Medium and low temperature geothermal well drilling and completion method and well drilling optimization system

Abstract

The invention discloses a medium and low temperature geothermal well drilling and completion optimization method and system. The method comprises the steps that a drilling equipment efficiency model (input energy and output footage) and a thermal reservoir response model (input parameters and output productivity indexes) are constructed, a full-process optimization model is established based on the two models, a drilling cost minimization and thermal reservoir productivity maximization function is taken as a target, decision variables comprise parameters such as energy input and a well bore structure, and a full-process optimization model is established. And iteratively solving and dynamically controlling the operation through a Benders decomposition algorithm. The system comprises an equipment efficiency modeling module, a heat storage response modeling module, an optimization solution engine module, a dynamic control terminal module and the like, the functions of well bore structure design, drilling process parameter generation, well completion sealing scheme decision making and the like can be achieved, and closed-loop optimization is formed. The method improves the drilling efficiency and productivity, reduces the cost and is suitable for medium and low temperature geothermal resource development.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geothermal drilling and completion, in particular to a method for drilling and completing a medium-low temperature geothermal well and a drilling optimization system. BACKGROUND

[0002] The conventional two-opening wellbore structure (surface casing + technical casing) in the fractured bedrock type geothermal reservoir is prone to cause reservoir pollution due to the long well section. In addition, the cement sealing is insufficient, which causes the water layers to communicate with each other, affecting the normal operation of the geothermal well and the effective development of geothermal resources. The commonly used expansion rubber water stopper is prone to failure due to aging in the actual use process. Once it fails, low-temperature water will seep into the wellbore, not only reducing the water temperature, but also causing the single-well production capacity to decrease, affecting the utilization efficiency of geothermal resources.

[0003] The conventional drilling fluid positive circulation method is prone to block the geothermal reservoir pores during drilling, hindering the flow of geothermal fluid. Although the clean water circulation has the advantage of environmental protection, its rock carrying capacity is weak, which will cause the cuttings to accumulate at the bottom of the well, thereby affecting the water yield of the geothermal well and reducing the development benefit of the geothermal well. In the recharging process, the mudstone section is prone to collapse, blocking the recharging channel. At the same time, fine silt is also prone to invade the formation, reducing the recharging efficiency and affecting the sustainable development and utilization of geothermal resources. SUMMARY

[0004] The present application aims to provide a method for optimizing drilling and completion of a medium-low temperature geothermal well, comprising the following steps: constructing a drilling equipment efficiency model: establishing an efficiency model for the drilling equipment subsystem, the input of which includes drilling energy input, and the output of which is drilling footage; constructing a geothermal reservoir response model: establishing a response model for the geothermal reservoir, the input of which includes drilling parameter combinations, and the output of which includes geothermal production capacity indicators; establishing a drilling optimization model: based on the efficiency model and the response model, establishing a drilling whole-process optimization model, the decision variables of which include drilling equipment energy input, wellbore structure parameters, and completion control parameters; the optimization target is a function of minimizing drilling cost and maximizing geothermal reservoir production capacity; iterative optimization solution: solving the optimization model multiple times through Benders decomposition algorithm, and dynamically controlling the drilling operation according to the solution result.

[0005] Further, the drilling equipment efficiency model specifically includes: obtaining historical drilling data, including: rig power, mud pump flow, air injection amount, formation leakage rate, and rate of penetration; establishing a first neural network model, and obtaining the drilling equipment efficiency model through historical data training, which is used to predict the drilling efficiency under different input parameters.

[0006] Furthermore, constructing a thermal reservoir response model specifically includes: Obtain historical thermal reservoir response data, including: drilling fluid density, pH value, screen type, gravel packing density, and well washing parameters; A second neural network model was established, and a thermal reservoir response model was obtained through historical data training to predict the mapping relationship between completion parameters and geothermal well water yield.

[0007] Furthermore, the iterative optimization solution adopts the Benders decomposition algorithm, including: Generate temporary decision variables: Generate wellbore structure parameters and drilling process parameters based on the current model; Execute simulated drilling: send simulation instructions to the thermal reservoir response model based on temporary parameters; Receive feedback data: including predicted water output, temperature decay rate and gradient information; When the relative difference between the upper bound and the lower bound of the objective function is less than the threshold, the final drilling plan is output.

[0008] Furthermore, the optimization objective function is: min(∑ɸ+ɵ-α×ʀ); Among them, ɸ is the drilling energy cost, ɵ is the completion material cost, ʀ is the predicted water yield, and α is the production capacity weight coefficient; Constraints include: wellbore structure compatibility, sand control screen strength limit, and underbalanced drilling pressure threshold.

[0009] Furthermore, the wellbore structure design is incorporated into the optimization model as a decision variable: For porous sandstone reservoirs, determine the technical casing diameter and screen type for the secondary wellbore structure; For bedrock fracture-type heat reservoirs, the length of the open hole section of the three-well structure and the wire wrapping process parameters are determined.

[0010] Furthermore, the composite drilling process parameters are dynamically generated through the optimization model: Generate gas lift reverse circulation drilling parameters in lost circulation formations, including double-wall drill bit inner diameter and cuttings return velocity; Generate water-filled air underbalanced drilling parameters in the leakage-prone layer, including air injection ratio and underpressure value.

[0011] Furthermore, the completion sealing plan is determined by the optimization model: Select the lithologic combination of casing and sand screen; Optimize the lead sealing layer thickness and cone angle of the special alloy hanger; Dynamically match the gravel packing density with the number of screen wire wrap layers.

[0012] Furthermore, it also includes the establishment of a dynamic logging parameter library: According to the logging scheme output by the optimization model, the reservoir permeability distribution is fed back in real time; The thermal reservoir response model is updated based on the feedback data to form a closed-loop optimization.

[0013] A drilling optimization system for implementing the low-temperature geothermal drilling and completion optimization method, comprising: An equipment efficiency modeling module for storing a drilling equipment efficiency model and receiving drilling rig and mud pump operation data in real time; A thermal reservoir response modeling module for storing a thermal reservoir response model and integrating geological data and historical production capacity data; An optimization solving engine for executing a Benders decomposition algorithm and outputting an optimal parameter combination of wellbore structure, drilling process and completion sealing; A dynamic control terminal for issuing optimization parameters to a drilling equipment execution unit and adjusting the gas lift reverse circulation device and the adaptive drilling fluid injection system in real time; The optimization solving engine further comprises: A sand control process decision sub-module for dynamically selecting a sand control scheme among wire-wrapped screen pipe, slotted liner and wrapped wire in the sand control process based on the thermal reservoir fracture characteristics; A sealing life prediction sub-module for optimizing the rubber-free sealing structure parameters through stress distribution simulation of the alloy hanger sealing layer; The dynamic control terminal executes in real time: A step-by-step well flushing instruction for starting gas lift reverse circulation well flushing, high-pressure jet flushing and chemical plugging agent injection in the optimized sequence; Drilling fluid dynamic regulation for automatically adjusting the drilling fluid performance according to the pH value and density output by the model.

[0014] The present application has the following advantages: The present application has the following advantages: The present application has the following advantages:

[0015] At the same time, the second neural network model is trained using historical thermal reservoir response data (drilling fluid density, screen pipe type, etc.) to establish a thermal reservoir response model, which can accurately map the relationship between completion parameters and water production. For example, the gravel packing density is set to 1.8 g / cm3 The model found that when the screen type is wire-wrapped screen, the filling density of 2.2 g / cm 3 can make the thermal reservoir water production of sandstone increase by 30%, and the field verification shows that the well section water production reaches 80 m 3 / h, which is 25% higher than the historical well of the same type. This dual-model construction technology provides a reliable data basis for subsequent optimization and solves the problems of poor model generalization and large prediction deviation in traditional methods.

[0016] The application has an iterative optimization mechanism driven by Benders decomposition algorithm, which realizes the collaborative optimization of drilling whole-process cost and productivity. The mechanism generates temporary decision variables (well structure, drilling process parameters), simulates the drilling process and receives thermal reservoir feedback data (water production, temperature decay rate, etc.), and outputs the optimal scheme when the relative difference between the upper and lower bounds of the objective function is less than the threshold. The core advantage is to decompose the complex mixed integer programming problem into equipment efficiency sub-problem and thermal reservoir response sub-problem, reducing the dimension of the solution. The optimization objective function min(∑ɸ+ɵ-α×ʀ) considers the drilling energy cost, completion material cost and predicted water production, and the introduction of constraint conditions (well structure compatibility, sand control screen strength, etc.) ensures that the optimization scheme is feasible in engineering practice. For example, when underbalanced drilling, the model automatically controls the pressure within the threshold value to avoid the risk of blowout.

[0017] The application has a well structure differentiated design technology based on the type of thermal reservoir, which solves the problem of pollution and channeling in different reservoirs. For sandstone pore-type thermal reservoirs, this technology decides the technical casing diameter and screen type of the second-opening well structure. The traditional second-opening structure often causes cement to seep into the pores due to mismatch between the casing diameter and porosity, resulting in reservoir pollution. For bedrock fissure-type thermal reservoirs, the technology decides the open hole length and wire-wrapped screen process parameters of the third-opening well structure. The traditional third-opening well section is too long, which easily leads to fissure loss and water layer channeling. A bedrock well uses an optimized open hole section of 200 m, combined with 3 layers of wire-wrapped screen and a gravel packing density of 2.0 g / cm 3 , compared with the traditional scheme (open hole section of 350 m and 2 layers), the temperature decay rate is reduced from 15% / 100 m to 8% / 100 m, and there is no channeling phenomenon, and the single well productivity is increased by 25%. This differentiated design realizes the precise matching of "reservoir characteristics-well structure-productivity" by integrating well structure parameters as decision variables into the optimization model, and solves the pollution and channeling problems caused by traditional unified structure from the root.

[0018] The application has a composite drilling process parameter dynamic generation technology, which is suitable for safe and efficient drilling in lost formation and easy lost formation. In the lost formation, the technology generates air-lift reverse circulation drilling parameters (double-wall drill inner diameter, cuttings upward velocity). The optimization model dynamically generates a parameter combination of double-wall drill inner diameter 127mm and upward velocity 2.5m / s according to the loss rate, and uses the negative pressure pumping effect of air-lift reverse circulation to take out the cuttings in time, and the accumulation thickness is controlled within 1cm / h. In the easy lost formation, the technology generates fresh water air-charge underbalanced drilling parameters (air injection ratio, underpressure value). The traditional fresh water circulation rock carrying capacity is weak, and improper underbalanced parameters can easily cause well wall collapse. In a certain easy lost mudstone section, the optimization model recommends air injection ratio 30% and underpressure value 0.5MPa, compared with traditional fresh water drilling (no air injection) and underpressure value control within the mudstone stability limit. The technology dynamically generates drilling parameters suitable for different formations, and solves the efficiency and safety bottleneck of traditional technology in complex formations.

[0019] The application has a multi-parameter collaborative optimization technology of well completion sealing and sand control scheme, which improves the sealing life and the backflow efficiency. The well completion sealing scheme decides the lithology combination of the casing and the screen pipe, the alloy hanger lead sealing layer parameters, and the gravel packing density and the screen pipe layer number matching through the optimization model. The traditional expanded rubber water stopper is easy to age and fail, the sand control process decision sub-module dynamically selects the sand control scheme based on the thermal reservoir fracture characteristics, and the collaborative action of the step-by-step well flushing instruction (air-lift reverse circulation well flushing→high-pressure jet flushing→chemical plug removal) and the drilling fluid dynamic regulation (pH value 8.5, density 1.1g / cm 3 The collaborative action greatly improves the reservoir permeability recovery rate after well completion. The technology solves the problems of sealing failure, sand particle invasion and backflow blockage through multi-parameter collaborative optimization, and prolongs the well completion sealing life. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The method flowchart of the application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0022] REFERENCE Figure 1The present application aims to provide a method for optimizing drilling and completion of low-to-moderate temperature geothermal wells, comprising the following steps: constructing a drilling equipment efficiency model: establishing an efficiency model for drilling equipment subsystems, the input of which includes drilling energy input, and the output of which is drilling footage; constructing a thermal reservoir response model: establishing a response model for the thermal reservoir, the input of which includes drilling parameter combinations, and the output of which includes geothermal production indicators; establishing a drilling optimization model: based on the efficiency model and the response model, establishing a drilling full-process optimization model, the decision variables of which include drilling equipment energy input, wellbore structure parameters, and completion control parameters; the optimization target is a function of minimizing drilling cost and maximizing thermal reservoir production capacity; iterative optimization solution: through Benders decomposition algorithm, the optimization model is solved multiple times, and drilling operations are dynamically controlled according to the solution results.

[0023] The theoretical basis and implementation mechanism of the double model construction are as follows: Drilling equipment efficiency model: based on the nonlinear mapping ability of neural network, the energy input parameters such as drilling rig power and mud pump flow are associated with drilling footage. The principle is to train through historical data, so that the neural network learns the complex mapping relationship of "energy input-formation response-drilling efficiency". For example, when the formation leakage rate increases, the effective utilization rate of mud pump flow decreases, and the neural network captures this nonlinear decay relationship through the weight adjustment of hidden layer nodes, thereby avoiding the prediction deviation of traditional linear models. The mathematical essence of this model is multivariate nonlinear regression, and the weight matrix is optimized through the error back propagation algorithm to minimize the mean square error of the predicted value and the actual value, which is suitable for processing the efficiency prediction problem of multiple parameter coupling and strong nonlinearity in the drilling process.

[0024] Thermal reservoir response model: taking advantage of the LSTM neural network in processing time series data, drilling fluid density, screen type and other parameters are dynamically mapped with geothermal production indicators (water production). The gating mechanism (forget gate, input gate, output gate) of LSTM can effectively remember the time series characteristics of different parameter effects, such as the long-term influence of gravel packing density on permeability. During model training, by learning the time series rules of "parameter application-reservoir response-production capacity change" in historical data, the future production capacity is predicted. The theoretical basis is the combination of reservoir percolation mechanics and machine learning, which fits the parameters that are difficult to quantify by theoretical models such as the influence of screen type on fracture flow conductivity through data-driven methods, solving the prediction error problem caused by too many assumptions in traditional analytical models.

[0025] The optimization principle and iteration logic of Benders decomposition algorithm are as follows: Algorithm framework: Benders decomposition belongs to a multi-level optimization algorithm, which decomposes complex mixed integer programming problems into upper master problem and lower sub-problem. In this invention, the master problem is responsible for decision-making well structure, drilling technology and other integer parameters (such as screen type, open hole length), and the sub-problem optimizes continuous parameters (such as drilling fluid density, sealing layer thickness) under the premise of given master problem parameters and feeds back the thermal reservoir response data (water production, temperature decay rate). This decomposition reduces the dimension of the optimization problem and reduces the computational complexity, which is suitable for optimization scenarios where discrete and continuous parameters coexist in the whole drilling process.

[0026] Iterative convergence mechanism: In each iteration, the master problem generates temporary decision variables, and the sub-problem calculates the objective function value and constraint conditions through the thermal reservoir response model. If the convergence condition is not met (the relative difference between the upper and lower bounds of the objective function is greater than or equal to the threshold), a Benders cut (i.e. constraint condition) is generated and returned to the master problem, limiting the search space in the subsequent iterations. For example, when the sub-problem finds that a certain open hole length leads to stress exceeding the limit of the sealing layer, it generates a Benders cut "open hole length ≤ 200m", which excludes the long open hole length scheme in the next iteration of the master problem. Through this iterative logic of "generation-verification-feedback-correction", the solution space is gradually reduced, and finally converges to the global optimal solution. The mathematical essence is to guide the master problem search through the dual information of the sub-problem, ensuring the feasibility and optimality of the optimization result.

[0027] The mathematical modeling principles of the objective function and constraint conditions are as follows: Objective function construction: min(∑ɸ+ɵ-α×ʀ) combines the multi-objective optimization idea of cost and production capacity. Among them, the drilling energy cost ɸ and the completion material cost ɵ are linearly accumulated, reflecting the direct economic input; the predicted water production ʀ is converted into a cost deduction item through the production capacity weight coefficient α (0 < α < 1), reflecting the contribution of production capacity to economic benefits. The mathematical meaning of this function is to establish a quantitative balance between cost and production capacity, and the value of α determines the optimization direction (for example, when α = 0.7, the production capacity is increased by 10 m / h, which is equivalent to deducting 70,000 yuan of cost). Through this linear weighting method, multi-objective optimization is converted into single-objective optimization, simplifying the solving process while retaining adaptability to different engineering requirements (cost control or production capacity improvement can be prioritized by adjusting α).

[0028] Constraint condition establishment: well structure compatibility constraint is based on geometric matching principle to ensure the mechanical stability of casing and formation; sand control screen strength limit constraint is based on material mechanics to avoid screen deformation and blockage; underbalanced drilling pressure threshold constraint is based on wellbore stability theory. These constraint conditions convert safety specifications in engineering practice into mathematical expressions, ensuring the engineering feasibility of the optimization scheme and realizing the unity of "theoretical optimization-engineering feasibility".

[0029] The technical logic of thermal reservoir type differentiation design and drilling process dynamic generation is as follows: The wellbore structure differentiation principle: for sandstone pore type thermal reservoir, the core is to prevent pollution, based on porous medium seepage theory, by increasing the diameter of technical casing (reducing cement invasion radius) and optimizing screen type (such as matching the size of wire wrapped screen gap with sand particle size), to reduce reservoir damage. The theoretical formula is: cement invasion depth L = K x (P / μ) x t (K is the permeability coefficient, P is the grouting pressure, μ is the cement viscosity, t is the time), optimizing the casing diameter can reduce the product of P and t, so that L is controlled within a safe range. For bedrock fissure type thermal reservoir, the goal is to protect productivity, according to the cubic law of fissure seepage Q = (gb 3 / 12μ) x ΔP (g is the acceleration of gravity, b is the fissure width, ΔP is the pressure difference), by optimizing the length of open hole section (increasing the exposure area of fissures) and wire wrapping parameters (reducing fissure blockage), to improve flow Q. The essence of this differentiation design is to match the corresponding wellbore structure parameters for different reservoir seepage mechanisms, to maximize energy transfer efficiency.

[0030] The dynamic generation logic of composite drilling process: in lost circulation formation, the principle of gas lift reverse circulation negative pressure suction is: by injecting high pressure gas (density pg) and drilling fluid (density pm) to form a mixed fluid, reducing the annular fluid column pressure Pc = pg x h (h is the well depth), when Pc < formation pressure Pf, negative pressure difference ΔP = Pf - Pc is generated, promoting cuttings to return. The model dynamically calculates ΔP according to the loss rate, matches the inner diameter d of double-wall drilling tool with the return velocity v, so that the cuttings carrying rate η = 0.85 x (v / vt) (vt is the critical velocity) ≥ 80%. In the easy-to-lose layer, water-filled air underbalanced drilling utilizes the compressibility of air, by controlling the air injection ratio β, adjusting the annular fluid density pa = pm x (1-β) + pg x β, to control the underpressure value ΔP = Pf - pa x h within the safe range of shale collapse pressure, while the increase of β enhances the fluid kinetic energy and improves the cuttings carrying capacity. The technical principle of this process is to control the fluid mechanics parameters to establish "pressure safety-carrying high efficiency" drilling conditions in complex formations, to solve the adaptability problem of traditional process.

[0031] The closed-loop optimization mechanism of completion sealing and dynamic logging is as follows: Collaborative optimization of multiple parameters for completion sealing: Based on elastic-plastic mechanics, the stress distribution σ(r,θ) of the lead sealing layer is related to the thickness h and the cone angle θ. Through finite element simulation, the constraint condition of σ(r,θ)≤σs (yield strength) is established to optimize the combination of h and θ. At the same time, the lithologic combination of casing and screen follows the principle of "elastic modulus matching". For example, the modulus difference between steel casing (E=210GPa) and wire-wrapped mesh screen (E=190GPa) is ≤10%, reducing thermal stress caused by temperature changes. The matching of gravel packing density ρ and the number of screen layers n is based on particle grading theory, ρ=ρ max ×(1-ε)(ρ max (where n is the maximum dry density and ε is the porosity) and when n ≥ 3 layers, sand particles with a diameter greater than 0.074 mm can be effectively blocked. The essence of this multi-parameter collaborative optimization is to establish a reliability model for the sealing system through multi-physics coupling analysis (mechanics, thermals, and fluid dynamics). This complete technology chain, from material selection and structural design to parameter matching, enhances seal life and sand control effectiveness.

[0032] Closed-Loop Optimization of a Dynamic Logging Parameter Library: Based on geostatistics, the reservoir permeability distribution k(x, y, z) fed back by logging is used to update the input parameters of the thermal reservoir response model via Kriging interpolation, forming a closed loop of "optimized model output logging plan → logging data feedback → model parameter correction → new round of optimization." The mathematical principle behind this optimization is Bayesian updating, where new logging data is used to modify the model's prior probability distribution to obtain the posterior distribution, allowing the model to continuously approximate the actual reservoir characteristics. For example, if logging reveals that the permeability of a certain area is lower than the model's predicted value, the model automatically adjusts the wellbore parameters (such as increasing the jet pressure) in the next round of optimization by updating the permeability coefficient k in that area to compensate for the impact of insufficient permeability on production capacity. This closed-loop optimization mechanism breaks away from the traditional "open-loop design-passive execution" model, enabling adaptive adjustments to the drilling and completion processes and significantly enhancing the system's robustness to geological uncertainties.

[0033] The following are specific examples.

[0034] A medium-low temperature geothermal field is located in the Guanzhong Plain. The target thermal reservoir is a fractured thermal reservoir in the Cambrian limestone of the Lower Paleozoic, with a burial depth of 1800-2200m and a formation temperature of 60-80℃. The expected single well design production capacity is 50m3. 3 / h. Preliminary exploration revealed complex geological conditions in the area, including uneven bedrock fractures, localized lost-flow formations (with a loss rate of 15%-30%), and mudstone interlayers. Traditional drilling methods encountered the following problems during adjacent well construction: secondary wellbore structures led to reservoir contamination, resulting in a 25% reduction in water production compared to predicted values; rubber seal failure caused a 10-15°C drop in water temperature; and positive circulation drilling achieved a mechanical penetration rate of only 1.5 m / h in lost-flow formations, resulting in a construction period of up to 45 days.

[0035] Drilling equipment efficiency model construction: Data collection: Collect the drilling data of 10 historical wells in this area, including rig power (400-500 kW), mud pump flow rate (25-40 L / s), air injection volume (0-50 m 3 / min), formation leakage rate (5%-40%), and mechanical drilling rate (0.8-3.0 m / h). For example, in a well with rig power of 450 kW, mud pump flow rate of 35 L / s, and leakage rate of 20%, the mechanical drilling rate is 2.1 m / h.

[0036] Model training: A three-layer BP neural network (5 nodes in the input layer, 10 nodes in the hidden layer, and 1 node in the output layer) is used, with 70% of the data as the training set and 30% as the test set. During training, the learning rate is set to 0.01, the number of iterations is 1000, and the loss function is mean squared error. After training, the average prediction error of the model for the test set is 4.8%, such as a test sample with actual drilling speed of 2.5 m / h, the model predicts 2.62 m / h, with an error of 5.2%, meeting the engineering precision requirements.

[0037] Thermal reservoir response model construction: Data integration: Organize the completion parameters and productivity data of historical wells, including drilling fluid density (1.05-1.2 g / cm 3 ), pH value (7.0-9.0), screen type (wire-wrapped screen, wrapped wire mesh), gravel packing density (1.8-2.4 g / cm 3 ), well flushing parameters (air lift time, jet pressure), and water production (30-70 m 3 / h). For example, in a well using wrapped wire mesh screen, packing density of 2.2 g / cm 3 , and well flushing jet pressure of 20 MPa, the water production is 65 m 3 / h.

[0038] Model establishment: LSTM neural network (5 nodes in the input layer, 50 nodes in the hidden layer, and 1 node in the output layer) is used to train the model to capture the time series relationship between parameters and water production. After testing, the average prediction error of the model for water production is 6.3%, and for a verification sample with actual water production of 55 m 3 / h, the predicted value is 58.2 m 3 / h, with an error of 5.8%, which can accurately reflect the impact of completion parameters on productivity.

[0039] Drilling optimization model establishment and solution: Decision variables setting: well structure parameters are three open hole section length (180-250 m) and wrapped screen layer number (2-4 layers); drilling process parameters are gas lift reverse circulation double wall drill inner diameter (108-139 mm) and cuttings upflow velocity (2.0-3.0 m / s); completion control parameters are lead sealing layer thickness (10-20 mm) and cone angle (25°-35°).

[0040] Objective function and constraints: the objective function is min(∑ɸ+ɵ-0.7×ʀ), where ɸ is drilling energy consumption cost (kW·h unit price 0.8 yuan), ɵ is completion material cost (screen pipe, hanger, etc.), and ʀ is predicted water production (m 3 / h). The constraint conditions include: open hole section length ≤ 250 m, sealing layer stress ≤ lead material yield strength (18 MPa), underbalanced pressure ≥ 0.3 MPa and ≤ 0.8 MPa.

[0041] Benders decomposition iteration: the first iteration generates temporary parameters: open hole section 220 m, wrapped screen layer number 3, drill inner diameter 127 mm, upflow velocity 2.5 m / s, sealing thickness 15 mm, and cone angle 30°. After inputting the thermal reservoir model, the predicted water production is 68 m 3 / h, energy consumption cost is 280,000 yuan, material cost is 150,000 yuan, and the objective function value = 28+15-0.7×68=15.4. After 5 iterations, the relative difference between the upper and lower bounds decreases from 12% to 2.3% (< threshold 5%), and converges to the optimal scheme: open hole section 200 m, wrapped screen layer number 4, drill inner diameter 127 mm, upflow velocity 2.8 m / s, sealing thickness 16 mm, and cone angle 32°, at which the water production is 72 m 3 / h, energy consumption cost is 250,000 yuan, material cost is 180,000 yuan, and the objective function value = 25+18-0.7×72=12.6, which is optimized by 20.8% compared with the initial scheme.

[0042] Dynamic control and field implementation: Drilling process execution: gas lift reverse circulation is started in the lost circulation formation (loss rate 25%), double wall drill inner diameter is adjusted to 127 mm according to the model parameters, cuttings upflow velocity is controlled to 2.8 m / s, actual mechanical drilling speed reaches 3.2 m / h, which is improved by 113% compared with traditional positive circulation, and no cuttings accumulation occurs. Air-lift underbalanced drilling is used in the mudstone interlayer section, air injection ratio is 28%, underbalanced pressure value is 0.6 MPa, wellbore is stable, and cuttings carrying efficiency is improved by 55%, which shortens the construction period of this well section from the planned 10 days to 6 days.

[0043] Well completion sealing and sand control: A lithologic combination of steel casing and four layers of wire-wrapped mesh screen was selected, with an optimized lead sealing layer thickness of 16 mm and a cone angle of 32°. Stress simulation showed that the maximum stress of the sealing layer was 16.5 MPa < 18 MPa, meeting the strength requirements. The gravel packing density was 2.3 g / cm according to the model output. 3 Implementation, the sand control effect is significant, the sand intrusion amount is less than 0.8kg / m 3 The cascade well flushing was carried out in the sequence of "gas lift reverse circulation (4 hours) → high-pressure jetting (pressure 25 MPa, 2 hours) → chemical deblocking (pH 8.8 deblocking agent, 1 hour)". After the well flushing, the reservoir permeability recovered to 96%.

[0044] Dynamic logging and model update: Real-time logging feedback on reservoir permeability distribution revealed that the permeability of the 2050-2100 m section was 15% lower than the model prediction. The thermal reservoir response model parameters were immediately updated, and the well flushing jet pressure in this section was adjusted to 28 MPa. The final water yield reached 70 m 3 / h, exceeding the designed production capacity by 40%, the outlet water temperature is 78℃, 13℃ higher than that of the adjacent well, and there is no channeling phenomenon.

[0045] Implementation effect and comparison: The total construction period of this well is 32 days, which is 13 days shorter than the traditional method, and the drilling cost is reduced by 18% (energy consumption is saved by 50,000 yuan, and material optimization is saved by 30,000 yuan), the single well production capacity is increased by 40%, and the sealing life is expected to exceed 20 years. Compared with the adjacent wells, the water output of the traditional well is 50m 3 / h, the temperature is 65 ° C, and after one year the temperature drops to 55 ° C due to failure of the rubber seal; after three years of operation, the well in this embodiment was tested and the water output was stable at 68m 3 / h, temperature 76℃, and recharge efficiency 82%, which verified the effectiveness of this method.

[0046] In the foregoing specification, examples have been described with reference to specific exemplary embodiments. However, it will be apparent that various modifications and changes can be made to the specific examples without departing from the scope as set forth in the appended claims, and the claims are not limited to the specific examples described above.

Claims

1. A method for optimizing medium and low temperature geothermal drilling and completion, characterized in that: The following steps are involved: Constructing a drilling equipment efficiency model: Build an efficiency model for the drilling equipment subsystem, with the input including drilling energy input and the output being drilling footage. Constructing a thermal reservoir response model: Build a response model for the thermal reservoir, whose input includes a combination of drilling parameters and output includes geothermal productivity indicators; Establishing a drilling optimization model: Based on the efficiency model and response model, a full-process drilling optimization model is established. Decision variables include drilling equipment energy input, wellbore structural parameters, and completion control parameters. The optimization objective is a function of minimizing drilling costs and maximizing thermal storage capacity. Iterative optimization solution: The optimization model is solved iteratively multiple times using the Benders decomposition algorithm, and drilling operations are dynamically controlled based on the solution results.

2. The medium-low temperature geothermal drilling and completion optimization method according to claim 1, characterized in that: The construction of drilling equipment efficiency model specifically includes: Obtain historical drilling data, including: drilling rig power, mud pump flow, air injection volume, formation leakage rate, and mechanical penetration rate; The first neural network model was established and the drilling equipment efficiency model was obtained through historical data training to predict the drilling efficiency under different input parameters.

3. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 1, characterized in that: It is characterized in that Constructing a thermal reservoir response model specifically includes: Obtain historical thermal reservoir response data, including: drilling fluid density, pH value, screen type, gravel packing density, and well washing parameters; A second neural network model was established, and a thermal reservoir response model was obtained through historical data training to predict the mapping relationship between completion parameters and geothermal well water yield.

4. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 1, characterized in that: The iterative optimization solution uses the Benders decomposition algorithm, including: Generate temporary decision variables: Generate wellbore structure parameters and drilling process parameters based on the current model; Execute simulated drilling: send simulation instructions to the thermal reservoir response model based on temporary parameters; Receive feedback data: including predicted water output, temperature decay rate and gradient information; When the relative difference between the upper bound and the lower bound of the objective function is less than the threshold, the final drilling plan is output.

5. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 4, characterized in that: The optimization objective function is: min(∑ɸ+ɵ-α×ʀ); Among them, ɸ is the drilling energy cost, ɵ is the completion material cost, ʀ is the predicted water yield, and α is the production capacity weight coefficient; Constraints include: wellbore structure compatibility, sand control screen strength limit, and underbalanced drilling pressure threshold.

6. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 1, characterized in that: Wellbore structure design is incorporated into the optimization model as a decision variable: For porous sandstone reservoirs, determine the technical casing diameter and screen type for the secondary wellbore structure; For bedrock fracture-type heat reservoirs, the length of the open hole section of the three-well structure and the wire wrapping process parameters are determined.

7. The medium-low temperature geothermal drilling and completion optimization method according to claim 1, characterized in that: Composite drilling process parameters are dynamically generated through the optimization model: Generate gas lift reverse circulation drilling parameters in lost circulation formations, including double-wall drill bit inner diameter and cuttings return velocity; Generate water-filled air underbalanced drilling parameters in the leakage-prone layer, including air injection ratio and underpressure value.

8. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 1, characterized in that: The completion sealing plan is determined by the optimization model: Select the lithologic combination of casing and sand screen; Optimize the lead sealing layer thickness and cone angle of the special alloy hanger; Dynamically match the gravel packing density with the number of screen wire wrap layers.

9. The method for optimizing medium and low temperature geothermal drilling and completion according to claim 1, characterized in that: It also includes the establishment of a dynamic logging parameter library: Based on the logging plan output by the optimization model, real-time feedback of reservoir permeability distribution is provided; The thermal reservoir response model is updated based on the feedback data to form a closed-loop optimization.

10. A drilling optimization system for implementing the medium- and low-temperature geothermal drilling and completion optimization method according to any one of claims 1 to 9, characterized in that: include: Equipment efficiency modeling module, used to store drilling equipment efficiency models and receive real-time drilling rig and mud pump operation data; Thermal reservoir response modeling module, which is used to store thermal reservoir response models and integrate geological data with historical production data; An optimization engine that executes the Benders decomposition algorithm and outputs the optimal parameter combination for wellbore structure, drilling technology, and completion sealing; Dynamic control terminal, used to send optimized parameters to the drilling equipment execution unit, and adjust the gas lift reverse circulation device and adaptive drilling fluid injection system in real time; The optimization solution engine also includes: The sand control process decision submodule is used to dynamically select sand control schemes among wire-wound screens, slotted liners, and wire-wound mesh based on the characteristics of thermal reservoir fractures. Seal life prediction submodule, used to optimize the rubber-free seal structure parameters by simulating the stress distribution of the alloy hanger seal layer; The dynamic control terminal performs in real time: Stepped well-washing instructions are used to start gas lift reverse circulation well-washing, high-pressure jet flushing, and chemical plugging agent injection in an optimized sequence; Dynamic control of drilling fluid is used to automatically adjust the drilling fluid properties according to the pH value and density output by the model.

Images