Intelligent control method for construction and drilling parameters of bored pile in cobblestone stratum

Abstract

The invention provides a cobblestone stratum bored pile construction and drilling parameter intelligent control method, and relates to the technical field of artificial intelligence and bored pile construction, and the method comprises the following steps: arranging a sound wave emission array at the end part of a drill bit to collect cobblestone distribution information, identifying a weak connecting band as a passable area, calculating an optimal obstacle avoidance track, and setting a posture control point; and drill bit displacement, slurry injection and drill rod deformation parameters are adjusted, so that the drilling tool can intelligently pass along the obstacle avoidance track. Large cobblestones can be effectively avoided, the drilling resistance is reduced, the drilling efficiency is improved, and equipment abrasion is reduced.

Description

Technical Field

[0001] The present invention relates to artificial intelligence and bored pile construction technology, and particularly to an intelligent control method for bored pile construction and drilling parameters in cobblestone strata. Background Art

[0002] In the construction of bored piles in cobblestone strata, the traditional manual experience control method lacks the ability to perceive the drilling environment in real time, and cannot accurately obtain the formation structure characteristics and obstacle distribution information in front of the drill bit, resulting in great blindness in drilling trajectory planning and parameter optimization.

[0003] The current intelligent control system mainly adjusts the drilling parameters relying on single displacement or pressure sensing data, fails to establish the mapping relationship between the motion state of the drill tool and the formation characteristics, and cannot achieve the adaptive response to complex formation environments. At the same time, due to the lack of the fusion analysis and real-time decision-making ability of multi-source information during the drilling process, it is difficult to ensure the continuity of the drilling trajectory and the construction efficiency.

[0004] Therefore, there is an urgent need for an intelligent control method for bored pile construction and drilling parameters in cobblestone strata. Through artificial intelligence algorithms such as acoustic wave detection, feature extraction, and trajectory planning, it can achieve the precise perception of the drilling environment and the adaptive regulation of drilling parameters, and improve the intelligent level of bored pile construction. Summary of the Invention

[0005] The embodiments of the present invention provide an intelligent control method for bored pile construction and drilling parameters in cobblestone strata, which can solve the problems in the prior art.

[0006] In the first aspect of the embodiments of the present invention, an intelligent control method for bored pile construction and drilling parameters in cobblestone strata is provided, including: Set an annular acoustic wave emission array at the end of the drill bit, collect the reflection signals of the detection acoustic waves among the cobblestones, perform spectrum analysis and waveform superposition processing on the reflection signals, extract the attenuation characteristics and reflection characteristics of the acoustic waves in different media, and draw the cobblestone distribution density map within the three-dimensional space range in front of the drill bit; According to the cobblestone distribution density map, identify the weak connection zones between adjacent cobblestones as passable areas. In the passable areas, calculate the distances and direction angles from the center of gravity of the drill tool to the centers of each weak connection zone, select the sequence of weak connection zones with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory, and set attitude control points on the obstacle avoidance trajectory; For each attitude control point, calculate the telescopic displacement of each quadrant part of the drill bit and the bending deformation amount of the drill pipe, and adjust the liquid outlet direction and injection pressure of the mud nozzles in each quadrant to form a directional softening channel, so that the drill tool passes through each control point in sequence; Collect the spatial position and attitude angle data of the drill string in real time, extract the strength and trend characteristics of the weak connection zone in the current drilling area, calculate the position deviation between the drill string and each attitude control point, and adjust the bit telescopic displacement, drill pipe bending deformation and mud injection pressure parameters in real time according to the position deviation and the distribution law of the weak connection zone, so that the drill string keeps moving along the obstacle avoidance trajectory.

[0007] In an alternative embodiment, Collect the reflection signals of the detection sound wave between cobblestones, perform spectrum analysis and waveform superposition processing on the reflection signals, extract the attenuation characteristics and reflection characteristics of the sound wave in different media, and draw the cobblestone distribution density map within the three-dimensional space in front of the drill bit, including: Perform wavelet decomposition on the reflection signal to obtain the energy components of different frequency bands, extract the amplitude attenuation rate and phase delay value of each frequency band signal, and calculate the change amount of the acoustic impedance of the medium on the propagation path according to the attenuation degree difference of the sound wave with different frequencies by the soil body and cobblestones; Based on the mutation points of the acoustic impedance change amount, determine the spatial coordinates of the medium interface on the sound wave propagation path, use the spatial coordinates as the target position, perform delay superposition on the received reflection signals by using the spatial beam synthesis method, and dynamically adjust the delay compensation amount of each reflection signal according to the phase delay value, so that the echo signals at the target position are in-phase enhanced; Divide the three-dimensional space in front of the drill bit into multiple layers of concentric circular grid voxels. For each voxel position, calculate the cobblestone existence probability value corresponding to the voxel position according to the echo signal intensity, phase delay value and acoustic impedance change amount; Use the three-dimensional distance weight interpolation algorithm to perform continuous processing on the cobblestone existence probability value, and generate the cobblestone distribution density map within the three-dimensional space in front of the drill bit.

[0008] In an alternative embodiment, According to the cobblestone distribution density map, identify the weak connection zone between adjacent cobblestones as the passable area, including: Perform multi-scale density threshold segmentation on the cobblestone distribution density map, use the adaptive iteration method to determine the optimal segmentation threshold, and obtain the binary density image of the cobblestone area; Extract the cobblestone boundary contour from the binary density image, perform closing operation with a morphological operator with adjustable structural radius to eliminate the internal holes of the boundary, use edge-preserving morphological opening operation to smooth the boundary, obtain the regularized cobblestone area, construct an anisotropic distance field for the regularized cobblestone area, adaptively adjust the distance weight based on the density gradient information, and calculate the directional distance gradient map; Extract the continuous region with the largest gradient value in the distance gradient map as the initial demarcation zone, perform density sampling along the center line of the initial demarcation zone to obtain a density sampling sequence, perform region growing based on the density sampling sequence, expand and mark the continuous region with a density value lower than the dynamic threshold as the weak connection zone, and perform morphological optimization on the weak connection zone to obtain the final passable region.

[0009] In an alternative embodiment, Within the passable region, calculate the distance and direction angle from the center of gravity of the drill string to the center of each weak connection zone, and select the sequence of weak connection zones with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory, and set attitude control points on the obstacle avoidance trajectory, including: Classify the weak connection zones in the passable region according to their widths to obtain weak connection zones of different width levels; extract the center lines of each level of weak connection zones and establish a multi-level weak connection zone network including the center lines and transverse connection relationships; In the multi-level weak connection zone network, establish a dynamic coordinate system with the center of gravity of the drill string as the origin, and calculate the distance and direction angle from the center of gravity of the drill string to the center line of each weak connection zone; construct a passage evaluation function based on the distance, direction angle, and transverse connection cost, where the transverse connection cost decreases as the width of the weak connection zone increases; Use the passage evaluation function to perform bidirectional search in the multi-level weak connection zone network: while expanding the search space forward from the current position to the target position, expand the search space backward from the target position to the current position; determine the optimal expansion direction according to the evaluation function values of the two search directions, and select the sequence of weak connection zones with the smallest passage evaluation function value as the obstacle avoidance trajectory; Set attitude control points on the obstacle avoidance trajectory, and the spacing between adjacent attitude control points is proportional to the width of the corresponding weak connection zone; in the area where the width of the weak connection zone changes, add transition control points by minimizing the local curvature change rate to ensure the continuous and smooth transition of the trajectory.

[0010] In an alternative embodiment, For each attitude control point, calculate the telescopic displacement of each quadrant part of the drill bit and the bending deformation of the drill pipe, and adjust the liquid outlet direction and injection pressure of the mud nozzles in each quadrant to form a directional softening channel, so that the drill string passes through each control point in sequence, including: Establish a local coordinate system at the attitude control point, divide the drill bit into four quadrants: upper, lower, left, and right, calculate the telescopic displacement of each quadrant part of the drill bit, calculate the bending deformation of the drill pipe based on the drill pipe elastic deformation theory, and calculate the telescopic correction coefficient of each quadrant by taking the ratio of the telescopic displacement to the bending deformation; Collect the difference in rock hardness between each quadrant of the drill bit and the wellbore wall, calculate the rock breaking power ratio for each quadrant, and calculate the initial softening weight for each quadrant by multiplying the rock breaking power ratio by the telescopic correction coefficient; According to the initial softening weight, the contact pressure between each quadrant of the drill bit and the wellbore wall, and the bending deformation amount of the drill pipe, initially adjust the mud nozzles for each quadrant to obtain the initial jet state parameters for each quadrant; Real-time collect the spatial deviation of the drill tool position and attitude control points, correct the initial softening weight in combination with the initial jet state parameters to obtain the real-time softening weight, and dynamically adjust the jet pressure and liquid outlet direction of the mud nozzles for each quadrant based on the real-time softening weight to form a directional softening channel, so that the drill tool sequentially passes through each attitude control point.

[0011] In an alternative embodiment, Real-time collect the spatial position and attitude angle data of the drill tool, extract the strength and trend characteristics of the weak connection zone in the current drilling area, and calculate the position deviation between the drill tool and each attitude control point, including: Install a set of motion sensors along the axial direction on the drill tool body to collect the original motion data; set up a strain sensor array around the installation points of the motion sensor group to establish a local deformation vector field of the drill tool; use the deformation vector field to decompose and calculate the radial displacement and axial displacement of the sensor installation points, and eliminate the radial displacement and axial displacement from the original motion data to obtain the compensated real-time spatial position and attitude angle of the drill tool; Arrange multiple groups of acoustic transducers along the circumferential direction at the end of the drill bit, and each group of transducers includes a transmitting unit and a receiving unit; control adjacent transducer groups to alternately transmit detection signals and collect the reflected signals; perform segmented phase superposition on the reflected signals to enhance the boundary characteristics, and construct the corresponding relationship between the circumferential scanning angle of the drill tool and the amplitude of the reflected signal; based on the corresponding relationship, identify the boundary of the connection zone and the change in density, and combine the compensated real-time spatial position of the drill tool to determine the spatial distribution range and trend characteristics of the weak connection zone; Project the corrected real-time spatial position and attitude angle of the drill tool onto the coordinate systems where each attitude control point is located through spatial coordinate transformation, establish the drill tool force influence coefficient at each control point according to the strength and trend characteristics of the weak connection zone, correct each projection coordinate, and calculate the vector difference between each corrected coordinate and the corresponding attitude control point to obtain the position deviation between the drill tool and each attitude control point.

[0012] In an alternative embodiment, According to the position deviation and the distribution law of the weak connection zone, adjust the telescopic displacement amount of the drill bit, the bending deformation amount of the drill pipe, and the mud jet pressure parameters in real time, so that the drill tool maintains a movement along the obstacle avoidance trajectory, including: According to the magnitude of the position deviation and the distribution law of the weak connection zones, the drilling process is divided into a stable drilling section where the deviation is less than a preset deviation threshold and an obstacle avoidance adjustment section where the deviation is greater than the preset deviation threshold; When the drill string is located in the stable drilling section, the telescopic displacement of each quadrant of the drill bit is calculated based on the position deviation, and the bending deformation amount between adjacent drill pipe joints is determined according to the distribution law of the weak connection zones. An adjustment instruction is output according to the set ratio relationship between the telescopic displacement and the bending deformation amount; When the drill string is located in the rapid obstacle avoidance section, the optimal obstacle avoidance direction is calculated according to the distribution law of the weak connection zones. Based on the optimal obstacle avoidance direction, the circumferential arrangement position of the mud nozzles is determined, and the mud jet pressure parameters of each nozzle are adjusted according to the circumferential arrangement position to form an obstacle avoidance propulsion force. An adjustment instruction is output according to the obstacle avoidance propulsion force; Collect the movement trajectory of the drill string after executing the adjustment instruction, calculate the new position deviation, collect the drill string force data, evaluate the movement stability, and use the new position deviation and movement stability as evaluation parameters; Judge according to the evaluation parameters: when the new position deviation decreases and the movement stability meets the requirements, maintain the current adjustment parameters; otherwise, return the new position deviation and movement stability as inputs, and recalculate the telescopic displacement of the drill bit, the bending deformation amount of the drill pipe, and the mud jet pressure parameters until the drill string keeps moving along the obstacle avoidance trajectory.

[0013] In a second aspect of an embodiment of the present invention, an electronic device is provided, including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0014] In a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is implemented.

[0015] In this embodiment, by arranging an annular acoustic wave emission array at the end of the drill bit, the accurate detection and visualization of the distribution state of the cobblestone formation are realized, the ability to identify the formation structure during the drilling construction is greatly improved, and the risks of drill bit damage and sticking caused by encountering large cobblestones during the drilling process are effectively reduced. Based on the cobblestone distribution density map, the weak connection zones are intelligently identified and the optimal obstacle avoidance trajectory is planned. By adjusting the telescopic displacement of each quadrant part of the drill bit and the bending deformation amount of the drill pipe, the precise navigation of the drill tool in the complex formation is realized, the drilling efficiency is significantly improved, the construction period is reduced, and the engineering cost is lowered. An intelligent control method for real-time dynamically adjusting the drilling parameters is adopted. According to the formation characteristics of different regions, the mud injection direction and pressure are automatically optimized to form a directional softening channel, enabling the drill tool to smoothly advance along the predetermined trajectory, improving the construction quality and safety, and being particularly suitable for the construction of bored piles under complex formation conditions containing a large number of irregular cobblestones. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flow chart of the intelligent control method for the construction of bored piles in cobblestone formations and drilling parameters in the embodiments of the present invention; Figure 2 is the optimized thermal map of the cobblestone boundary before and after morphological processing in the embodiments of the present invention; Figure 3 is the flow chart of the trajectory planning framework in the embodiments of the present invention; Figure 4 is the thermal map of the adjustment of the injection pressure and liquid outlet direction of the mud nozzle in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] The technical solutions of the present invention will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0019] Figure 1 is a schematic flow chart of the intelligent control method for the construction of bored piles in cobblestone formations and drilling parameters in the embodiments of the present invention, as Figure 1 shown, the method includes: An annular acoustic emission array is arranged at the end of the drill bit to collect the reflected signals of the detection acoustic waves among the cobblestones, perform spectrum analysis and waveform superposition processing on the reflected signals, extract the attenuation characteristics and reflection characteristics of the acoustic waves in different media, and draw the cobblestone distribution density map within the three-dimensional space in front of the drill bit; According to the cobblestone distribution density map, identify the weak connection zones between adjacent cobblestones as passable areas. Within the passable areas, calculate the distances and direction angles from the center of gravity of the drilling tool to the centers of each weak connection zone, select the sequence of weak connection zones with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory, and set attitude control points on the obstacle avoidance trajectory; For each attitude control point, calculate the telescopic displacements of each quadrant part of the drill bit and the bending deformation amount of the drill pipe, and adjust the liquid outlet directions and injection pressures of the mud nozzles in each quadrant to form a directional softening channel, so that the drilling tool sequentially passes through each control point; Real-time collect the spatial position and attitude angle data of the drilling tool, extract the strength and trend characteristics of the weak connection zones in the current drilling area, calculate the position deviation between the drilling tool and each attitude control point, and according to the position deviation and the distribution law of the weak connection zones, adjust the telescopic displacement amount of the drill bit, the bending deformation amount of the drill pipe and the mud injection pressure parameters in real time, so that the drilling tool maintains movement along the obstacle avoidance trajectory.

[0020] In an alternative embodiment, collecting the reflected signals of the detection acoustic waves among the cobblestones, performing spectrum analysis and waveform superposition processing on the reflected signals, and extracting the attenuation characteristics and reflection characteristics of the acoustic waves in different media, and drawing the cobblestone distribution density map within the three-dimensional space in front of the drill bit includes: Perform wavelet decomposition on the reflected signals to obtain energy components in different frequency bands, extract the amplitude attenuation rate and phase delay value of each frequency band signal, and calculate the change amount of the acoustic impedance of the medium on the propagation path according to the attenuation degree difference of different frequency acoustic waves by the soil body and the cobblestones; Based on the mutation points of the acoustic impedance change amount, determine the spatial coordinates of the medium interface on the acoustic wave propagation path, use the spatial coordinates as the target positions, use the spatial beam synthesis method to perform delay superposition on the received reflected signals, and dynamically adjust the delay compensation amount of each reflected signal according to the phase delay value, so that the echo signals at the target positions are in-phase enhanced; Divide the three-dimensional space in front of the drill bit into multiple layers of concentric circular grid voxels. For each voxel position, calculate the cobblestone existence probability value corresponding to the voxel position according to the echo signal intensity, phase delay value and acoustic impedance change amount; Use the three-dimensional distance weight interpolation algorithm to perform continuous processing on the cobblestone existence probability values to generate the cobblestone distribution density map within the three-dimensional space in front of the drill bit.

[0021] This embodiment provides a system implementation method for detecting the distribution of cobblestones by sound waves. Through sound wave acquisition, signal processing, and spatial modeling techniques, an accurate mapping of the distribution density of cobblestones within the three-dimensional space in front of the drill bit is achieved.

[0022] In actual operation, the sound wave detection system is configured at the front end of the drill bit and includes a transmitting transducer and at least four receiving transducers. The frequency range of the detection sound wave signal emitted by the transmitting transducer is 1 kHz to 10 kHz, and the duration is 10 ms. The system sampling frequency is set to 100 kHz, and the reflected signal with a duration of 500 ms is collected for each detection. The data accuracy is 16 bit.

[0023] After the signal acquisition is completed, wavelet decomposition processing is performed to obtain the energy components in different frequency bands. In specific implementation, six-layer wavelet decomposition is adopted to decompose the original signal into six frequency bands: 0 - 0.78 kHz, 0.78 - 1.56 kHz, 1.56 - 3.13 kHz, 3.13 - 6.25 kHz, 6.25 - 12.5 kHz, and 12.5 - 25 kHz. Practice shows that for cobblestones with a diameter of 5 - 30 cm, the signal in the 3.13 - 6.25 kHz frequency band has the best recognition effect. Calculate the energy envelope for the signal in each frequency band, and obtain the amplitude attenuation rate by analyzing the slope change of the energy curve. For example, in the area containing cobblestones, the amplitude attenuation rate of the signal in the 3.13 - 6.25 kHz frequency band is usually 0.6 - 0.8 dB / m, while in ordinary soil it is 1.2 - 1.5 dB / m.

[0024] The extraction of the phase delay value is achieved through Hilbert transform. After performing Hilbert transform on the signal, calculate the instantaneous phase of the signal. Compare the phase changes of the signals in different frequency bands during propagation to establish a phase delay curve. For example, in a measured case, when the sound wave encounters a cobblestone with a diameter of about 15 cm, the phase delay value of the signal in the 3.13 - 6.25 kHz frequency band increases by 27° to 35° compared to the predicted value of the standard soil model.

[0025] Based on the obtained amplitude attenuation rate and phase delay value, calculate the change amount of the acoustic impedance of the medium on the sound wave propagation path. In practical applications, the typical value of the acoustic impedance of soil is about 1.5×10^6 kg / (m 2 s), while the typical value of the acoustic impedance of cobblestones is about 7.8×10 6 kg / (m 2 s). The sliding window method is adopted in the calculation. The window width is 10 sampling points, and the step is 5 sampling points. When the calculated change amount of the acoustic impedance exceeds 1.2×10 6 kg / (m 2 s) in three consecutive windows, it is determined as the medium interface.

[0026] After the mutation points of acoustic impedance changes are determined, a three-dimensional coordinate calculation model is used to determine the spatial coordinates of these interfaces. In practical applications, based on the time difference from the emission to the reception of the acoustic wave and the propagation speed of the acoustic wave in the soil (about 1500 m / s), combined with the spatial layout information of the receiving transducers (the four receiving transducers are arranged in a square layout with a side length of 10 cm), the spatial coordinates of the reflection point are calculated through the principle of triangulation. For example, in a certain test case, a cobblestone with a diameter of about 20 cm was detected 78 cm in front of the drill bit. After determining the target position, spatial beam synthesis processing is performed. A grid with a spatial resolution of 5 cm×5 cm×5 cm is selected. For each grid point, the time delay compensation amount is calculated according to the distance difference from it to each receiving transducer. During the processing, the signals obtained by each receiving transducer are delayed and superimposed, and the time delay compensation amount is dynamically adjusted according to the previously calculated phase delay value. For example, when the phase delay value of a certain grid point is 30°, the corresponding time delay compensation adjustment amount is 0.026 ms. This processing makes the echo signals at the target position in-phase enhanced, significantly improving the signal-to-noise ratio, which can be increased by about 6 - 9 dB in actual measurements.

[0027] In order to draw the cobblestone distribution density map in the three-dimensional space in front of the drill bit, the space is divided into multiple layers of concentric circular grid voxels, with a radius range of 0.5 - 3 meters, an angular resolution of 5°, and a radial resolution of 10 cm. For each voxel position, the cobblestone presence probability value is calculated, and the calculation basis includes: the echo signal intensity (normalized to 0 - 1), the phase delay value (weighting coefficient 0.3), and the acoustic impedance change amount (weighting coefficient 0.7). Tests show that when the comprehensive probability value exceeds 0.75, there is a high probability that a cobblestone exists at this position.

[0028] The three-dimensional distance weight interpolation algorithm is used to continuously process the above cobblestone presence probability values to generate a visualized density distribution map. In the specific implementation, an interpolation radius of 15 cm and a distance weight factor of 2 are selected to smooth the probability values. The generated density map uses a four-color gradient of red - yellow - green - blue to represent the probability level, where the red area (probability value > 0.85) represents the area with the highest cobblestone density, and the blue area (probability value < 0.3) represents the area without cobblestones.

[0029] Based on the above technical solution, it is possible to achieve high-precision detection and visualization of the cobblestone distribution in the complex geological structure in front of the drill bit, significantly improving the resolution and reliability of geological detection. By extracting the attenuation characteristics and phase information of acoustic waves in different frequency bands through wavelet decomposition, it is possible to accurately distinguish different media such as soil and cobblestones and identify their spatial distribution interfaces. Introducing spatial beamforming and dynamic time delay compensation technologies can enhance the signal-to-noise ratio of the echo signal at the target position, suppress interference and multipath effects, and improve the clarity and accuracy of the image. Using voxel probability modeling and three-dimensional interpolation algorithms, the distribution density of cobblestones in the area in front of the drill bit can be continuously expressed, providing a reliable basis for drilling path optimization, risk assessment, and automatic control.

[0030] In an alternative embodiment, identifying the weak connection zone between adjacent cobblestones as a passable area according to the cobblestone distribution density map includes: Performing multi-scale density threshold segmentation on the cobblestone distribution density map, using an adaptive iterative method to determine the optimal segmentation threshold, and obtaining a binary density image of the cobblestone area; Extracting the cobblestone boundary contour from the binary density image, performing a closing operation using a morphological operator with an adjustable structural radius to eliminate internal holes in the boundary, and performing an edge-preserving morphological opening operation to smooth the boundary to obtain a regularized cobblestone area. Constructing an anisotropic distance field for the regularized cobblestone area, adaptively adjusting the distance weight based on density gradient information, and calculating a directional distance gradient map; Extracting the continuous area with the maximum gradient value in the distance gradient map as the initial demarcation zone, performing density sampling along the center line of the initial demarcation zone to obtain a density sampling sequence, performing region growing based on the density sampling sequence, expanding and marking the continuous area with a density value lower than the dynamic threshold as the weak connection zone, and performing morphological optimization on the weak connection zone to obtain the final passable area.

[0031] This embodiment provides a method for identifying the weak connection zone between adjacent cobblestones as a passable area according to the cobblestone distribution density map. First, obtain the cobblestone distribution density map and preprocess it to form a grayscale image, where the grayscale value represents the cobblestone distribution density, and the higher the grayscale value, the greater the density.

[0032] Perform multi-scale density threshold segmentation on the cobblestone distribution density map. Specifically, an adaptive iterative method is used to determine the optimal segmentation threshold. This method first selects an initial threshold T0 (for example, taking the gray mean value of the density map as 128), divides the image into a foreground region R1 and a background region R2, calculates the average gray values μ1 and μ2 of R1 and R2 respectively, and then uses (μ1 + μ2) / 2 as the new threshold T1, repeating the iteration until the threshold change value is less than the preset threshold (such as 0.5). In practical applications, the initial threshold can be set to 128 (8-bit image). After 6 iterations, the final threshold T = 143 is obtained. The regions with density values greater than 143 are marked as cobblestone regions, and the regions less than or equal to 143 are marked as non-cobblestone regions, forming a binary density image. Next, extract the cobblestone boundary contours from the binary density image. The 8-neighborhood boundary tracking algorithm is used to detect boundary points and generate a boundary contour sequence. For a typical cobblestone region (with an area of about 500 square pixels), the number of boundary contour points is about 80 - 120.

[0033] Optimize the extracted boundary contours. First, use morphological closing operation with adjustable structural radius to eliminate the internal holes in the boundary. The structural element is selected as a disk shape, and the radius is adaptively adjusted according to the average size of the cobblestones. In practice, for cobblestones with an average diameter of 30 pixels, it is more appropriate to set the structural element radius to 5 pixels. After the closing operation, then use edge-preserving morphological opening operation to smooth the boundary. Use a structural element with the same shape but a radius of 3 pixels to retain the main morphological features of the cobblestones while removing small protrusions. After these two steps of operation, a regularized cobblestone region is obtained.

[0034] Construct an anisotropic distance field based on the regularized cobblestone region. The traditional Euclidean distance field cannot accurately reflect the actual passability in the case of uneven density distribution, so density information is introduced to correct the distance calculation. First, calculate the Euclidean distance d(x, y) from each pixel point in the non-cobblestone region to the nearest cobblestone boundary, and at the same time obtain the density value ρ(x, y) of this point. Then, adaptively adjust the distance weight according to the density gradient information, and correct the distance value D(x, y)=d(x, y)×(1 + α×ρ(x, y) / ρmax), where α is the weight coefficient (the value is 0.8 in the experiment), and ρmax is the maximum value of the density map (255). This makes the distance value increased in the region with higher density, indicating an increase in the passing difficulty. After calculating the corrected distances of all pixel points, calculate the gradient of the distance field to obtain a distance gradient map with directionality.

[0035] Extract the continuous region with the maximum gradient value in the distance gradient map as the initial demarcation band. Set the gradient threshold Tg (take 75% of the maximum gradient value in the experiment, about 0.3), and mark the region with a gradient value greater than Tg as the initial demarcation band. The initial demarcation band usually shows a band-like distribution with a width of about 8 - 15 pixels. Conduct density sampling along the centerline of the initial demarcation band to obtain a density sampling sequence. Use a thinning algorithm to extract the centerline of the initial demarcation band, and sample density values at 5-pixel intervals along the centerline to form a density sampling sequence {ρ1, ρ2,..., ρn}. In a typical scenario, a demarcation band about 200 pixels long will generate approximately 40 density sampling points. Based on the density sampling sequence, perform region growing to mark the weak connection band. Calculate the mean μρ and standard deviation σρ of the density sampling sequence, and set the dynamic threshold Td = μρ - β×σρ, where β is an adjustment coefficient (take 1.5 in the experiment). Starting from the sampling point with the lowest density value, expand to both sides, and mark the region with continuous density values lower than Td as the candidate area for the weak connection band. In the example, μρ is about 110, σρ is about 20, then Td is about 80.

[0036] Perform morphological optimization on the candidate area for the weak connection band. First, perform conditional dilation. The dilation structure element is a 3×3 square, and limit the density value of the dilated area not to exceed 1.2×Td to prevent over-expansion into high-density areas. Then, perform morphological smoothing, using a 5×5 Gaussian kernel for filtering to eliminate jagged edges. Finally, perform path width optimization to ensure that the width of the connection band is not less than the preset minimum passing width (such as 15 pixels), and appropriately expand the narrow areas. After this series of optimizations, the final passable area is obtained.

[0037] In the prior art, the recognition of the cobblestone area in front of the drill bit mostly relies on fixed-threshold segmentation and simple morphological processing, which is difficult to cope with complex geological environments with drastic density changes and blurred boundaries, resulting in low recognition accuracy and poor robustness of the passing path. To solve the above problems, this application uses a multi-scale density threshold segmentation and adaptive iteration method, which can dynamically determine the optimal segmentation threshold according to the actual density distribution characteristics, effectively adapting to density differences in different regions; introduces a morphological closing operation with an adjustable structural radius and an edge-preserving opening operation to enhance the flexibility and smoothness of boundary processing, and improve the problems of discontinuous boundaries and misrecognition; by constructing an anisotropic distance field and adjusting weights based on density gradient information, a directional distance gradient map is obtained, realizing the directional recognition of the internal structure of the cobblestone-dense area; on this basis, extract the continuous region of gradient extrema, conduct density sampling and region growing, further identify the weak connection band with loose structure and low density, and effectively calibrate the passable area. The overall improvement starts from the goal of improving recognition accuracy and adaptability, and finally realizes the accurate extraction and dynamic optimization of the passing path in the cobblestone area under complex and dense environments, enhancing the intelligent level of the drilling navigation and obstacle avoidance system.

[0038] Figure 2 This is the optimized thermal map of the cobblestone boundary before and after morphological processing in the embodiment of the present invention. As Figure 2 shown, this figure shows the optimization effect of the cobblestone boundary contour before and after morphological processing. On the left side of the figure is the cobblestone boundary before processing, where 3 obvious internal cavities can be clearly seen. The boundary is in a jagged and irregular shape, and the density value distribution is uneven. On the right side is the cobblestone boundary after morphological optimization by the present technical solution. The morphological closing operation with adjustable structural radius is used to eliminate the internal cavities in the boundary, and the morphological opening operation that preserves the edge is used to smooth the boundary. From the comparison of density values, the density values in the area before processing range from D = 0.45 to D = 0.72 and are unevenly distributed; after processing, the density values increase and become more uniform, ranging from D = 0.48 to D = 0.75. Quantitative analysis shows that the average boundary roughness before processing is 0.65, and it drops to 0.23 after processing, and the boundary smoothness is significantly improved. In particular, the low-density area with an original D = 0.51 is increased to D = 0.54 after processing, improving the density uniformity. This optimization process improves the regularization degree of the area while maintaining the original boundary morphological characteristics, laying a foundation for subsequent distance field construction and demarcation zone extraction.

[0039] In an alternative embodiment, within the passable area, calculate the distance and direction angle from the center of gravity of the drill to the center of each weak connection band, and select the sequence of weak connection bands with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory. And set attitude control points on the obstacle avoidance trajectory, including: Classify the weak connection bands in the passable area according to their widths to obtain weak connection bands of different width levels; extract the centerlines of each level of weak connection bands and establish a multi-level weak connection band network including the centerlines and transverse connection relationships; In the multi-level weak connection band network, establish a dynamic coordinate system with the center of gravity of the drill as the origin, and calculate the distance and direction angle from the center of gravity of the drill to the centerlines of each weak connection band; construct a passage evaluation function based on the distance, direction angle, and transverse connection cost, where the transverse connection cost decreases as the width of the weak connection band increases; Use the passage evaluation function to perform bidirectional search in the multi-level weak connection band network: while expanding the search space forward from the current position to the target position, expand the search space backward from the target position to the current position; determine the optimal expansion direction according to the evaluation function values in the two search directions, and select the sequence of weak connection bands with the smallest passage evaluation function value as the obstacle avoidance trajectory; Set attitude control points on the obstacle avoidance trajectory, and the spacing between adjacent attitude control points is proportional to the width of the corresponding weak connection band; in the area where the width of the weak connection band changes, add transition control points by minimizing the local curvature change rate to ensure the continuous and smooth transition of the trajectory.

[0040] Exemplarily, after the classification, the centerline of each level of the weak connection belt area is extracted. The centerline represents the optimal passage path of the connection belt in space, which can be achieved by skeleton extraction algorithm, morphological distance transformation or central axis search method. The extraction of the centerline must ensure that it does not deviate from the path boundary inside the connection belt, while retaining the continuity and representativeness of the path direction as much as possible. After the centerline extraction is completed, combined with the intersection and connection relationship between connection belts of different levels, a multi-level weak connection belt network containing centerline information and lateral connection relationship is established. The network not only contains the level and position attributes of each weak connection belt, but also contains the type and cost attributes of the connection relationship, among which the lateral connection relationship is used to describe the conversion channel between connection belts in different directions, and its connection cost decreases with the increase of the width level of the weak connection belt, that is, the lateral connection between wider connection belts is smoother, while the lateral switching cost of narrower connection belts is higher.

[0041] After constructing a multi-level network, a dynamic coordinate system is established with the current center of gravity of the drill as the reference origin, and the center lines of each weak connection zone are spatially mapped. The spatial distance between the center of gravity of the drill and each center line, as well as the angle between the current direction of travel of the drill and the extension direction of the center line are calculated. The distance is used to measure the cost of the drill approaching a specific connection zone, and the direction angle is used to evaluate the operational intensity required for posture adjustment. When performing the above calculations, actual operating constraints such as drill size, turning radius, and forward inertia should be considered.

[0042] The pass evaluation function is constructed based on the distance, azimuth and lateral connection cost. This function is used to measure the comprehensive cost that the drill needs to pay to pass through a certain connection belt in the current dynamic coordinate system. To ensure the rationality of the function construction, the following constraints should be set: the shorter the travel distance, the smaller the azimuth deviation and the wider the connection belt, the smaller the evaluation value, that is, the better. In the construction process, avoid using specific formulas, but build a logical weight model based on the above three factors, and gradually evaluate the quality of the pass path in a distance-first-backward manner. For example, for a pass path starting from the current drill position, it needs to pass through two narrow connection belts and then enter a wide connection belt. Although the overall distance is not long, due to the narrow width of the first two sections of the connection belt, the posture needs to be adjusted frequently, and there is a blind spot for turning, so its evaluation value will be significantly higher than a path that is slightly farther but has wide connection belts.

[0043] To improve the efficiency and accuracy of obstacle avoidance path planning, based on the above-mentioned passage evaluation function, a bidirectional search is carried out in the multi-level weak connection belt network. Bidirectional search means that while expanding the search space from the current position of the drill string towards the target area, a reverse search is carried out from the target area towards the current position. The process of bidirectional expansion adopts a progressive method, that is, the direction with a smaller value of the passage evaluation function is preferentially expanded. During the expansion process, a priority queue or cache structure is set up to record the cumulative cost of the current path and the state of the path direction, dynamically update the passage evaluation value of the known path, and perform real-time sorting on all connection belts to be expanded to ensure that the optimal direction is selected for each step of expansion. After the two search directions meet at a point in space, a feasible path can be considered to be found. Further analyze the passage evaluation value of the path corresponding to the intersection point, and select the path with the smallest passage evaluation function value among all possible intersection paths as the optimal obstacle avoidance trajectory.

[0044] After the obstacle avoidance trajectory is determined, attitude control points are set on it. Attitude control points are important reference points for fine-tuning the drill string attitude and stable progress, and their positions should fully consider the width and connection type of the weak connection belt. In the passage path, the spacing between adjacent attitude control points is proportional to the width of the connection belt where the path is located, that is, the control point spacing is larger in the wide connection belt, and the control point spacing should be appropriately reduced in the narrow connection belt to enhance the frequency and accuracy of the drill string attitude adjustment. For example, when the drill string passes through a connection belt with a lateral width of three meters, the control point spacing can be set to two meters, while when passing through a connection belt only one meter wide, the control point spacing should be adjusted to 0.5 meters or even smaller. In addition, in the area where the width of the connection belt changes significantly in the path, such as when suddenly transitioning from a wide connection belt to a narrow connection belt, transition control points need to be set to ensure the continuity and stability of the trajectory. The setting of transition control points should aim to minimize the change rate of the drill string travel curvature, that is, by adding additional control points in the transition area to adjust the path bending degree and avoid sharp turns or jitters.

[0045] For example, in a certain underground drilling scenario, the drilling tool needs to move from entrance A to target B, and during this process, it has to pass through a tunnel area with a complex structure and a compact space. First, a three-dimensional laser scanning device is used to obtain the spatial data of the tunnel area, and the passage path is spatially segmented and the width is calculated. Dozens of weak connection zones are identified and classified into three grades according to their widths. Then, a centerline extraction algorithm is used to extract the centerlines of each weak connection zone, and a network structure is constructed based on the connection relationship to form a multi-level network containing information such as position, direction, and connection cost. Next, with the current position of the drilling tool as the origin, the spatial distance and direction angle of each centerline are calculated, and a passage evaluation function is established. After constructing a bidirectional search structure, the system simultaneously expands the path search from point A and point B, and finally establishes an intersection path between a point ten meters away from the entrance and a point fifteen meters away from the target. The path with the minimum passage evaluation value consists of seven different grade connection zones, with a total path length of thirty meters, and the width of the narrowest area is only one meter. Pose control points are set based on this path, six control points are set in the narrowest area, and three transition control points are set in the transition area to ensure that the trajectory of the drilling tool remains continuous and smooth during passing without yaw.

[0046] In the prior art, the path planning of the drilling tool in a complex geological structure usually relies on a static map or a one-way search algorithm, which cannot dynamically adapt to the changes in the spatial structure in the cobblestone area and lacks precise control over the changes in the drilling pose, easily leading to path deviation or drill bit jamming. In this application, a multi-level weak connection zone network is constructed within the passable area. By grading the widths of the weak connection zones and extracting the centerlines, the hierarchical relationship of the path structure is clarified, and a dynamic network structure including transverse connections is introduced to provide more comprehensive passage information support for subsequent path selection. By constructing a passage evaluation function including distance, direction angle, and transverse connection cost, and combining the forward and reverse bidirectional search mechanisms, the global optimality and search efficiency of the path planning are improved. To solve the problem of insufficient pose control at the path turning points, pose control points are further set on the obstacle avoidance trajectory, and the spacing of the control points is dynamically adjusted according to the width of the weak connection zone, and a minimum curvature change rate constraint is introduced in the width change area to ensure the continuity and smoothness of the path. The overall improvement starts from enhancing the adaptability, passage efficiency, and pose control accuracy of the path planning, and finally realizes the stable and smooth obstacle avoidance passage ability of the drilling tool under complex geological conditions.

[0047] Figure 3 This is the flow chart of the trajectory planning framework for the embodiments of the present invention, as Figure 3As shown, first start from the classification of the weak connection belts. Divide the passable area into n levels according to the width size, and record the width of each level as Wi (i = 1, 2,..., n). Then, extract the centerlines and construct the network. Extract the centerlines of the weak connection belts at each level, establish the lateral connection relationships, and form the network topology structure. Next, establish a dynamic coordinate system with the center of gravity of the drill tool as the origin, and calculate the distance and the direction angle. Based on these parameters, construct a pass evaluation function. In the search stage, adopt a bidirectional search strategy. While searching forward from the starting point to the ending point (the number of expansions is 83 times, and the expansion range is 28.4 m), search backward from the ending point to the starting point (the number of expansions is 76 times, and the expansion range is 25.7 m) to ensure the search efficiency. Based on the bidirectional search results, determine the obstacle avoidance trajectory with the minimum evaluation function value. The passing cost of this trajectory is 0.37, and the trajectory length is 52.7 m. Finally, set attitude control points on the obstacle avoidance trajectory. The distance between the control points is proportional to the width of the weak connection belt. And in the area where the width of the weak connection belt changes, additional transition control points are added according to the minimum curvature change rate criterion to ensure the smooth transition of the trajectory. The whole process fully reflects the core features of this technical solution: the construction of a multi-level weak connection belt network, the bidirectional search strategy, the width-adaptive control point setting, and the curvature smoothing optimization.

[0048] In an alternative implementation, for each attitude control point, calculate the telescopic displacement of each quadrant part of the drill bit and the bending deformation of the drill pipe, and adjust the liquid outlet direction and injection pressure of the mud nozzles in each quadrant to form a directional softening channel, so that the drill tool passes through each control point in sequence, including: Establish a local coordinate system at the attitude control point, divide the drill bit into four quadrants: upper, lower, left, and right. Calculate the telescopic displacement of each quadrant part of the drill bit, calculate the bending deformation of the drill pipe based on the drill pipe elastic deformation theory, and calculate the telescopic correction coefficient of each quadrant by taking the ratio of the telescopic displacement to the bending deformation. Collect the difference in rock hardness between each quadrant of the drill bit and the wellbore wall, calculate the rock breaking power ratio of each quadrant, and calculate the initial softening weight of each quadrant by multiplying the rock breaking power ratio by the telescopic correction coefficient. According to the initial softening weight, the contact pressure between each quadrant of the drill bit and the wellbore wall, and the bending deformation of the drill pipe, initially adjust the mud nozzles in each quadrant to obtain the initial injection state parameters of each quadrant. Real-time collect the spatial deviation between the position of the drill tool and the attitude control point, correct the initial softening weight by combining the initial injection state parameters to obtain the real-time softening weight, and dynamically adjust the injection pressure and liquid outlet direction of the mud nozzles in each quadrant based on the real-time softening weight to form a directional softening channel, so that the drill tool passes through each attitude control point in sequence.

[0049] Exemplarily, first establish a local coordinate system at the attitude control point, and divide the drill bit into four quadrants: upper, lower, left, and right. Taking the axis of the drill bit as the origin, establish a right-handed coordinate system, where the x-axis points to the right, the y-axis points upward, and the z-axis points forward along the axis of the drill bit. The position and attitude data of the drill bit in this coordinate system are collected in real time through pressure sensors and position sensors. For example, the center position of the drill bit is (0.02m, -0.03m, 0m), indicating that the center of the drill bit is 2cm to the right and 3cm downward relative to the control point.

[0050] When calculating the telescopic displacement of each quadrant of the drill bit, a displacement sensor is used to measure the deviation of each quadrant of the drill bit from the ideal trajectory. Taking the right quadrant as an example, when the deviation between the right side of the drill bit and the ideal trajectory is detected to be 2.5cm, the right quadrant needs to contract by about 2.5cm to correct the deviation. Similarly, the telescopic displacement values are calculated for the upper, lower, and left quadrants respectively. For example, the upper quadrant extends 1.8cm, the lower quadrant contracts 2.2cm, and the left quadrant extends 1.5cm. Based on the theory of elastic deformation of the drill pipe, the bending deformation amount of the drill pipe is calculated. The strain data of each cross-section of the drill pipe are collected through strain gauges, and combined with the material properties of the drill pipe (such as steel with an elastic modulus of 210GPa), the bending deformation amounts of the drill pipe in each direction are calculated. For example, at the cross-section of the drill pipe 10m away from the drill bit, the bending deformation amount in the x direction is 3.2cm, and the bending deformation amount in the y direction is 2.8cm.

[0051] The ratio of the telescopic displacement to the bending deformation amount is calculated to obtain the telescopic correction coefficient for each quadrant. Taking the right quadrant as an example, the telescopic displacement is 2.5cm, and the bending deformation amount in the corresponding direction is 3.2cm, so the telescopic correction coefficient is 2.5 / 3.2 = 0.78. Similarly, the correction coefficients for other quadrants are calculated. For example, the upper quadrant is 0.64, the lower quadrant is 0.79, and the left quadrant is 0.47. The difference in rock hardness between each quadrant of the drill bit and the wellbore wall is collected. The rock hardness of the wellbore wall is measured through a micro-hardness tester or acoustic logging instrument, and the difference from the hardness of the drill bit is calculated. For example, the rock hardness in contact with the wellbore wall in the right quadrant is 80MPa, the hardness of the drill bit is 900MPa, and the hardness difference is 820MPa; the upper quadrant is 790MPa, the lower quadrant is 850MPa, and the left quadrant is 810MPa. The rock-breaking power ratio for each quadrant is calculated. According to the hardness difference and parameters such as the rotation speed and pressure of the drill bit, the rock-breaking power for each quadrant is calculated. For example, the rock-breaking power in the right quadrant is 12kW, the upper quadrant is 10.5kW, the lower quadrant is 13kW, and the left quadrant is 11kW. The total power of the drill bit is 46.5kW, so the rock-breaking power ratio in the right quadrant is 12 / 46.5 = 0.258, the upper quadrant is 0.226, the lower quadrant is 0.280, and the left quadrant is 0.236.

[0052] Calculate the initial softening weight of each quadrant by multiplying the rock-breaking power ratio by the telescopic correction coefficient. Taking the right quadrant as an example, the rock-breaking power ratio is 0.258 and the telescopic correction coefficient is 0.78, so the initial softening weight is 0.258×0.78 = 0.201. Similarly, calculate the initial softening weights of other quadrants. For example, the upper quadrant is 0.145, the lower quadrant is 0.221, and the left quadrant is 0.111.

[0053] According to the initial softening weight, the contact pressure between each quadrant of the drill bit and the wellbore, and the bending deformation of the drill pipe, initially adjust the mud nozzles in each quadrant. The contact pressure is collected by a pressure sensor. For example, the contact pressure in the right quadrant is 18 MPa, the upper quadrant is 15 MPa, the lower quadrant is 20 MPa, and the left quadrant is 16 MPa. Adjust the liquid outlet direction and injection pressure of the mud nozzles to obtain the initial injection state parameters of each quadrant. Taking the right quadrant as an example, the initial softening weight is 0.201, the contact pressure is 18 MPa, and the output pressure of the mud pump is 30 MPa. Then the initial injection pressure of the nozzle in the right quadrant is set to 30×0.201 = 6.03 MPa, and the nozzle angle is adjusted to 15° with the normal direction of the wellbore. Similarly, set the initial injection state parameters of other quadrants.

[0054] Collect the spatial deviation of the position and attitude control points of the drill string in real time. The actual position and attitude of the drill string are measured in real time by sensors such as gyroscopes and accelerometers, compared with the preset control points, and the spatial deviation is calculated. For example, the actual position of the drill string is (0.03 m, -0.02 m, 0.01 m), and the position deviation from the control point is 3.74 cm. Combine the initial injection state parameters to correct the initial softening weight to obtain the real-time softening weight. The correction formula considers factors such as spatial deviation, actual drilling speed, and rock feedback. For example, the initial softening weight in the right quadrant is 0.201, and the spatial deviation correction factor is 1.15. Then the real-time softening weight is adjusted to 0.201×1.15 = 0.231. Similarly, correct the softening weights of other quadrants.

[0055] Dynamically adjust the injection pressure and liquid outlet direction of the mud nozzles in each quadrant based on the real-time softening weight. For example, the real-time softening weight in the right quadrant is 0.231, and the output pressure of the mud pump is 30 MPa. Then the injection pressure of the nozzle in the right quadrant is dynamically adjusted to 30×0.231 = 6.93 MPa, and the nozzle angle is adjusted to 18° with the normal direction of the wellbore to form a stronger right-side directional softening channel.

[0056] Through the directional softening channels formed by the above steps, the forces on each quadrant of the drill bit are balanced, and the drill string can pass through each attitude control point along the preset trajectory in sequence, realizing precise directional drilling. The system executes a complete calculation and adjustment cycle every second to ensure real-time control and precise navigation of the drilling process.

[0057] In the prior art, when the drill string passes through complex paths or turning areas, it usually relies on mechanical control or adjusts the nozzle with fixed parameters to soften the rock formation. There is a lack of precise perception and response to the attitude of the drill bit and the contact state with the wellbore wall, which easily leads to an increase in local resistance or deviation of the drill bit, affecting the drilling efficiency and path accuracy. To solve this problem, the present application introduces a local coordinate system centered on the attitude control point, refines the coordinated calculation of the telescopic displacement in each quadrant of the drill bit and the amount of drill pipe bending deformation, obtains a telescopic correction coefficient that truly reflects the deformation state of the drill string, and constructs an initial softening weight in combination with the hardness difference between the drill bit and the wellbore wall to achieve a differential expression of the rock-breaking difficulty in different quadrants. On this basis, the initial jet state of the mud nozzle is adjusted in combination with the contact pressure and deformation degree in each quadrant to improve the accuracy and response speed of softening control. By continuously collecting the attitude deviation of the drill string, the initial softening weight is dynamically corrected, and the liquid outlet direction and pressure of the nozzle are adjusted in real time to form a directional softening channel in front of the drill bit that continuously updates with the change of the path. The overall improvement starts from improving the attitude control accuracy and directional drilling ability, and finally realizes the smooth passage of the drill string through the control point in the complex path, reduces the resistance and deviation risk, and improves the path tracking and passing efficiency.

[0058] Figure 4 The heat map for adjusting the jet pressure and liquid outlet direction of the mud nozzle in the embodiment of the present invention is as Figure 4 shown. This heat map intuitively shows the relationship between the adjustment of the jet pressure and liquid outlet direction of the mud nozzle. In the figure, the horizontal axis represents the adjustment angle of the liquid outlet direction, ranging from -15° to 25°; the vertical axis represents the serial numbers of 7 different attitude control points. The heat map uses a gray scale gradient to represent the magnitude of the jet pressure, and the darker the color, the higher the pressure. It can be clearly seen from the figure that at control points 3 and 4, when the adjustment angle of the liquid outlet direction is 0°, the jet pressure reaches the highest values, which are 19.8 MPa and 19.5 MPa respectively, and these two regions are also marked as the optimal adjustment regions. In contrast, the jet pressures at control point 6 at angles of -15° and 25° are 14.2 MPa and 10.3 MPa respectively, which are significantly lower than the central region. The pressure range in the first quadrant is 16.5 - 19.8 MPa, and the pressure range in the second quadrant is 10.3 - 14.5 MPa, indicating that the pressure requirements in different quadrants are significantly different. From the overall distribution, the best jet angles are mainly concentrated in the range of 0° to 5°, which provides an important reference for accurately controlling the drilling direction. By finely adjusting the jet pressure and liquid outlet direction of the mud nozzle in each quadrant, the present technical solution forms a directional softening channel, which is significantly better than the uniform pressure distribution method used in traditional jet drilling technologies (such as conventional pressure drilling technology). The traditional method usually uses fixed pressure and angle and is difficult to cope with complex formations and precise trajectory requirements, while the optimal parameter combination determined by the heat map analysis in this solution can achieve the precise passage of each attitude control point, greatly improving the efficiency and accuracy of drilling in complex trajectories.

[0059] In an alternative embodiment, the spatial position and attitude angle data of the drill string are collected in real time, the strength and trend characteristics of the weak connection zone in the current drilling area are extracted, and the position deviation between the drill string and each attitude control point is calculated, including: Motion sensor groups are arranged axially on the drill string body to collect original motion data; a strain sensor array is arranged around the installation points of the motion sensor groups to establish a local deformation vector field of the drill string; the radial displacement and axial displacement of the sensor installation points are calculated by decomposing the deformation vector field, and the radial displacement and axial displacement are eliminated from the original motion data to obtain the compensated real-time spatial position and attitude angle of the drill string; Multiple groups of acoustic transducers are arranged circumferentially at the end of the drill bit, and each group of transducers includes a transmitting unit and a receiving unit; adjacent transducer groups are controlled to alternately transmit detection signals and collect reflected signals; the reflected signals are segmented and phase-summed to enhance the boundary characteristics, and the corresponding relationship between the circumferential scanning angle of the drill string and the amplitude of the reflected signal is constructed; based on the corresponding relationship, the connection zone boundary and density change are identified, and the spatial distribution range and trend characteristics of the weak connection zone are determined in combination with the compensated real-time spatial position of the drill string; The corrected real-time spatial position and attitude angle of the drill string are projected onto the coordinate systems where each attitude control point is located through spatial coordinate transformation respectively. According to the strength and trend characteristics of the weak connection zone, the drill string force influence coefficients at each control point are established, the projection coordinates are corrected, and the vector difference between each corrected coordinate and the corresponding attitude control point is calculated to obtain the position deviation between the drill string and each attitude control point.

[0060] This embodiment provides a method for real-time acquisition of drill string spatial position and attitude angle data and extraction of weak connection zone characteristics. A motion sensor group is arranged axially on the drill string body to collect original motion data. Specifically, a set of triaxial acceleration sensors and triaxial gyroscopes is installed every 0.5 meters on the drill string body to form a sensor network. The measurement ranges of these sensors are ±16g and ±2000° / s respectively, and the sampling frequency is 200Hz, which can capture the acceleration changes and angular velocity changes of the drill string in three-dimensional space in real time. The original data is transmitted to the data acquisition unit through the CAN bus for preliminary filtering to remove high-frequency noise. To compensate for the influence of local deformation of the drill string on position measurement, a strain sensor array is arranged around the installation point of each motion sensor group. The specific arrangement is as follows: 8 strain gauges are evenly arranged in the circumferential direction around the sensor installation point, with a measurement range of ±3000με and a sensitivity of 2mV / με. The collected strain data is used to establish the local deformation vector field of the drill string. Through interpolation fitting of multi-point strain values, the deformation distribution within a range of 200mm around the installation point can be obtained. The least squares method is applied to decompose this deformation field, and the displacement components of the sensor installation point in the radial and axial directions are calculated, with typical values of 0.2 - 1.5mm and 0.1 - 0.8mm respectively. These displacement values are eliminated from the original motion data to obtain the compensated real-time spatial position and attitude angle data of the drill string, with a position accuracy of up to ±3cm and an angle accuracy of up to ±0.5°.

[0061] When detecting the weak connection zone at the drill bit end, 12 groups of acoustic transducers are evenly arranged in the circumferential direction. Each group of transducers includes a transmitting unit and a receiving unit. The transmitting unit generates a narrow pulse ultrasonic signal with a frequency of 200kHz, a peak power of 50W, and a pulse width of 10μs. Adjacent transducer groups work in an alternating manner, and the transmitting time sequence interval is 5ms to avoid signal interference. When the detection distance is 300mm, the typical reflection signal intensity is -40dB to -60dB, and the signal-to-noise ratio is about 15 - 25dB.

[0062] The collected reflection signals are processed to enhance the boundary characteristics. The specific steps are as follows: First, the reflection signals are divided into 30 segments according to the propagation time, and each segment corresponds to a 10μs time window; then envelope extraction and phase alignment are performed on each segment of the signal; then phase superposition of adjacent 5 segments of the signal is carried out to enhance the response of continuous boundaries; finally, a mapping relationship table between the 360° scanning angle and the reflection signal amplitude is constructed, with a resolution of 1°. In practical applications, the signal amplitude at the boundary of the weak connection zone is usually 6 - 12dB higher than that of the surrounding rock mass, showing an obvious peak feature.

[0063] Identify the boundaries and density changes of the connecting band based on the above mapping relationship. When the amplitude of the reflected signal is continuously detected to be higher than the threshold (usually the average background noise plus 8 dB) in a certain angular direction and the continuous angular range exceeds 15°, it is determined that there is a weak connecting band. The intensity of the reflected signal is negatively correlated with the density of the connecting band. For every 3 dB increase in the amplitude of the reflected signal, the corresponding density of the connecting band decreases by about 20%. By marking the starting angle and ending angle of the high-amplitude region in the scanning result, determine the circumferential distribution range of the weak connecting band on the drill string. Combining the compensated real-time spatial position data of the drill string, using three-dimensional spatial coordinate transformation, map the local scanning result to the global coordinate system to determine the spatial distribution range and trend characteristics of the weak connecting band. For example, during a certain drilling process, a weak connecting band is detected at a position 15 - 30 cm in front of the drill bit. Significant reflected signals are detected in the range of 120° to 210° in the circumferential direction of the drill string, and the average signal intensity is -42 dB. Combining the analysis of the drill string position data, the trend of this connecting band is 40° east of north, the dip angle is about 65°, the width is about 25 cm, and the density is estimated to be 60% of the surrounding rock mass.

[0064] Calculate the position deviation between the drill string and each attitude control point. First, project the corrected real-time spatial position and attitude angle of the drill string onto the coordinate system where each attitude control point is located through spatial coordinate transformation. Attitude control points are usually set at key positions of the drill string trajectory, such as turning points, target horizons, etc. According to the strength and trend characteristics of the weak connecting band described above, establish the drill string force influence coefficient at each control point. Specifically, when the drill string passes through a weak connecting band with a strength of 60% of the standard rock mass, the force distribution on the drill bit is uneven, resulting in a drill string trajectory deviation coefficient of about 0.05 - 0.15 m / kN, depending on the intersection angle between the connecting band and the drill string axis.

[0065] When correcting each projected coordinate, consider the influence of drill string force deviation. For example, when a weak connecting band with a strength of 65% of the surrounding rock mass is detected at a 30° intersection angle in front of the drill string, the corresponding trajectory correction amount is 8 - 12 cm. Compare the corrected coordinates with the coordinates of the attitude control points, calculate the vector difference, and obtain the position deviation between the drill string and each attitude control point. In practical applications, this system can provide the three-dimensional deviation vector of the drill string relative to the control point in real time, with a typical accuracy of ±5 cm and an update frequency of 10 Hz, providing a basis for trajectory adjustment during drilling.

[0066] In this embodiment, it is possible to achieve high-precision real-time perception and deviation calculation of the position and attitude of the drill string in a complex formation environment. Compared with the existing positioning method that relies on a single sensor, this solution integrates the data of motion sensors and strain sensors to construct a local deformation vector field, effectively eliminating the interference of the self-deformation of the drill string on the pose measurement, and improving the accuracy of the spatial position and attitude angle from the source. At the same time, by arranging acoustic transducers and enhancing the phase superposition, the recognition ability of the boundary and density change of the weak connection zone is improved, enabling the drill string to accurately perceive the structural characteristics of the current drilling area. Combining spatial coordinate projection and the modeling of the influence of the force on the connection zone, the dynamic correction of the spatial deviation between the drill string and the attitude control point is realized. Solving the pose error problem caused by formation complexity and drill string deformation, finally realizing the timely discovery and accurate correction of path deviation during continuous drilling, and improving the trajectory tracking accuracy and drilling stability.

[0067] In an alternative embodiment, according to the position deviation and the distribution law of the weak connection zone, the real-time adjustment of the telescopic displacement of the drill bit, the bending deformation of the drill pipe, and the mud injection pressure parameters to keep the drill string moving along the obstacle avoidance trajectory includes: According to the magnitude of the position deviation and the distribution law of the weak connection zone, the drilling process is divided into a stable drilling section where the deviation is less than the preset deviation threshold and an obstacle avoidance adjustment section where the deviation is greater than the preset deviation threshold; When the drill string is located in the stable drilling section, the telescopic displacement of each quadrant of the drill bit is calculated based on the position deviation, and the bending deformation between adjacent drill pipe joints is determined according to the distribution law of the weak connection zone. An adjustment instruction is output according to the set ratio relationship between the telescopic displacement and the bending deformation; When the drill string is located in the rapid obstacle avoidance section, the optimal obstacle avoidance direction is calculated according to the distribution law of the weak connection zone. Based on the optimal obstacle avoidance direction, the circumferential arrangement position of the mud nozzle is determined. The mud injection pressure parameters of each nozzle are adjusted according to the circumferential arrangement position to form an obstacle avoidance propulsion force, and an adjustment instruction is output according to the obstacle avoidance propulsion force; Collect the movement trajectory of the drill string after executing the adjustment instruction, calculate the new position deviation, collect the force data of the drill string, evaluate the movement stability, and use the new position deviation and movement stability as evaluation parameters; Judge according to the evaluation parameters: when the new position deviation decreases and the movement stability meets the requirements, keep the current adjustment parameters; otherwise, return the new position deviation and movement stability as inputs, and recalculate the telescopic displacement of the drill bit, the bending deformation of the drill pipe, and the mud injection pressure parameters until the drill string keeps moving along the obstacle avoidance trajectory.

[0068] For example, before the drilling operation begins, the system pre-sets the position deviation threshold to 0.8 meters, and divides the drilling process into a stable drilling section with a deviation less than 0.8 meters and an obstacle avoidance adjustment section with a deviation greater than or equal to 0.8 meters. At the same time, the system determines the distribution characteristics of the weak connection zone through geological exploration data, including parameters such as azimuth, inclination, and layer thickness. For example, during the drilling process of a coal seam, it was found that the main weak connection zone was located at an azimuth of 45°, an inclination of 15°, and a layer thickness of about 1.2 meters.

[0069] When operating in the stable drilling section, the real-time position data of the drill tool is first collected. For example, the current position coordinates are (125.6, 78.3, -56.2) meters, the target position is (125.8, 78.5, -56.4) meters, and the position deviation is calculated to be 0.4 meters. Since the deviation is less than the preset threshold of 0.8 meters, the system determines that it is currently in the stable drilling section. The telescopic displacement of each quadrant of the drill bit is calculated based on the position deviation value. The drill bit is divided into four quadrants, corresponding to the upper, right, lower and left directions respectively. For the above-mentioned 0.4-meter deviation, the system calculates that the telescopic displacement of the first quadrant (upper direction) of the drill bit is +3.5 mm, the telescopic displacement of the second quadrant (right direction) is +2.8 mm, the telescopic displacement of the third quadrant (lower direction) is -1.6 mm, and the telescopic displacement of the fourth quadrant (left direction) is -1.2 mm. This asymmetric telescopic configuration can generate a resultant force in the target direction.

[0070] Taking into account the distribution law of the detected weak connection belt (azimuth angle 45°, inclination angle 15°), the bending deformation between adjacent drill pipe sections is determined. For each node of the drill pipe, the system sets a different bending deformation. For example, the bending deformation between the first and second nodes is 2.2 degrees, between the second and third nodes is 1.8 degrees, and between the third and fourth nodes is 1.5 degrees, which decreases successively to form a smooth bending profile, ensuring that the drill can move along the optimal path to avoid the weak connection belt.

[0071] According to the preset ratio of 1:5 between telescopic displacement and bending deformation (i.e., every 1 mm of telescopic displacement corresponds to 5 degrees of bending deformation), an adjustment instruction is generated and sent to the drill tool actuator through the drilling control system. For example, when the telescopic displacement in the first quadrant is +3.5 mm, the corresponding bending deformation control amount is 17.5 degrees. When the drill tool enters the obstacle avoidance adjustment section, if the position deviation increases to 0.9 meters and exceeds the preset threshold of 0.8 meters, the system automatically switches to the obstacle avoidance adjustment mode. At this time, the system first calculates the optimal obstacle avoidance direction based on the distribution law of the weak connection belt. Considering that the current weak connection belt is at an azimuth of 45°, the system determines that the optimal obstacle avoidance direction is an azimuth of 225° (i.e., avoiding the opposite direction of the weak area).

[0072] Based on the calculated optimal obstacle avoidance direction of 225°, adjust the circumferential arrangement position of the mud nozzles. The standard drill bit is equipped with 8 circumferentially evenly distributed mud nozzles. The system sets 3 nozzles within the range of 225° ± 30° (i.e., the nozzles in the 195° - 255° interval) as the low-pressure area, and 3 nozzles within the range of 45° ± 30° (i.e., the nozzles in the 15° - 75° interval) as the high-pressure area, and the remaining nozzles maintain the standard pressure. Precisely adjust the mud injection pressure parameters of each nozzle. The pressure of the nozzles in the high-pressure area is set to 18 MPa, the standard pressure area is set to 12 MPa, and the low-pressure area is set to 6 MPa. This pressure distribution forms an obstacle avoidance propulsion force towards the azimuth angle of 225°, with a value of approximately 2.5 kN, which is sufficient to guide the drill bit to avoid obstacles along the predetermined trajectory. The system sends these parameters to the mud pump control system as adjustment instructions.

[0073] After executing the adjustment instructions, the system collects the motion trajectory data of the drill string through the position sensors and gyroscopes built into the drill string. For example, 10 minutes after the adjustment, the position of the drill string is updated to (126.2, 78.9, -56.7) meters, and the new position deviation is reduced to 0.3 meters. At the same time, the system collects the force data of the drill string, including an axial force of 12.6 kN, a torque of 420 N·m, and a lateral force of 1.8 kN. Evaluate the motion stability by analyzing these data, mainly examining three parameters: the torque volatility is less than 8%, the drilling speed stability is higher than 92%, and the vibration amplitude is less than the critical value of 0.5 g. The currently measured torque volatility is 5.2%, the drilling speed stability is 96.3%, and the vibration amplitude is 0.32 g, all of which meet the stability requirements.

[0074] Based on the new position deviation of 0.3 meters (less than the threshold of 0.8 meters) and the motion stability meeting the requirements, it is decided to continue drilling while maintaining the current adjustment parameters. If the new position deviation does not decrease or the motion is unstable, the system will re-enter these data into the calculation unit, adjust the drill bit telescopic displacement, drill pipe bending deformation, and mud injection pressure parameters, and loop through the above steps until the drill string maintains stable motion along the predetermined obstacle avoidance trajectory.

[0075] Based on the above technical solution, it is possible to realize the dynamic deviation perception and adaptive adjustment control of the drill string in a complex formation environment, so that it can accurately advance along the obstacle avoidance trajectory while maintaining a stable posture. The prior art usually cannot respond in real time to the deviation and formation structure changes during drilling, with single adjustment means and lagging feedback, which easily leads to the drill bit deviating from the path or abnormal stress on the drill string. This application dynamically divides the drilling stage by introducing a combined criterion of position deviation and the distribution law of weak connection zones, and respectively matches applicable control strategies, maintaining smooth movement during the stable drilling stage and quickly generating optimal adjustment instructions during the obstacle avoidance adjustment stage. At the same time, combining three regulation methods of the drill bit telescopic displacement, drill pipe deformation and mud injection, a real-time closed-loop regulation mechanism is constructed to ensure that the adjustment process has the ability of continuous feedback and stability evaluation. Starting from improving the continuity of path tracking and the accuracy of obstacle avoidance adjustment, this solution effectively improves the problems of lagging response and low control accuracy in the prior art, and realizes the collaborative adaptive optimization of the drill string posture and path.

[0076] In the second aspect of the embodiments of the present invention, an electronic device is provided, including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method described above.

[0077] In the third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described above is realized.

[0078] The present invention can be a method, device, system and / or computer program product. The computer program product may include a computer-readable storage medium, on which computer-readable program instructions for executing various aspects of the present invention are loaded.

[0079] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. Intelligent control method for construction and drilling parameters of cobblestone formation bored piles, characterized in that, Including: An annular acoustic emission array is arranged at the end of the drill bit to collect the reflection signals of the detection acoustic wave among the cobblestones, perform spectral analysis and waveform superposition processing on the reflection signals, extract the attenuation characteristics and reflection characteristics of the acoustic wave in different media, and draw the cobblestone distribution density map within the three-dimensional space in front of the drill bit; According to the cobblestone distribution density map, identify the weak connection zones between adjacent cobblestones as passable areas. Within the passable areas, calculate the distances and direction angles from the center of gravity of the drill string to the centers of each weak connection zone, select the sequence of weak connection zones with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory, and set attitude control points on the obstacle avoidance trajectory; For each attitude control point, calculate the telescopic displacements of each quadrant part of the drill bit and the bending deformation amount of the drill pipe, and adjust the liquid outlet directions and injection pressures of the mud nozzles in each quadrant to form a directional softening channel, so that the drill string passes through each control point in sequence; Collect the spatial position and attitude angle data of the drill string in real time, extract the strength and trend characteristics of the weak connection zones in the current drilling area, calculate the position deviations between the drill string and each attitude control point, and adjust the telescopic displacement amount of the drill bit, the bending deformation amount of the drill pipe, and the mud injection pressure parameters in real time according to the position deviations and the distribution law of the weak connection zones, so that the drill string keeps moving along the obstacle avoidance trajectory.

2. The method according to claim 1, wherein Collecting the reflection signals of the detection acoustic wave among the cobblestones, performing spectral analysis and waveform superposition processing on the reflection signals, and extracting the attenuation characteristics and reflection characteristics of the acoustic wave in different media, and the steps for drawing the cobblestone distribution density map within the three-dimensional space in front of the drill bit include: Perform wavelet decomposition on the reflection signals to obtain energy components in different frequency bands, extract the amplitude attenuation rate and phase delay value of each frequency band signal, and calculate the change amount of acoustic impedance of the medium on the propagation path according to the attenuation degree difference of different frequency acoustic waves by the soil body and the cobblestones; Based on the mutation points of the acoustic impedance change amount, determine the spatial coordinates of the medium interface on the acoustic wave propagation path, use the spatial coordinates as the target positions, adopt the spatial beam synthesis method to perform delay superposition on the received reflection signals, and dynamically adjust the time delay compensation amount of each reflection signal according to the phase delay value, so that the echo signals at the target positions are in-phase enhanced; Divide the three-dimensional space in front of the drill bit into multiple layers of concentric circular grid voxels. For each voxel position, calculate the cobblestone existence probability value corresponding to the voxel position according to the echo signal intensity, phase delay value, and acoustic impedance change amount; Adopt a three-dimensional distance weight interpolation algorithm to perform continuous processing on the cobblestone existence probability values to generate the cobblestone distribution density map within the three-dimensional space in front of the drill bit.

3. The method according to claim 1, wherein According to the cobblestone distribution density map, identifying the weak connection zones between adjacent cobblestones as passable areas includes: Perform multi-scale density threshold segmentation on the cobblestone distribution density map, adopt an adaptive iterative method to determine the optimal segmentation threshold, and obtain the binary density image of the cobblestone area; Extract the pebble boundary contour from the binary density image. Use a morphological operator with an adjustable structural radius to perform a closing operation to eliminate the internal holes of the boundary, and use an edge-preserving morphological opening operation to smooth the boundary to obtain a regularized pebble area. Construct an anisotropic distance field for the regularized pebble area, adaptively adjust the distance weight based on density gradient information, and calculate a directional distance gradient map. Extract the continuous area with the maximum gradient value in the distance gradient map as the initial demarcation zone. Perform density sampling along the centerline of the initial demarcation zone to obtain a density sampling sequence. Based on the density sampling sequence, perform region growing, expand and mark the continuous area with a density value lower than the dynamic threshold as the weak connection zone, and perform morphological optimization on the weak connection zone to obtain the final passable area.

4. The method according to claim 1, wherein Within the passable area, calculate the distance and direction angle from the center of gravity of the drill string to the center of each weak connection zone. Select the sequence of weak connection zones with the shortest distance and the smallest change in direction angle as the obstacle avoidance trajectory, and set attitude control points on the obstacle avoidance trajectory, including: Classify the weak connection zones in the passable area according to their widths to obtain weak connection zones of different width levels. Extract the centerlines of the weak connection zones at each level and establish a multi-level weak connection zone network including the centerlines and transverse connection relationships. In the multi-level weak connection zone network, establish a dynamic coordinate system with the center of gravity of the drill string as the origin, and calculate the distance and direction angle from the center of gravity of the drill string to the centerlines of the weak connection zones. Construct a passage evaluation function based on the distance, direction angle, and transverse connection cost, where the transverse connection cost decreases as the width of the weak connection zone increases. Use the passage evaluation function to perform bidirectional search in the multi-level weak connection zone network: while expanding the search space forward from the current position to the target position, expand the search space backward from the target position to the current position. Determine the optimal expansion direction according to the evaluation function values in the two search directions, and select the sequence of weak connection zones with the minimum passage evaluation function value as the obstacle avoidance trajectory. Set attitude control points on the obstacle avoidance trajectory, and the spacing between adjacent attitude control points is proportional to the width of the corresponding weak connection zone. In the area where the width of the weak connection zone changes, add transition control points by minimizing the local curvature change rate to ensure the continuous and smooth transition of the trajectory.

5. The method according to claim 1, wherein For each attitude control point, calculate the telescopic displacement of each quadrant of the drill bit and the bending deformation of the drill pipe, and adjust the liquid outlet direction and injection pressure of the mud nozzles in each quadrant to form a directional softening channel, so that the drill string passes through each control point in sequence, including: Establish a local coordinate system at the attitude control point, divide the drill bit into four quadrants: upper, lower, left, and right, calculate the telescopic displacement of each quadrant of the drill bit, calculate the bending deformation of the drill pipe based on the drill pipe elastic deformation theory, and calculate the telescopic correction coefficient of each quadrant by taking the ratio of the telescopic displacement to the bending deformation. Collect the difference in rock hardness between each quadrant of the drill bit and the wellbore wall, calculate the rock breaking power ratio of each quadrant, and calculate the initial softening weight of each quadrant by multiplying the rock breaking power ratio by the telescopic correction coefficient. Based on the initial softening weight, the contact pressure between each quadrant of the drill bit and the wellbore wall, and the bending deformation amount of the drill pipe, the mud nozzles in each quadrant are initially adjusted to obtain the initial jet state parameters for each quadrant; The spatial deviation of the position and attitude control points of the drill string is collected in real time, the initial softening weight is corrected by combining the initial jet state parameters to obtain the real-time softening weight, and the jet pressure and liquid outlet direction of the mud nozzles in each quadrant are dynamically adjusted based on the real-time softening weight to form a directional softening channel, so that the drill string sequentially passes through each attitude control point.

6. The method according to claim 1, wherein The spatial position and attitude angle data of the drill string are collected in real time, the strength and trend characteristics of the weak connection zone in the current drilling area are extracted, and the position deviation between the drill string and each attitude control point is calculated, including: A group of motion sensors is axially arranged on the main body of the drill string to collect the original motion data; a strain sensor array is arranged around the installation points of the motion sensor group to establish a local deformation vector field of the drill string; the radial displacement and axial displacement of the sensor installation points are calculated by decomposing the deformation vector field, and the radial displacement and axial displacement are eliminated from the original motion data to obtain the compensated real-time spatial position and attitude angle of the drill string. A plurality of groups of acoustic transducers are arranged circumferentially at the end of the drill bit, and each group of transducers includes a transmitting unit and a receiving unit; adjacent transducer groups are controlled to alternately transmit detection signals and collect the reflected signals; the reflected signals are subjected to segmented phase superposition to enhance the boundary characteristics, and the corresponding relationship between the circumferential scanning angle of the drill string and the amplitude of the reflected signal is constructed; based on the corresponding relationship, the boundary of the connection zone and the change in density are identified, and the spatial distribution range and trend characteristics of the weak connection zone are determined in combination with the compensated real-time spatial position of the drill string. The corrected real-time spatial position and attitude angle of the drill string are projected onto the coordinate systems where each attitude control point is located through spatial coordinate transformation respectively. According to the strength and trend characteristics of the weak connection zone, the drill string force influence coefficients at each control point are established, the projection coordinates are corrected, and the vector difference between each corrected coordinate and the corresponding attitude control point is calculated to obtain the position deviation between the drill string and each attitude control point.

7. The method according to claim 1, wherein According to the position deviation and the distribution law of the weak connection zone, the telescopic displacement amount of the drill bit, the bending deformation amount of the drill pipe, and the mud jet pressure parameters are adjusted in real time to keep the drill string moving along the obstacle avoidance trajectory, including: According to the magnitude of the position deviation and the distribution law of the weak connection zone, the drilling process is divided into a stable drilling section with a deviation less than the preset deviation threshold and an obstacle avoidance adjustment section with a deviation greater than the preset deviation threshold; When the drill string is located in the stable drilling section, the telescopic displacement amount of each quadrant of the drill bit is calculated based on the position deviation, and the bending deformation amount between adjacent drill pipe joints is determined according to the distribution law of the weak connection zone. An adjustment instruction is output according to the set ratio relationship between the telescopic displacement amount and the bending deformation amount. When the drill string is located in the fast obstacle avoidance section, the optimal obstacle avoidance direction is calculated according to the distribution law of the weak connection zone, the circumferential arrangement position of the mud nozzles is determined based on the optimal obstacle avoidance direction, the mud jet pressure parameters of each nozzle are adjusted according to the circumferential arrangement position to form an obstacle avoidance propulsion force, and an adjustment instruction is output according to the obstacle avoidance propulsion force. Collect the movement trajectory of the drill tool after executing the adjustment instruction, calculate the new position deviation, collect the force data of the drill tool, evaluate the movement stability, and use the new position deviation and movement stability as evaluation parameters; Judge according to the evaluation parameters: when the new position deviation decreases and the movement stability meets the requirements, maintain the current adjustment parameters; otherwise, return the new position deviation and movement stability as inputs, and recalculate the bit telescopic displacement, drill pipe bending deformation, and mud injection pressure parameters until the drill tool maintains movement along the obstacle avoidance trajectory.

8. An electronic device, characterized in that, Including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images