CN117668453A - FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method - Google Patents
FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method Download PDFInfo
- Publication number
- CN117668453A CN117668453A CN202311620844.1A CN202311620844A CN117668453A CN 117668453 A CN117668453 A CN 117668453A CN 202311620844 A CN202311620844 A CN 202311620844A CN 117668453 A CN117668453 A CN 117668453A
- Authority
- CN
- China
- Prior art keywords
- well
- data
- instability
- risk
- tree
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005553 drilling Methods 0.000 claims abstract description 80
- 238000013500 data storage Methods 0.000 claims abstract description 20
- 238000007418 data mining Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012502 risk assessment Methods 0.000 claims abstract description 6
- 230000002265 prevention Effects 0.000 claims abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims abstract description 3
- 239000012530 fluid Substances 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 239000003208 petroleum Substances 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a system and a method for predicting and assisting decision-making of a well wall instability risk based on FP-growth, which belong to the field of data mining and the field of petroleum drilling. Wherein the system comprises: the system comprises a well history data storage module, a well Shi Shuju processing module, a well instability risk FP tree growing module, a well instability risk data mining module, a well instability risk assessment module and a well instability auxiliary decision making module. The beneficial technical effects of the invention are as follows: the invention provides a system and a method for predicting and assisting decision-making of a well instability risk based on FP-growth, wherein the possibility of the well instability of the well section is obtained through the prediction of the well instability risk prediction system based on FP-growth, and reasonable advice is provided according to the magnitude change of abnormal parameters when a well instability accident occurs in the same block, so that the advanced prediction and prevention and control of the well instability are achieved, and a more accurate and effective decision-making basis can be provided for drilling technicians based on the judgment basis, so that the efficiency of drilling operation is improved.
Description
Technical Field
The invention relates to a system and a method for predicting and assisting decision-making of a well instability risk based on FP-growth, and belongs to the fields of data mining and petroleum drilling.
Background
Along with the improvement of development technology, the exploration and exploitation of oil and gas resources gradually develop towards the ultra-deep oil and gas direction, and the safe and efficient drilling construction is ensured to have important significance for developing the ultra-deep oil and gas resources. However, the underground accident typified by the instability of the well wall is always one of the core problems affecting safe and efficient drilling and is also a technical problem of worldwide drilling engineering. The instability of the well wall can cause great difficulty to the drilling engineering, and the problems are mainly manifested by shrinkage, collapse, stuck drilling, borehole expansion and the like, and the accidents not only lead to the extension of the drilling period, but also greatly increase the drilling cost. Because the research of the stability of the stratum well wall is very complex, and a plurality of systems such as drilling engineering, geology, rock mechanics and the like are involved, the research result has a plurality of disputes and problems due to the high complexity of the problems.
At present, students at home and abroad mainly deal with the problem of instability of the well wall from three aspects of experimental test, mathematical model calculation and on-site drilling fluid adjustment. Great variability often occurs in the results of laboratory tests because the laboratory cannot fully simulate the actual state of various rocks in the formation. When the problem of instability of the well wall is analyzed by using a mathematical model, the damage condition of the well shaft cannot be intuitively simulated due to complex geological conditions, unknown stress conditions, temperature change in the well and the like. In the drilling process, the problem of instability of the well wall is often treated by adjusting construction parameters such as drilling fluid density and the like, and the stratum condition is deduced mainly by experience in the mode, so that the method is difficult to popularize and has great risk. Therefore, it is necessary to build a system for predicting risk of borehole instability in combination with field actual data.
Disclosure of Invention
Aiming at the defects of a real-time prediction method for the well wall instability risk of an oil-gas well in the prior art, the invention aims to provide a well wall instability risk prediction system and a well wall instability risk prediction method based on FP-growth, the system can combine data which are generated in the well drilling process of well drilling data, well logging data, well drilling fluid data, well logging data and the like and are easy to obtain, the well wall instability risk is predicted in real time for each well site of different areas by taking the area as a unit, and the performance of the well drilling fluid is adjusted according to the prediction result, so that the accident rate of the well wall instability is reduced.
In order to achieve the above object, the present invention is realized by the following technical scheme:
a well instability risk prediction system based on FP-growth comprises a well history data storage module, a well Shi Shuju processing module, a well instability risk FP tree growing module, a well instability risk data mining module, a well instability risk assessment module and a well instability auxiliary decision-making module.
A FP-growth based risk prediction system for wellbore instability, the system comprising:
the well history data storage module is mainly used for classifying and importing a large amount of data of different sources such as drilling data, logging data, drilling fluid data, logging data and the like into a database according to geological blocks, so that partial data loss caused by confusion of a data storage format is avoided, actually measured data generated by on-site drilling is imported into a single table, and besides, all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs are stored into the database in a form of decision codes.
The well Shi Shuju processing module is used for preprocessing well history data, firstly setting input parameters corresponding to drilling data to be trained, combining the data of the same well in different modes, and respectively preprocessing the data according to each parameter attribute of the drilling data. The data preprocessing method comprises data cleaning, data integration and data conversion. If the data source system is complete and has no noise, the data conversion processing is directly carried out.
The above technical solution is further characterized in that the requirement must be closely related to the risk of instability of the well wall when setting the input parameters corresponding to the well Shi Shuju to be trained, and the specific parameters include: well depth, horizon, lithology, bit type, bit size, hook load, weight on bit, torque, rotational speed, rate of drilling, vertical weight, flow, drilling fluid density, drilling fluid viscosity, ten second shear, ten shear, drilling fluid type, three-turn reading, one hundred-turn reading.
And the well instability risk FP tree growth module is used for sorting all the well history data in the form of elements so as to generate all the element items according to different well Shi Shuju parameters, traversing all the data elements stored in the well history data storage module twice, finding out the occurrence frequency of each element item respectively, determining frequent items, taking the first element in the frequent items as a root node, and judging whether each element is a child node of the root node one by one or not, so that an FP tree is generated and grows gradually until all the elements are in the frequent items.
The system comprises a well instability risk data mining module, a well instability risk data storage module and a well history data processing module, wherein the well instability risk data mining module is used for arranging frequent items generated in the well instability risk FP tree growth module to generate a condition mode base, the condition mode base is used as input data, a condition FP tree is created through a method of creating the FP tree, other element items are circulated to find out more and larger frequent item sets, branches and leaves of the condition FP tree are enlarged, actual measurement data generated by on-site drilling in the well history data storage module are input into the condition FP tree, and a well instability risk real-time prediction output result is generated.
The well instability risk assessment module analyzes the output result of the well instability risk data mining module, judges the possibility of the well section to generate well instability, and derives the possibility to a system interface.
The borehole instability auxiliary decision-making module is used for comparing and analyzing the drilling parameter instance and the borehole instability risk real-time prediction output result when the borehole instability accident occurs, judging which specific parameters are suggested to be adjusted in the next step, and exporting the specific parameters to the system interface in a comparison table mode.
A well wall instability risk prediction method based on FP-growth comprises the following steps:
step S1: collecting well history data and on-site drilling actual measurement data, respectively storing the data into a database according to geological blocks, and storing all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs into the database in the form of decision codes;
step S2: setting input parameters corresponding to drilling data to be trained, and respectively preprocessing the data aiming at each parameter attribute of the drilling data, wherein the data preprocessing method comprises data cleaning, data integration and data conversion;
step S3: arranging each well Shi Shuju into the form of an element, finding frequent items from all data elements of the well history data, generating an FP tree by using the elements in the frequent items as nodes and gradually growing until all the elements are in the frequent items;
step S4: generating a condition pattern base by using frequent items in the FP tree, creating a condition FP tree by taking the condition pattern base as a base, gradually expanding branches and leaves of the condition FP tree, inputting field drilling actual measurement data into the condition FP tree, and generating a real-time prediction output result of the risk of the well instability;
step S5: analyzing the real-time prediction output result of the risk of the well instability, judging the possibility of the well instability of the well section, giving corresponding reasonable suggestions on the premise of referring to successful instances of the well stability, and optimizing and selecting the most suitable parameter adjustment decision code according to the well instability accidents of different conditions so as to better help on-site drilling operators to make auxiliary decisions.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a data processing block diagram;
FIG. 2 is a workflow diagram of a well wall instability risk prediction and decision-making aid system;
figure 3 is a flow chart of a method for predicting and assisting decision-making of the well wall instability risk.
Detailed Description
In order to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
FIG. 1 is a block diagram of data preprocessing in the technical scheme of the present invention, and as can be seen from FIG. 1, the data processing content includes data cleaning, integration and conversion, wherein the data cleaning content mainly includes a data deficiency method and a noise data smoothing technology; the data integration content mainly comprises entity identification and matching, redundancy and related analysis and tuple repeated data monitoring; the data conversion content is mainly normalized for data.
Fig. 2 is a workflow diagram of a system for predicting risk of instability of well wall, as can be seen from fig. 2, the system for predicting risk of instability of well wall based on FP-growth of the present invention comprises: the system comprises a well history data storage module, a well Shi Shuju processing module, a well instability risk FP tree growing module, a well instability risk data mining module, a well instability risk assessment module and a well instability auxiliary decision making module.
A FP-growth based risk prediction system for wellbore instability, the system comprising:
1) The well history data storage module is mainly used for classifying and importing a large amount of data of different sources such as drilling data, logging data, drilling fluid data, logging data and the like into a database according to geological blocks, so that partial data loss caused by confusion of a data storage format is avoided, actually measured data generated by on-site drilling is imported into a single table, and besides, all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs are stored into the database in a form of decision codes.
2) The well Shi Shuju processing module is used for preprocessing well history data, firstly setting input parameters corresponding to drilling data to be trained, combining the data of the same well in different modes, and respectively preprocessing the data according to each parameter attribute of the drilling data. The data preprocessing method comprises data cleaning, data integration and data conversion. If the data source system is complete and has no noise, the data conversion processing is directly carried out.
The above technical solution is further characterized in that the requirement must be closely related to the risk of instability of the well wall when setting the input parameters corresponding to the well Shi Shuju to be trained, and the specific parameters include: well depth, horizon, lithology, bit type, bit size, hook load, weight on bit, torque, rotational speed, rate of drilling, vertical weight, flow, drilling fluid density, drilling fluid viscosity, ten second shear, ten shear, drilling fluid type, three-turn reading, one hundred-turn reading.
3) And the well instability risk FP tree growth module is used for sorting all the well history data in the form of elements so as to generate all the element items according to different well Shi Shuju parameters, traversing all the data elements stored in the well history data storage module twice, finding out the occurrence frequency of each element item respectively, determining frequent items, taking the first element in the frequent items as a root node, and judging whether each element is a child node of the root node one by one or not, so that an FP tree is generated and grows gradually until all the elements are in the frequent items.
The technical scheme is further characterized in that the specific method for generating the well instability risk FP tree in the well instability risk FP tree growth module comprises the following steps:
3-1) sorting all the well history data in the well history data storage module in the form of elements, creating a dictionary type head pointer table, and storing the total number of each type of elements and pointers pointing to the first element item of each type of elements by taking the well Shi Shuju parameters as units, so that all the elements of a given type in the FP tree can be quickly accessed by using the head pointer table;
3-2) traversing the well Shi Shuju for the first time to obtain the occurrence frequency of each element item, storing the occurrence frequency in a head pointer table, then traversing the head pointer table, setting the minimum support degree to be 20%, and removing elements which do not meet the minimum support degree;
3-3) traversing the dataset a second time, considering only those frequent items. Extracting frequent items of element items corresponding to each parameter as transactions, ordering the frequent items in a descending order, and constructing a well instability risk FP tree by using the ordered frequent items, wherein the well instability risk FP tree is filled with one transaction by one transaction;
3-4) for each transaction, looking up if the first element exists as a child node of the root node, if so, increasing the count, if not, building a new child node, and updating the pointer of the element of the head pointer table;
3-5) if the pointer is None, indicating that the element first appears, pointing the pointer to the node element, if the pointer is not None, indicating that the element has appeared under other child nodes, if the child node is the root node for the first time, pointing the pointer to the tail along the linked list, and pointing the tail node pointer to the new node here;
3-6) after each transaction is completed on the first element, repeating 3-4) and 3-5) to sequentially add the following elements into the well instability risk FP tree according to the method, so that the well instability risk FP tree gradually grows up, and finally, the well instability risk FP tree becomes a data mining model containing a large amount of well history data.
4) The system comprises a well instability risk data mining module, a well instability risk data storage module and a well instability risk data prediction output module, wherein the well instability risk data mining module is used for arranging frequent items generated in a well instability risk FP tree growth module to generate a condition mode base, the condition mode base is used as input data, a condition FP tree is created by a method of creating the FP tree, other element items are circulated to find more and larger frequent item sets, branches and leaves of the well instability risk condition FP tree are enlarged, actual measurement data generated by on-site drilling in the well history data storage module are input into the well instability risk condition FP tree, and the well instability risk real-time prediction output result is generated.
The technical scheme is further characterized in that the specific method for creating the well wall instability risk condition FP tree is as follows:
4-1) starting from a single element of the first frequent set, ending with the searched element item, and recording the searched prefix path, namely all contents between the searched element item and the tree root node of the well instability risk FP tree, wherein the set of the prefix path is a conditional mode base;
4-2) using a condition mode base as input data, generating a well instability risk condition FP tree again by a method for generating the well instability risk FP tree, and creating a well instability risk condition FP tree for each frequent item.
5) The well instability risk assessment module analyzes the output result of the well instability risk data mining module, judges the possibility of the well section to generate well instability, and derives the possibility to a system interface.
6) The borehole instability auxiliary decision-making module is used for comparing and analyzing the drilling parameter instance and the borehole instability risk real-time prediction output result when the borehole instability accident occurs, judging which parameters are suggested to be adjusted in the next step, and exporting the parameters to the system interface in a comparison table mode.
The invention is further characterized in that the possibility of the well section to generate the well instability is obtained through the prediction of the well instability risk prediction system based on the FP-growth, and reasonable suggestions are provided according to the magnitude change of abnormal parameters when the well instability accident occurs in the same block, such as the increase of the viscosity of a drilling fluid hopper, the reduction of the drilling pressure and the like, so that the advance prediction and prevention and the control of the well instability are achieved, and more accurate and effective decision basis can be provided for drilling technicians and constructors by taking the probability as the judgment basis, so that the efficiency of drilling operation is improved.
Fig. 3 shows a flowchart of a method for predicting the risk of well instability based on FP-growth, which comprises the following steps:
step S1: collecting well history data and on-site drilling actual measurement data, respectively storing the data into a database according to geological blocks, and storing all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs into the database in the form of decision codes;
step S2: setting input parameters corresponding to drilling data to be trained, and respectively preprocessing the data aiming at each parameter attribute of the drilling data, wherein the data preprocessing method comprises data cleaning, data integration and data conversion;
step S3: arranging each well Shi Shuju into the form of an element, finding frequent items from all data elements of the well history data, generating an FP tree by using the elements in the frequent items as nodes and gradually growing until all the elements are in the frequent items;
step S4: generating a condition pattern base by using frequent items in the FP tree, creating a condition FP tree by taking the condition pattern base as a base, gradually expanding branches and leaves of the condition FP tree, inputting field drilling actual measurement data into the condition FP tree, and generating a real-time prediction output result of the risk of the well instability;
step S5: analyzing the real-time prediction output result of the risk of the well instability, judging the possibility of the well instability of the well section, giving corresponding reasonable suggestions on the premise of referring to successful instances of the well stability, and optimizing and selecting the most suitable parameter adjustment decision code according to the well instability accidents of different conditions so as to better help on-site drilling operators to make auxiliary decisions.
The above embodiments are only for illustrating the present invention, and not for limiting the same; although the invention has been described in detail with reference to the specific embodiments described above, it will be appreciated by those of ordinary skill in the art. The present invention may be modified or substituted for some of the features described above, without departing from the spirit and scope of the invention.
Claims (3)
1. A FP-growth based risk prediction system for wellbore instability, the system comprising:
1) The well history data storage module is mainly used for classifying and importing a large amount of data of different sources such as drilling data, logging data, drilling fluid data, logging data and the like into a database according to geological blocks, so that partial data loss caused by confusion of a data storage format is avoided, actually measured data generated by on-site drilling is imported into a single table, and in addition, all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs are stored into the database in a form of decision codes;
2) The well Shi Shuju processing module is used for preprocessing well history data, firstly setting input parameters corresponding to drilling data to be trained, combining the data of the same well in different modes, and respectively preprocessing data according to various parameter attributes of the drilling data; the data preprocessing method comprises data cleaning, data integration and data conversion; if the data source system is complete and has no noise point, directly performing data conversion processing;
the above technical solution is further characterized in that the requirement must be closely related to the risk of instability of the well wall when setting the input parameters corresponding to the well Shi Shuju to be trained, and the specific parameters include: well depth, horizon, lithology, bit type, bit size, hook load, weight on bit, torque, rotational speed, rate of drilling, vertical pressure, flow, drilling fluid density, drilling fluid viscosity, ten second shear force, ten shear force, drilling fluid type, three-turn reading, one-hundred-turn reading;
3) The well instability risk FP tree growth module is used for sorting all the well history data in the form of elements so as to generate all the element items according to different well Shi Shuju parameters, traversing all the data elements of the data stored in the well history data storage module twice, finding out the occurrence frequency of each element item respectively so as to determine frequent items, taking the first element in the frequent items as a root node, judging whether each element is a child node of the root node one by one, and generating an FP tree and growing gradually until all the elements are in the frequent items;
the technical scheme is further characterized in that the specific method for generating the well instability risk FP tree in the well instability risk FP tree growth module comprises the following steps:
3-1) sorting all the well history data in the well history data storage module in the form of elements, creating a dictionary type head pointer table, and storing the total number of each type of elements and pointers pointing to the first element item of each type of elements by taking the well Shi Shuju parameters as units, so that all the elements of a given type in the FP tree can be quickly accessed by using the head pointer table;
3-2) traversing the well Shi Shuju for the first time to obtain the occurrence frequency of each element item, storing the occurrence frequency in a head pointer table, then traversing the head pointer table, setting the minimum support degree to be 20%, and removing elements which do not meet the minimum support degree;
3-3) traversing the dataset a second time, considering only those frequent items; extracting frequent items of element items corresponding to each parameter as transactions, ordering the frequent items in a descending order, and constructing a well instability risk FP tree by using the ordered frequent items, wherein the well instability risk FP tree is filled with one transaction by one transaction;
3-4) for each transaction, looking up if the first element exists as a child node of the root node, if so, increasing the count, if not, building a new child node, and updating the pointer of the element of the head pointer table;
3-5) if the pointer is None, indicating that the element first appears, pointing the pointer to the node element, if the pointer is not None, indicating that the element has appeared under other child nodes, if the child node is the root node for the first time, pointing the pointer to the tail along the linked list, and pointing the tail node pointer to the new node here;
3-6) after each transaction is finished with the first element, repeating the steps 3-4) and 3-5) to sequentially add the following elements into the well instability risk FP tree according to the method, so that the well instability risk FP tree gradually grows up, and finally, a data mining model containing a large amount of well history data is formed;
4) The system comprises a well instability risk data mining module, a well instability risk data storage module and a well instability risk data prediction output module, wherein the well instability risk data mining module is used for arranging frequent items generated in a well instability risk FP tree growth module to generate a condition mode base, taking the condition mode base as input data, creating a condition FP tree by a method of creating the FP tree, circulating other element items to find more and larger frequent item sets, so that branches and leaves of the well instability risk condition FP tree are enlarged, and inputting actual measurement data generated by on-site drilling in the well history data storage module into the well instability risk condition FP tree to generate a well instability risk real-time prediction output result;
the technical scheme is further characterized in that the specific method for creating the well wall instability risk condition FP tree is as follows:
4-1) starting from a single element of the first frequent set, ending with the searched element item, and recording the searched prefix path, namely all contents between the searched element item and the tree root node of the well instability risk FP tree, wherein the set of the prefix path is a conditional mode base;
4-2) using a condition mode base as input data, generating a well instability risk condition FP tree again by a method for generating the well instability risk FP tree, and creating a well instability risk condition FP tree for each frequent item;
5) The well wall instability risk assessment module analyzes the output result of the well wall instability risk data mining module, judges the possibility of the well wall instability of the well section and exports the possibility to a system interface;
6) The borehole instability auxiliary decision-making module is used for comparing and analyzing the drilling parameter instance and the borehole instability risk real-time prediction output result when the borehole instability accident occurs, judging which parameters are suggested to be adjusted in the next step, and exporting the parameters to the system interface in a comparison table mode.
2. The FP-growth based risk prediction system for well instability according to claim 1, wherein the process of the system for predicting the risk of well instability and making an auxiliary decision is as follows:
the possibility of the well section to generate the well instability is obtained through the prediction of the well instability risk prediction system based on the FP-growth, and reasonable suggestions are provided according to the magnitude change of abnormal parameters when the well instability accident occurs in the same block, such as increasing the viscosity of a drilling fluid hopper, reducing the weight on bit and the like, so that the pre-prediction and prevention of the well instability are achieved, and more accurate and effective decision-making basis can be provided for drilling technicians and constructors based on the pre-prediction and prevention of the well instability, so that the efficiency of drilling operation is improved.
3. A well wall instability risk prediction method flow chart based on FP-growth comprises the following steps:
step S1: collecting well history data and on-site drilling actual measurement data, respectively storing the data into a database according to geological blocks, and storing all collected drilling parameter examples and parameter adjustment conditions when a well instability accident occurs into the database in the form of decision codes;
step S2: setting input parameters corresponding to drilling data to be trained, and respectively preprocessing the data aiming at each parameter attribute of the drilling data, wherein the data preprocessing method comprises data cleaning, data integration and data conversion;
step S3: arranging each well Shi Shuju into the form of an element, finding frequent items from all data elements of the well history data, generating an FP tree by using the elements in the frequent items as nodes and gradually growing until all the elements are in the frequent items;
step S4: generating a condition pattern base by using frequent items in the FP tree, creating a condition FP tree by taking the condition pattern base as a base, gradually expanding branches and leaves of the condition FP tree, inputting field drilling actual measurement data into the condition FP tree, and generating a real-time prediction output result of the risk of the well instability;
step S5: analyzing the real-time prediction output result of the risk of the well instability, judging the possibility of the well instability of the well section, giving corresponding reasonable suggestions on the premise of referring to successful instances of the well stability, and optimizing and selecting the most suitable parameter adjustment decision code according to the well instability accidents of different conditions so as to better help on-site drilling operators to make auxiliary decisions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311620844.1A CN117668453A (en) | 2023-11-30 | 2023-11-30 | FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311620844.1A CN117668453A (en) | 2023-11-30 | 2023-11-30 | FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117668453A true CN117668453A (en) | 2024-03-08 |
Family
ID=90070716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311620844.1A Pending CN117668453A (en) | 2023-11-30 | 2023-11-30 | FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117668453A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150354336A1 (en) * | 2014-06-05 | 2015-12-10 | Sas Institute Inc. | Control parameter determination in steam assisted gravity drainage oil drilling |
| CN109858147A (en) * | 2019-01-30 | 2019-06-07 | 西南石油大学 | A kind of borehole well instability quantifying risk evaluation method based on Reliability Theory |
| CN111291097A (en) * | 2020-05-08 | 2020-06-16 | 西南石油大学 | Drilling leaking layer position real-time prediction method based on decision tree data mining |
| CN111738620A (en) * | 2020-07-17 | 2020-10-02 | 西南石油大学 | Well leakage risk prediction and leakage stoppage decision system and method based on association rules |
| CN113073959A (en) * | 2021-02-24 | 2021-07-06 | 西南石油大学 | Drilling well loss mechanism prediction and auxiliary decision method based on fuzzy decision tree |
| CN114836178A (en) * | 2021-02-01 | 2022-08-02 | 中国石油天然气股份有限公司 | Water-based drilling fluid composition and water-based drilling fluid |
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
| CN115438090A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics |
| CN116296848A (en) * | 2023-03-21 | 2023-06-23 | 中国科学院武汉岩土力学研究所 | Evaluation method for stability of broken belt well wall |
-
2023
- 2023-11-30 CN CN202311620844.1A patent/CN117668453A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150354336A1 (en) * | 2014-06-05 | 2015-12-10 | Sas Institute Inc. | Control parameter determination in steam assisted gravity drainage oil drilling |
| CN109858147A (en) * | 2019-01-30 | 2019-06-07 | 西南石油大学 | A kind of borehole well instability quantifying risk evaluation method based on Reliability Theory |
| CN111291097A (en) * | 2020-05-08 | 2020-06-16 | 西南石油大学 | Drilling leaking layer position real-time prediction method based on decision tree data mining |
| CN111738620A (en) * | 2020-07-17 | 2020-10-02 | 西南石油大学 | Well leakage risk prediction and leakage stoppage decision system and method based on association rules |
| CN114836178A (en) * | 2021-02-01 | 2022-08-02 | 中国石油天然气股份有限公司 | Water-based drilling fluid composition and water-based drilling fluid |
| CN113073959A (en) * | 2021-02-24 | 2021-07-06 | 西南石油大学 | Drilling well loss mechanism prediction and auxiliary decision method based on fuzzy decision tree |
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
| CN115438090A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics |
| CN116296848A (en) * | 2023-03-21 | 2023-06-23 | 中国科学院武汉岩土力学研究所 | Evaluation method for stability of broken belt well wall |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1984860B1 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| US8504341B2 (en) | Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| CN108388921B (en) | Overflow loss real-time identification method based on random forest | |
| AU2007211294B2 (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator | |
| CN112308269A (en) | Yield prediction method and device for low-permeability oil and gas reservoir | |
| CN111738371B (en) | Stratum fracture number prediction method based on random forest data mining | |
| CN114117881A (en) | Sand production risk prediction method and system | |
| CN115438823A (en) | Borehole wall instability mechanism analysis and prediction method and system | |
| CN115586086A (en) | Borehole wall instability analysis method based on big data | |
| CN113326661B (en) | RS-XGboost-based tunnel advanced drilling quantitative interpretation method and device | |
| WO2019023255A1 (en) | Developing oilfield models using cognitive computing | |
| CN114117654A (en) | Horizontal well perforation optimization design method and device based on machine learning | |
| CN115438090A (en) | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics | |
| Song et al. | Classifying the surrounding rock of tunnel face using machine learning | |
| CN117668453A (en) | FP-growth-based well wall instability risk prediction and auxiliary decision-making system and method | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass | |
| CN113887049A (en) | Drilling speed prediction method and system for petroleum drilling based on machine learning | |
| CN114077861A (en) | Method and system for identifying lithology in real time in drilling process | |
| CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
| Chen et al. | Machine Learning Based Shale Gas Proration Synchronized Computing Method | |
| Wan et al. | Intelligent prediction of drilling rate of penetration based on method-data dual validity analysis | |
| CN115169760B (en) | Method and device for optimizing coal bed gas and coal coordinated development mode and electronic equipment | |
| CN118313234A (en) | Gas well gas-liquid two-phase mouth flow prediction method based on cascade forward neural network | |
| Poteriailo et al. | Data optimization for the knowledge bases in the oil and gas Monitoring-While-Drilling (MWD) Systems | |
| Carpenter | Machine-Learning Approach Optimizes Well Spacing |
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 |