CN115929285A - Geothermal gradient prediction method based on Lagrange support vector machine algorithm - Google Patents
Geothermal gradient prediction method based on Lagrange support vector machine algorithm Download PDFInfo
- Publication number
- CN115929285A CN115929285A CN202211409823.0A CN202211409823A CN115929285A CN 115929285 A CN115929285 A CN 115929285A CN 202211409823 A CN202211409823 A CN 202211409823A CN 115929285 A CN115929285 A CN 115929285A
- Authority
- CN
- China
- Prior art keywords
- support vector
- data
- vector machine
- geothermal gradient
- lagrange
- 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
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005553 drilling Methods 0.000 claims abstract description 56
- 239000013598 vector Substances 0.000 claims abstract description 43
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 230000009977 dual effect Effects 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000005065 mining Methods 0.000 claims abstract description 3
- 230000008569 process Effects 0.000 claims description 15
- 230000001172 regenerating effect Effects 0.000 claims description 3
- 235000009508 confectionery Nutrition 0.000 claims description 2
- 238000007418 data mining Methods 0.000 abstract description 8
- 239000003208 petroleum Substances 0.000 abstract description 3
- 230000015572 biosynthetic process Effects 0.000 abstract description 2
- 238000004140 cleaning Methods 0.000 description 10
- 230000009467 reduction Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 4
- 238000013501 data transformation Methods 0.000 description 4
- 239000012530 fluid Substances 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 239000010959 steel Substances 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000003129 oil well Substances 0.000 description 1
- 239000012188 paraffin wax Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/10—Geothermal energy
Abstract
The embodiment of the application provides a geothermal gradient prediction method based on a Lagrange support vector machine algorithm, and belongs to the field of petroleum drilling and the field of data mining. The method comprises the following steps: acquiring historical data and real-time data of a target block, and performing data preprocessing; dividing the preprocessed historical drilling data into a training set and a testing set, and respectively carrying out sample segmentation on the training set and the testing set; generating geothermal gradient parameter vectors, calculating the modes and projection lengths of the parameter vectors, and performing Lagrange dual transformation; generating a geothermal gradient prediction support vector machine sensor model with the accuracy meeting the requirement; and connecting the generated geothermal gradient prediction support vector machine sensor model with the drilling data instant acquisition platform to obtain a model, namely a geothermal gradient prediction model based on a Lagrange support vector machine, and mining the real-time drilling data by using the model so as to achieve the effect of predicting the formation geothermal gradient in real time.
Description
Technical Field
The invention relates to a geothermal gradient prediction method based on a Lagrange support vector machine algorithm, and belongs to the field of petroleum drilling and the field of data mining.
Background
The well drilling is an engineering of drilling a stratum from the surface to the underground into a cylindrical hole with a certain depth by using mechanical equipment and related technologies, the oil well drilling is a drilling engineering aiming at finding hydrocarbon substances such as oil, natural gas and the like, the well drilling has irreplaceable important roles in the development of the oil and natural gas industry, and the exploration and development of the well drilling cannot be carried out.
In the drilling process, the geothermal gradient is an important parameter influencing the performance of the drilling fluid, the prediction precision of the geothermal gradient directly determines the temperature condition of thousands of meters under a stratum, and the accuracy of the stratum temperature directly influence the plastic viscosity, dynamic shear force, n value, k value and other important parameters of the drilling fluid in the stratum drilling process, so that the performance effects of the drilling fluid on cleaning a shaft, balancing the stratum pressure, transmitting hydraulic power and the like are directly influenced, and finally the production stagnation of the whole petroleum drilling construction is caused.
The current method for predicting the geothermal gradient in China mainly comprises a steel wire well testing technology: the instrument is installed into the lubricator through the steel wire, the steel wire is placed into the pulley groove through the well testing pulley, and the measuring instrument is controlled to go into the well, so that the purpose of measuring the ground temperature gradient is achieved. Although the method has the advantages of good measurement precision, complex operation, not only needs an independent steel wire car to go to a well for treatment, but also needs a professional to perform complex operation, the anti-bouncing pin and the paraffin removal gate can not ensure the smooth entering of the instrument, and more importantly, each stratum needs to be tested once, so that a large amount of labor and material cost is increased for drilling construction.
Disclosure of Invention
Aiming at the defects of the geothermal gradient prediction method in the prior art, the invention aims to provide the geothermal gradient prediction method based on the Lagrange support vector machine algorithm.
Specifically, the invention is realized by adopting the following technical scheme, which comprises the following steps:
1) Collecting relevant historical drilling data, historical geothermal gradient predicted true values and real-time drilling data of the target block, and performing data preprocessing;
2) Dividing the preprocessed historical drilling data into a training set and a testing set, and respectively carrying out sample segmentation on the training set and the testing set;
3) Expressing various parameters related to the geothermal gradient in a vector form to generate parameter vectors, calculating the modes of the parameter vectors and the data projection lengths of other vectors, and performing Lagrange dual transformation;
4) Generating a new sensor model according to the obtained mode of the parameter vector, the projection length and the Lagrange dual transformation result, wherein the model is a Lagrange support vector machine geothermal gradient prediction sensor model, testing the Lagrange support vector machine geothermal gradient prediction sensor model through the data of the test set, and regenerating the Lagrange support vector machine geothermal gradient prediction sensor model if the test result does not meet the precision requirement until the precision requirement is met;
5) And connecting the finally generated geothermal gradient prediction support vector machine sensor model meeting the precision requirement with the drilling data instant acquisition platform to obtain a model, namely a support vector machine prediction model based on a Lagrange support vector machine, and mining the real-time drilling data by using the model so as to achieve the effect of predicting the geothermal gradient in the stratum in real time.
The technical scheme is further characterized in that in the step 1), the data preprocessing process comprises cleaning, filling, transforming and dimensionality reduction, and the specific process comprises the following steps:
1-1) cleaning data, namely judging noise data in the drilling historical data by using a least square method, and then deleting irrelevant data, repeated data and noise data in an original data set of the drilling historical data;
1-2) data complementation, namely complementing various types of data deleted in the data cleaning process by using a Lagrange interpolation method so as to ensure the integrity of the data;
1-3) data transformation is to carry out standardization processing on drilling history data and convert the drilling history data into a form suitable for data mining;
1-4) data dimension reduction is to carry out dimension reduction processing on drilling historical data, so that the drilling historical data is easier to classify and mine by a support vector machine algorithm;
the above technical solution is further characterized in that in step 2), the training set and the test set are respectively subjected to sample segmentation, and the specific process is as follows:
2-1) setting the functions of the two support vectors as wx + b =1 and wx + b = -1 respectively;
wherein x is an unknown number, and w and b are respectively the data projection slope and intercept of the preprocessed historical drilling data in two dimensions;
2-2) respectively carrying out sample segmentation on the training set and the test set according to the function straight line of the two support vectors;
compared with other existing geothermal gradient detection methods, the method has the advantages that the defects that the existing method is limited by complex geological environment and is high in cost are overcome, the result of predicting the geothermal gradient in real time is achieved by data mining on historical drilling data of the target block and establishing a geothermal gradient prediction model based on a Lagrange support vector machine algorithm, the geothermal gradients at different depths and different positions can be judged according to the result, and therefore a low-cost and high-quality auxiliary decision-making effect is provided for drilling engineering.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a block diagram of data processing;
FIG. 2 is a flow chart of a geothermal gradient prediction method based on a Lagrange support vector machine algorithm;
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a data processing block diagram in the technical solution of the present invention, and as can be seen from fig. 1, the preprocessing content includes data cleaning, data gap filling, data transformation, and data dimension reduction, where the data cleaning is to delete irrelevant data and repeated data in the original data set of the drilling history data, smooth noise data, and simultaneously screen out data irrelevant to drilling fluid leaking layer position prediction; the data filling is to fill the collected drilling history data missing values and the missing values after the data cleaning by using a Lagrange interpolation method; the data transformation is to convert the parameters of the formation lithology and the drill bit type in the data information, which are expressed by characters, into a digital form which can be used for data mining by using a single-hot coding method; data dimension reduction is to reduce the multidimensional disordered data such as the well drilling historical data to the dimension which is easier to classify and mine by a support vector machine algorithm.
Fig. 2 is a flowchart of a geothermal gradient prediction method based on the lagrangian support vector machine algorithm, and as can be seen from fig. 2, the specific implementation steps of the geothermal gradient prediction method based on the lagrangian support vector machine algorithm of the present invention are as follows:
1) Collecting related historical drilling data, historical geothermal gradient predicted true values and real-time drilling data of the target block, and performing data preprocessing;
2) Dividing the preprocessed historical drilling data into a training set and a testing set, and respectively carrying out sample segmentation on the training set and the testing set;
3) Expressing various parameters related to the geothermal gradient in a vector form to generate parameter vectors, calculating the modes of the parameter vectors and the data projection lengths of other vectors, and performing Lagrange dual transformation;
4) Generating a new sensor model according to the obtained mode of the parameter vector, the projection length and the Lagrange dual transformation result, wherein the model is a Lagrange support vector machine geothermal gradient prediction sensor model, testing the Lagrange support vector machine geothermal gradient prediction sensor model through the data of the test set, and regenerating the Lagrange support vector machine geothermal gradient prediction sensor model if the test result does not meet the precision requirement until the precision requirement is met;
5) And connecting the finally generated geothermal gradient prediction support vector machine sensor model meeting the precision requirement with a drilling data instant acquisition platform to obtain a model, namely a support vector machine prediction model based on a Lagrange support vector machine, and performing data mining on real-time drilling data by using the model so as to achieve the effect of real-time prediction of the geothermal gradient of the stratum.
The technical scheme is further characterized in that in the step 1), the data preprocessing process comprises cleaning, filling, transforming and dimensionality reduction, and the specific process comprises the following steps:
1-1) cleaning data, namely judging noise data in the drilling historical data by using a least square method, and then deleting irrelevant data, repeated data and noise data in an original data set of the drilling historical data;
1-2) data filling, namely filling various types of data deleted in the data cleaning process by using a Lagrange interpolation method so as to ensure the integrity of the data;
1-3) the data transformation is to carry out standardization processing on the drilling history data and convert the drilling history data into a form suitable for data mining;
1-4) data dimension reduction is to carry out dimension reduction processing on drilling historical data, so that the drilling historical data is easier to classify and mine by a support vector machine algorithm;
the above technical solution is further characterized in that in step 2), the training set and the test set are respectively subjected to sample segmentation, and the specific process is as follows:
2-1) setting the functions of the two support vectors as wx + b =1 and wx + b = -1 respectively;
wherein x is an unknown number, and w and b are respectively the data projection slope and intercept of the preprocessed historical drilling data in two dimensions;
2-2) respectively carrying out sample segmentation on the training set and the test set according to the function straight line of the two support vectors;
the above technical solution is further characterized in that in step 3), the modes of the parameter vectors and the data projection lengths of other vectors are calculated, and lagrangian dual transformation is performed, and the specific process is as follows:
3-1) obtaining the maximum value of the distance d between the two support vectors through the formula (1);
3-2) converting the maximum value of the distance d obtained in 3-1) into the minimum value problem, i.e. obtaining min | | w | | sweet hair 2 |；
3-3) whether the function of the support vector is wx + b =1 or wx + b = -1, all parameters may be divided into points inside the function and points outside the function, i.e., equation (2) is satisfied for points on the support vector and equation (3) is satisfied for points not on the support vector;
y (i) (w T x (i) +b)＝1 (2)
y (i) (w T x (i) +b)≥1 (3)
3-4) constructing the distance problem of all the parameter points and the support vector into a Lagrange function through Lagrange transformation, namely, the distance problem is shown in an equation (4);
wherein: alpha is a parameter vector of single parameter input;
the above technical solution is further characterized in that, in the step 4), a new sensor model is generated according to the obtained mode of the parameter vector, the projection length and the lagrangian dual transformation result, and the model is a lagrangian support vector machine geothermal gradient prediction sensor model, and the specific process is as follows:
4-1) converting the functions of the two support vectors into convex functions, and constructing a KKT condition to obtain a formula (5);
4-2) bringing w into the original problem of Lagrangiation can be given by equation (6);
4-3) obtaining the optimal solution law through quadratic programming problem must have the optimal solution alpha * So that it satisfies alpha * ＝(α 1 ，…，α 1 ) Therefore, a support vector machine training formula (7) and a prediction formula (8) after the training are obtained;
and 4-4) carrying out KKT condition constraint on the support vector machine operation result obtained by the formula (8) through a formula (5), and obtaining a final ground temperature gradient prediction sensor model of the Lagrange support vector machine.
Compared with other existing geothermal gradient prediction methods, the method has the advantages that the defects that the existing method is limited by complex geological environment and is high in cost are overcome, the result of predicting the geothermal gradient in real time is achieved by data mining on historical drilling data of the target block and establishing a geothermal gradient prediction model based on a Lagrange support vector machine algorithm, the geothermal gradients at different depths and different positions can be judged according to the result, and therefore a low-cost and high-quality auxiliary decision-making effect is provided for drilling engineering.
The above specific technical solutions are only used to illustrate the present invention, but not to limit it; although the present invention has been described in detail with reference to the specific embodiments thereof, it will be appreciated by those skilled in the art that the invention is not limited thereto. The present invention may be modified and equivalents may be substituted for some of the features described above without departing from the spirit and scope of the present invention.
Claims (4)
1. A geothermal gradient prediction method based on a Lagrange support vector machine algorithm is characterized by comprising the following steps:
1) Collecting related historical drilling data, historical geothermal gradient predicted true values and real-time drilling data of the target block, and performing data preprocessing;
2) Dividing the preprocessed historical drilling data into a training set and a testing set, and respectively carrying out sample segmentation on the training set and the testing set;
3) Expressing various parameters related to the geothermal gradient in a vector mode to generate parameter vectors, calculating modes of the parameter vectors and data projection lengths of other vectors, and performing Lagrange dual transformation;
4) Generating a new sensor model according to the obtained mode of the parameter vector, the projection length and the Lagrange dual transformation result, wherein the model is a Lagrange support vector machine geothermal gradient prediction sensor model, testing the Lagrange support vector machine geothermal gradient prediction sensor model through the data of the test set, and regenerating the Lagrange support vector machine geothermal gradient prediction sensor model if the test result does not meet the precision requirement until the precision requirement is met;
5) And connecting the finally generated geothermal gradient prediction support vector machine sensor model meeting the precision requirement with the drilling data instant acquisition platform to obtain a model, namely a support vector machine prediction model based on a Lagrange support vector machine, and mining the real-time drilling data by using the model so as to achieve the effect of predicting the geothermal gradient in the stratum in real time.
2. The method for predicting the geothermal gradient based on the Lagrange support vector machine algorithm according to claim 1, wherein in step 2), the training set and the test set respectively perform sample segmentation, and the specific process is as follows:
2-1) setting the functions of the two support vectors as wx + b =1 and wx + b = -1 respectively;
wherein x is an unknown number, and w and b are respectively the data projection slope and intercept of the preprocessed historical drilling data in two dimensions;
2-2) respectively carrying out sample segmentation on the training set and the test set according to the function straight line of the two support vectors.
3. The method for predicting the geothermal gradient based on the lagrangian support vector machine algorithm according to claim 1, wherein in step 3) of the method, the modes of the parameter vectors and the data projection lengths of other vectors are calculated, and lagrangian dual transformation is performed, and the specific process is as follows:
3-1) obtaining the maximum value of the distance d between the two support vectors by the formula (1);
3-2) converting the maximum value of the distance d obtained in 3-1) into the minimum value problem, i.e. obtaining min | | w | | sweet hair 2 |；
3-3) whether the function of the support vector is wx + b =1 or wx + b = -1, all parameters may be divided into points inside the function and points outside the function, i.e., equation (2) is satisfied for points on the support vector and equation (3) is satisfied for points not on the support vector;
y (i) (w T x (i) +b)＝1 (2)
y (i) (w T x (i) +b)≥1 (3)
3-4) constructing the distance problem of all the parameter points and the support vector into a Lagrange function through Lagrange transformation, namely, the distance problem is shown in an equation (4);
wherein: alpha is a parameter vector of a single parameter input.
4. The method for predicting the geothermal gradient based on the lagrangian support vector machine algorithm according to claim 1, wherein a new sensor model is generated according to the obtained model of the parameter vector, the projection length and the lagrangian dual transformation result in step 4) of the method, and the model is the lagrangian support vector machine geothermal gradient prediction sensor model, and the specific process is as follows:
4-1) converting the functions of the two support vectors into convex functions, and constructing a KKT condition to obtain a formula (5);
4-2) bringing w into the original problem of Lagrangiation can be given by equation (6);
4-3) byThe optimal solution law of the quadratic programming problem can be obtained by certain existence of the optimal solution alpha, so that the optimal solution alpha satisfies alpha = (alpha) 1 ，…，α 1 ) Therefore, a support vector machine training formula (7) and a prediction formula (8) after the training are obtained;
-y (i) (w T x (i) +b)+1＝0 (7)
and 4-4) carrying out KKT condition constraint on the support vector machine operation result obtained by the formula (8) through a formula (5) to obtain a final Lagrange support vector machine geothermal gradient prediction sensor model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211409823.0A CN115929285A (en) | 2022-11-11 | 2022-11-11 | Geothermal gradient prediction method based on Lagrange support vector machine algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211409823.0A CN115929285A (en) | 2022-11-11 | 2022-11-11 | Geothermal gradient prediction method based on Lagrange support vector machine algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115929285A true CN115929285A (en) | 2023-04-07 |
Family
ID=86653156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211409823.0A Pending CN115929285A (en) | 2022-11-11 | 2022-11-11 | Geothermal gradient prediction method based on Lagrange support vector machine algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115929285A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030101161A1 (en) * | 2001-11-28 | 2003-05-29 | Bruce Ferguson | System and method for historical database training of support vector machines |
| CA2632230A1 (en) * | 2005-11-26 | 2007-05-31 | Gene Security Network, Inc. | System and method for cleaning noisy genetic data and using genetic, phentoypic and clinical data to make predictions |
| US20070282766A1 (en) * | 2006-05-05 | 2007-12-06 | Pavilion Technologies, Inc. | Training a support vector machine with process constraints |
| AU2011221435A1 (en) * | 2010-09-01 | 2012-03-15 | The University Of Sydney | System and method for terrain analysis |
| WO2012163972A1 (en) * | 2011-05-31 | 2012-12-06 | Avl List Gmbh | Machine-implemented method for obtaining data from a nonlinear dynamic real system during a test run |
| CN108510111A (en) * | 2018-03-14 | 2018-09-07 | 中国石油大学(北京) | A kind of method and device of prediction annular space supercharging |
| US20190129063A1 (en) * | 2016-04-30 | 2019-05-02 | Scientific Drilling International, Inc. | Method for wellbore survey instrument fault detection |
| CN110845659A (en) * | 2019-11-15 | 2020-02-28 | 西南石油大学 | Preparation and evaluation method of polymer nanoparticles for drilling fluid |
| US20200183046A1 (en) * | 2018-12-11 | 2020-06-11 | Exxonmobil Research And Engineering Company | Subsurface models with uncertainty quantification |
| CN111767323A (en) * | 2020-09-02 | 2020-10-13 | 西南石油大学 | Method for predicting length of stratum fracture in real time based on kernel SMO algorithm |
| US20200364623A1 (en) * | 2019-05-13 | 2020-11-19 | Saudi Arabian Oil Company | Calcium carbonate scale prediction and inhibition in hydrocarbon wells using machine learning |
| CN112949186A (en) * | 2021-03-05 | 2021-06-11 | 西南石油大学 | Method for predicting wax precipitation point temperature of wax-containing crude oil based on SSA-LSSVM model |
| GB202108326D0 (en) * | 2020-07-15 | 2021-07-28 | Landmark Graphics Corp | High floworate formation tester |
| CN115293066A (en) * | 2022-08-09 | 2022-11-04 | 西南石油大学 | Gas well temperature field calculation method considering stratum seepage heat transfer effect |
-
2022
- 2022-11-11 CN CN202211409823.0A patent/CN115929285A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030101161A1 (en) * | 2001-11-28 | 2003-05-29 | Bruce Ferguson | System and method for historical database training of support vector machines |
| CA2632230A1 (en) * | 2005-11-26 | 2007-05-31 | Gene Security Network, Inc. | System and method for cleaning noisy genetic data and using genetic, phentoypic and clinical data to make predictions |
| US20070282766A1 (en) * | 2006-05-05 | 2007-12-06 | Pavilion Technologies, Inc. | Training a support vector machine with process constraints |
| AU2011221435A1 (en) * | 2010-09-01 | 2012-03-15 | The University Of Sydney | System and method for terrain analysis |
| WO2012163972A1 (en) * | 2011-05-31 | 2012-12-06 | Avl List Gmbh | Machine-implemented method for obtaining data from a nonlinear dynamic real system during a test run |
| US20190129063A1 (en) * | 2016-04-30 | 2019-05-02 | Scientific Drilling International, Inc. | Method for wellbore survey instrument fault detection |
| CN108510111A (en) * | 2018-03-14 | 2018-09-07 | 中国石油大学(北京) | A kind of method and device of prediction annular space supercharging |
| US20200183046A1 (en) * | 2018-12-11 | 2020-06-11 | Exxonmobil Research And Engineering Company | Subsurface models with uncertainty quantification |
| US20200364623A1 (en) * | 2019-05-13 | 2020-11-19 | Saudi Arabian Oil Company | Calcium carbonate scale prediction and inhibition in hydrocarbon wells using machine learning |
| CN110845659A (en) * | 2019-11-15 | 2020-02-28 | 西南石油大学 | Preparation and evaluation method of polymer nanoparticles for drilling fluid |
| GB202108326D0 (en) * | 2020-07-15 | 2021-07-28 | Landmark Graphics Corp | High floworate formation tester |
| CN111767323A (en) * | 2020-09-02 | 2020-10-13 | 西南石油大学 | Method for predicting length of stratum fracture in real time based on kernel SMO algorithm |
| CN112949186A (en) * | 2021-03-05 | 2021-06-11 | 西南石油大学 | Method for predicting wax precipitation point temperature of wax-containing crude oil based on SSA-LSSVM model |
| CN115293066A (en) * | 2022-08-09 | 2022-11-04 | 西南石油大学 | Gas well temperature field calculation method considering stratum seepage heat transfer effect |
Non-Patent Citations (3)
| Title |
|---|
| 左富银;苏俊霖;黄进军;李立宗;赵洋;秦祖海: "泥页岩微裂缝微观封堵模拟", 化学世界, no. 012, 31 December 2020 (2020-12-31), pages 822 - 828 * |
| 张博;胡旭光;刘贵义;李宜君;孙伟峰;戴永寿: "面向早期溢流监测的钻井工程参数仿真建模方法", 录井工程, vol. 30, no. 004, 31 December 2019 (2019-12-31), pages 44 - 51 * |
| 李红冀;蒲晓林;赵黎丽;王贵;苏俊林: "基于支持向量机的水基钻井液配方优化设计", 计算机与应用化学, vol. 31, no. 007, 28 July 2014 (2014-07-28), pages 787 - 791 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875122B (en) | Artificial intelligence method and system for calculating geological parameters by using logging-while-drilling data | |
| US8490693B2 (en) | Determining fracture orientation using wellbore acoustic radial profiles | |
| Moosavi et al. | Auto-characterization of naturally fractured reservoirs drilled by horizontal well using multi-output least squares support vector regression | |
| CN111665560B (en) | Hydrocarbon reservoir identification method, apparatus, computer device and readable storage medium | |
| CN103026202A (en) | Method for obtaining consistent and integrated physical properties of porous media | |
| WO2021008630A1 (en) | Method, apparatus, and system for quantitative analysis of sealing strength of trap fault | |
| KR102170765B1 (en) | Method for creating a shale gas production forecasting model using deep learning | |
| CN110162851B (en) | Cable formation test pumping numerical simulation and numerical correction method of process thereof | |
| Song et al. | Potential for vertical heterogeneity prediction in reservoir basing on machine learning methods | |
| CN116291271A (en) | Rock-soil body parameter inversion method and system based on while-drilling test | |
| CN114066084B (en) | Method and system for predicting phase permeation curve based on machine learning | |
| Qin et al. | Predicting pore-water pressure in front of a TBM using a deep learning approach | |
| Taipova et al. | Verifying reserves opportunities with multi-well pressure pulse-code testing | |
| CN113486539A (en) | Method for analyzing uncertainty of formation pressure in whole deep water drilling process | |
| LIANG et al. | Stratum identification based on multiple drilling parameters and probability classification | |
| CN115929285A (en) | Geothermal gradient prediction method based on Lagrange support vector machine algorithm | |
| CN111767323B (en) | Method for predicting length of stratum fracture in real time based on kernel SMO algorithm | |
| CN112285773B (en) | Quantitative characterization method for binary structure of buried fault | |
| CN113534248A (en) | Method, device and system for quantitatively analyzing closure of trap fault | |
| Zhao et al. | Pore-scale hydraulic properties of virtual sandstone microstructures: spatial variations and voxel scale effects | |
| CN111663935B (en) | Method and system for evaluating annular air tightness of shaft | |
| Chen et al. | GINI coefficient: An effective way to evaluate inflow profile equilibrium of horizontal wells in Shengli Oil Field | |
| Roy et al. | The modern interpretation of the high-flow gas wells study results | |
| Nath et al. | Prediction and analysis of geomechanical properties using deep learning: A Permian Basin case study | |
| CN114912340B (en) | Shale gas preservation condition quantitative determination method oriented to multi-source information fusion |
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 |