Pressure and flow control method, system and device for pressure-controlled drilling and related equipment
By acquiring real-time logging and sensor data, and combining graph theory algorithms and deep learning models, the problem of engineer dependence in controlled pressure drilling has been solved, and unmanned pressure and flow control has been achieved.
Patent Information
- Application Number
- CN202410966184.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2026-01-20
AI Technical Summary
The pressure and flow control of existing controlled pressure drilling systems is highly dependent on on-site engineers and requires continuous inspection, making it difficult to achieve minimal or unmanned operation.
By acquiring logging data and sensor data in real time, the throttle valve opening value is calculated, and graph theory algorithms and deep learning models are used for real-time control. Combined with the drive mechanism, unmanned management of the throttle valve is achieved.
It enables real-time adjustment and accurate control of pressure and flow in controlled pressure drilling, reducing reliance on on-site engineers and supporting unmanned operation.
Smart Images

Figure CN121363419A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of oil and gas drilling engineering, and particularly relates to a pressure flow control method, system and device for managed pressure drilling and related equipment. BACKGROUND
[0002] With the oil and gas exploration moving into new fields such as ultra-deep, super-deep and deep water, the number of high-difficulty wells such as complex ultra-deep wells, ultra-long horizontal wells and deep water wells is increasing, which puts higher requirements on the complex response capability of drilling operations. The pressure flow regulation technology in the drilling process is a characteristic technology for solving downhole complexity and ensuring well control safety, and the technical demand is increasing year by year.
[0003] The existing pressure flow control equipment for managed pressure drilling can basically meet the needs of conventional managed pressure drilling operations, but the control of pressure flow for managed pressure drilling relies heavily on field engineers, and engineers need to conduct uninterrupted on-site inspection, which is still far from "fewer people" and "unmanned". SUMMARY
[0004] In order to overcome the problem that the control of pressure flow for managed pressure drilling relies heavily on field engineers and engineers need to conduct uninterrupted on-site inspection, the present application provides a pressure flow control method, system and device for managed pressure drilling and related equipment.
[0005] In a first aspect, in order to solve the above technical problems, the present application provides a pressure flow control method for managed pressure drilling, comprising:
[0006] Real-time acquisition of logging data collected by each sampling point logging instrument and sensor data collected by a sensor; wherein each managed pressure drilling data recording point is a sampling point;
[0007] According to the positions of the sampling points, the upstream and downstream sampling points of each sampling point in the spatial relationship are determined;
[0008] According to the logging data and sensor data of the current sampling point at the current time, and the logging data and sensor data of the upstream and downstream sampling points of the current sampling point at the current time, the throttle opening value of the current sampling point at the current time is calculated;
[0009] According to the throttle opening value corresponding to the current sampling point at the current time, the throttle of the current sampling point is controlled.
[0010] In a second aspect, the present application provides a pressure flow control system for managed pressure drilling, comprising:
[0011] A data acquisition module for real-time acquisition of logging data collected by each sampling point logging instrument and sensor data collected by a sensor; wherein each managed pressure drilling data recording point is a sampling point;
[0012] The up-and-down sampling point determination module is configured to determine the upstream sampling point and the downstream sampling point of each sampling point in the spatial relationship according to the positions of the sampling points.
[0013] The throttle opening value determination module is configured to calculate the throttle opening value of the current sampling point at the current time according to the logging data and the sensor data of the current sampling point at the current time, and the logging data and the sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time.
[0014] The throttle control module is configured to control the throttle of the current sampling point according to the throttle opening value corresponding to the current sampling point at the current time.
[0015] In a third aspect, the present application provides a pressure flow control device for managed pressure drilling, comprising: a detachable throttle control module, a data acquisition module and a terminal platform, the detachable throttle control module is arranged on the valve body of the throttle in each managed pressure drilling, the data acquisition module is arranged in each managed pressure drilling, the detachable throttle control module is connected with the data acquisition module and the terminal platform respectively, and the data acquisition module is connected with the terminal platform.
[0016] The terminal platform is configured to execute the pressure flow control method for managed pressure drilling as described above.
[0017] In a fourth aspect, the present application provides a computing device, comprising a memory, a processor and a program stored in the memory and running on the processor, and the processor executes the program to realize the steps of the pressure flow control method for managed pressure drilling as described above.
[0018] In a fifth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions run on a terminal device, the terminal device executes the steps of the pressure flow control method for managed pressure drilling as described above.
[0019] The present application has the following beneficial effects: logging data and sensor data of each sampling point are obtained in real time, the spatial relationship of each sampling point is established according to the position, thereby obtaining the logging data and the sensor data of the upstream sampling point and the downstream sampling point of each sampling point, finally, the throttle opening value of the current sampling point is obtained through the logging data and the sensor data of the current sampling point, the upstream sampling point and the downstream sampling point, and the throttle of the current sampling point is controlled in real time. The present application calculates the throttle opening value in real time to adjust the pressure flow of the managed pressure drilling in real time, realizes the unmanned real-time control of the throttle, and in addition, the data of the upstream and downstream sampling points are also referred to in the real-time control of the pressure flow of the throttle, so that the data of the adjacent sampling points are associated with each other, and the throttle control is more accurate. BRIEF DESCRIPTION OF DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the present application will be further described below with reference to the drawings and embodiments.
[0021] Figure 1 A flowchart of a pressure flow control method for controlled pressure drilling of an embodiment of the present application;
[0022] Figure 2 A structural diagram of a pressure flow control system for controlled pressure drilling of an embodiment of the present application;
[0023] Figure 3 A structural diagram of a pressure flow control device for controlled pressure drilling of an embodiment of the present application;
[0024] Figure 4 A structural diagram of a detachable throttle control module;
[0025] Figure 5 A structural diagram of a detachable electrically-controlled mechanical device;
[0026] Figure 6 A structural diagram of a pressure flow control device for controlled pressure drilling of another embodiment of the present application. DETAILED DESCRIPTION
[0027] The following embodiments are further explanations and supplements of the present application and do not constitute any limitation on the present application.
[0028] The following describes a pressure flow control method, system, device and related equipment for controlled pressure drilling of an embodiment of the present application.
[0029] As shown in Figure 1 , the present application provides a pressure flow control method for controlled pressure drilling, comprising:
[0030] S1, real-time acquisition of logging data collected by each sampling point logging instrument and sensor data collected by a sensor; wherein each controlled pressure drilling data recording point is taken as a sampling point.
[0031] S2, determination of upstream sampling points and downstream sampling points of each sampling point in spatial relationship according to positions of the sampling points.
[0032] S3, calculation of a throttle opening value of a current sampling point at a current time according to logging data and sensor data of the current sampling point at the current time, and logging data and sensor data of upstream sampling points and downstream sampling points of the current sampling point at the current time.
[0033] S4, control of a throttle of the current sampling point according to the throttle opening value corresponding to the current sampling point at the current time.
[0034] In this embodiment, the logging data and sensor data of each sampling point are acquired in real time, and the spatial relationship of each sampling point is established according to the position, so as to acquire the logging data and sensor data of the upstream sampling point and the downstream sampling point of each sampling point. Finally, the throttle opening value of the current sampling point is obtained through the logging data and sensor data of the current sampling point, the upstream sampling point and the downstream sampling point, and the throttle of the current sampling point is controlled in real time. The throttle opening value is calculated in real time in this application, so as to adjust the pressure flow of the managed pressure drilling in real time, and the unmanned real-time control of the throttle is realized. In addition, the data of the upstream and downstream sampling points are also referred to in the real-time control of the pressure flow of the throttle, so that the data of the adjacent sampling points are associated with each other, and the throttle control is more accurate.
[0035] In this embodiment, the logging data is measured by a logging instrument, wherein the logging data includes well depth data and corresponding managed pressure drilling curve values.
[0036] In addition, the managed pressure drilling curve values include basic logging data curves, rock sample collection data curves, drilling fluid logging data curves and managed pressure drilling analysis data curves. The above-mentioned managed pressure drilling curves change with the change of the depth of the managed pressure drilling; wherein:
[0037] The basic logging data curves include: ROP (rate of penetration), depth, pump pressure, drilling pressure, torque, hook load, standpipe pressure, drilling time, drilling fluid outlet conductivity, bottom hole annulus temperature, bottom hole drilling fluid conductivity, bottom hole annulus pressure, bottom hole annulus temperature, drilling fluid outlet temperature, rock lithology, gas measurement and rock description, and mud rheological characteristics.
[0038] The rock sample collection data curves include: managed pressure drilling depth, coring horizon, lithology name, rock sample category, coring length, core characteristics and other information.
[0039] The drilling fluid logging data curves include: density, viscosity, yield value, drilling fluid type, PH value and sand content of the drilling fluid.
[0040] The managed pressure drilling analysis data curves mainly include sample analysis, stratification data, fluorescence analysis, gas measurement analysis and comprehensive analysis.
[0041] In this embodiment, the sensor data is collected by different sensors, including pressure sensors, flow sensors and throttle sensors; wherein:
[0042] The pressure sensor is used to monitor the pressure data of the downhole and the ground, and to ensure the real-time monitoring of the internal pressure of the wellbore.
[0043] The flow sensor is used to monitor the flow conditions in the wellbore, including the flow of liquid and gas, so as to control the flow.
[0044] a throttle valve sensor for monitoring the opening degree of the throttle valve to control the wellbore flow rate.
[0045] Optionally, before calculating the throttle valve opening degree value of the current sampling point at the current time according to the logging data and the sensor data of the current sampling point at the current time, and the logging data and the sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time, the method further comprises:
[0046] comparing the logging data of the current sampling point at the current time with different first preset threshold ranges, and comparing the sensor data with different second preset threshold ranges to determine the working condition state of the current sampling point at the current time;
[0047] calculating the throttle valve opening degree value of the current sampling point at the current time according to the logging data and the sensor data of the current sampling point at the current time, and the logging data and the sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time, comprises:
[0048] calculating the throttle valve opening degree value of the current sampling point at the current time according to the logging data, the sensor data and the working condition state of the current sampling point at the current time, and the logging data, the sensor data and the working condition state of the upstream sampling point and the downstream sampling point of the current sampling point at the current time.
[0049] In the embodiment, the working condition state of managed pressure drilling is additionally added when calculating the throttle valve opening degree value, which enriches the associated parameters when calculating the throttle valve opening degree value, so that the pressure flow of managed pressure drilling under different factors (working condition state) can be more scientifically and accurately controlled.
[0050] In the embodiment, the working condition state comprises overflow, loss, collapse and sticking, wherein:
[0051] The overflow is divided into saltwater invasion overflow, rock cuttings gas invasion, formation gas invasion overflow, oil invasion overflow, drilling pumping overflow, and post-pumping formation rebound false overflow.
[0052] The loss is divided into fracture loss, displacement loss, overflow and loss coexistence, and post-pumping formation compression false loss.
[0053] Optionally, the working condition state of each current sampling point at the current time is determined by comparing the logging data of the current sampling point at the current time with different first preset threshold ranges, and comparing the sensor data with different second preset threshold ranges, comprising:
[0054] comparing the logging data of the current sampling point at the current time with different first preset threshold ranges to determine the first target threshold range corresponding to the logging data of the current sampling point at the current time;
[0055] comparing the sensor data of the current sampling point at the current time with different second preset threshold ranges to determine a second target threshold range corresponding to the sensor data of the current sampling point at the current time;
[0056] obtaining a working condition corresponding table, wherein the working condition corresponding table stores preset working conditions corresponding to different first target threshold ranges and different second target threshold ranges;
[0057] searching, according to the first target threshold range corresponding to the current sampling point at the current time and each second target threshold range, the preset working condition corresponding to the current sampling point at the current time from the working condition corresponding table;
[0058] taking the preset working condition corresponding to the current sampling point at the current time as a working condition state.
[0059] The working condition corresponding table in the embodiment is obtained according to the summary of experienced engineers, and needs to be set according to the actual situation of the local managed pressure drilling, so the first preset threshold range and the second preset threshold range are not fixed.
[0060] In addition, it needs to be particularly pointed out that, since the logging data and the sensor data include multiple types of data, the preset threshold ranges corresponding to each type of data can be different, for example, the logging data includes depth values and drilling pressure values, and the sensor data includes pressure values and flow values of the choke valve, so the first preset threshold ranges corresponding to the depth values and the first preset threshold ranges corresponding to the drilling pressure values can be different, and the second preset threshold ranges corresponding to the pressure values and the second preset threshold ranges corresponding to the flow values of the choke valve are also different.
[0061] For example, the logging data includes depth values, pump pressure values and drilling pressure values, and the sensor data includes pressure values of the downhole and the ground and flow values of the choke valve.
[0062] At this time, it is necessary to determine that the depth values are located in the first preset threshold range a1, the drilling pressure values are located in the first preset threshold range b1, the pressure values of the downhole and the ground are located in the second preset threshold range c1, and the flow values of the choke valve are located in the first preset threshold range d1, so that the working condition state corresponding to a1, b1, c1 and d1 is overflow of salt water invasion through the working condition corresponding table, and the working condition state of the current sampling point at the current time is overflow of salt water invasion.
[0063] Optionally, according to the positions of each sampling point, upstream sampling points and downstream sampling points of each sampling point in the spatial relationship are determined, including:
[0064] constructing each sampling point in the spatial relationship between positions in the graph data at the current time;
[0065] According to the graph data, upstream sampling points and downstream sampling points of each sampling point in spatial relationship are determined.
[0066] In this embodiment, the relationship between different sampling points is modeled as nodes and edges of a graph by using a graph algorithm, so that the graph data can accurately reflect the pressure and flow conditions inside the managed pressure drilling, and subsequent calculation of the choke valve opening value can quickly obtain corresponding data from the graph data.
[0067] In this embodiment, the choke valve opening value can be calculated by a deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a Transformer, which is used to process the graph data and make predictions. The deep learning model is trained using the collected data to accurately predict the pressure and flow of the managed pressure drilling, thereby controlling the pressure and flow of the managed pressure drilling.
[0068] Optionally, the graph data at the current time is constructed according to the spatial relationship between the positions of the sampling points, including:
[0069] Each sampling point is taken as a node in the graph data, and each node is given an attribute value, including the sampling point logging data and sensor data corresponding to the current node;
[0070] The connection order of the sampling points in the spatial relationship is determined according to the positions of the sampling points;
[0071] For any two adjacent sampling points in the connection order, the weight of the edge between the two sampling points is determined according to the difference between the logging data and the sensor data of the two sampling points at the current time;
[0072] The sampling points are connected by edges according to the connection order to construct the graph data.
[0073] In this embodiment, the specific representation of the graph data is as follows:
[0074] Node definition: Each sampling point can be regarded as a node in the graph, and each node can be given an attribute value, such as well depth data and corresponding basic logging data curve. It should be particularly noted that the working condition state of each sampling point obtained in this embodiment can be added to the attribute value of the node.
[0075] Edge definition: The edge represents the relationship between different sampling points. For example, according to the position, the adjacent sampling points in space are connected; in addition, the weight of the edge can be defined according to the difference between the two nodes, such as depth difference, time difference, pressure difference, etc.
[0076] Graph representation: The graph data structure is represented by using an adjacency matrix or an adjacency list.
[0077] Up to now, the graph data is constructed, and when the throttle opening value is calculated, the features of the nodes and edges can be directly extracted, for example, the node features can be a multi-dimensional vector containing data of various attribute values; the edge features can be the difference between the nodes, that is, the weight, so as to quickly calculate the throttle opening value.
[0078] Optionally, the throttle valve of the current sampling point is controlled according to the throttle opening value corresponding to the current sampling point at the current time, including:
[0079] According to the throttle opening value corresponding to the current sampling point at the current time, the opening and closing degree of the throttle valve corresponding to the current sampling point is driven by the driving mechanism.
[0080] The driving mechanism in the embodiment can be a hydraulic cylinder or a mechanical arm or the like device for pushing the opening and closing of the throttle valve.
[0081] As shown in Figure 2 The present application provides a pressure flow control system for managed pressure drilling, including:
[0082] A data acquisition module is configured to acquire real-time logging data collected by each sampling point logging instrument and sensor data collected by a sensor; wherein each managed pressure drilling data recording point is regarded as a sampling point.
[0083] An up and down sampling point determination module is configured to determine the upstream sampling point and the downstream sampling point of each sampling point in the spatial relationship according to the position of each sampling point.
[0084] A throttle opening value determination module is configured to calculate the throttle opening value of the current sampling point at the current time according to the logging data and sensor data of the current sampling point at the current time, and the logging data and sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time.
[0085] A throttle control module is configured to control the throttle valve of the current sampling point according to the throttle opening value corresponding to the current sampling point at the current time.
[0086] Optionally, it further includes a working condition state determination module, which is specifically configured to:
[0087] Compare the logging data of the current sampling point at the current time with different first preset threshold ranges, and compare the sensor data with different second preset threshold ranges, to determine the working condition state of the current sampling point at the current time.
[0088] The throttle opening value determination module is specifically configured to:
[0089] The throttle opening value of the current sampling point at the current time is calculated according to the logging data, sensor data and working condition state of the current sampling point at the current time, and the logging data, sensor data and working condition state of the upstream sampling point and the downstream sampling point of the current sampling point at the current time.
[0090] Optionally, the working condition state determining module is specifically configured to:
[0091] The logging data of the current sampling point at the current time is compared with different first preset threshold ranges to determine a first target threshold range corresponding to the logging data of the current sampling point at the current time.
[0092] The sensor data of the current sampling point at the current time is compared with different second preset threshold ranges to determine a second target threshold range corresponding to the sensor data of the current sampling point at the current time.
[0093] A working condition corresponding table is obtained, wherein the working condition corresponding table stores preset working conditions corresponding to different first target threshold ranges and different second target threshold ranges.
[0094] The preset working condition corresponding to the current sampling point at the current time is searched from the working condition corresponding table according to the first target threshold range and the second target threshold range corresponding to the current sampling point at the current time.
[0095] The preset working condition corresponding to the current sampling point at the current time is taken as the working condition state.
[0096] Optionally, the working condition state determining module is specifically configured to:
[0097] The sampling points are constructed in graph data at the current time according to the spatial relationship between positions.
[0098] According to the graph data, the upstream sampling point and the downstream sampling point of each sampling point in the spatial relationship are determined.
[0099] Optionally, the working condition state determining module is specifically configured to:
[0100] Each sampling point is taken as a node in the graph data, and each node is given an attribute value, and the attribute value includes the logging data and sensor data of the sampling point corresponding to the current node.
[0101] The connection order of the sampling points in the spatial relationship is determined according to the positions of the sampling points.
[0102] For any two adjacent sampling points in the connection order, the weight of the edge between the two sampling points is determined according to the difference between the logging data and sensor data of the two sampling points at the current time.
[0103] The sampling points are connected through edges according to the connection order to construct the graph data.
[0104] Optionally, the throttle control module is specifically used for:
[0105] According to the throttle opening value corresponding to the current sampling point at the current time, the opening and closing degree of the throttle corresponding to the current sampling point is driven by the driving mechanism.
[0106] As shown in Figure 3 , the present application provides a pressure flow control device for managed pressure drilling, comprising: a detachable throttle control module, a data acquisition module and a terminal platform, the detachable throttle control module is arranged on the valve body of the throttle in each managed pressure drilling, the data acquisition module is arranged in each managed pressure drilling, the detachable throttle control module is connected with the data acquisition module and the terminal platform respectively, and the data acquisition module is connected with the terminal platform; the terminal platform is used for executing the pressure flow control method for managed pressure drilling provided by any one of the above embodiments. In this embodiment, the terminal platform can be a drilling platform or a remote monitoring center.
[0107] Optionally, as shown in Figure 4 , the detachable throttle control module comprises a UPS power module, a control box, a PLC controller, a detachable electric control mechanical device and a flow monitoring device, wherein, from Figure 4 it can be seen that the detachable throttle control module can be directly connected with the throttle valve body, realizing the rapid modification of the original manual throttle valve in the drilling site, and changing the manual throttle valve into an electrically controlled throttle valve.
[0108] As shown in Figure 5 , the detachable electric control mechanical device comprises a servo motor 101, a reversing device 102, a speed reduction mechanism 103, a driving rod 104, a mechanical transmission part clamping mechanism 105 and a driver power supply interface 106; wherein, the mechanical transmission part clamping mechanism 105 is detachably installed on the throttle valve body, after the driver power supply interface 106 is connected with the power supply, the servo motor 101 is started and applies power to the reversing device 102, the reversing device 102 converts the power applied by the servo motor 101 into transverse power, so as to drive the driving rod 104 to make transverse motion to control the opening degree of the throttle valve.
[0109] In this embodiment, the PLC controller is a special electronic control system provided for the throttle valve, and the PLC controller can receive instructions from the drilling platform or the remote monitoring center (terminal platform), and accurately adjust the opening degree of the throttle valve according to the instructions.
[0110] The function of the UPS power module is to supply power for the PLC controller and the detachable electric control mechanical device. In this embodiment, the detachable electric control mechanical device can be a hydraulic cylinder or a mechanical arm.
[0111] The PLC controller operates the choke valve through a drive mechanism (i.e., a detachable electrically controlled mechanical device). When receiving an adjustment instruction, the drive mechanism drives the valve to open or close, thereby changing the cross-sectional area of the fluid passing through the choke valve. The main function of the choke valve is to adjust the wellhead pressure and flow rate by changing the cross-sectional area of the fluid passing through. When the valve opening degree decreases, the cross-sectional area of the fluid passing through decreases, the flow rate increases, the pressure rises, and the flow rate increases. Conversely, when the valve opening degree increases, the cross-sectional area of the fluid passing through increases, the flow rate decreases, the pressure decreases, and the flow rate decreases. In this way, the choke valve can accurately control the wellhead pressure to prevent safety accidents caused by excessive or insufficient wellhead pressure.
[0112] The flow monitoring device serves as a monitoring and feedback system to monitor the outlet flow rate of the managed pressure drilling (e.g., MG-12 and MG-13) in real time. If the flow rate continues to change, the information is fed back to the PLC controller, which adjusts in real time according to the feedback information to ensure stable operation of the choke valve.
[0113] Optionally, the data acquisition module includes various sensor devices, microcontrollers, communication modules, power management chips, device protection shells, real-time clock chips, sensor calibration and detection systems, etc., for real-time acquisition of conventional logging data, pressure and flow monitoring data, and choke valve opening degree data, to ensure that the collected data is of high quality and high timeliness to meet the needs of subsequent model training and prediction.
[0114] Among them, the sensor device includes: a pressure sensor for monitoring downhole and surface pressure data to ensure real-time monitoring of wellbore internal pressure; a flow sensor for monitoring the flow rate of liquid and gas in the wellbore to control the flow rate; a choke valve sensor for monitoring the opening degree of the choke valve to control the wellbore flow rate; and a logging instrument data exchange terminal for measuring well depth data and corresponding managed pressure drilling curve values to obtain conventional logging data.
[0115] Microcontroller: used to control data acquisition and transmission of sensors and logging instrument data exchange terminals, as well as data preprocessing and storage.
[0116] Communication module: used for data communication with other devices or systems, including wired or wireless communication interfaces, to transmit the collected data to subsequent processing modules or systems.
[0117] Power management chip: used to manage the power supply of the device, including battery management, power consumption control, etc., to ensure stable operation and long-term use of the device.
[0118] Device protection shell: used to protect the internal circuits and components of the device from external environmental influences and damage. Waterproof and dustproof design: considering the possibility of using the device in harsh downhole environments, it is necessary to ensure that the device has good waterproof and dustproof performance.
[0119] Real-time clock chip: used to record the timestamp of data collection to ensure the timeliness and accuracy of the data.
[0120] Sensor calibration and detection system: calibration module for periodic calibration of sensor modules to ensure data accuracy and reliability; self-diagnosis system for monitoring the working status of sensor modules and data acquisition modules to discover and solve problems in a timely manner.
[0121] Optionally, the terminal platform includes a data processing and feature extraction module, a graph data construction module, a deep learning model design and training module, and an implementation decision integration system module, wherein:
[0122] The data processing and feature extraction module pre-processes, cleans, and integrates the collected data to ensure data usability and consistency, implements feature extraction algorithms, and extracts valuable features from conventional logging data, pressure-flow monitoring data, and choke valve opening data to construct graph data. The workflow is as follows:
[0123] A. Data preprocessing: cleaning, denoising, and filling missing values of raw data to ensure data quality and consistency.
[0124] B. Data conversion: transforming, normalizing, and standardizing data to meet algorithm requirements and improve algorithm performance and stability.
[0125] C. Feature extraction: extracting representative and discriminative features from raw data to reflect important characteristics and structures of data, providing a foundation for subsequent modeling and analysis.
[0126] D. Feature selection: selecting features based on their importance and relevance, excluding useless or redundant features to simplify the model and improve the model's generalization ability.
[0127] E. Dimensionality reduction techniques: using dimensionality reduction techniques such as principal component analysis (PCA), linear discriminant analysis (LDA), etc. to reduce the dimension and complexity of data, improve computational efficiency and model interpretability.
[0128] F. Feature engineering: further processing and handling features, including feature combination, feature derivation, feature cross, etc. to enhance feature expression ability and model performance.
[0129] G. Real-time processing: Supports real-time data processing and feature extraction to meet the needs of real-time data analysis and decision-making.
[0130] H. Scalability: Provides flexible interfaces and functional extension mechanisms to support customization of different data types and processing needs.
[0131] I. Performance optimization: For large-scale data and high-dimensional feature processing needs, performance optimization and parallel processing are performed to improve processing efficiency and scalability.
[0132] Visualization and interaction: Provide data visualization and interactive interface to help users intuitively understand the process and results of data processing and feature extraction.
[0133] The graph data construction module uses graph theory algorithms to model the relationship between different data points as nodes and edges of a graph, ensuring that the graph data accurately reflects the pressure and flow conditions inside the wellbore.
[0134] The deep learning model design and training module designs a pressure and flow control model for managed pressure drilling based on deep learning, selects appropriate deep learning architectures such as convolutional neural networks (CNN), recurrent neural networks (RNN), or Transformers, etc., for processing graph data and making predictions, and trains the deep learning model using collected data to accurately predict the pressure and flow of managed pressure drilling, thereby controlling the pressure and flow of managed pressure drilling.
[0135] The implementation decision integration system module is used to control the pressure and flow of managed pressure drilling in real time, ensuring that the decision system can respond to the prediction results of the managed pressure drilling pressure and flow control model in a timely manner and generate corresponding control instructions, and combining the expert decision system with the deep learning model to allow for manual intervention or confirmation when necessary.
[0136] Based on the above, as shown in Figure 6 The pressure and flow control device for managed pressure drilling includes a detachable throttle valve control module 100, a data acquisition module 200, a data processing and feature extraction module 300, a graph data construction module 400, a deep learning model design and training module 500, and an implementation decision integration system module 600. The detachable throttle valve control module is connected to the data acquisition module, the data acquisition module is connected to the data processing and feature extraction module, the data processing and feature extraction module is connected to the graph data construction module, the graph data construction module is connected to the deep learning model design and training module, the deep learning model design and training module is connected to the implementation decision integration system module, and the implementation decision integration system module is connected to the detachable throttle valve control module.
[0137] The embodiment of the present application also provides a computing device, comprising a memory, a manager and a program stored in the memory and running on the manager, and the manager implements part or all of the steps of the pressure flow control method for managed pressure drilling when executing the program.
[0138] Correspondingly, the program is computer software, and the parameters and steps in the computing device of the present application are described above in the embodiment of the pressure flow control method for managed pressure drilling, and will not be repeated here.
[0139] Those skilled in the art know that the present application can be implemented as a system, a method or a computer program product. Therefore, the present disclosure can be embodied in the form of a complete hardware, a complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which are generally referred to as "circuitry", "module" or "system" herein. In addition, in some embodiments, the present application can also be embodied in the form of a computer program product in one or more computer readable media, which contains computer readable program codes. The computer readable storage medium may, for example, be but not limited to an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or apparatus, or any combination thereof.
[0140] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.
[0141] Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.
Claims
1. A pressure flow control method for managed pressure drilling, characterized in that, The method comprises the following steps: Real-time acquisition of logging data collected by each sampling point logging unit and sensor data collected by a sensor; wherein each managed pressure drilling data recording point is taken as a sampling point; According to the positions of each sampling point, upstream sampling points and downstream sampling points of each sampling point in spatial relationship are determined; According to the logging data and the sensor data of the current sampling point at the current time, and the logging data and the sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time, a choke valve opening value of the current sampling point at the current time is calculated; According to the choke valve opening value corresponding to the current sampling point at the current time, the choke valve of the current sampling point is controlled.
2. The method of claim 1, wherein, The method further comprises the following steps: The logging data of the current sampling point at the current time is compared with different first preset threshold ranges, and the sensor data is compared with different second preset threshold ranges, to determine the working condition state of the current sampling point at the current time; Then, according to the logging data and the sensor data of the current sampling point at the current time, and the logging data and the sensor data of the upstream sampling point and the downstream sampling point of the current sampling point at the current time, the choke valve opening value of the current sampling point at the current time is calculated, which comprises the following steps: According to the logging data, the sensor data and the working condition state of the current sampling point at the current time, and the logging data, the sensor data and the working condition state of the upstream sampling point and the downstream sampling point of the current sampling point at the current time, the choke valve opening value of the current sampling point at the current time is calculated.
3. The method of claim 2, wherein, The logging data of the current sampling point at the current time is compared with different first preset threshold ranges, and the sensor data is compared with different second preset threshold ranges, to determine the working condition state of each current sampling point at the current time, which comprises the following steps: The logging data of the current sampling point at the current time is compared with different first preset threshold ranges, to determine the first target threshold range corresponding to the logging data of the current sampling point at the current time; The sensor data of the current sampling point at the current time is compared with different second preset threshold ranges, to determine the second target threshold range corresponding to the sensor data of the current sampling point at the current time; A working condition corresponding table is acquired; wherein the working condition corresponding table stores preset working conditions corresponding to different first target threshold ranges and different second target threshold ranges; According to the first target threshold range and the second target threshold range corresponding to the current sampling point at the current time, the preset working condition corresponding to the current sampling point at the current time is searched from the working condition corresponding table; The preset working condition corresponding to the current sampling point at the current time is taken as the working condition state.
4. The method of claim 1, wherein, According to the positions of each sampling point, upstream sampling points and downstream sampling points of each sampling point in spatial relationship are determined, which comprises the following steps: Each sampling point is constructed in a graph data at the current time according to the spatial relationship between the positions of the sampling points; According to the graph data, upstream sampling points and downstream sampling points of each sampling point in spatial relationship are determined.
5. The method of claim 4, wherein, The sampling points are constructed in the graph data at the current moment according to the spatial relationship between positions, including: Each of the sampling points is taken as a node in the graph data, and each node is given an attribute value, which includes the logging data and sensor data of the sampling point corresponding to the current node; The connection order of each of the sampling points in the spatial relationship is determined according to the position of each of the sampling points; For any two adjacent sampling points in the connection order, the weight of the edge between the two sampling points is determined according to the difference between the logging data and sensor data of the two sampling points at the current moment; The sampling points are connected through the edges according to the connection order to construct the graph data.
6. The method according to any one of claims 1 to 5, characterized in that, The throttle valve of the current sampling point is controlled according to the throttle opening value corresponding to the current sampling point at the current moment, including: The opening and closing degree of the throttle valve corresponding to the current sampling point is driven by the driving mechanism according to the throttle opening value corresponding to the current sampling point at the current moment.
7. A pressure flow control system for managed pressure drilling, characterized by It includes: A data acquisition module is configured to acquire logging data collected by a logging instrument and sensor data collected by a sensor in real time; wherein each pressure control drilling data recording point is taken as a sampling point; An upstream and downstream sampling point determination module is configured to determine the upstream and downstream sampling points of each of the sampling points in the spatial relationship according to the position of each of the sampling points; A throttle opening value determination module is configured to calculate the throttle opening value of the current sampling point at the current moment according to the logging data and sensor data of the current sampling point at the current moment, and the logging data and sensor data of the upstream and downstream sampling points of the current sampling point at the current moment; A throttle valve control module is configured to control the throttle valve of the current sampling point according to the throttle opening value corresponding to the current sampling point at the current moment.
8. Pressure flow control device for managed pressure drilling, characterized in that It includes: A detachable throttle valve control module, a data acquisition module and a terminal platform, the detachable throttle valve control module is arranged on the valve body of the throttle valve in each pressure control drilling, the data acquisition module is arranged in each pressure control drilling, the detachable throttle valve control module is connected with the data acquisition module and the terminal platform respectively, and the data acquisition module and the terminal platform are connected; The terminal platform is used to execute the pressure and flow control method of the pressure control drilling according to any one of claims 1 to 6.
9. A computing device comprising a memory, a processor, and a program stored on the memory and running on the processor, wherein, The processor executes the program to realize the steps of the pressure and flow control method of the pressure control drilling according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions, when the instructions run on the terminal device, the terminal device executes the steps of the pressure and flow control method of the pressure control drilling according to any one of claims 1 to 6.