CN107292467A - A kind of drilling risk Forecasting Methodology - Google Patents
A kind of drilling risk Forecasting Methodology Download PDFInfo
- 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
- characteristic vector
- 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.)
- Pending
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 8
- 239000012530 fluid Substances 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 241001074085 Scophthalmus aquosus Species 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
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
Technical field
The present invention relates to oil-gas exploration and development technical field, specifically, it is related to a kind of drilling risk prediction side
Method.
Background technology
Drilling risk prediction refers to the method certain according to drillng operation data application to present in drillng operation
Risk is predicted, to reach the purpose of prevention and control.Drillng operation has sufficiently complex flow, its mistake
There is the influence of many uncertain factors in journey.Therefore, it is pre- to the influence factor progress risk in drilling process
Survey just particularly significant, effectively predict the outcome to have for situ of drilling well operation and great know meaning.
Carrying out the method for drilling risk prediction at present mainly includes the method such as neural network and reasoning by cases method,
Being limited in that for these methods needs substantial amounts of offset well data.And the offset well data for new block is less,
This also allows for these methods and is difficult to play a role in drilling risk prediction.Meanwhile, even in possessing offset well case
In the case of example sample, the size of sample size also determines the drilling risk prediction accuracy of these methods.Also
It is to say, in the case of historical sample amount is less, the degree of accuracy of these existing drilling risk Forecasting Methodologies is also handed over
Bottom, it is impossible to meet the requirement of actual production.
The content of the invention
To solve the above problems, the invention provides a kind of drilling risk Forecasting Methodology, methods described includes：
Initial data obtaining step, obtains the measured data of drilling well to be analyzed, and the measured data includes multiple shadows
Ring the initial data of parameter；
Characteristic vector determines step, and the initial data is handled, obtain the feature of the measured data to
Amount；
Degree of association coefficient determines step, and square is judged according to the characteristic vector of the measured data and default drilling risk
Battle array, calculates the degree of association system of each element and each fault type of the characteristic vector of the measured data respectively
Number；
Risk profile step, the measured data and the pass of each fault type are calculated according to the degree of association coefficient
Connection degree, and judge that the drilling well to be analyzed whether there is risk according to the degree of association.
According to one embodiment of present invention, in the characteristic vector determines step,
According to the initial data, the variable quantity of each affecting parameters is calculated respectively；
According to the variable quantity of each affecting parameters, the characteristic vector of the measured data is determined.
According to one embodiment of present invention, when calculating the variable quantity of each affecting parameters, each influence is calculated first
The average value of parameter, then determines that each influence is joined according to the difference of each affecting parameters and its average value
Several variable quantities.
According to one embodiment of present invention, the variable quantity of affecting parameters includes：
Change in torque amount, total pond body product net change amount, difference in flow, hook carry variable quantity, drilling tool bore hole quiescent time,
The pressure of the drill variable quantity, mechanical specific energy values and underground circulation equal yield density.
According to one embodiment of present invention, in the characteristic vector determines step, become calculating the moment of torsion
During change amount, real-time moment of torsion is standardized as moment of torsion of the pre-set dimension drill bit under predetermined depth first, so as to obtain
Standard torque, and the change in torque amount is calculated according to the standard torque.
According to one embodiment of present invention, in the degree of association coefficient determines step：
The characteristic vector of the measured data is calculated respectively to miss with the maximum of default drilling risk criterion matrix
Difference and minimum error values；
According to the worst error value and minimum error values, each yuan in the characteristic vector of the measured data is calculated
The degree of association coefficient of element and each fault type.
According to one embodiment of present invention, in the characteristic vector that the measured data is calculated according to following expression
The degree of association coefficient of each element and each fault type：
Wherein, ξijRepresent j-th of element y in the characteristic vector of measured datajFor the association of the i-th class failure
Coefficient is spent, m represents the sum of fault type, and n represents the element number that the characteristic vector of every kind of failure is included,
δmaxAnd δminRepresent that the characteristic vector of measured data is missed with the maximum of default drilling risk criterion matrix respectively
Difference and minimum error values, ρ represent resolution ratio, xijRepresent the i-th row in default drilling risk criterion matrix
The element of jth row.
According to one embodiment of present invention, the characteristic vector of measured data is calculated according to following expression with presetting
The worst error value and minimum error values of drilling risk criterion matrix：
Wherein, δmaxAnd δminThe characteristic vector and default drilling risk criterion square of measured data are represented respectively
The worst error value and minimum error values of battle array, yjRepresent j-th of element in the characteristic vector of measured data, xij
Represent the element that the i-th row jth is arranged in default drilling risk criterion matrix.
According to one embodiment of present invention, the drilling risk for calculating each affecting parameters according to following expression is associated
Degree：
Wherein, riRepresent the degree of association of measured data and the i-th class failure, ωjRepresent the characteristic vector of measured data
In j-th of element be directed to the i-th class failure weight, ξijRepresent j-th yuan in the characteristic vector of measured data
Element is directed to the degree of association coefficient of the i-th class failure, and m represents the sum of fault type, and n represents the spy of every kind of failure
Levy the element number that vector is included.
The present invention devises a kind of new method of the drilling risk prediction associated based on improved grey model, utilizes real-time record
Well data, with reference to parameters such as drill string size, borehole size, property of drilling fluid, are calculated at a certain time interval
(its risk that can be predicted includes the risk association degree size each put along along well track：Drill bit fails, and breaks
Drilling tool, leakage, well kick, be hampered card and drilling string not well braked etc.), any position of full well section is carried out in drilling course
The prediction of drilling risk, Real time identification drilling risk and early warning, help construction technical staff control drilling risk.
Other features and advantages of the present invention will be illustrated in the following description, also, partly from specification
In become apparent, or by implement the present invention and understand.The purpose of the present invention and other advantages can pass through
Specifically noted structure is realized and obtained in specification, claims and accompanying drawing.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment
Or the accompanying drawing required in description of the prior art does simple introduction：
Fig. 1 is the flow chart of drilling risk prediction according to an embodiment of the invention；
Fig. 2 is the flow chart of determination characteristic vector according to an embodiment of the invention；
Fig. 3 is the flow chart of determination degree of association coefficient according to an embodiment of the invention.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, whereby to the present invention such as
What application technology means solves technical problem, and reaches the implementation process of technique effect and can fully understand and evidence
To implement.As long as it should be noted that do not constitute conflict, each embodiment in the present invention and each implementing
Example in each feature can be combined with each other, the technical scheme formed protection scope of the present invention it
It is interior.
Meanwhile, in the following description, many details are elaborated for illustrative purposes, to provide to this
The thorough understanding of inventive embodiments.It will be apparent, however, to one skilled in the art, that this hair
It is bright to implement without detail here or described ad hoc fashion.
In addition, the step of the flow of accompanying drawing is illustrated can such as one group computer executable instructions meter
Performed in calculation machine system, and, although logical order is shown in flow charts, but in some situations
Under, can be with the step shown or described by being performed different from order herein.
For problems of the prior art, the invention provides a kind of drilling risk based on grey correlation is pre-
Survey method, this method is based on improved Grey Relation Algorithm, and risk profile is carried out to full well section in drilling process,
The degree of association for obtaining embodying various risks with this.By the degree of association, workmen can be in wellbore construction process
In recognize all kinds of drilling risks in time and take countermeasure, so as to avoid the hair of drilling risk to greatest extent
It is raw.
Fig. 1 shows the flow chart for the drilling risk Forecasting Methodology that the present embodiment is provided.
As shown in figure 1, the drilling risk Forecasting Methodology that the present embodiment is provided is first in measured data obtaining step
The measured data for treating drilling well to be analyzed is obtained in S101.In the present embodiment, accessed by step S101
Measured data includes the initial data of multiple affecting parameters.
By the analysis to existing drilling risk Forecasting Methodology, existing drilling risk Forecasting Methodology is in risk profile mistake
The foundation of standard failure pattern used in journey is limited only to the change of logging data, and it does not consider drilling fluid
Influence to drilling tool, while also not considering the influence of bit size and well depth to moment of torsion.
In the present embodiment, multiple affecting parameters that accessed measured data is included in step S101 are excellent
Selection of land includes：Moment of torsion, total pond body product, flow, hook load, drilling tool bore hole quiescent time, the pressure of the drill, mechanical ratio with
And circulation equal yield density (Equivalent Circulating Dedsity, referred to as ECD).Wherein, obtaining
During the initial data of above-mentioned affecting parameters, obtain relevant parameter (bag is gathered in real-time logging data first
Include well depth, moment of torsion, inlet flow rate, rate of discharge, total pond body product, the pressure of the drill, hook load, standpipe pressure,
During brill and rotating speed etc.), obtained followed by data such as property of drilling fluid, BHA and the drill bits at scene
The initial data of above-mentioned affecting parameters.
In the present embodiment, predicting final for the parameters such as drilling tool and drilling well can be reflected by parameter ECD
As a result influence.Meanwhile, drilling fluid can also be reflected to the influence finally predicted the outcome by buoyant weight, be floated
It is buoyancy of the drilling fluid to drilling tool again.
And the influence of bit size and well depth to moment of torsion can then be embodied by standard torque, the present embodiment
In, real-time torque value will be standardized as to the moment of torsion of 8-1/2 " 1000 meters of well depths of drill bit.
There is the abnormal generation for being all likely to result in risk in the link of any one in drilling well, it is therefore desirable to consider brill
In various factors in well, such as drilling fluid, drilling tool, drill bit, drilling process drilling parameter (including moment of torsion,
The pressure of the drill etc.).Exception, which occurs, in a certain factor may cause the generation of risk, therefore the various influence ginsengs of comprehensive analysis
Number, when the change of a certain or multiple parameters exceedes respective doors limit value, judges according to the grey correlation theory model of foundation
Go out respective risk, drilling risk is predicted and analyzed in real time, scene is instructed.
The method that the present embodiment is provided in step s 102, is handled the initial data in measured data,
So as to obtain the characteristic vector of measured data.In the present embodiment, resulting measured data in step s 102
Characteristic vector in each element can characterize correspondence affecting parameters variable quantity size.
Specifically, as shown in Fig. 2 it is determined that during the characteristic vector of measured data, first in step
According to the initial data of each affecting parameters in S201, the variable quantity of each affecting parameters is calculated respectively, is then existed
The characteristic vector of measured data is determined in step S202 according to the variable quantity of each affecting parameters.
Wherein, during the variable quantity of a certain affecting parameters is calculated, the affecting parameters are measured first a certain
Initial data in preset duration, so as to obtain multiple sampled values of the affecting parameters in the preset duration.With
Average value processing is carried out to these sampled values afterwards, so as to obtain average value of the affecting parameters in preset duration.
Finally by the sampled value and the difference of above-mentioned average value for calculating the moment affecting parameters to be analyzed, you can be somebody's turn to do
The variable quantity of affecting parameters.
It is pointed out that the present embodiment calculates the process of the variable quantity of each affecting parameters in step s 201
It is similar, therefore the process no longer to the variable quantity of each affecting parameters is repeated herein.
It is also desirable to which, it is noted that in other embodiments of the invention, other reasonable sides can also be passed through
Formula calculates the variable quantity of each affecting parameters, and the invention is not restricted to this.For example in one embodiment of the present of invention
In, each affecting parameters can be calculated using modes such as mean filter, consecutive means flat in preset duration
Average, can also determine each shadow by calculating variance of each affecting parameters in preset duration or standard deviation
Ring the variable quantity of parameter.
In the present embodiment, in order to reduce the influence of bit size and well depth value to torque value, become in calculated torque
During change amount, real-time moment of torsion is standardized as moment of torsion of the pre-set dimension drill bit under predetermined depth first, so as to obtain
Standard torque, and according to standard torque come the average value of calculated torque and change in torque amount.Specifically, this reality
Apply the moment of torsion that moment of torsion is preferably standardized as to 8-1/2 " 1000 meters of well depths of drill bit in example.Certainly, according to actual need
Will, in other embodiments of the invention, moment of torsion can also be standardized as other reasonable bit sizes and/or
The moment of torsion of well depth, the invention is not restricted to this.
During total pond body product net change amount is calculated, total pond body is calculated first with real-time total pond body product
Product variable quantity, drill string volume change in well is calculated using drill string volume in well, and well is calculated using well depth change
Eye deepens the total pond body product reduced, then calculates the arithmetic sum of above-mentioned three.And the arithmetic sum of above-mentioned three is
For the net change amount due to total pond body product caused by artificial increase and decrease mud, well kick, leakage.In the present embodiment,
It is used for judging well kick, leakage accident using total pond body product net change amount.
Involved flow difference is the difference of rate of discharge and inlet flow rate in the present embodiment, wherein, difference in flow
Value can be used in characterizing well kick or leakage accident.Hook, which carries variable quantity and can be used in sign, to be hampered card accident, its
It can be obtained using hook load, the pressure of the drill, the mathematic interpolation of buoyant weight.Drilling tool bore hole quiescent time can be used in
Lock of tool drilling is characterized, it can be determined by measuring drilling tool in Luo Yanchong quiescent time.The pressure of the drill variable quantity
It can be used for characterizing in drilling string not well braked accident, the present embodiment, pass through the pressure of the drill variable quantity and hook position and bit diameter
Difference is used as the Main Basiss for judging whether to occur drilling string not well braked accident.
Mechanical specific energy values are represented in the mechanical energy needed for unit interval fragmentation volume rock, the present embodiment, mechanical ratio
Energy value can be calculated according to following expression and obtained：
Wherein, MSE represents mechanical specific energy values, and WOB represents the pressure of the drill, and Dia represents shaft bottom diameter, RPM table
Show rotary rpm, TOB represents torque-on-bit, and ROP represents rate of penetration.
In the present embodiment, during circulation equal yield density ECD is calculated, first according to casing programme, well
Eye track, drilling tool structure, mud property, drilling technical parameter for gathering in real time etc. calculate drill string internal pressure in real time
The downhole hydraulic parameter such as consumption, bit pressuredrop, annular pressure lost, then integrates ground and measures in real time on this basis
Relevant parameter, COMPREHENSIVE CALCULATING determines underground ECD values.Certainly, in other embodiments of the invention, also
Underground ECD values can be determined by other rational methods, the invention is not restricted to this.
In step S202, according to the variable quantity of each affecting parameters can determine the feature of measured data to
Amount.In the present embodiment, for each affecting parameters, it would be of interest to the phase of its numerical value in actual applications
To in situation of change, therefore the present embodiment by set respectively a threshold value corresponding with each affecting parameters come
The situation of change of horizontal each affecting parameters of amount.When the variable quantity of affecting parameters exceedes threshold value, then just think
The affecting parameters are changed.In the present embodiment, it is preferred to use 1 come represent affecting parameters increase, utilize
- 1 come represent affecting parameters reduce, represented using 0 affecting parameters keep it is constant.It so also can be obtained by certain
The characteristic vector of measured data accessed by one moment.
Again as shown in figure 1, after the characteristic vector of measured data is obtained, in step s 103 according to actual measurement
The characteristic vector of data and default drilling risk judgment matrix, calculate the characteristic vector and each failure of measured data
The degree of association coefficient of type.
In the present embodiment, measured data is calculated preferably by gray relative analysis method in step s 103
Characteristic vector and the degree of association coefficient of each fault type.Grey correlation analysis is to carry out failure using gray model
Know method for distinguishing.When system occurs abnormal, detected data will show some exceptions, and every kind of former
Barrier has its corresponding characteristic phenomenon.And the essence of grey correlation analysis be determine measured data feature to
Amount and the similarity degree of standard failure characteristic sequence eigenvectors matrix (presetting drilling risk judgment matrix).
Wherein, curve is closer to the degree of association between corresponding data sequence is also bigger.
In the present embodiment, it is assumed that the fault type being likely to occur during wellbore construction is total up to m, every kind of event
The element number that the characteristic vector of barrier type is included is n.By foregoing description, n in the present embodiment
Value is 8.
In the present embodiment, standard failure characteristic sequence eigenvectors matrix (presets drilling risk judgment matrix)
XRIt can be expressed as：
Wherein, XiRepresent the characteristic vector of the i-th class failure.It is pointed out that for standard failure feature sequence
Row eigenvectors matrix XRFor, each element in its each row has identical physical significance, but it takes
Being worth size may be different.
In the present embodiment, the characteristic vector Y for the measured data determined in step s 102TIt can be expressed as：
YT=[y1,y2,...,yn] (3)
Wherein, yjJ-th of element in the characteristic vector of measured data.
Fig. 3, which is shown, calculates the characteristic vector of measured data and the degree of association of each fault type in the present embodiment
The flow chart of coefficient.
As shown in figure 3, the present embodiment calculates the characteristic vector of measured data with presetting respectively in step S301
The worst error value and minimum error values of drilling risk criterion matrix, then in step s 302 based on upper
Worst error value and minimum error values are stated, the characteristic vector of measured data respectively and the pass of each fault type is calculated
Connection degree coefficient.
Specifically, the method that the present embodiment is provided calculates actual measurement in step S301 according to following expression
The characteristic vector of data and the worst error value δ of default drilling risk criterion matrixmaxAnd minimum error values
δmin：
Wherein, xijRepresent the element that the i-th row jth is arranged in default drilling risk criterion matrix.
And the present embodiment is according to the characteristic vector of following expression calculating measured data and each in step 302
The degree of association coefficient of fault type：
Wherein, ξijRepresent j-th of element y in the characteristic vector of measured datajFor the association of the i-th class failure
Coefficient is spent, m represents the sum of fault type, and n represents the element number that the characteristic vector of every kind of failure is included,
ρ represents resolution ratio.
Again as shown in figure 1, when each element in the characteristic vector for obtaining measured data and each fault type
After degree of association coefficient, the method that the present embodiment is provided is in step S104 according to above-mentioned degree of association coefficient come really
Determine the degree of association of measured data and each fault type, and judge that drilling well to be analyzed whether there is according to the degree of association
Risk.
Because different affecting parameters are different for the influence degree of wellbore construction process, therefore in order to characterize difference
The significance level of affecting parameters, the method that the present embodiment is provided is calculating actual measurement according to each degree of association coefficient
When data and the degree of association of each fault type, different weights also are imparted to each degree of association coefficient.Specifically
In ground, the present embodiment, measured data and the degree of association of each fault type are carried out preferably by following expression
Calculate：
Wherein, riRepresent the degree of association of measured data and the i-th class failure, ωjRepresent the characteristic vector of measured data
In j-th of element be directed to the i-th class failure weight.
It is pointed out that for the characteristic vector of measured data, it meets：
In the present embodiment, each fault type respectively correspond to is preset with a degree of association threshold value, if measured data with
The degree of association of a certain fault type is more than its respective associated degree threshold value, then then represent that now drilling well to be analyzed occurs
Failure can also determine the fault type of the failure simultaneously.
In order to verify the practicality for the drilling risk Forecasting Methodology that the present embodiment is provided, the present embodiment utilizes the party
Method is analyzed the area X drilling wells of first dam.The drilling data of the regional drilling well in first dam is obtained first, and to data
Analyzed, so as to obtain useful data.Then accessed Data Data is carried out manually to count, divided
Analysis, arrangement.The parameter of complex situations well is occurred according to first dam area, anomaly parameter changing rule, parameter is summarized
Threshold value of change etc..
X drilling well wells get into 5496 meters, by inquiring that Field Force is determined without artificial reduction mud, do not have
Ground is lost, and is reduced using the pond body product amount of having a net increase of is calculated, by logging data variation phenomenon, difference in flow increases
Greatly, the calculating finally by theoretical model draws the degree of association 0.89 of leakage beyond the leakage degree of association with matching
Thresholding, therefore can be determined that as leakage.Find that leakage occurs for scene by this method, and the processing of progress in time is kept away
The further generation of risk is exempted from.
From foregoing description as can be seen that the present invention devise it is a kind of based on improved grey model associate drilling risk it is pre-
The new method of survey, using real-time logging data, with reference to parameters such as drill string size, borehole size, property of drilling fluid,
Risk association degree size (its wind that can be predicted each put along along well track is calculated at a certain time interval
Danger includes：Drill bit fails, drillling tool twisting off, leakage, well kick, is hampered and blocks and drilling string not well braked etc.), in drilling course
Position any to full well section carries out the prediction of drilling risk, Real time identification drilling risk and early warning, helps skill of constructing
Art personnel control drilling risk.
It should be understood that disclosed embodiment of this invention is not limited to specific structure disclosed herein or processing
Step, and the equivalent substitute for these features that those of ordinary skill in the related art are understood should be extended to.Also
It should be appreciated that term as used herein is only used for describing the purpose of specific embodiment, and it is not meant to limit
System.
Special characteristic that " one embodiment " or " embodiment " mentioned in specification means to describe in conjunction with the embodiments,
During structure or characteristic are included at least one embodiment of the present invention.Therefore, specification various places throughout occurs
Phrase " one embodiment " or " embodiment " same embodiment might not be referred both to.
Although above-mentioned example is used to illustrate principle of the present invention in one or more applications, for this area
For technical staff, without departing substantially from the present invention principle and thought in the case of, hence it is evident that can in form, use
Various modifications may be made in method and the details of implementation and without paying creative work.Therefore, the present invention is by appended power
Sharp claim is limited.
Claims (9)
1. a kind of drilling risk Forecasting Methodology, it is characterised in that methods described includes：
Initial data obtaining step, obtains the measured data of drilling well to be analyzed, and the measured data includes multiple shadows
Ring the initial data of parameter；
Characteristic vector determines step, and the measured data is handled, obtain the feature of the measured data to
Amount；
Degree of association coefficient determines step, and square is judged according to the characteristic vector of the measured data and default drilling risk
Battle array, calculates the degree of association system of each element and each fault type of the characteristic vector of the measured data respectively
Number；
Risk profile step, the measured data and the pass of each fault type are calculated according to the degree of association coefficient
Connection degree, and judge that the drilling well to be analyzed whether there is risk according to the degree of association.
2. the method as described in claim 1, it is characterised in that in the characteristic vector determines step,
According to the measured data, the variable quantity of each affecting parameters is calculated respectively；
According to the variable quantity of each affecting parameters, the characteristic vector of the measured data is determined.
3. method as claimed in claim 2, it is characterised in that when calculating the variable quantity of each affecting parameters,
The average value of each affecting parameters is calculated first, then according to the difference of each affecting parameters and its average value come really
The variable quantity of fixed each affecting parameters.
4. method as claimed in claim 2 or claim 3, it is characterised in that the variable quantity of affecting parameters includes：
Change in torque amount, total pond body product net change amount, difference in flow, hook carry variable quantity, drilling tool bore hole quiescent time,
The pressure of the drill variable quantity, mechanical specific energy values and underground circulation equal yield density.
5. method as claimed in claim 4, it is characterised in that in the characteristic vector determines step,
When calculating the change in torque amount, real-time moment of torsion is standardized as pre-set dimension drill bit under predetermined depth first
Moment of torsion, so as to obtain standard torque, and the change in torque amount is calculated according to the standard torque.
6. such as method according to any one of claims 1 to 5, it is characterised in that in the degree of association coefficient
Determine in step：
The characteristic vector of the measured data is calculated respectively to miss with the maximum of default drilling risk criterion matrix
Difference and minimum error values；
According to the worst error value and minimum error values, each yuan in the characteristic vector of the measured data is calculated
The degree of association coefficient of element and each fault type.
7. method as claimed in claim 6, it is characterised in that the actual measurement is calculated according to following expression
The degree of association coefficient of each element and each fault type in the characteristic vector of data：
<mrow>
<msub>
<mi>&xi;</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>&delta;</mi>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>&rho;&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>&rho;&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, ξijRepresent j-th of element y in the characteristic vector of measured datajFor the association of the i-th class failure
Coefficient is spent, m represents the sum of fault type, and n represents the element number that the characteristic vector of every kind of failure is included,
δmaxAnd δminRepresent that the characteristic vector of measured data is missed with the maximum of default drilling risk criterion matrix respectively
Difference and minimum error values, ρ represent resolution ratio, xijRepresent the i-th row in default drilling risk criterion matrix
The element of jth row.
8. method as claimed in claims 6 or 7, it is characterised in that calculated and surveyed according to following expression
The characteristic vector of data and the worst error value and minimum error values of default drilling risk criterion matrix：
<mrow>
<msub>
<mi>&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>&le;</mo>
<mi>i</mi>
<mo>&le;</mo>
<mi>m</mi>
</mrow>
</munder>
<mo>&lsqb;</mo>
<munder>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
<mrow>
<mn>1</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo>&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>&rsqb;</mo>
</mrow>
<mrow>
<msub>
<mi>&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>&le;</mo>
<mi>i</mi>
<mo>&le;</mo>
<mi>m</mi>
</mrow>
</munder>
<mo>&lsqb;</mo>
<munder>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
<mrow>
<mn>1</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo>&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>&rsqb;</mo>
</mrow>
Wherein, δmaxAnd δminThe characteristic vector and default drilling risk criterion square of measured data are represented respectively
The worst error value and minimum error values of battle array, yjRepresent j-th of element in the characteristic vector of measured data, xij
Represent the element that the i-th row jth is arranged in default drilling risk criterion matrix.
9. such as method according to any one of claims 1 to 8, it is characterised in that according to following expression meter
Calculate the drilling risk degree of association of each affecting parameters：
<mrow>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>&omega;</mi>
<mi>j</mi>
</msub>
<msub>
<mi>&xi;</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>,</mo>
<mn>0</mn>
<mo>&le;</mo>
<msub>
<mi>&omega;</mi>
<mi>j</mi>
</msub>
<mo>&le;</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>&le;</mo>
<mi>i</mi>
<mo>&le;</mo>
<mi>m</mi>
</mrow>
Wherein, riRepresent the degree of association of measured data and the i-th class failure, ωjRepresent the characteristic vector of measured data
In j-th of element be directed to the i-th class failure weight, ξijRepresent j-th yuan in the characteristic vector of measured data
Element is directed to the degree of association coefficient of the i-th class failure, and m represents the sum of fault type, and n represents the spy of every kind of failure
Levy the element number that vector is included.
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)
| 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)
| 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 |
-
2016
- 2016-03-31 CN CN201610197209.0A patent/CN107292467A/en active Pending
Patent Citations (5)
| 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)
| 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 | |
| US9557438B2 (en) | System and method for well data analysis | |
| US9970266B2 (en) | Methods and systems for improved drilling operations using real-time and historical drilling data | |
| CN104806226B (en) | intelligent drilling expert system | |
| Diaz et al. | Drilling data from an enhanced geothermal project and its pre-processing for ROP forecasting improvement | |
| CA2705194C (en) | A method of training neural network models and using same for drilling wellbores | |
| CA3064241C (en) | Methods and systems for improved drilling operations using real-time and historical drilling data | |
| 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 | |
| CN104695937A (en) | Well drilling comprehensive speed accelerating optimization expert system | |
| CN102979500A (en) | A method of controlling a direction of drilling of the drill string used to form an opening in a subsurface formation | |
| US11091989B1 (en) | Real-time parameter adjustment in wellbore drilling operations | |
| CN110671095B (en) | Intelligent while-drilling soft measurement method for formation pressure | |
| US10781683B2 (en) | Optimizing sensor selection and operation for well monitoring and control | |
| Krishna et al. | Conventional and intelligent models for detection and prediction of fluid loss events during drilling operations: A comprehensive review | |
| Naraghi et al. | Prediction of drilling pipe sticking by active learning method (ALM) | |
| CN115586086A (en) | Borehole wall instability analysis method based on big data | |
| Singh et al. | A comprehensive review of fracture-driven interaction in unconventional oil and gas plays: Characterization, real-time diagnosis, and impact on production | |
| CN111625916A (en) | Method and system for calculating stability value of well wall | |
| CN112241835A (en) | Deep shaft project water inrush disaster multi-source information evaluation method | |
| CN117420150B (en) | Analysis and prediction system and prediction method based on drilling parameters | |
| Sarwono et al. | Stuck Pipe Detection For North Sumatera Geothermal Drilling Operation Using Artificial Neural Network | |
| Wang et al. | An online drilling rate of penetration (ROP) optimization method | |
| Wang et al. | An Artificial Intelligence Algorithm for the Real-Time Early Detection of Sticking Phenomena in Horizontal Shale Gas Wells. |
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 |