CN114169656A - Drilling stuck risk early warning method and system based on adjacent well historical data - Google Patents
Drilling stuck risk early warning method and system based on adjacent well historical data Download PDFInfo
- Publication number
- CN114169656A CN114169656A CN202010952500.0A CN202010952500A CN114169656A CN 114169656 A CN114169656 A CN 114169656A CN 202010952500 A CN202010952500 A CN 202010952500A CN 114169656 A CN114169656 A CN 114169656A
- Authority
- CN
- China
- Prior art keywords
- data
- drilling
- risk
- well
- real
- 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 250
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000010586 diagram Methods 0.000 claims abstract description 94
- 238000009826 distribution Methods 0.000 claims abstract description 90
- 230000002776 aggregation Effects 0.000 claims abstract description 12
- 238000004220 aggregation Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 31
- 239000000725 suspension Substances 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 6
- 238000012502 risk assessment Methods 0.000 claims description 4
- 238000012821 model calculation Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000009933 burial Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Earth Drilling (AREA)
- Development Economics (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
Abstract
The invention provides a drilling stuck risk early warning method and a drilling stuck risk early warning system based on adjacent well historical data, wherein the method comprises the steps of counting real-time logging data and corresponding drilling risk record data of each historical well in a block where a target well is located, and counting and drawing a drill bit depth and hanging weight data scatter distribution diagram corresponding to each drilling working condition based on the sorted real-time logging data; reversely drawing a density thermodynamic diagram reflecting the aggregation of the corresponding hanging weight data of different drill bit positions of the historical well based on the density thermodynamic diagram; and then analyzing and judging the drilling sticking risk of the set time of the target well by utilizing the density thermodynamic diagram corresponding to the working condition of the target well according to the acquired real-time logging data of the target well. By adopting the scheme, the implementation is carried out according to the easily acquired historical well logging data and risk record data, the indirect model calculation of key parameters is avoided, the problems of insufficient accuracy and low prediction efficiency in the prior art can be solved, in addition, the early warning method can intuitively reflect the drilling stuck risk of the target well, and the missing report and the false report are further avoided.
Description
Technical Field
The invention relates to the technical field of petroleum exploration engineering, in particular to a drilling stuck risk early warning method and system based on adjacent well historical data.
Background
With the continuous deepening of exploration and development, the oil and gas exploration and development difficulty is higher and higher, the geological condition is more and more complex, the reservoir burial depth is increased, the complex situations faced by drilling engineering are more and more, the resource amount and the cost required for processing drilling risks and accidents are higher and higher, the realization of safe drilling is the primary target of the drilling industry, and therefore the construction risks in the exploration process need to be pre-warned by means of reliable technical means, especially the drilling jamming risks in the drilling process.
Although the control of the drilling risk in the drilling operation process is always the key point of industrial research, based on the existing research, the early warning analysis can be carried out on the drilling downhole risk by theoretically depending on a calculation model related to key parameters such as formation pressure, shaft pressure, friction torque and the like, the key parameters such as the downhole formation pressure, the shaft pressure, the friction torque and the like directly related to the drilling sticking risk cannot be directly measured by using a sensor in the drilling process, and can only be indirectly calculated by using a numerical calculation model or a grey correlation method and the like according to ground logging data and then be applied to the sticking risk early warning, as the calculation models have a plurality of assumed conditions at the beginning of establishment, the calculation models have deviation with the real downhole environment, and meanwhile, factors such as downhole high-frequency vibration, high temperature and high pressure, drilling fluid flow and the like can also directly restrict the use of the sensor to obtain downhole condition parameters, so that the reliability of the obtained result is difficult to ensure, the accuracy of the risk early warning result is affected.
In the prior art, a part of exploration projects are judged by using a critical threshold, but the problems of low early warning accuracy and high false alarm rate inevitably occur, correspondingly, the identification of the drilling site stuck drill risk can also depend on the past experiences of a few personnel such as site drillers and drilling engineers, but the identification method has too strong dependence on professionals, the situations of error judgment and untimely processing are difficult to avoid, the false alarm rate and the false alarm rate are high, the reference value for the site engineers and operators is low, and the requirement of safe drilling in the field cannot be well met. Based on the current situation, it is very necessary to provide a stuck drill early warning method capable of effectively improving the stuck drill risk early warning accuracy.
Disclosure of Invention
In order to solve the above problems, the present invention provides a drilling stuck risk early warning method based on adjacent well historical data, and in one embodiment, the method includes:
step S1, counting real-time logging data of all historical wells in the block where the target well is located and corresponding drilling risk record data; the real-time logging data comprises real-time drilling pressure, drill bit position, inlet flow, rotating speed data, hook hanging weight and other data in the drilling process;
s2, arranging the real-time logging data of each historical well according to the drilling risk record data, and drawing a drill bit depth and hanging weight data scatter point distribution diagram corresponding to each drilling working condition based on the arranged real-time logging data statistics;
step S3, calculating and drawing a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
and S4, acquiring real-time logging data of the target well within a set time period, determining the corresponding working condition of the target well according to the real-time logging data of the target well, and determining the drilling sticking risk of the set time of the target well based on the density thermodynamic diagram corresponding to the working condition of the target well and the large hook hanging weight data distribution of the target well.
Preferably, in the step S2, the real-time logging data of each historical well is sorted by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well.
In an embodiment, before the step S2 of drawing a drill bit depth and suspension data scatter distribution map corresponding to each drilling condition, the method includes:
based on the sorted real-time logging data, taking the drill bit positions as identifiers, extracting real-time logging data of different time points corresponding to the drill bit positions, and analyzing the drilling working conditions of the different time points corresponding to the drill bit positions by comprehensively utilizing parameters related to the drilling working conditions;
wherein the drilling conditions include: drilling working conditions, tripping working conditions, drilling working conditions, reaming working conditions and circulating working conditions.
In one embodiment, the step S2 includes: and extracting and recording all the hook overhang weight data of different drill bit positions corresponding to different drilling working conditions of each historical well, longitudinally representing the depth value of the drill bit position, and transversely representing the hook overhang weight values of various discrete distributions corresponding to the depth of each drill bit position, and drawing a drill bit depth and overhang weight data scatter point distribution diagram corresponding to each drilling working condition of the historical well.
In one embodiment, the step S3 includes the following operations:
determining the center point of the hanging weight data at different drill bit positions by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
In one embodiment, the step S4, in determining the risk of sticking in the target well at the set time, includes:
extracting the drill bit depth value and the hook weight value of the target well, selecting a density thermodynamic diagram corresponding to the drilling working condition of the target well at a set time, drawing the hook weight value of the drill bit depth corresponding to the target well in the selected density thermodynamic diagram, and analyzing the distribution condition of the hook weight value;
and if the hook overhang value of the target well is distributed in the risk data area, judging that the target well has a drilling sticking risk in the set time.
In accordance with another aspect of any one or more embodiments of the present invention, there is provided a drilling stuck risk early warning system based on adjacent well historical data, the system including:
the historical data acquisition module is configured to count real-time logging data of all historical wells in a block where the target well is located and corresponding drilling risk record data;
the real-time logging data comprises real-time drilling pressure, drill bit position, inlet flow, rotating speed data, hook hanging weight and other data in the drilling process;
the scatter diagram drawing module is configured to sort the real-time logging data of each historical well according to the drilling risk record data, and draw a drill bit depth and hanging weight data scatter diagram corresponding to each drilling working condition based on the sorted real-time logging data statistics;
the thermodynamic diagram conversion module is configured to calculate and draw a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
and the risk analysis module is configured to acquire real-time logging data of the target well within a set time period, determine the corresponding working condition of the target well according to the real-time logging data of the target well, and judge the drilling sticking risk of the target well at the set time based on the density thermodynamic diagram corresponding to the working condition of the target well in combination with the large hook hanging weight data distribution of the target well.
Preferably, in one embodiment, the scattergram rendering module collates the real-time logging data of each historical well by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well.
In one embodiment, the scatter plot rendering module is configured to:
and extracting and recording all the hook overhang weight data of different drill bit positions corresponding to different drilling working conditions of each historical well, longitudinally representing the depth value of the drill bit position, and transversely representing the hook overhang weight values of various discrete distributions corresponding to the depth of each drill bit position, and drawing a drill bit depth and overhang weight data scatter point distribution diagram corresponding to each drilling working condition of the historical well.
In one embodiment, the thermodynamic diagram conversion module is configured to:
determining the center point of the hanging weight data at different drill bit positions by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
Compared with the closest prior art, the invention also has the following beneficial effects:
compared with the existing drilling stuck early warning method, the drilling stuck risk early warning method based on the adjacent well historical data is implemented according to the easily acquired real-time logging data and risk record data of the corresponding block historical well, so that indirect model calculation of parameters is avoided, the subjective influence of prediction personnel is avoided, reliable source data support is provided, and the problems of insufficient accuracy and low prediction efficiency caused by assumed parameter calculation in the prior art are solved;
in addition, the method and the device perform early warning based on the regional historical data distribution rule, can visually reflect the drilling sticking risk of the target well, avoid the problems of high missing report rate and high false report rate of the conventional method, improve the early warning accuracy, do not need repeated calculation to obtain the distribution rule of the historical data, can realize accurate and efficient prediction through concise calculation and analysis, and can provide reliable decision support for the safety implementation of exploration engineering.
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 is a schematic flow chart of a drilling stuck risk early warning method based on adjacent well historical data according to an embodiment of the present invention;
FIG. 2 is a detailed flow chart of an implementation of the method for warning the risk of stuck drilling based on the historical data of the adjacent well according to another embodiment of the present invention;
FIG. 3 is a thermodynamic diagram of the aggregate distribution density of the hanging weight data under the condition of tripping of the drill according to the method for early warning of the drilling sticking risk based on the historical data of the adjacent well in the embodiment of the invention;
FIG. 4 is a schematic structural diagram of a drilling stuck risk early warning system based on adjacent well historical data according to still another embodiment of the present invention.
Detailed Description
The following detailed description will be provided for the embodiments of the present invention with reference to the accompanying drawings and examples, so that the practitioner of the present invention can fully understand how to apply the technical means to solve the technical problems, achieve the technical effects, and implement the present invention according to the implementation procedures. It should be noted that, unless otherwise conflicting, the embodiments and features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are all within the scope of the present invention.
With the continuous deepening of exploration and development, the oil and gas exploration and development difficulty is higher and higher, the geological condition is more and more complex, the reservoir burial depth is increased, the complex situations faced by drilling engineering are more and more, the resource amount and the cost required for processing drilling risks and accidents are higher and higher, the realization of safe drilling is the primary target of the drilling industry, and therefore the construction risks in the exploration process need to be pre-warned by means of reliable technical means, especially the drilling jamming risks in the drilling process.
Although the control of the drilling risk in the drilling operation process is always the key point of industrial research, based on the existing research, the early warning analysis can be carried out on the drilling downhole risk by theoretically depending on a calculation model related to key parameters such as formation pressure, shaft pressure, friction torque and the like, the key parameters such as the downhole formation pressure, the shaft pressure, the friction torque and the like directly related to the drilling sticking risk cannot be directly measured by using a sensor in the drilling process, and can only be indirectly calculated by using a numerical calculation model or a grey correlation method and the like according to ground logging data and then be applied to the sticking risk early warning, as the calculation models have a plurality of assumed conditions at the beginning of establishment, the calculation models have deviation with the real downhole environment, and meanwhile, factors such as downhole high-frequency vibration, high temperature and high pressure, drilling fluid flow and the like can also directly restrict the use of the sensor to obtain downhole condition parameters, so that the reliability of the obtained result is difficult to ensure, the accuracy of the risk early warning result is affected.
Specifically, the existing technical scheme applicable to the stuck drill risk monitoring in the exploration process includes the following steps, although the technical scheme can represent the stuck drill risk precursor in the drilling process to a certain extent, the technical scheme has inevitable technical defects and cannot meet the requirements of the exploration project, and the invention provides basic introduction aiming at each technical scheme as follows:
CN105089620A a system, method and device for monitoring stuck drill, which belongs to the technical field of petroleum drilling engineering, and the invention aims to be realized by the following operations: initializing a system, and loading an analytic hierarchy process model; inputting design data of a current borehole; calculating friction resistance and torque of each point on the drill string by using a finite element calculation method according to design data and the current real-time working condition, and calculating predicted values of large hook load and turntable torque in an overlapping manner; comparing the rotary table torque and the large hook load in the real-time comprehensive logging data with a predicted value, if the rotary table torque and the large hook load exceed the predicted value within a certain range, giving out an early warning, normalizing an abnormal difference value and transmitting the normalized abnormal difference value into a drill chuck type analysis module; and calculating the probability of occurrence of various drilling sticking accidents according to the pre-recorded drilling sticking analysis model and the membership degree of each bottom layer element so as to judge the type of the drilling sticking accidents.
According to the scheme, the drilling construction process is monitored, the large hook load and the turntable torque which are acquired in real time are compared with the model calculated value, the pre-judgment of the drill jamming accident is realized, in the implementation process, the measured value is compared with the friction torque model calculated value, the drill jamming type is judged by applying an analytic hierarchy process after the abnormality is found, however, the assumption conditions of the friction torque model applied in the current industry are too many, the model calculation result is used as a reference, and the accuracy is inevitably different from the actual underground condition, so that the accuracy of the judgment and early warning of the method is influenced.
CN106156385A A method for predicting sticking and sticking risks of a drill string, which comprises acquiring well track data to obtain coordinates of each position of a well track; determining geological parameters and engineering parameters according to the coordinates of each position; determining the fuzzy quantity of contribution of each influence factor at each position to the generation of the sticking and sticking drill by using the geological parameters and the engineering parameters at each position; and obtaining the sticking stuck drill risk coefficient at the position based on the fuzzy quantity of the contribution of each influence factor to the generation of the sticking stuck drill. The method is based on prediction of sticking and sticking risks at any position of the whole well section in the environment while drilling, a fine geological model needs to be established, meanwhile, a deviation measurement tool while drilling is needed to provide well track data, and the required data source is difficult to obtain for most wells; on the other hand, the fuzzy quantity of each influence factor contributing to the generation of sticking and sticking of the drill bit is artificially determined, so that the final prediction result is greatly influenced by subjectivity and cannot be used as a reliable basis for monitoring the risk of sticking of the drill bit in the drilling engineering.
CN109508827A a drilling accident early warning model based on time recursion neural network, the core steps in the scheme include: the method comprises the steps of firstly, predicting a drilling characteristic value at a certain moment by adopting an autoregressive model analysis method, and measuring the difference between the predicted characteristic value and the drilling real data at the moment, thereby obtaining an accident candidate set. Then, judging the truth of the accidents in the accident candidate set by using expert knowledge, and dividing the accident types; finally, obtaining a plurality of marked well drilling time sequence data; and training a supervised model on the premise of obtaining the labeled data, and constructing a time recurrent neural network model based on deep learning. Firstly, randomly selecting part of marked time sequence data as a training set, specifically inputting the combination of each characteristic and the selection of a time window, then training a model, and finally predicting the accident occurrence probability and the accident occurrence type after outputting one minute. The method has the core steps that a neural network model is applied, a large amount of data training needs to be carried out, overfitting occurs to the neural network model at the maximum probability, and the balance problem between the model training capacity and the prediction capacity needs to be solved.
CN109594967 is a method for detecting and warning a stuck drill accident based on big logging data, which realizes automatic marking of a drilling accident by preprocessing service parameters collected by an automatic logging device and log data recorded by a manager; then, resampling and smoothing the original data, judging the importance of the data field, and processing the stuck drill detection data by adopting a random forest model; and then, adjusting parameters of the learning model by adopting a cross validation method, and using the finally generated model for detecting drilling engineering abnormity. Effective information in business data is mined to serve for stuck drill detection, but it needs to be explained that data adopted by a model are inlet flow and riser pressure, data sources are too few, the hook overhang weight directly reflecting stuck drill change is not included in calculation, and meanwhile, a random forest model is easy to be overfitting to part of training data.
In addition, in the prior art, a large part of exploration projects are judged by using a critical threshold, but the problems of low early warning accuracy and high false alarm rate inevitably occur, correspondingly, the identification of drilling site stuck drilling risks can also depend on the past experiences of a small number of personnel such as site drillers and drilling engineers, but the identification method has too strong dependence on professionals, the situations of judgment errors and untimely processing are difficult to avoid, the false alarm rate and the false alarm rate are high, the reference value to the site engineers and operators is low, and the requirement of safe drilling in the field cannot be well met. Based on the current situation, it is urgently needed to provide a stuck drill early warning method capable of effectively improving the stuck drill risk early warning accuracy, so as to provide support for managing and optimizing exploration drilling engineering.
The conventional method and technology rely on obvious threshold value judgment for the drilling stuck risk early warning, the problems of low accuracy and high false alarm rate are inevitable, the risk early warning effect is influenced, and the reference value for field engineers and operators is low. The invention provides a new technical idea, based on historical well logging data, through working condition identification and density distribution calculation processing, a reverse thermodynamic diagram of data distribution of the big hook hanging weight scattering point with the variation of the drill bit depth under different working conditions is drawn, through comparison with real-time logging data of a target well, the drilling sticking risk early warning is realized by a simpler, more convenient and more accurate method, drilling personnel are assisted to realize safe drilling, the drilling sticking risk early warning accuracy rate is improved, the false alarm rate is reduced, field engineers and operating personnel can adjust operating parameters in time according to the early warning, the drilling sticking risk is avoided, prevented and controlled, and safe drilling is realized.
And on the basis of real-time logging data of historical wells in the block, density thermodynamic diagrams of corresponding working conditions and underground hook weight distribution are drawn by analyzing different drilling working conditions under the condition of no drilling risk and the condition of large hook weight distribution under different well depths, and the real-time logging data of a target well is compared on the basis of the drawn density thermodynamic diagrams to warn the drilling sticking risk.
Specifically, in order to solve the problems and effectively overcome the problem that the well drilling stuck early warning method is high in false alarm rate and missed alarm rate, the invention provides a well drilling stuck risk early warning method based on adjacent well historical data. The embodiments of the present invention will be described in detail with reference to the accompanying drawings and examples, so that the technical effects of the present invention can be fully understood and implemented.
Example one
Fig. 1 is a schematic flow chart illustrating a drilling stuck risk early warning method based on adjacent well historical data according to an embodiment of the present invention, and as can be seen from fig. 1, the method includes the following steps.
Step S110, counting real-time logging data of all historical wells in a block where a target well is located and corresponding drilling risk record data; the real-time logging data comprises real-time drilling pressure, drill bit position, inlet flow, rotating speed data, hook hanging weight and other data in the drilling process;
step S120, arranging the real-time logging data of each historical well according to the drilling risk record data, and statistically drawing a drill bit depth and hanging weight data scatter point distribution diagram corresponding to each drilling working condition based on the arranged real-time logging data;
s130, calculating and drawing a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
step S140, collecting real-time logging data of the target well within a set time period, determining a corresponding target well working condition according to the real-time logging data of the target well, and determining a drilling sticking risk of the target well at the set time based on the density thermodynamic diagram corresponding to the target well working condition and the large hook hanging weight data distribution of the target well.
Fig. 2 shows an implementation flow detail diagram of a drilling stuck risk early warning method based on adjacent well historical data provided in an embodiment of the present invention, and as shown in fig. 3, the present invention implements early warning of a target well stuck risk by sequentially performing the following operations:
(1) collecting data: collecting real-time logging data, drilling risk related data and the like of all historical wells in a block where a target well is located, and constructing a database; the well drilling risk record data comprises the type of risk occurrence (such as well leakage, well kick, stuck drill and the like), the risk occurrence time, the position of the drill bit when the risk occurs (namely the well depth of the drill bit), the well depth when the risk occurs, the risk end time and the like;
(2) and (3) data filtering: determining data sections which belong to risk occurrence and risk processing processes in logging data of historical wells by taking the drilling risk data of the historical wells as reference, and deleting and filtering;
(3) data extraction: for the logging data of one historical well, the position of a drill bit is taken as an identifier, if the position of the drill bit is at the depth of 1000m, the logging data of the drill bit is traversed, and the logging data of different time points of the position of the drill bit at the depth are extracted;
(4) and (3) working condition identification: after logging data of all time points of a certain drill bit depth are obtained, further extracting logging data 30 seconds-5 minutes before the certain time point according to the logging data of the certain time point, and comprehensively judging the drilling working condition of the time point by using the data such as the bit pressure, the drill bit position, the inlet flow, the rotating speed and the like, wherein the data comprises but is not limited to drilling, tripping, drilling, reaming, circulation and the like;
(5) and (3) data recording: after the identification of the drilling conditions of the logging data of the drill bit at all time points at a certain depth is completed, dividing the types of the working conditions, extracting and recording the large hook hanging weight value of the drill bit under the corresponding drilling conditions of the depth, wherein the number of the hanging weight data extracted under different working conditions of the drill bit depth is possibly different, for example, 1 data value exists under the drilling working condition, and a plurality of data values exist under the drilling and tripping working conditions;
(6) repeating the steps (3) and (5) to complete the hanging weight records of all the historical well drill bit positions at different depths and under different working conditions;
(7) data summarization: for a certain working condition, such as a tripping working condition, the drill bit depth is used as an identifier, the hanging weight data of all historical wells in a drilling block is summarized and recorded, the longitudinal direction is that the depth of the drill bit position is from 0 to 7000m (the maximum well depth of the historical wells in the region), and the transverse direction is a plurality of hanging weight values which are distributed discretely and are positioned at the depth of each drill bit position;
(8) inverse density thermodynamic diagram plotting: for a certain working condition, for example, a drilling condition, a center point of the hanging weight value distribution of a drill bit under each depth is calculated as a thermodynamic diagram center by using a related density distribution calculation method, and according to the hanging weight value distribution aggregation condition, a scatter diagram of the well depth and the hanging weight data is converted and drawn into a reverse density thermodynamic diagram, fig. 3 shows the hanging weight data aggregation distribution density thermodynamic diagram under the drilling condition of the drilling stuck-drill risk early warning method in the embodiment of the invention, as shown in fig. 3, the most dense region of the hanging weight data distribution under each depth is green, otherwise, the most dense region is red, in the reverse density thermodynamic diagram, the calculated center point is used as the center, 80% of data distribution regions are green, 80% -100% of data distribution regions are red, and the region between two black oblique lines is a green region with 80% of data aggregation; the required density thermodynamic diagram can also be directly drawn by using mature code programs such as Malab/R and the like;
(9) repeating the steps (7) to (8) to finish the inverse density thermodynamic diagram drawing of the well depth and the change of the suspended weight data distribution under all the drilling working conditions;
(10) judging the current drilling working condition according to the real-time data of the target well and the previous data of 30 seconds to 5 minutes, selecting a corresponding hanging weight distribution density thermodynamic diagram from the step (9) based on the current drilling working condition, extracting the position and hanging weight value of the drill bit in the current time point of the target well and the previous 10 to 30s of logging data, drawing and analyzing the distribution condition of the drill bit in the reverse thermodynamic diagram, wherein the drill bit risk is not present in a green area, the drill bit risk is present in a red area, and the risk is higher beyond the green area, so that the early warning of the drill bit risk of the target well is realized.
Specifically, in one embodiment, the present invention collects real-time logging data and drilling risk record data of all historical wells in the drilling block where the target well is located in step S110, and constructs a corresponding database based on the collected real-time logging data and drilling risk record data; the well drilling risk record data comprises the type of risk occurrence (such as well leakage, well kick, stuck drill and the like), the risk occurrence time, the position of the drill bit when the risk occurs (namely the well depth of the drill bit), the well depth when the risk occurs, the risk end time and the like;
in practical application, a worker can select set parameters as tags according to requirements and store the tags and other data in a partition mode according to association of the tags and other data, for example, numbers of different historical wells in a drilling block are respectively selected as first-level tags, drill bit position parameters in real-time logging data of the historical wells are selected as second-level tags, and then the real-time logging data and drilling risk recording data of the historical wells are flexibly stored on the basis of the selected multi-level tags.
In addition, in consideration of logging data corresponding to a drilling sticking risk generation process and a subsequent risk processing stage, there is no effective support for reflecting whether a drilling sticking risk will occur in a drilling process, and therefore, in the embodiment of the present invention, in order to reduce a data processing amount without affecting prediction accuracy, for real-time logging data of each historical well, parameters in a risk generation and risk processing time period are deleted based on risk recording data, and therefore, in step S120, the real-time logging data of each historical well is sorted by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well.
It should be noted that in the process of sorting real-time logging data, it is necessary to ensure that the data segments belonging to the risk occurrence and risk processing processes in the logging data are determined by taking the risk record data of the corresponding historical well as a reference, and then delete and filter the data segments, so that valuable logging data parameters cannot be filtered out. In practical application, the data can be sorted by adopting a data filtering algorithm and a data backup function of the database, so that the reliability of a data sorting result is guaranteed, and the processing efficiency is effectively improved.
Furthermore, considering that the amount of logging data related to a historical well drilling process is large, in order to facilitate analysis and subsequent processing, the embodiment of the invention adopts an idea of respectively analyzing the data based on the drilling working conditions, and needs to identify the drilling working conditions of different historical wells based on the technical idea, and in the actual exploration process, a plurality of logging parameters capable of representing the drilling working conditions exist, so that the drilling working conditions corresponding to the real-time logging data of the historical wells can be distinguished by using the change rules of data items such as the position of a drill bit, hook load, drilling pressure and the like in the real-time logging data, and the identification accuracy rate of the real-time logging data can basically reach more than 95%. Therefore, in one embodiment, before drawing a drill depth and hanging weight data scatter distribution diagram corresponding to each drilling working condition, the method extracts real-time logging data corresponding to different time points of each drill position based on the sorted real-time logging data by taking the drill position as an identifier, and analyzes the drilling working conditions corresponding to different time points of each drill position by comprehensively utilizing all parameters related to the drilling working conditions;
wherein the drilling conditions include at least: drilling working conditions, tripping working conditions, drilling working conditions, reaming working conditions and circulating working conditions.
Based on logging data with the drilling working conditions as identification, extracting and recording all the hook overhang weight data of different drill bit positions corresponding to different drilling working conditions of each historical well, making the longitudinal direction be depth values reflecting the drill bit positions, and the transverse direction be the hook overhang weight values of various discrete distributions corresponding to the depths of the drill bit positions, and drawing drill bit depths and suspension weight data scatter distribution graphs corresponding to the drilling working conditions of each historical well so as to obtain scatter point distribution conditions of the hook overhang weight data of various depth points under different working conditions in the drilling process of the historical well in the block. In practical application, the depth value of the drill bit position may be set to 0-7000 m, and of course, in this step, the drilling depth of each historical well in the corresponding block may be set reasonably by the operator, which is not limited by the present invention.
Further, in consideration of the close relationship between the hook weight value and the drill sticking risk during the drilling process, the embodiment of the present invention transforms and plots the scatter plot of the well depth and the hanging weight data under the drilling condition into the inverse density thermodynamic diagram according to the hanging weight value distribution aggregation condition by using the related density distribution calculation method for each condition, such as the drilling condition, so that in the step S130, the present invention includes the following operations:
determining the center point of the hanging weight data at different drill bit positions by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
In the embodiment of the invention, the density thermodynamic diagram is drawn through the steps to reflect the distribution situation of the hanging weight data of each working condition of the historical well under different drill bit depths, in order to improve the identification degree and the identification efficiency of a large amount of data for workers, preferably, the risk data area can be divided according to the drilling risk record data of different drill bit positions under each working condition of the historical well, the hanging weight data in the risk data area in the density thermodynamic diagram indicates that the corresponding logging data belongs to the logging parameters with the drilling sticking risk, the probability of the drilling sticking risk occurring at the corresponding moment is higher, and otherwise, the probability of the drilling sticking risk occurring at the corresponding moment is lower.
In practical application, the region dividing line can be divided by adopting color or directly,
for example, in the inverse density thermodynamic diagram, the most dense region of the suspended weight data distribution at each depth is green, otherwise, the most dense region is red, and as shown in fig. 3, the region between two black oblique lines is a dense aggregation region of 80% of data, that is, a green region, and the region outside the two black oblique lines is a red region, that is, a risk data region, and the suspended weight data falling in the region correspondingly indicates that the drilling time of the suspended weight data has a drilling risk, as shown in the central point of the calculation, in addition, in other embodiments, a mature code program such as Malab/R can be used to directly draw the required density thermodynamic diagram. Based on the logic, the invention realizes the pre-judgment of the sticking risk of the target well set time by the following means:
extracting the drill bit depth value and the hook weight value of the target well, selecting a density thermodynamic diagram corresponding to the drilling working condition of the target well at a set time, drawing the hook weight value of the drill bit depth corresponding to the target well in the selected density thermodynamic diagram, and analyzing the distribution condition of the hook weight value;
and if the hook overhang value of the target well is distributed in the risk data area, judging that the target well has a drilling sticking risk in the set time.
Specifically, in one embodiment, the current drilling condition is judged according to the current real-time logging data of the target well and the logging data of 30 seconds to 5 minutes before the target well, a corresponding hanging weight distribution density thermodynamic diagram is selected based on the drilling condition, the position and the hanging weight value of a drill bit in the current time point of the target well and the logging data of 10 to 30 seconds before the target well are extracted, the distribution condition of the drill bit in the corresponding density thermodynamic diagram is drawn and analyzed, the drilling risk is not caused in a green area, the drilling risk is caused in a red area, and the risk is higher in an outer area, so that the drilling risk early warning of the target well is realized.
Compared with the existing drilling stuck early warning method, the method for early warning based on the regional historical data distribution rule can intuitively reflect the risk of sticking of the target well, avoid the problems of high missing report rate and false report rate in the prior art, and improve the early warning accuracy.
In addition, the regional historical data used by the method mainly comprise real-time logging data and drilling risk data, a required data source is easier to obtain accurately, and the calculation analysis method is simpler, more convenient and easier to use.
Supplementary notes
The technical scheme of the invention selects 10 new drilling wells for experimental application in the third operation area of the Tahe block of the northwest oil field.
Firstly, 120 historical well logging data in a third operation area of the tower river block are collected to construct a database.
And then, analyzing 120 historical well logging data, identifying drilling conditions one by one, carrying out large-class division according to the drilling conditions, taking the drill bit depth as a longitudinal coordinate and the hook overhang as a transverse coordinate, extracting the drill bit depth and the hook overhang in all the historical well logging data under the conditions, drawing the drill bit depth and the hook overhang as a scatter diagram, and converting the scatter diagram into a reverse thermodynamic diagram by methods such as density distribution calculation and the like, wherein the region with the most dense suspension distribution is green, and the region with the most dense suspension distribution is red on the contrary.
The method comprises the steps that 10 new wells identify the current working condition according to real-time logging data in the drilling process, then the hanging weight reverse thermodynamic diagrams under the corresponding working conditions are called, the positions of drill bits and the hanging weights of hooks in the current logging data of a test well are drawn into the reverse thermodynamic diagrams to analyze the distribution conditions of the hanging weight reverse thermodynamic diagrams, if the hanging weights are distributed in a green area, the hanging weights are normal, if the hanging weights are distributed in a red area, the drilling blocking risk is indicated, and drilling blocking risk early warning is sequentially carried out.
And (4) counting the drilling sticking risk early warning condition after the 10 wells are drilled. 1-well-time stuck drilling actually occurs in 10 wells, the method accurately carries out early warning, the rate of missing report is 0, the risk of false-report stuck drilling is 2 wells, and the average rate of false reports is 0.2 times per well; and the number of the 120 historical wells in the operation area is 13 well times of stuck drilling in total, 9 well times are actually pre-warned when the conventional grey correlation or analytic hierarchy process is used for pre-warning, the missing report rate is 30.77%, the false alarm stuck drilling risk is 273 well times, and the average false alarm rate is 2.28 times per well.
By using the method provided by the invention, the early warning accuracy rate of the drilling sticking risk is improved and the false alarm rate is reduced.
Example two
In view of other aspects of any one or more of the above embodiments, the present invention also provides a drilling stuck risk early warning system based on adjacent well historical data, wherein each structure or module is used for executing the method or steps in any one or more of the above embodiments.
Specifically, fig. 4 shows a schematic structural diagram of a drilling stuck risk early warning system based on adjacent well historical data in an embodiment of the present invention, and as shown in fig. 4, the system includes:
a historical data acquisition module 41 configured to count real-time logging data of all historical wells in a block where the target well is located and corresponding drilling risk record data; the real-time logging data comprises real-time drilling pressure, drill bit position, inlet flow, rotating speed data, hook hanging weight and other data in the drilling process;
a scatter diagram drawing module 43, configured to sort the real-time logging data of each historical well according to the drilling risk record data, and draw a scatter point distribution diagram of the drill depth and the hanging weight data corresponding to each drilling condition based on the sorted real-time logging data statistics;
the thermodynamic diagram conversion module 45 is configured to calculate and draw a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
and the risk analysis module 47 is configured to acquire real-time logging data of the target well within a set time period, determine a corresponding working condition of the target well according to the real-time logging data of the target well, and determine a drilling sticking risk of the target well at the set time based on the density thermodynamic diagram corresponding to the working condition of the target well in combination with the distribution of the hook overhang data of the target well.
Further, in one embodiment, the scatter plot rendering module 43 collates the real-time log data for each historical well by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well. The well drilling risk record data comprises the type of risk occurrence (such as well leakage, well kick, stuck drill and the like), the risk occurrence time, the position of the drill bit when the risk occurs (namely the well depth of the drill bit), the well depth when the risk occurs, the risk end time and the like;
in one embodiment, before the scatter diagram drawing module 43 draws the drill depth and the suspension weight data scatter distribution diagram corresponding to each drilling condition, the following operations are further performed:
based on the sorted real-time logging data, taking the drill bit positions as identifiers, extracting real-time logging data of different time points corresponding to the drill bit positions, and analyzing the drilling working conditions of the different time points corresponding to the drill bit positions by comprehensively utilizing parameters related to the drilling working conditions;
wherein the drilling conditions include: drilling working conditions, tripping working conditions, drilling working conditions, reaming working conditions and circulating working conditions.
Preferably, the scatter plot rendering module 43 is configured to: and extracting and recording all the hook overhang weight data of different drill bit positions corresponding to different drilling working conditions of each historical well, longitudinally representing the depth value of the drill bit position, and transversely representing the hook overhang weight values of various discrete distributions corresponding to the depth of each drill bit position, and drawing a drill bit depth and overhang weight data scatter point distribution diagram corresponding to each drilling working condition of the historical well.
In one embodiment, the thermodynamic diagram conversion module 45 is configured to:
determining the center point of the hanging weight data at different drill bit positions by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
Based on the above design, the risk analysis module 47 of an embodiment of the present invention implements the stuck risk early warning of the target well by:
extracting the drill bit depth value and the hook weight value of the target well, selecting a density thermodynamic diagram corresponding to the drilling working condition of the target well at a set time, drawing the hook weight value of the drill bit depth corresponding to the target well in the selected density thermodynamic diagram, and analyzing the distribution condition of the hook weight value;
and if the hook overhang value of the target well is distributed in the risk data area, judging that the target well has a drilling sticking risk in the set time.
In the drilling stuck risk early warning system based on the adjacent well historical data, provided by the embodiment of the invention, each module or unit structure can be independently operated or operated in a combined mode according to the actual application requirements, so that the corresponding technical effect is realized.
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, appearances of the phrase "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 descriptions are only for the convenience of understanding the present invention, and are 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 drilling stuck risk early warning method based on adjacent well historical data is characterized by comprising the following steps:
step S1, counting real-time logging data of all historical wells in the block where the target well is located and corresponding drilling risk record data; the real-time logging data comprises real-time bit pressure, bit position, inlet flow, rotating speed data and hook overhang data in the drilling process;
s2, arranging the real-time logging data of each historical well according to the drilling risk record data, and drawing a drill bit depth and hanging weight data scatter point distribution diagram corresponding to each drilling working condition based on the arranged real-time logging data statistics;
step S3, calculating and drawing a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
and S4, acquiring real-time logging data of the target well within a set time period, determining the corresponding working condition of the target well according to the real-time logging data of the target well, and determining the drilling sticking risk of the set time of the target well based on the density thermodynamic diagram corresponding to the working condition of the target well and the large hook hanging weight data distribution of the target well.
2. The method of claim 1, wherein in step S2, the real-time logging data of each historical well is collated by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well.
3. The method according to claim 1 or 2, wherein the step S2, before the step of plotting the drill bit depth and the suspension weight data scatter distribution map corresponding to each drilling condition, comprises:
based on the sorted real-time logging data, taking the drill bit positions as identifiers, extracting real-time logging data of different time points corresponding to the drill bit positions, and analyzing the drilling working conditions of the different time points corresponding to the drill bit positions by comprehensively utilizing parameters related to the drilling working conditions;
wherein the drilling conditions include: drilling working conditions, tripping working conditions, drilling working conditions, reaming working conditions and circulating working conditions.
4. The method according to any one of claims 1 to 3, wherein the step S2 includes: and extracting and recording all the hook overhang weight data under different drill bit depths corresponding to different drilling working conditions of each historical well, enabling the longitudinal direction to be the depth value reflecting the position of the drill bit and the transverse direction to be the hook overhang weight values of each discrete distribution corresponding to the depth where each drill bit is positioned, and drawing a drill bit depth and overhang weight data scatter point distribution diagram corresponding to each drilling working condition of the historical well.
5. The method according to claim 1, wherein in the step S3, the following operations are included:
determining the center point of the hanging weight data under different drill bit depths by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
6. The method according to claim 1, wherein the step S4, in determining the risk of sticking to the drill at the time set by the target well, comprises:
extracting the drill bit depth value and the hook weight value of the target well, selecting a density thermodynamic diagram corresponding to the drilling working condition of the target well at a set time, drawing the hook weight value of the drill bit depth corresponding to the target well in the selected density thermodynamic diagram, and analyzing the distribution condition of the hook weight value;
and if the hook overhang value of the target well is distributed in the risk data area, judging that the target well has a drilling sticking risk in the set time.
7. A drilling stuck risk early warning system based on adjacent well historical data, the system comprising:
the historical data acquisition module is configured to count real-time logging data of all historical wells in a block where the target well is located and corresponding drilling risk record data; the real-time logging data comprises real-time bit pressure, bit position, inlet flow, rotating speed data and hook overhang data in the drilling process;
the scatter diagram drawing module is configured to sort the real-time logging data of each historical well according to the drilling risk record data, and draw a drill bit depth and hanging weight data scatter diagram corresponding to each drilling working condition based on the sorted real-time logging data statistics;
the thermodynamic diagram conversion module is configured to calculate and draw a density thermodynamic diagram corresponding to the drill bit depth and suspension weight data scatter distribution diagram under each drilling working condition by using a density distribution calculation method;
and the risk analysis module is configured to acquire real-time logging data of the target well within a set time period, determine the corresponding working condition of the target well according to the real-time logging data of the target well, and judge the drilling sticking risk of the target well at the set time based on the density thermodynamic diagram corresponding to the working condition of the target well in combination with the large hook hanging weight data distribution of the target well.
8. The system of claim 7, wherein the scatter plot rendering module collates real-time log data for each historical well by:
and selecting real-time logging data of the historical wells in a risk occurrence stage and a risk processing stage according to the drilling risk record data of each historical well, filtering the data from the original real-time logging data, and taking the residual real-time logging data as the sorted real-time logging data of each historical well.
9. The system of claim 7 or 8, wherein the scatter plot rendering module is configured to:
and extracting and recording all the hook overhang weight data of different drill bit positions corresponding to different drilling working conditions of each historical well, longitudinally representing the depth value of the drill bit position, and transversely representing the hook overhang weight values of various discrete distributions corresponding to the depth of each drill bit position, and drawing a drill bit depth and overhang weight data scatter point distribution diagram corresponding to each drilling working condition of the historical well.
10. The system of claim 7, wherein the thermodynamic diagram conversion module is configured to:
determining the center point of the hanging weight data at different drill bit positions by using a density distribution calculation method according to different drilling working conditions;
taking the determined center point as the thermodynamic diagram center, and converting and drawing the drill bit depth and suspension weight data scatter point distribution diagram into a density thermodynamic diagram according to the distribution and aggregation condition of the hook suspension weight values;
and dividing a risk data area according to the drilling risk record data of different drill bit positions under various working conditions of the historical well.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010952500.0A CN114169656A (en) | 2020-09-11 | 2020-09-11 | Drilling stuck risk early warning method and system based on adjacent well historical data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010952500.0A CN114169656A (en) | 2020-09-11 | 2020-09-11 | Drilling stuck risk early warning method and system based on adjacent well historical data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114169656A true CN114169656A (en) | 2022-03-11 |
Family
ID=80476000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010952500.0A Pending CN114169656A (en) | 2020-09-11 | 2020-09-11 | Drilling stuck risk early warning method and system based on adjacent well historical data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114169656A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117579625A (en) * | 2024-01-17 | 2024-02-20 | 中国矿业大学 | Inspection task pre-distribution method for double prevention mechanism |
-
2020
- 2020-09-11 CN CN202010952500.0A patent/CN114169656A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117579625A (en) * | 2024-01-17 | 2024-02-20 | 中国矿业大学 | Inspection task pre-distribution method for double prevention mechanism |
| CN117579625B (en) * | 2024-01-17 | 2024-04-09 | 中国矿业大学 | Inspection task pre-distribution method for double prevention mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2848766B1 (en) | A method and system for monitoring a drilling operation | |
| CN109508827B (en) | Drilling accident early warning method based on time recursion neural network | |
| CN111738620B (en) | Well leakage risk prediction and leakage stoppage decision system and method based on association rules | |
| CN110110740B (en) | Drilling process working condition identification method based on multi-time scale features and neural network | |
| CN114417697A (en) | Neural network-based TBM hob abrasion real-time prediction method and system | |
| CN113431496A (en) | Drilling and production ship cooperative operation fault diagnosis and decision-making assisting method | |
| CN114444823A (en) | Method and system for predicting lost circulation risk in drilling operation process | |
| CN111738371B (en) | Stratum fracture number prediction method based on random forest data mining | |
| CN113496302B (en) | Method and system for carrying out intelligent identification and early warning on drilling risk | |
| CN114169656A (en) | Drilling stuck risk early warning method and system based on adjacent well historical data | |
| CN105484725A (en) | Drilling downhole anomaly monitoring device | |
| CN116066062A (en) | Drilling sticking real-time early warning method based on parameter change trend abnormity diagnosis | |
| CN115688956A (en) | While-drilling blocking early warning method and system based on intelligent learning of mobile sliding window | |
| CN117271675A (en) | TBM tunneling rock mass digability identification method and device based on big data mining | |
| CN114429253A (en) | Method and system for intelligently prompting adjacent well risk in drilling process | |
| CN116777085A (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| CN114970921A (en) | Early warning method and system for severity of drilling blockage | |
| CN114611958A (en) | Petroleum drilling big data processing method and device based on machine learning | |
| CN109033593B (en) | Big data analysis method for inverting working face salient risk factors by utilizing local salient risk prediction forecast data | |
| CN114169558A (en) | Method and system for predicting well kick risk | |
| CN115729910A (en) | Implementation method and system for analyzing drilling speed of drilling machine in real time | |
| CN116701952B (en) | Knowledge-graph-based underground complex working condition identification method | |
| Sarwono et al. | Stuck Pipe Detection For North Sumatera Geothermal Drilling Operation Using Artificial Neural Network | |
| Tian et al. | Real-time monitoring model of PDC bit wear based on GRU neural network |
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 |