CN117094236B - High-precision calibration method for deep water drilling gas invasion data analysis - Google Patents
High-precision calibration method for deep water drilling gas invasion data analysis Download PDFInfo
- Publication number
- CN117094236B CN117094236B CN202311364026.XA CN202311364026A CN117094236B CN 117094236 B CN117094236 B CN 117094236B CN 202311364026 A CN202311364026 A CN 202311364026A CN 117094236 B CN117094236 B CN 117094236B
- Authority
- CN
- China
- Prior art keywords
- model
- data
- gas invasion
- drilling
- deep water
- 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.)
- Active
Links
- 230000009545 invasion Effects 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000005553 drilling Methods 0.000 title claims abstract description 66
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 34
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 20
- 230000000694 effects Effects 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 10
- 238000002790 cross-validation Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 238000000546 chi-square test Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000012407 engineering method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000009533 lab test Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 3
- 239000007789 gas Substances 0.000 description 62
- 230000006872 improvement Effects 0.000 description 7
- 239000012530 fluid Substances 0.000 description 4
- 239000003208 petroleum Substances 0.000 description 3
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a high-precision calibration method for deep water drilling gas invasion data analysis, which particularly relates to the technical field of deep water drilling, and comprises the following steps of: s1, data acquisition; s2, preprocessing data; s3, data conversion; s4, establishing a gas invasion model; s5, parameter estimation; s6, model verification; s7, calibrating precision; s8, optimizing a model; s9, analyzing results; s10, model application. The invention facilitates better understanding and describing the law and the characteristic of the gas invasion phenomenon, thereby more accurately predicting the occurrence and the change trend of the gas invasion, and can apply the high-precision gas invasion prediction model in the actual drilling process, and timely adjust the drilling parameters and the process by monitoring and early warning the gas invasion process in real time so as to reduce the influence of the gas invasion on the drilling process, improve the drilling efficiency and the safety, and reduce the drilling accidents and the downtime caused by the gas invasion, thereby reducing the drilling cost and the risk.
Description
Technical Field
The invention relates to the technical field of deep water drilling, in particular to a high-precision calibration method for deep water drilling gas invasion data analysis.
Background
Deep water drilling generally refers to offshore operation water depth exceeding 900 meters, industrial common deep water and extreme water depth are distinguished, the extreme water depth refers to water depth greater than 1500 meters, when the existing petroleum reserve exploitation proportion is continuously increased, new petroleum resources are urgent to explore, and the ocean depth is a precious area for petroleum exploitation.
The deep water drilling gas invasion refers to a process that when deep sea petroleum or natural gas drilling operation is carried out, gas in stratum enters into drilling fluid for various reasons, so that the gas and the liquid are mixed together, the phenomenon is common in the deep sea drilling process, but the drilling operation is possibly negatively influenced, so that accurate analysis and response are required, once the deep water drilling gas invasion happens, adverse effects on the drilling operation, such as influencing parameters of the density, viscosity, rheological property and the like of the drilling fluid, damage to normal operation of equipment and possibly pollute marine environment are caused, therefore, effective preventive and response measures are required to be established through analysis and prediction of gas invasion data, the safety and smooth progress of the deep sea drilling operation are ensured, and in the prior art, the analysis of the deep water drilling gas invasion data lacks a high-precision calibration method, so that the occurrence and change trend of the predicted gas invasion are difficult, the efficiency and the safety are influenced, accidents and the downtime caused by the gas invasion are further caused, and the drilling cost and the risk are increased.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a high-precision calibration method for deep water drilling gas invasion data analysis.
In order to achieve the above purpose, the present invention provides the following technical solutions: a high-precision calibration method for deep water drilling gas invasion data analysis comprises the following steps:
s1, data acquisition: collecting gas invasion data in the deepwater drilling process through a sensor and monitoring equipment;
s2, data preprocessing: preprocessing the collected original data;
s3, data conversion: normalizing the preprocessed original data or converting the engineering unit into a more visual physical unit;
s4, establishing a gas invasion model: establishing a mathematical model to describe a gas invasion process according to a gas invasion mechanism of deep water drilling;
s5, parameter estimation: estimating unknown parameters in the model by using historical data and known parameters through a least square method and a maximum likelihood estimation method;
s6, model verification: substituting the estimated parameters into a model, and verifying the model by using residual analysis and fitting goodness test;
s7, precision calibration: performing accuracy calibration on the model by using calibration data from laboratory experiments and field test aspects;
s8, model optimization: optimizing the model according to the calibration result;
s9, analyzing results: analyzing the prediction results of the model, including prediction accuracy and error distribution, to evaluate the performance of the model;
s10, model application: and applying the calibrated model to deep water drilling gas invasion data analysis, and providing support for realizing gas invasion early warning and optimizing a drilling process.
As a further improvement of the technical scheme of the invention, the gas invasion data acquired in the S1 comprises pressure, temperature and flow, and also comprises the steps of acquiring video and audio data of a drilling site and geological and weather information to provide data reference for the subsequent construction of a gas invasion model.
As a further improvement of the technical scheme of the invention, in the step S2, the preprocessing of the original data comprises the steps of removing abnormal values and filling missing values, and meanwhile, the characteristic engineering method of characteristic selection, characteristic extraction and characteristic construction can be adopted to preprocess the original data.
As a further improvement of the technical scheme of the invention, the data conversion in S3 is to convert the original data into a format convenient for analysis, including converting the pressure, temperature and flow data into engineering units.
As a further improvement of the technical scheme of the invention, the gas intrusion model in the S4 can be selected to be based on physics or data, the gas intrusion model is Darcy' S Law, forchheimer Equation and Turbulent Flow Equation, and meanwhile, a machine learning model and a deep learning model can be adopted for the model establishment stage, and the most suitable model can be selected in combination with the actual situation.
As a further improvement of the technical scheme of the invention, the method for calibrating the precision in the S7 comprises the following steps:
a. cross-validation: dividing the data into a training set and a testing set, respectively training and testing, and comparing the predicted result and the actual result of the model;
b. k-fold cross validation: the data are divided into K subsets, training is carried out by using K-1 subsets each time, the rest subset is tested, the test is repeated for K times, and finally, the average predicted result and the actual result of the model are compared.
As a further improvement of the technical scheme of the invention, the optimization method adopted in the step S8 of model optimization comprises the following steps:
a. adjusting model parameters: optimizing parameters in the model by utilizing a linear regression model and a decision tree model, finding an optimal parameter combination to improve the prediction effect of the model, specifically, dividing a data set into a training set and a test set by a cross verification method, searching the optimal parameters on the training set, and then evaluating the prediction effect of the model on the test set;
b. feature selection: selecting features with the greatest influence on the model prediction effect under the condition that a large number of features exist, selecting features based on statistical methods including chi-square test and correlation analysis, and performing feature selection based on machine learning methods including recursive feature elimination and feature importance;
c. and (3) ensemble learning: a plurality of models are fused by adopting a Bagging and Boosting integrated learning method, so that a stronger model is formed to predict the precision and improve the stability.
As a further improvement of the technical scheme of the invention, in the step S9, the analysis result can be intuitively displayed by adopting a visual means including a histogram, a line graph and a thermodynamic diagram in the stage of the analysis of the result; in the S10 model application, in practical application, the model can be deployed to edge equipment or cloud to perform real-time and efficient gas intrusion early warning and analysis.
The invention has the beneficial effects that:
1. through the steps of data acquisition, preprocessing, conversion, modeling, parameter estimation, model verification, precision calibration and the like, a high-precision gas intrusion prediction model can be constructed, and the model can better understand and describe the rules and characteristics of gas intrusion phenomena, so that the occurrence and change trend of gas intrusion can be predicted more accurately;
2. the high-precision gas invasion prediction model can be applied to the actual drilling process through model application, and drilling parameters and processes can be timely adjusted through real-time monitoring and early warning of the gas invasion process, so that the influence of gas invasion on the drilling process is reduced, and the drilling efficiency and safety are improved;
3. by analyzing and predicting the gas invasion data, drilling accidents and downtime caused by gas invasion can be reduced, so that drilling cost and risk are reduced, and meanwhile, a high-precision gas invasion prediction model can help to optimize the formula and the use amount of the drilling fluid, so that the cost of the drilling fluid is reduced;
4. through the high-precision gas invasion prediction model, gas invasion risks can be rapidly and accurately estimated and future trends can be predicted, important reference basis is provided for decision making of drilling engineering, and accordingly decision making efficiency is improved;
5. the gas invasion problem in the deepwater drilling process not only affects the drilling efficiency, but also can pollute the marine environment, and the gas invasion phenomenon can be better managed and controlled through a high-precision gas invasion prediction model, so that the negative influence on the environment is reduced, and the benefit of marine environment protection is improved.
Drawings
FIG. 1 is a flow chart of a high-precision calibration method for deep water drilling gas invasion data analysis.
Detailed Description
The following description will clearly and fully describe the technical solutions of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The high-precision calibration method for deep water drilling gas invasion data analysis shown in the attached figure 1 comprises the following specific steps:
s1, data acquisition: collecting gas invasion data in the deepwater drilling process through a sensor and monitoring equipment;
s2, data preprocessing: preprocessing the collected original data;
s3, data conversion: normalizing the preprocessed original data or converting the engineering unit into a more visual physical unit;
s4, establishing a gas invasion model: establishing a mathematical model to describe a gas invasion process according to a gas invasion mechanism of deep water drilling;
s5, parameter estimation: estimating unknown parameters in the model by using historical data and known parameters through a least square method and a maximum likelihood estimation method;
s6, model verification: substituting the estimated parameters into a model, and verifying the model by using residual analysis and fitting goodness test;
s7, precision calibration: performing accuracy calibration on the model by using calibration data from laboratory experiments and field test aspects;
s8, model optimization: optimizing the model according to the calibration result;
s9, analyzing results: analyzing the prediction results of the model, including prediction accuracy and error distribution, to evaluate the performance of the model;
s10, model application: and applying the calibrated model to deep water drilling gas invasion data analysis, and providing support for realizing gas invasion early warning and optimizing a drilling process.
Preferably, the gas invasion data collected in S1 includes pressure, temperature and flow, and also includes collecting video and audio data of the drilling site, and geological and weather information to provide data reference for the subsequent construction of the gas invasion model.
Preferably, in S2, the preprocessing of the original data includes removing the outlier and filling the missing value, and at the same time, the feature engineering method of feature selection, feature extraction and feature construction can also be used to preprocess the original data.
Preferably, the data conversion in S3 is converting the raw data into a format that facilitates analysis, including converting pressure, temperature and flow data into engineering units.
Preferably, the gas intrusion model in S4 may be selected to be based on physical or data, and the gas intrusion model includes Darcy' S Law, forchheimer Equation and Turbulent Flow Equation, and for the model building stage, a machine learning model and a deep learning model may be adopted, and the best-fit model may be selected in combination with the actual situation.
Preferably, the method for calibrating accuracy in S7 includes:
a. cross-validation: dividing the data into a training set and a testing set, respectively training and testing, and comparing the predicted result and the actual result of the model;
b. k-fold cross validation: the data are divided into K subsets, training is carried out by using K-1 subsets each time, the rest subset is tested, the test is repeated for K times, and finally, the average predicted result and the actual result of the model are compared.
Preferably, in the step S8, the optimization method includes:
a. adjusting model parameters: optimizing parameters in the model by utilizing a linear regression model and a decision tree model, finding an optimal parameter combination to improve the prediction effect of the model, specifically, dividing a data set into a training set and a test set by a cross verification method, searching the optimal parameters on the training set, and then evaluating the prediction effect of the model on the test set;
b. feature selection: selecting features with the greatest influence on the model prediction effect under the condition that a large number of features exist, selecting features based on statistical methods including chi-square test and correlation analysis, and performing feature selection based on machine learning methods including recursive feature elimination and feature importance;
c. and (3) ensemble learning: a plurality of models are fused by adopting a Bagging and Boosting integrated learning method, so that a stronger model is formed to predict the precision and improve the stability.
Preferably, in the step S9, the result analysis may also be visually displayed in a manner of a visualization means including a histogram, a line graph and a thermodynamic diagram in the stage of the result analysis; s10, the model is applied, and in practical application, the model can be deployed to edge equipment or cloud to perform real-time and efficient gas intrusion early warning and analysis.
Working principle: the invention designs a high-precision calibration method for deep water drilling gas invasion data analysis, which comprises the following steps: s1, data acquisition: collecting gas invasion data in the deepwater drilling process through a sensor and monitoring equipment, wherein the collected gas invasion data comprises pressure, temperature and flow, and meanwhile, collecting video and audio data of a drilling site and geological and weather information to provide data reference for a subsequent gas invasion model construction;
s2, data preprocessing: preprocessing the collected original data, wherein the preprocessing of the original data comprises the steps of removing abnormal values and filling missing values, and meanwhile, the original data can be preprocessed by adopting feature engineering methods of feature selection, feature extraction and feature construction;
s3, data conversion: normalizing the preprocessed original data or converting the engineering unit into a more visual physical unit;
s4, establishing a gas invasion model: according to the gas invasion mechanism of deep water drilling, a mathematical model is built to describe the gas invasion process, the gas invasion model can be selected to be based on physics or data, the gas invasion model comprises Darcy's Law, forchheimer Equation and Turbulent Flow Equation, meanwhile, for the model building stage, a machine learning model and a deep learning model can be adopted, and the best-fit model can be selected in combination with the actual situation;
s5, parameter estimation: estimating unknown parameters in the model by using historical data and known parameters through a least square method and a maximum likelihood estimation method;
s6, model verification: substituting the estimated parameters into a model, and verifying the model by using residual analysis and fitting goodness test;
s7, precision calibration: the method for performing precision calibration on the model by using calibration data from laboratory experiments and field test comprises the following steps:
a. cross-validation: dividing the data into a training set and a testing set, respectively training and testing, and comparing the predicted result and the actual result of the model;
b. k-fold cross validation: dividing the data into K subsets, training by using K-1 subsets each time, testing the rest subset, repeating K times, and finally comparing the average predicted result and the actual result of the model;
s8, model optimization: the model is optimized according to the calibration result, and the adopted optimization method comprises the following steps:
a. adjusting model parameters: optimizing parameters in the model by utilizing a linear regression model and a decision tree model, finding an optimal parameter combination to improve the prediction effect of the model, specifically, dividing a data set into a training set and a test set by a cross verification method, searching the optimal parameters on the training set, and then evaluating the prediction effect of the model on the test set;
b. feature selection: selecting features with the greatest influence on the model prediction effect under the condition that a large number of features exist, selecting features based on statistical methods including chi-square test and correlation analysis, and performing feature selection based on machine learning methods including recursive feature elimination and feature importance;
c. and (3) ensemble learning: a plurality of models are fused by adopting a Bagging and Boosting integrated learning method, so that a stronger model is formed to predict the precision and improve the stability;
s9, analyzing results: analyzing the prediction results of the model, including prediction accuracy and error distribution to evaluate the performance of the model, wherein in the result analysis stage, the analysis results can be intuitively displayed in a manner of visualization means including a histogram, a line graph and a thermodynamic diagram;
s10, model application: the calibrated model is applied to deep water drilling gas invasion data analysis, support is provided for gas invasion early warning and optimizing a drilling process, and in practical application, the model can be deployed to edge equipment or cloud to perform real-time and efficient gas invasion early warning and analysis.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A high-precision calibration method for deep water drilling gas invasion data analysis is characterized by comprising the following steps of:
s1, data acquisition: collecting gas invasion data in the deepwater drilling process through a sensor and monitoring equipment;
s2, data preprocessing: preprocessing the collected original data;
s3, data conversion: normalizing the preprocessed original data or converting the engineering unit into a more visual physical unit;
s4, establishing a gas invasion model: establishing a mathematical model to describe a gas invasion process according to a gas invasion mechanism of deep water drilling;
s5, parameter estimation: estimating unknown parameters in the model by using historical data and known parameters through a least square method and a maximum likelihood estimation method;
s6, model verification: substituting the estimated parameters into a model, and verifying the model by using residual analysis and fitting goodness test;
s7, precision calibration: performing accuracy calibration on the model by using calibration data from laboratory experiments and field test aspects;
s8, model optimization: optimizing the model according to the calibration result;
s9, analyzing results: analyzing the prediction results of the model, including prediction accuracy and error distribution, to evaluate the performance of the model;
s10, model application: the calibrated model is applied to deep water drilling gas invasion data analysis, so that support is provided for realizing gas invasion early warning and optimizing a drilling process;
the method for calibrating the precision in the S7 comprises the following steps:
a. cross-validation: dividing the data into a training set and a testing set, respectively training and testing, and comparing the predicted result and the actual result of the model;
b. k-fold cross validation: dividing the data into K subsets, training by using K-1 subsets each time, testing the rest subset, repeating K times, and finally comparing the average predicted result and the actual result of the model;
when the model optimization is performed in the step S8, the adopted optimization method comprises the following steps:
a. adjusting model parameters: optimizing parameters in the model by utilizing a linear regression model and a decision tree model, finding an optimal parameter combination to improve the prediction effect of the model, specifically, dividing a data set into a training set and a test set by a cross verification method, searching the optimal parameters on the training set, and then evaluating the prediction effect of the model on the test set;
b. feature selection: selecting features with the greatest influence on the model prediction effect under the condition that a large number of features exist, selecting features based on statistical methods including chi-square test and correlation analysis, and performing feature selection based on machine learning methods including recursive feature elimination and feature importance;
c. and (3) ensemble learning: a plurality of models are fused by adopting a Bagging and Boosting integrated learning method, so that a stronger model is formed to improve the prediction precision and stability of the model.
2. The high-precision calibration method for deep water drilling gas invasion data analysis according to claim 1, wherein the method comprises the following steps of: the gas invasion data acquired in the step S1 comprises pressure, temperature and flow, and also comprises the steps of acquiring video and audio data of a drilling site and geological and weather information to provide data reference for a gas invasion model of a subsequent component.
3. The high-precision calibration method for deep water drilling gas invasion data analysis according to claim 1, wherein the method comprises the following steps of: in the step S2, the preprocessing of the original data comprises the steps of removing abnormal values and filling missing values, and meanwhile, the original data can be preprocessed by adopting feature engineering methods of feature selection, feature extraction and feature construction.
4. The high-precision calibration method for deep water drilling gas invasion data analysis according to claim 1, wherein the method comprises the following steps of: the data conversion in S3 is to convert the original data into a format convenient for analysis, including converting the pressure, temperature and flow data into engineering units.
5. The high-precision calibration method for deep water drilling gas invasion data analysis according to claim 1, wherein the method comprises the following steps of: the gas intrusion model in the step S4 can be selected to be based on physics or data, and the gas intrusion model is Darcys Law, forchheimer Equation and Turbulent Flow Equation, and meanwhile, a machine learning model and a deep learning model can be adopted for the model establishment stage, and the most suitable model can be selected according to actual conditions.
6. The high-precision calibration method for deep water drilling gas invasion data analysis according to claim 1, wherein the method comprises the following steps of: in the step S9, the result analysis may also be performed visually by using a visualization means including a histogram, a line graph and a thermodynamic diagram in the stage of the result analysis; in the S10 model application, in practical application, the model can be deployed to edge equipment or cloud to perform real-time and efficient gas intrusion early warning and analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311364026.XA CN117094236B (en) | 2023-10-20 | 2023-10-20 | High-precision calibration method for deep water drilling gas invasion data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311364026.XA CN117094236B (en) | 2023-10-20 | 2023-10-20 | High-precision calibration method for deep water drilling gas invasion data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117094236A CN117094236A (en) | 2023-11-21 |
CN117094236B true CN117094236B (en) | 2023-12-26 |
Family
ID=88780271
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311364026.XA Active CN117094236B (en) | 2023-10-20 | 2023-10-20 | High-precision calibration method for deep water drilling gas invasion data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117094236B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9612187B1 (en) * | 2016-09-08 | 2017-04-04 | China University Of Petroleum (East China) | Experimental apparatus for studying gas invasion and migration mechanism in oil and gas wellbores |
CN112483074A (en) * | 2019-09-11 | 2021-03-12 | 中国石油化工股份有限公司 | Method and system for predicting gas invasion phenomenon in drilling process |
CN113323653A (en) * | 2021-06-15 | 2021-08-31 | 中海油研究总院有限责任公司 | Early warning method and device for deep water drilling overflow |
CN113482595A (en) * | 2021-08-04 | 2021-10-08 | 中海石油(中国)有限公司 | Well drilling overflow early warning method, system, equipment and storage medium |
CN116066091A (en) * | 2022-12-26 | 2023-05-05 | 中国石油天然气集团有限公司 | Ocean pressure control drilling experiment simulation device and experimental method thereof |
CN116887211A (en) * | 2023-09-06 | 2023-10-13 | 北京航天华腾科技有限公司 | Low-power consumption system for deep water drilling gas invasion data analysis |
-
2023
- 2023-10-20 CN CN202311364026.XA patent/CN117094236B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9612187B1 (en) * | 2016-09-08 | 2017-04-04 | China University Of Petroleum (East China) | Experimental apparatus for studying gas invasion and migration mechanism in oil and gas wellbores |
CN112483074A (en) * | 2019-09-11 | 2021-03-12 | 中国石油化工股份有限公司 | Method and system for predicting gas invasion phenomenon in drilling process |
CN113323653A (en) * | 2021-06-15 | 2021-08-31 | 中海油研究总院有限责任公司 | Early warning method and device for deep water drilling overflow |
CN113482595A (en) * | 2021-08-04 | 2021-10-08 | 中海石油(中国)有限公司 | Well drilling overflow early warning method, system, equipment and storage medium |
CN116066091A (en) * | 2022-12-26 | 2023-05-05 | 中国石油天然气集团有限公司 | Ocean pressure control drilling experiment simulation device and experimental method thereof |
CN116887211A (en) * | 2023-09-06 | 2023-10-13 | 北京航天华腾科技有限公司 | Low-power consumption system for deep water drilling gas invasion data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN117094236A (en) | 2023-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110781592B (en) | Method and system for predicting residual life of equipment | |
CN110795853B (en) | Early overflow horizon while-drilling identification method in oil and gas drilling process | |
CN115311828B (en) | Intelligent underwater engineering structure detection method and system based on digital twins | |
CN107291667B (en) | Method and system for determining communication degree between wells | |
CN111738371B (en) | Stratum fracture number prediction method based on random forest data mining | |
GB2594187A (en) | Determining reservoir fluid properties from downhole fluid analysis data using machine learning | |
CN114444823A (en) | Method and system for predicting lost circulation risk in drilling operation process | |
CN109902265B (en) | Underground early warning method based on hidden Markov model | |
CN117094236B (en) | High-precision calibration method for deep water drilling gas invasion data analysis | |
CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
CN117236771A (en) | Engineering quality detection and evaluation system and method based on big data technology | |
CN109488290A (en) | Evaluation method and device of the drilling fluid to reservoir damage degree | |
CN114562236B (en) | Geological engineering integrated lost circulation real-time early warning method based on integrated learning model | |
CN111488666A (en) | Gas reservoir horizontal well productivity prediction model establishing and predicting method and device | |
CN113392576B (en) | Method for evaluating and early warning tension state of main mooring rope of tethered balloon | |
CN111985146B (en) | Method and device for determining measure potential well | |
CN112347424A (en) | Method for evaluating safe drilling probability of ultra-high temperature and high pressure development based on Weibull function | |
Fernández Berrocal et al. | Evaluation and Interpretation on Data Driven ROP Models From Engineering Perspectives | |
CN116976146B (en) | Fracturing well yield prediction method and system coupled with physical driving and data driving | |
CN117688681A (en) | Viscous soil non-drainage shear strength estimation method based on pore-pressure static cone penetration test | |
CN112883562B (en) | Ocean platform actual measurement stress spectrum repairing method based on neural network algorithm | |
CN117345194A (en) | Differential pressure stuck probability prediction method and system based on Bayesian belief network | |
CN118278728A (en) | Method and device for predicting well drilling overflow | |
CN118095878A (en) | Oil well blocking removal two-stage well selection method, device, computing equipment and storage medium | |
CN118095813A (en) | Visual monitoring method and system for foundation settlement based on BIM technology |
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 |