Complex fault block thin oil layer drilling trajectory optimization method and device

Abstract

The invention discloses a complex fault block thin oil reservoir drilling trajectory optimization method and device. The method comprises the steps that geological data and a three-dimensional geological model of a complex fault block reservoir are obtained; inputting the geological data into a pre-trained recognition model, and outputting a recognition result; determining a well position optimization target position; evaluating the well wall stability, high pressure and leakage risk of each position in the three-dimensional geologic model to generate an evaluation result; according to the well position optimization target position, the evaluation result and the preset trajectory parameters, the optimal drilling trajectory is generated, complex distribution characteristics and variable reservoir conditions of the underground thin oil layer can be fully considered, the well position and drilling trajectory determination efficiency is effectively improved, the determined well position and drilling trajectory can improve the drilling success rate, and the drilling efficiency is improved. The exploitation efficiency and yield of an oil field are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of oil and gas exploration and development technology, and in particular to a method and apparatus for optimizing drilling trajectories in complex fault-block thin oil layers. Background Technology

[0002] This section is intended to provide background or context for embodiments of the present invention. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] In the process of oilfield development, the exploration and development of complex fault-block thin oil layers face many challenges. Traditional well location determination methods mainly rely on human experience and simple geological models, which are difficult to fully consider the complex distribution characteristics and variable reservoir conditions of underground thin oil layers. This leads to inaccurate well location selection, high drilling risk, inaccurate production prediction, and low economic benefits. Summary of the Invention

[0004] This invention provides a method for optimizing drilling trajectories in complex fault-block thin oil-bearing formations. This method fully considers the complex distribution characteristics and variable reservoir conditions of the underground thin oil-bearing formations, effectively improving the efficiency of well location and drilling trajectory determination. The determined well location and drilling trajectory enhance the drilling success rate, significantly improving oilfield production efficiency and output. The method includes:

[0005] Obtain geological data of complex fault-block reservoirs and establish three-dimensional geological models based on the geological data of complex fault-block reservoirs;

[0006] Geological data is input into a pre-trained recognition model, and the recognition result is output. The recognition result is the probability that each location in the three-dimensional geological model is a thin oil layer. The recognition model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities.

[0007] The areas identified as having a higher probability of being thin oil layers than the preset probability, not being faults or folds based on geological data and three-dimensional geological models, and having pressures lower than the preset pressures and collapse probabilities lower than the preset collapse probabilities are identified as well location optimization targets.

[0008] Based on geological data, the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model are assessed, and assessment results are generated.

[0009] The optimal drilling trajectory is generated based on the well location optimization target, evaluation results, and preset trajectory parameters.

[0010] This invention also provides a drilling trajectory optimization device for complex fault-block thin oil layers, which fully considers the complex distribution characteristics and variable reservoir conditions of underground thin oil layers, effectively improves the efficiency of well location and drilling trajectory determination, and enables the determined well location and drilling trajectory to improve the drilling success rate, significantly improving the oilfield's production efficiency and output. The device includes:

[0011] The acquisition module is used to acquire geological data of complex fault-block reservoirs and to build three-dimensional geological models based on the geological data of complex fault-block reservoirs.

[0012] The identification module is used to input geological data into a pre-trained identification model and output identification results; the identification results are the probability that each location in the three-dimensional geological model is a thin oil layer; the identification model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities;

[0013] The determination module is used to identify areas where the probability of identification as a thin oil layer is greater than the preset probability, which are determined not to be faults or folds based on geological data and three-dimensional geological models, and which have pressures lower than the preset pressures and collapse probabilities lower than the preset collapse probabilities as well location optimization targets.

[0014] The assessment module is used to assess the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model based on geological data, and generate assessment results.

[0015] The generation module is used to generate the optimal drilling trajectory based on the well location optimization target, evaluation results, and preset trajectory parameters.

[0016] Compared with existing fracturing stimulation effect analysis techniques, this invention obtains geological data of complex fault-block reservoirs and establishes a three-dimensional geological model based on the geological data. The geological data is input into a pre-trained recognition model, which outputs the recognition result. The recognition result represents the probability that each location in the three-dimensional geological model is a thin oil layer. The recognition model is trained using historical geological data with labeled thin oil layer probabilities. The invention distinguishes between locations where the probability of a thin oil layer is greater than a preset probability and locations where the probability is not determined based on the geological data and the three-dimensional geological model. Faults or folds, areas with pressures lower than preset pressures and collapse probabilities lower than preset collapse probabilities are identified as well location optimization targets. Based on geological data, wellbore stability, high pressure, and leakage risks at each location in the 3D geological model are assessed, and assessment results are generated. Based on the well location optimization targets, assessment results, and preset trajectory parameters, the optimal drilling trajectory is generated. This fully considers the complex distribution characteristics and variable reservoir conditions of thin underground oil layers, effectively improving the efficiency of well location and drilling trajectory determination. The determined well locations and drilling trajectories can improve the drilling success rate and significantly improve the oilfield's production efficiency and output. Attached Figure Description

[0017] 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. In the drawings:

[0018] Figure 1 This is a flowchart of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in an embodiment of the present invention;

[0019] Figure 2 This is a flowchart illustrating a specific example of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in this invention.

[0020] Figure 3 This is a flowchart illustrating a specific example of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in this invention.

[0021] Figure 4 This is a flowchart illustrating the training process of the recognition model provided in this embodiment of the invention.

[0022] Figure 5 This is a schematic diagram of well location optimization target determination provided in an embodiment of the present invention;

[0023] Figure 6 This is a flowchart of drilling engineering risk assessment provided in an embodiment of the present invention;

[0024] Figure 7 This is a flowchart of the capacity forecasting and optimization decision-making process provided in this embodiment of the invention;

[0025] Figure 8 This is a flowchart of the economic benefit evaluation process in an embodiment of the present invention;

[0026] Figure 9 This is a schematic diagram of a drilling trajectory optimization device for complex fault-block thin oil layers provided in an embodiment of the present invention;

[0027] Figure 10 This is a schematic diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0030] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0031] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0032] In oilfield development, the exploration and development of complex fault-block thin oil-bearing layers face numerous challenges. Traditional well location determination methods rely mainly on manual experience and simple geological models, which fail to fully consider the complex distribution characteristics and variable reservoir conditions of underground thin oil-bearing layers. This leads to inaccurate well location selection, high drilling risks, inaccurate production predictions, and low economic efficiency. Therefore, there is an urgent need for an automated well location optimization method that can comprehensively consider geological structure, reservoir development, oil layer distribution, and production data to improve oilfield extraction efficiency and production.

[0033] Figure 1 This is a flowchart of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in an embodiment of the present invention, such as... Figure 1 As shown, the method may include:

[0034] Step 101: Obtain geological data of complex fault-block reservoirs and a three-dimensional geological model based on the geological data of complex fault-block reservoirs;

[0035] Step 102: Input the geological data into the pre-trained recognition model and output the recognition result; the recognition result is the probability that each location in the three-dimensional geological model is a thin oil layer; the recognition model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities;

[0036] Step 103: The area whose identification results show that the probability of it being a thin oil layer is greater than the preset probability, which is determined to be a fault or fold based on geological data and three-dimensional geological model, and whose pressure is lower than the preset pressure and whose collapse probability is lower than the preset collapse probability is identified as the well location optimization target.

[0037] Step 104: Based on geological data, assess the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model, and generate assessment results;

[0038] Step 105: Generate the optimal drilling trajectory based on the well location optimization target, evaluation results, and preset trajectory parameters.

[0039] This invention provides an automatic well location optimization method and apparatus for complex fault-block thin oil layers. By comprehensively considering structural features, reservoir development, oil layer distribution, and existing well locations and production data, and utilizing computer deep learning algorithms, it accurately identifies and analyzes the distribution characteristics of underground thin oil layers, determines the potential target locations of the target layer, continuously optimizes the drilling trajectory, significantly improves the oilfield's extraction efficiency and production, and has broad application prospects.

[0040] Figure 2 This is a flowchart illustrating a specific example of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in this invention, such as... Figure 2 As shown, the drilling trajectory optimization method for complex fault-block thin oil-bearing layers can include the following steps: collecting and inputting geological structural features, reservoir development, oil layer distribution, existing well locations, and production data; using geological models and reservoir feature data to assess the distribution characteristics of underground thin oil-bearing layers and identify potential reservoir and oil layer locations; using deep learning algorithms to analyze the collected data and accurately identify and predict the distribution characteristics of thin oil-bearing layers; determining the potential target locations of target oil-bearing layers based on the analysis results; assessing drilling engineering risks and formulating anti-collision strategies; conducting production capacity prediction and optimization decisions, and continuously optimizing the drilling trajectory; conducting economic benefit evaluation; and outputting the optimized decision scheme and related data.

[0041] Figure 3 This is a flowchart illustrating a specific example of a drilling trajectory optimization method for complex fault-block thin oil reservoirs provided in this invention, such as... Figure 3 As shown, to achieve the above objectives, this invention provides a method for optimizing drilling trajectories in complex fault-block thin oil reservoirs, comprising the following specific steps:

[0042] Data Collection and Input: Collect and input geological structural features, reservoir development, oil layer distribution, existing well locations, and production data. This includes, but is not limited to, the following data:

[0043] (1) Geological structural features: Obtain regional geological structural data, including geological structures such as faults and folds.

[0044] (2) Reservoir development status: Collect reservoir development parameters such as reservoir thickness, porosity, and permeability.

[0045] (3) Oil layer distribution: Collect data on oil layer thickness, oil-water interface, reservoir boundary, etc.

[0046] (4) Existing well locations and production data: Input the existing well location distribution and its historical production data, including production rate, pressure changes, etc.

[0047] This step requires integrating and preprocessing data from multiple sources (seismic, core, well logging, etc.) to ensure data consistency and integrity, and to generate a comprehensive dataset that can be analyzed.

[0048] Geological and reservoir risk assessment: Utilizing geological models and reservoir characteristic data, a comprehensive assessment of the distribution characteristics of thin underground oil-bearing layers is conducted to identify potential reservoir and oil-bearing layer locations. Faults and stratigraphic horizons are identified by analyzing the reflection characteristics of seismic waves at different underground levels. Combining seismic data and well logging interpretation results, geostatistical inversion methods are employed to precisely predict the distribution of underground reservoirs and the extent of oil-bearing layers.

[0049] Furthermore, based on the collected geological structure and reservoir data, a three-dimensional geological model is constructed to clarify the spatial distribution framework of the stratigraphy. Using the geological model and reservoir characteristic data, the distribution characteristics of thin oil layers are comprehensively evaluated, potential reservoir and oil layer locations are identified, and their development and production potential are assessed.

[0050] In addition, attribute modeling can be performed to combine with three-dimensional geological models to determine underground conditions. For example, reservoir attributes such as lithology, porosity, and permeability can be modeled in three-dimensional spatial distribution within the geological model to generate a reservoir attribute model.

[0051] Deep learning algorithm analysis: This involves using computer deep learning algorithms to analyze the collected data and accurately identify and predict the distribution characteristics of thin oil layers. The specific steps are as follows:

[0052] (1) Data preprocessing: Standardize the collected historical data to ensure the consistency and integrity of the historical data.

[0053] (2) Model selection and training: Select appropriate deep learning algorithms (such as neural networks, support vector machines, random forests, etc.) and use historical data to train the model so that it can identify and predict the distribution characteristics of underground thin oil layers.

[0054] (3) Model validation and optimization: Use the validation dataset to validate the trained model and adjust the model parameters to improve the prediction accuracy.

[0055] (4) Distribution feature prediction: Using the trained model, the distribution features of thin oil layers in the target area are predicted to identify high-potential reservoirs and oil layer locations.

[0056] Well location potential target location determination: Based on the analysis results of deep learning algorithms, the potential target locations of the target oil layer are determined.

[0057] Based on the prediction results of deep learning algorithms, high-potential oil-bearing reservoir areas are identified. Combining geological models and reservoir characteristics, optimal well location potential targets are determined.

[0058] Drilling project risk assessment: Taking into account geological structure and reservoir characteristics, assess drilling project risks and formulate collision prevention strategies.

[0059] Assess drilling risks at potential target sites, including wellbore stability, formation pressure, and leakage risk. Based on production forecasts, develop optimization strategies, including well trajectory optimization and drilling parameter adjustments.

[0060] Production capacity forecasting and optimization decision-making: Based on well location potential and drilling engineering risks, production capacity is forecasted, optimization decision-making schemes are formulated, and the drilling trajectory is continuously optimized. Specific steps are as follows:

[0061] (1) Production capacity prediction: The production capacity of potential targets is predicted by using static geological model simulation and dynamic numerical simulation.

[0062] (2) Optimization decision-making: Based on the production capacity forecast results, formulate optimization decision-making schemes, including drilling trajectory optimization and drilling parameter adjustment.

[0063] (3) Continuous optimization: During the drilling process, monitor drilling parameters in real time, continuously optimize the drilling trajectory, and improve drilling success rate and economic benefits.

[0064] Economic benefit evaluation: Evaluate the economic benefits of the optimized decision-making plan to ensure its cost-effectiveness. This includes:

[0065] Evaluate the implementation costs of the optimized decision-making plan, including drilling costs, equipment costs, etc.

[0066] Analyze the expected economic benefits of the optimization plan, including economic indicators such as return on investment and net present value;

[0067] Taking into account both costs and benefits, evaluate the economic feasibility of the optimization plan to ensure that the cost-effectiveness of the plan is maximized.

[0068] Data Output: Outputs the optimized well location plan and related data for decision-making purposes, specifically including:

[0069] Generate detailed optimization decision reports, including well location selection, risk assessment, production capacity forecast, and economic benefit evaluation;

[0070] Data output: Export the optimized well location plan and related data for relevant departments to use in decision-making.

[0071] Through the above steps, the method of the present invention can achieve automatic well location optimization for complex fault-block thin oil layers, improve oilfield extraction efficiency and production, and has significant economic and social benefits.

[0072] In one embodiment, geological data may include one or any combination of seismic interpretation data, reservoir data, oil reservoir data, well location distribution data, and historical production data of existing well locations.

[0073] Specifically, geological data may include:

[0074] 1. Seismic interpretation data:

[0075] Fault data: including information such as fault orientation, dip angle, and displacement;

[0076] Interpretive data: Seismic interpretation horizon data;

[0077] Tectonic unit division: The division of tectonic units within a region and their spatial relationships.

[0078] 2. Reservoir data:

[0079] Reservoir thickness: Reservoir thickness distribution data;

[0080] Lithological data: Types and distribution of reservoir lithology;

[0081] Porosity: The porosity distribution of reservoir rocks;

[0082] Permeability: Reservoir permeability data used to assess the fluid flow capacity of a reservoir.

[0083] 3. Reservoir data:

[0084] Oil layer thickness: The thickness distribution of the oil layer;

[0085] Oil-water interface: Data on the location of the interface between the oil layer and the water layer;

[0086] Reservoir boundary: The distribution and geometric shape of reservoir boundaries.

[0087] 4. Well location distribution data and historical production data of existing well locations

[0088] Well location distribution: Geographic coordinates and well trajectory data of existing well locations;

[0089] Historical production data includes production rates, cumulative output, pressure changes, and other production data.

[0090] Drilling log: Records data such as formation, pressure, and wellbore stability encountered during the drilling process.

[0091] In one embodiment, acquiring geological data of complex fault-block reservoirs and establishing a three-dimensional geological model based on the geological data of complex fault-block reservoirs may include: establishing a three-dimensional geological model based on seismic interpretation data, reservoir data, oil reservoir data, and well location distribution data; and adjusting the parameters of the three-dimensional geological model using historical production data and reservoir data of existing well locations. The three-dimensional geological model includes stratigraphic structure, faults, folds, and reservoir properties, etc.

[0092] Assessment methods for evaluating the distribution characteristics of thin subsurface oil layers using geological models and reservoir characteristic data can include:

[0093] 1. Tectonic interpretation of earthquakes

[0094] Reflection wave imaging: By analyzing the reflection characteristics of seismic waves at different underground levels, reflection wave images of underground geological structures are generated to identify faults and strata.

[0095] Velocity analysis: By analyzing the propagation patterns of seismic waves underground, a fine velocity field is established, and the interpretation results in the time domain are converted into interpretation results in the depth domain.

[0096] 2. Reservoir Characteristic Analysis

[0097] Sequence stratigraphy analysis: Using sequence stratigraphy methods, we can identify and interpret the temporal and spatial relationships of strata, divide stratigraphic units, and identify sedimentary environments.

[0098] Lithology and lithofacies analysis: Through laboratory rock sample analysis and well logging interpretation, the lithology and lithofacies characteristics of the reservoir are identified, and the reservoir's physical properties and oil and gas potential are inferred.

[0099] Porosity and permeability: Using drilling core data and logging data, analyze the porosity and permeability distribution of the reservoir to assess its development and reservoir performance.

[0100] Reservoir prediction: Combining seismic data and well logging interpretation results, geostatistical inversion methods are used to accurately predict the distribution of underground reservoirs and the pattern of oil layer development.

[0101] 3. Geological Model Construction

[0102] 3D geological modeling: By integrating seismic interpretation results and well logging data, a 3D geological model is constructed to accurately describe the subsurface structural layers and reservoir spatial distribution.

[0103] In one embodiment, the data used for thin oil layer identification by deep learning algorithm in step 102 can be the reservoir and thin oil layer interpreted by well logging as inversion constraints, the reservoir and thin oil layer predicted by geostatistical inversion and other methods, and verified by blind wells. This can effectively improve the prediction accuracy and precision of reservoir inversion. The inversion results and well logging interpretation results can be used together as the training dataset for the deep learning model.

[0104] In one embodiment, the algorithm used by the deep learning model in step 102 may include at least one of the following: neural network algorithm, support vector machine algorithm, and random forest algorithm, selecting an appropriate model to handle different types of data and tasks.

[0105] In one embodiment, the drilling trajectory optimization method for complex fault-block thin oil layers may further include: acquiring historical geological data; labeling the historical geological data according to whether the location corresponding to the historical geological data is a thin oil layer; and training a deep learning model using the labeled historical geological data to obtain a recognition model.

[0106] The deep learning model analyzes the input data to predict the distribution characteristics of thin oil layers. The model outputs the probability or label of whether each location is a thin oil layer. Labeled historical data is used as training data and input into the deep learning model for training. By learning features and patterns in the data, the model can identify the distribution characteristics of thin oil layers. Cross-validation is used to evaluate the model's performance and avoid overfitting. Validation dataset: The trained model is validated using a validation dataset (logging interpretation results from new wells or blind wells) to evaluate its performance on unseen data. Model parameters are adjusted based on the validation results to optimize model performance and improve prediction accuracy. The model's predictions are combined with a geological model to generate a distribution map of thin oil layers. Comprehensive analysis of geological and reservoir characteristics further determines the location and extent of thin oil layers.

[0107] Figure 4 This is a flowchart illustrating the training process of the recognition model provided in this embodiment of the invention. Figure 4 As shown, the principle of deep learning algorithms is to learn and extract features and patterns from a large amount of historical data through training, thereby enabling accurate identification and prediction of the distribution of thin oil layers in new data. These algorithms can handle high-dimensional, complex, nonlinear data and have strong generalization capabilities, including:

[0108] Data preprocessing: Standardize the collected data to ensure its consistency and integrity.

[0109] Model selection and training: Select appropriate deep learning algorithms (such as neural networks, support vector machines (SVM), random forests, convolutional neural networks (CNN), and long short-term memory networks (LSTM), etc.) and train the model using historical data.

[0110] Model validation and optimization: Use a validation dataset to validate the trained model and adjust the model parameters to improve prediction accuracy.

[0111] Distribution feature prediction: Using a trained model, the distribution features of thin oil layers in the target area are predicted.

[0112] It is necessary to utilize geological models, reservoir properties, deep learning prediction results, and engineering factors to conduct a multi-parameter comprehensive evaluation to determine the optimal well location potential target, i.e., the well location optimization target. The specific process is as follows:

[0113] 1. Reservoir assessment:

[0114] Lithological analysis: Select lithologies with good reservoir properties, such as sandstone or fractured carbonate rocks.

[0115] Reservoir thickness: Assess the thickness distribution of the reservoir and select areas with greater thickness.

[0116] Porosity and permeability: Select reservoir areas with high porosity and good permeability, as these areas typically have good storage capacity and fluid flow.

[0117] Here, the reservoir results serve as constraints for predicting oil-bearing layers. That is, reservoir data is first obtained through reservoir prediction methods such as geostatistical inversion, and then oil-bearing layer data is inverted under the constraints of the reservoir data to obtain the initial dataset for deep learning.

[0118] 2. Deep learning prediction results:

[0119] Thin oil layer distribution: By combining the thin oil layer distribution map predicted by the deep learning model, the location of oil layers with high potential is identified.

[0120] High-potential regions: Select regions identified as high-potential in deep learning prediction results as initial targets.

[0121] Geological and engineering factors to consider:

[0122] Faults and folds: Avoid fault and fold areas that may pose geological risks, and choose areas with relatively stable geology.

[0123] Drilling risks: Consider the engineering risks during the drilling process and avoid high-pressure formations or formations that are prone to collapse.

[0124] Comprehensive decision-making:

[0125] Multi-parameter comprehensive evaluation: Using geological models, reservoir properties, deep learning prediction results and engineering factors, a multi-parameter comprehensive evaluation is conducted to determine the optimal well location target.

[0126] The subsequent applications of well location optimization targets include: Decision-making output: The identified potential well locations are output as part of the decision-making plan to the oilfield development decision-making team. Production prediction: Static geological model simulation: Based on the potential well locations, static geological model simulations are performed to predict the production capacity of the oil reservoir. Dynamic numerical simulation: Combining historical production data and geological models, dynamic numerical simulations are performed to evaluate the long-term production capacity and economic benefits of different well locations. Optimization decision-making: Real-time monitoring and adjustment: During drilling and production, drilling parameters and production data are monitored in real time, and well locations and drilling trajectories are dynamically adjusted to optimize well location selection and production strategies. Risk management: Collision avoidance strategies and risk management measures are developed to ensure the safety and economy of well location selection and the drilling process. Figure 5 This is a schematic diagram of well location optimization target determination provided in an embodiment of the present invention, as shown below. Figure 5 As shown, KI is the name of the stratigraphic layer, Segment 1 is the name of the fault block, and different colors in the figure represent different elevation depths in meters. Based on the oil layer distribution results predicted by the deep learning algorithm and the reservoir development in the geological model, areas with well-developed reservoirs and high production potential are selected as potential well sites.

[0127] Now that the well location optimization target has been obtained, the next step is to formulate a suitable drilling trajectory based on the well location optimization target and to conduct a risk assessment of the drilling project.

[0128] Figure 6 This is a flowchart of drilling engineering risk assessment provided in an embodiment of the present invention, such as... Figure 6 As shown, drilling engineering risk assessment comprehensively considers geological structure and reservoir characteristics to evaluate drilling engineering risks and formulate collision prevention strategies. Through geological and reservoir data, potential risk factors during the drilling process are assessed, such as wellbore stability issues, blowout risks due to excessive formation pressure, and formation leakage, and corresponding collision prevention strategies and risk control measures are formulated.

[0129] The assessment of potential risk factors during the drilling process includes:

[0130] Wellbore stability assessment: Analyze the mechanical properties of the formation lithology to assess the stability of the wellbore.

[0131] Formation pressure assessment: Using formation pressure prediction models, assess formation pressure distribution and identify high-pressure formations.

[0132] Leakage risk assessment: Analyze porosity and permeability data to assess the leakage risk of the formation.

[0133] Collision Avoidance Strategy Generation: ① Strategy Library: Stores pre-defined collision avoidance strategies and rules by experts for computer access. ② Path Planning: Automatically generates the optimal drilling path based on the 3D geological model and risk assessment results, combined with rules from the strategy library. ③ Real-time Adjustment: Monitors drilling data in real time and dynamically adjusts the drilling path based on feedback. ④ Collision Avoidance Strategy Implementation: Generates a detailed drilling execution plan, including parameters such as drilling angle, drilling speed, and pressure control. Through real-time monitoring and feedback mechanisms, drilling strategies are adjusted promptly to ensure the effective implementation of collision avoidance strategies.

[0134] In one embodiment, the drilling trajectory optimization method for complex fault-block thin oil layers may further include: acquiring real-time drilling data for drilling based on the well location optimized target position and the optimal drilling trajectory; and adjusting the optimal drilling trajectory based on the real-time drilling data and preset trajectory parameters.

[0135] Based on well location potential targets and drilling engineering risks, production capacity is predicted, optimization decision-making plans are formulated, and drilling trajectory is continuously optimized.

[0136] Figure 7 The flowchart for capacity forecasting and optimization decision-making provided in this embodiment of the invention is as follows: Figure 7 As shown, based on the well location potential target and drilling engineering risks, production capacity is predicted, an optimized decision-making scheme is formulated, and the drilling trajectory is continuously optimized. Through static geological models and dynamic numerical simulations, the production capacity of the oil reservoir is predicted. Combined with real-time monitoring data, the drilling trajectory and parameters are dynamically adjusted to ensure the optimization of the drilling process, maximize the oil reservoir output, and ensure the scientific and economical deployment of well locations.

[0137] The static geological model simulation mainly utilizes the constructed three-dimensional geological model to determine the distribution of underground fluids and calculate oil and gas reserves, assess reservoir development and oil and gas accumulation potential, and describe reservoir properties and spatial distribution. The specific steps are as follows:

[0138] (1) Data collection and integration:

[0139] Seismic data: Acquire reflected wave imaging data and velocity analysis data to identify stratigraphic interfaces and structural features.

[0140] Well logging data: Collect well logging interpretation results data, including but not limited to porosity, permeability, lithology, fluid properties and other data.

[0141] Geological survey data: Obtain geological information such as faults, folds, and lithological distribution.

[0142] (2) Constructing a three-dimensional geological model:

[0143] Geological modeling: Based on seismic reflection layer data, construct the geometry of the strata, including stratum thickness, bedding plane location and angle, and describe structural features and fault displacement.

[0144] Attribute modeling: Spatial interpolation and modeling of well logging data and seismic attribute data to generate reservoir attribute models such as porosity, permeability, and lithology.

[0145] (3) Model calibration and validation:

[0146] Historical data comparison: Using historical production data and logging data from existing well locations, the geological model is calibrated to ensure its accuracy and reliability.

[0147] Model tuning: Based on the calibration results, adjust the model parameters and input data to improve the model's prediction accuracy.

[0148] 2. Dynamic numerical simulation is used to perform dynamic numerical simulations based on static geological models to predict reservoir productivity and pressure changes during development, simulate fluid flow during reservoir development, and predict reservoir productivity and production dynamics. The specific steps are as follows:

[0149] (1) Establish a dynamic model:

[0150] Mesh generation: The three-dimensional geological model is discretized into mesh cells, each containing attributes such as porosity, permeability, and fluid saturation.

[0151] Initial conditions setting: Set the initial conditions of the model, including formation pressure, fluid saturation, temperature, etc.

[0152] (2) Determine the physical property parameters:

[0153] Rock properties: Based on laboratory analysis and well logging interpretation results, determine parameters such as porosity, permeability, relative permeability, and capillary pressure of the rock.

[0154] Fluid properties: Based on experimental data of the physical properties of oil, water, and gas, determine parameters such as density, viscosity, and solubility of the fluid.

[0155] (3) Establish the flow equation:

[0156] Continuity equation: describes the mass conservation in the reservoir, taking into account the multiphase flow of oil, water and gas.

[0157] Momentum equation: Based on Darcy's law, it describes the flow law of fluids in porous media.

[0158] Energy equation: Considering the effect of formation temperature changes on fluid flow.

[0159] (4) Boundary conditions and production data input:

[0160] Boundary conditions: Set the boundary conditions of the model, such as closed boundaries, pressure boundaries, etc.

[0161] Production data: Input the production data for the existing well location, including production output, injection volume, bottom hole flowing pressure, etc.

[0162] (5) Numerical solution:

[0163] Discretization methods: Numerical methods such as finite difference, finite element, or finite volume are used to discretize the flow equations.

[0164] Solver selection: Select an appropriate numerical solver, such as the Newton-Raphson iterative method, to solve the equations.

[0165] (5) Historical fit:

[0166] Historical data fitting: The dynamic model is fitted using historical production data, and the model parameters are adjusted to ensure that the model can accurately reflect the actual production dynamics of the reservoir.

[0167] Fitting results analysis: Analyze the fitting results to evaluate the accuracy and reliability of the model.

[0168] (6) Prediction and optimization:

[0169] Capacity forecasting: Based on a well-fitted dynamic model, predict future capacity and production dynamics, and evaluate the effectiveness of different development schemes.

[0170] Optimization Decisions: Based on the forecast results, optimize well location selection, drilling trajectory and production parameters to formulate the optimal development plan.

[0171] Figure 8 This is a flowchart of the economic benefit evaluation process in an embodiment of the present invention, such as... Figure 8 As shown, an economic benefit evaluation is conducted on the optimized decision-making scheme to ensure its cost-effectiveness. The implementation costs of the optimized decision-making scheme are assessed, including drilling costs and equipment costs. The expected economic benefits of the optimized scheme are analyzed, including economic indicators such as return on investment (ROI) and net present value (NPV). Taking into account both costs and benefits, the economic feasibility of the optimized scheme is evaluated to ensure maximum cost-effectiveness. The optimized well location scheme and related data are output for decision-making purposes. A detailed optimization decision-making report is generated, including well location selection, risk assessment, production capacity forecasting, and economic benefit evaluation. The optimized well location scheme and related data are exported for decision-making by relevant departments. The economic benefit evaluation includes ROI analysis and NPV analysis.

[0172] In one embodiment, the drilling trajectory optimization method for complex fault-block thin oil reservoirs may further include: determining multiple drilling implementation strategies based on the well location optimization target and the optimal drilling trajectory; determining the implementation cost, expected benefit, workload, safety risk information, resource utilization rate, energy consumption, success rate, failure rate, maintenance cost, oil and gas production rate, and resource recovery rate of each of the multiple drilling implementation strategies; the implementation cost includes drilling cost and equipment cost; the expected benefit includes return on investment and net present value; and determining the optimal drilling implementation strategy among the multiple drilling implementation strategies based on the implementation cost, expected benefit, workload, safety risk information, resource utilization rate, energy consumption, success rate, failure rate, maintenance cost, oil and gas production rate, and resource recovery rate, and outputting it to a designated terminal device.

[0173] The process of determining the optimal drilling implementation strategy from multiple drilling implementation strategies and outputting it to a designated terminal device, based on the implementation costs, expected benefits, workload, safety risk information, resource utilization, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate, may include:

[0174] 1. Implementation cost assessment: Computer-based assessment of the implementation costs of the optimization decision-making scheme, including drilling costs, equipment costs, etc.

[0175] 2. Expected economic benefit analysis: Analyze the expected economic benefits of the optimization plan, including economic indicators such as return on investment and net present value.

[0176] 3. Environmental Impact Assessment: Evaluate the workload, output data, and production increase measures of different options, as well as potential risk factors, and select the option with the least environmental impact.

[0177] 4. Resource utilization efficiency assessment: Evaluate the resource utilization rate and energy consumption of different schemes, and select the scheme with the highest resource utilization efficiency.

[0178] 5. Technical Reliability Assessment: Evaluate the success rate, failure rate, and maintenance cost of different solutions, and select the solution with the highest technical reliability.

[0179] 6. Productivity and Recovery Rate Assessment: Predict the oil and gas productivity and resource recovery rate of different schemes, and select the scheme with the highest productivity and recovery rate.

[0180] 7. Security assessment: Evaluate the security risks and security measures of different options, and select the option with the lowest security risk.

[0181] 8. Comprehensive evaluation: Taking into account economic benefits, environmental impact, resource utilization efficiency, technical reliability, productivity and safety, evaluate the technical and economic feasibility of the optimization plan to ensure that the cost-effectiveness and technical advantages of the plan are maximized.

[0182] 9. Data Output: Generate detailed optimization decision reports, including well location selection, risk assessment, production capacity forecast, economic benefits, and technical characteristic evaluation. Export the optimized well location plan and related data for relevant departments to use in decision-making.

[0183] This invention also proposes a drilling trajectory optimization device for complex fault-block thin oil layers, the principle of which is similar to the drilling trajectory optimization method for complex fault-block thin oil layers, and will not be described in detail here.

[0184] Figure 9 This is a schematic diagram of a drilling trajectory optimization device for complex fault-block thin oil layers provided in an embodiment of the present invention, as shown below. Figure 9 As shown, the drilling trajectory optimization device for complex fault-block thin oil layers may include:

[0185] The acquisition module 901 is used to acquire geological data of complex fault-block reservoirs and a three-dimensional geological model based on the geological data of complex fault-block reservoirs.

[0186] The identification module 902 is used to input geological data into a pre-trained identification model and output identification results; the identification results are the probability that each location in the three-dimensional geological model is a thin oil layer; the identification model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities;

[0187] The determination module 903 is used to determine the well location optimization target as the area whose identification results show that the probability of it being a thin oil layer is greater than the preset probability, which is determined not to be a fault or fold according to geological data and three-dimensional geological model, and whose pressure is lower than the preset pressure and whose collapse probability is lower than the preset collapse probability.

[0188] The assessment module 904 is used to assess the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model based on geological data, and generate assessment results.

[0189] The generation module 905 is used to generate the optimal drilling trajectory based on the well location optimization target, evaluation results, and preset trajectory parameters.

[0190] In one embodiment, the drilling trajectory optimization device for complex fault-block thin oil layers may further include: a training module, used for:

[0191] Obtain historical geological data;

[0192] Historical geological data are labeled based on whether the location corresponding to the historical geological data is a thin oil layer;

[0193] The deep learning model was trained using labeled historical geological data to obtain the recognition model.

[0194] In one embodiment, the drilling trajectory optimization device for complex fault-block thin oil reservoirs may further include: a drilling trajectory optimization module, used for:

[0195] Obtain real-time drilling data based on the well location, optimized target position, and optimal drilling trajectory;

[0196] The optimal drilling trajectory is adjusted based on real-time drilling data and preset trajectory parameters.

[0197] In one embodiment, the geological data includes one or any combination of seismic interpretation data, reservoir data, oil reservoir data, well location distribution data, and historical production data of existing well locations.

[0198] In one embodiment, the drilling trajectory optimization device for complex fault-block thin oil layers may further include: an optimal drilling implementation strategy determination module, used for:

[0199] Multiple drilling implementation strategies are determined based on well location optimization target position and optimal drilling trajectory;

[0200] The implementation costs, expected benefits, workload, safety risk information, resource utilization rate, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies are determined separately; the implementation costs include drilling costs and equipment costs; the expected benefits include return on investment and net present value;

[0201] Based on the implementation costs, expected benefits, workload, safety risk information, resource utilization, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies, the optimal drilling implementation strategy is determined and output to the designated terminal equipment.

[0202] In one embodiment, the acquisition module 901 is specifically used for:

[0203] A three-dimensional geological model was established based on seismic interpretation data, reservoir data, oil reservoir data, and well location distribution data.

[0204] The parameters of the three-dimensional geological model are adjusted using historical production data and reservoir data from existing well locations.

[0205] Compared with existing fracturing stimulation effect analysis techniques, this invention obtains geological data of complex fault-block reservoirs and establishes a three-dimensional geological model based on the geological data. The geological data is input into a pre-trained recognition model, which outputs the recognition result. The recognition result represents the probability that each location in the three-dimensional geological model is a thin oil layer. The recognition model is trained using historical geological data with labeled thin oil layer probabilities. The invention distinguishes between locations where the probability of a thin oil layer is greater than a preset probability and locations where the probability is not determined based on the geological data and the three-dimensional geological model. Faults or folds, areas with pressures lower than preset pressures and collapse probabilities lower than preset collapse probabilities are identified as well location optimization targets. Based on geological data, wellbore stability, high pressure, and leakage risks at each location in the 3D geological model are assessed, and assessment results are generated. Based on the well location optimization targets, assessment results, and preset trajectory parameters, the optimal drilling trajectory is generated. This fully considers the complex distribution characteristics and variable reservoir conditions of thin underground oil layers, effectively improving the efficiency of well location and drilling trajectory determination. The determined well locations and drilling trajectories can improve the drilling success rate and significantly improve the oilfield's production efficiency and output.

[0206] This invention provides an automatic well location optimization method and apparatus for complex fault-block thin oil layers. By comprehensively considering structural features, reservoir development, oil layer distribution, and existing well locations and production data, and utilizing computer deep learning algorithms, it accurately identifies and analyzes the distribution characteristics of underground thin oil layers, determines the potential target location of the target layer, continuously optimizes the drilling trajectory, and significantly improves the oilfield's production efficiency and output.

[0207] The method and apparatus of this invention, by comprehensively considering structural features, reservoir development, oil layer distribution, and existing well locations and production data, utilize deep learning algorithms for precise identification and analysis, effectively achieving automatic well location optimization and significantly improving oilfield production efficiency and output. Furthermore, the apparatus design of this invention takes into account ease of operation and cost-effectiveness, effectively improving the deployment efficiency of well location optimization, increasing drilling success rates, and possessing broad application prospects.

[0208] This invention also provides a computer device. Figure 10 This is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 1000 includes a memory 1010, a processor 1020, and a computer program 1030 stored in the memory 1010 and executable on the processor 1020. When the processor 1020 executes the computer program 1030, it implements the above-mentioned method for optimizing drilling trajectories in complex fault-block thin oil layers.

[0209] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing drilling trajectories in complex fault-block thin oil layers.

[0210] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for optimizing drilling trajectories in complex fault-block thin oil layers.

[0211] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0212] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0213] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0214] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0215] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing drilling trajectories in complex fault-block thin oil reservoirs, characterized in that, include: Obtain geological data of complex fault-block reservoirs and establish three-dimensional geological models based on the geological data of complex fault-block reservoirs; Geological data is input into a pre-trained recognition model, and the recognition result is output. The identification result is the probability that each location in the three-dimensional geological model is a thin oil layer; the identification model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities. The areas identified as having a higher probability of being thin oil layers than the preset probability, not being faults or folds based on geological data and three-dimensional geological models, and having pressures lower than the preset pressures and collapse probabilities lower than the preset collapse probabilities are identified as well location optimization targets. Based on geological data, the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model are assessed, and assessment results are generated. The optimal drilling trajectory is generated based on the well location optimization target, evaluation results, and preset trajectory parameters.

2. The method as described in claim 1, characterized in that, Also includes: Obtain historical geological data; Historical geological data are labeled based on whether the location corresponding to the historical geological data is a thin oil layer; The deep learning model was trained using labeled historical geological data to obtain the recognition model.

3. The method as described in claim 1, characterized in that, Also includes: Obtain real-time drilling data based on the well location, optimized target position, and optimal drilling trajectory; The optimal drilling trajectory is adjusted based on real-time drilling data and preset trajectory parameters.

4. The method as described in claim 1, characterized in that, The geological data includes one or any combination of seismic interpretation data, reservoir data, oil reservoir data, well location distribution data, and historical production data of existing well locations.

5. The method as described in claim 1, characterized in that, Also includes: Multiple drilling implementation strategies are determined based on well location optimization target position and optimal drilling trajectory; The implementation costs, expected benefits, workload, safety risk information, resource utilization rate, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies are determined separately; the implementation costs include drilling costs and equipment costs; the expected benefits include return on investment and net present value; Based on the implementation costs, expected benefits, workload, safety risk information, resource utilization, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies, the optimal drilling implementation strategy is determined and output to the designated terminal equipment.

6. The method as described in claim 1, characterized in that, Acquire geological data of complex fault-block reservoirs and establish three-dimensional geological models based on the geological data of complex fault-block reservoirs, including: A three-dimensional geological model was established based on seismic interpretation data, reservoir data, oil reservoir data, and well location distribution data. The parameters of the three-dimensional geological model are adjusted using historical production data and reservoir data from existing well locations.

7. A drilling trajectory optimization device for complex fault-block thin oil reservoirs, characterized in that, include: The acquisition module is used to acquire geological data of complex fault-block reservoirs and to build three-dimensional geological models based on the geological data of complex fault-block reservoirs. The recognition module is used to input geological data into a pre-trained recognition model and output the recognition results; The identification result is the probability that each location in the three-dimensional geological model is a thin oil layer; the identification model is obtained by training a deep learning model based on historical geological data with labeled thin oil layer probabilities. The determination module is used to identify areas where the probability of identification as a thin oil layer is greater than the preset probability, which are determined not to be faults or folds based on geological data and three-dimensional geological models, and which have pressures lower than the preset pressures and collapse probabilities lower than the preset collapse probabilities as well location optimization targets. The assessment module is used to assess the wellbore stability, high pressure, and leakage risk at each location in the three-dimensional geological model based on geological data, and generate assessment results. The generation module is used to generate the optimal drilling trajectory based on the well location optimization target, evaluation results, and preset trajectory parameters.

8. The apparatus as claimed in claim 7, characterized in that, Also includes: The training module is used for: Obtain historical geological data; Historical geological data are labeled based on whether the location corresponding to the historical geological data is a thin oil layer; The deep learning model was trained using labeled historical geological data to obtain the recognition model.

9. The apparatus as claimed in claim 7, characterized in that, Also includes: The drilling trajectory optimization module is used for: Obtain real-time drilling data based on the well location, optimized target position, and optimal drilling trajectory; The optimal drilling trajectory is adjusted based on real-time drilling data and preset trajectory parameters.

10. The apparatus as claimed in claim 7, characterized in that, The geological data includes one or any combination of seismic interpretation data, reservoir data, oil reservoir data, well location distribution data, and historical production data of existing well locations.

11. The apparatus as claimed in claim 7, characterized in that, Also includes: The optimal drilling implementation strategy determination module is used for: Multiple drilling implementation strategies are determined based on well location optimization target position and optimal drilling trajectory; The implementation costs, expected benefits, workload, safety risk information, resource utilization rate, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies are determined separately; the implementation costs include drilling costs and equipment costs; the expected benefits include return on investment and net present value; Based on the implementation costs, expected benefits, workload, safety risk information, resource utilization, energy consumption, success rate, failure rate, maintenance costs, oil and gas production rate, and resource recovery rate of multiple drilling implementation strategies, the optimal drilling implementation strategy is determined and output to the designated terminal equipment.

12. The apparatus as claimed in claim 7, characterized in that, The acquisition module is specifically used for: A three-dimensional geological model was established based on seismic interpretation data, reservoir data, oil reservoir data, and well location distribution data. The parameters of the three-dimensional geological model are adjusted using historical production data and reservoir data from existing well locations.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

15. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images