An intelligent drilling system for oil fields

Abstract

The present invention provides an intelligent oilfield drilling system, which relates to the technical field of oilfield drilling. The system includes a data monitoring module, a trajectory prediction module, a control optimization module, and an execution control module. Environmental parameters and operating parameters are collected; a theoretical wellbore trajectory is generated, and drilling trajectory prediction offset data is obtained to obtain a final predicted trajectory; a control parameter adjustment plan is generated and a drilling pressure-speed matching curve is adjusted. The present invention realizes comprehensive monitoring and intelligent management of the oilfield drilling process through the collaborative operation of multiple modules. Not only does it improve efficiency, but it also reduces equipment wear and failure rate, and extends the service life of the equipment. By improving the accuracy and efficiency of drilling, reducing the occurrence of accidents and the frequency of equipment failures, the drilling cost is optimized as a whole, the drilling cycle is effectively shortened, and the single well production is increased, thereby bringing significant economic benefits.

Description

Technical Field

[0001] The present invention relates to the technical field of oilfield drilling, and in particular to an oilfield intelligent drilling system. Background Art

[0002] Oilfield drilling technology has undergone years of development, gradually transitioning from initial mechanical drilling to modern intelligent drilling. Current drilling methods rely heavily on numerical control technology and automated equipment, but they still have many limitations in practical application. Generally speaking, the traditional drilling process includes well design, drill bit selection, drilling execution, and wellbore stabilization. At each stage, operators often rely on experience and historical data to make decisions, resulting in insufficient information utilization. In the oilfield drilling industry, with the gradual depletion of resources and increasing extraction difficulties, traditional drilling methods face numerous challenges. These challenges primarily manifest in drilling accuracy, efficiency, safety, and real-time adaptability. Traditional drilling techniques often rely on experience and manual judgment, leading to frequent deviations and steering errors in dynamic environments, resulting in reduced drilling efficiency and increased safety risks.

[0003] Many current drilling systems rely on static models and qualitative analysis, resulting in significant discrepancies between theoretical and actual wellbore trajectories. Due to a lack of real-time monitoring and predictive capabilities, traditional drilling is prone to wellbore deviations. This is not only time-consuming and labor-intensive, but can also lead to equipment damage and safety incidents, resulting in additional repair and downtime costs. Summary of the Invention

[0004] The present invention provides an oilfield intelligent drilling system to solve the defects in the prior art.

[0005] The present invention provides an oilfield intelligent drilling system, comprising:

[0006] The data monitoring module is used to collect real-time downhole environmental parameters of the oil field and equipment operating parameters for remote control drilling.

[0007] The trajectory prediction module is used to construct a physical model based on finite element analysis of drill string dynamics to generate a theoretical wellbore trajectory, build a prediction model based on long-short-term memory network to obtain drilling trajectory prediction offset data, and combine the theoretical wellbore trajectory and predicted offset data to obtain the final predicted trajectory.

[0008] The control optimization module is used to generate a control parameter adjustment plan based on the final predicted trajectory.

[0009] The execution control module is used to execute the control parameter adjustment plan using the PID control algorithm and adjust the drilling pressure-speed matching curve by correcting the steering tool face angle in real time.

[0010] According to the present invention, an intelligent oilfield drilling system comprises a data monitoring module comprising a multi-source sensing unit, a data transmission unit, and a data preprocessing unit. The multi-source sensing unit is used to collect downhole environmental parameters in real time and simultaneously acquire drilling equipment operating parameters. Downhole environmental parameters include temperature, pressure, gamma value, and formation resistivity, while equipment operating parameters include drilling pressure, rotational speed, torque, and mud displacement. The data transmission unit is compatible with multiple communication media and enables data transmission between downhole environmental parameters and equipment operating parameters. The data preprocessing unit is used to preprocess the downhole environmental parameters and equipment operating parameters to obtain preprocessed environmental data and preprocessed operating data.

[0011] According to an oilfield intelligent drilling system provided by the present invention, the process of pre-processing downhole environmental parameters and equipment operating parameters includes:

[0012] Filter underground environmental parameters and equipment operating parameters to suppress high-frequency noise.

[0013] The synchronization technology based on the drilling depth counter is used to align the downhole environmental parameters and equipment operating parameters in time and space to generate a time-space synchronized multidimensional data set.

[0014] Wavelet transform and principal component analysis are used to extract features and reduce dimensionality of multidimensional data sets to obtain feature vector matrices.

[0015] Z-score standardization is used to standardize each parameter column in the eigenvector matrix to obtain preprocessing environment data and preprocessing operation data.

[0016] According to the present invention, an intelligent oilfield drilling system comprises a trajectory prediction module comprising a reference trajectory generation unit, an offset prediction unit, and a risk assessment unit. The reference trajectory generation unit is used to construct a three-dimensional drill string dynamics model based on ABAQUS, input preprocessed operational data, and output a theoretical wellbore trajectory. The offset prediction unit is used to construct a prediction model based on a long-short-term memory network, input preprocessed environmental data and real-time trajectory data, and output predicted offset data for the drilling trajectory, the predicted offset data including a predicted offset probability and a predicted offset distance. The risk assessment unit is used to combine the theoretical wellbore trajectory and the predicted offset data using a fusion algorithm to obtain a final predicted trajectory, and to quantify the offset risk level of the final predicted trajectory using Monte Carlo simulation.

[0017] According to an oilfield intelligent drilling system provided by the present invention, the process of outputting a theoretical wellbore trajectory includes:

[0018] Define geometric parameters, including drill string length, diameter, and material properties.

[0019] According to the geometric parameters, ABAQUS is used to establish a physical model of the three-dimensional drill string, and the geometric parameters are matched for each part in the physical model.

[0020] Boundary conditions and loads are applied to the physical model. The boundary conditions include the fixed conditions and contact conditions of the drill string, and the loads include bit pressure and torque.

[0021] Select a nonlinear solver in the physical model and set the solution parameters based on the time step and solution accuracy.

[0022] Start the solver to simulate the dynamic behavior of the drill string and obtain the theoretical wellbore trajectory.

[0023] According to an oilfield intelligent drilling system provided by the present invention, the process of constructing a prediction model based on a long short-term memory network includes:

[0024] Collect historical data of the oilfield drilling process, including historical environment data, historical trajectory data and historical offset data.

[0025] Normalize the historical data and set the time step to construct the normalized data into a time series format.

[0026] Build the basic model of long short-term memory network and define the long short-term memory network structure, including input layer, LSTM layer and output layer.

[0027] The current moment environmental data and current moment trajectory data in the historical data are used as input, and the next moment offset data is used as output. The basic model is trained, and the model parameters that meet the preset accuracy are retained to obtain the prediction model.

[0028] According to the present invention, a control optimization module of an intelligent oilfield drilling system includes a deviation data analysis unit and a control strategy generation unit. The deviation data analysis unit is used to analyze the final predicted trajectory using statistical analysis methods to obtain the deviation pattern and deviation trend of the drilling trajectory. The control strategy generation unit is used to generate a control parameter adjustment plan based on the deviation pattern and deviation trend, and optimize the control parameter adjustment plan using a particle swarm algorithm.

[0029] According to an oilfield intelligent drilling system provided by the present invention, the process of analyzing the final predicted trajectory using a statistical analysis method includes:

[0030] Collect historical trajectories, including historical baseline trajectories and historical offsets.

[0031] Data smoothing technology is used to process historical trajectories and remove invalid values ​​and noise.

[0032] Statistical history offset overall characteristics, including the average, standard deviation, maximum and minimum values.

[0033] Plot the frequency distribution of historical offsets based on population characteristics.

[0034] Hierarchical clustering method is used to classify historical offsets and obtain offset patterns, which include normal offset, abnormal offset and periodic offset.

[0035] According to the frequency distribution diagram, an ARIMA-based offset trend model is constructed, and the offset trend is obtained by analyzing the trend of offset changes over time through time series analysis.

[0036] According to an oilfield intelligent drilling system provided by the present invention, the process of optimizing the control parameter adjustment scheme using the particle swarm algorithm includes:

[0037] It is defined that each particle represents a possible combination of control parameters, including bit weight, rotation speed and angle.

[0038] Randomly generate a set of particle positions and velocities, where the position represents the control parameter combination and the velocity represents the adjustment direction of the control parameter combination.

[0039] For each particle, the fitness is evaluated according to the objective function, which represents the cost function that minimizes the offset.

[0040] Update the speed and position of each particle within the preset control parameter range until the preset fitness value is met.

[0041] The position and velocity of the particle that meets the preset fitness value are output, and the corresponding control parameter combination and adjustment direction are used as the control parameter adjustment scheme.

[0042] According to the present invention, an intelligent oilfield drilling system comprises an execution control module comprising a solution execution unit, a feedback detection unit, and a decision adjustment unit. The solution execution unit is configured to execute a control parameter adjustment solution using a PID control algorithm, adjusting equipment operating parameters in real time. The feedback monitoring unit is configured to collect real-time adjusted equipment operating data. The decision adjustment unit is configured to dynamically adjust the control parameter adjustment solution based on equipment operating data and real-time downhole environmental data.

[0043] The intelligent oilfield drilling system provided by this invention achieves comprehensive monitoring of the drilling process by collecting downhole environmental parameters and equipment operating status in real time. This system not only instantly acquires critical data but also promptly identifies potential risks, such as sudden changes in downhole pressure and abnormal temperatures, thereby significantly reducing the risk of accidents. Combining finite element analysis of drill string dynamics with a long-short-term memory network model, it accurately predicts drilling trajectory deviations. This enables operators to proactively respond, ensuring the drilling trajectory remains within a safe and predetermined range, thereby reducing drilling accidents caused by deviations and improving overall safety. The theoretical wellbore trajectory is combined with real-time predicted deviation data to generate the final predicted trajectory. This allows for the generation of more precise control parameter adjustment plans. This scientific, data-based optimization method significantly increases drilling speed and reduces drilling costs. Through real-time adjustments using intelligent algorithms, the system can quickly and effectively respond to different situations, ensuring the stability and smoothness of the drilling process. This not only improves efficiency but also reduces equipment wear and failure rates, extending its service life. By improving drilling accuracy and efficiency, reducing accidents and equipment failure frequency, the overall drilling cost is optimized, the drilling cycle is effectively shortened, and the single well production is increased, thus bringing significant economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 This is a schematic structural diagram of an oilfield intelligent drilling system provided by an embodiment of the present invention;

[0046] Figure 2 is a flow chart for obtaining a theoretical wellbore trajectory in an embodiment of the present invention;

[0047] Figure 3 4 is a flow chart of performing statistical analysis on the final predicted trajectory in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0049] The following combination Figure 1-Figure 3 An intelligent oilfield drilling system according to the present invention is described.

[0050] Figure 1 The diagram is a structural diagram of an intelligent oilfield drilling system provided by an embodiment of the present invention.

[0051] like Figure 1 As shown, an embodiment of the present invention provides an oilfield intelligent drilling system, which includes a data monitoring module, a trajectory prediction module, a control optimization module and an execution control module.

[0052] The data monitoring module is used to collect real-time downhole environmental parameters of the oil field and equipment operating parameters for remote control drilling.

[0053] The data monitoring module includes a multi-source sensing unit, a data transmission unit, and a data preprocessing unit. The multi-source sensing unit is used to collect downhole environmental parameters in real time and simultaneously obtain drilling equipment operating parameters. Downhole environmental parameters include temperature, pressure, gamma value, and formation resistivity. Equipment operating parameters include drilling pressure, rotational speed, torque, and mud displacement. The data transmission unit is compatible with multiple communication media and enables data transmission between downhole environmental parameters and equipment operating parameters. The data preprocessing unit is used to preprocess the downhole environmental parameters and equipment operating parameters to obtain preprocessed environmental data and preprocessed operating data.

[0054] Temperature sensors are installed at key locations along the drill string to monitor downhole temperature changes in real time. High-voltage voltage sensors are used to ensure accurate downhole pressure measurement in high-pressure environments. Gamma-ray detectors monitor the radioactive components of the formation, supporting formation characterization. Adaptive resistivity sensors measure the resistivity of the formation through the flow of current to assess fluid saturation.

[0055] A strain gauge sensor, connected between the drill bit and the drill string, reports the applied weight on bit in real time. A rotary encoder monitors the rig's rotational speed in real time to ensure consistency with the current drilling plan. A DC torque sensor records torque feedback from the drill string to assess energy efficiency and wear during drilling. A flow meter measures mud flow to ensure stable mud circulation and prevent blowouts.

[0056] All sensors convert analog signals into digital signals through A / D converters, and use industrial controllers to synchronously collect various parameters to achieve the integration of timely data.

[0057] The process of preprocessing downhole environmental parameters and equipment operating parameters includes:

[0058] Algorithms are used to filter noise from the collected data, identifying and removing measurements that are outside a reasonable range or have anomalies, such as data fluctuations caused by sensor failure or environmental interference.

[0059] Calibrate the output of various sensors to ensure that the data signals meet engineering standards and convert them into corresponding engineering units.

[0060] The synchronization technology based on the drilling depth counter is used to align the downhole environmental parameters and equipment operating parameters in time and space to generate a time-space synchronized multidimensional data set.

[0061] Wavelet transform and principal component analysis are used to extract features and reduce dimensionality of multidimensional data sets to obtain feature vector matrices.

[0062] Z-score standardization is used to standardize each parameter column in the eigenvector matrix to obtain preprocessing environment data and preprocessing operation data.

[0063] The trajectory prediction module is used to construct a physical model based on finite element analysis of drill string dynamics to generate a theoretical wellbore trajectory, build a prediction model based on long-short-term memory network to obtain drilling trajectory prediction offset data, and combine the theoretical wellbore trajectory and predicted offset data to obtain the final predicted trajectory.

[0064] The trajectory prediction module includes a baseline trajectory generation unit, an offset prediction unit, and a risk assessment unit. The baseline trajectory generation unit is used to construct a three-dimensional drill string dynamics model based on ABAQUS, taking preprocessed operational data as input and outputting a theoretical wellbore trajectory. The offset prediction unit is used to construct a prediction model based on a long-short-term memory network, taking preprocessed environmental data and real-time trajectory data as input and outputting predicted offset data for the drilling trajectory, including the predicted offset probability and predicted offset distance. The risk assessment unit uses a fusion algorithm to combine the theoretical wellbore trajectory and predicted offset data to obtain the final predicted trajectory. Monte Carlo simulation is then used to quantify the offset risk level of the final predicted trajectory.

[0065] Figure 2 This is a flow chart for obtaining theoretical wellbore trajectory in an embodiment of the present invention.

[0066] like Figure 2 As shown in Figure 2, the process of outputting theoretical wellbore trajectory includes:

[0067] Define geometric parameters, including drill string length, diameter, and material properties.

[0068] Based on the geometric parameters, a 3D physical model of the drill string was created using ABAQUS, with geometric parameters assigned to each component within the physical model. ABAQUS software was used to perform geometric modeling of the 3D model, creating the geometry of the drill string, including the drill bit, drill string, and wellbore wall. Material properties for the drill string and wellbore wall, including density, elastic modulus, and Poisson's ratio, were input to ensure the model accurately reflected the mechanical properties of the materials.

[0069] Boundary conditions and loads are applied to the physical model. The boundary conditions include the fixed conditions and contact conditions of the drill string, and the loads include bit pressure and torque.

[0070] Select a nonlinear solver in the physical model and set the solution parameters based on the time step and solution accuracy.

[0071] The solver is launched to simulate the dynamic behavior of the drill string and obtain the theoretical wellbore trajectory. An ABAQUS finite element simulation is run, using either explicit dynamic analysis or implicit static analysis methods to calculate the drill string's kinematic characteristics and deformation during drilling. Numerical simulations are used to determine the drill string's deformation and stress field distribution, which are then used to calculate the corresponding theoretical wellbore trajectory. After the model is run, the coordinate data for the theoretical wellbore trajectory is output, including information such as wellbore position and inclination angle.

[0072] The process of building a prediction model based on LSTM networks includes:

[0073] Collect historical data of the oilfield drilling process, including historical environment data, historical trajectory data and historical offset data.

[0074] Normalize the historical data and set the time step to construct the normalized data into a time series format.

[0075] Build a basic LSTM network model and define its structure, including an input layer, an LSTM layer, and an output layer. The input layer sets input nodes based on the number of features in the collected data. The LSTM layer adds multiple LSTM units to increase the model's learning capabilities and process time series information. The output layer is set as a fully connected layer, outputting the predicted offset probability and predicted offset distance.

[0076] The current moment environmental data and current moment trajectory data in the historical data are used as input, and the next moment offset data is used as output. The basic model is trained, and the model parameters that meet the preset accuracy are retained to obtain the prediction model.

[0077] The model is trained using historical data, using mean squared error as the loss function and applying the Adam optimization algorithm to adjust model weights. Model performance is evaluated and the training process is adjusted using early stopping to avoid overfitting.

[0078] The trained prediction model is used to process the new input data, output the predicted deviation probability and predicted deviation distance, and quantify the potential deviation of the drilling trajectory.

[0079] The risk assessment unit uses a fusion algorithm to combine the theoretical wellbore trajectory and predicted deviation data to obtain the final predicted trajectory and quantify its deviation risk level.

[0080] Fusion algorithms, such as weighted averaging or Bayesian inference, combine theoretical wellbore trajectories with offset prediction data to generate the final predicted trajectory. By setting weights, the relative importance of the theoretical trajectory and the predicted results is adjusted to better suit the current drilling situation.

[0081] Monte Carlo simulation is used to assess the risk of the final predicted trajectory. By randomly sampling the excursion probability, possible excursion scenarios are repeatedly simulated.

[0082] Based on the simulation results, the probability distribution of deviations from the planned trajectory is calculated to assess the degree of risk. The risk level can be quantified into different levels such as low, medium, and high, and a risk report can be generated.

[0083] The control optimization module is used to generate a control parameter adjustment plan based on the final predicted trajectory.

[0084] The control optimization module includes a deviation data analysis unit and a control strategy generation unit. The deviation data analysis unit uses statistical analysis methods to analyze the final predicted trajectory to obtain the deviation pattern and deviation trend of the drilling trajectory. The control strategy generation unit generates a control parameter adjustment plan based on the deviation pattern and deviation trend and optimizes the control parameter adjustment plan using a particle swarm algorithm.

[0085] Figure 3 4 is a flow chart of performing statistical analysis on the final predicted trajectory in an embodiment of the present invention.

[0086] like Figure 3 As shown in Figure 2, the process of analyzing the final predicted trajectory using statistical analysis methods includes:

[0087] Collect historical trajectories, including historical baseline trajectories and historical offsets.

[0088] Data smoothing technology is used to process historical trajectories and remove invalid values ​​and noise.

[0089] Statistical history offset overall characteristics, including the average, standard deviation, maximum and minimum values.

[0090] Plot the frequency distribution of historical offsets based on population characteristics.

[0091] Hierarchical clustering method is used to classify historical offsets and obtain offset patterns, which include normal offset, abnormal offset and periodic offset.

[0092] According to the frequency distribution diagram, an ARIMA-based offset trend model is constructed, and the offset trend is obtained by analyzing the trend of offset changes over time through time series analysis.

[0093] Based on the deviation pattern and trend, determine which control parameters need to be adjusted, such as weight on bit, rotational speed, torque, and mud displacement. Set preliminary control parameter adjustment rules. For example, if the prediction model indicates that excessive weight on bit may cause deviation, the weight on bit should be reduced.

[0094] Based on the analysis results, develop a plan for adjusting control parameters. Each adjustment should be quantitatively analyzed based on the impact of different drift patterns. For example, the drift trends observed over a period of time should be reflected in the adjustment strategy. If increased WOB causes drift, reduce WOB. If low RPM is associated with frequent drift, increase RPM appropriately.

[0095] The process of optimizing the control parameter adjustment scheme using the particle swarm algorithm includes:

[0096] It is defined that each particle represents a possible combination of control parameters, including bit weight, rotation speed and angle.

[0097] Randomly generate a set of particle positions and velocities, where the position represents the control parameter combination and the velocity represents the adjustment direction of the control parameter combination.

[0098] For each particle, the fitness is evaluated according to the objective function, which represents the cost function that minimizes the offset.

[0099] Update the speed and position of each particle within the preset control parameter range until the preset fitness value is met.

[0100] The position and velocity of the particle that meets the preset fitness value are output, and the corresponding control parameter combination and adjustment direction are used as the control parameter adjustment scheme.

[0101] The execution control module is used to implement the control parameter adjustment plan using the PID control algorithm and adjust the drilling pressure-speed matching curve by correcting the steering tool face angle in real time.

[0102] The execution control module includes a plan execution unit, a feedback detection unit, and a decision adjustment unit. The plan execution unit uses a PID control algorithm to execute the control parameter adjustment plan and adjust equipment operating parameters in real time. The feedback monitoring unit collects real-time equipment operating data after adjustment. The decision adjustment unit dynamically adjusts the control parameter adjustment plan based on equipment operating data and real-time downhole environmental data.

[0103] The PID control algorithm consists of three parts: proportional, integral and differential, which are used for the immediate response of control parameters, correction of past errors of the system and prediction of future change trends.

[0104] According to the control parameter adjustment plan provided by the control strategy generation unit, set the target drilling pressure, speed and torque parameters.

[0105] During each control cycle, real-time data on equipment operation, such as drilling pressure and rotational speed, is collected and the error between the current output and the set value is calculated. Based on this error, a PID control signal is generated.

[0106] Adjust the equipment's drive control signals in real time to adjust the drilling pressure and speed to ensure they approach the set values ​​in real time. The adjusted control signals are sent to the drilling equipment via the actuator or control interface, and parameter adjustments are executed.

[0107] Through multi-source sensing units, key operating parameters of the equipment during the drilling process, such as current drilling pressure, speed, torque, mud displacement, temperature, etc., are monitored and captured in real time.

[0108] The collected feedback data is sent to the monitoring system in real time through the data transmission unit.

[0109] Establish a real-time monitoring control panel to centrally display and record the operating data of various equipment, making it convenient for operators to observe, monitor and make real-time analysis.

[0110] Store real-time feedback data in a database for subsequent inspection, analysis, and data mining. Set timestamps to ensure that all data is traceable.

[0111] Use machine learning algorithms to assess equipment conditions, monitor feedback data, and combine it with environmental parameters such as temperature and pressure for real-time analysis.

[0112] Evaluate the system's responsiveness when monitored equipment parameters, such as WOB and RPM, consistently deviate from their design targets. For example, if WOB remains above target for a prolonged period, reassess the control strategy and make adjustments.

[0113] If the error between the operating data collected by the feedback monitoring unit and the target value continues to exceed a preset threshold, the decision-making and adjustment unit will invoke a previously set control parameter adjustment plan and make corrections. For example, increasing the Kp of the PID control to improve the system's responsiveness to errors. The new control parameters are then sent to the plan execution unit to adjust the drilling equipment's operating parameters, forming a closed-loop control process.

[0114] In summary, this embodiment provides an intelligent oilfield drilling system that enables comprehensive monitoring of the drilling process through real-time acquisition of downhole environmental parameters and equipment operating status. This system not only instantly captures critical data but also promptly identifies potential risks, such as sudden changes in downhole pressure and abnormal temperatures, significantly reducing the risk of accidents. By combining finite element analysis of drill string dynamics with a long-short-term memory network model, it accurately predicts drilling trajectory deviations. This enables operators to proactively respond and ensure the drilling trajectory remains within a safe and predetermined range, thereby reducing drilling accidents caused by deviations and improving overall safety. By combining the theoretical wellbore trajectory with real-time predicted deviation data, a final predicted trajectory is generated. This allows for more precise control parameter adjustment plans. This scientific, data-driven optimization method significantly increases drilling speed and reduces drilling costs. Through real-time adjustments using intelligent algorithms, the system can quickly and effectively respond to various situations, ensuring a stable and smooth drilling process. This not only improves efficiency but also reduces equipment wear and failure rates, extending equipment life. By improving drilling accuracy and efficiency, reducing accidents and equipment failure frequency, the overall drilling cost is optimized, the drilling cycle is effectively shortened, and the single well production is increased, thus bringing significant economic benefits.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0116] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An oilfield intelligent drilling system, characterized in that: include: Data monitoring module, used to collect real-time downhole environmental parameters of the oil field and equipment operating parameters for remote control drilling; A trajectory prediction module is used to construct a physical model based on finite element analysis of drill string dynamics to generate a theoretical wellbore trajectory, construct a prediction model based on a long short-term memory network to obtain drilling trajectory prediction offset data, and combine the theoretical wellbore trajectory and the predicted offset data to obtain a final predicted trajectory; The process of outputting theoretical wellbore trajectory includes: defining geometric parameters, including drill string length, diameter, and material properties; According to the geometric parameters, a physical model of the three-dimensional drill string is established using ABAQUS, and geometric parameters are matched for each part in the physical model; Applying boundary conditions and loads to the physical model, wherein the boundary conditions include a fixed condition and a contact condition of the drill string, and the loads include weight on bit and torque; Selecting a nonlinear solver in the physical model and setting solution parameters according to a time step and solution accuracy; Start the solver to simulate the dynamic behavior of the drill string and obtain the theoretical wellbore trajectory; The process of building a prediction model based on LSTM networks includes: Collecting historical data of the oilfield drilling process, wherein the historical data includes historical environmental data, historical trajectory data, and historical offset data; Normalizing the historical data and setting a time step to construct the normalized data into a time series format; Build the basic model of the long short-term memory network and define the long short-term memory network structure, including the input layer, LSTM layer and output layer; The current moment environment data and the current moment trajectory data in the historical data are used as input, and the next moment offset data is used as output, the basic model is trained, and the model parameters that meet the preset accuracy are retained to obtain a prediction model; a control optimization module, configured to generate a control parameter adjustment scheme based on the final predicted trajectory; The execution control module is used to execute the control parameter adjustment scheme by adopting a PID control algorithm, and adjust the bit pressure-speed matching curve by correcting the steering tool face angle in real time.

2. The intelligent oilfield drilling system according to claim 1, characterized in that: The data monitoring module includes a multi-source sensing unit, a data transmission unit and a data preprocessing unit; the multi-source sensing unit is used to collect downhole environmental parameters in real time and synchronously obtain drilling equipment operating parameters, the downhole environmental parameters include temperature, pressure, gamma value and formation resistivity, and the equipment operating parameters include drilling pressure, rotation speed, torque and mud displacement; the data transmission unit is used to be compatible with multiple communication media to realize data transmission between the downhole environmental parameters and the equipment operating parameters; the data preprocessing unit is used to preprocess the downhole environmental parameters and the equipment operating parameters to obtain preprocessed environmental data and preprocessed operating data.

3. The intelligent oilfield drilling system according to claim 2, characterized in that: The process of preprocessing the downhole environmental parameters and the equipment operating parameters includes: Filtering the downhole environmental parameters and the equipment operating parameters to suppress high-frequency noise; Using a synchronization technology based on a drilling depth counter to perform spatiotemporal alignment on the downhole environmental parameters and the equipment operating parameters to generate a spatiotemporal synchronized multidimensional dataset; Performing feature extraction and dimensionality reduction processing on the multidimensional data set using wavelet transform and principal component analysis to obtain a feature vector matrix; Each parameter column in the eigenvector matrix is ​​standardized using Z-score standardization to obtain preprocessing environment data and preprocessing operation data.

4. The intelligent oilfield drilling system according to claim 3, characterized in that: The trajectory prediction module includes a reference trajectory generation unit, an offset prediction unit and a risk assessment unit; the reference trajectory generation unit is used to construct a three-dimensional drill string dynamics model based on ABAQUS, input the preprocessed operation data, and output a theoretical wellbore trajectory; the offset prediction unit is used to construct a prediction model based on a long short-term memory network, input the preprocessed environmental data and real-time trajectory data, and output predicted offset data of the drilling trajectory, wherein the predicted offset data includes a predicted offset probability and a predicted offset distance; the risk assessment unit is used to use a fusion algorithm to combine the theoretical wellbore trajectory and the predicted offset data to obtain a final predicted trajectory, and use Monte Carlo simulation to quantify the offset risk level of the final predicted trajectory.

5. The intelligent oilfield drilling system according to claim 1, characterized in that: The control optimization module includes an offset data analysis unit and a control strategy generation unit; the offset data analysis unit is used to analyze the final predicted trajectory using a statistical analysis method to obtain the offset pattern and offset trend of the drilling trajectory; the control strategy generation unit is used to generate a control parameter adjustment plan based on the offset pattern and the offset trend, and use a particle swarm algorithm to optimize the control parameter adjustment plan.

6. The intelligent oilfield drilling system according to claim 5, characterized in that: The process of analyzing the final predicted trajectory using a statistical analysis method includes: Collecting historical trajectories, wherein the historical trajectories include historical reference trajectories and historical offsets; Using data smoothing technology to process the historical trajectory and remove invalid values ​​and noise; Counting overall characteristics of the historical offsets, where the overall characteristics include an average value, a standard deviation, a maximum value, and a minimum value; Draw a frequency distribution diagram of the historical offset according to the overall characteristics; Using a hierarchical clustering method to classify the historical offsets to obtain an offset pattern, wherein the offset pattern includes a normal offset, an abnormal offset, and a periodic offset; According to the frequency distribution diagram, an ARIMA-based offset trend model is constructed, and the offset trend is obtained by analyzing the trend of the offset changing over time through time series analysis.

7. The intelligent oilfield drilling system according to claim 5, characterized in that: The process of optimizing the control parameter adjustment scheme using the particle swarm algorithm includes: Each particle is defined to represent a possible combination of control parameters, where the control parameters include weight on bit, rotation speed, and angle; Randomly generate a set of particle positions and velocities, where the positions represent the control parameter combination and the velocities represent the adjustment direction of the control parameter combination; For each particle, fitness evaluation is performed according to an objective function, where the objective function represents a cost function that minimizes the offset; Update the speed and position of each particle within the preset control parameter range until the preset fitness value is met; The position and velocity of the particle that meets the preset fitness value are output, and the corresponding control parameter combination and adjustment direction are used as the control parameter adjustment scheme.

8. The intelligent oilfield drilling system according to claim 1, characterized in that: The execution control module includes a scheme execution unit, a feedback monitoring unit and a decision adjustment unit; the scheme execution unit is used to use the PID control algorithm to execute the control parameter adjustment scheme and adjust the equipment operating parameters in real time; the feedback monitoring unit is used to collect the adjusted equipment operating data in real time; the decision adjustment unit is used to dynamically adjust the control parameter adjustment scheme based on the equipment operating data and real-time downhole environmental data.

Images