Method and device for determining verticality while drilling, rotary drilling rig and storage medium

Abstract

The present application relates to the field of engineering construction technology, and provides a method and device for judging verticality while drilling, a rotary drilling rig and a storage medium, comprising: synchronously collecting at least two types of verticality-related data based on different measurement principles in real time: drill bit absolute spatial position data obtained based on spatial positioning technology, and mast relative attitude data obtained based on inertial measurement technology; processing the drill bit absolute spatial position data and the mast relative attitude data through a data fusion algorithm, eliminating measurement deviation caused by elastic deformation of the drill pipe by using the spatial geometric constraint relationship between the two, and obtaining comprehensive verticality reflecting the actual drilling axis; and performing time sequence correlation analysis on the comprehensive verticality and drilling condition parameters, and determining diagnostic information of the cause of the current vertical deviation by using a preset deviation pattern recognition rule. In this way, the hole axis state can be truly reflected, and the cause of the rotary drilling rig deviation can be intelligently diagnosed.

Description

Technical Field

[0001] This invention relates to the field of engineering construction technology, and in particular to a method, device, rotary drilling rig, and storage medium for determining verticality during drilling. Background Technology

[0002] Currently, in rotary drilling rig construction, verticality monitoring mainly relies on tilt sensors installed on the mast. This existing technology indirectly estimates borehole inclination by measuring the mast's tilt angle, which has significant problems: First, it can only sense the mast's posture and cannot detect elastic bending deformation caused by the drill rod's stress, leading to measurement distortion where the mast is vertical but the actual borehole inclination is off-center. Second, this measurement system has limited functionality, only providing numerical display and over-limit alarms, and cannot intelligently diagnose the causes of inclination, such as encountering obstacles, changes in geological formation, or improper operation. Therefore, solving the problems of measurement distortion of actual borehole inclination and the inability to find the cause of inclination in existing rotary excavator construction technologies has become an urgent technical problem that the industry needs to address. Summary of the Invention

[0003] In view of this, the main objective of the present invention is to provide a method, device, rotary drilling rig, and storage medium for determining verticality while drilling, which can accurately reflect the state of the borehole shaft and intelligently diagnose the causes of deviation of the rotary drilling rig.

[0004] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0005] In a first aspect, embodiments of the present invention provide a method for determining verticality while drilling, comprising: real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles:

[0006] Absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology;

[0007] The absolute spatial position data of the drill bit and the relative attitude data of the mast are processed by data fusion algorithm. The spatial geometric constraint relationship between the two is used to eliminate the measurement deviation caused by the elastic deformation of the drill rod and obtain the comprehensive verticality that reflects the actual borehole axis.

[0008] The comprehensive verticality is correlated with drilling parameters over time, and diagnostic information for the cause of the current vertical deviation is determined by using preset deviation pattern recognition rules.

[0009] The absolute spatial position data of the drill bit is obtained through a dual-antenna satellite positioning system;

[0010] The real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles includes:

[0011] Using carrier phase differential technology, the precise three-dimensional coordinates of the two antennas are calculated in real time to form a spatial baseline vector representing the mast axis. The two antennas are a first satellite positioning antenna and a second satellite positioning antenna respectively installed at the top and bottom of the mast.

[0012] By combining the mechanical structural parameters of the mast with the length of the drill bit, the real-time absolute spatial position data of the drill bit is calculated.

[0013] as well as,

[0014] The mast relative attitude data is obtained through a miniature inertial measurement module installed on the mast, which includes at least a three-axis accelerometer and a three-axis gyroscope.

[0015] The real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles includes:

[0016] Real-time measurement of the mast's tilt angle relative to the gravity vector and the change in the angular velocity of the tilt angle.

[0017] The process involves using a data fusion algorithm to process the absolute spatial position data of the drill bit and the relative attitude data of the mast. By utilizing the spatial geometric constraints between the two, measurement deviations caused by the elastic deformation of the drill rod are eliminated, resulting in a comprehensive verticality reflecting the actual borehole axis. This includes:

[0018] The absolute spatial position data of the drill bit is used as an external direct observation value;

[0019] The relative attitude data of the mast is used as the content motion constraint observation value;

[0020] Based on the mechanical structure model of the drilling rig, a system state equation is established that includes the overall tilt angle state of the mast and the elastic deformation displacement state of the drill pipe segments.

[0021] The system state equation is filtered and iterated by a state estimation algorithm to estimate and separate the contributions of the overall mast tilt and the drill pipe elastic deformation to the verticality measurement in real time. This allows the error component caused by the drill pipe elastic deformation to be extracted from the mast relative attitude data, and the overall verticality can be calculated in the end.

[0022] The mechanical structure model based on the drilling rig establishes system equations that include the overall tilt angle state of the mast and the elastic deformation displacement state of the drill pipe segments, including:

[0023] Based on the mechanical structure model of the drilling rig, the mechanical structure parameters of the drilling rig, the interface characteristic parameters of the drill rod, and the real-time drilling depth and real-time drilling load are obtained. The mechanical structure model will be dynamically updated based on the real-time drilling depth, the interface characteristics of the drill rod, and the real-time drilling load.

[0024] Based on the obtained parameters, the mast is modeled as a rigid body rotating about its bottom hinge point, and the drill pipe is discretized into multiple elastic beam elements connected in sequence.

[0025] Based on the connection conditions and force balance relationship between the rigid body and the elastic beam unit, a system state equation is constructed with the overall tilt angle and angular velocity of the mast, as well as the nodal positions and rotation angles of each elastic beam unit as state variables.

[0026] The step of performing a time-series correlation analysis between the overall verticality and drilling condition parameters, and determining diagnostic information for the cause of the current vertical deviation based on preset deviation pattern recognition rules, includes:

[0027] An association matrix is ​​constructed based on historical drilling condition parameters. The association matrix is ​​used to define the mapping relationship between different comprehensive verticality deviation time series patterns and drilling condition parameter time series patterns.

[0028] During the drilling process, the time series of the current comprehensive verticality and the time series of drilling condition parameters synchronized with the comprehensive verticality are extracted and together form the current time series feature vector.

[0029] The current time-series feature vector is matched with the correlation matrix to identify the best-matching deviation pattern;

[0030] The cause mapped by the identified deviation pattern is determined as the cause of the current vertical deviation, and the diagnostic information is output.

[0031] The diagnostic information for determining the cause of the current verticality deviation using preset deviation pattern recognition rules includes:

[0032] Using a preset deviation pattern recognition rule, a classification model trained by machine learning based on historical borehole data is used to associate and map the temporal characteristics of vertical deviation with the change patterns of operating parameters, and output diagnostic information. The classification model is an end-to-end model based on a deep neural network. Its input is the temporal data of the comprehensive verticality corresponding to the temporal data of the operating parameters within a fixed time window, and the output is the probability distribution of each cause type.

[0033] The diagnostic results indicated by the diagnostic information include at least one of the following categories: initial mast leveling error, guide mechanism clearance sway, encounter with obstacles or hard interlayers, drilling at the interface of soft and hard formations, and instability of drilling pressure and rotation speed.

[0034] The method further includes:

[0035] Based on the diagnostic information, a preset correction strategy library is matched to generate and output targeted operation guidance information or direct control commands. If the cause diagnosis result indicates that the gradual deviation is caused by drilling at the interface between soft and hard formations, the generated command is to send a continuous, small-amplitude reverse compensation signal to the automatic leveling system of the drilling rig mast. If the cause diagnosis result indicates that the instantaneous impact deviation is caused by encountering an obstacle or hard interlayer, the generated command is to prompt the operator with alarm information, which includes reminders to raise the drill bit and switch the drilling rig mode.

[0036] Secondly, embodiments of the present invention provide a drilling verticality determination device, comprising:

[0037] The multi-source acquisition module is used to acquire at least two types of vertically correlated data based on different measurement principles in real time: absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology.

[0038] The processing module is used to process the absolute spatial position data of the drill bit and the relative attitude data of the mast through a data fusion algorithm. By utilizing the spatial combination constraint relationship between the two, the measurement deviation caused by the elastic deformation of the drill rod is eliminated, and the comprehensive verticality reflecting the actual borehole is obtained.

[0039] The determination module is used to perform time-series correlation analysis between the overall verticality and real-time drilling operating parameters, and to determine the diagnostic information of the cause of the current vertical deviation using preset deviation pattern recognition rules.

[0040] Thirdly, embodiments of the present invention provide a rotary drilling rig, including: the vertical judgment device described in the second aspect.

[0041] Fourthly, embodiments of the present invention provide a computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the drilling vertical determination method provided in any embodiment of the present invention.

[0042] This invention provides a method, device, and storage medium for determining verticality while drilling. It synchronously acquires at least two types of vertical-related data based on different measurement principles in real time: absolute spatial position data of the drill bit obtained using spatial positioning technology, and relative mast attitude data obtained using inertial measurement technology. The absolute spatial position data of the drill bit and the relative mast attitude data are processed using a data integration algorithm. Utilizing the spatial geometric constraints between the two, measurement deviations caused by the elastic deformation of the drill pipe are eliminated, resulting in a comprehensive verticality reflecting the actual borehole axis. The comprehensive verticality is then correlated with drilling condition parameters over time. Using preset deviation pattern recognition rules, diagnostic information determining the cause of the current verticality deviation is obtained. Thus, by synchronously acquiring data from two different principles—spatial positioning and inertial measurement—a mutually verifying observation system is constructed, ensuring the reliability and complementarity of the data from the source. Secondly, by utilizing the spatial geometric constraints between the two types of data, a data fusion algorithm separates the overall mast tilt angle from the drill pipe elastic deformation, fundamentally eliminating measurement distortion caused by drill pipe bending. This yields a comprehensive verticality reflecting the true borehole axis. Furthermore, by performing time-series correlation analysis between the comprehensive verticality and operating parameters such as rotational speed and drilling pressure, and matching preset deviation pattern rules, the system can intelligently diagnose the causes of deviations (such as obstacles, formation changes, etc.), achieving a leap from measurement to diagnosis. Ultimately, this embodiment transforms verticality control from passive monitoring relying on human experience to proactive early warning and guidance based on precise and intelligent analysis, thereby fundamentally ensuring borehole quality and improving construction efficiency. In other words, this embodiment effectively solves the problem of verticality measurement distortion caused by drill pipe elastic deformation in the prior art. By fusing observation data from different principles, it accurately restores the actual borehole axis state. Simultaneously, the system achieves intelligent diagnosis of the causes of vertical deviations, accurately distinguishing between different inducing factors such as geological, mechanical, or operational factors. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating a drilling verticality determination method according to an embodiment of the present invention.

[0044] Figure 2 This is another flowchart illustrating the drilling verticality determination method provided in an embodiment of the present invention;

[0045] Figure 3 This is another flowchart illustrating the drilling verticality determination method provided in one embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of the structure of a drilling verticality determination device provided in an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of the structure of a rotary drilling rig provided in an embodiment of the present invention. Detailed Implementation

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] It should be noted that rotary drilling rigs, as core equipment in modern pile construction, have a critical indicator that directly affects the quality, bearing capacity, and safety of the pile body, with the verticality of the drilled borehole being a key factor. In projects with extremely high verticality requirements, such as high-rise buildings, bridges, and wind power foundations, how to monitor and control the borehole verticality in real time and accurately has always been a key focus and challenge in the field of intelligent construction technology and equipment.

[0051] Currently, the industry primarily relies on tilt sensors (such as biaxial tiltmeters) mounted on the drilling mast to monitor the verticality of rotary drilling rigs. This technology indirectly infers the verticality of the borehole by measuring the tilt angle of the mast relative to the direction of gravity. However, this method has inherent limitations: First, it measures the posture of the "mast," not the posture of the "actual borehole axis." During drilling, due to the unbalanced forces generated by the interaction between the drill bit and the formation, the friction between the drill rod and the borehole wall, and the weight of the drill rod itself, the slender drill rod undergoes significant elastic bending deformation. This results in the mast possibly being vertical, but the drill rod and drill bit deviating from the design axis, forming what is known as "hole inclination," which cannot be detected by a single mast tilt measurement. Second, this technology is an indirect, static approximation measurement, unable to distinguish whether the verticality deviation stems from inaccurate mast leveling, initial bending of the drill rod, or dynamic deviation caused by geological changes during drilling. The measurement results are one-sided and lagging.

[0052] To obtain the spatial position of the drill bit, some advanced solutions attempt to incorporate satellite positioning technology, such as installing RTK positioning modules on the drill bit or mast top. However, single spatial positioning data is affected by signal obstruction, multipath effects, etc., and its instantaneous accuracy and reliability are difficult to consistently meet the requirements of high-precision verticality control in complex construction scenarios. More importantly, both single inertial measurement and single spatial positioning only provide "one side" of verticality information, failing to integrate the advantages of data from two different physical principles, and thus unable to construct a robust observation model that can resist local interference and reflect the true state of the borehole axis.

[0053] Furthermore, most existing monitoring systems are limited to "display" and "alarm" functions, lacking in-depth intelligent analysis capabilities. When vertical deviation occurs, the system can only provide an over-limit alarm, but cannot automatically diagnose the root cause of the deviation (such as encountering isolated rocks, entering soft-hard interbedded formations, or mismatched operating parameters). This makes it difficult for operators to take quick and targeted measures, often relying on personal experience for trial adjustments, which is inefficient and has uncertain results, making it difficult to achieve the leap from "passive monitoring" to "proactive prevention and control."

[0054] Therefore, there is an urgent need for a method for judging verticality while drilling that can integrate multi-source heterogeneous data, eliminate measurement errors caused by drill rod deformation, accurately reflect the state of the borehole axis, and intelligently diagnose the causes of deviations, so as to fundamentally improve the quality control capability and intelligence level of rotary drilling rig construction.

[0055] like Figure 1 As shown, an embodiment of the present invention provides a method for determining drilling verticality, the method comprising the following steps:

[0056] Step 101: Real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles: absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology.

[0057] It should be noted that this step can be achieved using multiple sensor systems deployed on the rotary drilling rig. For example, a first satellite positioning antenna and a second satellite positioning antenna can be installed at the top and bottom of the drilling rig mast, respectively, forming a measurement baseline; an inertial measurement unit (IMU) can be rigidly fixed to the main body of the mast, and during drilling, a unified timing system can control and synchronously trigger the above two types of sensors to collect data.

[0058] Among them, space positioning technology can refer to carrier phase differential positioning technology (such as BeiDou / GNSS RTK). This space positioning technology receives navigation satellite signals and uses differential correction information provided by a reference station to calculate the three-dimensional coordinates of the antenna phase center in the Earth coordinate system in real time.

[0059] Among them, the absolute spatial position data of the drill bit can refer to the real-time three-dimensional coordinates of the center point of the drill bit in the Earth coordinate system obtained by geometric calculation through the above-mentioned spatial positioning technology and combined with the mechanical size parameters of the drilling rig, such as mast height and drill rod length. This data is absolute, that is, its reference frame is a geodetic reference frame independent of the drilling rig itself, and directly represents the actual position of the drill bit in global or regional space.

[0060] Inertial measurement technology refers to the use of, for example, microelectromechanical systems (MEMS) inertial measurement units (IMUs), which typically include a three-axis accelerometer and a three-axis gyroscope. By sensing its own specific force and angular velocity, it measures the motion and attitude changes of its carrier (such as a mast). This technology does not rely on external signals and has high dynamic response characteristics.

[0061] The mast relative attitude data refers to the attitude information of the mast relative to the local horizontal plane (direction of gravity) or inertial space, output by the aforementioned inertial measurement unit. It typically includes at least the roll and pitch angles, and may also include angular velocity. This data is relative, meaning it describes the degree and trend of the mast's tilt relative to gravity or its initial attitude, rather than its absolute orientation in the geodetic coordinate system.

[0062] Understandably, step 101 can obtain the absolute position of the drill bit in its basic coordinate system using satellite positioning technology, while simultaneously sensing the relative tilt of the mast relative to the direction of gravity using inertial measurement technology. This simultaneous acquisition of these two types of data in space and time provides a heterogeneous, complementary observational basis with geometrically constrained relationships for subsequent fusion processing.

[0063] Step 102: The absolute spatial position of the drill bit and the relative attitude of the mast are processed by a data fusion algorithm. The spatial geometric constraint relationship between the two is used to eliminate the measurement deviation caused by the elastic deformation of the drill rod and obtain the comprehensive verticality that reflects the actual borehole axis.

[0064] It should be noted that this step can be completed in the embedded processing unit. The system takes the synchronously acquired absolute spatial position data of the drill bit and the relative attitude data of the mast as input and feeds them into a pre-established data fusion algorithm model (such as a Kalman filter) based on state estimation for processing. The core of this algorithm is a system state equation that includes the rigid body motion of the mast and the elastic deformation dynamics of the drill pipe. Through iterative calculation, the algorithm continuously verifies and corrects the results using the spatial geometric constraints between the two types of observation data, and finally outputs an optimal estimate, namely the comprehensive verticality.

[0065] The data fusion algorithm can define unknown quantities that need to be estimated, such as the true tilt angle of the mast and the deformation position of each section of the drill pipe, as state variables; establish system state equations describing how the state variables change over time and observation equations describing the relationship between the observed data and the state variables; then the algorithm performs two steps at each time step: prediction and update. The prediction can be based on the state at the previous time step and the model to estimate the current state; the update can use the actual observation data at the current time step, i.e., spatial position and attitude data, to correct the predicted value, and obtain the optimal estimate of the state by minimizing the covariance of the estimation error.

[0066] Spatial geometric constraints refer to the fixed geometric relationships between the mast base, mast top, and drill bit, determined by the drilling rig's mechanical structure. Under ideal rigidity conditions, the spatial position of the mast top can be uniquely determined geometrically by the mast base position and mast attitude (length and inclination), and the drill bit position can be deduced from the mast attitude and drill string length. This inherent geometric chain provides the physical constraints and verification basis for fusing absolute position (from satellite positioning) and relative attitude (from IMU) data.

[0067] It is important to understand that during drilling, the drill pipe is not an ideal rigid body. When subjected to huge axial drilling pressure, torsional torque, friction and collision with the borehole wall, and its own gravity, these forces will cause the slender drill pipe to undergo recoverable bending and stretching deformation.

[0068] Furthermore, the traditional single tilt sensor solution assumes that the mast attitude is directly equal to the borehole axis attitude. However, the elastic deformation of the drill rod will cause the actual spatial position of the drill bit to deviate from the theoretical position calculated from the mast attitude and the nominal drill rod length. Therefore, calculating verticality based solely on the mast attitude, i.e. the mast relative attitude data mentioned above, will systematically ignore the deviation caused by the drill rod deformation, resulting in distorted measurement results and mistakenly judging a bent borehole axis as vertical.

[0069] The actual borehole axis refers to the true borehole axis derived from the drill bit center point, taking into account drill rod deformation. The overall verticality refers to the degree of inclination of this actual axis relative to the designed vertical axis, usually indicated by an angle and borehole bottom offset. It can be understood that the overall verticality is the most accurate and reliable estimate obtained after data integration algorithms, collaboratively utilizing absolute spatial position and inertial relative attitude information, and eliminating the influence of errors such as drill rod deformation. It reflects the direct quality state of the borehole.

[0070] Understandably, this step solves the problem of verticality measurement distortion caused by drill rod bending in traditional single-sensor measurements. By intelligently fusing absolute position data and relative attitude data based on different physical principles, and using their inherent spatial geometric constraints for mutual verification and compensation, it can effectively eliminate or counteract the interference of drill rod elastic deformation on the final verticality reading, directly producing a more realistic and reliable comprehensive verticality that reflects the actual state of the borehole axis. This comprehensive verticality can change the reference object for vertical monitoring from the mast to the borehole axis, providing a reliable data foundation for subsequent precise construction control and intelligent diagnosis, and providing technical support for achieving high-precision borehole quality control.

[0071] Step 103: Perform time-series correlation analysis between the overall verticality and drilling condition parameters, and use the preset deviation pattern recognition rules to determine the diagnostic information of the cause of the current verticality deviation.

[0072] Understandably, this step can be executed on an in-vehicle terminal or remote server with edge computing capabilities. The system continuously receives the comprehensive verticality time-series data stream from step 102, while simultaneously acquiring the drilling condition parameter time-series data stream from the drilling sensor network. These two types of time-series data are fed into a deviation pattern recognition engine in real time. This engine has a built-in preset deviation pattern recognition rule base or model. By running pattern matching, time series correlation, or lightweight machine learning inference algorithms, it compares and matches the current verticality and condition data features with typical patterns in the rule base in real time. Once a highly matching pattern is identified, the system immediately generates and outputs the corresponding diagnostic information, which is communicated to the operator or control system through a human-machine interface such as a screen pop-up or voice prompt, or through a data link such as uploading to a management platform.

[0073] Drilling condition parameters refer to physical quantities that directly reflect the drilling operation status and stress environment of the rotary drilling rig. Here, drilling condition parameters mainly refer to at least one of the following: real-time monitored power head rotation speed, drilling pressure or oil pressure, current drilling depth, and depth change rate. The depth change rate can characterize the drilling speed. Of course, in some implementations, drilling condition parameters may also include torque and vibration amplitude. It is understood that these drilling condition parameters collectively characterize the dynamic process of how the drill bit interacts with the formation.

[0074] The deviation pattern recognition rule can be understood as a set of logical judgments or data models that associate specific verticality deviation characteristics with specific working condition parameters and their changing trends. This deviation pattern recognition rule can be pre-established in the system before its actual use through methods such as summarizing engineering experience, analyzing historical construction big data, or training with machine learning; it can be a knowledge base within the system. For example, a rule could correspond to "If, under moderate drilling pressure, the verticality exhibits rapid, small-amplitude periodic fluctuations, accompanied by fluctuations in rotational speed," then the pattern recognition would be "The drill bit is jumping in a fractured and heterogeneous stratum."

[0075] It is understandable that diagnostic information can be a qualitative or semi-quantitative judgment based on pattern recognition rules regarding the root cause of the current vertical deviation. It is also understandable that diagnostic information is not simply an alarm indicating excessive verticality, but rather includes specific explanations with identifiable causes. For example, the diagnostic information could suggest that the current deviation is primarily caused by entering a soft-hard geological interface, with hard rock located on the left side of the borehole; or it could indicate a suspected encounter with a local obstacle on the drill bit's side, such as a boulder; or it could suggest that excessive drill pressure has caused slight instability in the drill pipe.

[0076] Understandably, diagnostic information can provide a direct basis for subsequent targeted decision-making and treatment.

[0077] Understandably, this step enables real-time output from verticality deviation to its root cause, transforming verticality control from passive monitoring and alarming to proactive intelligent diagnosis. By correlating changes in verticality with drilling parameters during construction, the system can automatically and quickly pinpoint the root cause of problems, providing operators with precise operational guidance. For example, if encountering hard formations, it suggests adjusting the drilling pressure, or it provides clear adjustment guidelines for the automatic control system. For instance, if the geological dip causes leftward deviation, it initiates a fine-tuning to the right. This reduces reliance on operator experience, shortens problem response time, and effectively prevents borehole deviation quality accidents caused by misjudgment or delayed handling, fundamentally improving the level of intelligent construction and the first-time borehole success rate.

[0078] In summary, this embodiment first constructs a mutually verifying observation system by simultaneously collecting data from two different principles: spatial positioning and inertial measurement. This ensures the reliability and complementarity of the data from the source. Second, utilizing the spatial geometric constraints between the two types of data, a data fusion algorithm separates the overall mast tilt from the elastic deformation of the drill pipe, fundamentally eliminating measurement distortion caused by drill pipe bending. This yields a comprehensive verticality reflecting the true borehole axis. Furthermore, by performing time-series correlation analysis between the comprehensive verticality and operating parameters such as rotational speed and drilling pressure, and matching preset deviation pattern rules, the system can intelligently diagnose the causes of deviations (such as obstacles, formation changes, etc.), achieving a leap from measurement to diagnosis. Finally, this embodiment transforms verticality control from passive monitoring relying on human experience to proactive early warning and guidance based on precise and intelligent analysis, thereby fundamentally ensuring borehole quality and improving construction efficiency. In other words, the embodiments of this application effectively solve the problem of verticality measurement distortion caused by the elastic deformation of the drill pipe in the prior art. By integrating observation data from different principles, the actual borehole axis state is realistically restored. At the same time, the system realizes intelligent diagnosis of the cause of vertical deviation and can accurately distinguish different causes such as geological, mechanical or operational factors.

[0079] In some embodiments, the absolute control position data of the drill bit can be obtained through a dual-antenna satellite positioning system;

[0080] In step 101, the real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles includes:

[0081] Using carrier phase differential technology, the precise three-dimensional coordinates of the two antennas are calculated in real time to form a spatial baseline vector representing the mast axis. The two antennas are the first satellite positioning antenna and the second satellite positioning antenna, which are respectively installed at the top and bottom of the mast.

[0082] By combining the mechanical structural parameters of the mast with the length of the drill string, the real-time absolute spatial position data of the drill bit is calculated.

[0083] as well as,

[0084] The mast's relative attitude data is obtained through a miniature inertial measurement module mounted on the mast, which includes at least a three-axis accelerometer and a three-axis gyroscope.

[0085] In step 101, at least two types of vertical correlation data based on different measurement principles are collected in real time, including:

[0086] Real-time measurement of the mast's tilt angle relative to the gravity vector and the change in the angular velocity of the tilt angle.

[0087] For example, a first satellite positioning antenna and a second satellite positioning antenna are rigidly mounted at the top and bottom of the rotary drilling rig mast, or more specifically, at the joints near the bottom where they are rigidly connected to the mast, respectively, forming a spatial measurement baseline. A miniature inertial measurement unit (MIMU), integrating a three-axis accelerometer and a three-axis gyroscope, is rigidly mounted at a stable position in the middle of the mast or near the base. All sensors can be connected via cables or a vehicle network to an onboard embedded industrial computer, such as a smart terminal, which performs power supply, synchronous data acquisition, data processing, and data fusion.

[0088] Understandably, the two satellite positioning antennas here synchronously receive signals from global navigation satellite systems such as BeiDou and GPS. For example, using carrier phase differential technology, the precise three-dimensional coordinates of the two antennas are calculated in real time to form a spatial baseline vector representing the mast axis. This includes: the aforementioned smart terminal receiving carrier phase differential correction data from a nearby BeiDou reference station in real time via a mobile network; using carrier phase differential technology to calculate the three-dimensional coordinates of the phase center of the first antenna and the phase center of the second antenna in the Earth coordinate system, for example, (X1, Y1, Z1) and (X2, Y2, Z2); subsequently, the spatial baseline vector is calculated based on the two coordinate points, which can accurately describe the spatial direction and length of the mast axis at the current moment. By combining the mechanical structural parameters of the mast with the length of the drill string, the real-time absolute spatial position data of the drill bit is calculated. This includes: combining the pre-input system with precisely measured mechanical parameters such as the mast structural height and the total length of the drill string, and using the bottom antenna coordinates as a reference, geometric calculation is performed along the spatial baseline vector direction to finally obtain the real-time absolute three-dimensional coordinates of the drill bit center point, which is the absolute spatial position data of the drill bit.

[0089] For example, real-time measurement of the mast's tilt angle and angular velocity relative to the gravity vector can include: using a miniature inertial unit (MIMU) to measure the three-axis specific force (e.g., acceleration) and three-axis angular velocity in its body coordinate system at a high frequency (e.g., 100Hz); then processing the raw inertial data using an attitude calculation algorithm in a smart terminal (e.g., based on complementary filtering or gradient descent); using accelerometer data to sense the direction of the gravity vector and calculating the mast's roll and pitch angles (i.e., tilt angle) relative to the local horizontal plane; simultaneously, fusing angular velocity data measured by gyroscopes to provide the dynamic rate of change of the tilt angle, correcting errors in pure accelerometer calculations under dynamic conditions, and outputting stable, highly dynamic response mast attitude data, i.e., tilt angle and its angular velocity.

[0090] It should be noted that the smart terminal provides a unified timestamp for all sensors, ensuring that spatial positioning data and inertial measurement data are strictly synchronized in time, laying the foundation for subsequent accurate data fusion.

[0091] Thus, in this embodiment, the spatial baseline vector directly calculated by the dual-antenna RTK positioning technology can accurately reflect the true three-dimensional orientation of the mast in the geodetic coordinate system at the centimeter level. This reduces the limitation of single-antenna positioning, which can only obtain a single point position and cannot directly determine the axis direction, providing the most intuitive spatial geometric reference for verticality determination. Furthermore, by using, for example, a miniature inertial measurement unit (MIMU), the system can respond to the instantaneous swaying and vibration of the mast at extremely high frequencies, providing angular velocity information that is lacking in satellite positioning technology. This compensates for the limitations of RTK technology, such as limited update rate and data interruption during brief signal blockages, ensuring... This confirms the continuity of monitoring. Furthermore, RTK data provides an absolute, accurate, but slightly slower-updating spatial reference; MIMU data provides a relative, continuous, and highly dynamic attitude change. By combining the two, we can grasp both the overall absolute position and capture instantaneous dynamic details. Moreover, under good signal conditions, the mast tilt angle calculated from the RTK baseline vector can be cross-compared with the tilt angle calculated by the MIMU. If both are known within the tolerance range, they mutually verify the reliability of the data. If a large difference occurs, it can trigger a system self-check alarm, indicating that there may be sensor failure or abnormal interference, thereby enhancing the robustness and reliability of the entire monitoring system.

[0092] Finally, the embodiments of this application obtain at least two types of vertical correlation data based on different measurement principles, which can provide high-quality observation inputs with clear physical meaning for advanced data fusion algorithms in subsequent steps. The inclined installation position and known mechanical parameters enable the spatial geometric constraints to be expressed very accurately in the data model, thereby ensuring that the drill pipe deformation error can be effectively removed and the true comprehensive verticality can be obtained.

[0093] In some embodiments, please refer to Figure 2 ,like Figure 2 As shown, in step 102, the absolute spatial position data of the drill bit and the relative attitude data of the mast are processed by a data fusion algorithm. Utilizing the spatial geometric constraints between the two, the measurement deviation caused by the elastic deformation of the drill pipe is eliminated, resulting in a comprehensive verticality reflecting the actual borehole axis, including:

[0094] Step 1021: Use the absolute spatial position data of the drill bit as an external direct observation;

[0095] Step 1022: Use the mast relative attitude data as internal motion constraint observations;

[0096] Step 1023: Based on the mechanical structure model of the drilling rig, establish the system state equations that include the overall tilt angle state of the mast and the elastic deformation state of the drill pipe segments;

[0097] Step 1024: The system state equation is filtered and iterated using a state estimation algorithm to estimate and separate the contributions of the overall mast tilt angle and the drill pipe elastic deformation to the vertical measurement in real time, so as to extract the error component caused by the drill pipe elastic deformation from the mast relative attitude data, and finally calculate the comprehensive verticality.

[0098] Understandably, external direct observations refer to data that directly measures the physical quantities of the target in the global coordinate system, independent of the drilling rig's mechanical structure itself. In this case, it refers to the absolute spatial position of the drill bit directly measured using satellite positioning technology, with the Earth as its reference frame and independent of the drilling rig's attitude. Internal motion constraint observations refer to data that depends on and is measured by sensors mounted on the drilling rig itself, reflecting the relative motion or attitude between mechanical components. In this case, it refers to the mast's relative attitude measured by the inertial measurement unit (IMU), which provides high-frequency, continuous motion change signals. However, the measurements are relative, and their accuracy accumulates over time.

[0099] Here, the mechanical structure model of the drilling rig refers to a simplified mathematical model used to describe the geometric relationship, mass distribution, and elastic properties of the mast-to-drill-pipe system. For example, key parameters of the mechanical structure model, such as mast height, hinge point location, drill-pipe segment length, moment of inertia, and modulus of elasticity, can be obtained from the drilling rig's CAD design drawings, factory parameter tables, and physical test reports for the drill-pipe material, and are entered during system initialization.

[0100] The overall mast tilt angle can refer to the angle between the mast's axis and the vertical line when the mast is considered a rigid body. It should be noted that the tilt angle mentioned above is the actual value read by the inertial sensor. This tilt angle is measured by the IMU mounted on the mast when the drill pipe undergoes elastic bending. This tilt angle is a mixture of the overall mast tilt angle and the localized minute rotation angle transmitted from the connection between the mast and the drill pipe due to drill pipe deformation; it differs from the overall mast tilt angle.

[0101] Understandably, discretizing the continuous drill pipe into several segments, such as every 3-5 meters, and modeling each segment as an elastic beam element, is a segmented approach. This segmentation is intended to approximate the bending of an infinite-degree-of-freedom continuous body using finite-dimensional state variables, such as the displacement and rotation angle of each segment. Understandably, the more segments there are, the more accurate the model becomes, but the greater the computational load.

[0102] Understandably, the system state equation can be a set of equations that are usually difference or differential equations. Mathematically, it defines how the system state variables evolve from the previous moment to the current moment, reflecting the dynamic laws of the system. For example, how the tilt angle changes due to the drilling rig's leveling action, and how the drill rod deformation changes due to changes in drilling pressure.

[0103] Understandably, a state estimation algorithm can be a mathematical method for optimally estimating the internal state of a system with uncertainty, which cannot be directly measured, such as drill pipe deformation. Filtering iteration can refer to the cyclical process of the algorithm from prediction to update. In each cycle, the algorithm uses the model to predict the state, and then uses the new observation data to update and correct the prediction. This process is repeated to make the estimate more and more accurate.

[0104] Understandably, separating the error component caused by the elastic deformation of the drill pipe from the mast relative attitude data can be achieved by using an algorithm to separate the overall mast tilt signal mixed with the local additional tilt signal caused by the drill pipe deformation in the IMU observations, retaining only the former as the basis for calculating verticality. This is because verticality is the tilt of the entire borehole axis, which is mainly determined by the overall tilt of the mast. Although the local bending of the drill pipe will affect the position of the drill bit, it will not change the macroscopic orientation of the borehole. Therefore, the IMU data contains this part of the false signal of local bending. If it is not separated, it will lead to the distortion of the verticality calculation result, mistakenly taking the bending of the drill pipe as the tilt of the entire hole. After separation, what is obtained is the overall mast tilt angle that truly represents the macroscopic orientation of the borehole axis, thus obtaining the comprehensive verticality that reflects the quality of the borehole.

[0105] Thus, this embodiment of the application solves a key pain point in engineering monitoring by indirectly and accurately estimating the internal elastic deformation state of the drill pipe, which cannot be directly measured by sensors, through the fusion of algorithms and observable data. Then, through state estimation and separation technology, the interference components introduced by the elastic deformation of the drill pipe are identified and removed from the IMU data, so that the overall tilt angle of the mast used to determine verticality is not affected by this error, thereby obtaining a comprehensive verticality that reflects the true hole axis orientation, laying a reliable data foundation for subsequent steps of accurate working condition correlation and fault diagnosis.

[0106] In some embodiments, in step 103, based on the mechanical structure model of the drilling rig, a system state equation is established that includes the overall tilt angle state of the mast and the elastic deformation displacement state of the drill pipe segments, including:

[0107] Based on the mechanical structure model of the drilling rig, the mechanical structure parameters of the drilling rig, the cross-sectional characteristic parameters of the drilling rig, and the real-time drilling depth and real-time drilling load are obtained. The mechanical structure model will be dynamically updated based on the real-time drilling depth, the cross-sectional characteristics of the drill rod, and the real-time drilling load.

[0108] Based on the obtained parameters, the mast is modeled as a rigid body rotating about its bottom hinge point, and the drill pipe is discretized into multiple elastic beam elements connected in sequence.

[0109] Based on the connection conditions and force balance relationship between the rigid body and the elastic beam element, the system state equation is constructed with the overall tilt angle and angular velocity of the mast and the nodal displacement and rotation angle of each elastic beam element as state variables.

[0110] Thus, in this embodiment, by dynamically updating the model parameters, a digital twin that can reflect the drill string assembly and stress state in real time is constructed, making the model highly matched with the actual working conditions. This significantly improves the accuracy and stability of verticality state estimation and can adapt to different drill string specifications and formation changes, ensuring robustness under all working conditions. At the same time, the deep mechanical state information of the drill string provided by this model lays the foundation for subsequent realization of advanced intelligent diagnostics such as drill string early warning and formation identification.

[0111] In some embodiments, please refer to Figure 3 ,like Figure 3 As shown, in step 104, a time-series correlation analysis is performed on the overall verticality and drilling condition parameters. Using preset deviation pattern recognition rules, diagnostic information determining the cause of the current vertical deviation is obtained, including:

[0112] Step 1041: Construct an association matrix based on historical drilling condition parameters. The association matrix is ​​used to define the mapping relationship between different comprehensive verticality deviation time series patterns and drilling condition parameter time series patterns.

[0113] Step 1042: During the drilling process, extract the time series of the current comprehensive verticality and the time series of drilling condition parameters synchronized with the comprehensive verticality time, and combine them to form the current time series feature vector;

[0114] Step 1043: Match the current time series feature vector with the correlation matrix to identify the best-matching deviation pattern;

[0115] Step 1044: Determine the cause of the current vertical deviation by mapping the identified deviation pattern and output diagnostic information.

[0116] It should be noted that the association matrix is ​​a trained knowledge base or model that stores the mapping relationship between the feature vectors of various deviation patterns and their causes. In fact, it represents a lookup table from pattern to cause.

[0117] For example, the association matrix can exist in the following exemplary tabular form. It should be noted that the following parameters are also exemplary parameters.

[0118]

[0119] Understandably, the comprehensive verticality deviation time-series pattern can refer to the morphological characteristics of the comprehensive verticality value changing over time. For example, a linear growth pattern where it increases linearly from 0.1° to 0.5° within 5 seconds, or a pulse pattern where a 0.3° peak appears within 1 second followed by a rapid decline. The drilling condition parameter time-series pattern can refer to the combined morphological characteristics of one or more condition parameters changing over time. For example, a high drill pressure-reduced rotational speed pattern where drill pressure remains high while rotational speed decreases, or a stalled drill pattern where the rate of change of drilling depth (speed) suddenly decreases to near zero.

[0120] Here, the best-matching deviation pattern refers to the preset pattern that has the highest similarity to the verticality-operating condition joint time-series features presented by the current real-time data, calculated by the algorithm.

[0121] Thus, in this embodiment of the application, by establishing a time-series correlation and pattern recognition mechanism between comprehensive verticality and drilling condition parameters, a fundamental breakthrough has been achieved from comprehensive verticality over-limit alarm to intelligent diagnosis of causes. Based on accurate diagnosis, the system can guide operators or automatic control systems to quickly collect targeted measures, thereby improving decision-making efficiency and hole formation quality.

[0122] For example, drilling parameters include at least the power head rotation speed, drilling pressure, current drilling depth, and depth change rate. The power head rotation speed affects the drill bit's rock-breaking method and stability; the drilling pressure affects the drill pipe's axial pressure and bending tendency; and the drilling depth and depth change rate are related to formation changes and drilling efficiency. Thus, through comprehensive analysis of multi-dimensional, dynamic parameters, the reliability and accuracy of the final results can be guaranteed.

[0123] In some embodiments, in step 104, diagnostic information determining the cause of the current verticality deviation is obtained using preset deviation pattern recognition rules, including:

[0124] Using a preset deviation pattern recognition rule, a classification model trained by machine learning based on historical borehole data is used to associate and map the temporal features of vertical deviation with the change patterns of working condition parameters, and output the diagnostic information. The classification model is an end-to-end model based on a deep neural network. Its input is the comprehensive verticality time series data and the corresponding working condition parameter time series data within a fixed time window, and the output is the probability distribution of each cause type.

[0125] The classification model can be trained offline based on a large amount of historical drilling data collected by the system, including time series data of comprehensive verticality under different working conditions, time series data of corresponding drilling working condition parameters, and actual cause labels labeled by experts or verified afterward.

[0126] Of course, the classification model can also be trained online by using a sliding window during real-time drilling, where the system extracts the most recent fixed-duration (e.g., 30 seconds) comprehensive verticality time-series data and strictly synchronized drilling condition parameter time-series data in a sliding window manner; these two sets of time-series data are then concatenated and normalized to form a standardized input vector, which is fed into the pre-trained classification model; then the model performs forward computation and directly outputs a probability distribution vector, where each element represents the probability of a preset cause type (e.g., initial mast leveling error, encountering an obstacle, etc.); finally, the system determines the most likely cause of the current verticality deviation according to a preset strategy (e.g., selecting the cause corresponding to the highest probability value), and outputs diagnostic information containing this judgment.

[0127] Thus, in this embodiment, by introducing a classification model based on deep neural networks, the verticality deviation diagnosis is upgraded from "pattern matching" that relies on fixed rules to "intelligent identification" based on data drive. It can automatically discover and utilize complex causal patterns hidden in historical data to achieve high-precision, adaptive diagnosis of multiple causes such as mast leveling errors, mechanical failures, geological anomalies, and improper operation, significantly improving the system's intelligence level, diagnostic accuracy, and adaptability to complex working conditions.

[0128] In some embodiments, the diagnostic results indicated by the diagnostic information include at least one of the following categories: initial mast leveling error, guide mechanism clearance sway, encounter with obstacles or hard interlayers, drilling at the interface of soft and hard formations, and instability of drilling pressure and rotation speed.

[0129] The method further includes:

[0130] Based on the diagnostic information, a preset calibration strategy library is matched to generate and output targeted operation guidance information or direct control commands.

[0131] If the cause diagnosis indicates that the gradual deviation is caused by drilling at the interface between soft and hard formations, the generated instruction is to send a continuous, small-amplitude reverse compensation signal to the automatic leveling system of the drilling rig mast.

[0132] If the cause diagnosis indicates that the momentary impact deviation was caused by encountering an obstacle or hard interlayer, the generated instruction is an alarm message to prompt the operator, wherein the alarm message includes a reminder message to raise the drill bit and switch the drilling mode.

[0133] For example, in practical applications, based on actual engineering conditions, the preset deviation patterns include at least the following common causes:

[0134] Initial mast leveling error: This refers to a systematic deviation caused by inaccurate mast leveling before drilling begins. This error causes the borehole axis to deviate from the designed vertical line during the initial drilling stage and continues to cause a fixed directional shift during subsequent drilling, thus constituting a systematic deviation cause.

[0135] Guide mechanism clearance sloshing: This refers to the uncontrolled micro-displacement caused by assembly clearances or wear in the guide mechanisms of mechanical components such as the drilling mast and power head, during drilling vibrations or rod changing operations. This leads to irregular micro-oscillations or drifts of the borehole axis, and is considered a mechanical condition-related factor.

[0136] Encountering obstacles or hard interlayers: This refers to the drill bit suddenly hitting a localized high-strength object such as a boulder, boulders, concrete obstacle, or hard rock layer during drilling. This will generate an instantaneous lateral impact or huge resistance on the drill bit, causing a sudden, step-like change in verticality, which is a sudden geological trigger.

[0137] Drilling at the interface between soft and hard formations: This refers to the process where the drill bit moves from a formation with weaker mechanical properties (such as clay) into a formation with significantly different mechanical properties (such as rock), especially when the interface is inclined. Due to the uneven resistance of the formation on both sides of the drill bit, the borehole axis will experience a continuous and gradual directional deviation towards the softer side, which is a gradual geological inducement.

[0138] Unstable drilling pressure and rotation speed: This refers to situations where improper operation or automatic control failure results in excessively high or low drilling pressure, or a rotation speed that is mismatched with the formation. This can lead to drill pipe buckling instability or abnormal drill bit slippage at the bottom of the hole, causing irregular changes in verticality accompanied by drastic fluctuations in parameters. This is considered an operationally induced cause.

[0139] Thus, in this embodiment, by automatically associating the intelligent diagnostic results with a preset correction strategy library, a closed-loop control from "intelligent diagnosis" to "precise handling" is achieved. Based on the specific causes diagnosed (such as formation interfaces or obstacles), the system can automatically generate and execute the most suitable compensation instructions or operational suggestions, greatly improving the timeliness and accuracy of the correction response. This not only frees operators from complex decision-making but also effectively prevents borehole deviation accidents through automated control, ensuring borehole quality and construction safety.

[0140] In another embodiment, such as Figure 4 As shown, a drilling verticality determination device is also provided, comprising:

[0141] The multi-source acquisition module 41 is used to acquire at least two types of vertically related data based on different measurement principles in real time: absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology.

[0142] Processing module 42 is used to process the absolute spatial position data of the drill bit and the relative attitude data of the mast through a data fusion algorithm. By utilizing the spatial geometric constraint relationship between the two, the measurement deviation caused by the elastic deformation of the drill rod is eliminated, and the comprehensive verticality reflecting the actual borehole is obtained.

[0143] The determination module 43 is used to perform time-series correlation analysis between the comprehensive verticality and drilling condition parameters, and to determine the diagnostic information of the cause of the current vertical deviation using preset deviation pattern recognition rules.

[0144] Optionally, the absolute spatial position data of the drill bit is obtained through a dual-antenna satellite positioning system; the relative attitude data of the mast is obtained through a miniature inertial measurement module installed on the mast, the miniature inertial measurement module including at least a three-axis accelerometer and a three-axis gyroscope;

[0145] The multi-source acquisition module 41 is also used for:

[0146] Using carrier phase differential technology, the precise three-dimensional coordinates of the two antennas are calculated in real time to form a spatial baseline vector representing the mast axis. The two antennas are a first satellite positioning antenna and a second satellite positioning antenna respectively installed at the top and bottom of the mast.

[0147] By combining the mechanical structural parameters of the mast with the length of the drill bit, the real-time absolute spatial position data of the drill bit is calculated.

[0148] as well as,

[0149] Real-time measurement of the mast's tilt angle relative to the gravity vector and the change in the angular velocity of that tilt angle.

[0150] Optionally, the processing module 42 is further configured to:

[0151] The absolute spatial position data of the drill bit is used as an external direct observation value;

[0152] The relative attitude data of the mast is used as the observation value of the internal motion constraint.

[0153] Based on the mechanical structure model of the drilling rig, a system state equation is established that includes the overall tilt angle state of the mast and the elastic deformation displacement state of the drill pipe segments.

[0154] The system state equation is filtered and iterated by a state estimation algorithm to estimate and separate the contributions of the overall mast tilt angle and the drill pipe elastic deformation to the verticality measurement in real time. This allows the error component caused by the drill pipe elastic deformation to be extracted from the mast relative attitude data, and the overall verticality can be calculated in the end.

[0155] Optionally, the processing module 42 is specifically used for:

[0156] Based on the mechanical structure model of the drilling rig, the mechanical structure parameters of the drilling rig, the cross-sectional characteristic parameters of the drill rod, and the real-time drilling depth and real-time drilling load are obtained. The mechanical structure model is dynamically updated based on the real-time drilling depth, the cross-sectional characteristics of the drill rod, and the real-time drilling load.

[0157] Based on the obtained parameters, the mast is modeled as a rigid body rotating about its bottom hinge point, and the drill pipe is discretized into multiple elastic beam elements connected in sequence.

[0158] Based on the connection conditions and force balance between the rigid body and the elastic beam unit, a system state equation is constructed with the overall tilt angle and angular velocity of the mast, as well as the nodal displacements and rotation angles of each elastic beam unit as state variables.

[0159] Optionally, the determining module 43 is further configured to:

[0160] An association matrix is ​​constructed based on historical drilling condition parameters. The association matrix is ​​used to define the mapping relationship between different comprehensive verticality deviation time series patterns and drilling condition parameter time series patterns.

[0161] During the drilling process, the time series of the current comprehensive verticality and the time series of drilling condition parameters synchronized with the comprehensive verticality are extracted and together form the current time series feature vector.

[0162] The current time-series feature vector is matched with the correlation matrix to identify the best-matching deviation pattern;

[0163] The cause mapped by the identified deviation pattern is determined as the cause of the current vertical deviation, and the diagnostic information is output.

[0164] Optionally, the determining module 43 is further configured to:

[0165] Using a preset deviation pattern recognition rule, a classification model trained by machine learning based on historical borehole data is used to associate and map the temporal features of vertical deviation with the change patterns of operating parameters, and output the diagnostic information. The classification model is an end-to-end model based on a deep neural network. Its input is the comprehensive verticality time series data and the corresponding operating parameter time series data within a fixed time window, and the output is the probability distribution of each cause type.

[0166] Optionally, the diagnostic results indicated by the diagnostic information include at least one of the following categories: initial mast leveling error, guide mechanism clearance sway, encounter with obstacles or hard interlayers, drilling at the interface of soft and hard formations, and instability of drilling pressure and rotation speed.

[0167] The device further includes:

[0168] The generation and output module is used to match the diagnostic information with a preset correction strategy library, generate and output targeted operation guidance information or direct control commands, wherein...

[0169] If the cause diagnosis indicates that the gradual deviation is caused by drilling at the interface between soft and hard formations, the generated instruction is to send a continuous, small-amplitude reverse compensation signal to the automatic leveling system of the drilling rig mast.

[0170] If the cause diagnosis indicates that the momentary impact deviation was caused by encountering an obstacle or hard interlayer, the generated instruction is an alarm message to prompt the operator, wherein the alarm message includes a reminder message to raise the drill bit and switch the drilling mode.

[0171] The drilling verticality determination device provided in the above embodiments is illustrated only by the division of the above-described program modules during the drawing process. In practical applications, the above steps can be assigned to different program modules as needed. That is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. Furthermore, the drilling verticality determination device and the drilling verticality determination method embodiments provided in the above embodiments belong to the same concept. For details of their specific implementation process, please refer to the method embodiments, which will not be repeated here.

[0172] To achieve the above objectives, embodiments of the present invention also provide a rotary drilling rig, such as... Figure 5 As shown, the rotary drilling rig includes a computing device with the aforementioned processing capabilities. The computing device may include a processor 501 and a memory 503 connected to the processor 501 via a communication bus 502. The memory 503 is used for a drilling verticality determination program. The processor 501 is used to execute the drilling verticality determination program to implement the drilling verticality determination method described in any of the above schemes.

[0173] Optionally, the processor 501 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Here, the program executed by the processor 501 may be stored in a memory 503 connected to the processor 501 via a communication bus 502. The memory 503 may be volatile memory or non-volatile memory, or may include both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache.By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Sync Link Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM). The memory 503 described in this embodiment is intended to include, but is not limited to, these and any other suitable types of memory 503. The memory 503 in this embodiment is used to store various types of data to support the operation of the processor 501. Examples of this data include: any computer programs operated by the processor 501, such as operating systems and applications; contact data; phonebook data; messages; pictures; videos, etc. The operating system contains various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks.

[0174] In some embodiments of the present invention, the memory 503 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 503 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0175] The processor 501 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 501 or by software instructions. The processor 501 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 503, and the processor 501 reads the information in memory 503 and, in conjunction with its hardware, completes the steps of the above method. In some embodiments, the embodiments described herein can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0176] For software implementation, the techniques described herein can be achieved through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or externally.

[0177] Another embodiment of the present invention provides a computer storage medium storing an executable program. When executed by a processor 501, the executable program can implement the steps of the drilling vertical determination method applied to the computing device. For example, as... Figures 1-3 One or more of the methods shown.

[0178] In some embodiments, the computer storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0179] It should be noted that the technical solutions described in the embodiments of the present invention can be combined arbitrarily without conflict.

[0180] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A method for determining verticality while drilling, characterized in that, include: Real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles: absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology; Data fusion algorithms are used to process the absolute spatial position data of the drill bit and the relative attitude data of the mast. Utilizing the spatial geometric constraints between the two, measurement deviations caused by the elastic deformation of the drill pipe are eliminated, resulting in a comprehensive verticality reflecting the actual borehole axis. This process includes: using the absolute spatial position data of the drill bit as an external direct observation; using the relative attitude data of the mast as an internal motion constraint observation; establishing a system state equation based on the mechanical structure model of the drilling rig, encompassing the overall tilt angle state of the mast and the segmented elastic deformation displacement state of the drill pipe; filtering and iterating the system state equation using a state estimation algorithm to estimate and separate the contributions of the overall tilt angle of the mast and the elastic deformation of the drill pipe to the verticality measurement in real time, thereby extracting the error component caused by the elastic deformation of the drill pipe from the relative attitude data of the mast, and finally calculating the comprehensive verticality. The comprehensive verticality is correlated with drilling parameters over time, and diagnostic information for the cause of the current verticality deviation is determined by using preset deviation pattern recognition rules.

2. The method according to claim 1, characterized in that, The absolute spatial position data of the drill bit is obtained through a dual-antenna satellite positioning system; the relative attitude data of the mast is obtained through a miniature inertial measurement module installed on the mast, the miniature inertial measurement module including at least a three-axis accelerometer and a three-axis gyroscope; The real-time synchronous acquisition of at least two types of vertical correlation data based on different measurement principles includes: Using carrier phase differential technology, the precise three-dimensional coordinates of the two antennas are calculated in real time to form a spatial baseline vector representing the mast axis. The two antennas are a first satellite positioning antenna and a second satellite positioning antenna respectively installed at the top and bottom of the mast. By combining the mechanical structural parameters of the mast with the length of the drill bit, the real-time absolute spatial position data of the drill bit is calculated. as well as, Real-time measurement of the mast's tilt angle relative to the gravity vector and the change in the angular velocity of that tilt angle.

3. The method according to claim 1, characterized in that, The mechanical structure model based on the drilling rig establishes a system state equation that includes the overall tilt angle state of the mast and the elastic deformation displacement state of the drill pipe segments, including: Based on the mechanical structure model of the drilling rig, the mechanical structure parameters of the drilling rig, the cross-sectional characteristic parameters of the drill rod, and the real-time drilling depth and real-time drilling load are obtained. The mechanical structure model is dynamically updated based on the real-time drilling depth, the cross-sectional characteristics of the drill rod, and the real-time drilling load. Based on the obtained parameters, the mast is modeled as a rigid body rotating about its bottom hinge point, and the drill pipe is discretized into multiple elastic beam elements connected in sequence. Based on the connection conditions and force balance between the rigid body and the elastic beam unit, a system state equation is constructed with the overall tilt angle and angular velocity of the mast, as well as the nodal displacements and rotation angles of each elastic beam unit as state variables.

4. The method according to claim 1, characterized in that, The step of performing a time-series correlation analysis between the comprehensive verticality and drilling condition parameters, and using preset deviation pattern recognition rules to determine the diagnostic information for the cause of the current vertical deviation, includes: An association matrix is ​​constructed based on historical drilling condition parameters. The association matrix is ​​used to define the mapping relationship between different comprehensive verticality deviation time series patterns and drilling condition parameter time series patterns. During the drilling process, the time series of the current comprehensive verticality and the time series of drilling condition parameters synchronized with the comprehensive verticality are extracted and together form the current time series feature vector. The current time-series feature vector is matched with the correlation matrix to identify the best-matching deviation pattern; The cause mapped by the identified deviation pattern is determined as the cause of the current vertical deviation, and the diagnostic information is output.

5. The method according to claim 1, characterized in that, The diagnostic information for determining the cause of the current verticality deviation using preset deviation pattern recognition rules includes: Using a preset deviation pattern recognition rule, a classification model trained by machine learning based on historical borehole data is used to associate and map the temporal features of vertical deviation with the change patterns of operating parameters, and output the diagnostic information. The classification model is an end-to-end model based on a deep neural network. Its input is the comprehensive verticality time series data and the corresponding operating parameter time series data within a fixed time window, and the output is the probability distribution of each cause type.

6. The method according to claim 1, characterized in that, The diagnostic information indicates diagnostic results including at least one of the following categories: initial mast leveling error, guide mechanism clearance sway, encounter with obstacles or hard interlayers, drilling at the interface of soft and hard formations, and instability of drilling pressure and rotation speed. The method further includes: Based on the diagnostic information, a preset correction strategy library is matched to generate and output targeted operation guidance information or direct control commands, wherein... If the cause diagnosis indicates that the gradual deviation is caused by drilling at the interface between soft and hard formations, the generated instruction is to send a continuous, small-amplitude reverse compensation signal to the automatic leveling system of the drilling rig mast. If the cause diagnosis indicates that the momentary impact deviation was caused by encountering an obstacle or hard interlayer, the generated instruction is an alarm message to prompt the operator, wherein the alarm message includes a reminder message to raise the drill bit and switch the drilling mode.

7. A drilling verticality judgment device, characterized in that, include: The multi-source acquisition module is used to acquire at least two types of vertically correlated data based on different measurement principles in real time: absolute spatial position data of the drill bit obtained based on spatial positioning technology, and relative attitude data of the mast obtained based on inertial measurement technology. The processing module is used to process the absolute spatial position data of the drill bit and the relative attitude data of the mast through a data fusion algorithm. Utilizing the spatial geometric constraints between the two, it eliminates measurement deviations caused by the elastic deformation of the drill pipe, obtaining a comprehensive verticality reflecting the actual borehole. This includes: using the absolute spatial position data of the drill bit as an external direct observation; using the relative attitude data of the mast as an internal motion constraint observation; establishing a system state equation based on the mechanical structure model of the drilling rig, including the overall tilt angle state of the mast and the segmented elastic deformation displacement state of the drill pipe; filtering and iterating the system state equation through a state estimation algorithm, estimating and separating the contributions of the overall tilt angle of the mast and the elastic deformation of the drill pipe to the verticality measurement in real time, so as to extract the error component caused by the elastic deformation of the drill pipe from the relative attitude data of the mast, and finally calculating the comprehensive verticality. The determination module is used to perform time-series correlation analysis between the overall verticality and drilling condition parameters, and to determine the diagnostic information of the cause of the current vertical deviation using preset deviation pattern recognition rules.

8. A rotary drilling rig, characterized in that, include: The drilling verticality determination device as described in claim 7.

9. A computer storage medium, characterized in that, The computer storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, it implements the drilling vertical judgment method as described in any one of claims 1 to 6.

Images