Throttling kill manifold control method based on Internet of Things system and related equipment

Abstract

According to the throttling and killing manifold control method based on the Internet of Things system, the accuracy and timeliness of manifold control instructions are remarkably improved, at present, in the well drilling, oil testing and downhole operation processes of a well site, the control instructions sent to a throttling and killing manifold completely depend on experience of commanders, and the control instructions are not limited by the experience of the commanders. The inspection of the degree manifold state completely depends on the regular inspection of inspectors. Timing inspectors have the problems that the mastering of data and manifold states is not comprehensive and not specific enough, and the risk that hidden problems are difficult to find in real time possibly exists. By constructing an intelligent comparison model and relying on a novel information acquisition system, data visualization, valve real-time opening and closing state explicit and hydraulic valve opening state clarification are achieved, operation suggestions are provided according to a preset model and feedback information of all valves and pressure data, throttling and killing manifold management blind areas are effectively reduced, and the management efficiency is improved. The whole mastering of the throttling kill manifold information is realized, and the accuracy and timeliness of the control instruction are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of oil drilling and production well control, and specifically relates to a throttling and well killing manifold control method based on an Internet of Things system and related equipment. Background Art

[0002] The throttle and well-killing manifold is a special fluid manifold composed of a throttle valve, various gate valves, pipelines, pressure gauges, etc. It is used to control the discharge channel of the wellbore annulus fluid during drilling, oil testing, and downhole operations. It can also inject clean water, well-killing fluid and other fluids into the wellbore annulus through the throttle and well-killing manifold to achieve the purpose of well killing, blowout prevention, and balancing the wellbore pressure. It is an important and indispensable equipment for well control operations, especially well killing operations after overflow occurs during drilling, oil testing, and downhole operations.

[0003] When safety risk events such as overflow occur, it is necessary to operate the opening and closing of multiple valves on the choke manifold and the well-killing manifold, and perform well control operations by observing the indication of the choke and well-killing manifold pressure gauge. For the choke manifold, the well-killing operation can be carried out through the throttling effect of the throttle valve, the fluid in the well can be controlled so that it does not flow out of the wellhead, and the wellhead back pressure (vertical pressure casing pressure) can be controlled to maintain the bottom hole pressure not lower than the formation pressure, thereby preventing overflow. At the same time, after the wellhead is closed with the full-sealed gate of the blowout preventer, it is necessary to hang heavy mud into the wellbore through the well-killing manifold to carry out the well-killing operation. It can be seen that the close cooperation of the commander and the operator is required to successfully implement this series of operations. The commander gives the operation instructions by analyzing the manifold information such as the vertical pressure casing pressure and mud density, and the operator executes the instructions by manually controlling the valve switch and the opening of the throttle valve.

[0004] At present, when controlling the throttling well-killing manifold, the manifold information is collected manually, and then uploaded to the background for information processing. After the processing, the corresponding control information is generated to inform the staff to open and close the valves located at different manifold positions and control the throttle valve opening. The whole process of operation relies on the manual information transmission and manual execution of operation actions by the operator.

[0005] This method has the disadvantages of being unsafe, inaccurate and unreliable. Summary of the invention

[0006] The present invention provides a throttling and well-killing manifold control method and related equipment based on an Internet of Things system, which solves the problems of unsafe, inaccurate and unreliable manual operation in the prior art.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The throttling and well-killing manifold control method based on the Internet of Things system includes:

[0009] Get manifold information;

[0010] Determine the detection position information and valve position information according to the manifold information;

[0011] Modeling the manifold information according to the detection position information and the valve position information to obtain first manifold modeling information;

[0012] Respectively combining the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information to obtain the second manifold modeling information;

[0013] Performing anomaly detection on the second manifold modeling information to determine whether the manifold detection information at different locations has preset anomalies;

[0014] If there is a preset abnormality in the manifold detection information, a processing plan is generated according to the abnormality type of the preset abnormality, and the pipeline is controlled and the processing plan is displayed.

[0015] Preferably, the first manifold modeling adopts BIM modeling technology, and finally generates the first manifold modeling by establishing a network and manifold lines, importing CAD documents, establishing columns, beams and slabs, coloring and outputting them into CAD drawings and detailed lists.

[0016] Preferably, the second manifold modeling is obtained by using supermap idesktop technology to process the data and merge it with the BIM model. First, a new data set is created, and then a data type is set in the new data set. The data set name is defined as the detection position information and the manifold detection information. Then, the detection position information and the manifold detection information are appended to the first manifold modeling information through the data processing function, and finally the second manifold modeling information is obtained.

[0017] Preferably, the displayed content includes the number of abnormal combinations corresponding to the choke and kill manifold and abnormal combination information.

[0018] Preferably, the control pipeline is specifically to control the corresponding hydraulic valve opening device to operate after the hydraulic valve opening instruction is issued, and control its opening pressure through the model so that the main manifold is opened with other manifolds at an appropriate opening, and at the same time, the opening data of the corresponding valve in the second throttling and well killing manifold modeling information is recorded.

[0019] Preferably, the judgment whether the manifold detection information has a preset abnormality is specifically as follows: the throttling and well-killing manifold maintenance information is analyzed to determine the number of type combinations of different manifold abnormality types in the manifold maintenance information and the time series length corresponding to each abnormal type combination in the number of type combinations, and the manifold maintenance information is unsupervisedly sorted based on the time series length and the number of abnormal combinations to obtain a first throttling and well-killing manifold matrix data, and then based on the first throttling and well-killing manifold matrix data, a second throttling and well-killing manifold matrix data is generated, and finally, based on the second throttling and well-killing manifold matrix data, the third throttling and well-killing manifold modeling information is obtained, and based on the third throttling and well-killing manifold modeling information, it is judged whether there is a manifold in the third throttling and well-killing manifold modeling information whose throttling and well-killing manifold weight information does not meet the preset weight information.

[0020] Preferably, the second throttling and killing manifold matrix data is generated according to the first throttling and killing manifold matrix data, and finally the third throttling and killing manifold modeling information is obtained according to the second throttling and killing manifold matrix data, specifically:

[0021] Inputting the first throttling and well-killing manifold matrix data into a trained manifold prediction model to perform vector feature extraction to obtain the number of throttling and well-killing manifold feature dimensions, and combining the obtained number of throttling and well-killing manifold feature dimensions with the first throttling and well-killing manifold matrix data to generate second throttling and well-killing manifold matrix data;

[0022] Data contained in the second throttling and well-killing manifold matrix data is processed to obtain manifold hazard data, and the obtained manifold hazard data is input into a preset algorithm model for data extrapolation to generate the number of abnormal combinations and abnormal combination information occurring at different manifold positions in the second throttling and well-killing manifold modeling information within a future preset time period; abnormal weight analysis is performed based on the number of abnormal combinations and the abnormal combination information to obtain manifold weight information, and the manifold weight information is combined with the second throttling and well-killing manifold modeling information to obtain third throttling and well-killing manifold modeling information.

[0023] The throttling and killing manifold control device based on the Internet of Things system includes:

[0024] Acquisition module: used to obtain manifold information;

[0025] Detection module: used to determine the detection position information, valve opening and closing information and valve position information according to the manifold information;

[0026] A first modeling module: used to model the manifold information according to the detection position information and the valve position information to obtain first manifold modeling information;

[0027] A second modeling module: used to combine the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information to obtain the second manifold modeling information;

[0028] Anomaly detection module: used to perform anomaly detection on the second manifold modeling information, and determine whether the manifold detection information at different locations has preset anomalies;

[0029] Solution generation module: If there is a preset abnormality in the manifold detection information, a treatment plan is generated according to the abnormality type of the preset abnormality, and the pipeline is controlled and the treatment plan is displayed

[0030] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, steps of a throttling and well-killing manifold control method based on an Internet of Things system are implemented.

[0031] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a throttling and well-killing manifold control method based on an Internet of Things system are implemented.

[0032] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a throttling and well-killing manifold control method based on the Internet of Things system, which significantly improves the accuracy and timeliness of the manifold control instructions. At present, during the drilling, oil testing and downhole operations at the well site, the control instructions issued to the throttling and well-killing manifold completely rely on the experience of the commander, and the inspection of the manifold status also completely relies on the regular inspection of the patrol personnel. The commander's decision-making basis is mostly limited meter reading data, and there is a risk of misjudgment in the issuance of control instructions; the regular patrol personnel may have the risk of hidden problems being difficult to discover in real time due to the lack of comprehensive and specific grasp of the data and manifold status. The present invention realizes data visualization, explicitness of the real-time opening and closing status of the valve and clarification of the opening status of the hydraulic valve by constructing an intelligent comparison model and relying on a new information collection system, and provides operation suggestions based on the preset model and the feedback information of each valve and pressure data, effectively reducing the blind spot of the throttling and well-killing manifold management, realizing the overall grasp of the throttling and well-killing manifold information, and improving the accuracy and timeliness of the control instructions.

[0033] Furthermore, the accuracy of information transmission of each key control node of the throttling and well-killing manifold is effectively guaranteed. Currently, the data information of the throttling and well-killing manifold and the vertical casing pressure are mainly manually transcribed by operators, and reported to the driller or commander in the form of a report after being summarized. Since manual transcription often omits certain key data due to the long time interval, and the pressure values ​​may continue to change during the reporting process, problems such as data lag and insufficient accuracy exist. The present invention realizes the digitization of pressure data by setting an information-based sensor, and connects the sensor signal to a dedicated data collector and processor. By setting a high-frequency sampling data acquisition module, real-time data collection and updating are realized, which provides a guarantee for the driller and commander to make decisions through accurate real-time data.

[0034] Furthermore, in general, if an erroneous operation occurs, it is often not observed by the operator before a more serious accident occurs, which has the problem of high hidden risks and may lead to the expansion of accidents. The present invention realizes real-time comparison of current operation control information and pressure data with the safe operation model by constructing an operation logic database and a feedback information comparison model. When an erroneous operation is found, the pressure exceeds the safety threshold, etc., an alarm signal will be issued and suggested operation information guidance will be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of a throttling and well-killing manifold control method based on an Internet of Things system;

[0036] Figure 2 It is a block diagram of a choke and kill manifold control device based on an Internet of Things system;

[0037] Figure 3 It is a schematic diagram of the connection logic of the electronic equipment in this control device. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0039] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0041] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0042] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0043] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] like Figure 1 As shown, the present invention provides a throttling and well-killing manifold control method based on the Internet of Things system, S10~S15 are 6 operation steps, namely step S10, step S11, step S12, step S13, step S14, and step S15.

[0045] The specific action of step S10 is to obtain the manifold information.

[0046] The specific action of step S11 is to determine the detection position information and the valve position information based on the manifold detection information.

[0047] The specific action of step S12 is to model the manifold information according to the detection position information and the valve position information to obtain the first manifold modeling information. For this patent, the manifold is modeled using BIM modeling technology, and the first manifold modeling information is finally obtained through a series of steps such as establishing a network and manifold lines, importing CAD documents, establishing columns, beams and slabs, color rendering, and outputting into CAD drawings and detailed lists.

[0048] The main action of step S13 is to combine the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information to obtain the second manifold modeling information. For the embodiment of the present invention, the supermap idesktop technology is used to process the operation of merging data with the BIM model. First, a new data set is created, and then a data type is set in the new data set, and the data set name is defined as the detection position information and the manifold detection information. Then, the detection position information and the manifold detection information are appended to the first manifold modeling information through the data processing function, and finally the second manifold modeling information is obtained.

[0049] The main action of step S14 is to perform anomaly detection on the second manifold modeling information to determine whether the manifold detection information located at different positions has a preset anomaly.

[0050] The main action of step S15 is to generate a processing plan according to the abnormality type of the preset abnormality if there is a preset abnormality in the manifold detection information, and control the display of the processing plan.

[0051] like Figure 2As shown, the present invention also provides a throttling and well-killing manifold control device based on the Internet of Things system. The 20 manifold control device based on the Internet of Things system can specifically include: 21 acquisition module, 22 detection module, 23 first modeling module, 24 second modeling module, 25 abnormality detection module and 26 solution generation module. Among them, 21 acquisition module is used to obtain manifold information, and the manifold information includes: manifold detection information with different detection characteristics located at different positions of the manifold and opening and closing information of the current manifold valve; 22 detection module is used to determine the detection position information based on the manifold detection information, and determine the valve position information based on the opening and closing information; 23 first modeling module, used to model the manifold information according to the detection position information and the valve position information, and obtain the first manifold modeling information; 24 second modeling module, used to respectively combine the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information, and obtain the second manifold modeling information; 25 abnormality detection module, used to perform abnormality detection on the second manifold modeling information, and determine whether the manifold detection information located at different positions has preset abnormalities; 26 solution generation module, if the manifold detection information has preset abnormalities, then generate a processing solution according to the abnormality type of the preset abnormality, and control the display of the processing solution.

[0052] like Figure 3 As shown, the electronic device 300 includes, in addition to conventional configuration devices: a processor 301 and a memory 303. The processor 301, the memory 303 and the transceiver 304 are connected via a bus 302. The processor 301 can implement or execute set logic instructions; the bus 302 acts as a data path to transmit information between the above components; the memory 303 is a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, and is used to store and read related measurement data and logic instructions; the transceiver 304 is used to implement remote communication and can transmit system data to a target address via the Internet.

[0053] Another embodiment of the present invention provides a throttling and well-killing manifold control method based on an Internet of Things system:

[0054] The present invention can obtain sensor detection information with different detection characteristics at different positions of a choke and well-killing manifold and the opening and closing information of the current manifold valve, and determine the sensor position information based on the sensor detection information. The manifold is modeled based on the valve opening and closing information and the valve position information to obtain the first choke and well-killing manifold modeling information. The sensor detection information corresponding to the sensor position information and the opening and closing information corresponding to the valve position information are respectively combined with the first choke and well-killing manifold modeling information to obtain the second choke and well-killing manifold modeling information; the second choke and well-killing manifold modeling information is abnormally detected to determine whether the sensor detection information at different positions has a preset abnormality. If it exists, corresponding processing is performed according to the abnormality type of the preset abnormality, and the corresponding processing equipment is controlled to solve the abnormality, and the maintenance information is synchronized with the second choke and well-killing manifold modeling information. After the hydraulic valve opening instruction is issued, the corresponding hydraulic valve opening equipment can be controlled to operate (solenoid valve), and its opening pressure is controlled by the model so that the main manifold is opened with other manifolds at an appropriate opening, and the corresponding valve in the second choke and well-killing manifold modeling information is opened. Data is recorded.

[0055] Acquire the throttling and well-killing manifold maintenance information within a preset time period in the past, wherein the manifold maintenance information is maintenance information of different manifold abnormality types corresponding to different positions in the second throttling and well-killing manifold modeling information. Analyze the throttling and well-killing manifold maintenance information, determine the number of type combinations of different manifold abnormality types in the manifold maintenance information and the time series length corresponding to each abnormal type combination in the number of type combinations, and perform unsupervised time series data sorting on the manifold maintenance information based on the time series length and the number of abnormal combinations to obtain the first throttling and well-killing manifold matrix data; input the first throttling and well-killing manifold matrix data into the trained manifold prediction model for vector feature extraction to obtain the number of throttling and well-killing manifold feature dimensions, and perform data combination processing on the obtained number of throttling and well-killing manifold feature dimensions and the first throttling and well-killing manifold matrix data to generate the second throttling and well-killing manifold matrix data; extract the data contained in the second throttling and well-killing manifold matrix data. According to the data, data is processed to obtain manifold hazard data, and the obtained manifold hazard data is input into a preset algorithm model for data extrapolation to generate the number of abnormal combinations and abnormal combination information that occur at different manifold positions in the second throttling and well-killing manifold modeling information within a future preset time period; abnormal weight analysis is performed based on the number of abnormal combinations and the abnormal combination information to obtain manifold weight information, and the manifold weight information is combined with the second throttling and well-killing manifold modeling information to obtain the third throttling and well-killing manifold modeling information; it is determined whether there is a manifold in the third throttling and well-killing manifold modeling information whose throttling and well-killing manifold weight information does not conform to the preset weight information, and if so, the throttling and well-killing manifold is marked, and the number of abnormal combinations and the abnormal combination information corresponding to the throttling and well-killing manifold are controlled to be displayed.

[0056] Another embodiment of the present invention provides a throttling and well-killing manifold control method based on an Internet of Things system. The present application embodiment provides a manifold control method based on an Internet of Things system, which is executed by an on-site computer terminal. The computer is equipped with an information processor, a memory, and a computer-readable storage medium.

[0057] When the system is used at the well site, position sensors are installed at the throttle valve and each manual valve to sense the opening of the throttle valve and each manual flat valve. The system obtains manifold information through step S10, including the throttle valve opening, flat valve opening, opening and closing of each manual valve, throttle and well killing manifold pipeline pressure, wellhead casing pressure, and wellhead riser pressure, and inputs the obtained information into step S11.

[0058] In step S11, after obtaining the current manifold detection information, the corresponding template can be called out by querying the server or local database to determine the valve position in the current state and the open and closed state of each valve, forming a summary of the current valve open and closed state, and input into step S12.

[0059] In step S12, the manifold is modeled using database query modeling technology, and a series of steps such as establishing a grid and transient sampling analysis, importing statistical information, and establishing a reference model are performed to finally obtain the first manifold modeling information, and the model is input into step S13.

[0060] In step S13, the operation of processing data using the Internet of Things technology is to first create a new data collection, then extract current data from the new data collection, define the current data as detection position information and manifold detection information, and then match and correct the detection position information and manifold detection information with the first manifold modeling information template through the data processing function to obtain the second manifold modeling information, and input the second manifold modeling information into step S14.

[0061] Step S14, perform anomaly detection on the second manifold modeling information and the first manifold modeling information to determine whether there is an abnormality in the manifold detection information at different positions. The manifold detection information is received according to the sensors of various detection types installed on the pipeline, and then the parameter values ​​in the manifold detection information are extracted one by one, and the extracted parameter values ​​are compared with the abnormal parameter value range in the preset abnormality. When the extracted parameter value satisfies the abnormal parameter value range, it is determined that the current pipeline has a preset abnormality. In this embodiment, the preset abnormalities include: pressure abnormality, switch failure, opening degree and other abnormalities, among which the pressure abnormality indicates that the casing pressure suddenly increases; the switch failure means that the flat valve switch is not in place; the opening degree abnormality means that the throttle valve opening is too large or too small under the current casing pressure. If there is no abnormal parameter, the "no abnormality" signal is transmitted to step S15; if there is a difference with the preset range value, the "manifold abnormality" information and the corresponding fault code are transmitted to step S15.

[0062] In step S15, if a signal and code indicating abnormal manifold detection information is received, a processing plan is generated according to the fault code and the abnormality type, and the processing plan is displayed. At the same time, the execution system performs corresponding processing according to the preset abnormality type, controls the corresponding equipment to solve the abnormality, and synchronizes the solution maintenance information with the second manifold modeling information to update the manifold status.

[0063] The above embodiment introduces a manifold control method based on the Internet of Things system from the perspective of method flow, and the following embodiment introduces a manifold control device based on the Internet of Things system from the perspective of functional modules. For details, please refer to the following embodiment.

[0064] like Figure 2 As shown, the manifold control device 20 based on the Internet of Things system specifically includes: an acquisition module 21, a detection module 22, a first modeling module 23, a second modeling module 24, an anomaly detection module 25 and a solution generation module 26.

[0065] When the manifold control device 20 is connected to the throttling well killing manifold, the acquisition module 21 acquires the casing pressure, vertical pressure, throttle valve control pressure, flat valve switch status, and current throttle valve opening information, and transmits the information to the detection module 22 through the data bus after summarizing the information. After receiving the valve opening and closing information and the vertical pressure and casing pressure information, the detection module 22 analyzes the information to determine the detection position of each data, and associates the valve opening and closing information with the data address of each valve to form packaged data, and inputs the packaged data into the first modeling module 23 and the second modeling module 24. The first modeling module 23 performs pipeline logic modeling according to the received manifold pressure and valve information according to the position address, obtains the first manifold modeling model information, and transmits the model framework to the second modeling module 24. After receiving the real-time data from the detection module 22 and the pipeline model of the first modeling module, the second modeling module 24 extracts and merges the manifold detection information corresponding to the current manifold detection position information and the opening and closing information corresponding to the valve position information according to the first manifold modeling template, and obtains the second manifold modeling model data into which the real-time manifold switch and pressure data are substituted. In order to ensure safety, the model data of the second manifold modeling is input into the abnormality detection module 25 through the bus, which is used to detect abnormalities in the second manifold modeling information and determine whether there are preset abnormalities in the manifold detection information at different positions. If it is found through detection that the opening and closing state of the valve does not match the vertical casing pressure, the corresponding information is input into the solution generation module 26. If the casing pressure is too high, but the throttle valve opening is too small, the module generates a processing solution based on the abnormality, "The vertical pressure is too high, it is recommended to open the throttle valve to a certain data", and displays the processing solution on the display.

[0066] From the perspective of physical electronic devices, the system Figure 3 shown. Figure 3 The electronic device 300 shown includes, in addition to conventional configuration devices: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected via a bus 302. At the same time, in order to achieve remote wireless transmission, the electronic device 300 may also include a transceiver 304.

[0067] Processor 301 is an STM32 microcontroller based on ARM architecture. Through the optocoupler isolation module, dozens of switch quantity information are collected. The analog signals transmitted by sensors such as vertical pressure, sleeve pressure, and temperature are collected through the ADC chip of the multi-way switch plus I2C; Beidou satellite positioning information is collected through the UART serial port; UPS power supply information is collected through the 232 chip, and computer debugging and industrial touch screen display are supported. The 4G chip is connected through UART to upload data to the data center. At the same time, the local industrial real-time database of the Ethernet intranet can be connected through the second-level Ethernet chip to output real-time data.

[0068] Bus 302 uses EISA Extended Industry Standard Architecture as an information transmission path for transmitting information between the above components.

[0069] The memory 303 uses a data bank to store program codes and manifold pressure and valve opening and closing information transmitted by the processor 301. The processor 301 can run the preset program in the memory 303, and display the control suggestions under the current manifold conditions according to the abnormal information, and control the throttling and killing manifold hydraulic valve.

[0070] Although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments and application fields, and the above-mentioned specific embodiments are only illustrative and instructive, rather than restrictive. Under the guidance of the specification, a person skilled in the art can also make many forms without departing from the scope of protection of the claims of the present invention, all of which belong to the scope of protection of the present invention.

Claims

1. A throttling and well-killing manifold control method based on the Internet of Things system, characterized in that: include: Get manifold information; Determine the detection position information and valve position information according to the manifold information; Modeling the manifold information according to the detection position information and the valve position information to obtain first manifold modeling information; Respectively combining the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information to obtain the second manifold modeling information; Performing anomaly detection on the second manifold modeling information to determine whether the manifold detection information at different locations has preset anomalies; If there is a preset abnormality in the manifold detection information, a processing plan is generated according to the abnormality type of the preset abnormality, and the pipeline is controlled and the processing plan is displayed.

2. The throttling and killing manifold control method based on the Internet of Things system according to claim 1 is characterized in that: The first manifold modeling adopts BIM modeling technology. By establishing networks and manifold lines, importing CAD documents, establishing columns, beams and slabs, color rendering and outputting them into CAD drawings and detailed lists, the first manifold modeling is finally generated.

3. The throttling and killing manifold control method based on the Internet of Things system according to claim 2 is characterized in that: The second manifold modeling is obtained by using supermap idesktop technology to process the data and merge it with the BIM model. First, a new dataset is created, and then the data type is set in the new dataset. The dataset name is defined as the detection position information and the manifold detection information. Then, the detection position information and the manifold detection information are appended to the first manifold modeling information through the data processing function, and finally the second manifold modeling information is obtained.

4. The throttling and killing manifold control method based on the Internet of Things system according to claim 1 is characterized in that: The displayed content includes the number of abnormal combinations corresponding to the choke and kill manifold and abnormal combination information.

5. The throttling and killing manifold control method based on the Internet of Things system according to claim 1 is characterized in that: Specifically, the control pipeline controls the corresponding hydraulic valve opening device to operate after the hydraulic valve opening instruction is issued, and controls its opening pressure through the model so that the main manifold is opened with other manifolds at an appropriate opening, and at the same time, the opening data of the corresponding valve in the second throttling and well-killing manifold modeling information is recorded.

6. The throttling and killing manifold control method based on the Internet of Things system according to claim 1 is characterized in that: The judgment whether the manifold detection information has a preset abnormality is specifically as follows: the throttling and well-killing manifold maintenance information is analyzed to determine the number of type combinations of different manifold abnormality types in the manifold maintenance information and the time series length corresponding to each abnormal type combination in the number of type combinations, and the manifold maintenance information is unsupervisedly sorted based on the time series length and the number of abnormal combinations to obtain a first throttling and well-killing manifold matrix data, and then based on the first throttling and well-killing manifold matrix data, a second throttling and well-killing manifold matrix data is generated, and finally, based on the second throttling and well-killing manifold matrix data, the third throttling and well-killing manifold modeling information is obtained, and based on the third throttling and well-killing manifold modeling information, it is judged whether there is a manifold in the third throttling and well-killing manifold modeling information whose throttling and well-killing manifold weight information does not meet the preset weight information.

7. The throttling and killing manifold control method based on the Internet of Things system according to claim 1 is characterized in that: According to the first throttling and well-killing manifold matrix data, the second throttling and well-killing manifold matrix data is generated, and finally the third throttling and well-killing manifold modeling information is obtained according to the second throttling and well-killing manifold matrix data, which is specifically: Inputting the first throttling and well-killing manifold matrix data into a trained manifold prediction model to perform vector feature extraction to obtain the number of throttling and well-killing manifold feature dimensions, and combining the obtained number of throttling and well-killing manifold feature dimensions with the first throttling and well-killing manifold matrix data to generate second throttling and well-killing manifold matrix data; Data contained in the second throttling and well-killing manifold matrix data is processed to obtain manifold hazard data, and the obtained manifold hazard data is input into a preset algorithm model for data extrapolation to generate the number of abnormal combinations and abnormal combination information occurring at different manifold positions in the second throttling and well-killing manifold modeling information within a future preset time period; abnormal weight analysis is performed based on the number of abnormal combinations and the abnormal combination information to obtain manifold weight information, and the manifold weight information is combined with the second throttling and well-killing manifold modeling information to obtain third throttling and well-killing manifold modeling information.

8. The throttling and well-killing manifold control device based on the Internet of Things system is characterized by: include: Acquisition module: used to obtain manifold information; Detection module: used to determine the detection position information, valve opening and closing information and valve position information according to the manifold information; A first modeling module: used to model the manifold information according to the detection position information and the valve position information to obtain first manifold modeling information; A second modeling module: used to combine the manifold detection information corresponding to the detection position information and the opening and closing information corresponding to the valve position information with the first manifold modeling information to obtain the second manifold modeling information; Anomaly detection module: used to perform anomaly detection on the second manifold modeling information, and determine whether the manifold detection information at different locations has preset anomalies; Solution generation module: If there is a preset abnormality in the manifold detection information, a treatment plan is generated according to the abnormality type of the preset abnormality, and the pipeline is controlled and the treatment plan is displayed.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the throttling and well-killing manifold control method based on the Internet of Things system as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the throttling and well-killing manifold control method based on the Internet of Things system as described in any one of claims 1 to 7 are implemented.

Images