between physical events represented by two heterogeneous time sequences.
And judging the degree of difference between the real-time sequence data of the specified parameters and the lost circulation model data through a DTW algorithm.
After the real-time sequence data of the outlet flow rate, the total volume of the ground liquid and the pressure of the vertical pipe of the well drilling site are obtained, the time sequence array constructed by the real-time sequence data of each parameter is compared with the time sequence array constructed by the corresponding well leakage model data, the DTW regular distance between the two is calculated, and the DTW regular distance is used as the similarity between the real-time sequence data and the well leakage model data.
For example, the similarity between two time series X and Y is calculated, a two-dimensional matrix is formed by X and Y, a normalization Path (Warp Path) calculation is performed, and the distance of the shortest normalization Path between the two time series is taken as the DTW normalization distance between the two sequences.
The pseudo code for calculating the DTW normalized distance is as follows (using python3.6 and scikitlearn 1.0.0):
(5) DTW computer well leakage discrimination rule
In this embodiment, the lost circulation model data curve of TPIT begins to drop rapidly after lost circulation occurs, so we can predict lost circulation by the change in similarity between the real-time sequence data curve of TPIT and the lost circulation model data curve of TPIT of the real-time data. FLOWOUT and SPP, and so on.
And calculating according to the similarity between the real-time sequence data and the lost circulation model data to obtain a DTW regular distance between the real-time sequence data and the lost circulation model data, and further carrying out lost circulation prediction according to the DTW regular distance.
By experimental analysis of the data of a plurality of lost circulation cases on site, the judgment standard of lost circulation prediction can be determined, so that higher lost circulation prediction accuracy is obtained.
For example, criteria for lost circulation prediction may include two types:
1) If the difference degree corresponding to any one of the three parameter indexes is smaller than 10, the well leakage is determined;
2) And if the difference degree of any two parameter indexes in the three parameter indexes is simultaneously smaller than 15, the well leakage is determined.
(6) Well site real-time data acquisition and identification
Real-time sequence data of the outlet flow rate of the drilling well site, the total volume of the surface liquid filling and the pressure of the vertical pipe are acquired, the real-time sequence data can comprise sampling points with the same number or different numbers as the well leakage model data, for example, 125 sampling points can be acquired, a time sequence array is constructed by the 125 sampling points, the DTW regular distance between the time sequence array and the time sequence data constructed by the well leakage model data with corresponding parameters is calculated, and whether well leakage occurs is predicted according to the DTW regular distance.
According to the method, firstly, data samples of a specific area are collected and combed systematically, time sample sequences of TPIT, SPP, FLOWOUT key parameters of occurrence of lost circulation are screened out through expert experience, and lost circulation model data are constructed. And calculating the DTW regular distance between the real-time sequence data of the well site and the corresponding well leakage model data, so as to predict the well leakage working condition of the well drilling according to the DTW regular distance.
According to the method, the lost circulation model data is constructed by using the lost circulation historical logging data, the similarity between the real-time sequence data and the lost circulation model data in the drilling process is calculated through a DTW algorithm, lost circulation prediction is achieved according to the similarity, and high prediction accuracy is achieved.
Because the real-time data of the well drilling site has the characteristic of time sequence trend representation, the time sequence data analysis has good application prospect. The method of the embodiment fully utilizes expert experience to develop screening analysis of the lost circulation model data sample, and is favorable for obtaining extremely high lost circulation prediction accuracy by combining the time sequence of the data.
The method of the embodiment is used for carrying out experiments and implementation in remote monitoring projects of drilling construction of a certain oil field exploration block, collecting drilling real-time sequence data of 13 test wells in total of the exploration block, constructing lost circulation model data based on SPP, TPIT and FLOWOUT parameters, and carrying out lost circulation working condition prediction on 13 test wells.
Meanwhile, the other 6 wells are subjected to well leakage event prediction, and the result proves that the method of the embodiment can realize the prediction of all well leakage working conditions, and compared with the original well leakage working condition manual recording time, the method of the embodiment advances the prediction time by 1-8 minutes, realizes the advance of well leakage identification time, and provides more buffering time for later well leakage working condition processing.
Example III
The present embodiment provides a lost circulation prediction apparatus, including: the data acquisition module is used for acquiring real-time sequence data of specified parameters in the drilling process of the target well; the data comparison module is used for comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data; and the lost circulation prediction module is used for determining lost circulation of the target drilling engineering in the drilling process when the similarity meets the similarity threshold condition.
In another embodiment, the lost circulation prediction apparatus further comprises a processor and a memory, the processor configured to execute the following program modules stored in the memory: the data acquisition module, the data comparison module and the lost circulation prediction module are used for predicting lost circulation in the drilling process
Example IV
The present embodiment provides a computing device including a processor and a memory, where the memory stores a computer program that, when executed by the processor, implements the steps of the lost circulation prediction method described above.
In one embodiment, the computing device may include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or FLASH memory (FLASH RAM). Memory is an example of computer-readable media.
Example five
The present embodiment provides a storage medium in which a computer program is stored which, when executed by a processor, implements the steps of the lost circulation prediction method described above.
A computer program may employ any combination of one or more storage media. The storage medium may be a readable signal medium or a readable storage medium.
The readable storage medium may comprise, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include the following: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave in which a readable computer program is embodied. Such a propagated data signal may take many forms, including, for example, electro-magnetic, optical, or any suitable combination of the preceding. A readable signal medium may also be any storage medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer program embodied on a storage medium may be transmitted using any appropriate medium, which may include, for example, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
The computer programs for performing the operations of the present invention can be written in any combination of one or more programming languages. The programming languages may include object oriented programming languages such as Java, C++, etc., and may also include conventional procedural programming languages such as the "C" language or similar programming languages. The computer program may execute entirely on the user's computing device, partly on the user's device, or entirely on a remote computing device or server. In situations involving a remote computing device, the remote computing device may be connected to the user computing device through any kind of network (e.g., may include a local area network or a wide area network), or may be connected to an external computing device (e.g., connected over the internet using an internet service provider).
It is noted that the terms used herein are used merely to describe particular embodiments and are not intended to limit exemplary embodiments in accordance with the present application, when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It should be noted that the terms "first," "second," and the like in the description and the claims and drawings of the present application are used for distinguishing between similar objects and not for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances.
It should be understood that the exemplary embodiments in this specification may be embodied in many different forms and should not be construed as limited to only the embodiments set forth herein. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of these exemplary embodiments to those skilled in the art, and should not be construed as limiting the application.
While the spirit and principles of the present invention have been described with reference to several particular embodiments, it is to be understood that the invention is not limited to the disclosed embodiments nor does it imply that features of the various aspects are not useful in combination, nor are they useful in any combination, such as for convenience of description. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (10)

1. A lost circulation prediction method, comprising:
acquiring real-time sequence data of appointed parameters in the drilling process of the target well;
comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data;
And when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process.
2. The lost circulation prediction method according to claim 1, wherein comparing the real-time series data of the specified parameter with the corresponding lost circulation model data, determining the similarity between the real-time series data of the specified parameter and the corresponding lost circulation model data comprises:
comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data, determining the time regular distance between the real-time sequence data of the specified parameters and the corresponding lost circulation model data through a DTW algorithm, and taking the time regular distance as the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data;
when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process, including:
And when the time regular distance is smaller than a preset distance threshold value, determining that lost circulation of the target drilling engineering occurs in the drilling process.
3. The lost circulation prediction method of claim 1, wherein the real-time temporal data of the specified parameters comprises real-time temporal data of at least two specified parameters;
Comparing the real-time sequence data of the specified parameter with corresponding lost circulation model data, determining the similarity between the real-time sequence data of the specified parameter and the corresponding lost circulation model data, comprising:
Comparing the real-time sequence data of at least two specified parameters with the corresponding lost circulation model data respectively, and determining the similarity between the real-time sequence data of at least two specified parameters and the corresponding lost circulation model data respectively;
when the similarity meets a similarity threshold condition, determining that lost circulation of the target drilling engineering occurs in the drilling process, including:
When the number of the specified parameters of which the similarity meets the corresponding similarity threshold value condition reaches a preset number, determining that lost circulation of the target drilling engineering occurs in the drilling process.
4. The lost circulation prediction method according to claim 3, wherein the at least two specified parameters comprise: outlet flow, surface fluid volume, and/or riser pressure.
5. The lost circulation prediction method according to claim 1, wherein the step of generating lost circulation model data corresponding to the specified parameters comprises:
acquiring historical logging data of specified parameters of a plurality of welltimes with preset time periods before and after occurrence of well leakage, and generating a plurality of well leakage sample time sequence data of the specified parameters corresponding to the plurality of welltimes one by one according to the historical logging data of the specified parameters;
fitting the time sequence data of the plurality of lost circulation samples according to a preset fitting method to obtain lost circulation model data corresponding to the specified parameters.
6. The lost circulation prediction method according to claim 5, wherein the preset fitting method comprises: mean fitting and/or median fitting.
7. The lost circulation prediction method according to claim 1 or 5, wherein the specified parameters are determined from a plurality of parameters of the drilling process using principal component analysis and/or multidimensional scaling analysis.
8. A lost circulation prediction device, comprising:
The data acquisition module is used for acquiring real-time sequence data of specified parameters in the drilling process of the target well;
the data comparison module is used for comparing the real-time sequence data of the specified parameters with corresponding lost circulation model data and determining the similarity between the real-time sequence data of the specified parameters and the corresponding lost circulation model data;
And the lost circulation prediction module is used for determining lost circulation of the target drilling engineering in the drilling process when the similarity meets a similarity threshold condition.
9. A computing device comprising a processor and a memory, the memory having stored therein a computer program which, when executed by the processor, implements the steps of the lost circulation prediction method of any one of claims 1 to 7.
10. A storage medium having stored therein a computer program which, when executed by a processor, implements the steps of the lost-circulation prediction method according to any one of claims 1 to 7.
CN202310003854.4A 2023-01-03 2023-01-03 Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium Pending CN118297196A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310003854.4A CN118297196A (en) 2023-01-03 2023-01-03 Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310003854.4A CN118297196A (en) 2023-01-03 2023-01-03 Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium

Publications (1)

Publication Number Publication Date
CN118297196A true CN118297196A (en) 2024-07-05

Family

ID=91685111

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310003854.4A Pending CN118297196A (en) 2023-01-03 2023-01-03 Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium

Country Status (1)

Country Link
CN (1) CN118297196A (en)

Similar Documents

Publication Publication Date Title
RU2595828C1 (en) Method to control operation of submersible electric pump
CA2673637C (en) Method and apparatus for multi-dimensional data analysis to identify rock heterogeneity
RU2723805C9 (en) Method and computer system for control of drilling of the wells
CN102597422B (en) Formation fluid sampling control
CA2808858C (en) Wellbore real-time monitoring and analysis of fracture contribution
Ponomareva et al. Operational method for determining bottom hole pressure in mechanized oil producing wells, based on the application of multivariate regression analysis
US8265874B2 (en) Expert system for selecting fit-for-purpose technologies and wells for reservoir saturation monitoring
AU2007211291A1 (en) Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators
BR112015009197B1 (en) METHOD AND SYSTEM FOR PERFORMING A DRILLING OPERATION
US20090182694A1 (en) Evaluation of acid fracturing treatments in an oilfield
US11767750B1 (en) Gas-oil ratio forecasting in unconventional reservoirs
US20140172303A1 (en) Methods and systems for analyzing the quality of a wellbore
CN118133159B (en) Drilling risk identification method, system and related equipment thereof
RU2714997C1 (en) Optimum storage of data on load for prediction of service life of equipment used during well operation
Molinari et al. A Reduced Physics Modeling Approach to Understand Multiphase Well Production Performance for Unconventional Reservoirs
US20110087471A1 (en) Methods and Systems For Determining Near-Wellbore Characteristics and Reservoir Properties
CN116307133A (en) Tight oil and gas reservoir natural fracture prediction method, system, medium, equipment and terminal
CN117471922B (en) Intelligent control method and system for oil casing electric punching equipment
CN107605477B (en) Method for determining breakthrough of oil gas extracted by underground pump and stabilization time of water content
CN118297196A (en) Lost circulation prediction method, lost circulation prediction device, computing equipment and storage medium
US11525356B1 (en) Identifying types of contaminations of drilling fluids for a drilling operation
CN117236403A (en) Shaft stability prediction model training and shaft stability prediction method and device
CN118965023B (en) Data-model coupling driven drilling overflow mode identification system and method
CN116579263B (en) Comprehensive analysis method based on oil and gas well drainage dynamic data
Sankaran et al. Hybrid Data-Driven and Physics-Informed Reservoir Modeling for Unconventional Reservoirs

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