CN113323647A - Method and device for monitoring compressive strength and drillability of rock - Google Patents
Method and device for monitoring compressive strength and drillability of rock Download PDFInfo
- Publication number
- CN113323647A CN113323647A CN202010088788.1A CN202010088788A CN113323647A CN 113323647 A CN113323647 A CN 113323647A CN 202010088788 A CN202010088788 A CN 202010088788A CN 113323647 A CN113323647 A CN 113323647A
- Authority
- CN
- China
- Prior art keywords
- data
- rock
- well
- drillability
- compressive strength
- 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.)
- Granted
Links
- 239000011435 rock Substances 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000005553 drilling Methods 0.000 claims abstract description 97
- 238000004364 calculation method Methods 0.000 claims abstract description 38
- 238000007637 random forest analysis Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000000547 structure data Methods 0.000 claims abstract description 7
- 239000012530 fluid Substances 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000002790 cross-validation Methods 0.000 claims description 9
- 230000035515 penetration Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
- E21B44/02—Automatic control of the tool feed
- E21B44/04—Automatic control of the tool feed in response to the torque of the drive ; Measuring drilling torque
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B45/00—Measuring the drilling time or rate of penetration
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/06—Measuring temperature or pressure
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The present invention provides a method for monitoring compressive rock strength and drillability, comprising: collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, well track measurement data and drill bit information of an adjacent well to be drilled; calculating to obtain the bottom hole drilling pressure corresponding to each depth point of each adjacent well near the well to be drilled; constructing a feature set, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth; determining hyper-parameters of a random forest regressor, and training and establishing a rock compressive strength prediction model and a rock drillability prediction model; and acquiring real-time logging data of the to-be-drilled well, inputting the built rock compressive strength prediction model and the rock drillability prediction model, and realizing real-time calculation of the compressive strength and the drillability of the to-be-drilled well. The invention comprehensively considers the mapping relation between various factors and the compressive strength and the drillability of the rock and has higher calculation precision.
Description
Technical Field
The invention relates to the technical field of petroleum and natural gas exploration and development, in particular to a method and a device for monitoring compressive strength and drillability of rock.
Background
The real-time monitoring of the geological information at the drill bit in the petroleum drilling process has important significance for the optimization of drilling construction parameters, the formulation of drilling measures and the optimization of drilling tools. At present, the evaluation of the rock strength and the drillability of the stratum mainly depends on the real-time interpretation of acoustic logging data while drilling, but due to the high price of a measuring instrument or the high service cost, a non-key well or a non-reservoir stratum is generally not provided with a logging tool while drilling, and the real-time data of the rock strength and the drillability cannot be obtained.
The traditional logging parameter-based downhole rock strength characterization is mainly based on an analytical formula, and has few consideration factors, such as bit pressure, rotation speed and bit size, and neglects the influence of friction resistance on the downhole bit pressure in the drilling process, so that the calculation precision is low, and the method is particularly not suitable for monitoring the rock strength and the drillability of deep wells, directional wells and horizontal well sections.
The present invention therefore provides a method and apparatus for monitoring the compressive strength and drillability of rock.
Disclosure of Invention
To solve the above problems, the present invention provides a method for monitoring compressive rock strength and drillability, the method comprising the steps of:
the method comprises the following steps: collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, well track measurement data and drill bit information of an adjacent well to be drilled;
step two: according to hook load data and drilling fluid density data in the logging information, combining the borehole trajectory measurement data and the drilling tool assembly data, and calculating to obtain bottom hole drilling pressure corresponding to each depth point of each adjacent well near the well to be drilled;
step three: constructing a feature set for calculating the compressive strength and the drillability of the rock in real time in the drilling process, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth;
step four: establishing a random forest algorithm regressor, determining hyperparameters of the random forest regressor by taking the characteristics in the characteristic set as input parameters and the rock compressive strength data and the rock drillability data of corresponding depths as output parameters, and training and establishing a rock compressive strength prediction model and a rock drillability prediction model;
step five: the method comprises the steps of collecting real-time logging data to be drilled, calculating to obtain corresponding bottom hole drilling pressure, inputting the calculated bottom hole drilling pressure and other characteristics in the real-time logging data into the built rock compressive strength prediction model and the rock drillability prediction model, and achieving real-time calculation of the rock compressive strength and the drillability of the to-be-drilled well.
According to an embodiment of the invention, in the second step, the bottom hole weight corresponding to each depth point of each adjacent well near the well to be drilled is determined through a three-dimensional borehole axial force flexible rod calculation model.
According to one embodiment of the invention, the deviated interval axial force is calculated by the following formula:
wherein, F2Axial force, KN, at the upper end of the well section unit; f1Axial force, KN, at the lower end of the well section unit; beta is a buoyancy coefficient; w is the weight of the drill unit wire, kg/m; Δ L is the calculation unit length, m; α is the well angle, rad; mu is a friction coefficient;
is the angle between the axial direction and the tangential direction of motion of the drilling tool, rad.
According to one embodiment of the invention, the curved-section axial force is calculated by the following formula:
wherein, theta2Is the azimuth angle, rad, of the upper end of the well section unit; theta1Is the azimuth angle, rad, of the lower end of the well section unit; alpha is alpha2Is the well head angle, rad, of the upper end of the well section unit; alpha is alpha1Is the well section unit lower end well bevel angle, rad.
According to an embodiment of the present invention, in the third step, the features in the feature set are aligned to the same depth axis by means of linear interpolation.
According to one embodiment of the invention, the features in the feature set include: depth, bottom hole weight, rotational speed, drilling fluid density, bit diameter, bit type, rate of penetration, and rotary table torque.
According to an embodiment of the invention, in the fourth step, the hyper-parameters of the random forest regressor are determined by a k-fold cross validation and grid search method.
According to an embodiment of the invention, in the fifth step, working condition recognition is carried out on the real-time logging data, and real-time data which do not belong to the working condition of the drilling process are removed.
According to another aspect of the present invention there is also provided an apparatus for monitoring compressive rock strength and drillability, the apparatus comprising:
the system comprises a collecting module, a data processing module and a data processing module, wherein the collecting module is used for collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, well track measurement data and drill bit information of adjacent wells to be drilled;
the calculation module is used for calculating and obtaining the bottom hole drilling pressure corresponding to each depth point of each adjacent well near the well to be drilled according to hook load data and drilling fluid density data in the logging information and by combining the borehole trajectory measurement data and the drilling tool assembly data;
the construction module is used for constructing a feature set for calculating the compressive strength and the drillability of the rock in real time in the drilling process, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth;
the training module is used for establishing a random forest algorithm regressor, determining the hyperparameter of the random forest regressor by taking the characteristics in the characteristic set as input parameters and the rock compressive strength data and the rock drillability data with corresponding depths as output parameters, and training and establishing a rock compressive strength prediction model and a rock drillability prediction model;
and the real-time calculation module is used for acquiring real-time logging data to be drilled, calculating to obtain the corresponding bottom hole drilling pressure, and inputting the calculated bottom hole drilling pressure and other characteristics in the real-time logging data into the built rock compressive strength prediction model and the rock drillability prediction model to realize the real-time calculation of the rock compressive strength and the drillability to be drilled.
According to one embodiment of the invention, the calculation module comprises a three-dimensional borehole axial force flexible rod calculation model used for determining the bottom hole weight corresponding to each depth point of each adjacent well near the well to be drilled.
The method and the device for monitoring the compressive strength and the drillability of the rock, provided by the invention, comprehensively consider the mapping relations of various factors and the compressive strength and the drillability of the rock, and respectively establish the real-time stratum parameter calculation models based on the random forest algorithm.
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
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 shows a flow chart of a method for monitoring compressive rock strength and drillability according to an embodiment of the invention;
FIG. 2 is a graph showing the bottom hole weight-on-bit calculation during drilling of a well;
FIG. 3 shows a sample set comprising depth, downhole weight-on-bit, rotational speed, drilling fluid density, bit diameter, bit model, rate-of-penetration, rotary table torque, uniaxial compressive strength, and;
FIG. 4 shows a schematic diagram of a rock compressive strength prediction model according to an embodiment of the invention;
FIG. 5 shows a schematic diagram of a rock drillability prediction model according to an embodiment of the invention;
FIG. 6 shows a schematic representation of real-time logging parameter condition identification;
FIG. 7 shows a comparison of the results of compressive strength calculations by well logging interpretation methods, methods provided by the present invention, and methods of analyzing the rate of penetration equation;
FIG. 8 shows a comparison of results from calculating rock drillability by a well logging interpretation method and the method provided by the present invention; and
fig. 9 shows a block diagram of an apparatus for monitoring compressive rock strength and drillability according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below with reference to the accompanying drawings.
Fig. 1 shows a flow chart of a method for monitoring compressive rock strength and drillability according to an embodiment of the invention.
Referring to fig. 1, in step S101, well structure data, drill tool assembly data, rock compressive strength data, rock drillability data, logging data, borehole trajectory measurement data, and drill bit information of an adjacent well to be drilled are collected.
Generally, well bore configuration data includes casing size and casing depth; logging data comprises rotation speed, hook load, torque and drilling fluid density; the borehole trajectory measurement data comprises a well inclination angle and an azimuth angle; the drill information includes a model number and a size.
As shown in fig. 1, in step S102, according to the hook load data and the drilling fluid density data in the logging data, the borehole trajectory measurement data and the drilling tool assembly data are combined to calculate and obtain the bottom hole weight corresponding to each depth point of each adjacent well near the to-be-drilled well.
In general, the bottom hole weight (axial force) corresponding to each depth point of each adjacent well near the well to be drilled is determined through a three-dimensional borehole axial force flexible rod calculation model.
Particularly, the three-dimensional borehole axial force flexible rod calculation model is mainly used for calculating the stress condition of the drilling tool in the borehole along the axial direction of the pipe column under the condition of inputting boundary conditions. By inputting ground hooking data, the model can calculate the axial force corresponding to each depth point in an accumulated mode from top to bottom, and finally calculate the bottom hole weight. The three-dimensional borehole axial force soft rod model considers the drilling tool shape and the stress characteristics under the three-dimensional borehole structure, the soft rod concept assumes that the curvature of the drilling tool in the borehole is consistent with that of the borehole, the complexity of calculation from top to bottom point by point can be effectively reduced, and the method is a simple, convenient and effective method for calculating the bottom hole bit pressure.
In one embodiment, the slant well section axial force is calculated by the following formula:
wherein, F2Axial force, KN, at the upper end of the well section unit; f1Is well section unit downEnd axial force, KN; beta is a buoyancy coefficient; w is the weight of the drill unit wire, kg/m; Δ L is the calculation unit length, m; α is the well angle, rad; mu is a friction coefficient;
is the angle between the axial direction and the tangential direction of motion of the drilling tool, rad.
In one embodiment, the curved-interval axial force is calculated by the following equation:
wherein, theta2Is the azimuth angle, rad, of the upper end of the well section unit; theta1Is the azimuth angle, rad, of the lower end of the well section unit; alpha is alpha2Is the well head angle, rad, of the upper end of the well section unit; alpha is alpha1Is the well section unit lower end well bevel angle, rad.
It should be noted that the axial force refers to the force of the drilling tool in the axial direction of the pipe string in the borehole, the bottom hole weight is the force of the end of the drilling tool, and the bottom hole weight is one of the axial forces. By calculating the axial force point by point, the bottom hole weight on bit can be finally calculated.
As shown in fig. 1, in step S103, a feature set for calculating compressive rock strength and drillability in real time during drilling is constructed, features in the feature set are aligned to the same depth axis, and a data set is randomly shuffled according to depth.
Generally, the features in the feature set are aligned to the same depth axis by means of linear interpolation.
Specifically, the features in the feature set include: depth H, bottom hole weight on bit DWOB, rotation speed RPM, drilling fluid density MW, bit diameter Db, bit model Tb, rate of penetration ROP, and rotary table torque T.
In addition, the purpose of randomly scrambling the data set by depth is: the original data are generally arranged according to the increasing sequence of the depth, and the sequence must be disturbed before the machine learning training, so that the model training effect can be effectively improved, and the model parameters are prevented from falling into the local optimum.
Specifically, the step of randomly scrambling the data set by depth includes:
taking a data sample as an example, the shape is [ h, v ], wherein h is a depth sequence and v is a characteristic parameter sequence; creating an array for storing the samples after the disordering sequence, wherein the shape of the array is [ h1, v1 ]; knowing the number of samples as n, generating a random number between 1 and n, copying the samples at the corresponding positions of the random number from [ h, v ] to [ h1, v1], checking whether the samples are added before copying, and continuing to generate the next random number if the samples are added until all the samples in [ h, v ] are copied to [ h1, v1 ].
As shown in fig. 1, in step S104, a random forest algorithm regressor is established, the features in the feature set are used as input parameters, the rock compressive strength data and the rock drillability data of the corresponding depth are used as output parameters, the hyper-parameters of the random forest regressor are determined, and a rock compressive strength prediction model and a rock drillability prediction model are trained and established.
Generally, the input parameters include depth, downhole weight on bit, rotational speed, drilling fluid density, bit diameter, bit model, rate of penetration, and rotary table torque; the output parameters include rock compressive strength and rock drillability.
In general, the hyper-parameters of the random forest regressor are determined by k-fold cross validation and grid search methods.
Specifically, the hyper-parameters of the random forest, such as the number of trees and the depth of trees, have a large influence on the performance of the regressor. Traversing all possible combinations of the hyper-parameters by a grid search method, and determining the optimal hyper-parameters by precision comparison for training the final regressor.
And the grid search is used for arranging and combining the possible values of the hyper-parameters, listing all possible combination results to form a grid, then using the combination of each node of the grid for training a random forest regression, determining the regression precision by using a cross validation method, and finally selecting the optimal regression.
The K-fold cross validation is to divide an initial sample set into K sub sample sets, take 1 sub sample set as a validation set, take the rest K-1 sub sample sets as a training set, train a model and determine the precision of one-time training through the validation set, sequentially take the K sub sample sets as the validation set, take the rest as the training set, and synthesize K training results as model evaluation indexes of the cross validation. The K-fold cross validation can effectively improve the stability of the model performance evaluation.
Specifically, the random forest method is a machine learning method, has strong mapping capability of a high-dimensionality nonlinear problem, is less in hyper-parameters and not easy to over-fit, and is suitable for pattern recognition problems under different data volumes. The invention adopts a random forest method, considers various influence factors, respectively establishes the prediction models of the compressive strength and the drillability of the rock, and can effectively improve the calculation precision and the adaptability to complex borehole conditions.
As shown in fig. 1, in step S105, real-time logging data of a to-be-drilled well is collected, a corresponding bottom hole bit pressure is calculated, and the calculated bottom hole bit pressure and other characteristics in the real-time logging data are input into the established rock compressive strength data prediction model and the rock drillability prediction model, so as to realize real-time calculation of the rock compressive strength data and the drillability of the to-be-drilled well.
In general, other features include: depth, rotational speed, drilling fluid density, bit diameter, bit type, rate of penetration, and rotary table torque.
Specifically, step S105 further includes: and identifying the working condition of the real-time logging data, and eliminating the real-time data which do not belong to the working condition of the drilling process.
The method is suitable for monitoring the compressive strength and the drillability of the rock in real time in the drilling process of different well conditions (a vertical well, a directional well and a horizontal well), and can guide the optimization of construction parameters while drilling and the optimization of drilling tools.
In one embodiment, zone M is used as a test zone, and wellbore configuration data (casing size, casing depth), tool assembly data, rock compressive strength data, rock drillability data, logging data (rotational speed, hook load, torque, drilling fluid density), borehole trajectory measurement data (angle of inclination, azimuth), and bit information (bit model, bit size) are collected for the drilled wells in zone M.
And then, determining the bottom hole drilling pressure (axial force) corresponding to each depth point of each well by utilizing a three-dimensional borehole axial force soft rod calculation model according to hook load and drilling fluid density data in logging information and combining empirical track measurement data and drilling tool combination data, as shown in figure 2.
Then, as shown in fig. 3, on the basis of the previous two steps, a feature set is constructed, all features in the feature set are aligned to the same depth axis in a linear interpolation manner, and the features in the feature set include: depth H, bottom hole weight on bit DWOB, rotation speed RPM, drilling fluid density MW, bit diameter Db, bit model Tb, rate of penetration ROP, and rotary table torque T. And carrying out One-Hot coding processing on the drill bit type number Tb. The data set is shuffled randomly by depth.
The sample set shown in fig. 3 contains, in addition to depth H, bottom hole weight on bit DWOB, rotational speed RPM, drilling fluid density MW, bit diameter Db, bit model Tb, rate of penetration ROP, and rotary table torque T, uniaxial compressive strength UCS, and rock drillability (rock drillability level value Kd, range [ 0-10 ], dimensionless units), where the uniaxial compressive strength UCS is used to characterize the rock compressive strength.
Then, a random forest algorithm regressor is established, the depth, the bottom hole drilling pressure, the rotating speed, the drilling fluid density, the drill bit diameter, the drill bit model, the mechanical drilling speed and the rotary table torque are used as input parameters (characteristics), the rock compressive strength of the corresponding depth is used as an output parameter (label), the hyperparameters of the random forest regressor are determined by using a k-fold cross validation and grid search method, and finally a rock compressive strength prediction model based on logging data is trained and established (as shown in figure 4).
Establishing a random forest algorithm regressor, taking the depth, the bottom hole drilling pressure, the rotating speed, the drilling fluid density, the drill bit diameter, the drill bit model, the mechanical drilling speed and the turntable torque as input parameters (characteristics), taking the rock drillability of the corresponding depth as output parameters (labels), determining the hyperparameters of the random forest regressor by using a k-fold cross validation and grid search method, and finally training and establishing a rock drillability prediction model (as shown in figure 5) based on logging data.
Finally, accessing real-time logging data, identifying the working conditions of the real-time logging data, eliminating real-time data (such as figure 6) which do not belong to the working conditions of the drilling process, calculating the drilling pressure at the bottom of the well by using the collected real-time logging data in combination with the well structure, the drilling tool assembly, the well track and the drilling fluid density data, and accessing the drilling pressure at the bottom of the well and other characteristic parameters (depth, rotating speed, drilling fluid density, drill diameter, drill model, mechanical drilling speed and rotary table torque) to the built compressive strength and drillability prediction model to realize the real-time calculation of the compressive strength and drillability of the rock.
As shown in fig. 7 and 8, wherein, the first column in fig. 7 shows the rock compressive strength results calculated by the well logging interpretation method; the second column represents the rock compressive strength results calculated by the method for monitoring rock compressive strength and drillability provided by the invention; the third column shows the rock compressive strength results calculated by the analytical rate of penetration equation method (motahari). In FIG. 8, the first column represents the rock drillability results calculated by the well logging interpretation method; the second column represents rock drillability results calculated by the method for monitoring rock compressive strength and drillability provided by the present invention.
The method can guide the optimization of the rock breaking tool and the optimization of engineering parameters in the drilling process in real time, and comprises 5 steps of data collection and preprocessing, well bottom drilling pressure calculation, sample set construction, building of a rock compressive strength and rock drillability prediction model by using a random forest algorithm, and real-time calculation of the rock compressive strength and the rock drillability. The method has the advantages that the mapping relations among the well depth, the well bottom drilling pressure, the rotating speed, the mechanical drilling speed, the torque and the drill bit characteristics and the well bottom rock compressive strength and the drillability are respectively established, particularly, the influence of friction resistance in the drilling process on the well bottom drilling pressure is considered, the accuracy of rock compressive strength and drillability prediction in the deep well and the directional drilling process is greatly improved, and scientific basis can be provided for optimization of drilling parameters and optimization of a drilling speed-up tool.
Fig. 9 shows a block diagram of an apparatus for monitoring compressive rock strength and drillability according to an embodiment of the present invention. As shown in fig. 9, the monitoring apparatus 900 includes: a collection module 901, a calculation module 902, a construction module 903, a training module 904, and a real-time calculation module 905.
The collecting module 901 is used for collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, borehole trajectory measurement data and drill bit information of an adjacent well to be drilled.
The calculation module 902 is configured to calculate, according to hook load data and drilling fluid density data in the logging data, a bottom hole drilling pressure corresponding to each depth point of each adjacent well near the to-be-drilled well in combination with wellbore trajectory measurement data and drilling tool assembly data.
The construction module 903 is used for constructing a feature set for calculating the compressive strength and the drillability of the rock in real time in the drilling process, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth.
The training module 904 is configured to establish a random forest algorithm regressor, determine hyper-parameters of the random forest regressor by using the features in the feature set as input parameters and using the rock compressive strength data and the rock drillability data of corresponding depths as output parameters, and train and establish a rock compressive strength prediction model and a rock drillability prediction model.
The real-time calculation module 905 is used for acquiring real-time logging data of a to-be-drilled well, calculating to obtain a corresponding bottom hole drilling pressure, and inputting the calculated bottom hole drilling pressure and other characteristics in the real-time logging data into the established rock compressive strength prediction model and the rock drillability prediction model to realize real-time calculation of the rock compressive strength and the drillability of the to-be-drilled well.
In conclusion, the method and the device for monitoring the compressive strength and the drillability of the rock, provided by the invention, comprehensively consider the mapping relation between various factors and the compressive strength and the drillability of the rock, and respectively establish the real-time stratum parameter calculation model based on the random forest algorithm.
It is to be understood that the disclosed embodiments of the invention are not limited to the particular structures, process steps, or materials disclosed herein but are extended to equivalents thereof as would be understood by those ordinarily skilled in the relevant arts. 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.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for monitoring the compressive strength and drillability of rock, characterized in that the method comprises the steps of:
the method comprises the following steps: collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, well track measurement data and drill bit information of an adjacent well to be drilled;
step two: according to hook load data and drilling fluid density data in the logging information, combining the borehole trajectory measurement data and the drilling tool assembly data, and calculating to obtain bottom hole drilling pressure corresponding to each depth point of each adjacent well near the well to be drilled;
step three: constructing a feature set for calculating the compressive strength and the drillability of the rock in real time in the drilling process, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth;
step four: establishing a random forest algorithm regressor, determining hyperparameters of the random forest regressor by taking the characteristics in the characteristic set as input parameters and the rock compressive strength data and the rock drillability data of corresponding depths as output parameters, and training and establishing a rock compressive strength prediction model and a rock drillability prediction model;
step five: the method comprises the steps of collecting real-time logging data to be drilled, calculating to obtain corresponding bottom hole drilling pressure, inputting the calculated bottom hole drilling pressure and other characteristics in the real-time logging data into the built rock compressive strength prediction model and the rock drillability prediction model, and achieving real-time calculation of the rock compressive strength and the drillability of the to-be-drilled well.
2. The method as claimed in claim 1, wherein in the second step, the bottom hole weight corresponding to each depth point of each adjacent well near the well to be drilled is determined through a three-dimensional borehole axial force flexible rod calculation model.
3. The method of claim 1, wherein the deviated interval axial force is calculated by the formula:
wherein, F2Axial force, KN, at the upper end of the well section unit; f1Axial force, KN, at the lower end of the well section unit; beta is a buoyancy coefficient; w is the weight of the drill unit wire, kg/m; Δ L is the calculation unit length, m; α is the well angle, rad; mu is a friction coefficient;
is the angle between the axial direction and the tangential direction of motion of the drilling tool, rad.
4. The method of claim 3, wherein the curved-interval axial force is calculated by the formula:
wherein, theta2Is the azimuth angle, rad, of the upper end of the well section unit; theta1Is the azimuth angle, rad, of the lower end of the well section unit; alpha is alpha2Is the well head angle, rad, of the upper end of the well section unit; alpha is alpha1Is the well section unit lower end well bevel angle, rad.
5. The method of claim 1, wherein in step three, the features in the feature set are aligned to the same depth axis by linear interpolation.
6. The method of claim 1, wherein the features in the feature set comprise: depth, bottom hole weight, rotational speed, drilling fluid density, bit diameter, bit type, rate of penetration, and rotary table torque.
7. A method as claimed in claim 1, wherein in step four, the hyper-parameters of the random forest regressor are determined by a k-fold cross validation and grid search method.
8. The method of claim 1, wherein in step five, the real-time logging data is subjected to condition identification, and real-time data which does not belong to the drilling process conditions is removed.
9. An apparatus for monitoring compressive rock strength and drillability, the apparatus comprising:
the system comprises a collecting module, a data processing module and a data processing module, wherein the collecting module is used for collecting well body structure data, drilling tool combination data, rock compressive strength data, rock drillability data, logging data, well track measurement data and drill bit information of adjacent wells to be drilled;
the calculation module is used for calculating and obtaining the bottom hole drilling pressure corresponding to each depth point of each adjacent well near the well to be drilled according to hook load data and drilling fluid density data in the logging information and by combining the borehole trajectory measurement data and the drilling tool assembly data;
the construction module is used for constructing a feature set for calculating the compressive strength and the drillability of the rock in real time in the drilling process, aligning the features in the feature set to the same depth axis, and randomly disordering the data set according to the depth;
the training module is used for establishing a random forest algorithm regressor, determining the hyperparameter of the random forest regressor by taking the characteristics in the characteristic set as input parameters and the rock compressive strength data and the rock drillability data with corresponding depths as output parameters, and training and establishing a rock compressive strength prediction model and a rock drillability prediction model;
and the real-time calculation module is used for acquiring real-time logging data to be drilled, calculating to obtain the corresponding bottom hole drilling pressure, and inputting the calculated bottom hole drilling pressure and other characteristics in the real-time logging data into the built rock compressive strength prediction model and the rock drillability prediction model to realize the real-time calculation of the rock compressive strength and the drillability to be drilled.
10. The apparatus of claim 9, wherein the calculation module comprises a three-dimensional borehole axial force flexible rod calculation model for determining a bottom hole weight per depth point for each adjacent well near the well to be drilled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010088788.1A CN113323647B (en) | 2020-02-12 | Method and device for monitoring compressive strength and drillability of rock |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010088788.1A CN113323647B (en) | 2020-02-12 | Method and device for monitoring compressive strength and drillability of rock |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113323647A true CN113323647A (en) | 2021-08-31 |
| CN113323647B CN113323647B (en) | 2024-07-02 |
Family
ID=
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114856540A (en) * | 2022-05-11 | 2022-08-05 | 西南石油大学 | Horizontal well mechanical drilling speed while drilling prediction method based on online learning |
| CN117763466A (en) * | 2024-02-22 | 2024-03-26 | 中石化经纬有限公司 | stratum drillability evaluation method and system based on clustering algorithm |
| CN117763466B (en) * | 2024-02-22 | 2024-07-09 | 中石化经纬有限公司 | Stratum drillability evaluation method and system based on clustering algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4914591A (en) * | 1988-03-25 | 1990-04-03 | Amoco Corporation | Method of determining rock compressive strength |
| CN105089620A (en) * | 2014-05-14 | 2015-11-25 | 中国石油天然气集团公司 | Drilling tool jamming monitoring system, drilling tool jamming monitoring method and drilling tool jamming monitoring device |
| CN105221071A (en) * | 2015-09-23 | 2016-01-06 | 中国石油大学(华东) | Horizontal well inverted drill string unitized designing method |
| US20160273330A1 (en) * | 2013-10-18 | 2016-09-22 | Baker Hughes Incorporated | Predicting drillability based on electromagnetic emissions during drilling |
| CN107448192A (en) * | 2017-08-04 | 2017-12-08 | 中国石油大学(华东) | The actual bottom hole WOB Forecasting Methodology of static pushing type rotary steering drilling tool |
| CN110397402A (en) * | 2018-04-23 | 2019-11-01 | 中国石油天然气股份有限公司 | Boring method and device |
| CN110671095A (en) * | 2019-09-23 | 2020-01-10 | 中国地质大学（武汉） | Intelligent while-drilling soft measurement method for formation pressure |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4914591A (en) * | 1988-03-25 | 1990-04-03 | Amoco Corporation | Method of determining rock compressive strength |
| US20160273330A1 (en) * | 2013-10-18 | 2016-09-22 | Baker Hughes Incorporated | Predicting drillability based on electromagnetic emissions during drilling |
| CN105089620A (en) * | 2014-05-14 | 2015-11-25 | 中国石油天然气集团公司 | Drilling tool jamming monitoring system, drilling tool jamming monitoring method and drilling tool jamming monitoring device |
| CN105221071A (en) * | 2015-09-23 | 2016-01-06 | 中国石油大学(华东) | Horizontal well inverted drill string unitized designing method |
| CN107448192A (en) * | 2017-08-04 | 2017-12-08 | 中国石油大学(华东) | The actual bottom hole WOB Forecasting Methodology of static pushing type rotary steering drilling tool |
| CN110397402A (en) * | 2018-04-23 | 2019-11-01 | 中国石油天然气股份有限公司 | Boring method and device |
| CN110671095A (en) * | 2019-09-23 | 2020-01-10 | 中国地质大学（武汉） | Intelligent while-drilling soft measurement method for formation pressure |
Non-Patent Citations (5)
| Title |
|---|
| 吴泽兵;郭龙龙;潘玉杰;: "水平井钻井过程中井底钻压预测及应用", 石油钻采工艺, no. 01, 8 March 2018 (2018-03-08), pages 9 - 13 * |
| 张思渊;刘皓;袁春娥;: "钻井参数判断岩石可钻性问题的研究与讨论", 山西建筑, no. 23, 10 August 2010 (2010-08-10), pages 163 - 164 * |
| 曲宝龙;安峰;李燃;马卫国;: "基于摩擦系数的连续油管钻桥塞力学特性研究", 科学技术与工程, no. 09, 28 March 2016 (2016-03-28), pages 61 - 65 * |
| 郑双进;黄志强;陈彬;周吉祥;: "定向井钻压传导计算方法", 断块油气田, no. 03, 25 May 2011 (2011-05-25), pages 135 - 137 * |
| 黄鸿;魏红;李俞静;: "Φ139.7套管内开窗侧钻三维水平井钻井技术", 新疆石油科技, no. 02, 15 June 2013 (2013-06-15), pages 5 - 9 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114856540A (en) * | 2022-05-11 | 2022-08-05 | 西南石油大学 | Horizontal well mechanical drilling speed while drilling prediction method based on online learning |
| CN114856540B (en) * | 2022-05-11 | 2024-05-28 | 西南石油大学 | Horizontal well mechanical drilling speed while drilling prediction method based on online learning |
| CN117763466A (en) * | 2024-02-22 | 2024-03-26 | 中石化经纬有限公司 | stratum drillability evaluation method and system based on clustering algorithm |
| CN117763466B (en) * | 2024-02-22 | 2024-07-09 | 中石化经纬有限公司 | Stratum drillability evaluation method and system based on clustering algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111520123B (en) | Mechanical drilling speed prediction method, device and equipment | |
| US8145462B2 (en) | Field synthesis system and method for optimizing drilling operations | |
| CN111520122B (en) | Method, device and equipment for predicting mechanical drilling speed | |
| CN103649781B (en) | Azimuthal brittleness logging systems and methods | |
| RU2693066C2 (en) | Method and device for control borehole deviation | |
| RU2663653C1 (en) | Improved estimation of well bore logging based on results of measurements of tool bending moment | |
| US20140025301A1 (en) | Determination of subsurface properties of a well | |
| CN110805469B (en) | Stability grading method for construction tunnel face by mountain tunnel drilling and blasting method | |
| BR112015009197B1 (en) | METHOD AND SYSTEM FOR PERFORMING A DRILLING OPERATION | |
| CN110130883A (en) | The determination method and device of formation parameters | |
| CN103443657A (en) | Methods and systems of estimating formation parameters | |
| CN110965991B (en) | Method and device for identifying mineral components of rock under drilling based on artificial intelligence | |
| CN107532473B (en) | Method for plotting advanced well logging information | |
| CN104220901B (en) | Systems and methods for computing surface of fracture per volume of rock | |
| CN102220865A (en) | Method for detecting limestone formation pore pressure | |
| RU2564423C2 (en) | System and method for simulation of interaction of reamer and bit | |
| CN102383788B (en) | Underground reservoir porosity measurement method during drilling | |
| CN104879115B (en) | A kind of downhole drill determination method for parameter and device | |
| US11906683B2 (en) | Dynamic time warping of signals plus user picks | |
| CN113323647B (en) | Method and device for monitoring compressive strength and drillability of rock | |
| CN113323647A (en) | Method and device for monitoring compressive strength and drillability of rock | |
| CN215256164U (en) | Device for monitoring formation change of drilling machine in drilling process | |
| CN110781571A (en) | Drill bit work efficiency evaluation system | |
| CN113464126A (en) | Device and method for monitoring stratum change of drilling machine in drilling process | |
| CN111206920B (en) | Natural deviation law evaluation method based on multi-well statistics and stratum characterization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |