CN113673175B - Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model - Google Patents

Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model Download PDF

Info

Publication number
CN113673175B
CN113673175B CN202111223740.8A CN202111223740A CN113673175B CN 113673175 B CN113673175 B CN 113673175B CN 202111223740 A CN202111223740 A CN 202111223740A CN 113673175 B CN113673175 B CN 113673175B
Authority
CN
China
Prior art keywords
factor
influence
factors
matrix
degree
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
CN202111223740.8A
Other languages
Chinese (zh)
Other versions
CN113673175A (en
Inventor
许玉强
韩超
管志川
来福辉
李千登
樊朝斌
刘铭刚
何保伦
刘宽
李雅婷
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 East China
Original Assignee
China University of Petroleum East China
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 East China filed Critical China University of Petroleum East China
Priority to CN202111223740.8A priority Critical patent/CN113673175B/en
Publication of CN113673175A publication Critical patent/CN113673175A/en
Application granted granted Critical
Publication of CN113673175B publication Critical patent/CN113673175B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Optimization (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Biophysics (AREA)
  • Algebra (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of oil and gas drilling, in particular to a drilling shaft pressure imbalance influence factor analysis method based on a BP-DEMATEL-ISM model, and the traditional DEMATEL is improved by introducing a BP neural network and an ISM algorithm. The BP neural network utilizes the weight between the input layer and the output layer to obtain the direct incidence matrix of the influence factors, and the efficiency and the objectivity of the analysis method are improved. The method comprises the steps of considering the prevention and control problem of risks, improving a DEMATEL model by using an ISM algorithm in order to obtain a simplest hierarchical cause network model, simultaneously considering the particularity of drilling engineering, optimizing the ISM model aiming at the problems of a plurality of logging parameters related to shaft pressure imbalance, and building a network according to driving force. Different advantages of BP, DEMATEL and ISM models are fused, and an accident cause network with high calculation efficiency, simplest structure and hierarchical relation can be obtained.

Description

Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model
Technical Field
The invention relates to the technical field of oil and gas drilling, in particular to a drilling shaft pressure imbalance influence factor analysis method based on a BP-DEMATEL-ISM model.
Background
The complex problem in the pit is easily caused by the unbalanced pressure of the shaft in the drilling process, and the drilling efficiency is seriously influenced. At present, the main consideration in the research on the problem of the wellbore pressure imbalance at home and abroad is the reason, identification and control means of the downhole risk caused by the wellbore pressure imbalance, the influence factors of the wellbore pressure imbalance are not concerned much, and especially the relevance analysis among the influence factors is lacked. Through analysis, one of the main reasons which pay little attention to the method is that factors causing wellbore pressure imbalance are numerous, and the factors have complex correlation, so that ideal results are difficult to obtain efficiently and accurately by adopting a conventional analysis method. And with the development of big data analysis and artificial intelligence algorithm, a new idea is provided for solving the problem.
The DEMATEL (decision Making triple and Evaluation laboratory) algorithm is a common method in the field of influence factor identification, and the method forms a direct correlation matrix by collecting system factor group knowledge and determines the correlation among all factors in a cause-effect graph mode. However, in the existing literature research, the direct correlation matrix is mainly determined by questionnaires and expert scoring, and has strong subjectivity and great difficulty in implementation. In addition, the conventional DEMATEL cannot take the problem of risk prevention and control into consideration, and has the problem of large workload due to the fact that a network model is complicated in layering.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a drilling shaft pressure imbalance influence factor analysis method based on a BP-DEMATEL-ISM model, the BP-DEMATEL-ISM combined model is introduced to carry out quantitative analysis on each influence factor, and a direct correlation matrix is obtained by calculating the weight between the influence factors and the underground working condition through a BP neural network, so that the defect that an expert experience is required to be relied on in a DEMATEL algorithm is overcome; in consideration of the prevention and control problem of risks and in order to obtain the simplest and hierarchical cause network model, the ISM algorithm is introduced to improve the DEMATEL algorithm, the simplest and hierarchical cause network model is established, and a decision basis is provided for the prevention and control of the underground complex problem.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a drilling shaft pressure imbalance influence factor analysis method based on a BP-DEMATEL-ISM model comprises the following steps:
s1, taking the logging parameters in the comprehensive logging as input layer neurons, taking the working conditions in the comprehensive logging as output layer neurons of the shaft pressure imbalance judgment model, and constructing a BP neural network model;
s2, calculating the initial direct correlation matrix B of the system influence factors according to the overall weight vector obtained by the BP neural network,
Figure 150143DEST_PATH_IMAGE001
（1），
in the formula (1), the reaction mixture is,
Figure 723076DEST_PATH_IMAGE002
is the importance of the ith influencing factor relative to the jth influencing factor, wherein
Figure 643758DEST_PATH_IMAGE003
，
Figure 524121DEST_PATH_IMAGE004
(if
Figure 10597DEST_PATH_IMAGE005
Then, then
Figure 301901DEST_PATH_IMAGE006
）；
S3, normalizing the initial direct correlation matrix B according to the formula (2) to obtain a direct correlation matrix C,
Figure 287043DEST_PATH_IMAGE007
（2）；
s4, calculating a comprehensive influence matrix T,
Figure 220364DEST_PATH_IMAGE008
（3），
in the formula (3), the reaction mixture is,
Figure 358084DEST_PATH_IMAGE009
is a matrix of the units,
Figure 774284DEST_PATH_IMAGE010
is composed of
Figure 263035DEST_PATH_IMAGE011
The inverse of (1);
s5, adding each element in the comprehensive influence matrix T according to rows and columns to obtain the influence degree of the corresponding factor
Figure 468888DEST_PATH_IMAGE012
And degree of influence
Figure 461115DEST_PATH_IMAGE013
Wherein the degree of influence
Figure 812331DEST_PATH_IMAGE014
Represents the comprehensive influence degree and the influenced degree of the element i on all other elements
Figure 522798DEST_PATH_IMAGE015
Indicating the overall influence of the element i by all other factors,
Figure 266763DEST_PATH_IMAGE016
（4），
Figure 395387DEST_PATH_IMAGE017
（5），
s6, drawing a reason-result chart, wherein the abscissa is
Figure 199395DEST_PATH_IMAGE018
On the ordinate of
Figure 600420DEST_PATH_IMAGE019
；
Figure 662923DEST_PATH_IMAGE020
The central degree of the influence factors represents the importance degree of the influence factor i in all the influence factors, and the larger the value of the influence factor i, the higher the importance of the influence factor i is;
Figure 98584DEST_PATH_IMAGE021
the causal factor is the causal degree of the influence factor and represents the causal logic association degree of the influence factor i and all other factors, if the causal factor is positive, the influence of the factor on other influence factors is large, the causal factor is called, and if the causal factor is negative, the influence of the factor on other influence factors is large, the causal factor is called as the result factor;
s7, calculating an overall influence matrix H,
Figure 293067DEST_PATH_IMAGE022
（6）；
s8, establishing a reachable matrix K by setting a threshold value according to the overall influence matrix H,
Figure 712547DEST_PATH_IMAGE023
(7)；
s9, defining the sum of each row element in the reachable matrix K as the driving force of the elementQ i The sum of each row of elements is defined as the dependency of the elementY i
Figure 329473DEST_PATH_IMAGE024
（8），
Figure 603328DEST_PATH_IMAGE025
（9）；
After obtaining each elementQAndYafter the numerical value is obtained, the factors with the same driving force are taken as the same structural hierarchy factor to obtain the increment of the factorsA hierarchical structure; and (3) regarding the row corresponding to the column 1 of each factor in the reachable matrix K as the out-degree direction of the factor, regarding the column corresponding to the row 1 of the factor as the in-degree direction of the factor, and establishing a network model of the downhole complex problem cause network.
Compared with the prior art, the drilling shaft pressure imbalance influence factor analysis method based on the BP-DEMATEL-ISM model has the beneficial effects that: (1) aiming at the problems that the relevance of the influence factors of the shaft pressure imbalance is lack of research at present, and the analysis result is strong in subjectivity and high in implementation difficulty and the like caused by the fact that research data are obtained through expert scoring or questionnaires, the traditional DEMATEL is improved by introducing a BP neural network and an ISM algorithm, and the efficient and accurate analysis method for the relevance of the influence factors of the shaft pressure imbalance is obtained. The BP neural network utilizes the weight between the input layer and the output layer to obtain the direct incidence matrix of the influence factors, the defect of strong subjectivity of a conventional DEMATEL model is overcome, and the efficiency and the objectivity of the analysis method are improved. (2) The method comprises the steps of considering the prevention and control problem of risks, improving a conventional DEMATEL model by using an ISM algorithm in order to obtain a simplest hierarchical cause network model, considering the particularity of drilling engineering, optimizing the ISM model aiming at the problems of a plurality of logging parameters related to wellbore pressure imbalance, building a network according to driving force, combining different advantages of BP, DEMATEL and ISM models, and obtaining a most simplified accident cause network with high calculation efficiency and hierarchical relation. (3) Compared with the traditional ISM model, the problem of large workload when the reachable matrix is hierarchically divided and the factor types are more exists is solved, and the improved ISM model is improved on the basis of the ISM algorithm idea, so that the calculation process is simpler and more convenient, and the calculation efficiency is higher.
The technical scheme of the invention is as follows: in step S1, the logging parameters include a standard well depth, a late arrival well depth, a drilling rate, a rotational speed, a riser pressure, an inlet drilling fluid flow rate, an inlet drilling fluid density, an outlet drilling fluid density, an equivalent drilling fluid density, an inlet drilling fluid conductance, an outlet drilling fluid conductance, an inlet drilling fluid temperature, an outlet drilling fluid temperature, a total pool volume, a vertical well depth, a casing pressure, a drilling rate, an inlet drilling rate, an outlet rate, a drilling rate of drilling rate, a drilling rate of drilling rate, a drilling rate of drilling rate, a drilling rate of drilling fluid, a drilling rate of drilling fluid, a drilling rate of drilling fluid, a drilling rate of drilling fluid, a drilling rate of drilling fluid, a drilling rateTime, DC index, Normal compacted formation DC index, weight on bit, drilling rig Torque, Outlet drilling fluid flow, hook load, SIGMA index, H2S content, wherein the working conditions comprise well leakage, overflow, gas invasion, abnormal gas logging and normal drilling. The logging data has real-time monitoring performance on underground working conditions in the drilling process, so that the comprehensive logging parameters are used as influence factors of shaft pressure imbalance.
Drawings
FIG. 1 is a graph showing the cause-effect of the factors affecting imbalance of wellbore pressure in the first embodiment.
FIG. 2 is a diagram of a wellbore pressure imbalance cause network in a first embodiment.
Detailed Description
The following examples are further illustrative of the present invention, but the present invention is not limited thereto. The present invention is relatively complicated, and therefore, the detailed description of the embodiments is only for the point of the present invention, and the prior art can be adopted for the present invention.
The first embodiment is as follows:
the Mixi gas field is one of the gas fields in the middle of China with earlier exploration and development, the reservoir mainly comprises dense carbonate rock distribution, and has an abnormally high pressure stratum and a brine layer, so the geological environment is complex; the complex conditions are frequent in the drilling process, and the well leakage, overflow, gas invasion and gas detection abnormity are taken as main conditions. The data of the history of the 3 exploratory wells of the Mixi gas field are selected as analysis cases, and the logging data have real-time monitoring performance on underground working conditions in the drilling process, so that the comprehensive logging parameters are used as influence factors of shaft pressure imbalance.
According to the drilling shaft pressure imbalance influence factor analysis method based on the BP-DEMATEL-ISM model, the embodiment comprises the following steps:
s1, taking the logging parameters in the comprehensive logging as input layer neurons, taking the working conditions in the comprehensive logging as output layer neurons of the shaft pressure imbalance judgment model, and constructing a BP neural network model;
wherein the logging parameters include standard well depth C1, late arrival well depth C2, drilling rate C3, rotation speed C4, riser pressure C5, inlet drilling fluid flow rate C6, inlet drillingWell fluid density C7, outlet drilling fluid density C8, equivalent drilling fluid density C9, inlet drilling fluid conductance C10, outlet drilling fluid conductance C11, inlet drilling fluid temperature C12, outlet drilling fluid temperature C13, total pit volume C14, vertical well depth C15, casing pressure C16, time to drill C17, DC index C18, normal compacted formation DC index C19, weight to drill C20, drill plate torque C21, outlet drilling fluid flow C22, hook load C23, SIGMA index C24, H gma index2S content C25; the logging parameters comprise the working conditions including lost circulation, overflow, gas invasion, abnormal gas logging and normal drilling;
calculating according to the formula (10) to obtain the number of nodes of the hidden layer
Figure 14718DEST_PATH_IMAGE026
，
Figure 187074DEST_PATH_IMAGE027
（10）
In the formula (10), the compound represented by the formula (10),
Figure 76532DEST_PATH_IMAGE028
respectively representing the number of nodes of an input layer, a hidden layer and an output layer.
And performing network training on each hidden layer node number candidate value in order to obtain the optimal training precision, and finally determining the number of hidden layer nodes with the optimal training precision to be 14. The initial value of the weight is
Figure 971938DEST_PATH_IMAGE029
The training learning rate is 0.1, the number of iterations is 1000, and the target error is 0.0001.
S2, calculating the initial direct correlation matrix B of the system influence factors according to the overall weight vector obtained by the BP neural network,
specifically, the matlab is used for neural network training to obtain the direct correlation matrix B among the influencing factors, because the neural network training is a random process, in order to improve the accuracy of the analysis result, the neural network training is carried out for a plurality of times and the obtained direct correlation matrix is averaged,
Figure 554229DEST_PATH_IMAGE030
（1），
in the formula (1), the reaction mixture is,
Figure 213881DEST_PATH_IMAGE031
is the importance of the ith influencing factor relative to the jth influencing factor, wherein
Figure 625139DEST_PATH_IMAGE032
，
Figure 358740DEST_PATH_IMAGE033
(if
Figure 862665DEST_PATH_IMAGE034
Then, then
Figure 9612DEST_PATH_IMAGE035
）；
S3, normalizing the initial direct correlation matrix B according to the formula (2) to obtain a direct correlation matrix C,
Figure 709715DEST_PATH_IMAGE036
（2）；
s4, in order to eliminate the sweep effect caused by the factor change, a comprehensive influence matrix T is calculated,
Figure 609407DEST_PATH_IMAGE038
（3），
in the formula (3), the reaction mixture is,
Figure 533501DEST_PATH_IMAGE039
is a matrix of the units,
Figure 902165DEST_PATH_IMAGE040
is composed of
Figure 867674DEST_PATH_IMAGE041
The inverse of (1);
s5, adding each element in the comprehensive influence matrix T according to rows and columns to obtain the influence degree of the corresponding factor
Figure 903763DEST_PATH_IMAGE014
And degree of influence
Figure 733179DEST_PATH_IMAGE015
Wherein the degree of influence
Figure 979353DEST_PATH_IMAGE014
Represents the comprehensive influence degree and the influenced degree of the element i on all other elements
Figure 83575DEST_PATH_IMAGE015
Indicating the overall influence of the element i by all other factors,
Figure 193745DEST_PATH_IMAGE043
（4），
Figure 662903DEST_PATH_IMAGE044
（5），
s6, drawing a reason-result graph (see FIG. 1), wherein the abscissa is
Figure 6160DEST_PATH_IMAGE020
On the ordinate of
Figure 897761DEST_PATH_IMAGE021
；
Figure 580547DEST_PATH_IMAGE020
The central degree of the influence factors represents the importance degree of the influence factor i in all the influence factors, and the larger the value of the influence factor i, the higher the importance of the influence factor i is;
Figure 17344DEST_PATH_IMAGE021
in order to influence the degree of the cause of the factor,the causal logic association degree of the influence factor i and all other factors is shown, if the causal logic association degree is positive, the influence of the factor on other influence factors is large, the factor is called a cause factor, and if the causal logic association degree is negative, the influence of the factor on other influence factors is large, and the factor is called an effect factor;
s7, considering the influence of the influence factors on the matrix, calculating an overall influence matrix H,
Figure 598629DEST_PATH_IMAGE045
（6）；
s8, the integral influence matrix H of the DEMATEL algorithm and the reachable matrix K of the ISM algorithm have a single mapping relation, and in order to divide the hierarchy of the cause factors and identify the complex incidence relation among the factors, the threshold value of the reachable matrix is taken
Figure 982337DEST_PATH_IMAGE046
Establishing a reachable matrix K by setting a threshold value according to the overall influence matrix H,
Figure 581946DEST_PATH_IMAGE047
(7)；
s9, considering the problem that the hierarchical division of the reachable matrix by the classical ISM model has large workload when the factor types are large, the improvement is carried out on the basis of the ISM algorithm idea, and the sum of each row of elements in the reachable matrix K is defined as the driving force of the elementQ i The sum of each row of elements is defined as the dependency of the elementY i
Figure 438912DEST_PATH_IMAGE048
（8），
Figure 694444DEST_PATH_IMAGE049
（9）；
After obtaining each elementQAndYthe same factor of the same driving force is defined as the same valueStructural hierarchy factors, obtaining a hierarchical hierarchy of the factors; and (3) regarding the row corresponding to the column 1 of each factor in the reachable matrix K as the outgoing direction of the factor, regarding the column corresponding to the column 1 of the factor as the incoming direction of the factor, reordering the reachable matrix and performing hierarchical division on the influencing factors, and finally drawing a network diagram of the factors caused by the imbalance of the pressure of the drilling shaft according to the reordered reachable matrix (see figure 2).
Figure 413002DEST_PATH_IMAGE051
Table 1 reordering reachable matrices
According to fig. 1, it can be clearly found that the influencing factors are divided into an upper part and a lower part, wherein the coordinate axis is the above-mentioned reason factor, the coordinate axis is the below-mentioned result factor, and in order to keep the pressure unbalance of the shaft, more attention needs to be allocated to the reason factor, because the reason factor implies the information of the influencing factor, and the result factor presents the information of the influencing factor. Secondly, according to table 1 and fig. 2, it can be found that the rotation speed C4, the inlet drilling fluid temperature C12, the total pool volume C14, the DC index C18 and the weight-on-bit C20 are at the bottom layer of the causal network due to strong driving force and weak dependence on other factors, and are regarded as core factors influencing the pressure imbalance of the wellbore; the equivalent drilling fluid density C9 is most affected by other factors, has a stronger dependence and weaker driving force, is listed at the top of the network, and is considered as a direct cause of wellbore pressure imbalance. Because the risk is mostly completed instantly, the difficulty of adjusting the influence factors of the top layer is high. Therefore, the bottom layer influence factor is used as a basic cause of wellbore pressure unbalance, the top layer influence factor is a direct cause, the middle factor is a transition cause, risks are prevented fundamentally, and the bottom layer influence factor is controlled to be larger. Finally, as can be seen from the directed graph in fig. 2, each influencing factor not only has a hierarchical relationship, but also has a complex association relationship, and the relationship not only appears between the upper and lower hierarchies, but also appears across hierarchies. For this field, in order to achieve wellbore pressure imbalance during drilling, observational control of the inlet drilling fluid temperature, total pit volume, DC index and weight-on-bit should be taken into account.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.

Claims (2)

1. A drilling shaft pressure imbalance influence factor analysis method based on a BP-DEMATEL-ISM model comprises the following steps:
s1, taking the logging parameters in the comprehensive logging as input layer neurons, taking the working conditions in the comprehensive logging as output layer neurons of the shaft pressure imbalance judgment model, and constructing a BP neural network model;
s2, calculating the initial direct correlation matrix B of the system influence factors according to the overall weight vector obtained by the BP neural network,
Figure 304261DEST_PATH_IMAGE001
（1），
in the formula (1), the reaction mixture is,
Figure 436165DEST_PATH_IMAGE002
is the importance of the ith influencing factor relative to the jth influencing factor, wherein
Figure 430666DEST_PATH_IMAGE003
，
Figure 40639DEST_PATH_IMAGE004
If, if
Figure 69775DEST_PATH_IMAGE005
Then, then
Figure 372580DEST_PATH_IMAGE006
；
S3, normalizing the initial direct correlation matrix B according to the formula (2) to obtain a direct correlation matrix C,
Figure 588798DEST_PATH_IMAGE007
（2）；
s4, calculating a comprehensive influence matrix T,
Figure 503927DEST_PATH_IMAGE008
（3），
in the formula (3), the reaction mixture is,
Figure 121990DEST_PATH_IMAGE009
is a matrix of the units,
Figure 595697DEST_PATH_IMAGE010
is composed of
Figure 564790DEST_PATH_IMAGE011
The inverse of (1);
s5, adding each element in the comprehensive influence matrix T according to rows and columns to obtain the influence degree of the corresponding factor
Figure 516565DEST_PATH_IMAGE012
And degree of influence
Figure 520293DEST_PATH_IMAGE013
Wherein the degree of influence
Figure 899322DEST_PATH_IMAGE012
Represents the comprehensive influence degree and the influenced degree of the element i on all other elements
Figure 355711DEST_PATH_IMAGE013
Indicating the overall influence of the element i by all other factors,
Figure 845598DEST_PATH_IMAGE014
（4），
Figure 438254DEST_PATH_IMAGE015
（5），
s6, drawing a reason-result chart, wherein the abscissa is
Figure 17877DEST_PATH_IMAGE016
On the ordinate of
Figure 695983DEST_PATH_IMAGE017
；
Figure 255141DEST_PATH_IMAGE016
The central degree of the influence factors represents the importance degree of the influence factor i in all the influence factors, and the larger the value of the influence factor i, the higher the importance of the influence factor i is;
Figure 702302DEST_PATH_IMAGE017
the causal factor is the causal degree of the influence factor and represents the causal logic association degree of the influence factor i and all other factors, if the causal factor is positive, the influence of the factor on other influence factors is large, the causal factor is called, and if the causal factor is negative, the influence of the factor on other influence factors is large, the causal factor is called as the result factor;
s7, calculating an overall influence matrix H,
Figure 423134DEST_PATH_IMAGE018
（6）；
s8, establishing a reachable matrix K by setting a threshold value according to the overall influence matrix H,
Figure 854115DEST_PATH_IMAGE019
(7)；
s9, defining the sum of each row element in the reachable matrix K as the driving force of the elementQ i The sum of the elements in each column definesIs the dependency of the elementY j
Figure 951384DEST_PATH_IMAGE020
（8），
Figure 784211DEST_PATH_IMAGE021
（9）；
After obtaining each elementQAndYtaking the factors with the same driving force as the same structural hierarchy factor to obtain the hierarchical structure of the factors; and (3) regarding the row corresponding to the column 1 of each factor in the reachable matrix K as the out-degree direction of the factor, regarding the column corresponding to the row 1 of the factor as the in-degree direction of the factor, and establishing a network model of the downhole complex problem cause network.
2. The method of analyzing borehole pressure imbalance impact factors based on the BP-demotel-ISM model of claim 1, wherein:
in the step S1, the logging parameters include a standard well depth (C1), a late arrival well depth (C2), a rate of penetration (C3), a rotational speed (C4), a riser pressure (C5), an inlet drilling fluid flow rate (C6), an inlet drilling fluid density (C7), an outlet drilling fluid density (C8), an equivalent drilling fluid density (C9), an inlet drilling fluid conductance (C10), an outlet drilling fluid conductance (C11), an inlet drilling fluid temperature (C12), an outlet drilling fluid temperature (C13), a total pool volume (C14), a vertical well depth (C15), a casing pressure (C16), a time of penetration (C17), a DC index (C18), a normal compacted rock formation DC index (C19), a weight on bit (C20), a drill plate torque (C21), an outlet drilling fluid flow rate (C22), a hook load (C23), a SIGMA index (C24), H2S content (C25), the working conditions including lost circulation, flooding, gas cut, gas logging anomaly and normal drilling.
CN202111223740.8A 2021-10-21 2021-10-21 Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model Active CN113673175B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111223740.8A CN113673175B (en) 2021-10-21 2021-10-21 Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111223740.8A CN113673175B (en) 2021-10-21 2021-10-21 Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model

Publications (2)

Publication Number Publication Date
CN113673175A CN113673175A (en) 2021-11-19
CN113673175B true CN113673175B (en) 2022-01-18

Family

ID=78550626

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111223740.8A Active CN113673175B (en) 2021-10-21 2021-10-21 Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model

Country Status (1)

Country Link
CN (1) CN113673175B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107918358A (en) * 2017-11-17 2018-04-17 山东师范大学 Numerical control equipment failure analysis methods and device
CN109886525A (en) * 2018-12-26 2019-06-14 国网内蒙古东部电力有限公司经济技术研究院 Transformer substation LCC influence factor identification model based on DEMATEL-ISM method
CN110388189A (en) * 2019-05-15 2019-10-29 西南石油大学 A kind of high temperature high pressure deep well drilling well overflow intelligence throttle well killing method and device

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1704770A (en) * 2004-05-25 2005-12-07 张向军 Dual fuzzy neural network reservoir bed oil gas prediction technique
CN102704857B (en) * 2012-06-21 2014-06-11 中国石油大学(华东) Underground supercharging and accelerating system
CN104821764B (en) * 2015-04-23 2018-04-27 王金全 A kind of power equivalent method of pulse load according to system dynamic characteristic
US10727404B1 (en) * 2019-01-23 2020-07-28 International Business Machines Corporation Tunable resistive element
CN112882100B (en) * 2021-02-25 2024-01-12 中海石油深海开发有限公司 Reservoir parameter determining method and device, electronic equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107918358A (en) * 2017-11-17 2018-04-17 山东师范大学 Numerical control equipment failure analysis methods and device
CN109886525A (en) * 2018-12-26 2019-06-14 国网内蒙古东部电力有限公司经济技术研究院 Transformer substation LCC influence factor identification model based on DEMATEL-ISM method
CN110388189A (en) * 2019-05-15 2019-10-29 西南石油大学 A kind of high temperature high pressure deep well drilling well overflow intelligence throttle well killing method and device

Also Published As

Publication number Publication date
CN113673175A (en) 2021-11-19

Similar Documents

Publication Publication Date Title
DK2539540T3 (en) System and method for optimizing the drilling speed
CN112529341B (en) Drilling well leakage probability prediction method based on naive Bayesian algorithm
CN112836349A (en) Injection-production joint debugging intelligent decision method and system based on shaft parameters
CN112861423A (en) Data-driven water-flooding reservoir optimization method and system
CN116451013B (en) Deep stratum rock in-situ drillability grade value prediction method
CN113062731B (en) Intelligent identification method for complex underground drilling conditions
CN107292467A (en) A kind of drilling risk Forecasting Methodology
CN116384554A (en) Method and device for predicting mechanical drilling speed, electronic equipment and computer storage medium
CN115438823A (en) Borehole wall instability mechanism analysis and prediction method and system
GB2615696A (en) Predictive models and multi-objective constraint optimization algorithm to optimize drilling parameters of a wellbore
CN115586086A (en) Borehole wall instability analysis method based on big data
WO2021022632A1 (en) Oil shale continuous exploration drilling position optimization method
CN110988997A (en) Hydrocarbon source rock three-dimensional space distribution quantitative prediction technology based on machine learning
CN113673175B (en) Drilling shaft pressure imbalance influence factor analysis method based on BP-DEMATEL-ISM model
CN117035197B (en) Intelligent lost circulation prediction method with minimized cost
CN117172360A (en) Drilling mechanical drilling speed optimization method, system, equipment and medium based on MLP and high-efficiency PSO
CN114562236B (en) Geological engineering integrated lost circulation real-time early warning method based on integrated learning model
CN116522583A (en) Horizontal well stratum pressure prediction method based on linear regression method
CN113431557B (en) Underground borehole track tracking method based on artificial intelligence
CN111625916A (en) Method and system for calculating stability value of well wall
CN112727433A (en) Drilling parameter optimization method
CN113935131B (en) Use effect prediction method and application of speed-increasing drilling tool
CN116754735B (en) Method for predicting water quality components and concentration content of mine water of coal mine
CN115619788B (en) Automatic quantitative evaluation method for quality of three-dimensional geological model
CN117973486A (en) Mechanical drilling speed prediction method based on artificial intelligence

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