Kinetic analysis system of rotary steerable drilling system

Abstract

The invention relates to the technical field of rotary steerable drilling system dynamics analysis and control, in particular to a rotary steerable drilling system dynamics analysis system which comprises a data acquisition module used for acquiring ground engineering parameters and underground dynamic parameters in real time and intercepting drilling parameter adjusting instructions; the digital twin modeling module is used for outputting a complete state vector of a digital twin model; the noise prediction module is used for generating a control source noise signal; the signal reconstruction module is used for executing self-adaptive hedging processing on the original mixed signal so as to reconstruct a pure geological signal; the cooperative control module is used for predicting the vibration risk caused by the change of the front stratum and generating an optimal control instruction for actively avoiding the vibration risk; the occurrence probability of malignant vibration is remarkably reduced, the drilling efficiency is improved, and the service life of a drilling tool is prolonged.

Description

Technical Field

[0001] This invention relates to the field of dynamic analysis and control technology for rotary steerable drilling systems, specifically a dynamic analysis system for rotary steerable drilling systems. Background Technology

[0002] In modern rotary steerable drilling engineering, downhole measurement while drilling (MWD) systems are the core technology for achieving precise geological guidance and ensuring operational safety. In order to effectively control the drilling process, the system needs to acquire downhole dynamic parameters that reflect formation characteristics in real time. However, in actual operations, drilling parameter adjustment commands issued from the surface, such as speeding up or pressurizing, will generate and propagate vibrations in the drill string system, forming a definite control source noise. This noise is superimposed on the target geological signal, forming a heavily contaminated original mixed signal. Existing technologies mostly employ passive signal filtering or vibration suppression strategies. These methods process signals after they have been contaminated, making it difficult to effectively remove control source noise that overlaps with the geological signal frequency band. This results in insufficient accuracy and reliability of geological guidance. Furthermore, due to the inability to obtain pure geological signals, the system struggles to accurately predict changes in the formation ahead, thus failing to proactively avoid the risks of severe vibrations such as stick-slip and shock caused by abrupt formation changes. The control strategy remains at the passive response level, contributing little to improving drilling efficiency and safety. Therefore, establishing a dynamic analysis and control method that can proactively predict and eliminate control source noise, reconstruct high-fidelity pure geological signals from a strong noise background, and thereby upgrade the control strategy from passive vibration suppression to proactive risk avoidance is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0003] To solve the above-mentioned technical problems, the present invention provides a dynamic analysis system for rotary steerable drilling systems. Specifically, the technical solution of the present invention includes: The data acquisition module is used to collect surface engineering parameters and downhole dynamic parameters in real time, and to intercept drilling parameter adjustment commands. The digital twin modeling module is used to construct and correct the dynamic digital twin model of the drill string system in real time based on surface engineering parameters and downhole dynamic parameters, and then output the complete state vector of the digital twin model. The noise prediction module is used to generate control source noise signals by calling the digital twin model to perform forward extrapolation based on drilling parameter adjustment commands and complete state vectors. The signal reconstruction module is used to obtain the original mixed signal from the downhole dynamic parameters and perform adaptive hedging processing on the original mixed signal based on the control source noise signal to reconstruct a pure geological signal. The collaborative control module is used to predict the vibration risk caused by changes in the strata ahead based on pure geological signals, and generate optimal control commands for actively avoiding vibration risks.

[0004] Preferably, the digital twin modeling module is specifically used for: Based on the preset geometric configuration, material properties and drilling fluid performance parameters of the drill string assembly, a physical dynamic model with state-space equations as its core is initialized and constructed. Using a Kalman filter, real-time acquired surface engineering parameters and downhole dynamic parameters are used as inputs. By minimizing the error between the model's predicted output and the measured values, the state of the digital twin model is continuously corrected and updated.

[0005] Preferably, the noise prediction module is specifically used for: The intercepted drilling parameter adjustment command is used as input, and the complete state vector of the digital twin model at the current moment is called as the initial condition; By using the transfer function built into the digital twin model, the vibration waveform caused by the drilling parameter adjustment command at the downhole sensor position is calculated, and the vibration waveform is defined as the control source noise signal.

[0006] Preferably, the signal reconstruction module is specifically used for: By using a clock synchronization mechanism, the control source noise signal is aligned with the original mixed signal on the time axis; By using an adaptive hedging algorithm, the weighted components of the aligned control source noise signal are subtracted from the original mixed signal to obtain a pure geological signal.

[0007] Preferably, the adaptive hedging algorithm is the least mean square algorithm, and the signal reconstruction module is also used for: Based on the principle of minimizing the output signal energy, the adaptive offset coefficient used to weight the control source noise signal is updated in real time using the iterative rules of the least mean square algorithm.

[0008] Preferably, the collaborative control module is specifically used for: Pure geological signals are input into a pre-defined lithology-mechanics conversion model to determine the predicted bottom hole torque sequence; The predicted bottom-hole torque sequence is used as the future load and input into the digital twin model for forward-looking simulation to obtain predictions of future dynamic response. The vibration risk index is calculated based on future dynamic response predictions. Based on the vibration risk index, the optimal control command is obtained by solving the problem through a multi-objective optimizer.

[0009] Preferably, the lithology-mechanics conversion model is a neural network model trained based on machine learning, which is used to predict the drillability or rock strength equivalent parameters of the strata to be encountered by drilling by identifying feature patterns in pure geological signals, so as to output a predicted bottom hole torque sequence.

[0010] Preferably, the multi-objective optimizer takes minimizing the future vibration risk index and maximizing drilling efficiency as optimization objectives, solves for a set of drilling parameter adjustment commands, and defines the commands as the optimal control commands.

[0011] Compared with the prior art, the present invention has the following beneficial effects: 1. This system constructs a dynamic digital twin model of the drill string system to proactively predict the deterministic noise waveform generated downhole by surface control commands. Based on this, the system actively offsets the noise from the original mixed signal to reconstruct a high-fidelity pure geological signal, which greatly improves the accuracy and reliability of geological guidance. 2. This system utilizes reconstructed pure geological signals to predict the lithological change trend of the strata ahead, and combines it with a digital twin model for forward-looking simulation. This enables the system to predict in advance the risk of severe vibrations such as stick-slip and shock caused by strata changes, realizing an upgrade in control strategy from passively suppressing vibrations to actively avoiding risks. 3. This system establishes an intelligent closed-loop control link from geological signal analysis and vibration risk prediction to the generation of optimal control commands. Through a multi-objective optimizer, the system seeks the best balance between avoiding vibration risks and improving drilling efficiency, thereby significantly reducing the probability of severe vibrations, improving drilling efficiency and extending drill string life. 4. This system combines physical mechanism-based modeling with Kalman filter correction based on real-time data to construct a high-fidelity digital twin model that combines mechanism accuracy with real-time adaptability. This model can accurately reproduce the real dynamic behavior of the downhole drill string, providing a core foundation for accurate noise prediction and reliable vibration simulation. Attached Figure Description

[0012] The present invention will be further explained below with reference to the accompanying drawings and embodiments: Figure 1 This is a structural diagram of the system of the present invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0014] Example 1: Please see Figure 1 A dynamic analysis system for a rotary steerable drilling system, comprising: The data acquisition module is used to collect surface engineering parameters and downhole dynamic parameters in real time, and to intercept drilling parameter adjustment commands. The digital twin modeling module is used to construct and correct the dynamic digital twin model of the drill string system in real time based on surface engineering parameters and downhole dynamic parameters, and then output the complete state vector of the digital twin model. The noise prediction module is used to generate control source noise signals by calling the digital twin model to perform forward extrapolation based on drilling parameter adjustment commands and complete state vectors. The signal reconstruction module is used to obtain the original mixed signal from the downhole dynamic parameters and perform adaptive hedging processing on the original mixed signal based on the control source noise signal to reconstruct a pure geological signal. The collaborative control module is used to predict the vibration risk caused by changes in the strata ahead based on pure geological signals, and generate optimal control commands for actively avoiding vibration risks.

[0015] This embodiment provides a dynamic analysis system for a rotary steerable drilling system. In a specific implementation scenario, the system is deployed at a ground control center and includes a data acquisition module, a digital twin modeling module, a noise prediction module, a signal reconstruction module, and a collaborative control module. These modules work together to form a complete technical chain from data acquisition, model building, signal processing to closed-loop control. The purpose of the data acquisition module is to provide real-time and comprehensive data input for the entire analysis system. It continuously acquires the drive torque and speed of the drive motor through an interface with the drilling rig's surface control system, and obtains surface engineering parameters such as drilling pressure through sensors in the hydraulic system. These surface engineering parameters are macroscopic physical quantities that can be directly measured on the surface and reflect the operating status of the drilling equipment; their function is to serve as the main driving input for the digital twin model. This module receives and analyzes downhole dynamic parameters transmitted from the downhole Measurement While Drilling (MWD) system via a mud pulse telemetry decoding unit. A key function of this module is to monitor the control system's command bus in real time to intercept drilling parameter adjustment commands, such as speed-up or pressurization commands issued by operators or the automatic control system. This instruction is the direct source of subsequent noise prediction; The purpose of the digital twin modeling module is to build and maintain a virtual model that can accurately reproduce the dynamic behavior of the actual downhole drill string system. This module receives surface engineering parameters and downhole dynamic parameters from the data acquisition module, and builds and corrects the drill string system dynamics digital twin model based on this real-time data. The core of this model is a state-space expression that can calculate the angular displacement and angular velocity at any position on the drill string with millisecond-level time resolution, thereby outputting the complete state vector of the digital twin model. This state vector is a comprehensive description of the current dynamic state of the entire drill string system and is the basis for subsequent noise prediction and vibration simulation. The purpose of the noise prediction module is to transform passive noise response into proactive prediction, providing crucial prior information for subsequent signal cleanup. This module receives drilling parameter adjustment commands intercepted by the data acquisition module. And obtain the real-time complete state vector provided by the digital twin modeling module. It uses a digital twin model to perform forward simulation based on drilling parameter adjustment commands and a complete state vector, simulating how the control commands will propagate through the drill string system and ultimately generate vibrations at the downhole LWD sensor location. The simulation result is defined as a time-series signal, i.e., the control source noise signal. ; The purpose of the signal reconstruction module is to accurately reconstruct a clean signal reflecting true formation information from severely contaminated downhole measurement signals; this module obtains the original mixed signal from downhole dynamic parameters. This signal is a superposition of geological information and various types of noise; it receives the control source noise signal generated by the noise prediction module. Based on this predicted signal, adaptive hedging processing is performed on the original mixed signal; through an adaptive filter, from Subtract precisely The components were ultimately reconstructed to reveal pure geological signals. ; The purpose of the collaborative control module is to utilize the high-quality information processed by the front-end module to upgrade the control strategy from passively suppressing vibration to actively avoiding it; this module is based on the pure geological signals output by the signal reconstruction module. It predicts the vibration risk caused by changes in the geological strata ahead; it analyzes... The system uses a model to predict upcoming changes in formation hardness and simulates the potential for severe vibrations such as stick-slip and shock under current drilling parameters. The optimizer within the system calculates a set of optimal control parameters to proactively mitigate these risks and generates optimal control commands for actively avoiding vibration risks. The order was issued to the drilling rig for execution. In addition, the system also integrates a health monitoring module to evaluate the prediction error of the digital twin model and the quality of the input signal in real time. When the error exceeds the preset threshold or the sensor data is abnormal, the system will trigger an alarm and can choose to switch to a more conservative control mode or return control to the human to ensure the safety and robustness of the entire drilling operation. This embodiment constructs a closed-loop dynamic analysis and control system by organically combining the above modules. It can not only extract high-fidelity geological signals from strong noise backgrounds, greatly improving the accuracy and reliability of geological guidance, but also significantly reduce the probability of severe vibrations through forward-looking vibration risk prediction and active avoidance, thereby improving drilling efficiency, extending drill bit life, and ensuring operational safety. This system focuses on predicting and eliminating deterministic noise caused by ground control adjustments. For other noise sources with stronger randomness, further processing can be carried out through subsequent conventional filtering methods.

[0016] Example 2: The digital twin modeling module is specifically used for: Based on the preset geometric configuration, material properties and drilling fluid performance parameters of the drill string assembly, a physical dynamic model with state-space equations as its core is initialized and constructed. Using a Kalman filter, real-time acquired surface engineering parameters and downhole dynamic parameters are used as inputs. By minimizing the error between the model's predicted output and the measured values, the state of the digital twin model is continuously corrected and updated.

[0017] This embodiment is a specific implementation of the digital twin modeling module described in Embodiment 1; Before drilling operations begin, this digital twin modeling module performs an initialization process. Based on the preset geometric configuration, material properties, and drilling fluid performance parameters of the drill string assembly (BHA), it initializes and constructs a physical dynamics model centered on state-space equations. State-space equations are a modern control theory mathematical model used to describe the dynamic behavior of a physical system, and their form is as follows:

[0018]

[0019] Where the state vector The physical meaning of is the collection of angular displacements and angular velocities at each discrete node along the drill string, which is a complete description of the internal dynamics of the system; input vector The source is the data acquisition module, which includes the surface driving torque and the torque of the bottom hole drill bit-rock interaction based on drilling pressure and lithology estimation; the output vector This corresponds to physical quantities measurable by ground sensors, such as ground rotation speed, used for comparison with measured values; parameter matrix. The initial value is derived from the finite element analysis (FEA) calculation results based on the drill string assembly design drawings, representing the inherent physical characteristics of the system; During drilling, to cope with the constantly changing downhole conditions, this module employs a Kalman filter. It takes real-time acquired surface engineering parameters and downhole dynamic parameters as input, and continuously corrects and updates the state of the digital twin model by minimizing the error between the model's predicted output and the measured values. The Kalman filter is a highly efficient recursive state estimator capable of estimating the state of a dynamic system from a series of incomplete and noisy measurements. Its function is to convert the model's predicted output values, such as the predicted surface rotational speed, into the measured values. The state vector is compared with the actual measured value from the sensor, and the error between the two is used to adjust the state vector in real time. This ensures that the digital twin model remains highly consistent with the actual downhole drill string dynamics at all times; By employing this two-step method of offline initialization followed by online correction, the digital twin model constructed in this embodiment combines the mechanistic accuracy of the physical model with the real-time adaptability of the data-driven model. This allows it to more accurately reflect real working conditions, providing a high-fidelity foundation for subsequent noise prediction and vibration simulation, thereby improving the overall system's analytical accuracy.

[0020] Example 3: The noise prediction module is specifically used for: The intercepted drilling parameter adjustment command is used as input, and the complete state vector of the digital twin model at the current moment is called as the initial condition; By using the transfer function built into the digital twin model, the vibration waveform caused by the drilling parameter adjustment command at the downhole sensor position is calculated, and the vibration waveform is defined as the control source noise signal.

[0021] This embodiment is a specific implementation of the noise prediction module described in Embodiment 1; When the data acquisition module intercepts a drilling parameter adjustment command that is about to be issued, the noise prediction module is immediately activated; it takes the intercepted drilling parameter adjustment command as input, which is a vector that causes changes in the system input. Simultaneously, it invokes the complete state vector of the digital twin model at the current moment. As an initial condition, this vector is provided in real time by the digital twin modeling module and represents the inertial state of the entire drill string system just before the control command takes effect. The module performs forward extrapolation of the state-space equations of the digital twin model to calculate the vibration waveform caused by drilling parameter adjustment commands at the downhole sensor locations, and the new input vector in this process. From the original input vector Drilling parameter adjustment instructions It is formed by superposition, and this process can be expressed mathematically as:

[0022] in, The future state vector is obtained by solving the following system of differential equations:

[0023] in It is a predicted time-series signal of vibration noise generated at the LWD sensor; the prediction process adjusts the commands based on the intercepted control parameters. As future input, and using the complete state vector of the digital twin model at the current moment. As initial conditions for simulation, the downhole vibration response caused by the command can be calculated by forward derivation of the state-space equations; the module defines this calculated vibration waveform as the control source noise signal. And pass it to the signal reconstruction module; This embodiment achieves accurate prediction of control source noise by using the intercepted control commands as future inputs to the digital twin model for forward extrapolation. This feedforward prediction mechanism enables the system to obtain accurate waveform samples of the noise before the actual noise contaminates the measurement signal, providing a high-quality reference signal for subsequent adaptive hedging.

[0024] Example 4: The signal reconstruction module is specifically used for: By using a clock synchronization mechanism, the control source noise signal is aligned with the original mixed signal on the time axis; By using an adaptive hedging algorithm, the weighted components of the aligned control source noise signal are subtracted from the original mixed signal to obtain a pure geological signal; The adaptive hedging algorithm is a least mean square algorithm, and the signal reconstruction module is also used for: Based on the principle of minimizing the output signal energy, the adaptive offset coefficient used to weight the control source noise signal is updated in real time using the iterative rules of the least mean square algorithm.

[0025] This embodiment is a specific implementation of the signal reconstruction module described in Embodiment 1, which adopts an adaptive hedging technique based on the Least Mean Square (LMS) algorithm; The signal reconstruction module receives the original mixed signal. and control source noise signal To achieve precise hedging, the module utilizes a clock synchronization mechanism to align the control source noise signal with the original mixed signal on the time axis. This clock synchronization mechanism uses GPS or other high-precision clock sources to ensure that the timestamps of the ground computing unit and the downhole measurement unit are consistent, and is based on the calibrated total mud pulse transmission delay. ,right Perform a precise time shift to obtain ; After alignment, the module uses an adaptive hedging algorithm to subtract the weighted component of the aligned control source noise signal from the original mixed signal to obtain a pure geological signal. As defined in Example 5, in this example, the adaptive hedging algorithm is a least mean square algorithm, and the actual signal reconstruction process is executed by the following core equation:

[0026] in It is a pure geological signal and is the key output of this module; It is the raw, mixed signal received from downhole; It is after a time delay Aligned predicted noise signal; It is an adaptive hedging coefficient, a dimensionless, time-varying weighted parameter whose value is updated in real time by the LMS algorithm; To optimize the hedging effect, the signal reconstruction module also updates the adaptive hedging coefficients used to weight the control source noise signal in real time, based on the principle of minimizing the output signal energy and utilizing the iterative rules of the least mean square (LMS) algorithm. The LMS algorithm is a classic adaptive filtering algorithm whose purpose is to minimize the energy of the reconstructed signal (i.e., the error signal) through iterative adjustments. Its iterative rule update expression in a discrete-time system is as follows:

[0027] in, It is the updated coefficient value for the next time step; It is the current moment. The coefficient value is a dimensionless parameter; It is the reconstructed signal at the current moment, also known as the error signal in adaptive filtering theory; It is the predicted noise signal after time delay alignment. For continuous time delay Equivalent delay under discrete sampling; To ensure that the iterative formula is strictly consistent in terms of physical dimensions, the step size convergence parameter... The dimensions of the product of the signals are set to be the reciprocals of the dimensions of the product of the signals; for example, if the signal... and The unit for all values ​​is volt (V). The unit is This ensures the update item Since it is dimensionless, it can be compared with dimensionless coefficients. Perform algebraic operations; The optimal values ​​were obtained through offline calibration: using a raw mixed signal containing multiple historical segments. and its corresponding known control source noise signal The calibration dataset, for a series The candidate values ​​are iterated and tested; for each candidate value, the LMS algorithm is applied to the entire calibration dataset and the output signal is calculated. The average residual energy; ultimately, the option that minimizes the average residual energy is chosen. Using the optimal step size as the convergence parameter, this method ensures a balance between the algorithm's convergence speed and steady-state error; the purpose of this iterative process is to continuously adjust... The value makes the output signal The energy tends to be minimized, thereby achieving optimal noise offset; By employing the LMS adaptive hedging algorithm, this embodiment can dynamically and in real time adjust the intensity of noise hedging, making the signal reconstruction process robust and adaptive, thereby obtaining a pure geological signal with clearer geological features after significantly suppressing the control source noise.

[0028] Example 5: The collaborative control module is specifically used for: Pure geological signals are input into a pre-defined lithology-mechanics conversion model to determine the predicted bottom hole torque sequence; The predicted bottom-hole torque sequence is used as the future load and input into the digital twin model for forward-looking simulation to obtain predictions of future dynamic response. The vibration risk index is calculated based on future dynamic response predictions. Based on the vibration risk index, the optimal control command is solved and generated by a multi-objective optimizer. The lithology-mechanics conversion model is a neural network model trained based on machine learning. It is used to predict the drillability or rock strength equivalent parameters of the formation to be encountered by drilling by identifying feature patterns in pure geological signals, so as to output a predicted bottom hole torque sequence. The multi-objective optimizer aims to minimize the future vibration risk index and maximize drilling efficiency, solves for a set of drilling parameter adjustment commands, and defines these commands as the optimal control commands.

[0029] This embodiment is a specific implementation of the collaborative control module described in Embodiment 1. It integrates machine learning prediction, forward simulation and multi-objective optimization technology to form an intelligent closed-loop control core. The collaborative control module receives high-fidelity, pure geological signals output by the signal reconstruction module. Pure geological signals are input into a pre-defined lithology-mechanical transformation model to determine the predicted bottom-hole torque sequence. The lithology-mechanics conversion model is a neural network model trained using machine learning. In this embodiment, the neural network model is a Long Short-Term Memory (LSTM) network, which learns from a large amount of historical data. The data is trained using supervised learning with the corresponding rock mechanics test data; the model is used to predict the drillability or rock strength equivalent parameters of the upcoming formation by identifying feature patterns in pure geological signals, so as to output a predicted bottom hole torque sequence. The module will use the predicted bottom hole torque sequence obtained in the previous step. As a future load, it is input into the digital twin model for forward-looking simulation; forward-looking simulation refers to simulation based on current drilling parameters. Below, a digital twin model is used to simulate what happens when the drill bit encounters... When the stratum represents a given timeframe, the system's dynamic behavior within a short future time window is determined; after the simulation, the module obtains a prediction of the future dynamic response. The module calculates the vibration risk index based on future dynamic response predictions. Vibration risk index It is a quantitative indicator whose definition integrates multiple dimensions such as the amplitude, frequency, and duration of predicted vibration fluctuations, and is used to assess the likelihood and severity of severe vibrations such as stick-slip and impact; for example, the vibration risk index. By using future time windows Normalized predicted angular velocity within Calculated by weighted integration, it can be expressed in one specific form as follows: ,in, To predict the average angular velocity within the time window, the first term penalizes fluctuations in angular velocity, and the second term penalizes drastic changes in angular acceleration. and These are the normalization coefficients for angular velocity and angular acceleration, respectively. For example, they can be taken as the standard deviation from historical data or the maximum allowable fluctuation value in the project, used to eliminate the influence of dimensions, making both items within the square brackets dimensionless. and The preset weighting coefficients are dimensionless and satisfy... ; The module, based on the vibration risk index, uses a multi-objective optimizer, for example, the non-dominated sorting genetic algorithm NSGA-II, to solve and generate the optimal control command; the multi-objective optimizer aims to minimize the future vibration risk index. Maximizing drilling efficiency, defined here as the predicted rate of penetration (ROP), is the optimization objective. This multi-objective optimizer seeks a Pareto optimal solution between two mutually constraining objectives. The optimizer then solves for a set of drilling parameter adjustment instructions. This instruction is defined as the optimal control instruction and sent to the drilling rig control system for execution. To ensure the effectiveness of the vibration risk index, weighting coefficients are used. and The calibration is performed as follows: A database containing multiple sets of historical severe vibration events is established, and the severity level of each event is labeled. In the simulation environment, a series of boundary conditions for these historical events are traversed. and Candidate value combinations, for example, From 0.1 to 0.9, with a step size of 0.1, for each weight group, calculate its predicted vibration risk index across all historical events. Choose a risk index that can handle vibration events of different severity levels. The set of weights with the highest discriminative power is used as the optimal calibration parameters; This embodiment uses a closed-loop link—predicting future loads from geological signals, simulating future vibrations using digital twins, and generating avoidance strategies through multi-objective optimization—to upgrade drilling control from a traditional passive response based on the current state to an active avoidance based on future predictions. This allows risks to be anticipated before severe vibrations occur, and optimal, gentle control actions can be taken in advance to mitigate those risks.

[0030] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A dynamic analysis system for a rotary steerable drilling system, characterized in that, include: The data acquisition module is used to collect surface engineering parameters and downhole dynamic parameters in real time, and to intercept drilling parameter adjustment commands. The digital twin modeling module is used to construct and correct the dynamic digital twin model of the drill string system in real time based on surface engineering parameters and downhole dynamic parameters, and then output the complete state vector of the digital twin model. The noise prediction module is used to generate control source noise signals by calling the digital twin model to perform forward extrapolation based on drilling parameter adjustment commands and complete state vectors. The signal reconstruction module is used to obtain the original mixed signal from the downhole dynamic parameters and perform adaptive hedging processing on the original mixed signal based on the control source noise signal to reconstruct a pure geological signal. The collaborative control module is used to predict the vibration risk caused by changes in the strata ahead based on pure geological signals, and generate optimal control commands for actively avoiding vibration risks.

2. The dynamic analysis system for a rotary steerable drilling system according to claim 1, characterized in that, The digital twin modeling module is specifically used for: Based on the preset geometric configuration, material properties and drilling fluid performance parameters of the drill string assembly, a physical dynamic model with state-space equations as its core is initialized and constructed. Using a Kalman filter, real-time acquired surface engineering parameters and downhole dynamic parameters are used as inputs. By minimizing the error between the model's predicted output and the measured values, the state of the digital twin model is continuously corrected and updated.

3. The dynamic analysis system for a rotary steerable drilling system according to claim 1, characterized in that, The noise prediction module is specifically used for: The intercepted drilling parameter adjustment command is used as input, and the complete state vector of the digital twin model at the current moment is called as the initial condition; By using the transfer function built into the digital twin model, the vibration waveform caused by the drilling parameter adjustment command at the downhole sensor position is calculated, and the vibration waveform is defined as the control source noise signal.

4. The dynamic analysis system for a rotary steerable drilling system according to claim 1, characterized in that, The signal reconstruction module is specifically used for: By using a clock synchronization mechanism, the control source noise signal is aligned with the original mixed signal on the time axis; By using an adaptive hedging algorithm, the weighted components of the aligned control source noise signal are subtracted from the original mixed signal to obtain a pure geological signal.

5. The dynamic analysis system for a rotary steerable drilling system according to claim 4, characterized in that, The adaptive hedging algorithm is a least mean square algorithm, and the signal reconstruction module is also used for: Based on the principle of minimizing the output signal energy, the adaptive offset coefficient used to weight the control source noise signal is updated in real time using the iterative rules of the least mean square algorithm.

6. The dynamic analysis system for a rotary steerable drilling system according to claim 1, characterized in that, The collaborative control module is specifically used for: Pure geological signals are input into a pre-defined lithology-mechanics conversion model to determine the predicted bottom hole torque sequence; The predicted bottom-hole torque sequence is used as the future load and input into the digital twin model for forward-looking simulation to obtain predictions of future dynamic response. The vibration risk index is calculated based on future dynamic response predictions. Based on the vibration risk index, the optimal control command is obtained by solving the problem through a multi-objective optimizer.

7. The dynamic analysis system for a rotary steerable drilling system according to claim 6, characterized in that, The lithology-mechanics conversion model is a neural network model trained based on machine learning. It is used to predict the drillability or rock strength equivalent parameters of the strata to be encountered by drilling by identifying feature patterns in pure geological signals, so as to output a predicted bottom hole torque sequence.

8. The dynamic analysis system for a rotary steerable drilling system according to claim 6, characterized in that, The multi-objective optimizer aims to minimize the future vibration risk index and maximize drilling efficiency, solves for a set of drilling parameter adjustment commands, and defines these commands as the optimal control commands.

Images