CN113868951A - A method of intelligently judging the best timing for drilling short trips - Google Patents
A method of intelligently judging the best timing for drilling short tripsDownload PDFInfo
- Publication number
- CN113868951A CN113868951ACN202111144394.4ACN202111144394ACN113868951ACN 113868951 ACN113868951 ACN 113868951ACN 202111144394 ACN202111144394 ACN 202111144394ACN 113868951 ACN113868951 ACN 113868951A
- Authority
- CN
- China
- Prior art keywords
- short
- drilling
- logging
- parameters
- values
- 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
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
- 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
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Fluid Mechanics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Algebra (AREA)
- Environmental & Geological Engineering (AREA)
- Geophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Earth Drilling (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the technical field of short tripping drilling, and particularly discloses a method for intelligently judging the optimal time of short tripping of drilling.
Background
An important objective of drilling is to increase the drilling rate, shorten the drilling and completion time, and minimize the drilling cost, thereby increasing the economic efficiency. Drilling cuttings are inevitably generated in the drilling process, excessive drilling cuttings are accumulated to cause drill sticking, so that drilling is difficult, termination even well kick, blowout and other safety accidents can be caused, unnecessary drilling and completion time is increased, and huge economic loss is caused. In order to solve the problem of drill sticking caused by the accumulation of drill cuttings and avoid more serious accidents caused by drill sticking, an effective method for solving the problem is urgently needed.
According to the literature, short-lift rock debris accumulation removal is a very effective method, but the short-lift cost is high, each short-lift cost is higher than the previous cost, the number of short-lifts needs to be strictly controlled, and the time which is most suitable for the short-lift needs to be found to reduce the drilling cost. The best opportunity for shortfalls is when the build-up of cuttings in the well is sufficient to cause sticking and drilling difficulties, and the wellbore pressure is less than the formation pressure. Finding the best time to start short is not the best way to improve drilling efficiency and reduce costs. The accumulation of drilling cuttings is related to poor well cleaning effect caused by low return rate of rock cuttings and rock cuttings generated in the drilling process, the return of the rock cuttings is directly related to the migration length of the rock cuttings, the migration length of the rock cuttings is related to the flow rate of drilling fluid, the annular speed and the fluid turbulence state, parameters are controlled to enable the well to be in a dynamic cleaning state all the time, the well cleaning effect is enabled to be optimal all the time, and the drilling is shortened until the rock cuttings which cannot be returned by the annular speed are accumulated to the extent that the drilling sticking is caused or the pressure of a shaft is lower than the formation pressure, so that the method is the optimal method for reducing the short-start times. The methods for cleaning the well and judging the cleaning state of the well are abundant and complete, the research for removing rock debris by short-rise is few, and whether the short-rise is needed or not is basically judged by experience, so that the time for accurately judging the short-rise cannot be realized.
Disclosure of Invention
The invention aims to provide a method for intelligently judging the optimal time of short start of a drilling well, and aims to solve the problem that the time of short start cannot be accurately judged.
In order to achieve the above object, the basic scheme of the invention is as follows: a method for intelligently judging the optimal time of drilling shortstart comprises the following steps:
s01: obtaining logging related parameters related to cuttings accumulation
Performing correlation normalization processing on relevant parameters of each logging to obtain relevant actual measurement parameter values;
s02: establishing a prediction model of normal values of related logging parameters
Obtaining normal values of related logging parameters by using the model;
s03: calculating a fusion deviation value for logging parameters
Comparing the predicted normal values of partial logging parameters with the measured values of relevant actual parameters, and calculating a fusion deviation value deltaSTF；
S04: judging whether a short start is needed
According to the fusion deviation value deltaSTFJudging whether the short start is needed;
s05: evaluation of short onset fruits
And comparing the partial logging parameters after the short start with the normal values of the prediction model, evaluating the short start effect by fusing the deviation degrees, and deleting the parameter measurement abnormal values after the short start.
Further, in S01, the logging related parameters include hook load, hook height, riser pressure, measurement well depth, vertical well depth, drill bit measurement depth, and drill bit vertical depth.
Further, in S02, the established model is a generalized regression neural network model based on a forest optimization algorithm, the model inputs are the measured well depth, the vertical well depth, the drill bit measured depth, and the drill bit vertical depth, and the model outputs are the hook load, the hook height, and the riser pressure.
Further, in S03, after obtaining the normal value and the actual measurement value of the logging parameter, the fusion deviation value Δ is calculated by the following formulaSTF：
DmWeight of hook load, DhWeight of hook height, DpIs the weight of the casing pressure, MfPrediction of normal value for hook load, MaFor actual measurement of hook load, HfPrediction of normal value for hook height, HaFor actual measurement of hook height, PfPredicting a normal value, P, for casing pressureaIs the actual measurement of casing pressure.
Further, in S04, the fusion deviation value is related to the drill cuttings accumulation degree and the wellbore pressure, and can directly reflect the drilling condition, and determine whether the drilling condition needs to be shortened, where the relationship is as follows:
the drilling is safe without short-time lifting;
the annular flow is required to be adjusted, and drilling can be continued;
a short start is required.
Further, in S05, the fusion deviation degree and the short-onset effect are related as follows:
the short-acting fruit is excellent;
short onset of action is better;
short onset and poor effect.
The principle and the beneficial effects of the invention are as follows: (1) in the scheme, the short starting time is judged through the related parameters instead of through experience judgment, and compared with the existing mode, the short starting time is more accurate.
(2) In the scheme, the generalized regression neural network based on the forest optimization algorithm is used for predicting normal values of part of parameters under abnormal conditions, and the abnormal values are deleted after each short start, so that the accuracy of the predicted normal values is ensured;
(3) in the scheme, the bottom hole drilling state can be accurately reflected by calculating the weighted sum of the fusion deviation values of three parameters of hook load, hook height and casing pressure, the fusion deviation values are derived, and whether the short start is needed or not and the annular flow is controlled or not is judged; and finally, judging the effect of the short start by fusing deviation value derivation. Compared with the prior art, the scheme greatly reduces the short-rise times, greatly improves the short-rise efficiency, greatly reduces the drilling cost, and has strong stability and high reaction speed.
Of course, the application does not necessarily require that all of the above-described technical effects be achieved at the same time.
Drawings
FIG. 1 is a flow chart in an embodiment of the invention;
FIG. 2 is a schematic diagram of a short start scenario in an embodiment of the present invention;
FIG. 3 is a short kick logging actual value in an embodiment of the present invention;
FIG. 4 is a short kick prediction value in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
Reference numerals in the drawings of the specification include:drill pipe 1,borehole 2,annulus 3,drill bit 4.
Example (b):
substantially as shown in figure 1: a method for intelligently judging the optimal time of drilling shortstart comprises the following steps:
s01: acquiring logging related parameters related to drill chip accumulation, in the embodiment, as shown in fig. 2, for an actual working condition, anannulus 3 is formed between thedrill rod 1 and thedrill bit 4 and theborehole 2, rock debris is generated in the drilling process, and even if the annulus flow is changed to clean the borehole, larger rock debris is deposited. In this embodiment, the comprehensive logging system is used to collect the measurement well depth, the vertical well depth, the drill bit measurement depth, the drill bit vertical depth, the hook load, the hook height, and the riser pressure parameters related to the accumulation of drill cuttings, and perform correlation normalization processing on the relevant logging parameters to obtain the relevant actual measurement parameters.
S02: establishing a generalized regression neural network model based on a forest optimization algorithm to predict and obtain normal values of related logging parameters, specifically 50000 groups of training data, replacing all measured abnormal data with normal values, and optimizing smooth parameters of the generalized regression neural network through the forest optimization algorithm, so that the prediction accuracy of output parameters is greatly improved, and predicted values of the output parameters are all normal values. In this embodiment, the model inputs are the measured well depth, the vertical well depth, the drill bit measured depth, and the drill bit vertical depth, and the model outputs are the hook load, the hook height, and the riser pressure. As shown in fig. 3 and 4. (A/B/C is respectively vertical pipe pressure, hook load and hook height)
S03: comparing the predicted normal value of the relevant logging parameters with the actual measurement parameters, and calculating a fusion deviation value deltaSTFThe specific calculation method is as follows:
Dmweight of hook load, DhRight of hook heightValue, DpIs the weight of the casing pressure, MfPrediction of normal value for hook load, MaFor actual measurement of hook load, HfPrediction of normal value for hook height, HaFor actual measurement of hook height, PfPredicting a normal value, P, for casing pressureaIs the actual measurement of casing pressure.
S04: according to the fusion deviation value deltaSTFJudging whether the starting is needed to be shortened or not, wherein the relation is as follows:
the drilling is safe without short-time lifting;
the annular flow is required to be adjusted, and drilling can be continued;
a short start is required.
S05: and comparing the related logging parameters after the short start with normal values, and evaluating the short start effect by fusing the deviation degree, wherein the relationship between the fusion deviation degree and the short start effect is as follows:
the short-acting fruit is excellent;
short onset of action is better;
short onset and poor effect.
In summary, the following steps: in the embodiment, the short-time starting opportunity is judged through the related parameters instead of through experience judgment, and compared with the existing mode, the short-time starting opportunity is more accurate.
In the embodiment, the generalized regression neural network based on the forest optimization algorithm is used for predicting normal values of part of parameters under abnormal conditions, and the abnormal values are deleted after each short start, so that the accuracy of the predicted normal values is ensured;
in the embodiment, the bottom hole drilling state can be accurately reflected by calculating the weighted sum of the fusion deviation values of the three parameters of the hook load, the hook height and the casing pressure, the fusion deviation value is derived, and whether the short start is needed or not and the annular flow is controlled or not is judged; and finally, judging the effect of the short start by fusing deviation value derivation. Compared with the prior art, the scheme greatly reduces the number of short-rise times, greatly improves the short-rise efficiency, greatly reduces the drilling cost, and has strong stability and fast reaction speed
The foregoing is merely an example of the present invention and common general knowledge in the art of specific structures and/or features of the invention has not been set forth herein in any way. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (6)
1. A method for intelligently judging the optimal time of drilling short start is characterized in that: the method comprises the following steps:
s01: obtaining logging related parameters related to cuttings accumulation
Performing correlation normalization processing on relevant parameters of each logging to obtain relevant actual parameter measurement values;
s02: establishing a prediction model of normal values of related logging parameters
Obtaining normal values of related logging parameters by using the model;
s03: calculating a fusion deviation value for logging parameters
Comparing the predicted normal values of partial logging parameters with the measured values of relevant actual parameters, and calculating a fusion deviation value deltaSTF；
S04: judging whether a short start is needed
According to the fusion deviation value deltaSTFJudging whether the short start is needed;
s05: evaluation of short onset fruits
And comparing the partial logging parameters after the short start with the normal values of the prediction model, evaluating the short start effect by fusing the deviation degrees, and deleting the parameter measurement abnormal values after the short start.
2. The method for intelligently judging the best time for drilling shortfall according to claim 1, wherein the method comprises the following steps: and in the S01, the logging related parameters comprise hook load, hook height, riser pressure, measurement well depth, vertical well depth, drill bit measurement depth and drill bit vertical depth.
3. The method for intelligently judging the best time for drilling shortfall according to claim 2, wherein the method comprises the following steps: in the S02, the established model is a generalized regression neural network model based on a forest optimization algorithm, the model inputs are the measured well depth, the vertical well depth, the drill bit measured depth and the drill bit vertical depth, and the model outputs are the hook load, the hook height and the riser pressure.
4. The method for intelligently judging the best time for drilling shortfall according to claim 3, wherein the method comprises the following steps: in S03, after the normal value and the actual measured value of the logging parameter are obtained, the fusion deviation value delta is calculated through the following formulaSTF：
DmWeight of hook load, DhWeight of hook height, DpIs the weight of the casing pressure, MfPrediction of normal value for hook load, MaFor actual measurement of hook load, HfPrediction of normal value for hook height, HaFor actual measurement of hook height, PfPredicting a normal value, P, for casing pressureaIs the actual measurement of casing pressure.
5. The method for intelligently judging the best time for drilling shortfall according to claim 4, wherein the method comprises the following steps: in the step S04, the fusion deviation value is related to the accumulation degree of drill cuttings and the wellbore pressure, and can directly reflect the drilling condition, and determine whether the drilling condition needs to be shortened, and the relationship is as follows:
the drilling is safe without short-time lifting;
the annular flow is required to be adjusted, and drilling can be continued;
a short start is required.
6. The method for intelligently judging the best time for drilling shortfall according to claim 5, wherein the method comprises the following steps: in S05, the fusion deviation degree and the short-onset effect are related as follows:
the short-acting fruit is excellent;
short onset of action is better;
short onset and poor effect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111144394.4ACN113868951B (en) | 2021-09-28 | 2021-09-28 | A method for intelligently judging the best time for drilling short start |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111144394.4ACN113868951B (en) | 2021-09-28 | 2021-09-28 | A method for intelligently judging the best time for drilling short start |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113868951Atrue CN113868951A (en) | 2021-12-31 |
| CN113868951B CN113868951B (en) | 2024-12-10 |
Family
ID=78992027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111144394.4AActiveCN113868951B (en) | 2021-09-28 | 2021-09-28 | A method for intelligently judging the best time for drilling short start |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868951B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116008510A (en)* | 2023-01-17 | 2023-04-25 | 中国石油大学(北京) | Intelligent measuring device and method for axial and cross-section distribution of rock debris bed of shaft |
| WO2024072490A1 (en)* | 2022-09-26 | 2024-04-04 | Landmark Graphics Corporation | Pack off indicator for a wellbore operation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104481398A (en)* | 2014-12-10 | 2015-04-01 | 中国石油化工股份有限公司 | Three-dimensional (3D) horizontal well drilling construction method |
| CN110857626A (en)* | 2018-08-14 | 2020-03-03 | 中国石油天然气股份有限公司 | While-drilling pressure prediction method and device based on comprehensive logging parameters and storage medium |
| US20200386066A1 (en)* | 2019-06-06 | 2020-12-10 | Weatherford Technology Holdings, Llc | Drilling System and Method Using Calibrated Pressure Losses |
| EP3833843A1 (en)* | 2019-05-08 | 2021-06-16 | Bentec GmbH Drilling & Oilfield Systems | Onshore drilling rig and method for moving a top drive in a drill mast of an onshore drilling rig |
- 2021
- 2021-09-28CNCN202111144394.4Apatent/CN113868951B/enactiveActive
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104481398A (en)* | 2014-12-10 | 2015-04-01 | 中国石油化工股份有限公司 | Three-dimensional (3D) horizontal well drilling construction method |
| CN110857626A (en)* | 2018-08-14 | 2020-03-03 | 中国石油天然气股份有限公司 | While-drilling pressure prediction method and device based on comprehensive logging parameters and storage medium |
| EP3833843A1 (en)* | 2019-05-08 | 2021-06-16 | Bentec GmbH Drilling & Oilfield Systems | Onshore drilling rig and method for moving a top drive in a drill mast of an onshore drilling rig |
| US20200386066A1 (en)* | 2019-06-06 | 2020-12-10 | Weatherford Technology Holdings, Llc | Drilling System and Method Using Calibrated Pressure Losses |
Non-Patent Citations (1)
| Title |
|---|
| 吴绪虎;袁俊;: "综合录井技术在安全钻井生产中的应用", 价值工程, no. 18, 28 June 2020 (2020-06-28)* |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024072490A1 (en)* | 2022-09-26 | 2024-04-04 | Landmark Graphics Corporation | Pack off indicator for a wellbore operation |
| US12378871B2 (en) | 2022-09-26 | 2025-08-05 | Landmark Graphics Corporation | Pack off indicator for a wellbore operation |
| GB2638569A (en)* | 2022-09-26 | 2025-08-27 | Landmark Graphics Corp | Pack off indicator for a wellbore operation |
| CN116008510A (en)* | 2023-01-17 | 2023-04-25 | 中国石油大学(北京) | Intelligent measuring device and method for axial and cross-section distribution of rock debris bed of shaft |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113868951B (en) | 2024-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105089620B (en) | Monitoring system, the method and device of bit freezing | |
| CN112627733A (en) | Method and equipment for optimizing hydraulic parameters of deepwater pressure-controlled drilling in real time | |
| CN113868951A (en) | A method of intelligently judging the best timing for drilling short trips | |
| CN113062731A (en) | An intelligent identification method for complex working conditions in drilling wells | |
| CN114352255B (en) | Method and device for monitoring state of oil and gas drilling shaft | |
| CN110795853A (en) | Early overflow horizon while-drilling identification method in oil and gas drilling process | |
| CN114444823A (en) | A method and system for predicting lost circulation risk during drilling operations | |
| CN107292754A (en) | A kind of drilling risk forecasting system | |
| CN117035197B (en) | A cost-minimizing intelligent prediction method for lost circulation | |
| WO2019010036A1 (en) | Drilling tubular identification | |
| CN116066062A (en) | A real-time early warning method for stuck pipe based on abnormal diagnosis of parameter variation trend | |
| CN111598366A (en) | Real-time drilling auxiliary decision-making method and system | |
| CN113129157B (en) | A real-time early warning method for downhole stuck drill failures in long water sections of shale gas | |
| CN119914244A (en) | A chip device for integrated control of electric workover rig | |
| CN118653819B (en) | Anti-collision risk control system and method for directional well drilling | |
| CN118861564B (en) | New energy power generation equipment monitoring method and system based on big data | |
| CN107944127A (en) | A kind of definite method of pit mining subsidence parameter flex point offset distance | |
| CN119572208A (en) | Method, device, equipment and medium for monitoring drilling working conditions | |
| CN117588195A (en) | A working condition identification method | |
| CN118423015A (en) | Drilling tripping overflow and leakage identification method and system based on unsupervised learning | |
| CN117077060A (en) | Shale gas well lost circulation early warning method and device, electronic equipment and storage medium | |
| CN111625916A (en) | Method and system for calculating stability value of well wall | |
| CN116411921A (en) | Early warning method and device for drilling tool jamming | |
| CN120235016A (en) | A drilling drill stuck early warning method, device, equipment and readable storage medium | |
| CN118551180B (en) | Horizontal well annulus cuttings concentration prediction method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |