Measurement-while-drilling-based rotary guide system risk identification method and identification terminal

Abstract

The invention relates to the technical field of oil field drilling engineering, in particular to a while-drilling measurement-based rotary guide system risk identification method and identification terminal, and the method comprises the steps: obtaining while-drilling measurement data; establishing a deep well wall surrounding rock stress-strain model, and constructing a well wall stability discrimination equation; establishing a random nonlinear disturbance force action model, and determining random dynamic response process parameters of the system with the rotary guide drill column under the deep well condition; determining the well wall stability according to the well wall stability discrimination equation, and determining the failure risk of the drill column system with the rotation guide according to the random dynamic response process; according to the method, effective strain and effective stress at the position, r away from a borehole, of a near-well-wall zone are calculated, and a well wall stability judgment equation is obtained through fitting to judge the possibility of well wall instability; and a Newmark method is adopted to carry out time discretization on the stochastic nonlinear dynamic model of the drill string system to invert the stochastic dynamic response process of the stochastic nonlinear dynamic model, and risk factors are clarified.

Description

Technical Field

[0001] The present invention relates to the technical field of oilfield drilling engineering, and particularly relates to a risk identification method and an identification terminal for a rotary steerable system based on measurement while drilling. Background Art

[0002] Rotary steerable deep well drilling operates in deep formations with high in-situ stress, high geothermal gradient and high formation pressure gradient, and the problem of wellbore instability is prominent. The forms of deep wellbore instability mainly include two categories: wellbore collapse failure and formation fracture damage. The influencing factors are complex and diverse, such as multiple formation pressure systems in deep formations, multi-field coupled physical and chemical effects, collisions between the rotary steerable drill string system and the wellbore wall, stick-slip vibration, fatigue failure of the bottom hole assembly materials, etc.

[0003] During the entire rotary steerable well deviation drilling operation, the rock is deformed and damaged by the rock-breaking action of the drill bit, and continuously exchanges matter and energy with the outside world (including drilling fluid in the annulus, rotary steerable drilling system, rock formations far from the wellbore, etc.). A part of the external force work done on the near-wellbore surrounding rock is converted into the dissipated energy of the surrounding rock, causing the internal micro-cracks of the rock to continuously develop and the strength to continuously weaken until the rock disintegrates and fails. If the above process is not timely warned and controlled, it is extremely easy to induce downhole accidents of the rotary steerable system.

[0004] Therefore, considering using measurement while drilling parameters, etc., to carry out research on the mechanism of deep wellbore stability, analyze the risk influencing factors of the rotary steerable drill string system under deep well conditions, and provide guiding references for the optimal design of domestic rotary steerable systems. Summary of the Invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide a risk identification method and an identification terminal for a rotary steerable system based on measurement while drilling, establish a stress-strain model of the deep wellbore surrounding rock, and obtain a wellbore stability discrimination equation; analyze the random dynamic response process of the rotary steerable drill string system under deep well conditions, clarify the risk factors, so as to carry out the failure risk assessment of the rotary steerable drilling system.

[0006] The present invention is realized by the following technical solutions:

[0007] A risk identification method for a rotary steerable system based on measurement while drilling includes:

[0008] S1. Obtain measurement while drilling data;

[0009] S2. Establish a stress-strain model of the deep wellbore surrounding rock and construct a wellbore stability discrimination equation;

[0010] S3. Establish a random non-linear disturbing force action model and determine the random dynamic response process parameters of the rotary steerable drill string system under deep well conditions;

[0011] S4. Determine the wellbore stability according to the wellbore stability discrimination equation, and determine the failure risk of the rotary steerable drill string system according to the random dynamic response process.

[0012] Specifically, in step S1, the real-time engineering parameter change signal of the bottom hole assembly is obtained through the built-in circuit of the downhole measurement while drilling sub.

[0013] Specifically, step S2 specifically includes:

[0014] Construct a wellbore plane model;

[0015] According to the linear elastic pore theory, determine the effective stress calculation model at a distance r from the wellbore in the near-wellbore zone; determine the effective strain calculation model at a distance r from the wellbore in the near-wellbore zone;

[0016] Carry out numerical simulation calculation of wellbore stability according to the generalized Hoek-Brown criterion, the finite element strength reduction method, the effective stress calculation model and the effective strain calculation model, establish a strength reduction mutation model function, and determine the wellbore strength reduction coefficient;

[0017] By gradually increasing the wellbore strength reduction coefficient, obtain the strain energy of the surrounding rock under multiple strength conditions, and fit the Taylor series expansion formula related to the strain energy of the wellbore surrounding rock and the wellbore strength reduction coefficient:

[0018] Among them. In the formula:

[0019] a0, a1, a2, a3, a4 are undetermined coefficients assigned according to the calculation results of effective stress and effective strain, and F is the undetermined sub-function after strength reduction fitting;

[0020] Obtain the bifurcation set equation according to the cusp bifurcation set theory, and construct the wellbore stability discrimination equation according to the bifurcation set equation: f(v, v) = 4u 3 +5u 2 +27v 2 +u + v, where (x, u, v) are the displacement components of the displacement mutation point in the x, u, and v directions, and the x direction, u direction, and v direction are perpendicular to each other in pairs.

[0021] Specifically, the method for constructing the wellbore plane model is: set the surrounding rock formation as a homogeneous anisotropic elastic body with a horizontal bedding plane, and the wellbore is a regular circle and perpendicular to the bedding plane.

[0022] Optionally, the effective stress calculation model is:

[0023]

[0024] σ r is the effective radial stress, σ θ is the effective tangential stress, σH , σ h are the maximum horizontal principal stress and the minimum horizontal principal stress respectively, r w is the wellbore radius, p r is the pressure at radius r, p i is the mud pressure in the wellbore, p p is the formation pore pressure, α is the effective stress coefficient, ξ is an intermediate parameter, μ is the Poisson's ratio of the rock, f is the average porosity of the formation, and θ is the critical shear angle for rock shear failure in the near-wellbore zone;

[0025] The effective strain calculation model is:

[0026] In the formula: ε r is the effective radial strain, ε θ is the effective tangential strain, μ is the Poisson's ratio of the rock, and E is the elastic modulus of the rock.

[0027] Specifically, step S3 specifically includes:

[0028] Construct a dynamic response model for the double-rotation steerable drill string system:

[0029] Among them, M is the overall generalized mass matrix of the double-rotation steerable drill string system, D is the elastic damping matrix of the double-rotation steerable drill string system, U is the elastic energy of the system, T represents the matrix transpose operation process, q is the generalized force vector acting on the double-rotation steerable drill string system, C represents the overall constraint equation of the double-rotation steerable drill string system, and λ represents the corresponding Lagrange operator vector, is the first derivative of the generalized force vector, is the second derivative of the generalized force vector, and t represents time;

[0030] Construct a model for the action of random non-linear disturbing forces:

[0031]

[0032] , where K represents the overall stiffness matrix of the double-rotation steerable drill string system, Φ represents the discrete mathematics calculation process, [] represents a large matrix composed of sub-matrices, and Q(t) is the force vector of the dynamic response random process of the drill string system at a certain transient state;

[0033] Use the Newmark method to discretize the time of the model for the action of random non-linear disturbing forces and determine the parameters of the random dynamic response process of the steerable drill string system under deep well conditions.

[0034] Specifically, in step S4, the method for determining wellbore stability according to the wellbore stability discrimination equation includes:

[0035] If f(u, v) > 0, it is determined that the wellbore in the complex formation of the deep well is stable;

[0036] If \(f(u, v)=0\), it is determined that the wellbore wall in the deep well complex formation is in critical instability;

[0037] If \(f(u, v)<0\), it is determined that the wellbore wall in the deep well complex formation has become unstable.

[0038] A method for determining the failure risk of a rotary steerable drill string system according to a random dynamic response process includes:

[0039] Collect and statistically analyze various downhole fault data occurring under different actual drilling conditions, and statistically analyze different random dynamic response process parameters and different risk outbreak data;

[0040] Establish a machine learning model, input the random dynamic response process parameters and risk outbreak data into the machine learning model, and obtain the weights of different random dynamic response process parameters in the risk outbreak by adjusting the amplitude, parameters, and weighting of the machine learning model;

[0041] Fit to obtain a failure risk function regarding the length of the risk outbreak time, and determine the failure risk value according to the failure risk function;

[0042] Input the random dynamic response process parameters calculated in step S3 into the failure risk function to obtain the failure risk value;

[0043] Set a failure risk limit value. If the failure risk value is greater than the failure risk limit value, it is determined that there is a failure risk.

[0044] Specifically, conduct a failure risk assessment of the rotary steerable drill string system when the wellbore wall in the deep well complex formation is in a stable state or a critical instability state; if the wellbore wall in the deep well complex formation is in an unstable state, directly issue a well control risk warning.

[0045] A risk identification terminal for a rotary steerable system based on measurement while drilling, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a risk identification method for a rotary steerable system based on measurement while drilling as described above.

[0046] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0047] The present invention obtains measurement while drilling data, studies and analyzes the changes of various parameters, calculates the effective strain and effective stress at a distance \(r\) from the wellbore in the near-wellbore zone, and based on the generalized Hoek-Brown criterion and the cusp bifurcation set theory, fits to obtain a wellbore stability discrimination equation to judge the possibility of wellbore instability; and uses the Newmark method to discretize the time of the random nonlinear dynamics model of the drill string system to invert its random dynamic response process, clarify the risk factors, and finally conduct a failure risk assessment and early warning disposal for the rotary steerable drilling system.

[0048] The present invention utilizes on-site measurement data while drilling to make the analysis results conform to actual engineering problems, having good guiding significance for engineering physics; at the same time, it incorporates the energy change of wellbore rocks and the finite element strength reduction method, meeting the current requirements of rotary steering operations for wellbore integrity and improving the simulation accuracy; in the process of identifying risk factors, the matrix prediction model adds a spatial scale and adopts a non-parametric probability method, considering both model uncertainty and increasing model predictability, facilitating the reasonable evaluation of risk factors and early warning disposal. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings illustrate exemplary embodiments of the present invention and, together with the description thereof, are used to explain the principles of the present invention. These drawings are included to provide a further understanding of the present invention, and the drawings are included in this specification and form a part of this specification, and do not constitute a limitation on the embodiments of the present invention.

[0050] Figure 1 Schematic diagram of the built-in circuit of the downhole measurement sub while drilling in the present invention;

[0051] Figure 2 Trend chart of the change of engineering parameters while drilling in the present invention. In the figure, a - weight on bit, b - torque, c - annulus pressure, b - vibration;

[0052] Figure 3 Schematic diagram of the plane stress analysis of the wellbore wall in the present invention;

[0053] Figure 4 Schematic diagram of the three-dimensional equilibrium surface of the displacement mutation of the formation unit in the present invention;

[0054] Figure 5 Schematic diagram of the stress distribution of the entire drill string structure in the present invention;

[0055] Figure 6 Law of the change of the stress of the rotary steering drill string system structure with time in the present invention;

[0056] Figure 7 Fatigue cumulative risk chart of the rotary steering drill string system in the present invention;

[0057] Figure 8 Stick-slip vibration risk chart of the rotary steering drill string system in the present invention;

[0058] Figure 9 Curve of the change of the radial displacement of the rotary steering drill string system with time in the present invention;

[0059] Figure 10 Collision risk chart of the rotary steering drill string system with the wellbore wall in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] To make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the relevant content and do not limit the present invention.

[0061] In addition, it should be noted that only parts related to the present invention are shown in the drawings for the convenience of description.

[0062] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and embodiments.

[0063] Embodiment 1

[0064] A method for risk identification of a rotary steering system based on measurement while drilling includes:

[0065] S1. Obtain measurement-while-drilling data; analyze the engineering physical meanings and change trends of different measurement parameters.

[0066] The steering tool realizes tool deviation correction in two modes: remote control and automatic control. In the remote control mode, the ground issues a deviation correction command to the downhole through wired conduction according to the downhole information to control the deviation correction of the drilling system. In the automatic control mode, the downhole device automatically judges the hole deviation situation and automatically performs deviation correction.

[0067] Figure 1 Show a built-in circuit of a downhole measurement-while-drilling sub-section, which can obtain the real-time change signal of the engineering parameters while drilling of the bottom hole assembly. That is, obtain the real-time change signal of the engineering parameters while drilling of the bottom hole assembly through the built-in circuit of the downhole measurement-while-drilling sub-section.

[0068] The measurement process is as follows: The signal emitted by the signal source is received through feedback, and after being amplified, voltage offset, filtered, and amplified again by the processing module, the signal is output to the main control module, processed and corrected by the AD numerical method, and finally the measurement value is calculated.

[0069] The transmitted signals include but are not limited to well inclination angle, azimuth angle, acceleration component, magnetic flux, temperature, magnetic field strength, drilling fluid pressure, etc. When the ground system fails to send signals for more than the specified time, the downhole device immediately switches to the automatic control mode.

[0070] Through the comparative study of the real-time engineering parameters while drilling, analyze the changes of the weight on bit, drill pipe torque, annulus pressure, and vibration parameters at the near-bit position, and explore the actual engineering operation process in cases such as weight transfer, drill string fatigue, and gas invasion and overflow.

[0071] In the automatic control mode, the downhole measurement-while-drilling sub-section can transmit information to the data storage device in the rotary steering stability control unit through wired communication and send it to the MWD main control sub-section along the optimized logic.

[0072] In the remote control mode, downhole data is sent to the surface via drilling fluid pulses, and finally the surface aggregates and analyzes the data through a software platform, sends out signals, and guides and controls the drilling system to correct the deviation.

[0073] The following are the engineering parameters while drilling, and the associated engineering physical meanings and change trends are as follows:

[0074] (1) Monitoring and analysis of the weight on bit: Figure 2 (a) As the well depth increases, the directional adjustment trajectory is carried out. The cuttings do not return to the surface in time, resulting in an increase in the downhole frictional resistance and a tendency to form a stuck weight. At this time, there is an obvious deviation between the surface / downhole weight-on-bit curves, that is, the surface weight on bit increases while the downhole weight on bit does not increase accordingly. During the subsequent pressurization process, the torque suddenly increases and the weight on bit starts to backpressure, indicating a change in the weight-on-bit transfer efficiency.

[0075] (2) Monitoring and analysis of the torque: Figure 2 (b) After the occurrence of stuck weight, the rotation torque of the PDC bit first tends to be stable. As the weight on bit is released, the downhole torque instantaneously increases, seriously threatening the safe use of downhole drill strings.

[0076] (3) Monitoring and analysis of the outer annulus pressure: Figure 2 (c) When the downhole outer annulus pressure starts to decrease, the reaction time interval with the surface outlet flow rate is about 5 minutes, and the reaction time interval with the total hydrocarbon is about 7 minutes. When the gas invasion section is discovered, the outer annulus pressure drops by up to 1.3 MPa.

[0077] (4) Monitoring and analysis of the vibration: Figure 2 (d) Due to the change in lithology, the adaptability of the bit becomes poor, inducing changes in downhole vibration, resulting in fluctuations in the build-up rate in different well depth sections and affecting the directional drilling effect.

[0078] S2. Establish a stress-strain model for the surrounding rock of the deep wellbore wall and construct a wellbore stability discrimination equation; thus, carry out the study on the stability of the deep wellbore wall in complex formations.

[0079] As a systematic project, the wellbore stability problem in deep drilling engineering is very crucial. The deep wellbore is prone to cracking, collapse, and diameter reduction, etc., causing downhole accidents such as stuck pipe, resulting in huge losses. The stable state of the deep wellbore wall is essentially an equilibrium state formed under the coupling action of multiple fields, and the instability of the wellbore wall stems from the destruction of the equilibrium state (the combined action of the drill string and the effective liquid column in the annulus).

[0080] Construct a plane model of the wellbore wall. The method is as follows: Set the surrounding rock formation as a homogeneous anisotropic elastic body with a horizontal bedding plane, the wellbore as a regular circle and perpendicular to the bedding plane, and transform the three-dimensional stress balance problem into a plane stress-strain problem.

[0081] According to Figure 3For the calculation of the wellbore plane model, since the deep well formation is mostly a fractured formation, considering the seepage effect of formation fluids, according to the linear elastic pore theory, the effective stress calculation model at a distance r from the wellbore in the near-wellbore zone is determined: Among them, σ r is the effective radial stress, MPa; σ θ is the effective tangential stress, MPa; σ H , σ h are the maximum horizontal principal stress and the minimum horizontal principal stress, MPa respectively; r w is the wellbore radius, m; p r is the pressure at radius r, MPa; p i is the mud pressure in the wellbore, MPa; p p is the formation pore pressure, MPa; α is the effective stress coefficient, dimensionless; μ is the rock Poisson's ratio; f is the average formation porosity, obtained by measuring core samples, %; θ is the critical shear angle for rock formation shear failure in the near-wellbore zone, obtained by conducting triaxial pressure tests on core samples. Determine the effective strain calculation model at a distance r from the wellbore in the near-wellbore zone: In the formula, ε r is the effective radial strain, dimensionless; ε θ is the effective tangential strain, dimensionless; μ is the rock Poisson's ratio, dimensionless; E is the rock elastic modulus, MPa.

[0082] During rotary steerable drilling, the rock continuously exchanges matter and energy with the outside world, deforms and fails, and part of the external work is converted into the dissipation energy of the rock skeleton, causing the continuous development of microcracks and the weakening of its strength inside.

[0083] According to the generalized Hoek-Brown criterion, the finite element strength reduction method, the effective stress calculation model and the effective strain calculation model, conduct numerical simulation calculations for wellbore stability. Based on the strain energy of the wellbore surrounding rock, establish a strength reduction mutation model function to assist in judging the possibility of wellbore instability. Establish the strength reduction mutation model function and determine the wellbore strength reduction coefficient;

[0084] The basic principle of the strength reduction method is: continuously reduce the rock mass strength parameters, substitute the reduced strength values into the numerical calculation, and finally make the rock mass reach the limit equilibrium state. Denote the structural strength safety factor of the rock mass at the limit equilibrium state as the reduction coefficient.

[0085] By gradually increasing the wellbore strength reduction coefficient, obtain the strain energy of the surrounding rock under multiple strength conditions, and fit the Taylor series expansion formula related to the strain energy of the wellbore surrounding rock and the wellbore strength reduction coefficient:

[0086] Among them. In the formula:

[0087] a0, a1, a2, a3, a4 are undetermined coefficients assigned according to the calculation results of effective stress and effective strain, dimensionless; F is the undetermined sub-function after strength reduction fitting, dimensionless.

[0088] Perform standard potential function processing on the above Taylor series expansion, consider the calculation of the displacement vectors of a certain geological unit in three-dimensional space along three orthogonal directions, and the critical point set when the surrounding rock strain energy undergoes a sudden change constitutes a three-dimensional equilibrium surface. Figure 4 The surface space graph in [reference] consists of upper, middle, and lower three leaves. The upper and lower leaves are stable, and the middle leaf is unstable. No matter how it changes along any path, the displacement mutation point (x, u, v) only changes stably on the upper leaf (or lower leaf). When reaching the edge of this leaf, a sudden jump occurs and it jumps over the middle leaf.

[0089] Therefore, obtain the bifurcation set equation according to the cusp bifurcation set theory, and construct the wellbore stability discrimination equation according to the bifurcation set equation: f(u, v) = 4u 3 + 5u 2 + 27v 2 + u + v, where (x, u, v) are the displacement components of the displacement mutation point in the x, u, and v directions, and the x direction, u direction, and v direction are perpendicular to each other pairwise.

[0090] S3. Establish a random nonlinear disturbance force action model to determine the random dynamic response process parameters of the rotary steerable drill string system under deep well conditions;

[0091] The wellbore trajectory designed by rotary steerable inclination control often shows as a two-dimensional curve, but the actual wellbore trajectory of a deep well is actually a three-dimensional space curve. When designing, correct the measured values of the well inclination angle and azimuth angle according to the real-time engineering parameters in step S1, and approximate the actual wellbore trajectory by interpolation calculation. Some of the drill string system parameters involved are shown in Table 1:

[0092] Table 1 Rotary Steerable Drill String System Parameters

[0093]

[0094]

[0095] Construct a dynamic response model of the rotary steerable drill string system:

[0096] where M is the overall generalized mass matrix of the rotary steerable drill string system, dimensionless; D is the elastic damping matrix of the rotary steerable drill string system, dimensionless; U is the elastic strain energy of the system, J; T is the matrix transpose operation process, dimensionless; q is the generalized force vector acting on the rotary steerable drill string system, N; C represents the overall constraint equation of the rotary steerable drill string system, dimensionless; λ represents the corresponding Lagrangian operator vector, dimensionless; is the first derivative of the generalized force vector, dimensionless; is the second derivative of the generalized force vector, dimensionless; t represents time, in minutes.

[0097] The random uncertainty in the prediction of complex systems is caused by data uncertainty and model uncertainty, which will lead to large errors. Therefore, it is necessary to consider the integrated analysis of the above uncertainties.

[0098] When the random dynamic response process of the rotary steerable drill string system under deep well conditions is full of uncertainties in the solution process of the drill string - wellbore stress - strain model, the action of random disturbing forces also needs to be considered in the system random dynamic response process; add a spatial scale to the prediction model and adopt a non - parametric probability method to consider both model uncertainty and increase model predictability.

[0099] Assume that the force vector of the random process of the dynamic response of the drill string system at a certain transient state is marked as Q(t), and construct a random non - linear disturbing force action model:

[0100]

[0101] , where K represents the overall stiffness matrix of the rotary steerable drill string system, dimensionless; Φ represents the discrete mathematics calculation process, dimensionless; [] represents a large matrix composed of sub - matrices, dimensionless; Q(t) is the force vector of the random process of the dynamic response of the drill string system at a certain transient state.

[0102] Use the Newmark method to discretize the time of the random non - linear disturbing force action model and determine the parameters of the random dynamic response process of the rotary steerable drill string system under deep well conditions.

[0103] The calculation method steps are as follows:

[0104] ① Initial calculation: Form the mass matrix, damping matrix and stiffness matrix; Given the initial displacement, velocity and acceleration; Select appropriate parameters, calculate the integral, form the effective stiffness matrix, and perform triangular decomposition on it;

[0105] ② Step - size calculation: First calculate the effective load at time, then calculate the displacement at time, and finally calculate the acceleration and velocity at time.

[0106] Based on the above calculation results, from the perspective of maintaining the integrity of the rotary steerable drill string system, the identified risk factors are mainly four:

[0107] The maximum structural stress value - If the stress value borne by the drill string is greater than this value, the rotary steerable system will be damaged;

[0108] Fatigue cumulative damage - If the damage value is greater than 1, there are cracks in the drill string structure, causing the drill string to fail and break;

[0109] Stick-slip stability coefficient - Avoid the generation of torsional instability and sliding adhesion in the low-value range;

[0110] Radial displacement of the drill string - When it is greater than the average thickness of the annulus, the drill string collides with the wellbore and the drill string is prone to failure.

[0111] S4. Determine the wellbore stability according to the wellbore stability discrimination equation, and determine the failure risk of the rotary steerable drill string system according to the random dynamic response process.

[0112] Regard the surrounding rock as an elastic body as a whole, and give the expression of the strain energy potential function: When the wellbore surrounding rock is in a stable state, the potential function takes a unique extreme value; when the potential function has multiple extreme values, the wellbore surrounding rock is in an unstable state. The method for determining the wellbore stability according to the wellbore stability discrimination equation includes:

[0113] If f(u, v) > 0, it is determined that the wellbore in the deep and complex formation is stable;

[0114] If f(u, v) = 0, it is determined that the wellbore in the deep and complex formation is in critical instability;

[0115] If f(u, v) < 0, it is determined that the wellbore in the deep and complex formation is unstable.

[0116] The method for determining the failure risk of the rotary steerable drill string system according to the random dynamic response process includes:

[0117] Collect and statistically analyze various downhole fault data occurring under different actual drilling conditions, and statistically analyze different random dynamic response process parameters and different risk outbreak data; the random dynamic response process parameters include structural stress, fatigue cumulative damage value, stick-slip stability coefficient, and radial displacement of the drill string.

[0118] Establish a machine learning model, input the random dynamic response process parameters and risk outbreak data into the machine learning model, and obtain the weights of different random dynamic response process parameters in the risk outbreak by adjusting the amplitude, parameters, and weighting of the machine learning model;

[0119] Fit to obtain a failure risk function for the risk outbreak time length, and determine the failure risk value according to the failure risk function;

[0120] Input the random dynamic response process parameters calculated in step S3 into the failure risk function to obtain the failure risk value;

[0121] Set a failure risk limit value. If the failure risk value is greater than the failure risk limit value, it is determined that there is a failure risk.

[0122] The overall idea is as follows: Count the frequencies of downhole failures and complex accidents caused by different risk factors (i.e., random dynamic response process parameters) under different actual drilling conditions, calculate the frequency ratios of these to the total number of downhole accident and outbreak risk events, use these as the weights for various risk outbreaks, and then use machine learning methods for value assignment, parameter adjustment, and weighting to determine the actual risk weight magnitudes of various risk factors under different actual drilling conditions. Finally, fit a failure risk calculation function for the risk outbreak time length (the time for handling accidents), and use its calculation result as the failure risk value. The longer the risk outbreak time length, the greater the failure risk. Plot the failure risk numerical results into a risk data chart. With data table processing software such as Excel and Origin, select the horizontal and vertical coordinates and read their values to know the risk magnitudes under corresponding conditions.

[0123] The obtained random dynamic response process parameters include structural stress, fatigue cumulative damage value, stick-slip stability coefficient, and drill string radial displacement;

[0124] Determine the maximum structural stress value. If the structural stress is greater than the maximum structural stress value, it is determined that the rotary steerable drill string system will be damaged;

[0125] If the fatigue cumulative damage value is greater than 1, it is determined that the drill string structure will be damaged;

[0126] Determine the stick-slip stability limit value. If the stick-slip stability coefficient is greater than the stick-slip stability limit value, it is determined that the torque is unstable and stick-slip motion occurs;

[0127] Determine the allowable radial displacement. If the drill string radial displacement is greater than the allowable radial position, it is determined that the drill string collides with the wellbore;

[0128] In addition, based on the dynamic response calculation results in S3, analysis is carried out, existing rotary steerable drilling accidents and anomalies are counted to form a chart, and a comprehensive evaluation is made on the identified failure risk factors of the rotary steerable drilling system.

[0129] Regarding the change in structural stress as a risk factor, the evaluation process is as follows: When the rotary table speed is 120 RPM and the weight on bit is 120 KN, using random nonlinear dynamics calculation, within the time range of 60 - 80 s, the structural stress distribution curve of the drill string along the well depth direction is as Figure 5 shown. It can be seen from the figure that the maximum structural stress at each point of the drill string is far lower than the stress limit of 650 MPa of the drill string material, and it can be considered that the risk value of the drill string system caused by stress is very low.

[0130] Regarding fatigue cumulative damage as a risk factor, the evaluation process is as follows: During the drilling process of the drill string, the dangerous point prone to fatigue failure of the drill string is near the drill collar, and the structural stress at this point basically changes periodically ( Figure 6 ). Under the condition that the rotary table speed is 120 RPM and the weight on bit is 120 KN, byFigure 7 The calculated fatigue failure risk value of the drill string is 0.1696, and it can be seen that "as the WOB increases, the failure risk of the drill string increases".

[0131] Regarding the risk factor of stick-slip vibration, the evaluation process is as follows: At a rotational speed of 80 RPM and a WOB of 120 KN, the drill string undergoes stick-slip motion at 62 - 65 s, and the drilling rate shows a huge fluctuation ( Figure 8 ), and the calculated system risk value caused by the stick-slip motion is 0.678.

[0132] Regarding the risk factor of the radial displacement of the drill string, the evaluation process is as follows: Figure 9 The upper straight line is the allowable radial displacement (the distance from the outer diameter of the drill string to the wellbore wall). The smaller the difference between the radial displacement of the drill string and the allowable radial displacement, the closer the drill string is to the wellbore wall, and the collision probability increases; when the difference is 0, the drill string collides with the wellbore wall. Figure 10 It can also be seen that within the time range of 60 - 80 s, the drill string collides with the wellbore wall multiple times, with high danger. The calculated risk value of the drill string system caused by the collision is 0.698.

[0133] Finally, since the main parameters actually controlling the motion of the drill string are the rotary table speed and the WOB, combined with the wellbore wall stability under the complex formation conditions of deep wells, comprehensively considering the structural stress, fatigue cumulative damage, sliding adhesion, and the radial displacement of the drill string, an overall risk assessment of the drill string system is carried out.

[0134] In the overall risk assessment results of the drill string system, at the same rotational speed, as the WOB increases, the risk value of the drill string continuously increases; when the WOB reaches 135 KN, the overall risk value of the drill string system is relatively large; when the WOB reaches 140 KN, the failure probability of the drill string is nearly 100%. At different rotational speeds, when the WOB is small, the risk value fluctuates little, and as the WOB increases, the fluctuation gradually increases.

[0135] Carry out the failure risk assessment of the rotary - guided drill string system under the condition that the wellbore wall of the deep - well complex formation is in a stable state or a critical instability state; if the wellbore wall of the deep - well complex formation is in an unstable state, directly issue a well control risk warning.

[0136] Construct an early warning feedback mechanism for the rotary - guided drill string system. Through software calculation and analysis, make early predictions, take measures, reasonably optimize the WOB parameters, and effectively avoid the drill string fatigue accidents caused by sticking.

[0137] Specifically, make full use of the measured changes in the outer annulus pressure to conduct well control risk warning. Through formation identification and analysis, effectively assist drilling operations, improve the service life of the drill bit, and protect the safety of the drill string. Through downhole vibration monitoring, combined with the changes in surface - downhole WOB, determine the risk rotational speed threshold range to avoid drill string resonance accidents, and achieve the risk control of drill string failures.

[0138] Example 2

[0139] A risk identification terminal for a rotary steering system based on measurement while drilling, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned risk identification method for a rotary steering system based on measurement while drilling.

[0140] The memory can be used to store software programs and modules. By running the software programs and modules stored in the memory, the processor can execute various functional applications and data processing of the terminal. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, execution programs required for at least one function, etc.

[0141] The data storage area can store data created according to the use of the terminal, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0142] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned risk identification method for a rotary steering system based on measurement while drilling.

[0143] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, magnetic tape cartridges, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art know that computer storage media are not limited to the above several. The above-mentioned system memory and mass storage devices can be collectively referred to as memory.

[0144] In the description of this specification, the description with reference to terms such as "one embodiment / way", "some embodiments / ways", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment / way or example are included in at least one embodiment / way or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment / way or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments / ways or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments / ways or examples described in this specification and the features of different embodiments / ways or examples.

[0145] In addition, the terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0146] Those skilled in the art should understand that the above-described embodiments are only for clearly illustrating the present invention and are not intended to limit the scope of the present invention. For those skilled in the art, other changes or modifications can be made based on the above invention, and these changes or modifications are still within the scope of the present invention.

Claims

1. A risk identification method for a rotary steering system based on measurement while drilling, characterized in that Including: S1. Obtain measurement-while-drilling data; S2. Establish a stress-strain model of the surrounding rock of the deep wellbore wall and construct a wellbore stability discrimination equation; S3. Establish a random nonlinear disturbing force action model and determine the random dynamic response process parameters of the rotary steerable drill string system under deep well conditions; S4. Determine the wellbore wall stability according to the wellbore stability discrimination equation and determine the failure risk of the rotary steerable drill string system according to the random dynamic response process.

2. The risk identification method of a rotary steering system based on measurement while drilling according to claim 1, wherein In step S1, the real-time measurement-while-drilling engineering parameter change signal of the bottom hole assembly is obtained through the built-in circuit of the downhole measurement-while-drilling sub.

3. A method for risk identification of a rotary steering system based on measurement while drilling according to claim 2, wherein Step S2 specifically includes: Construct a wellbore plane model; Determine the effective stress calculation model at a distance r from the wellbore in the near-wellbore zone according to the linear elastic pore theory; determine the effective strain calculation model at a distance r from the wellbore in the near-wellbore zone; Conduct numerical simulation calculations of wellbore stability according to the generalized Hoek-Brown criterion, the finite element strength reduction method, the effective stress calculation model and the effective strain calculation model, establish a strength reduction mutation model function, and determine the wellbore strength reduction coefficient; By gradually increasing the reduction coefficient of the shaft wall strength, the surrounding rock strain energy under multiple strength conditions is obtained, and a Taylor series expansion formula related to the reduction coefficient of the shaft wall strength and the surrounding rock strain energy is fitted: Among them. In the formula: a0, a1, a2, a3, a4 are undetermined coefficients assigned according to the calculation results of effective stress and effective strain, and F is a to-be-determined sub-function after strength reduction fitting; According to the cusp bifurcation set theory, the bifurcation set equation is obtained, and the wellbore stability discrimination equation is constructed based on the bifurcation set equation: f(u, v) = 4u 3 + 5u 2 + 27v 2 + u + v, where (x, u, v) are the displacement components of the displacement mutation point in the x, u, and v directions, and the x direction, u direction, and υ direction are perpendicular to each other in pairs.

4. A risk identification method for a rotary steering system based on measurement while drilling according to claim 3, characterized in that The method for constructing the wellbore plane model is: set the surrounding rock formation as a homogeneous anisotropic elastic body with a horizontal bedding plane, and the wellbore as a regular circle perpendicular to the bedding plane.

5. A risk identification method for a rotary steering system based on measurement while drilling according to claim 3, characterized in that The effective stress calculation model is: Among them, σ r is the effective radial stress, σ θ is the effective tangential stress, σ H , σ h are the maximum horizontal principal stress and the minimum horizontal principal stress respectively, r w is the wellbore radius, p r is the pressure at radius r, p i is the mud pressure in the wellbore, p p is the formation pore pressure, α is the effective stress coefficient, ξ is an intermediate parameter, μ is the Poisson's ratio of the rock, f is the average porosity of the formation, and θ is the critical shear angle for rock shear failure in the near-wellbore zone; The effective strain calculation model is: where: ε r is the effective radial strain, ε θ is the effective tangential strain, μ is the Poisson's ratio of the rock, and E is the elastic modulus of the rock.

6. A risk identification method for a rotary steerable system based on measurement while drilling according to claim 5, characterized in that, Step S3 specifically includes: Build the dynamic response model of the coiled coiled rotary steerable drill string system: where M is the overall generalized mass matrix of the coiled coiled rotary steerable drill string system, D is the elastic damping matrix of the coiled coiled rotary steerable drill string system, U is the elastic energy of the system, T represents the matrix transpose operation process, q is the generalized force vector acting on the coiled coiled rotary steerable drill string system, C represents the overall constraint equation of the coiled coiled rotary steerable drill string system, and λ represents the corresponding Lagrange operator vector, is the first derivative of the generalized force vector, is the second derivative of the generalized force vector, and t represents time; Construct a random nonlinear disturbing force action model: ， Wherein, K represents the overall stiffness matrix of the rotary steerable drill string system, Φ represents the discrete mathematical calculation process, [ ] represents the large matrix composed of sub-matrices, and Q(t) is the force vector of the drill string system dynamic response random process at a certain transient; Use the Newmark method to discretize the random nonlinear disturbing force action model in time and determine the random dynamic response process parameters of the rotary steerable drill string system under deep well conditions.

7. A method for risk identification of a rotary steering system based on measurement while drilling according to claim 6, characterized in that, In step S4, the method for determining the wellbore wall stability according to the wellbore stability discrimination equation includes: If f(u, υ) > 0, it is determined that the wellbore wall in the deep well complex formation is stable; If f(u, υ) = 0, it is determined that the wellbore wall in the deep well complex formation is in critical instability; If f(u, v) < 0, it is determined that the wellbore wall in the deep well complex formation has failed.

8. A method for risk identification of a rotary steering system based on measurement while drilling according to claim 7, characterized in that, In step S4, the method for determining the failure risk of the rotary steerable drill string system according to the random dynamic response process includes: Collect and statistically analyze various downhole fault data occurring under different actual drilling conditions, and statistically analyze different random dynamic response process parameters and different risk outbreak data; Establish a machine learning model, input the random dynamic response process parameters and risk outbreak data into the machine learning model, and obtain the weights of different random dynamic response process parameters in the risk outbreak by adjusting the amplitude, parameters and weights of the machine learning model; Fit to obtain a failure risk function regarding the risk outbreak time length and determine the failure risk value according to the failure risk function; Input the random dynamic response process parameters calculated in step S3 into the failure risk function to obtain the failure risk value; Set a failure risk limit value. If the failure risk value is greater than the failure risk limit value, it is determined that there is a failure risk.

9. A risk identification method for a rotary steerable system based on measurement while drilling according to claim 8, wherein, Conduct a failure risk assessment of the rotary steerable drill string system when the wellbore wall in deep well complex formations is in a stable state or a critical instability state; if the wellbore wall in deep well complex formations is in an unstable state, directly issue a well control risk warning.

10. A risk identification terminal for a rotary steering system based on measurement while drilling, 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 a risk identification method for a rotary steerable system based on measurement while drilling as described in any one of claims 1-9.

Images