Automatic under-pressure equipment operation method and system based on artificial intelligence

Abstract

The invention relates to the technical field of automatic under-pressure equipment operation, in particular to an automatic under-pressure equipment operation method and system based on artificial intelligence. Comprising the following steps: S1, extracting historical working data of the automatic under-pressure equipment, and extracting historical righting parameters, historical operation well data, historical oil pipe parameters and historical lowering parameters from the historical working data; historical operation wells, oil pipes and lowering parameters are integrated, real-time monitoring data are combined, high-precision simulation is conducted on the oil pipe lowering process through an artificial intelligence algorithm, for example, in the oil pipe deviation prediction link, complex factors such as formation pressure fluctuation, well deviation angle changes and oil pipe material characteristics are fully considered by means of a deep learning model, and the oil pipe lowering process is simulated. The deviation condition of the oil pipe in each section of underground area is accurately estimated, the deviation prediction accuracy can be improved by more than 60% compared with a traditional method, the oil pipe jamming and abrasion risks are greatly reduced, and smooth running operation is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of automated pressure-bearing equipment operation, and in particular to an automated pressure-bearing equipment operation method and system based on artificial intelligence. Background Art

[0002] In the field of oil and gas extraction, the oil pipeline lowering operation is a crucial link, the purpose of which is to accurately and safely place the oil pipeline underground to ensure the smooth extraction of subsequent oil and gas; At present, the lowering parameters are determined by technical personnel based on past operating experience of similar well conditions combined with basic theoretical calculations, and the position of the oil pipe is roughly controlled by naked eye observation or simple monitoring equipment. The oil pipe lowering work can be completed to a certain extent. However, under complex geological conditions, the formation pressure fluctuates violently and the well inclination angle changes irregularly. It is difficult to accurately consider these complex factors based on limited experience, resulting in low accuracy in the estimation of oil pipe deviation, which often causes the oil pipe to frequently collide with the well wall and get stuck during the lowering process. This not only seriously wears the oil pipe and reduces its service life, but also frequently interrupts the operation process, greatly increasing the mining cost and time cost. In addition, in the face of sudden abnormal working conditions, such as oil pipe deviation caused by sudden changes in formation pressure, it is difficult for manual decision-making based on experience to accurately adjust the working straightening parameters in a short time. The decision-making process is slow, and the best processing time is often missed, further exacerbating the safety risk. Therefore, an automatic pressure equipment operation method and system based on artificial intelligence are proposed. Summary of the invention

[0003] The purpose of the present invention is to provide an automated pressure equipment operation method and system based on artificial intelligence to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, one of the purposes of the present invention is to provide an automatic pressure equipment operation method based on artificial intelligence, comprising the following steps: S1. Extract historical working data of automated pressure-bearing equipment, and extract historical righting parameters, historical operating well data, historical tubing parameters, and historical lowering parameters from the historical working data; S2, collecting the operating well data and working tubing parameters, dividing the operating well into downhole areas according to the differences in the operating well data, and predicting the pressure fluctuation of each downhole area in combination with the working tubing parameters; S3, combining historical operating well data, historical tubing parameters and historical lowering parameters with automated pressure equipment to establish a tubing lowering simulation model, and then combining the tubing lowering simulation model with the predicted pressure fluctuations of each downhole area to perform working lowering parameter analysis; S4, combining the working lowering parameters of each downhole area with the operating well data and working tubing parameters to predict tubing deviation, and combining the predicted tubing deviation with historical righting parameters to perform working righting parameter analysis; S5. During the process of lowering the tubing, the tubing position and the wellbore center are detected for deviation in real time. When deviation occurs, the deviation data is combined with the working righting parameters for parameter selection analysis, and the working righting parameters are input according to the selection results.

[0005] As a further improvement of the present technical solution, S1 establishes an artificial intelligence module in the automated pressure-bearing equipment, records the historical working data of the automated pressure-bearing equipment through the artificial intelligence module, and extracts historical straightening parameters, historical operating well data, historical oil pipe parameters and historical lowering parameters from the historical working data.

[0006] As a further improvement of the technical solution, the steps of S2 are as follows: S2.1. Establish data acquisition connection between the operating well sensor and the oil pipe sensor and the automated pressure equipment with the help of the sensor network, obtain the operating well data through the data fed back by the operating well sensor, and then obtain the working oil pipe parameters through the data fed back by the oil pipe sensor; S2.2. Establish an operating well model based on the operating well data, and obtain the overall downhole area through which the oil pipe needs to be lowered in the operating well model. Then, divide the overall downhole area into multiple downhole areas according to different geographical locations and pressure differences; S2.3. Predict the pressure fluctuation of each downhole area in combination with the working oil pipe parameters to obtain the predicted pressure fluctuation corresponding to each downhole area.

[0007] As a further improvement of the technical solution, the steps of S3 are as follows: S3.1. Establish a tubing lowering simulation model by combining historical operating well data, historical tubing parameters and historical lowering parameters with automated pressure equipment; S3.2. Combine the tubing lowering simulation model with the predicted pressure fluctuation of each downhole area to analyze the working lowering parameters, obtain the working lowering parameters corresponding to each downhole area, and then adjust the working lowering parameters of each downhole area safely according to the average speed in the order of tubing lowering.

[0008] As a further improvement of the technical solution, the step of S4 is as follows: S4.1. The working lowering parameters of each section of the downhole area are combined with the working well data and the working tubing parameters to predict the tubing deviation, and obtain the predicted tubing deviation that will occur with probability when the tubing passes through each section of the downhole area; S4.2. The predicted tubing deviation is combined with the historical righting parameters and the working lowering parameters to perform working righting parameter analysis, and obtain working righting parameters that can keep the tubing consistent with the wellbore center.

[0009] As a further improvement of the technical solution, the step of S5 is as follows: S5.1. During the lowering process of the oil pipe, the position of the oil pipe is monitored in real time, and then the deviation between the position of the oil pipe and the center of the wellbore is detected in real time; S5.2, when S5.1 shows that the tubing position and the wellbore center are offset, the deviation data is combined with the working righting parameter to perform similarity matching with the predicted tubing deviation. When the deviation data is consistent with one of the predicted tubing deviation data, the working righting parameter corresponding to the predicted tubing deviation data is selected and sent to the automated pressure equipment. On the contrary, when the deviation data and the predicted tubing deviation data are not the same, the deviation data is combined with the automated pressure equipment to perform new working righting parameter analysis, and the newly generated working righting parameter is sent to the automated pressure equipment. S5.3. When S5.1 shows that there is no deviation between the tubing position and the wellbore center, continue monitoring.

[0010] As a further improvement of the technical solution, after the working righting parameters are input in S5, if the deviation trend between the oil pipe position and the wellbore center is still expanding, an early warning alarm is issued to the staff.

[0011] The second object of the present invention is to provide an automated pressure-carrying equipment operating system based on artificial intelligence, including any one of the automated pressure-carrying equipment operating methods based on artificial intelligence described above, including a data acquisition module, a parameter generation module and a parameter input module; The data acquisition module is used to extract the historical working data of the automated pressure-bearing equipment, collect the working well data and working tubing parameters, segment the working wells into downhole areas according to the differences in the working well data, and predict the pressure fluctuations; The parameter generation module is used to establish a tubing lowering simulation model, combine the tubing lowering simulation model with the predicted pressure fluctuation of each downhole area to perform working lowering parameter analysis, then combine the working lowering parameters of each downhole area with the operating well data and the working tubing parameters to predict tubing deviation, and combine the predicted tubing deviation with the historical righting parameters to perform working righting parameter analysis; The parameter input module is used to detect the real-time deviation between the tubing position and the wellbore center during the tubing lowering process. When deviation occurs, the deviation data is combined with the working righting parameters for parameter selection analysis, and the working righting parameters are input according to the selection results.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. An automated pressure equipment operation method and system based on artificial intelligence. By integrating historical operating wells, tubing and lowering parameters, combined with real-time monitoring data, and using artificial intelligence algorithms to perform high-precision simulation of the tubing lowering process, for example, in the process of predicting tubing deviation, the deep learning model fully considers complex factors such as formation pressure fluctuations, changes in well inclination angles, and tubing material properties, and accurately estimates the deviation of the tubing in each section of the downhole area. The deviation prediction accuracy can be increased by more than 60% compared with traditional methods, greatly reducing the risk of tubing jamming and wear, and ensuring smooth lowering operations.

[0013] 2. An artificial intelligence-based automated pressure equipment operation method and system, which accurately determines parameters such as the type of centralizer and installation spacing based on the predicted tubing deviation under different working conditions and historical centralizing experience, so that the average deviation between the tubing and the center of the wellbore is controlled within an extremely small range, effectively ensuring the tubing's centering state in the well and reducing fluid resistance and equipment loss in subsequent mining operations.

[0014] 3. An artificial intelligence-based automated pressurized equipment operation method and system, which collects and analyzes multi-source data such as tubing position, pressure, and temperature in real time in the face of the complex and changeable environment downhole, and uses prediction models to quickly determine whether the current working conditions are normal. Once it is detected that the tubing position is offset from the wellbore center, it can complete similarity matching within milliseconds, retrieve the best working straightening parameters from the pre-stored solution library and send them to the automated pressurized equipment, so as to promptly avoid safety accidents caused by the expansion of deviations and ensure operation continuity. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is the overall flow chart of the present invention; Figure 2 A flowchart for obtaining the predicted pressure fluctuation corresponding to each downhole area of ​​the present invention; Figure 3 A flow chart of establishing a simulation model for lowering a tubing for the present invention; Figure 4 A flowchart of the present invention for obtaining working straightening parameters that can keep the oil pipe consistent with the center of the wellbore; Figure 5 The present invention is a flowchart of sending the newly generated working righting parameters to the automated pressure-bearing equipment. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0017] like Figure 1 - Figure 5 As shown, one of the purposes of the present invention is to provide an automated pressure equipment operation method based on artificial intelligence, comprising the following steps: S1. Extract historical working data of automated pressure-bearing equipment, and extract historical righting parameters, historical operating well data, historical tubing parameters, and historical lowering parameters from the historical working data; S1 establishes an artificial intelligence module in the automated pressure-carrying equipment, records the historical working data of the automated pressure-carrying equipment through the artificial intelligence module, and extracts historical righting parameters, historical operating well data, historical tubing parameters, and historical lowering parameters from the historical working data. The specific steps are as follows: According to the complexity of the automated pressure-bearing equipment, data processing needs, and real-time requirements, TensorFlow was selected to design the module architecture, determine the data input layer, hidden layer structure, and output layer configuration to adapt to the analysis and processing tasks of various parameters, and then develop a special data access program to establish a connection with the database that stores the historical working data of the automated pressure-bearing equipment.

[0018] S2, collecting the operating well data and working tubing parameters, dividing the operating well into downhole areas according to the differences in the operating well data, and predicting the pressure fluctuation of each downhole area in combination with the working tubing parameters; The steps of S2 are as follows: S2.1. Use the sensor network to establish data acquisition connection between the operating well sensor and the tubing sensor and the automated pressure equipment, obtain the operating well data through the data fed back by the operating well sensor, and then obtain the working tubing parameters through the data fed back by the tubing sensor. The specific steps are as follows: Select pressure sensors, temperature sensors, liquid level sensors, etc. for the operating wells, and install operating well sensors at key locations of the operating wells, such as the bottom of the well, the interface between different oil layers, and the wellhead; Equip the oil pipe with strain sensors, acceleration sensors, and flow sensors. Install oil pipe sensors along the axial direction of the oil pipe at the oil pipe joints, easily deformed parts, and key monitoring sections to ensure that comprehensive information reflecting the equipment status can be obtained; Data collection of working wells: The automated pressure-bearing equipment sends collection instructions to the working well sensors through the configured network connection according to the set sampling frequency. After receiving the instructions, the working well sensors collect data such as pressure, temperature, and liquid level in real time, and encapsulate these data into data packets and send them back to the equipment. The collected working well data is then cached on the equipment side, waiting for further processing; Oil pipeline data collection: Data is also collected from the oil pipeline sensor at a set frequency. The collected oil pipeline parameter data is also cached on the device side and verified.

[0019] S2.2. Establish an operating well model based on the operating well data, and obtain the overall downhole area that the oil pipe needs to pass through in the operating well model. Then, divide the overall downhole area into multiple downhole areas according to different geographical locations and pressure differences. The specific steps are as follows: 3D operating well model construction: Using computer-aided design, with depth as the vertical axis and the well inclination angle as the direction vector, a 3D spatial trajectory model of the operating well is constructed. At the same time, in the model, corresponding pressure attribute values ​​are assigned to different depth areas based on pressure data, and the temperature field distribution is marked according to temperature data. The materials and characteristics of different formations are distinguished by combining formation lithology information. For example, sandstone formations and shale formations have different identifiers and parameter settings in the model; Determination of the overall downhole area for tubing lowering: The starting point of tubing lowering is usually the wellhead, whose coordinates can be set as the origin in the model, and the end point is the bottom of the operating well, which is known through the measurement of the operating well depth. The spatial range covered by the trajectory of the three-dimensional operating well model extending downward from the wellhead to the bottom of the well is the overall downhole area that the tubing needs to pass through; Pressure-dominated segmentation: Analyze the changing trend of pressure data along the depth direction of the operating well. When the pressure change rate exceeds the preset threshold, this point is used as a segmentation node. The formula is as follows:

[0020] Where rp is the pressure change rate, P i is a discrete pressure data sequence, i=1,2,...,n, Δh is the depth interval, ΔP th is the threshold value, when rp>ΔP th , as a segment node; At the same time, combined with the well inclination data and formation lithology information, when the well inclination angle changes beyond a certain angle threshold, such as entering a curved area with a large dogleg angle from a relatively flat area, or encountering a significant change in the formation lithology, these areas will be used as segmentation nodes even if the pressure change is not significant.

[0021] S2.3. Predict the pressure fluctuation of each downhole area in combination with the working tubing parameters to obtain the predicted pressure fluctuation corresponding to each downhole area. The formula is as follows:

[0022] Among them, P sli is the initial static pressure at a point in the depth direction of the i-th section of the downhole area, g is the gravitational acceleration, P 0i is the initial formation pressure of the ith downhole area, ρ s is the formation density, hh i1 is the depth difference of the downhole area in the ith section;

[0023] Where Gt is the deadweight of the tubing, ρ t is the density of the tubing material, V t is the volume of the oil pipe;

[0024] Among them, Δσ zi is the vertical stress increment, h is the depth in the downhole area, v s is the formation Poisson's ratio.

[0025]

[0026] Among them, P ri is the radial pressure of the formation on the tubing, E s is the formation elastic modulus, E t is the elastic modulus of the tubing material, Δr s为 The deformation of the stratum in the radial direction, Δr t is the deformation of the oil pipe in the radial direction;

[0027] Among them, P maxi is the maximum predicted pressure in this area, P mini is the minimum predicted pressure in this section, ΔP wi is the pressure fluctuation range of this section.

[0028] S3, combining historical operating well data, historical tubing parameters and historical lowering parameters with automated pressure equipment to establish a tubing lowering simulation model, and then combining the tubing lowering simulation model with the predicted pressure fluctuations of each downhole area to perform working lowering parameter analysis; The steps of S3 are as follows: S3.1. Combine historical well data, historical tubing parameters and historical lowering parameters with automated pressure equipment to establish a tubing lowering simulation model. Select the finite element method to build the model. The steps are as follows: Data integration: retrieve historical operating well data from the database, including operating well trajectory, formation characteristics; historical tubing parameters, such as tubing length, outer diameter, inner diameter, elastic modulus, yield strength; historical lowering parameters, such as past lowering speed, lowering force, lowering time, etc.; Model selection and construction: Based on physical principles, the model was constructed using the finite element analysis method. The model was then verified using historical successful case data. The model-predicted results of tubing deformation, stress distribution, etc. were compared with the actual recorded data. The model parameters were adjusted to keep the model prediction error within an acceptable range.

[0029] S3.2. Combine the tubing lowering simulation model with the predicted pressure fluctuation of each downhole area to analyze the working lowering parameters, obtain the working lowering parameters corresponding to each downhole area, and then adjust the working lowering parameters of each downhole area safely according to the order of tubing lowering, so as to avoid the large difference in lowering speed between the two areas, which may lead to abnormal pressure. The specific steps are as follows:

[0030] Among them, S ij is the sensitivity coefficient of the i-th output result to the j-th input parameter, y i is the i-th output result, which can be key indicators such as the maximum stress and maximum deformation of the oil pipe. j is the jth input parameter, which can be the tubing lowering speed, lowering start time, lowering interval, formation pressure, well inclination angle, etc. These are all parameters that can be changed and adjusted in the model. j The input parameter x j Small changes in In the tubing lowering simulation model, parameter sensitivity analysis can be used to determine which parameters have the greatest impact on key output results such as the mechanical properties of the tubing and pressure changes during the lowering process. If it is found that the sensitivity coefficient of the tubing lowering speed to the maximum stress of the tubing is very high, it means that in actual operation, special attention should be paid to and the lowering speed should be precisely controlled to ensure the safety of the tubing. At the same time, for parameters with lower sensitivity, their value range can be appropriately relaxed within a certain range, thereby providing a basis for optimizing the lowering parameters and improving the efficiency and safety of the tubing lowering operation. Assume that the order of the areas through which the oil pipe passes is k=1,2,...,p. To avoid the pressure abnormality caused by the large velocity difference between adjacent areas, the velocity difference threshold Δv between adjacent areas is set. th , Δv th Determined based on experience and the pressure bearing capacity of the oil pipe and formation; The initial lowering speed v of each section is known. k , starting from the first segment, check the speed difference between two adjacent segments |vk+1 -v k ∣, if it is greater than Δv th , then adjust the speed v of the next section k+1 , v k+1 The adjustment formula is as follows:

[0031] Among them, α is the weighting coefficient, which makes the speed transition gradually and avoids sudden changes. Then repeat this process until all areas are traversed, and finally obtain the work release parameters corresponding to each downhole area that meets the speed stability requirements. S4, combining the working lowering parameters of each downhole area with the operating well data and working tubing parameters to predict tubing deviation, and combining the predicted tubing deviation with historical righting parameters to perform working righting parameter analysis; The steps of S4 are as follows: S4.1. The working parameters of each downhole area are combined with the operating well data and working tubing parameters to predict the tubing deviation, and the predicted tubing deviation that will occur when the tubing passes through each downhole area is obtained. The formula is as follows:

[0032] Among them, EI is the bending stiffness, y is the displacement of the tubing in the direction perpendicular to the wellbore axis, that is, the deviation, x is equivalent to the depth d, q(x) is the distributed load function of the comprehensive force (gravity, formation friction, and formation pressure lateral force). The equation is solved by numerical method to obtain the predicted tubing deviation at different depths in each section of the downhole area.

[0033] S4.2. The predicted tubing deviation is combined with the historical righting parameters and the working lowering parameters to analyze the working righting parameters, and the working righting parameters that can keep the tubing consistent with the wellbore center are obtained. i A centralizer is installed at the position where the formula is as follows:

[0034] Among them, F r is the radial support force generated by the centralizer, k r is its own stiffness, d i is the depth, y(d i ) is the deviation corresponding to the depth. The radial support force will directly act on the tubing, causing it to move closer to the center of the wellbore and offset all deviations. Start to conduct simulation tests on different combinations of centralizer parameters, that is, by changing key parameters such as the type, installation spacing, and quantity of the centralizer, run the simulation program multiple times, observe the real-time deviation changes of the oil pipe in each section of the downhole area, and record in detail the degree of fit between the oil pipe and the center of the wellbore in each simulation. Generally, indicators such as average deviation value and maximum deviation value can be used for quantitative evaluation.

[0035] Comprehensively consider the data on the straightening effect obtained during the simulation process, such as which type of centralizer and what installation spacing can minimize the average deviation of the oil pipe in each section of the downhole area, while taking into account many practical factors such as construction cost, construction difficulty, equipment reliability, etc. For example, a rigid centralizer has strong support but may be inconvenient to install, and an elastic centralizer has good adaptability but limited ability to correct larger deviations. We must weigh the pros and cons and ultimately select one or several sets of optimal working straightening parameter combinations that can effectively keep the oil pipe consistent with the center of the wellbore, including specific parameter values ​​such as the type of centralizer, installation spacing, and quantity.

[0036] S5. During the process of lowering the tubing, the tubing position and the wellbore center are detected for deviation in real time. When deviation occurs, the deviation data is combined with the working righting parameters for parameter selection analysis, and the working righting parameters are input according to the selection results.

[0037] The steps of S5 are as follows: S5.1. During the lowering process of the oil pipe, the position of the oil pipe is monitored in real time, and then the deviation between the position of the oil pipe and the center of the wellbore is detected in real time; With the help of high-precision sensors installed at specific locations underground, the real-time position information of the oil pipe is captured at every moment the oil pipe is lowered, and the three-dimensional coordinate data of the oil pipe is accurately fed back, covering the axial, radial and circumferential position details. The real-time position data of the oil pipe obtained is simultaneously compared with the wellbore center coordinates obtained by modeling, and the difference algorithm is used to calculate the deviation vector between the two, including radial deviation and axial deviation.

[0038] S5.2, when S5.1 shows that the tubing position and the wellbore center are offset, the deviation data is combined with the working righting parameter to perform similarity matching with the predicted tubing deviation. When the deviation data is consistent with one of the predicted tubing deviation data, the working righting parameter corresponding to the predicted tubing deviation data is selected and sent to the automated pressurized equipment. On the contrary, when the deviation data and the predicted tubing deviation data are not the same, all the working righting parameters are combined with the deviation data for safety righting analysis, and the working righting parameter with the best righting effect is selected and sent to the automated pressurized equipment. S5.3. When S5.1 shows that there is no deviation between the tubing position and the wellbore center, continue monitoring. The specific steps are as follows: Similarity matching: Once it is determined that the tubing position and the wellbore center are offset, the similarity matching process is immediately started to compare the currently calculated real-time deviation data with the multiple sets of tubing deviation data previously simulated, predicted and stored based on different working conditions. Parameter selection and adjustment: If the predicted tubing deviation data that highly matches the current deviation data is found, the corresponding working righting parameters are directly extracted and quickly transmitted to the automated pressure-bearing equipment. After receiving the instructions, the equipment accurately controls the righting device to perform the corresponding actions. If the current deviation data does not match all the predicted values, all existing working righting parameters are immediately substituted into the safety righting analysis model in combination with the current deviation data. This model comprehensively considers factors such as the force balance of the tubing, formation friction, and fluid impact force, and simulates the subsequent movement trend of the tubing under different righting parameters. The righting effect (such as the rate at which the tubing deviation decreases in a subsequent specific time period and the degree to which it eventually approaches the center of the wellbore) is used as an evaluation indicator. Through traversal analysis, the righting parameter combination with the best righting effect is selected and sent to the automated pressure-carrying equipment to drive the correction operation. The formula is as follows:

[0039] Among them, R avg is the average deviation reduction rate, Δy i is the oil pipe deviation value at the i-th monitoring, Δy i+1 is the oil pipe deviation value at the i+1th monitoring, n is the number of monitoring times, R avg It reflects the average reduction ratio of tubing deviation over a period of time. The larger the value, the better the righting effect.

[0040] Among them, A avg is the average convergence, D is the maximum allowable deviation or wellbore radius, A avg It indicates the average degree of convergence of the tubing deviation value to the reference value, with a value range of 0-100. The closer it is to 100, the closer the tubing is to the wellbore center, and the better the straightening effect.

[0041] Among them, FZ is the comprehensive index of the righting effect, χ, δ, η, μ are weight coefficients determined according to the actual situation. By adjusting the weights, the influence of different aspects on the righting effect can be highlighted. target To record the time from the start of straightening to the time when the tubing deviation reaches or is less than the set target deviation value for the first time. The shorter the time, the better the straightening effect. stable It is the time required from the start of righting to the tubing deviation being stable within a certain range. The shorter the stabilization time, the faster the righting measures can stabilize the tubing in a better position and the better the righting effect. FZ can evaluate the righting effect more comprehensively. The larger the value, the better the righting effect.

[0042] Non-deviation monitoring and early warning: When there is no deviation between the oil pipe position and the wellbore center, the system is continuously in monitoring standby mode, collecting and updating position data at a fixed frequency to ensure that possible deviation signs can be keenly captured at any time; Once the working straightening parameters were entered, monitoring revealed that the deviation trend between the oil pipe position and the wellbore center was not curbed but continued to expand, immediately triggering an early warning alarm to notify on-site staff.

[0043] After the working righting parameters are input in S5, if the deviation trend between the oil pipe position and the wellbore center is still expanding, an early warning alarm is issued to the staff.

[0044] The second object of the present invention is to provide an artificial intelligence-based automated pressure-bearing equipment operating system, including any one of the above-mentioned artificial intelligence-based automated pressure-bearing equipment operating methods, including.

[0045] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An artificial intelligence-based automated pressure equipment operation method, characterized in that: The steps include: S1. Extract historical working data of automated pressure-bearing equipment, and extract historical righting parameters, historical operating well data, historical tubing parameters, and historical lowering parameters from the historical working data; S2, collecting the operating well data and working tubing parameters, dividing the operating well into downhole areas according to the differences in the operating well data, and predicting the pressure fluctuation of each downhole area in combination with the working tubing parameters; S3, combining historical operating well data, historical tubing parameters and historical lowering parameters with automated pressure equipment to establish a tubing lowering simulation model, and then combining the tubing lowering simulation model with the predicted pressure fluctuations of each downhole area to perform working lowering parameter analysis; S4, combining the working lowering parameters of each downhole area with the operating well data and working tubing parameters to predict tubing deviation, and combining the predicted tubing deviation with historical righting parameters to perform working righting parameter analysis; S5. During the process of lowering the tubing, the tubing position and the wellbore center are detected for deviation in real time. When deviation occurs, the deviation data is combined with the working righting parameters for parameter selection analysis, and the working righting parameters are input according to the selection results.

2. According to claim 1, an artificial intelligence-based automated pressure equipment operation method is characterized by: The S1 establishes an artificial intelligence module in the automated pressure-bearing equipment, records the historical working data of the automated pressure-bearing equipment through the artificial intelligence module, and extracts historical righting parameters, historical operating well data, historical tubing parameters, and historical lowering parameters from the historical working data.

3. The method for operating an automated pressure-bearing equipment based on artificial intelligence according to claim 1, characterized in that: The steps of S2 are as follows: S2.

1. Establish data acquisition connection between the operating well sensor and the oil pipe sensor and the automated pressure equipment with the help of the sensor network, obtain the operating well data through the data fed back by the operating well sensor, and then obtain the working oil pipe parameters through the data fed back by the oil pipe sensor; S2.

2. Establish an operating well model based on the operating well data, and obtain the overall downhole area through which the oil pipe needs to be lowered in the operating well model. Then, divide the overall downhole area into multiple downhole areas according to different geographical locations and pressure differences; S2.

3. Predict the pressure fluctuation of each downhole area in combination with the working oil pipe parameters to obtain the predicted pressure fluctuation corresponding to each downhole area.

4. The method for operating an automated pressure-bearing equipment based on artificial intelligence according to claim 1, characterized in that: The steps of S3 are as follows: S3.

1. Establish a tubing lowering simulation model by combining historical operating well data, historical tubing parameters and historical lowering parameters with automated pressure equipment; S3.

2. Combine the tubing lowering simulation model with the predicted pressure fluctuation of each downhole area to analyze the working lowering parameters, obtain the working lowering parameters corresponding to each downhole area, and then adjust the working lowering parameters of each downhole area safely according to the average speed in the order of tubing lowering.

5. The method for operating an automated pressure-bearing equipment based on artificial intelligence according to claim 1, characterized in that: The steps of S4 are as follows: S4.

1. The working lowering parameters of each section of the downhole area are combined with the working well data and the working tubing parameters to predict the tubing deviation, and obtain the predicted tubing deviation that will occur with probability when the tubing passes through each section of the downhole area; S4.

2. The predicted tubing deviation is combined with the historical righting parameters and the working lowering parameters to perform working righting parameter analysis, and obtain working righting parameters that can keep the tubing consistent with the wellbore center.

6. The method for operating an automated pressure-bearing equipment based on artificial intelligence according to claim 1, characterized in that: The steps of S5 are as follows: S5.

1. During the lowering process of the oil pipe, the position of the oil pipe is monitored in real time, and then the deviation between the position of the oil pipe and the center of the wellbore is detected in real time; S5.2, when S5.1 shows that the tubing position and the wellbore center are offset, the deviation data is combined with the working righting parameter to perform similarity matching with the predicted tubing deviation. When the deviation data is consistent with one of the predicted tubing deviation data, the working righting parameter corresponding to the predicted tubing deviation data is selected and sent to the automated pressure equipment. On the contrary, when the deviation data and the predicted tubing deviation data are not the same, the deviation data is combined with the automated pressure equipment to perform new working righting parameter analysis, and the newly generated working righting parameter is sent to the automated pressure equipment. S5.

3. When S5.1 shows that there is no deviation between the tubing position and the wellbore center, continue monitoring.

7. The method for operating an automated pressure-bearing equipment based on artificial intelligence according to claim 1, characterized in that: After the working righting parameters are input in S5, if the deviation trend between the oil pipe position and the wellbore center is still expanding, an early warning alarm is issued to the staff.

8. An artificial intelligence-based automated pressure-carrying equipment operating system, used to implement an artificial intelligence-based automated pressure-carrying equipment operating method as described in any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a parameter generation module and a parameter input module; The data acquisition module is used to extract the historical working data of the automated pressure-bearing equipment, collect the working well data and working tubing parameters, segment the working wells into downhole areas according to the differences in the working well data, and predict the pressure fluctuations; The parameter generation module is used to establish a tubing lowering simulation model, combine the tubing lowering simulation model with the predicted pressure fluctuation of each downhole area to perform working lowering parameter analysis, then combine the working lowering parameters of each downhole area with the operating well data and the working tubing parameters to predict tubing deviation, and combine the predicted tubing deviation with the historical righting parameters to perform working righting parameter analysis; The parameter input module is used to detect the real-time deviation between the tubing position and the wellbore center during the tubing lowering process. When deviation occurs, the deviation data is combined with the working righting parameters for parameter selection analysis, and the working righting parameters are input according to the selection results.

Images