CN107292467A - A kind of drilling risk Forecasting Methodology - Google Patents

A kind of drilling risk Forecasting Methodology Download PDF

Info

Publication number
CN107292467A
CN107292467A CN201610197209.0A CN201610197209A CN107292467A CN 107292467 A CN107292467 A CN 107292467A CN 201610197209 A CN201610197209 A CN 201610197209A CN 107292467 A CN107292467 A CN 107292467A
Authority
CN
China
Prior art keywords
mrow
msub
measured data
drilling
feature vector
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
CN201610197209.0A
Other languages
Chinese (zh)
Inventor
徐术国
李昌盛
杨传书
孙旭
张好林
赵勇
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 Research Institute of Petroleum Engineering
Original Assignee
China Petroleum and Chemical Corp
Sinopec Research Institute of Petroleum Engineering
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 Research Institute of Petroleum Engineering filed Critical China Petroleum and Chemical Corp
Priority to CN201610197209.0A priority Critical patent/CN107292467A/en
Publication of CN107292467A publication Critical patent/CN107292467A/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
    • G06Q10/06—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

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)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • Animal Husbandry (AREA)
  • General Health & Medical Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Agronomy & Crop Science (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Earth Drilling (AREA)

Abstract

A kind of drilling risk Forecasting Methodology, including：Initial data obtaining step, obtains the measured data of drilling well to be analyzed, and measured data includes the initial data of multiple affecting parameters；Characteristic vector determines step, and measured data is handled, and obtains the characteristic vector of measured data；Degree of association coefficient determines step, and according to the characteristic vector of measured data and default drilling risk judgment matrix, the degree of association coefficient of each element and each fault type of the characteristic vector of measured data is calculated respectively；Risk profile step, calculates measured data and the degree of association of each fault type, and judge that drilling well to be analyzed whether there is risk according to the degree of association according to degree of association coefficient.This method can carry out the prediction of drilling risk, Real time identification drilling risk and early warning in drilling course to any position of full well section, help construction technical staff control drilling risk.

Description

Drilling risk prediction method
Technical Field
The invention relates to the technical field of oil and gas exploration and development, in particular to a drilling risk prediction method.
Background
The drilling risk prediction means that the risk existing in the drilling operation is predicted by using a certain method according to the drilling operation data so as to achieve the purposes of prevention and control. The drilling operation has a very complex process, and the process has the influence of a plurality of uncertain factors. Therefore, the risk prediction of the influencing factors in the drilling process is very important, and the effective prediction result has great significance for the drilling field operation.
The current methods for predicting the drilling risk mainly comprise a neural network method, a case reasoning method and the like, and the methods have the limitation that a large amount of adjacent well information is needed. And the lack of adjacent well data for the new block makes these methods difficult to work in drilling risk prediction. At the same time, the size of the sample size determines the drilling risk prediction accuracy of these methods, even with an adjacent well case sample. That is, in the case of a small amount of historical samples, the accuracy of the existing drilling risk prediction methods is also compromised, and the actual production requirements cannot be met.
Disclosure of Invention
In order to solve the above problems, the present invention provides a drilling risk prediction method, including:
the method comprises the steps of obtaining original data, namely obtaining actual measurement data of a well to be analyzed, wherein the actual measurement data comprises original data of a plurality of influence parameters;
determining a characteristic vector, namely processing the original data to obtain the characteristic vector of the actually measured data;
determining relevance coefficients, namely respectively calculating relevance coefficients of each element of the feature vector of the measured data and each fault type according to the feature vector of the measured data and a preset drilling risk judgment matrix;
and risk prediction, namely calculating the correlation degree of the measured data and each fault type according to the correlation coefficient, and judging whether the well to be analyzed has risks or not according to the correlation degree.
According to one embodiment of the invention, in the feature vector determination step,
respectively calculating the variable quantity of each influence parameter according to the original data;
and determining the characteristic vector of the actually measured data according to the variable quantity of each influence parameter.
According to one embodiment of the present invention, when calculating the variation of each influence parameter, an average value of each influence parameter is first calculated, and then the variation of each influence parameter is determined according to a difference between each influence parameter and the average value thereof.
According to one embodiment of the invention, the amount of change in the influencing parameter comprises:
torque variation, net total pool volume variation, flow difference, hook load variation, drilling tool open hole dead time, weight-on-bit variation, mechanical specific energy value and downhole cyclic equivalent density.
According to an embodiment of the present invention, in the feature vector determining step, when the torque variation amount is calculated, the real-time torque is first normalized to the torque of a drill bit of a preset size at a preset depth, so as to obtain a standard torque, and the torque variation amount is calculated according to the standard torque.
According to an embodiment of the present invention, in the association degree coefficient determining step:
respectively calculating a maximum error value and a minimum error value of the feature vector of the measured data and a preset drilling risk judgment standard matrix;
and calculating the association degree coefficient of each element and each fault type in the feature vector of the measured data according to the maximum error value and the minimum error value.
According to an embodiment of the present invention, the correlation coefficient between each element in the feature vector of the measured data and each fault type is calculated according to the following expression:
wherein, ξijJ-th element y in feature vector representing measured datajThe relevance coefficient aiming at the ith fault, m represents the total number of fault types, n represents the number of elements contained in the feature vector of each fault,maxandminrespectively representing the characteristic vector of the measured data and the preset drilling risk judgment standard momentMaximum and minimum error values of the matrix, p representing the resolution factor, xijAnd (3) representing the element in the ith row and the jth column in the preset drilling risk judgment standard matrix.
According to one embodiment of the invention, the maximum error value and the minimum error value of the eigenvector of the measured data and the preset drilling risk judgment standard matrix are calculated according to the following expressions:
wherein,maxandminrespectively representing the maximum error value and the minimum error value of the eigenvector of the measured data and the preset drilling risk judgment standard matrix, yjJ-th element, x, in a feature vector representing measured dataijAnd (3) representing the element in the ith row and the jth column in the preset drilling risk judgment standard matrix.
According to one embodiment of the invention, the drilling risk relevance of each influencing parameter is calculated according to the following expression:
wherein r isiIndicating the degree of correlation, ω, between the measured data and the i-th faultjWeight of the jth element in the feature vector representing the measured data for the ith type of fault, ξijAnd the correlation coefficient of the jth element in the feature vector representing the measured data for the ith fault is obtained, m represents the total number of fault types, and n represents the number of elements contained in the feature vector of each fault.
The invention designs a novel method for predicting drilling risks based on improved grey correlation, which utilizes real-time logging data, combines parameters such as drill column size, well hole size and drilling fluid performance, calculates the risk correlation degree of each point on a well track at a certain time interval (the risk capable of being predicted comprises the risks of drill bit failure, drilling tool breakage, well leakage, well kick, obstruction card, sliding drilling and the like), predicts the drilling risks at any position of the whole well section in the process of drilling, identifies the drilling risks in real time, gives an early warning and helps construction technicians to control the drilling risks.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required in the description of the embodiments or the prior art:
FIG. 1 is a flow diagram of drilling risk prediction according to one embodiment of the present invention;
FIG. 2 is a flow diagram of determining a feature vector according to one embodiment of the invention;
fig. 3 is a flow chart for determining a correlation coefficient according to one embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced without some of these specific details or with other methods described herein.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
Aiming at the problems in the prior art, the invention provides a drilling risk prediction method based on grey correlation. Through the relevance, constructors can identify various drilling risks in time and take corresponding measures in the drilling construction process, so that the drilling risks are avoided to the maximum extent.
Fig. 1 shows a flow chart of a drilling risk prediction method provided by the present embodiment.
As shown in fig. 1, the drilling risk prediction method provided in this embodiment first obtains measured data of a drilling well to be analyzed in a measured data obtaining step S101. In this embodiment, the measured data acquired in step S101 includes raw data of a plurality of influence parameters.
Through the analysis of the existing drilling risk prediction method, the establishment of the standard failure mode used in the risk prediction process of the existing drilling risk prediction method is only limited to the change of logging data, the influence of drilling fluid on a drilling tool is not considered, and the influence of the size and the depth of a drill bit on the torque is also not considered.
In this embodiment, the plurality of influence parameters included in the measured data acquired in step S101 preferably include: torque, total sump volume, flow, hook load, tool open hole dead time, weight on bit, mechanical ratio, and cyclic Equivalent density (ECD). In the process of obtaining the original data of the influence parameters, firstly, relevant parameters (including well depth, torque, inlet flow, outlet flow, total pool volume, bit pressure, hook load, riser pressure, drilling time, rotating speed and the like) are collected from real-time logging data, and then the original data of the influence parameters are obtained by using data of field drilling fluid performance, drilling tool combination, drill bits and the like.
In the embodiment, the influence of parameters such as drilling tools and well drilling on the final prediction result can be reflected through the parameter ECD. Meanwhile, the influence of the drilling fluid on the final prediction result can be reflected through the floating weight, and the floating weight is the buoyancy of the drilling fluid on the drilling tool.
The effect of bit size and well depth on torque can be reflected by the standard torque, in this embodiment, the real-time torque value is normalized to a torque of 1000 meters of bit depth 8-1/2 ".
The occurrence of an abnormality in any one of the drilling steps may cause a risk, and therefore, various factors in the drilling process, such as the drilling fluid, the drilling tool, the drill bit, and the drilling parameters (including torque, weight on bit, etc.) during the drilling process, need to be comprehensively considered. And when one or more parameters change beyond corresponding threshold values, judging corresponding risks according to the established grey correlation theoretical model, predicting and analyzing the drilling risks in real time, and guiding the site.
In step S102, the method provided in this embodiment processes the original data in the measured data, so as to obtain the feature vector of the measured data. In this embodiment, each element in the feature vector of the measured data obtained in step S102 can represent the variation of the corresponding impact parameter.
Specifically, as shown in fig. 2, in the process of determining the feature vector of the measured data, first, in step S201, the variation of each influence parameter is calculated according to the original data of each influence parameter, and then, in step S202, the feature vector of the measured data is determined according to the variation of each influence parameter.
In the process of calculating the variation of a certain influence parameter, the original data of the influence parameter in a certain preset time length is measured first, so that a plurality of sampling values of the influence parameter in the preset time length are obtained. And then averaging the sampling values to obtain the average value of the influence parameter in a preset time length. And finally, calculating the difference value between the sampling value of the influence parameter at the moment to be analyzed and the average value to obtain the variation of the influence parameter.
It should be noted that, in the present embodiment, the process of calculating the variation of each impact parameter in step S201 is similar, and therefore, the process of calculating the variation of each impact parameter is not described herein again.
Meanwhile, it should be noted that, in other embodiments of the present invention, the variation of each influencing parameter may also be calculated in other reasonable manners, and the present invention is not limited thereto. For example, in an embodiment of the present invention, the average value of each influence parameter in the preset time period may be calculated by mean filtering, dynamic averaging, and the like, and the variation of each influence parameter may be determined by calculating the variance or standard deviation of each influence parameter in the preset time period.
In this embodiment, in order to reduce the influence of the bit size and the well depth on the torque value, when the torque variation is calculated, the real-time torque is first normalized to the torque of the bit with the preset size at the preset depth, so as to obtain the standard torque, and the average value of the torque and the torque variation are calculated according to the standard torque. Specifically, the torque is preferably normalized to a torque of 1000 meters of the 8-1/2 "drill bit in this embodiment. Of course, in other embodiments of the invention, the torque may be normalized to that of other reasonable bit sizes and/or well depths, as desired, and the invention is not limited in this regard.
In the process of calculating the net change of the total pool volume, the real-time total pool volume is firstly used for calculating the change of the total pool volume, the volume change of a drill string in the well is calculated by using the volume of the drill string in the well, the deepened and reduced total pool volume of the well is calculated by using the change of the well depth, and then the arithmetic sum of the three is calculated. The arithmetic sum of the three is the net change of the total pool volume caused by artificially increasing and decreasing mud, well kick and well leakage. In this embodiment, the net change in total pool volume is used to determine kick and loss accidents.
The flow difference referred to in this embodiment is the difference between the outlet flow and the inlet flow, where the flow difference can be used to characterize a kick or leak event. The hook load variation can be used for representing the blocking accident, and can be obtained by calculating the difference value of hook load, weight on bit and float weight. The open hole dead time of the drilling tool can be used for representing the drill sticking accident, and the dead time can be determined by measuring the serious dead time of the drilling tool. The bit pressure variation can be used for representing the drilling slip accident, and in the embodiment, the bit pressure variation, the hook position and the diameter difference of the drill bit are used as main basis for judging whether the drilling slip accident occurs.
The mechanical specific energy value represents the mechanical energy required to crush a volume of rock per unit time, and in this embodiment, the mechanical specific energy value can be calculated according to the following expression:
where MSE represents the mechanical specific energy value, WOB represents weight on bit, Dia represents bottom hole diameter, RPM represents rotational speed, TOB represents bit torque, and ROP represents rate of penetration.
In the embodiment, in the process of calculating the circulating equivalent density ECD, underground hydraulic parameters such as pressure loss in a drill string, bit pressure drop and annulus pressure loss are calculated in real time according to a well structure, a well track, a drilling tool structure, mud performance, drilling process parameters collected in real time and the like, and then the underground ECD value is determined by comprehensive calculation by synthesizing relevant parameters measured on the ground in real time on the basis. Of course, in other embodiments of the invention, the downhole ECD value may be determined in other reasonable ways, as the invention is not limited in this respect.
In step S202, a feature vector of the measured data may be determined according to the variation of each of the influencing parameters. In this embodiment, the relative change of the value of each influence parameter is of interest in practical application, so in this embodiment, the change of each influence parameter is measured by setting a threshold corresponding to each influence parameter. When the variation of the influence parameter exceeds the threshold value, the influence parameter is considered to be changed. In the present embodiment, it is preferable to use 1 to indicate that the influence parameter is increased, use-1 to indicate that the influence parameter is decreased, and use 0 to indicate that the influence parameter is kept unchanged. Therefore, the feature vector of the actually measured data acquired at a certain moment can be obtained.
As shown in fig. 1 again, after the eigenvector of the measured data is obtained, in step S103, the correlation coefficient between the eigenvector of the measured data and each fault type is calculated according to the eigenvector of the measured data and the preset drilling risk judgment matrix.
In this embodiment, in step S103, a grey correlation analysis method is preferably used to calculate a correlation coefficient between the feature vector of the measured data and each fault type. The gray correlation analysis is a method for identifying faults by using a gray model. When the system is abnormal, the detected data shows some abnormality, and each fault has its corresponding characteristic phenomenon. The essence of the grey correlation analysis is to determine the similarity between the eigenvector of the measured data and the eigenvector matrix of the standard fault signature sequence (i.e., the pre-set drilling risk judgment matrix). Wherein, the closer the curve is, the greater the correlation degree between the corresponding data sequences is.
In this embodiment, it is assumed that a total number of failure types that may occur during drilling construction is m, and the number of elements included in the feature vector of each failure type is n. As can be seen from the above description, n is 8 in this embodiment.
In this embodiment, the normal fault signature sequence eigenvector matrix (i.e., the predetermined drilling risk judgment matrix) XRCan be expressed as:
wherein, XiA feature vector representing the i-th type of fault. It is noted that the feature vector matrix X is used for the standard fault signature sequenceRIt is said that the elements in each column have the same physical meaning, but may differ in size.
In this embodiment, the feature vector Y of the measured data determined in step S102TCan be expressed as:
YT＝[y1,y2,...,yn](3)
wherein, yjThe jth element in the feature vector of the measured data.
Fig. 3 shows a flowchart for calculating the correlation coefficient between the feature vector of the measured data and each fault type in this embodiment.
As shown in fig. 3, in step S301, a maximum error value and a minimum error value of the eigenvector of the measured data and the predetermined drilling risk judgment standard matrix are calculated, and then in step S302, based on the maximum error value and the minimum error value, a correlation coefficient between the eigenvector of the measured data and each fault type is calculated.
Specifically, the method provided by the present embodiment calculates the measured value according to the following expression in step S301According to the maximum error value of the characteristic vector and the preset drilling risk judgment standard matrixmaxAnd a minimum error valuemin：
Wherein x isijAnd (3) representing the element in the ith row and the jth column in the preset drilling risk judgment standard matrix.
In step 302, the present embodiment calculates the correlation coefficient between the feature vector of the measured data and each fault type according to the following expression:
wherein, ξijJ-th element y in feature vector representing measured datajAnd for the relevance coefficient of the ith fault, m represents the total number of fault types, n represents the number of elements contained in the feature vector of each fault, and rho represents a resolution coefficient.
As shown in fig. 1 again, after obtaining the correlation coefficient between each element in the feature vector of the measured data and each fault type, the method provided in this embodiment determines the correlation between the measured data and each fault type according to the correlation coefficient in step S104, and determines whether there is a risk in the drilling well to be analyzed according to the correlation.
Because different influence parameters have different influence degrees on the drilling construction process, in order to represent the importance degrees of the different influence parameters, the method provided by the embodiment also gives different weights to the correlation coefficient when calculating the correlation between the measured data and each fault type according to the correlation coefficient. Specifically, in this embodiment, the association degree between the measured data and each fault type is preferably calculated by using the following expression:
wherein r isiIndicating the degree of correlation, ω, between the measured data and the i-th faultjA weight of a jth element in the feature vector representing the measured data for the ith type of fault.
It should be noted that, for the feature vector of the measured data, it satisfies:
in this embodiment, each fault type is preset with a correlation threshold, and if the correlation between the measured data and a certain fault type is greater than the correlation threshold, it indicates that the fault occurs in the well to be analyzed and the fault type of the fault can be determined.
In order to verify the practicability of the drilling risk prediction method provided by the embodiment, the embodiment analyzes the X drilling in the meta dam region by using the method. Firstly, well drilling data of a drilled well in the meta-dam area is obtained, and the data are analyzed, so that useful data are obtained. And then carrying out manual statistics, analysis and arrangement on the acquired data. And summarizing abnormal parameter change rules, parameter change threshold values and the like according to the parameters of wells with complex conditions in the meta-dam area.
The X well is drilled to 5496 meters, the field personnel are inquired to determine that no mud is artificially reduced and no ground loss exists, the net increment of the pool volume is reduced by calculation, the flow difference is increased by the logging data change phenomenon, and finally the correlation degree of the lost circulation is obtained by calculation and matching of a theoretical model, wherein the correlation degree of the lost circulation is 0.89 which exceeds the threshold of the correlation degree of the lost circulation, so that the lost circulation can be judged. The method can be used for finding the field leakage and timely processing the leakage, thereby avoiding the further occurrence of risks.
From the description, the invention designs a new method for predicting the drilling risk based on the improved grey correlation, which utilizes real-time logging data, combines parameters such as the size of a drill column, the size of a borehole, the performance of drilling fluid and the like, calculates the risk correlation degree of each point on a borehole track at certain time intervals (the risk capable of being predicted comprises the risks of bit failure, drilling tool breakage, well leakage, well kick, obstruction card, sliding drilling and the like), predicts the drilling risk at any position of the whole well section in the drilling process, identifies the drilling risk in real time and gives an early warning to help construction technicians to control the drilling risk.
It is to be understood that the disclosed embodiments of the invention are not limited to the particular structures or process steps disclosed herein, but extend to equivalents thereof as would be understood by those skilled in the relevant art. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting.
Reference in the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Thus, the appearances of the phrase "one embodiment" or "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
While the above examples are illustrative of the principles of the present invention in one or more applications, it will be apparent to those of ordinary skill in the art that various changes in form, usage and details of implementation can be made without departing from the principles and concepts of the invention. Accordingly, the invention is defined by the appended claims.

Claims (9)

1. A method of drilling risk prediction, the method comprising:
the method comprises the steps of obtaining original data, namely obtaining actual measurement data of a well to be analyzed, wherein the actual measurement data comprises original data of a plurality of influence parameters;
a feature vector determining step of processing the measured data to obtain a feature vector of the measured data;
determining relevance coefficients, namely respectively calculating relevance coefficients of each element of the feature vector of the measured data and each fault type according to the feature vector of the measured data and a preset drilling risk judgment matrix;
and risk prediction, namely calculating the correlation degree of the measured data and each fault type according to the correlation coefficient, and judging whether the well to be analyzed has risks or not according to the correlation degree.
2. The method of claim 1, wherein, in the feature vector determination step,
respectively calculating the variable quantity of each influence parameter according to the measured data;
and determining the characteristic vector of the actually measured data according to the variable quantity of each influence parameter.
3. The method according to claim 2, wherein in calculating the variation of each of the influencing parameters, the average value of each of the influencing parameters is first calculated, and then the variation of each of the influencing parameters is determined based on the difference between the influencing parameter and the average value thereof.
4. A method according to claim 2 or 3, wherein the amount of change in the influencing parameter comprises:
torque variation, net total pool volume variation, flow difference, hook load variation, drilling tool open hole dead time, weight-on-bit variation, mechanical specific energy value and downhole cyclic equivalent density.
5. The method as claimed in claim 4, wherein in the eigenvector determining step, in calculating the torque variation, the real-time torque is first normalized to the torque of a predetermined-sized drill bit at a predetermined depth to obtain a standard torque, and the torque variation is calculated based on the standard torque.
6. The method according to any one of claims 1 to 5, wherein in the correlation coefficient determining step:
respectively calculating a maximum error value and a minimum error value of the feature vector of the measured data and a preset drilling risk judgment standard matrix;
and calculating the association degree coefficient of each element and each fault type in the feature vector of the measured data according to the maximum error value and the minimum error value.
7. The method of claim 6, wherein the correlation coefficient of each element in the feature vector of the measured data with each fault type is calculated according to the following expression:
<mrow> <msub> <mi>&amp;xi;</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;delta;</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>+</mo> <msub> <mi>&amp;rho;&amp;delta;</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> </mrow> <mrow> <mo>|</mo> <msub> <mi>y</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>|</mo> <mo>+</mo> <msub> <mi>&amp;rho;&amp;delta;</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> </mrow> </mfrac> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mi>m</mi> <mo>;</mo> <mi>j</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mi>n</mi> </mrow>
wherein, ξijJ-th element y in feature vector representing measured datajThe relevance coefficient aiming at the ith fault, m represents the total number of fault types, n represents the number of elements contained in the feature vector of each fault,maxandminrespectively representing the maximum error value and the minimum error value of the characteristic vector of the measured data and a preset drilling risk judgment standard matrix, wherein rho represents a resolution coefficient, and x representsijAnd (3) representing the element in the ith row and the jth column in the preset drilling risk judgment standard matrix.
8. The method of claim 6 or 7, wherein the maximum and minimum error values of the eigenvector of the measured data and the matrix of predetermined drilling risk criteria are calculated according to the following expressions:
<mrow> <msub> <mi>&amp;delta;</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <munder> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> <mrow> <mn>1</mn> <mo>&amp;le;</mo> <mi>i</mi> <mo>&amp;le;</mo> <mi>m</mi> </mrow> </munder> <mo>&amp;lsqb;</mo> <munder> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> <mrow> <mn>1</mn> <mo>&amp;le;</mo> <mi>j</mi> <mo>&amp;le;</mo> <mi>n</mi> </mrow> </munder> <mo>|</mo> <msub> <mi>y</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>|</mo> <mo>&amp;rsqb;</mo> </mrow>
<mrow> <msub> <mi>&amp;delta;</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>=</mo> <munder> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> <mrow> <mn>1</mn> <mo>&amp;le;</mo> <mi>i</mi> <mo>&amp;le;</mo> <mi>m</mi> </mrow> </munder> <mo>&amp;lsqb;</mo> <munder> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> <mrow> <mn>1</mn> <mo>&amp;le;</mo> <mi>j</mi> <mo>&amp;le;</mo> <mi>n</mi> </mrow> </munder> <mo>|</mo> <msub> <mi>y</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>|</mo> <mo>&amp;rsqb;</mo> </mrow>
wherein,maxandminrespectively representing the maximum error value and the minimum error value of the eigenvector of the measured data and the preset drilling risk judgment standard matrix, yjJ-th element, x, in a feature vector representing measured dataijAnd (3) representing the element in the ith row and the jth column in the preset drilling risk judgment standard matrix.
9. The method of any of claims 1 to 8, wherein the drilling risk correlation for each impact parameter is calculated according to the expression:
<mrow> <msub> <mi>r</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>&amp;omega;</mi> <mi>j</mi> </msub> <msub> <mi>&amp;xi;</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>,</mo> <mn>0</mn> <mo>&amp;le;</mo> <msub> <mi>&amp;omega;</mi> <mi>j</mi> </msub> <mo>&amp;le;</mo> <mn>1</mn> <mo>,</mo> <mn>1</mn> <mo>&amp;le;</mo> <mi>i</mi> <mo>&amp;le;</mo> <mi>m</mi> </mrow>
wherein r isiIndicating the degree of correlation, ω, between the measured data and the i-th faultjWeight of the jth element in the feature vector representing the measured data for the ith type of fault, ξijAnd the correlation coefficient of the jth element in the feature vector representing the measured data for the ith fault is obtained, m represents the total number of fault types, and n represents the number of elements contained in the feature vector of each fault.
CN201610197209.0A 2016-03-31 2016-03-31 A kind of drilling risk Forecasting Methodology Pending CN107292467A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610197209.0A CN107292467A (en) 2016-03-31 2016-03-31 A kind of drilling risk Forecasting Methodology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610197209.0A CN107292467A (en) 2016-03-31 2016-03-31 A kind of drilling risk Forecasting Methodology

Publications (1)

Publication Number Publication Date
CN107292467A true CN107292467A (en) 2017-10-24

Family

ID=60086842

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610197209.0A Pending CN107292467A (en) 2016-03-31 2016-03-31 A kind of drilling risk Forecasting Methodology

Country Status (1)

Country Link
CN (1) CN107292467A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109308570A (en) * 2018-08-21 2019-02-05 中国石油天然气集团有限公司 A kind of underground complex working condition recognition methods, apparatus and system
CN109779602A (en) * 2018-12-12 2019-05-21 武汉盛华伟业科技股份有限公司 A kind of drilling engineering intelligent and safe method for prewarning risk and system
CN110121053A (en) * 2018-02-07 2019-08-13 中国石油化工股份有限公司 A kind of video monitoring method of situ of drilling well risk stratification early warning
CN110874686A (en) * 2018-09-04 2020-03-10 中国石油化工股份有限公司 Underground risk discrimination method
CN111119835A (en) * 2018-11-01 2020-05-08 中国石油化工股份有限公司 Method and system for identifying working conditions while drilling
CN111691873A (en) * 2019-03-13 2020-09-22 中国石油化工股份有限公司 Method and system for calculating borehole wall stability value for borehole wall stability prediction
CN113129157A (en) * 2019-12-30 2021-07-16 中石化石油工程技术服务有限公司 Underground stuck-drill fault real-time early warning method suitable for shale gas long water section
CN113393334A (en) * 2020-03-11 2021-09-14 中国石油化工股份有限公司 Drilling parameter optimization recommendation method and system
CN113775327A (en) * 2020-06-05 2021-12-10 中国石油化工股份有限公司 Method, device and equipment for detecting drilling abnormity, drilling well and storage medium
CN116128309A (en) * 2023-04-11 2023-05-16 胜利油田利丰石油设备制造有限公司 Petroleum engineering well site operation maintenance management system based on Internet of things

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102163301A (en) * 2011-04-12 2011-08-24 上海大学 Method for predicting emergence size of crop pests based on BP (back propagation) artificial neural network
CN103775072A (en) * 2014-01-16 2014-05-07 燕山大学 Logging information-based lithotype determining method
CN103971175A (en) * 2014-05-06 2014-08-06 华中科技大学 Short-term load prediction method of multistage substations
CN104156568A (en) * 2014-07-22 2014-11-19 国家电网公司 Transformer fault diagnosis method on basis of weighted gray correlation and fuzzy clustering
CN104794499A (en) * 2015-05-08 2015-07-22 上海电机学院 Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102163301A (en) * 2011-04-12 2011-08-24 上海大学 Method for predicting emergence size of crop pests based on BP (back propagation) artificial neural network
CN103775072A (en) * 2014-01-16 2014-05-07 燕山大学 Logging information-based lithotype determining method
CN103971175A (en) * 2014-05-06 2014-08-06 华中科技大学 Short-term load prediction method of multistage substations
CN104156568A (en) * 2014-07-22 2014-11-19 国家电网公司 Transformer fault diagnosis method on basis of weighted gray correlation and fuzzy clustering
CN104794499A (en) * 2015-05-08 2015-07-22 上海电机学院 Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110121053A (en) * 2018-02-07 2019-08-13 中国石油化工股份有限公司 A kind of video monitoring method of situ of drilling well risk stratification early warning
CN109308570A (en) * 2018-08-21 2019-02-05 中国石油天然气集团有限公司 A kind of underground complex working condition recognition methods, apparatus and system
CN109308570B (en) * 2018-08-21 2022-05-10 中国石油天然气集团有限公司 Underground complex working condition identification method, device and system
CN110874686A (en) * 2018-09-04 2020-03-10 中国石油化工股份有限公司 Underground risk discrimination method
CN110874686B (en) * 2018-09-04 2022-05-17 中国石油化工股份有限公司 Underground risk discrimination method
CN111119835A (en) * 2018-11-01 2020-05-08 中国石油化工股份有限公司 Method and system for identifying working conditions while drilling
CN109779602A (en) * 2018-12-12 2019-05-21 武汉盛华伟业科技股份有限公司 A kind of drilling engineering intelligent and safe method for prewarning risk and system
CN111691873B (en) * 2019-03-13 2023-09-19 中国石油化工股份有限公司 Well wall stability value calculation method and system for well wall stability prediction
CN111691873A (en) * 2019-03-13 2020-09-22 中国石油化工股份有限公司 Method and system for calculating borehole wall stability value for borehole wall stability prediction
CN113129157A (en) * 2019-12-30 2021-07-16 中石化石油工程技术服务有限公司 Underground stuck-drill fault real-time early warning method suitable for shale gas long water section
CN113393334A (en) * 2020-03-11 2021-09-14 中国石油化工股份有限公司 Drilling parameter optimization recommendation method and system
CN113393334B (en) * 2020-03-11 2024-05-14 中国石油化工股份有限公司 Drilling parameter optimization recommendation method and system
CN113775327A (en) * 2020-06-05 2021-12-10 中国石油化工股份有限公司 Method, device and equipment for detecting drilling abnormity, drilling well and storage medium
CN113775327B (en) * 2020-06-05 2024-04-09 中国石油化工股份有限公司 Method, device, equipment, well drilling and storage medium for detecting well drilling abnormality
CN116128309B (en) * 2023-04-11 2023-07-21 青岛科技大学 Petroleum engineering well site operation maintenance management system based on Internet of things
CN116128309A (en) * 2023-04-11 2023-05-16 胜利油田利丰石油设备制造有限公司 Petroleum engineering well site operation maintenance management system based on Internet of things

Similar Documents

Publication Publication Date Title
CN107292467A (en) A kind of drilling risk Forecasting Methodology
CN107292754A (en) A kind of drilling risk forecasting system
EP2912493B1 (en) System and method for well data analysis
US11286766B2 (en) System and method for optimizing tubular running operations using real-time measurements and modelling
RU2633006C1 (en) Automation of drilling with use of optimal control based on stochastic theory
CN105089620B (en) Monitoring system, the method and device of bit freezing
US20160076357A1 (en) Methods for selecting and optimizing drilling systems
US20140214326A1 (en) Well Integrity Management Using Coupled Engineering Analysis
CN104145079A (en) Determining optimal parameters for a downhole operation
CN102575516A (en) Methods to estimate downhole drilling vibration amplitude from surface measurement
CN114444823A (en) Method and system for predicting lost circulation risk in drilling operation process
US20140172303A1 (en) Methods and systems for analyzing the quality of a wellbore
Salminen et al. Stuck pipe prediction using automated real-time modeling and data analysis
RU2564423C2 (en) System and method for simulation of interaction of reamer and bit
CN115841247A (en) Digital drilling risk monitoring method and device
Liang et al. Intelligent early warning model of early-stage overflow based on dynamic clustering
CN111625916A (en) Method and system for calculating stability value of well wall
CN114169558B (en) Method and system for predicting well kick risk of well drilling
CN117420150B (en) Analysis and prediction system and prediction method based on drilling parameters
Wang et al. An online drilling rate of penetration (ROP) optimization method
RU2735794C1 (en) Method for prediction of sticking of drilling pipes
Zhang et al. Real-Time Recognition of Drill Bit Wear State Using Clustering Algorithm and GRU Neural Network
Sarwono et al. Stuck Pipe Detection For North Sumatera Geothermal Drilling Operation Using Artificial Neural Network
Yang et al. Real-Time Prediction of Bottomhole Equivalent Circulating Density (ECD) Based on Machine Learning Algorithms in Offshore Deepwater Drilling
CN118128504A (en) Method, system and equipment for early warning of sand setting stuck drill risk of underground drilling tool assembly in real time

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20171024

RJ01 Rejection of invention patent application after publication