CN110806859A - Modular drilling data monitoring and design system based on machine learning - Google Patents
Modular drilling data monitoring and design system based on machine learning Download PDFInfo
- Publication number
- CN110806859A CN110806859A CN201911092500.1A CN201911092500A CN110806859A CN 110806859 A CN110806859 A CN 110806859A CN 201911092500 A CN201911092500 A CN 201911092500A CN 110806859 A CN110806859 A CN 110806859A
- Authority
- CN
- China
- Prior art keywords
- drilling
- module
- unit
- design
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/20—Software design
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention relates to a modular drilling data monitoring and designing system based on machine learning, which is provided with a service unit and a management unit which are connected through signals, wherein the service unit comprises a drilling data monitoring unit, a machine learning unit and a drilling design unit which are connected, and data in the drilling data monitoring unit is acquired on a local platform and is monitored and stored on a cloud platform; the machine learning unit and the drilling design unit are arranged on the cloud platform; the management unit comprises an interaction unit for inputting and outputting system data, a user unit for managing user permission and user information and a control unit for controlling the system, wherein the interaction unit, the user unit and the control unit are connected through data streams of signals. The invention can realize accurate design before construction, and analyze and prejudge according to drilling data through a machine learning algorithm.
Description
Technical Field
The invention relates to a monitoring and designing system, in particular to a machine learning-based modular drilling data monitoring and designing system of a cloud platform.
Background
In the geological exploration and development process, the design before drilling construction, the pre-judgment of the drilling condition in the drilling process, the analysis of the drilling machine condition, the analysis and the treatment aiming at specific accidents or problems and the data arrangement after the drilling is finished are all of great importance to the whole drilling engineering and even the drilling industry. If reasonable design is not available before construction and timely analysis and judgment are not available in construction, the probability of accidents occurring in the construction process is greatly increased, and a large amount of time and economic loss can be caused by treatment after the accidents occur.
In the prior publication, the document with patent application No. CN201810967591.8 (a drilling rig intelligent control system) describes the acquisition and analysis of drilling rig data by a cloud platform, wherein the acquired data is focused on the planning of the drilling rig position and the calculation of the movement path.
The document with patent application number CN201810831354.9 (a geological big data platform for urban planning and construction) relates to a cloud platform and data monitoring uploading, but its main purpose is to monitor relevant contents for urban geology and climate, and does not relate to drilling relevant contents.
In a paper, "cloud computing-based geological big data mining connotation", a concept of geological big data mining is proposed, and relates to a structure of a geological data platform, but the structure focuses more on collection and analysis of existing geological data, and is not data collection and analysis in the drilling field, and the platform is based on analysis of the existing data and does not relate to related concepts of new data transmission and machine learning.
In summary, no parameter design and analysis data platform architecture mainly aiming at the drilling field for guiding the drilling operation exists at present. The drilling system of the existing intelligent drilling machine is mainly focused on a single machine version, namely, monitoring equipment is installed on the existing drilling machine, and parameter recommendation is carried out according to a fixed program or algorithm after data monitoring. This mode can achieve better results for an incident or pattern that has occurred (formation/drilling parameter combination/drilling equipment/drilling tool combination, etc.), but does not give an accurate prediction for a pattern that has not occurred at all. Most of the existing geological cloud systems aim at geological data, disaster data, climate data and the like, and do not have cloud processing and analyzing systems aiming at drilling engineering data. Moreover, although the existing intelligent cloud system has a machine learning function, most machine learning algorithms are inherent algorithms trained according to existing data, and cannot give more accurate prejudgment when facing a new scene.
Disclosure of Invention
The invention provides a machine learning-based modular drilling data monitoring and designing system, which realizes accurate design before construction and accurate monitoring and analysis in the construction process, and analyzes and prejudges drilling engineering data through a machine learning algorithm.
The invention relates to a modular drilling data monitoring and designing system based on machine learning, which is provided with a service unit and a management unit which are connected through signals, wherein the service unit comprises a drilling data monitoring unit, a machine learning unit and a drilling design unit, the drilling data monitoring unit is used for acquiring, monitoring and storing drilling engineering data, the machine learning unit is used for training and storing a current drilling working condition recognition algorithm according to the drilling engineering data, the drilling design unit is used for designing processes and parameters of a drilling engineering to be constructed, the machine learning unit is also used for storing a drilling parameter recommendation algorithm in the drilling design unit, the acquisition of the drilling engineering data in the drilling data monitoring unit is realized on a local platform, and the monitoring and storing are realized on a cloud platform; the machine learning unit and the drilling design unit are both arranged in the cloud platform; the design system stores various data modules and design modules in the cloud platform, and a user can select a proper design module to design according to design requirements. The design system automatically calls the machine learning unit stored in the cloud platform to perform relevant recommendation calculation according to the user requirements in the design process.
The system comprises a cloud platform, a management unit, an interaction unit, a user unit and a control unit, wherein the cloud platform is arranged on the management unit, the management unit is used for monitoring the system and comprises an interaction unit for inputting and outputting system data, the user unit for managing user authority and user information and the control unit for controlling the system, and the interaction unit, the user unit and the control unit are connected through data streams of signals.
Aiming at the defects of the prior art, after relevant data of drilling construction is collected locally, the strong computing power of a cloud platform is utilized to analyze the data so as to guide the drilling construction design and operation. Moreover, data can be continuously updated through the setting of the network cloud platform, and the problem of inaccurate prediction caused by a new scene can be avoided through continuous analysis and learning. Moreover, the self-learning machine learning unit can automatically run in a database continuously supplemented with new data, so that the learning algorithm is continuously perfected, and the accuracy of final analysis and judgment is effectively improved.
The invention is not limited to a specific algorithm, but the whole system architecture can involve some needed algorithms and processing modes in the system operation, and the algorithms can be carried in the system development process or uploaded by a user in the system using process. For example, drilling engineering data including but not limited to key data such as bit pressure, torque, pump capacity, pump pressure, rotating speed and the like are collected through a drilling data monitoring unit and stored in a cloud platform, then a machine learning unit reads various drilling engineering data stored in the drilling data monitoring unit from the cloud platform when analyzing and recommending the current drilling working condition, the data are introduced into related algorithms, condition descriptions such as drilling speed prediction, accident prediction, drilling tool damage prediction and the like are predicted through the algorithms, different predictions are given through different algorithms, the recognition of the current drilling working condition is realized after all predictions are integrated, and recommendation of related drilling tools, equipment combinations, drilling schemes and the like is carried out according to the current drilling working condition.
Specifically, in the drilling data monitoring unit of business unit, have collection module and the transmission module of locating local platform, collection module will be to drilling engineering data transmission to the storage module of locating the high in the clouds platform through the transmission module after local drilling engineering data acquisition, and storage module still is connected with the security module, the check-up module and the query module of locating the high in the clouds platform respectively. The safety module is used for maintaining data safety in the storage module, defending against invasion of external factors to data and guaranteeing accuracy of the data, the verification module checks integrity and accuracy of data uploaded by a user according to set verification rules and evaluates data value, and the query module queries and obtains relevant information from the storage module according to requirements of the user or a system.
Furthermore, a training module respectively connected with the monitoring analysis module and the design analysis module is arranged in a machine learning unit of the service unit, wherein the monitoring analysis module inquires drilling engineering data from the drilling data monitoring unit according to user requirements and carries out reasoning analysis to obtain corresponding current working condition information; the design analysis module carries out analysis and calculation of drilling design according to the current working condition information, the design module selected by the user and the filled data; the training module trains the monitoring analysis module and the design analysis module regularly according to the updated drilling engineering data, and the analysis accuracy of the two analysis modules is improved. The algorithms involved in the service unit may be self-carried in the system development process, and also can be uploaded by the user in the system use process, and the algorithms can adopt the existing method, which is not the innovation of the invention.
In the prior art in the field, the applied algorithms are analyzed and judged according to the inherent modes, but in the actual engineering process, new and unseen modes can appear in different environments, including unseen strata, drilling parameter combinations, drilling equipment, drilling tool combinations and the like. While algorithms derived from the natural modes derive with limited accuracy for these modes. In the system, because the data sharing is carried out on the cloud platform and the machine learning algorithm setting is automatically updated according to the data volume, the data volume of the system is continuously increased, the probability of the occurrence of a brand-new and unseen mode is greatly reduced, and the accuracy of the final calculation result is also greatly improved.
Furthermore, a basic information module for data sharing, a well body structure module, an equipment selection module, a drilling tool combination module, a drilling fluid module, a parameter design module, a well cementation design module, a well completion design module, an accident prevention module, a construction organization module, a progress control module and a budget control module are arranged in the drilling design unit, and each module is responsible for different aspects of design. The basic information module is responsible for designing basic information of the drilling hole, such as drilling hole coordinates, surrounding environment, drilling hole requirements and the like; the well structure module is responsible for recommending and calculating a well structure diagram of the planned drilling hole and a necessary casing structure diagram; the equipment selection module is used for selecting drilling equipment which can be used on site, such as a drilling machine, a derrick, a slurry pump and the like; the drilling tool combination module is used for selecting drilling tools which can be used on site, such as drilling tools of a drill bit, a drill rod, a drill collar, a stabilizer and the like, and carrying out recommendation calculation on the arrangement positions of the corresponding drilling tools; the drilling fluid module is used for selecting a possibly applicable drilling fluid formula on site and carrying out recommendation calculation on the corresponding drilling fluid performance; the parameter design module is responsible for combining the selected drilling tool and drilling fluid recommendation and calculating the applicable drilling engineering parameters; the well cementation design module is responsible for completing the recommendation calculation of corresponding formulas and parameters of well cementation equipment, well cementation fluid and the like; the well completion design module is responsible for carrying out recommendation calculation of corresponding well completion equipment and construction processes; the accident prevention module is responsible for carrying out possible accident prediction and design selection of a corresponding accident prevention scheme; the construction organization module is responsible for construction organization design, including construction equipment, flow, personnel, process and other related organization design; the progress control module is responsible for designing a construction progress chart and a control scheme; the budget control module is responsible for calculating the related construction cost in the design and intelligently conducts corresponding construction budget recommendation analysis.
Furthermore, an input/output module for interacting various data, a display module respectively connected with the input/output module, and an instruction analysis module for splitting a user input instruction into system executable instructions are arranged in the interaction unit of the management unit.
Furthermore, in the user unit of the management unit, a production user module and a use user module are respectively arranged according to users with different authorities. The users with production authority can provide new drilling engineering parameters, related design data or related machine learning algorithms, machine recommendation algorithms and the like to the system through the production user module, and the users with use authority can only use the related data in the system and cannot perform addition, deletion and modification operations.
Furthermore, a flow control module for opening or closing other modules according to user operation and a status analysis module for analyzing the operation status of the system are arranged in the control unit of the management unit.
The beneficial effects of the invention include:
(1) machine learning based drilling engineering data analysis: when a user uses the system, the system automatically calls functions of the machine learning unit, such as calculation parameters, model selection recommendation and the like, and carries out recommendation design by an artificial intelligent machine learning algorithm. According to the functional design of the system, the data analysis related to the drilling engineering data in the monitoring process mainly comprises the steps of identifying the current working condition, carrying out relevant calculation deduction according to the monitored parameters, and judging whether the current working condition is normal or not. If the working state is normal, drilling parameter recommendation can be carried out, and whether drilling parameters (such as key parameters including torque, weight on bit, pump capacity and the like) can be adjusted or not is calculated, so that more efficient drilling work is realized; if the working state is abnormal, predicting possible construction accidents, such as: stuck, broken, burned, etc., and drilling parameter recommendations that need to be adjusted to avoid accidents (e.g., critical parameters such as torque, weight on bit, pump rate, etc.). The data analysis involved in the drilling engineering data design process mainly consists in the relevant calculation of key parameters (such as well body structure, drilling tool usage, drilling fluid formulation, engineering parameter design, etc.) in the drilling design process.
(2) Designing a system structure based on modularization: the system is based on a modular concept in both design and use links. The modular design concept makes the system built more flexible, and also provides convenient conditions for updating and improving the system in later period, only corresponding modules need to be correspondingly added, deleted and adjusted, and the functions of other modules are not affected. For example, in terms of the function of drilling data monitoring, the modular design enables a user to select necessary monitoring modules and related accident early warning analysis algorithms according to needs, thereby being more beneficial to the personalized use of the user and improving the use efficiency of the user; and like the drilling construction design function, the modularized structure can enable a user to select a proper module for design according to the requirement, can more pointedly calculate and analyze a specific module, effectively improves the use efficiency of the user, and simultaneously improves the wide adaptability of the system.
(3) Open data and algorithm sharing mode: the data analysis and drilling construction design of the system of the present invention is based on drilling engineering data and corresponding algorithms. Sharing of drilling data and algorithms is a necessary function. The invention adopts a modularization concept, provides a standard uploading interface of drilling engineering data and algorithms, and a user can upload the data or the algorithms to the system only by ensuring that the interface of the data or the algorithms is correct when selecting an uploading mode, and the system automatically realizes modularized storage after uploading. After the data and the algorithm of the standard interface are uploaded to the system, a subsequent user can select the data or the algorithm module to serve the construction monitoring or construction design content of the user when using the system.
(4) Automated machine learning training based on updated data: besides the original algorithm of the system and the algorithm uploaded by the user, the system can monitor the data volume in the database in real time, automatically perform a training module of a machine learning unit when the data volume is increased to a certain degree, and train the machine learning analysis recommendation algorithm in the system. After training is started, the system still adopts the original algorithm for calculation before training is finished, the original algorithm is automatically reserved as an alternative after training is finished, the new algorithm is recommended by default, and a user can select the new algorithm according to own experience or needs.
Therefore, in conclusion, the method can analyze the collected drilling construction related data to guide drilling construction design and operation, continuously update the drilling engineering data through the setting of the network cloud platform, continuously analyze and learn to avoid the problem of inaccurate prediction caused by a new scene, continuously improve the learning algorithm according to continuously supplemented new data through self-learning machine learning, and effectively improve the accuracy of analysis and judgment.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. Various substitutions and alterations according to the general knowledge and conventional practice in the art are intended to be included within the scope of the present invention without departing from the technical spirit of the present invention as described above.
Drawings
FIG. 1 is a block diagram of a machine learning based modular drilling data monitoring and design system of the present invention.
Fig. 2 is a system architecture diagram of the present invention.
Detailed Description
The invention relates to a modular drilling data monitoring and designing system based on machine learning, which is provided with a service unit and a management unit connected through signals, and is shown in figure 1. The service unit comprises a drilling data monitoring unit, a machine learning unit and a drilling design unit, wherein the drilling data monitoring unit is used for collecting drilling working condition data, the machine learning unit is used for learning and storing corresponding algorithms, and the drilling design unit is used for presetting design of drilling engineering.
And the drilling data monitoring unit in the service unit is used for acquiring, monitoring and storing the drilling engineering data. The drilling data monitoring unit is provided with an acquisition module and a transmission module which are arranged on a local platform. The acquisition module acquires local drilling engineering data including but not limited to key data such as bit pressure, torque, pump capacity, pump pressure, rotating speed and the like, and stores the data in a storage module of the cloud-end platform through the transmission module. The storage module is further connected with a security module, a verification module and a query module which are arranged on the cloud platform respectively. The safety module is used for maintaining data safety in the storage module, defending against invasion of external factors to data and guaranteeing accuracy of the data, the verification module checks integrity and accuracy of data uploaded by a user according to set verification rules and evaluates data value, and the query module queries and obtains relevant information from the storage module according to requirements of the user or a system.
And the machine learning unit in the service unit is arranged in the cloud platform and is used for analyzing and designing the current drilling working condition according to the monitored drilling engineering data and intelligently recommending and analyzing according to a design module and input parameters in the drilling design unit selected by a user. A training module respectively connected with the monitoring analysis module and the design analysis module is arranged in the machine learning unit, wherein the monitoring analysis module inquires drilling engineering data from the drilling data monitoring unit according to user requirements and carries out reasoning analysis to obtain corresponding current working condition information; the design analysis module carries out analysis and calculation of drilling design according to the current working condition information, the design module selected by the user and the filled data; the training module trains the monitoring analysis module and the design analysis module regularly according to the updated drilling engineering data, and the analysis accuracy of the two analysis modules is improved. When the current drilling working condition is analyzed and recommended by the machine learning unit, various drilling engineering data stored by the drilling data monitoring unit are read from the cloud platform, then the data are introduced into related algorithms, and condition descriptions such as drilling speed prediction, accident prediction, drilling tool damage prediction and the like are predicted by the algorithms. Different predictions are given by different algorithms, the identification of the current drilling working condition is realized after all predictions are integrated, and then the recommendation of related drilling tools, equipment combinations, drilling schemes and the like is carried out by combining the obtained current drilling working condition according to a design module and design related data selected by a user. The algorithms involved in the service unit may be self-carried in the system development process, and also can be uploaded by the user in the system use process, and the algorithms can adopt the existing method, which is not the innovation of the invention.
And a drilling design unit in the service unit is arranged in the cloud platform, and drilling design is completed according to the recommended design of the machine learning unit. The drilling design unit is provided with a basic information module for data sharing, a well body structure module, an equipment selection module, a drilling tool combination module, a drilling fluid module, a parameter design module, a well cementation design module, a well completion design module, an accident prevention module, a construction organization module, a progress control module and a budget control module. Each module is responsible for the design of different aspects, and for the data needing to be shared among different modules, the data transmission can be realized among different modules in a signal transmission mode. The basic information module is responsible for designing basic information of the drilling hole, such as drilling hole coordinates, surrounding environment, drilling hole requirements and the like; the well structure module is responsible for recommending and calculating a well structure diagram of the planned drilling hole and a necessary casing structure diagram; the equipment selection module is used for selecting drilling equipment which can be used on site, such as a drilling machine, a derrick, a slurry pump and the like; the drilling tool combination module is used for selecting drilling tools which can be used on site, such as drilling tools of a drill bit, a drill rod, a drill collar, a stabilizer and the like, and carrying out recommendation calculation on the arrangement positions of the corresponding drilling tools; the drilling fluid module is used for selecting a possibly applicable drilling fluid formula on site and carrying out recommendation calculation on the corresponding drilling fluid performance; the parameter design module is responsible for combining the selected drilling tool and drilling fluid recommendation and calculating the applicable drilling engineering parameters; the well cementation design module is responsible for completing the recommendation calculation of corresponding formulas and parameters of well cementation equipment, well cementation fluid and the like; the well completion design module is responsible for carrying out recommendation calculation of corresponding well completion equipment and construction processes; the accident prevention module is responsible for carrying out possible accident prediction and design selection of a corresponding accident prevention scheme; the construction organization module is responsible for construction organization design, including construction equipment, flow, personnel, process and other related organization design; the progress control module is responsible for designing a construction progress chart and a control scheme; the budget control module is responsible for calculating the related construction cost in the design and intelligently conducts corresponding construction budget recommendation analysis.
When the corresponding design is carried out through each design module in the drilling design unit, the basic steps are as follows: 1. selecting a needed design module by a user; 2. the system carries out module sequencing according to the design module selected by the user, and the modules arranged behind call the calculation result of the front module; 3. the system gives parameters which can not be calculated by the system and need to be filled by the user in each design module, and the system calls and analyzes data according to the data filled by the user and the built-in database after the user fills in the design modules to complete the design analysis of the modules.
Taking the design process of the well structure module as an example: the system first requires the user to fill in the design drilling depth, the final hole diameter, the types of rock formations that may be present in this depth range and the respective depths (these parameters are design basis parameters that must be filled in by the user based on the actual situation and cannot be calculated by the system). For example, a user fills a design depth of 3000m, a final hole diameter of 76mm, granite at 0-1000m, limestone at 1000-2000m, limestone at 2000-3000m, a system calls a built-in database to respectively obtain relevant strength parameters (parameters such as density, compressive strength, shear strength, fracture and the like) of the granite, the limestone and the limestone, the crustal stress at a corresponding position is calculated by combining the parameters such as depth, self weight and the like, and a calculation result shows that a crack or crustal stress anomaly may exist at the position of 1500 m. And changing the diameter according to the specification requirement, then inquiring a self-contained database according to the final hole diameter of 76mm by the system to obtain the previous-stage hole diameter of 92mm, finally informing a user of proposing drilling of 92mm holes, and continuously drilling when the hole is drilled to 1500m and the diameter is changed to 76mm, thereby completing the whole well design. The above is only for illustrating the basic design process, and the parameters and algorithms involved in the actual design module are much more complicated than the above examples and are not described in detail.
When the cloud platform processes and analyzes the drilling engineering data, two aspects of monitoring and analyzing the drilling engineering data and drilling design for construction are mainly included. The data analysis involved in the drilling engineering data monitoring process comprises the identification of the current working condition and the relevant calculation deduction according to the monitored parameters through a machine learning unit so as to judge whether the current working condition is normal or not. If the working state is normal, calculating whether drilling parameters (key parameters such as torque, bit pressure and pump capacity) can be adjusted or not so as to realize more efficient drilling work; if the working state is abnormal, construction accidents (such as drill jamming, drill breaking, drill burning and the like) which possibly occur are predicted, and drilling parameters (key parameters such as torque, weight on bit, pump capacity and the like) which need to be adjusted to avoid the accidents are recommended. The data analysis involved in the drilling engineering data design process is mainly related to the calculation of key parameters (well bore structure, drilling tool usage, drilling fluid formulation, engineering parameter design, etc.) in the drilling design process.
The management unit is used for monitoring the system and is completely arranged on the cloud platform, the management unit comprises an interaction unit, a user unit and a control unit, and the interaction unit, the user unit and the control unit are connected through signals.
The interactive unit in the management unit is used for inputting and outputting system data, and is provided with an input and output module for interacting various data, a display module respectively connected with the input and output module, and an instruction analysis module for splitting a user input instruction into system executable instructions.
The user unit in the management unit is used for managing user authority and user information, and a production user module and a use user module are respectively arranged in the user unit according to users with different authorities. The users with production authority can provide new drilling engineering parameters, related design data or related machine learning algorithms, machine recommendation algorithms and the like to the system through the production user module, and the users with use authority can only use the related data in the system and cannot perform addition, deletion and modification operations.
The control unit in the management unit is used for controlling the system, and the control unit is provided with a flow control module for opening or closing other modules according to user operation and a condition analysis module for analyzing the operation condition of the system.
As shown in fig. 2, in the system architecture of the present invention, the hardware layer is composed of an acquisition module and a transmission module of a drilling data monitoring unit disposed on the local platform for data acquisition and processing; the data layer is composed of other modules of the drilling data monitoring unit arranged on the cloud platform; the machine learning unit and the drilling design unit are reasoning layers and are used for reasoning analysis, algorithm training and recommendation and completing various drilling designs; the whole management unit is connected with the reasoning layer through the control layer, the interaction layer and the service logic layer, and transmission, splitting, conversion and the like of control instructions are achieved.
According to the method, after relevant data of drilling construction is collected locally, the strong computing power of the cloud platform is utilized, and after the data are analyzed, the drilling construction design and operation are guided. Moreover, data can be continuously updated through the setting of the network cloud platform, and the problem of inaccurate prediction caused by a new scene can be avoided through continuous analysis and learning. Moreover, the self-learning machine learning unit can automatically run in a database continuously supplemented with new data, so that the learning algorithm is continuously perfected, and finally, the accuracy of analysis and judgment is effectively improved.
Claims (7)
1. Modular drilling data monitoring and design system based on machine learning, characterized by: the drilling engineering data acquisition and storage system comprises a service unit and a management unit which are connected through signals, wherein the service unit comprises a drilling data monitoring unit, a machine learning unit and a drilling design unit, the drilling data monitoring unit is used for acquiring, monitoring and storing drilling engineering data, the machine learning unit is used for training and storing a current drilling working condition recognition algorithm according to the drilling engineering data, the drilling design unit is used for carrying out process and parameter design on a drilling engineering to be constructed, the machine learning unit is also used for storing a drilling parameter recommendation algorithm in the drilling design unit, the drilling data acquisition in the drilling data monitoring unit is realized on a local platform, and the monitoring and storage are realized on a cloud platform; the machine learning unit and the drilling design unit are both arranged in the cloud platform;
the system comprises a cloud platform, a management unit, an interaction unit, a user unit and a control unit, wherein the cloud platform is arranged on the management unit, the management unit is used for monitoring the system and comprises an interaction unit for inputting and outputting system data, the user unit for managing user authority and user information and the control unit for controlling the system, and the interaction unit, the user unit and the control unit are connected through data streams of signals.
2. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: in the drilling data monitoring unit of the service unit, an acquisition module and a transmission module which are arranged on a local platform are arranged, the acquisition module transmits the drilling engineering data to a storage module arranged on a cloud platform through the transmission module after acquiring the local drilling engineering data, and the storage module is also respectively connected with a safety module, a check module and a query module which are arranged on the cloud platform.
3. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: a machine learning unit of the service unit is provided with a training module which is respectively connected with the monitoring analysis module and the design analysis module, wherein the monitoring analysis module inquires drilling engineering data from the drilling data monitoring unit according to the requirements of users and carries out reasoning analysis to obtain corresponding current working condition information; the design analysis module carries out analysis and calculation of drilling design according to the current working condition information, the design module selected by the user and the filled data; the training module trains the monitoring analysis module and the design analysis module regularly according to the updated drilling engineering data, and the analysis accuracy of the two analysis modules is improved.
4. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: the drilling design unit is provided with a basic information module for data sharing, a well body structure module, an equipment selection module, a drilling tool combination module, a drilling fluid module, a parameter design module, a well cementation design module, a well completion design module, an accident prevention module, a construction organization module, a progress control module and a budget control module.
5. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: the interactive unit of the management unit is provided with an input and output module for interacting various data, a display module respectively connected with the input and output module and an instruction analysis module for splitting a user input instruction into system executable instructions.
6. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: in the user unit of the management unit, a production user module and a use user module are respectively arranged according to users with different authorities.
7. The machine learning based modular drilling data monitoring and design system of claim 1, wherein: the control unit of the management unit is provided with a flow control module for opening or closing other modules according to user operation and a state analysis module for analyzing the operation condition of the system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911092500.1A CN110806859A (en) | 2019-11-11 | 2019-11-11 | Modular drilling data monitoring and design system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911092500.1A CN110806859A (en) | 2019-11-11 | 2019-11-11 | Modular drilling data monitoring and design system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110806859A true CN110806859A (en) | 2020-02-18 |
Family
ID=69501848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911092500.1A Pending CN110806859A (en) | 2019-11-11 | 2019-11-11 | Modular drilling data monitoring and design system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110806859A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111520122A (en) * | 2020-03-27 | 2020-08-11 | 中国石油化工股份有限公司石油工程技术研究院 | Mechanical drilling speed prediction method, device and equipment |
| CN111520123A (en) * | 2020-03-27 | 2020-08-11 | 中国石油化工股份有限公司石油工程技术研究院 | Mechanical drilling speed prediction method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106121621A (en) * | 2016-07-15 | 2016-11-16 | 西南石油大学 | A kind of intelligent drilling specialist system |
| CN107169575A (en) * | 2017-06-27 | 2017-09-15 | 北京天机数测数据科技有限公司 | A kind of modeling and method for visualizing machine learning training pattern |
| CN108756848A (en) * | 2018-05-21 | 2018-11-06 | 北京四利通控制技术股份有限公司 | A kind of intelligent drilling control cloud platform and intelligent drilling control system |
| US10364662B1 (en) * | 2015-06-08 | 2019-07-30 | DataInfoCom USA, Inc. | Systems and methods for analyzing resource production |
-
2019
- 2019-11-11 CN CN201911092500.1A patent/CN110806859A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10364662B1 (en) * | 2015-06-08 | 2019-07-30 | DataInfoCom USA, Inc. | Systems and methods for analyzing resource production |
| CN106121621A (en) * | 2016-07-15 | 2016-11-16 | 西南石油大学 | A kind of intelligent drilling specialist system |
| CN107169575A (en) * | 2017-06-27 | 2017-09-15 | 北京天机数测数据科技有限公司 | A kind of modeling and method for visualizing machine learning training pattern |
| CN108756848A (en) * | 2018-05-21 | 2018-11-06 | 北京四利通控制技术股份有限公司 | A kind of intelligent drilling control cloud platform and intelligent drilling control system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111520122A (en) * | 2020-03-27 | 2020-08-11 | 中国石油化工股份有限公司石油工程技术研究院 | Mechanical drilling speed prediction method, device and equipment |
| CN111520123A (en) * | 2020-03-27 | 2020-08-11 | 中国石油化工股份有限公司石油工程技术研究院 | Mechanical drilling speed prediction method, device and equipment |
| CN111520123B (en) * | 2020-03-27 | 2021-03-02 | 中国石油化工股份有限公司石油工程技术研究院 | Mechanical drilling speed prediction method, device and equipment |
| CN111520122B (en) * | 2020-03-27 | 2023-05-30 | 中国石油化工股份有限公司石油工程技术研究院 | Method, device and equipment for predicting mechanical drilling speed |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104806226B (en) | intelligent drilling expert system | |
| CN100392207C (en) | Method for predicting drilling system performance for given formation and its system | |
| US7861800B2 (en) | Combining belief networks to generate expected outcomes | |
| Macpherson et al. | Drilling-systems automation: Current state, initiatives, and potential impact | |
| CN109779602B (en) | Intelligent safety risk early warning method and system for drilling engineering | |
| CN106121621A (en) | A kind of intelligent drilling specialist system | |
| EA028514B1 (en) | System and method for online automation | |
| MXPA06010578A (en) | Method and apparatus and program storage device adapted for visualization of qualitative and quantitative risk assessment based on technical wellbore design and earth properties. | |
| CA3064241A1 (en) | Methods and systems for improved drilling operations using real-time and historical drilling data | |
| NO333726B1 (en) | Iterative drilling simulation method and iterative drilling simulation system for selecting drilling rig system characteristics for use in drilling in a subsurface formation | |
| US20190093468A1 (en) | Real time measurement of mud properties for optimization of drilling parameters | |
| CN110806859A (en) | Modular drilling data monitoring and design system based on machine learning | |
| CN111126735A (en) | Drilling digital twin system | |
| Khosravanian et al. | Methods for petroleum well optimization: automation and data solutions | |
| Said et al. | Theoretical development of a digital-twin based automation system for oil well drilling rigs | |
| Nybø | Fault detection and other time series opportunities in the petroleum industry | |
| CN108533244B (en) | Method and system for automatically identifying downhole state of drilling well | |
| Said | Development of a digital twin based real-time drilling optimization and control system | |
| Zhao et al. | Research and Application of Drilling Engineering Monitoring and Remote Support Technology for CNPC Key Wells | |
| US20220403729A1 (en) | Automated wellbore planning based on wellbore condition | |
| CN115059447A (en) | Safety early warning system for drilling operation | |
| Ge | Research and Application of Drilling Engineering Monitoring and Remote Support Technology for CNPC Key Wells | |
| Kaya | Simulation-based evaluation of blasthole drilling key performance metrics in surface mining | |
| Cao et al. | Drilling Advisory Automation with Digital Twin and AI Technologies | |
| Josef | Using digital technologies to automat and optimize drilling parameters in real-time, its impact on value creation, and work process |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200218 |
|
| RJ01 | Rejection of invention patent application after publication |