Fusion quantum optimization plugging slim hole horizontal section intelligent workover method and system

Abstract

The application discloses a small-hole horizontal section intelligent workover method and system fusing quantum optimization plugging, and the method comprises the following steps: downhole data acquisition, edge computing preprocessing, digital twin modeling, quantum-classical hybrid optimization decision, variable-diameter tool execution and effect monitoring feedback, etc. The system is composed of data acquisition, edge computing, digital twin, quantum optimization plugging, dynamic variable-diameter tool, plugging execution mechanism and monitoring feedback components, and is cooperated through a standardized interface. A quantum-classical hybrid algorithm is used to optimize plugging parameters with a multi-objective function, the dynamic variable-diameter tool is adapted to well conditions, intelligent workover is realized, plugging efficiency and effect are improved, the complex downhole environment is adapted, stable and efficient operation is ensured, and the optimization and upgrading of oil and gas field small-hole horizontal section workover operation are facilitated.

Description

Technical Field

[0001] This invention belongs to the interdisciplinary technical field of oil and gas field development engineering and petroleum intelligent equipment. Specifically, it involves the integrated application of downhole tools and well workover technology, quantum computing and optimization algorithms, intelligent well workover systems and digital oilfield technology. It is particularly suitable for intelligent well workover operations in the horizontal section of small wellbore during the development of unconventional oil and gas resources (such as shale gas and tight oil). It can realize dynamic adaptation of downhole tools, intelligent optimization of plugging parameters and automated closed-loop control of the well workover process, and promote the development of oil and gas field well workover operations towards high efficiency, automation and digitalization. Background Technology

[0002] With the growth of global energy demand and the increasing depletion of conventional oil and gas resources, the development of unconventional oil and gas resources (such as shale gas and tight oil) has become the mainstream direction of the oil and gas field industry. Small-diameter horizontal wells are widely used in shale oil and gas and tight reservoir development due to their significant advantages—both reducing drilling costs (20%-30% lower than conventional wells) and increasing single-well production by extending the horizontal section length (up to several kilometers) (3-5 times higher than vertical wells).

[0003] However, well workover operations for small-diameter horizontal wells face multiple technical bottlenecks, severely restricting their development efficiency and safety:

[0004] Poor adaptability of downhole tools: Small wellbore horizontal sections have irregular well conditions such as diameter reduction and erosion. The wellbore diameter usually fluctuates in the range of Φ88.9-120.6mm. Traditional workover tools adopt a fixed size design and cannot dynamically adapt to the diameter changes of different well sections. Not only is it difficult to effectively reach the target operation position of a horizontal section that is thousands of meters long, but it is also easy to cause tool jamming accidents due to size mismatch, resulting in operation interruption or even wellbore scrapping.

[0005] The sealing efficiency is low and the reliability is insufficient: horizontal sections are prone to crack-like leakage (the leakage rate often reaches 100-150L / min), and conventional sealing materials (such as cement grout and gel) are prone to failure under the scouring action of fluid in horizontal sections; at the same time, traditional sealing solutions rely on manual experience to select parameters such as material type, concentration and pumping rate, lacking scientific optimization methods, resulting in a sealing success rate of only 60%-70%, and the construction time is as long as 4-6 hours, with high costs.

[0006] The well workover process is highly dependent on manual labor: the parameter monitoring, scheme decision-making and tool control of existing well workover operations all rely on the experience judgment of on-site personnel. There is a lack of real-time data feedback mechanism and automated decision support system, which makes it difficult to cope with complex and changeable working conditions such as high temperature (usually >150℃), high pressure (usually >70MPa) and fluid corrosivity downhole. The decision response time exceeds 1 hour, which cannot meet the timeliness requirements of "smart oilfields".

[0007] Insufficient integration of interdisciplinary technologies: The integration of cutting-edge technologies such as quantum computing, digital twins, and edge computing with petroleum engineering is low. It is impossible to use the parallel advantages of quantum computing to quickly solve multi-parameter combination problems of plugging leaks, and it is also difficult to achieve high-fidelity simulation and scheme pre-drilling of the downhole environment through digital twins, which limits the level of intelligence of well workover operations.

[0008] Despite industry attempts to improve the situation, such as developing specialized small-bore tools or optimizing plugging material formulations, core bottlenecks remain unresolved: at the tool level, real-time downhole diameter changes are impossible; at the algorithm level, efficient multi-parameter optimization methods are lacking; and at the system level, an automated closed loop of "perception-decision-execution-feedback" has not been established. Therefore, a solution integrating dynamic diameter-changing tools, quantum-optimized plugging technology, and intelligent control systems is urgently needed to address the aforementioned challenges in small-bore horizontal well workover operations. Summary of the Invention

[0009] The purpose of this invention is to propose an intelligent well workover method and system for small-bore horizontal sections that integrates quantum-optimized plugging techniques. This aims to address issues such as poor downhole tool adaptability, low plugging efficiency, high reliance on manual labor, and insufficient integration of interdisciplinary technologies in existing small-bore horizontal section well workover operations. This method and system achieve dynamic adaptation of downhole tools, intelligent optimization of plugging parameters, and automated closed-loop control of the well workover process through a series of steps and components, including multi-source data acquisition, digital twin dynamic modeling, quantum-classical hybrid algorithm optimization of plugging parameters, dynamic variable-diameter tool adaptation to well conditions, and real-time monitoring and feedback.

[0010] To achieve the above objectives, this invention first discloses an intelligent well workover method for small-bore horizontal sections that integrates quantum-optimized plugging, the key of which includes the following steps:

[0011] S1. Real-time downhole data acquisition: Downhole data is acquired in real time through a sensor network. The downhole data includes well diameter, leakage rate, fracture type, formation temperature, formation pressure, and fluid velocity.

[0012] S2. Edge computing preprocessing: The real-time downhole data collected in step S1 is filtered, denoised, feature extracted and standardized protocol converted using edge computing nodes to obtain preprocessed data suitable for digital twin modeling and quantum optimization computing.

[0013] S3. Digital Twin Dynamic Modeling: The digital twin unit constructs a virtual downhole environment based on the preprocessed data in step S2, calls the geomechanical model and fluid dynamics model for dynamic modeling, simulates the implementation effect of different plugging schemes and assesses the risk level;

[0014] S4. Quantum-Classical Hybrid Optimization and Leak Plugging Parameter Decision: The quantum optimization leak plugging module receives the dynamic modeling results from step S3, optimizes the leak plugging parameters using a quantum-classical hybrid algorithm, solves for the theoretically optimal combination of leak plugging parameters, and determines the final leak plugging parameter decision result by combining the actual engineering constraints; the leak plugging parameters include the type of leak plugging material, material concentration, and pumping rate;

[0015] S5. Execution of the variable diameter tool and plugging operation: The edge computing node converts the final plugging parameter decision result of step S4 into control commands, which are then sent to the dynamic variable diameter tool and the plugging execution mechanism respectively. The dynamic variable diameter tool adjusts its own size according to the commands to adapt to the downhole conditions, and the plugging execution mechanism injects plugging material according to the commands to perform the plugging operation.

[0016] S6. Effect Monitoring Feedback and Operation Completion Judgment: The effect data after the downhole plugging operation is monitored in real time through a sensor network. The effect data includes changes in leakage, tool operating status, and downhole temperature and pressure data. If the leakage is not completely plugged, the process returns to step S3 to re-perform digital twin dynamic modeling. If the tool becomes stuck, the emergency adjustment procedure of the dynamic diameter-changing tool is triggered. If the downhole temperature and pressure are abnormal, the system self-protection mode is activated. If the plugging effect meets the standards and the tool is operating normally, the well workover operation is completed.

[0017] Furthermore, in step S4, the quantum-classical hybrid algorithm optimizes the discrete plugging parameters using the QUBO model, the expression of which is:

[0018]

[0019] J ij h represents the coupling strength between parameters, signifying the interaction between different discrete plugging parameters. i , is a single-parameter bias term, representing the weight of a single discrete plugging parameter, where x is a discrete plugging parameter variable, specifically the variable corresponding to the plugging material type; in the quantum-classical hybrid algorithm, the quantum annealing algorithm is used to process the discrete plugging parameters, and the classical genetic algorithm is used to optimize the continuous plugging parameters, which include material concentration and pumping rate.

[0020] Furthermore, in step S4, the quantum-classical hybrid algorithm achieves a minimum... x (f leak (x)+λ·f cost (x) is the objective function for solving the theoretically optimal combination of plugging parameters; where x is the combination of plugging parameters, including but not limited to material type, concentration, and pump speed; f leak A leakage prediction model based on fluid dynamics; f costλ is a construction cost function that includes material and operation costs; λ is a weighting coefficient that balances the effect and cost, and the weighting coefficient is dynamically adjusted with well depth.

[0021] Furthermore, step S4 also includes predicting the leakage amount using a data-driven model, the expression of which is:

[0022] f leak (x) = α·ReLU (W·x+b);

[0023] Where W and b are the weights of the neural network, which are obtained by training with historical well leakage data, α is the working condition correction coefficient, which is used to correct the influence of downhole temperature and pressure on the leakage prediction results, and x is the continuous plugging parameter variable.

[0024] Furthermore, in step S1, the data sampling frequency of the sensor network is 10Hz; in step S2, the preprocessing delay of the edge computing node is less than 50ms; in step S5, the total decision delay from real-time acquisition of downhole data to issuance of control commands is less than 200ms, and the control commands are issued via mud pulse transmission or 5G wireless transmission; in step S5, the wellbore diameter range adapted to the dynamic diameter-changing tool is Φ88.9-120.6mm, and it can achieve ±15% dynamic diameter adjustment.

[0025] Based on the foregoing description, this invention also discloses a system for implementing the intelligent well workover method for small-bore horizontal sections with fusion quantum-optimized plugging, the key of which includes:

[0026] The data acquisition subsystem is used to perform real-time downhole data acquisition, including ultrasonic caliper measuring equipment, formation pressure sensor, temperature sensor, flow meter and vibration sensor, to acquire downhole caliper, leakage, temperature and pressure data, etc.

[0027] Edge computing nodes are used to perform edge computing preprocessing, including filtering, denoising, feature extraction, and format conversion of real-time data collected by the data acquisition subsystem.

[0028] The digital twin unit is used to perform dynamic modeling of digital twins, construct a virtual downhole environment based on preprocessed data output from edge computing nodes, and dynamically simulate and evaluate the risks of plugging schemes through multi-subdomain models.

[0029] The quantum-optimized plugging module is used to perform quantum-classical hybrid optimization and plugging parameter decision-making. It receives the simulation results of the digital twin unit, optimizes the plugging parameters through the quantum-classical hybrid algorithm, and determines the final decision result.

[0030] The dynamic diameter adjustment tool is used to perform diameter adjustment operations, adjusting its own size according to the control commands issued by the edge computing node to adapt to the well conditions;

[0031] A leak-sealing actuator is used to perform leak-sealing operations and injects leak-sealing materials based on the final leak-sealing parameter decision results.

[0032] The monitoring and feedback component is used to perform effect monitoring and feedback, collect downhole effect data after plugging in real time and feed it back to the edge computing node;

[0033] The data acquisition subsystem, edge computing node, digital twin unit, quantum-optimized leak-stopping module, dynamic diameter-changing tool, leak-stopping execution mechanism, and monitoring feedback component work together through standardized data interfaces to form an automated closed-loop control from data acquisition to operation completion.

[0034] Furthermore, the dynamic diameter-adjusting tool is compatible with wellbore diameters ranging from Φ88.9 to 120.6 mm, and can achieve dynamic diameter adjustment of ±15%. The outer diameter of the dynamic diameter-adjusting tool is no greater than 95 mm, and the length is no greater than 2 m. The dynamic diameter-adjusting tool can withstand downhole pressures of no less than 70 MPa and downhole temperatures of no less than 150 °C. The dynamic diameter-adjusting tool includes a power module, an execution module, and a control unit. The power module and the execution module adopt a modular design. The control unit is electrically connected to both the power module and the execution module, and is used to receive data and control the power module to drive the execution module.

[0035] Furthermore, the power module includes a hydraulic circuit consisting of a micro hydraulic pump, a pressure accumulator, and an electromagnetic directional valve assembly. The micro hydraulic pump provides hydraulic power, the pressure accumulator stabilizes the hydraulic system pressure, and the electromagnetic directional valve assembly controls the flow direction of the hydraulic oil. The execution module includes at least two sets of telescopic arms, radial support sliders, displacement sensors, and shape memory alloy auxiliary return springs. The telescopic arms are distributed circumferentially, the radial support sliders are located at the ends of the telescopic arms for contact and support with the well wall, the displacement sensors monitor the telescopic arm's extension and retraction in real time, and the shape memory alloy auxiliary return springs are located in the extension and retraction path of the telescopic arms to assist in the return action of the telescopic arms.

[0036] Furthermore, the power module is equipped with dual hydraulic circuits to achieve redundant control. When one hydraulic circuit fails, it automatically switches to the backup hydraulic circuit. The control unit receives the extension / retraction data transmitted by the displacement sensor and the well diameter data from the monitoring feedback component. When the well diameter is less than the set value minus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm drive chamber, driving the telescopic arm to extend. At this time, the shape memory alloy auxiliary return spring is stretched. When the well diameter is greater than the set value plus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm retraction chamber. At the same time, the shape memory alloy auxiliary return spring releases its elastic potential energy to assist the telescopic arm in emergency retraction.

[0037] Furthermore, it also includes an extreme environment adaptation module, which comprises a high-temperature resistant packaging component and an adaptive power management unit; the high-temperature resistant packaging component adopts a ceramic substrate and gold wire bonding process, and has a temperature resistance of not less than 250°C; the power control algorithm expression of the adaptive power management unit is:

[0038] P dynamic =P base ·e -0.01(T-150) ;

[0039] Where P dynamic For dynamic power consumption, P base The reference power consumption is T, and the actual downhole temperature is T. This algorithm enables temperature-adaptive frequency reduction, ensuring stable operation of the system under high temperature and high pressure until the operation is completed.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] (1) Solved the problem of downhole tool compatibility: Traditional workover tools cannot adapt to irregular well conditions in small horizontal sections, thus effectively solving problems such as jamming and operation interruption. The dynamic variable diameter tool can dynamically adjust its own diameter based on real-time well diameter data, achieving ±15% dynamic diameter adjustment within the well diameter range of Φ88.9-120.6mm, thereby ensuring that the tool can smoothly reach the target operation position in a horizontal section several kilometers long. This greatly improves the tool's passability and the continuity of operation, avoids the risk of well abandonment due to tool jamming, reduces the risk of tool jamming from "high" to "extremely low", and increases the success rate of construction to over 95%.

[0042] (2) Significantly improved sealing efficiency and reliability: By optimizing sealing parameters through a quantum-classical hybrid algorithm and combining it with digital twin technology to simulate the implementation effects of different sealing schemes, the success rate of sealing has been increased from the traditional 60%-70% to over 92%. Simultaneously, construction time has been shortened from 4-6 hours to 2-3 hours, effectively reducing operating costs. Quantum optimization calculations can quickly solve for the theoretically optimal combination of sealing parameters, including the type of sealing material, material concentration, and pumping rate, ensuring that the sealing material maintains a good sealing effect even under the scouring action of fluid in the horizontal section.

[0043] (3) Automation and intelligence of the well workover process: This invention establishes an automated closed-loop control system of "perception-decision-execution-feedback," reducing the reliance on human experience in the well workover process. The sensor network collects downhole data in real time, edge computing nodes preprocess the data, digital twin units perform dynamic modeling and scheme simulation, the quantum-optimized plugging module implements parameter optimization decisions, the dynamic diameter-changing tool and plugging execution mechanism perform the work, and the monitoring and feedback component provides real-time feedback on the work results. Throughout the process, the decision response time is reduced from over 1 hour to less than 200 ms, enabling rapid response to complex and variable working conditions such as high temperature, high pressure, and fluid corrosivity downhole, meeting the timeliness requirements of "intelligent oilfields," and improving work accuracy by 30%.

[0044] (4) It promotes the deep integration of interdisciplinary technologies: It closely integrates cutting-edge technologies such as quantum computing, digital twins, and edge computing with petroleum engineering. The parallel advantages of quantum computing are used to quickly solve multi-parameter combination problems in well plugging, digital twins realize high-fidelity simulation and scheme pre-playing of the downhole environment, and edge computing improves the efficiency of data processing and decision-making. This integration of interdisciplinary technologies has brought new technical means and solutions to well workover operations in small-diameter horizontal sections, and improved the level of intelligence of the entire industry.

[0045] (5) Improved system adaptability to extreme environments: By setting up an extreme environment adaptation module, the system can operate stably under harsh conditions such as high temperature and high pressure. The high-temperature resistant packaging component uses a ceramic substrate and gold wire bonding process, with a temperature resistance of not less than 250℃ and a stable operating time of more than 100 hours under 70MPa environment, which can meet the operation requirements of deep small-diameter horizontal sections and effectively protect the electronic components inside the system. The adaptive power management unit uses a power control algorithm to achieve temperature-adaptive frequency reduction, ensuring the power consumption stability of the system under high temperature environment, extending the service life of the system, and ensuring that well workover operations can be carried out smoothly.

[0046] In summary, the intelligent well workover method and system for small-bore horizontal sections proposed in this invention, which integrates quantum-optimized plugging, has achieved remarkable results in solving the existing problems of well workover operations in small-bore horizontal sections, and provides strong technical support for the efficient development of resources such as shale oil and gas and tight reservoirs. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1This is a flowchart illustrating the operation of the intelligent well workover method for the horizontal section of a small wellbore in Example 1.

[0049] Figure 2 This is a schematic diagram of the data flow of the intelligent well workover method for the horizontal section of a small wellbore in Example 1;

[0050] Figure 3 This is a schematic diagram of the technical process for dynamic modeling of digital twins in Example 1;

[0051] Figure 4 This is a schematic diagram of the overall architecture of the quantum-classical hybrid algorithm in Example 1;

[0052] Figure 5 This is a three-dimensional exploded view of the dynamic diameter changing tool in Example 1;

[0053] Figure 6 This is a schematic diagram of the core mechanism of the dynamic diameter changing tool in Embodiment 1;

[0054] Figure 7 This is a schematic diagram of the control logic of the dynamic diameter changing tool in Example 1; Detailed Implementation

[0055] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0056] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0057] Figures 1 to 7 The first embodiment of the present invention is shown: a smart well workover method for small-bore horizontal sections integrating quantum-optimized plugging, comprising the following steps:

[0058] S1. Real-time downhole data acquisition: Downhole data is acquired in real time through a sensor network. The downhole data includes well diameter, leakage rate, fracture type, formation temperature, formation pressure, and fluid velocity.

[0059] S2. Edge computing preprocessing: The real-time downhole data collected in step S1 is filtered, denoised, feature extracted and standardized protocol converted using edge computing nodes to obtain preprocessed data suitable for digital twin modeling and quantum optimization computing.

[0060] S3. Digital Twin Dynamic Modeling: The digital twin unit constructs a virtual downhole environment based on the preprocessed data in step S2, calls the geomechanical model and fluid dynamics model for dynamic modeling, simulates the implementation effect of different plugging schemes and assesses the risk level;

[0061] S4. Quantum-Classical Hybrid Optimization and Leak Plugging Parameter Decision: The quantum optimization leak plugging module receives the dynamic modeling results from step S3, optimizes the leak plugging parameters using a quantum-classical hybrid algorithm, solves for the theoretically optimal combination of leak plugging parameters, and determines the final leak plugging parameter decision result by combining the actual engineering constraints; the leak plugging parameters include the type of leak plugging material, material concentration, and pumping rate;

[0062] S5. Execution of the variable diameter tool and plugging operation: The edge computing node converts the final plugging parameter decision result of step S4 into control commands, which are then sent to the dynamic variable diameter tool and the plugging execution mechanism respectively. The dynamic variable diameter tool adjusts its own size according to the commands to adapt to the downhole conditions, and the plugging execution mechanism injects plugging material according to the commands to perform the plugging operation.

[0063] S6. Effect Monitoring Feedback and Operation Completion Judgment: The effect data after the downhole plugging operation is monitored in real time through a sensor network. The effect data includes changes in leakage, tool operating status, and downhole temperature and pressure data. If the leakage is not completely plugged, the process returns to step S3 to re-perform digital twin dynamic modeling. If the tool becomes stuck, the emergency adjustment procedure of the dynamic diameter-changing tool is triggered. If the downhole temperature and pressure are abnormal, the system self-protection mode is activated. If the plugging effect meets the standards and the tool is operating normally, the well workover operation is completed.

[0064] This embodiment offers significant advantages over existing technologies. In terms of data acquisition, it can collect multi-dimensional downhole data in real time, providing a comprehensive and accurate understanding of the downhole situation. Existing technologies may only collect partial key data, resulting in incomplete information and inaccurate assessments of the downhole conditions. In the edge computing preprocessing stage, this invention utilizes edge computing nodes to process data, enabling rapid data filtering, feature extraction, and standardized protocol conversion near the data source, reducing data transmission latency and bandwidth consumption, and improving processing efficiency. Traditional methods may rely on remote servers for data processing, leading to long transmission times and network instability. During the digital twin dynamic modeling process, by constructing a virtual downhole environment and using geomechanical and hydrodynamic models for dynamic modeling, the implementation effects of different plugging schemes can be simulated and risk levels assessed, providing a scientific basis for subsequent plugging parameter decisions. In contrast, existing technologies may lack this dynamic simulation and risk assessment mechanism, relying solely on experience to select plugging schemes, making it difficult to guarantee effectiveness. In the quantum-classical hybrid optimization and plugging parameter decision-making process, a quantum-classical hybrid algorithm is used to optimize the plugging parameters. This algorithm can quickly find the theoretically optimal solution among numerous possible parameter combinations and determine the final decision result by combining it with actual engineering constraints, making the plugging parameters more accurate and reasonable. Traditional optimization algorithms, on the other hand, are slow to calculate and struggle to find the global optimum when dealing with complex plugging parameter optimization problems. During plugging operations, the dynamic diameter-adjusting tool can adjust its size according to instructions to adapt to downhole conditions, improving the tool's applicability and operational flexibility. Existing tools may not be able to adjust flexibly according to actual well conditions. Furthermore, in the effect monitoring and feedback and operation completion judgment stages, the effect data after the downhole plugging operation is monitored in real time, and corresponding measures are taken according to different situations, forming a closed-loop operation process that ensures the safety and effectiveness of well workover operations—a deficiency in existing technologies.

[0065] In this embodiment, the quantum-classical hybrid algorithm in step S4 optimizes the discrete plugging parameters using the QUBO model, the expression of which is:

[0066]

[0067] J ij h represents the coupling strength between parameters, signifying the interaction between different discrete plugging parameters. i , is a single-parameter bias term, representing the weight of a single discrete plugging parameter, where x is a discrete plugging parameter variable, specifically the variable corresponding to the plugging material type; in the quantum-classical hybrid algorithm, the quantum annealing algorithm is used to process the discrete plugging parameters, and the classical genetic algorithm is used to optimize the continuous plugging parameters, which include material concentration and pumping rate.

[0068] This approach, combining quantum annealing and classical genetic algorithms, fully leverages the advantages of both. When dealing with discrete plugging parameters, the quantum annealing algorithm utilizes the properties of quantum mechanics to quickly find the optimal solution in a complex parameter space, significantly improving the efficiency and accuracy of plugging material selection. Meanwhile, the classical genetic algorithm, for optimizing continuous plugging parameters, is based on the principles of biological evolution, iteratively determining the optimal material concentration and injection rate by simulating natural selection and genetic mechanisms. In actual intelligent well workover operations in small-diameter horizontal sections, complex interactions exist between different plugging material types, and the coupling strength J between parameters in the QUBO model... ij This precise description of the effect allows for a comprehensive consideration of various factors when selecting the type of sealing material. Simultaneously, the single-parameter bias term h... i Each discrete plugging parameter was assigned a reasonable weight, ensuring that the importance of each parameter was properly considered during the optimization process. For continuous plugging parameters, precise control of material concentration and pumping rate is crucial for plugging effectiveness and cost control. Classical genetic algorithms, through continuous evolution and selection, can find the optimal combination under different well depths, geological conditions, and leakage scenarios. For example, under certain geological conditions, higher material concentrations may help improve plugging effectiveness, but they also increase costs and construction time. Optimization using classical genetic algorithms can find the optimal material concentration and pumping rate that ensures both plugging effectiveness and cost and construction time control. Furthermore, this quantum-classical hybrid algorithm optimization method also has good scalability and adaptability. As well workover operation data accumulates and geological conditions change, the parameters of the QUBO model can be adjusted, and the relevant parameters of the classical genetic algorithm can be optimized, enabling the algorithm to continuously adapt to different operating environments and requirements. In this way, the overall performance and reliability of intelligent well workover operations in small-diameter horizontal sections are further improved, providing stronger technical support for the efficient development of small-diameter horizontal wells.

[0069] In specific implementation, the quantum-classical hybrid algorithm in step S4 uses min x (f leak (x)+λ·f cost (x) is the objective function for solving the theoretically optimal combination of plugging parameters; where x is the combination of plugging parameters, including but not limited to material type, concentration, and pump speed; f leak A leakage prediction model based on fluid dynamics; f cost λ is a construction cost function that includes material and operation costs; λ is a weighting coefficient that balances the effect and cost, and the weighting coefficient is dynamically adjusted with well depth.

[0070] Logic: Set "minimum leakage" as the top priority, use λ to fine-tune the cost (e.g., λ = 0.2, so that the leakage weight accounts for 80%), ensure that leakage points are blocked first, and then control the cost appropriately.

[0071] Scenario: For wells at risk of blowout and well workover operations of high-yield gas wells, it is imperative to stop the leakage quickly, even at the cost of increased investment.

[0072] This objective function setting allows the algorithm to comprehensively consider the two key factors of leakage and construction cost during the solution process. The leakage prediction model based on fluid dynamics can accurately simulate downhole leakage conditions, allowing the algorithm to adjust the plugging parameters according to the actual leakage situation. Meanwhile, the construction cost function, which includes material and operational costs, ensures effective cost control while pursuing effective plugging results.

[0073] The ability to dynamically adjust weighting coefficients with well depth further enhances the algorithm's adaptability. Under different well depths, downhole geological conditions, pressure environments, leakage rates, and cost structures all change. By dynamically adjusting the weighting coefficients, the algorithm can better cope with these changes, finding the optimal parameter combination at different well depths that satisfies both plugging effectiveness and cost considerations.

[0074] Compared to traditional methods, which may only consider leakage or cost and struggle to achieve a balance between the two, the quantum-classical hybrid algorithm of this invention, through such an objective function and dynamic adjustment mechanism, can significantly improve the accuracy and effectiveness of plugging parameter optimization. This, in turn, enhances the overall quality and efficiency of intelligent well workover operations in small-diameter horizontal sections, reduces resource waste and time consumption during workover operations, and provides more reliable technical support for the development of small-diameter horizontal wells.

[0075] In some other embodiments, the objective function of the quantum-classical hybrid algorithm in step S4 is:

[0076] min F = α·leakage + β·cost + γ·construction time;

[0077] Where α, β, and γ are weighting coefficients, and α+β+γ=1, the weighting coefficients are dynamically adjusted with well depth;

[0078] The normalized expression for the above objective function is:

[0079]

[0080] In this normalized expression, the denominators of each term represent the baseline values ​​of their respective indicators. Q0 is the baseline value for leakage, a pre-set reference leakage under specific operating conditions used to measure the relative relationship between actual leakage and the baseline. C0 is the baseline value for cost, a cost reference standard determined based on a combination of factors such as historical operating data, market prices, and expected cost ranges. T0 is the baseline value for construction time, a standard construction time set based on experience and work plans. By dividing each indicator by its corresponding baseline value, indicators of different dimensions and magnitudes can be compared and calculated on the same scale. This avoids a situation where a single indicator dominates the objective function due to excessively large differences in magnitude between indicators, thus affecting the accuracy and fairness of the optimization results.

[0081] Logic: By dynamically adjusting the weights of α / β / γ (e.g., α=0.5, β=0.3, γ=0.2), the system balances "blocking leakage (large α value), reducing costs (moderate β value), and ensuring efficiency (small γ value)" to adapt to most conventional well workover operations.

[0082] Scenario: Routine well repair of ordinary oil and gas wells, and operations with limited budgets but requiring basic efficiency.

[0083] Setting the weighting coefficients in this way and dynamically adjusting them with well depth offers several advantages. In shallow wells, leakage may be relatively low, allowing for a more moderate increase in the weighting coefficients for cost and workover time, such as by increasing the values ​​of β and γ, thus focusing more on cost control and shortening workover time. However, in deep wells, leakage conditions may be more complex and severe, requiring a larger weighting coefficient α for leakage to prioritize plugging effectiveness and reduce the negative impact of leakage on the overall well workover operation.

[0084] This dynamic adjustment allows the quantum-classical hybrid algorithm to better adapt to the actual conditions at different well depths, enabling the objective function to more accurately reflect the optimal goal pursued by well workover operations under different well depth conditions. Furthermore, in actual operation, a model relating well depth to weighting coefficients can be constructed based on a large amount of past well workover operation data. When a new well workover operation is initiated, the appropriate weighting coefficients can be quickly determined based on the current well depth, improving operational efficiency and accuracy.

[0085] Meanwhile, with the continuous development of well workover technology and the deepening understanding of well conditions under different geological conditions, this correspondence model can be continuously optimized to further improve the application effectiveness of quantum-classical hybrid algorithms in intelligent well workover operations in small-diameter horizontal sections.

[0086] In this embodiment, step S4 further includes predicting the leakage amount using a data-driven model, wherein the expression of the data-driven model is:

[0087] fleak (x) = α·ReLU (W·x+b);

[0088] Where W and b are the weights of the neural network, which are obtained by training with historical well leakage data, α is the working condition correction coefficient, which is used to correct the influence of downhole temperature and pressure on the leakage prediction results, and x is the continuous plugging parameter variable.

[0089] In practical applications, to ensure the accuracy and reliability of the data-driven model, it is necessary to collect a large amount of historical well leakage data for training. This data should cover various conditions such as different well depths, geological conditions, material concentrations, and pumping rates to fully reflect the leakage characteristics under various operating conditions. During training, optimization algorithms such as gradient descent are used to iteratively update the neural network weights W and b, so that the model's prediction results can be as close as possible to the actual leakage. The operating condition correction coefficient α is dynamically adjusted based on real-time monitored downhole temperature and pressure data. By establishing a correlation model between temperature, pressure, and leakage, the impact of downhole operating conditions on leakage can be assessed more accurately. For example, when the downhole temperature or pressure increases, the value of α will be adjusted accordingly to correct the prediction results, making the model's predictions more consistent with the actual situation. The continuous plugging parameter variable x includes key parameters such as material concentration and pumping rate. The value range of these parameters will be reasonably defined according to different well depths and geological conditions. In practical calculations, by analyzing and optimizing the continuous values ​​of the x variable, combined with the objective function, the optimal parameter combination can be found that effectively controls leakage while achieving an optimal balance between cost and construction time under different operating conditions. Simultaneously, as the well workover operation progresses, the real-time collected data is continuously fed back into the data-driven model, enabling real-time updates and optimizations. This further improves the model's prediction accuracy and algorithm adaptability, thereby better meeting the needs of intelligent well workover operations in small-diameter horizontal sections.

[0090] In this embodiment, the data sampling frequency of the sensor network in step S1 is 10Hz; the preprocessing delay of the edge computing node in step S2 is less than 50ms; the total decision delay from real-time acquisition of downhole data to issuance of control commands in step S5 is less than 200ms, and the control commands are issued through mud pulse transmission or 5G wireless transmission; the wellbore diameter range adapted to the dynamic diameter-changing tool in step S5 is Φ88.9-120.6mm, and the diameter can be dynamically adjusted by ±15%.

[0091] In practical applications, the computation time of the quantum computing module in step S3 is less than 100ms to ensure that the optimization calculation of the plugging parameters is completed in a short time. In step S4, the classical computing module sets the number of iterations for the objective function to 50, ensuring optimization effectiveness while avoiding over-computation. In step S5, the injection accuracy of the plugging actuator is controlled within ±2% to accurately inject plugging material according to the final plugging parameter decision results. In step S5, for the mud pulse transmission method, its transmission rate is stabilized at 10bps to ensure that control commands are transmitted accurately and promptly. For the 5G wireless transmission method, the signal strength coverage in the downhole working environment can meet the requirements of an area with a radius of at least 500 meters, ensuring the stability of data transmission. Simultaneously, the system has an automatic transmission mode switching function; when one transmission mode fails or the signal is poor, it can quickly switch to another mode to ensure the normal issuance of control commands. Furthermore, the dynamic diameter adjustment tool has a response time of less than 30s when adjusting the diameter, enabling it to quickly adapt to changes in different wellbore diameters and improve the efficiency of well workover operations. The tool is made of high-strength, corrosion-resistant alloy materials to ensure long-term stable operation in complex downhole environments and reduce operational interruptions due to tool damage. Furthermore, the tool surface undergoes special treatment, providing excellent lubrication properties, reducing friction with the wellbore, and further improving its service life and operational efficiency.

[0092] It should be noted that the plugging materials adapted to the quantum-optimized plugging module in practical applications include nano-SiO2 modified gel, carbon nanotube cement-based materials, nano-clay / resin composite materials, nano-Al2O3 reinforced elastomers, and graphene-polymer hybrid materials; among them, the nano-SiO2 modified gel has a nano-SiO2 addition amount of 5-10wt% and a temperature resistance of 120-150℃; the graphene-polymer hybrid material has a functionalized graphene addition amount of 1-3wt% and a temperature resistance of 250-300℃.

[0093] These plugging materials each possess unique performance advantages. Nano-SiO2 modified gel, with its appropriate amount of nano-SiO2, not only exhibits excellent temperature resistance but also demonstrates good flexibility and adhesion, enabling it to form an effective sealing layer in various leakage channels. Carbon nanotube cement-based materials combine the high strength of carbon nanotubes with the stability of cement, enhancing the overall strength of the plugging structure and resisting complex downhole pressure environments. Nano-clay / resin composites utilize the adsorption properties of nano-clay and the adhesive properties of resin to quickly fill leakage pores and solidify. Nano-Al2O3-reinforced elastomers possess excellent elasticity and wear resistance, adapting to wellbore deformation during the plugging process and maintaining a good sealing effect. Graphene-polymer hybrid materials, due to the addition of functionalized graphene, maintain stable performance even at high temperatures, providing a reliable solution for plugging leakage in high-temperature well sections. In practical applications, appropriate plugging materials can be flexibly selected based on different well conditions, leakage situations, and temperature conditions to achieve the best plugging effect.

[0094] like Figures 5 to 7 As shown, based on the foregoing description, Embodiment 1 also discloses a system for implementing the intelligent well workover method for small-bore horizontal sections using quantum-optimized plugging, comprising: a data acquisition subsystem for performing real-time downhole data acquisition, including an ultrasonic caliper measuring device, formation pressure sensor, temperature sensor, flow meter, and vibration sensor, to acquire downhole caliper, leakage, temperature, and pressure data; an edge computing node for performing edge computing preprocessing, filtering and denoising, extracting features, and converting the format of the real-time data acquired by the data acquisition subsystem; a digital twin unit for performing dynamic modeling of the digital twin, constructing a virtual downhole environment based on the preprocessed data output by the edge computing node, and dynamically simulating and evaluating the risk of plugging schemes through multi-subdomain models; and a quantum-optimized plugging module for performing quantum-classical... The system incorporates a hybrid optimization and plugging parameter decision-making mechanism. It receives simulation results from a digital twin unit, optimizes plugging parameters using a quantum-classical hybrid algorithm, and determines the final decision result. A dynamic diameter adjustment tool performs diameter adjustment operations, adjusting its size according to control commands issued by the edge computing node to adapt to well conditions. A plugging actuator performs plugging operations, injecting plugging material based on the final plugging parameter decision result. A monitoring and feedback component monitors and provides feedback on the performance, collecting downhole performance data in real time and feeding it back to the edge computing node. The data acquisition subsystem, edge computing node, digital twin unit, quantum-optimized plugging module, dynamic diameter adjustment tool, plugging actuator, and monitoring and feedback component work together through a standardized data interface to form an automated closed-loop control system from data acquisition to operation completion.

[0095] This collaborative working mode of the system greatly enhances the intelligence and precision of well workover operations in small-diameter horizontal sections. The data acquisition subsystem acts like a keen "eye" and "ear," capturing various key downhole data comprehensively and in real time, providing a solid foundation for subsequent decision-making. Edge computing nodes function as efficient "processors," rapidly processing the massive amounts of acquired data, removing interference, and extracting the most valuable features, allowing the data to be used by subsequent modules in a more suitable form. The digital twin unit is like a virtual "laboratory," constructing a highly realistic virtual downhole environment using pre-processed data output from the edge computing nodes. Through dynamic simulation of multi-subdomain models, it can simulate the potential effects of different plugging schemes in advance, accurately assess the risks involved, and provide a reliable reference for the quantum-optimized plugging module. The quantum-optimized plugging module is the "intelligent brain" of the entire system. It utilizes advanced quantum-classical hybrid algorithms to deeply analyze and optimize the simulation results given by the digital twin unit. Among numerous possible combinations of plugging parameters, it quickly selects the optimal solution, determines the final decision, and thus achieves efficient and precise plugging operations. The dynamic diameter-adjustable tool, like a flexible "Transformer," can rapidly adjust its size according to control commands issued by the edge computing node, perfectly adapting to the complex and ever-changing well conditions downhole, ensuring the smooth progress of plugging operations. The plugging actuator is the "executor" of the specific task; it accurately injects plugging material according to the final plugging parameter decision results determined by the quantum-optimized plugging module, completing the plugging operation. The monitoring and feedback component acts like a "quality inspector," collecting downhole effect data in real time after the plugging operation and promptly feeding this data back to the edge computing node. The edge computing node evaluates the feedback information; if the plugging effect does not meet expectations, the system can quickly initiate a new round of decision-making and operational processes, forming a complete and efficient automated closed-loop control system. This closed-loop control system allows the entire well workover operation to be continuously adjusted and optimized according to actual conditions, greatly improving the success rate and efficiency of well workover operations, reducing operating costs and risks, and providing strong technical support for the development of small-diameter horizontal wells.

[0096] In specific implementation, the dynamic diameter-changing tool is adapted to a wellbore diameter range of Φ88.9-120.6mm, and can achieve ±15% dynamic diameter adjustment; the outer diameter of the dynamic diameter-changing tool is no greater than 95mm, and the length is no greater than 2m; the dynamic diameter-changing tool can withstand a downhole pressure of no less than 70MPa and a downhole temperature of no less than 150℃; the dynamic diameter-changing tool includes a power module, an execution module, and a control unit. The power module and the execution module adopt a modular design, and the control unit is electrically connected to the power module and the execution module respectively, and is used to receive data and control the power module to drive the execution module to move.

[0097] The power module provides stable and robust power support to the execution module, ensuring rapid response to control unit commands even in complex downhole environments. Driven by the power module, the execution module precisely adjusts the tool's diameter to adapt to different wellbore diameters. The control unit possesses high-precision data processing capabilities, enabling real-time analysis of control commands received from edge computing nodes and rapid, accurate adjustment of the power and execution modules' operating states. In actual operation, when the wellbore diameter changes, the control unit immediately calculates the required adjustment based on received data and sends corresponding commands to the power module. The power module quickly starts and drives the execution module to adjust the diameter; the entire process is completed in a short time, significantly improving operational efficiency. Furthermore, the modular design of this dynamic diameter-changing tool makes maintenance and component replacement more convenient and faster, reducing maintenance costs and time. Simultaneously, it can withstand downhole pressures of at least 70 MPa and downhole temperatures of at least 150°C, ensuring stable and reliable operation even in harsh downhole environments, providing a solid guarantee for well workover operations in small-bore horizontal wells.

[0098] In this embodiment, the power module includes a hydraulic circuit consisting of a micro hydraulic pump, a pressure accumulator, and an electromagnetic directional valve group. The micro hydraulic pump provides hydraulic power, the pressure accumulator stabilizes the hydraulic system pressure, and the electromagnetic directional valve group controls the flow direction of the hydraulic oil. The execution module includes at least two sets of telescopic arms, radial support sliders, displacement sensors, and shape memory alloy auxiliary return springs. The telescopic arms are distributed circumferentially, the radial support sliders are located at the ends of the telescopic arms for contact and support with the well wall, the displacement sensors monitor the telescopic arm's extension and retraction in real time, and the shape memory alloy auxiliary return springs are located in the extension and retraction path of the telescopic arms to assist in the return action of the telescopic arms.

[0099] This collaborative design of the power module and execution module enables the dynamic diameter-adjusting tool to achieve greater precision and efficiency in diameter adjustment. A micro hydraulic pump provides a continuous and stable hydraulic power supply, while a pressure accumulator ensures stable hydraulic system pressure, preventing pressure fluctuations from affecting the tool's adjustment accuracy. The electromagnetic directional valve assembly precisely controls the flow of hydraulic oil according to the control unit's commands, thereby driving the extension and retraction of the telescopic arm. The circumferentially distributed design of the telescopic arm ensures uniform contact between the tool and the wellbore wall, providing stable support. The radial support slider effectively disperses pressure upon contact with the wellbore wall, reducing damage. A displacement sensor monitors the telescopic arm's extension and retraction in real time and feeds the data back to the control unit. Based on this data, the control unit further adjusts the power module's operating status to ensure the tool's diameter adjustment achieves the expected precision. A shape memory alloy auxiliary return spring plays a crucial supporting role in the telescopic arm's extension and retraction. When the telescopic arm needs to return to its initial position, the shape memory alloy auxiliary return spring responds quickly, helping the telescopic arm return rapidly to its initial position, improving the tool's working efficiency and response speed. Meanwhile, this spring also possesses elasticity and cushioning properties, reducing impact and vibration during the extension and retraction of the telescopic boom, thus extending the tool's service life. Furthermore, this modular design facilitates individual maintenance and upgrades of the power and execution modules. If a component malfunctions, only the corresponding module needs to be replaced, eliminating the need for extensive disassembly and repair of the entire tool, significantly reducing maintenance costs and downtime. In practical applications, this design better adapts to different downhole environments and operational requirements, providing a more reliable and efficient solution for well workover operations in small-diameter horizontal wells.

[0100] Specifically, the power module is equipped with dual hydraulic circuits to achieve redundant control. When one hydraulic circuit fails, it automatically switches to the backup hydraulic circuit. The control unit receives extension / retraction data transmitted by the displacement sensor and well diameter data from the monitoring feedback component. When the well diameter is less than the set value minus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm drive chamber, driving the telescopic arm to extend. At this time, the shape memory alloy auxiliary return spring is stretched. When the well diameter is greater than the set value plus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm retraction chamber. At the same time, the shape memory alloy auxiliary return spring releases its elastic potential energy to assist the telescopic arm in emergency retraction.

[0101] The dual hydraulic circuit design of the power module not only improves system reliability but also enhances its ability to respond to emergencies. The backup hydraulic circuit is always on standby, and can immediately and seamlessly take over operation should the main hydraulic circuit fail, ensuring the normal operation of the telescopic boom. Moreover, this redundant control mechanism can reduce system maintenance difficulty and cost to a certain extent. Because when the main hydraulic circuit fails, only the faulty circuit needs to be repaired, without affecting the normal operation of the entire power module, thus reducing downtime.

[0102] In specific application scenarios, the system also includes an extreme environment adaptation module, which comprises a high-temperature resistant packaging component and an adaptive power management unit. The high-temperature resistant packaging component uses a ceramic substrate and gold wire bonding process, and has a temperature resistance of not less than 250°C. The power control algorithm expression of the adaptive power management unit is as follows:

[0103] P dynamic =P base ·e -0.01(T-150) ;

[0104] Where P dynamic For dynamic power consumption, P base The reference power consumption is T, and the actual downhole temperature is T. This algorithm enables temperature-adaptive frequency reduction, ensuring stable operation of the system under high temperature and high pressure until the operation is completed.

[0105] The extreme environment adaptation module significantly enhances the system's adaptability to harsh operating conditions. The ceramic substrate of the high-temperature resistant packaging component possesses excellent insulation and thermal stability, while gold wire bonding ensures reliable electrical connections, effectively preventing short circuits and signal interference even in high-temperature environments. The adaptive power management unit's power control algorithm is particularly sophisticated; as the actual downhole temperature rises, the system's dynamic power consumption decreases according to a specific pattern. When the actual downhole temperature exceeds 150°C, the system significantly reduces power consumption and heat generation, preventing system failures due to overheating. This adaptive frequency reduction not only ensures stable system operation under high temperature and high pressure environments but also extends the system's lifespan. In extreme environments, system stability and reliability are crucial; this module acts as a "protective shield," allowing the system to operate continuously under harsh conditions of high temperature and high pressure until well workover operations are completed. Furthermore, this module broadens the system's application scope, enabling it to function in various complex downhole environments and providing strong technical support for intelligent well workover operations in small-diameter horizontal sections. In actual well workover operations, well conditions of different depths, temperatures and pressures may be encountered. The extreme environment adaptation module can automatically adjust the system status according to specific environmental parameters to ensure that the system is always in the best working condition.

[0106] In summary, this invention utilizes a combination of sensor networks and edge computing to achieve real-time acquisition and rapid processing of downhole data, with a preprocessing latency of less than 50ms, providing timely data support for subsequent decision-making. The introduction of a quantum-classical hybrid optimization algorithm, using the QUBO model to handle discrete parameters and combining it with classical algorithms to optimize continuous parameters, significantly improves the optimization efficiency and accuracy of plugging parameters. The objective function comprehensively considers leakage, cost, and construction time, achieving multi-objective optimization. The dynamic diameter-adjustable tool adopts a modular design, suitable for wellbore diameters ranging from Φ88.9-120.6mm, and can achieve ±15% dynamic adjustment. Combined with a shape memory alloy auxiliary return spring and a dual hydraulic circuit redundancy design, the risk of tool jamming is effectively reduced, improving equipment reliability. The system integrates a digital twin unit, using virtual simulation to preview the effect of the plugging scheme, and combining this with monitoring feedback to form a closed-loop control, significantly improving the plugging success rate. The extreme environment adaptation module uses high-temperature resistant packaging and adaptive power management to ensure stable operation of the system under high temperatures of 250℃ and high pressures of 70MPa, expanding the environmental adaptability range of well workover operations.

[0107] The above description discloses only one preferred embodiment of the present invention, and should not be construed as limiting the scope of the present invention. Those skilled in the art will understand that all or part of the processes of the above embodiments can be implemented, and equivalent changes made in accordance with the claims of the present invention are still within the scope of the invention.

Claims

1. A smart well workover method for small-bore horizontal sections integrating quantum-optimized plugging, characterized in that, Includes the following steps: S1. Real-time downhole data acquisition: Downhole data is acquired in real time through a sensor network. The downhole data includes well diameter, leakage rate, fracture type, formation temperature, formation pressure, and fluid velocity. S2. Edge computing preprocessing: The real-time downhole data collected in step S1 is filtered, denoised, feature extracted and standardized protocol converted using edge computing nodes to obtain preprocessed data suitable for digital twin modeling and quantum optimization computing. S3. Digital Twin Dynamic Modeling: The digital twin unit constructs a virtual downhole environment based on the preprocessed data in step S2, calls the geomechanical model and fluid dynamics model for dynamic modeling, simulates the implementation effect of different plugging schemes and assesses the risk level; S4. Quantum-Classical Hybrid Optimization and Leak Plugging Parameter Decision: The quantum optimization leak plugging module receives the dynamic modeling results from step S3, optimizes the leak plugging parameters using a quantum-classical hybrid algorithm, solves for the theoretically optimal combination of leak plugging parameters, and determines the final leak plugging parameter decision result by combining the actual engineering constraints; the leak plugging parameters include the type of leak plugging material, material concentration, and pumping rate; S5. Execution of the variable diameter tool and plugging operation: The edge computing node converts the final plugging parameter decision result of step S4 into control commands, which are then sent to the dynamic variable diameter tool and the plugging execution mechanism respectively. The dynamic variable diameter tool adjusts its own size according to the commands to adapt to the downhole conditions, and the plugging execution mechanism injects plugging material according to the commands to perform the plugging operation. S6. Effect Monitoring Feedback and Operation Completion Judgment: The effect data after the downhole plugging operation is monitored in real time through a sensor network. The effect data includes changes in leakage, tool operating status, and downhole temperature and pressure data. If the leakage is not completely plugged, the process returns to step S3 to re-perform digital twin dynamic modeling. If the tool becomes stuck, the emergency adjustment procedure of the dynamic diameter-changing tool is triggered. If the downhole temperature and pressure are abnormal, the system self-protection mode is activated. If the plugging effect meets the standards and the tool is operating normally, the well workover operation is completed. In step S4, the quantum-classical hybrid algorithm optimizes the discrete plugging parameters using the QUBO model, the expression of which is: ； in The coupling strength between parameters represents the interactive influence between different discrete plugging parameters. This is a single-parameter bias term, representing the weight of a single discrete plugging parameter. These are discrete plugging parameter variables, specifically variables corresponding to the plugging material type. In the quantum-classical hybrid algorithm, the quantum annealing algorithm is used to process the discrete plugging parameters, and the classical genetic algorithm is used to optimize the continuous plugging parameters, which include material concentration and pumping rate. In step S4, the quantum-classical hybrid algorithm is used to To find the theoretically optimal combination of plugging parameters for the objective function; where, For the combination of plugging parameters, including but not limited to material type, concentration, and pump speed; This is a leakage prediction model based on fluid dynamics; This is a construction cost function that includes both material and operational costs. The weighting coefficients are used to balance the effectiveness and cost, and these weighting coefficients are dynamically adjusted with well depth.

2. The intelligent well workover method for small-bore horizontal sections with quantum-optimized plugging as described in claim 1, characterized in that: Step S4 also includes predicting the leakage amount using a data-driven model, the expression of which is: ； in , The weights are obtained by training with historical well leakage data. This is a working condition correction factor used to correct for the impact of downhole temperature and pressure on the predicted leakage rate. The variable is the continuous leak-stopping parameter variable.

3. The intelligent well workover method for small-bore horizontal sections with quantum-optimized plugging as described in claim 2, characterized in that: In step S1, the data sampling frequency of the sensor network is 10Hz; in step S2, the preprocessing delay of the edge computing node is less than 50ms; in step S5, the total decision delay from real-time acquisition of downhole data to issuance of control commands is less than 200ms, and the control commands are issued via mud pulse transmission or 5G wireless transmission; in step S5, the wellbore diameter range adapted to the dynamic diameter-changing tool is Φ88.9-120.6mm, and the diameter can be dynamically adjusted by ±15%.

4. A system for implementing the intelligent well workover method for small-bore horizontal sections with quantum-optimized plugging as described in any one of claims 1-3, characterized in that, include: The data acquisition subsystem is used to perform real-time downhole data acquisition, including ultrasonic caliper measuring equipment, formation pressure sensor, temperature sensor, flow meter and vibration sensor, to acquire downhole caliper, leakage, temperature and pressure data; Edge computing nodes are used to perform edge computing preprocessing, including filtering, denoising, feature extraction, and format conversion of real-time data collected by the data acquisition subsystem. The digital twin unit is used to perform dynamic modeling of digital twins, construct a virtual downhole environment based on preprocessed data output from edge computing nodes, and dynamically simulate and evaluate the risks of plugging schemes through multi-subdomain models. The quantum-optimized plugging module is used to perform quantum-classical hybrid optimization and plugging parameter decision-making. It receives the simulation results of the digital twin unit, optimizes the plugging parameters through a quantum-classical hybrid algorithm, and determines the final decision result. The dynamic diameter adjustment tool is used to perform diameter adjustment operations, adjusting its own size according to the control commands issued by the edge computing node to adapt to the well conditions; A leak-sealing actuator is used to perform leak-sealing operations and injects leak-sealing materials based on the final leak-sealing parameter decision results. The monitoring and feedback component is used to perform effect monitoring and feedback, collect downhole effect data after plugging in real time and feed it back to the edge computing node; The data acquisition subsystem, edge computing node, digital twin unit, quantum-optimized leak-stopping module, dynamic diameter-changing tool, leak-stopping execution mechanism, and monitoring feedback component work together through standardized data interfaces to form an automated closed-loop control from data acquisition to operation completion.

5. The system according to claim 4, characterized in that: The dynamic diameter-adjusting tool is compatible with wellbore diameters ranging from Φ88.9 to 120.6 mm, and can achieve dynamic diameter adjustment of ±15%. The outer diameter of the dynamic diameter-adjusting tool is no greater than 95 mm, and the length is no greater than 2 m. The dynamic diameter-adjusting tool can withstand downhole pressures of no less than 70 MPa and downhole temperatures of no less than 150 °C. The dynamic diameter-adjusting tool includes a power module, an execution module, and a control unit. The power module and the execution module adopt a modular design. The control unit is electrically connected to both the power module and the execution module, and is used to receive data and control the power module to drive the execution module.

6. The system according to claim 5, characterized in that: The power module includes a hydraulic circuit consisting of a micro hydraulic pump, a pressure accumulator, and an electromagnetic directional valve assembly. The micro hydraulic pump provides hydraulic power, the pressure accumulator stabilizes the hydraulic system pressure, and the electromagnetic directional valve assembly controls the flow direction of the hydraulic oil. The execution module includes at least two sets of telescopic arms, radial support sliders, displacement sensors, and shape memory alloy auxiliary return springs. The telescopic arms are distributed circumferentially, the radial support sliders are located at the ends of the telescopic arms for contact and support with the well wall, the displacement sensors monitor the telescopic arm's extension and retraction in real time, and the shape memory alloy auxiliary return springs are located in the extension and retraction path of the telescopic arms to assist in the return action of the telescopic arms.

7. The system according to claim 6, characterized in that: The power module is equipped with dual hydraulic circuits for redundant control. When one hydraulic circuit fails, it automatically switches to the backup hydraulic circuit. The control unit receives extension / retraction data from the displacement sensor and well diameter data from the monitoring feedback component. When the well diameter is less than the set value minus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm drive chamber, driving the telescopic arm to extend. At this time, the shape memory alloy auxiliary return spring is stretched. When the well diameter is greater than the set value plus the tolerance, the control unit controls the electromagnetic directional valve group to allow hydraulic oil to enter the telescopic arm retraction chamber. Simultaneously, the shape memory alloy auxiliary return spring releases its elastic potential energy to assist the telescopic arm in emergency retraction.

8. The system according to any one of claims 4-7, characterized in that: It also includes an extreme environment adaptation module, which includes a high-temperature resistant packaging component and an adaptive power management unit; the high-temperature resistant packaging component adopts a ceramic substrate and gold wire bonding process, and has a temperature resistance of not less than 250°C; The power control algorithm expression for the adaptive power management unit is: ； in For dynamic power consumption, As a reference power consumption, Based on the actual downhole temperature, this algorithm enables temperature-adaptive frequency reduction, ensuring stable system operation under high temperature and high pressure until the operation is completed.

Images