Abrasion detection method and system of drill bit based on stone drilling

Abstract

The invention discloses a wear detection method and system for a drill bit based on stone drilling, and relates to the technical field of wear detection methods, a torque curve graph of the drill bit is determined based on the rotation torque of the drill bit, and a corresponding wear image is marked in a torque node in the torque curve graph; multiple curve graphs of the drill bit are determined according to the drilling curve graphs and the corresponding wear images, a drilling data set of the drill bit is determined according to recognition of the multiple curve graphs, the sub-wear condition of the drill bit is determined, and the sub-wear condition of the drill bit is further accurately controlled. The form of each functional part is determined based on the form of the drill bit, the wear form graph of the drill bit is determined according to the form of each functional part and each sub-wear condition, and the wear grade of each functional part is determined according to recognition of the wear form graph, so that the accuracy of the wear form graph of the drill bit is improved, and the wear detection accuracy of the drill bit is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wear detection methods, and in particular to a wear detection method and system for a drill bit based on stone drilling. Background Art

[0002] With the development of science and technology, drill bits are used to drill holes in stone bodies, and the parameters of the drill bits are adjusted so that the stone bodies can be drilled to different degrees along different drilling patterns. In the existing technology, the drill bits are in a state of continuous working for a long time and are gradually worn out with use. Generally, the surface image of the drill bit is detected and the corresponding wear features are marked. The wear condition of the drill bit is presented through the wear features, but the sub-wear condition of the drill bit is ignored. The accuracy of the multiple curve graphs of the drill bit cannot be guaranteed, thereby affecting the accuracy of the wear detection of the drill bit. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a wear detection method and system for a drill bit based on stone drilling.

[0004] An embodiment of the present invention provides a method for detecting wear of a drill bit in stone drilling, comprising: A real-time image of the tail of the drill bit during the drilling process is collected, and a drilling curve diagram is determined based on the real-time image and the shape of the drill bit; the real-time image is an image of the tail of the drill bit collected by a camera arranged in a radial extension direction of the tail of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; Determine a torque curve of the drill bit based on the rotational torque of the drill bit, and mark corresponding wear images at torque nodes in the torque curve; Determining a multiplexed graph of the drill bit based on the drilling graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiplexed graph to determine the sub-wear condition of the drill bit; The shapes of various functional parts are determined based on the shape of the drill bit, the wear shape map of the drill bit is determined according to the shapes of various functional parts and various sub-wear conditions, and the wear level of each functional part is determined based on the identification of the wear shape map.

[0005] An embodiment of the present invention provides a wear detection system for a drill bit used for stone drilling. The wear detection system for a drill bit used for stone drilling is applied to the above-mentioned wear detection method for a drill bit used for stone drilling. The wear detection system for a drill bit used for stone drilling includes: A real-time image module is used to capture real-time images of the rear end of the drill bit during the drilling process and determine a drilling curve diagram based on the real-time image and the shape of the drill bit; the real-time image is an image of the rear end of the drill bit captured by a camera arranged in the radial extension direction of the rear end of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; a wear image module, configured to determine a torque curve of the drill bit based on the rotational torque of the drill bit, and mark corresponding wear images at torque nodes in the torque curve; a sub-wear condition module for determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit; The wear level module is used to determine the shape of each functional part based on the shape of the drill bit, determine the wear shape map of the drill bit according to the shape of each functional part and each sub-wear condition, and determine the wear level of each functional part based on the identification of the wear shape map.

[0006] Compared with the prior art, the present invention has the following beneficial effects: In an embodiment of the present invention, a method in an embodiment of the present invention is used to collect real-time images of the tail of the drill bit during the drilling process, and a drilling curve graph is determined based on the real-time image and the shape of the drill bit; the real-time image is an image of the tail of the drill bit collected by a camera arranged in the radial extension direction of the tail of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; the torque curve graph of the drill bit is determined based on the rotational torque of the drill bit, and the corresponding wear image is marked at the torque node in the torque curve graph; a multiple curve graph of the drill bit is determined based on the drilling curve graph and the corresponding wear image, and a drilling data set of the drill bit is determined based on the recognition of the multiple curve graph to determine the sub-wear condition of the drill bit, and the wear image is introduced, which is compatible with the overall consideration of the drilling curve graph and the corresponding wear image, thereby improving the accuracy of the multiple curve graph of the drill bit and further accurately controlling the sub-wear condition of the drill bit.

[0007] Therefore, the morphology of each functional part is determined based on the morphology of the drill bit, the wear morphology diagram of the drill bit is determined according to the morphology of each functional part and each sub-wear condition, and the wear level of each functional part is determined based on the identification of the wear morphology diagram, thereby improving the accuracy of the wear morphology diagram of the drill bit, thereby determining the wear level of each functional part and improving the accuracy of wear detection of the drill bit. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 1 is a flow chart of a method for detecting wear of a drill bit based on stone drilling in an embodiment of the present invention; Figure 2 1 is a flow chart of step S11 in the wear detection method of a drill bit based on stone drilling in an embodiment of the present invention; Figure 3 1 is a flow chart of step S12 in the wear detection method of a drill bit based on stone drilling in an embodiment of the present invention; Figure 4 1 is a flow chart of step S13 in the wear detection method of a drill bit based on stone drilling in an embodiment of the present invention; Figure 5 1 is a flow chart of step S14 in the wear detection method of a drill bit based on stone drilling in an embodiment of the present invention; Figure 6 1 is a flow chart of step S15 in the wear detection method of a drill bit based on stone drilling in an embodiment of the present invention; Figure 7 Schematic diagram of the structure of a wear detection system for a drill bit based on stone drilling in an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0010] See also Figures 1 to 7 A wear detection method for a drill bit based on stone drilling is applied to the wear detection scenario of the drill bit; the wear detection method for a drill bit based on stone drilling includes: Step S11: capturing a real-time image of the tail of the drill bit during the drilling process, and determining a drilling curve diagram based on the real-time image and the shape of the drill bit; the real-time image is an image of the tail of the drill bit captured by a camera arranged in a radial extension direction of the tail of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; Step S12: determining a torque curve of the drill bit based on the rotational torque of the drill bit, and marking corresponding wear images at torque nodes in the torque curve; Step S13: determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit; Step S14: determining the morphology of each functional part based on the morphology of the drill bit, determining a wear morphology map of the drill bit according to the morphology of each functional part and each sub-wear condition, and determining the wear level of each functional part based on the identification of the wear morphology map; Step S15: Determine the remaining drilling workload of the drill bit based on the remaining drilling path of the stone body and the shape of the drill bit, and optimize the current drilling mode of the drill bit according to the remaining drilling workload of the drill bit, the wear level of each functional part, and the actual drilling posture of the drill bit to dynamically control the balance relationship between the wear levels of the functional parts; refer to Figure 2In step S11, the specific steps are: S111: real-time monitoring of the drilling process of the drill bit on the rock body. The drill bit drills the rock body while rotating, and a camera arranged in a radial extension direction of the tail of the drill bit is used to capture real-time images of the tail of the drill bit during the drilling process. Drilling characteristics of the drill bit at different time stages are determined based on recognition of each real-time image; the midpoint of the camera coincides with the extension line of the drill bit axis. S112: Capture images of the drill bit and the stone body, and determine the shape of the drill bit based on the recognition of the drill bit's outer image, determine the shape of the stone body based on the recognition of the stone body's image, determine the shape influence coefficient based on the shape of the drill bit and the shape of the stone body, and determine a corresponding drilling curve based on the shape influence coefficient, the real-time image, and the corresponding image shooting time. The drilling curve presents the force distribution of the drill bit during the drilling process.

[0011] In an embodiment of the present application, the drilling process of the drill bit on the stone body is monitored in real time, the drill bit drills the stone body in a rotating state, and the real-time image of the tail of the drill bit during the drilling process is determined under the capture of a camera arranged in the radial extension direction of the tail of the drill bit, and the drilling characteristics of the drill bit at different time stages are determined based on the recognition of each real-time image; the midpoint of the camera coincides with the extension line of the drill bit axis, thereby ensuring the accuracy of the drilling characteristics of the drill bit at different time stages.

[0012] At this time, a high-speed industrial camera (recommended 500fps or above) is used to continuously capture the tail of the drill bit, and an LED ring light source is used to ensure image quality. Monitoring parameters include key parameters such as drill speed (usually 100-2000rpm), feed speed (5-50mm / min), and drilling depth. A synchronous acquisition system is used to ensure that the image data and the timestamps of the working condition parameters accurately correspond.

[0013] The camera is installed in the radial extension direction of the drill bit tail, about 50-100 mm away from the drill bit tail. The midpoint of the camera coincides with the extension line of the drill bit axis, and the deviation is controlled within ±0.5 mm. The recommended resolution is 1920×1080 to ensure that the detailed features of the drill bit tail can be clearly captured. The vibration amplitude, yaw angle, speed stability and other features of the drill bit tail are extracted through image processing algorithms. The drilling process is divided into the initial stage (0-30 seconds), the stable stage (30 seconds-80% of the drilling depth), and the end stage (the last 20%). The feature changes in different time stages are compared to identify abnormal patterns.

[0014] Specifically, drill bit type: diamond core drill bit (diameter 50mm); stone material: granite (hardness level 6-7); drilling parameters: rotation speed 800rpm, feed speed 20mm / min, target hole depth 200mm; initial stage (0-30 seconds): the camera captured the vibration amplitude of the drill tail of 0.2mm and the deflection angle of 1.5°; image analysis showed that there was a slight impact when the drill bit contacted the stone body, but it stabilized after 3 seconds; feature recognition result: the initial contact was normal, with no signs of abnormal wear; stable stage (30 seconds-160mm depth): at a depth of 50mm, the camera detected that the vibration amplitude suddenly increased to 0.5mm; image analysis showed that the drill tail had periodic deflection, and the deflection angle increased to 3.2°; feature recognition result: the drill bit encountered hard inclusions inside the stone body, and it is recommended to reduce the feed speed.

[0015] Abnormal detection (at a depth of 120mm): The camera captured irregular vibrations at the tail of the drill bit, with an amplitude of 0.8mm. Image analysis revealed signs of fine cracks at the tail of the drill bit, and an unstable yaw angle (fluctuating between 2.5° and 4.5°). Feature recognition results indicated that the drill bit had experienced early fatigue damage, and it was recommended that the drill bit be inspected. End stage (160-200mm): The vibration amplitude remained at 0.6-0.7mm, and the yaw angle stabilized at around 3.8°. Image analysis revealed obvious signs of wear at the tail of the drill bit, but the working condition was relatively stable. Feature recognition results indicated that the drill bit had entered a state of moderate wear, and it was recommended that it be replaced after drilling.

[0016] Through real-time monitoring and feature recognition in step S111, the abnormal state of the drill bit at a depth of 120mm was successfully predicted, avoiding the drill bit breakage accident. During the entire drilling process, the system collected a total of 12,000 frames of images and identified three key wear stages, providing precise time node data for subsequent torque analysis and wear assessment.

[0017] Furthermore, images of the drill bit and the stone body are collected, and the shape of the drill bit is determined based on the recognition of the outer image of the drill bit, the shape of the stone body is determined based on the recognition of the image of the stone body, the morphological influence coefficient is determined based on the shape of the drill bit and the shape of the stone body, and the corresponding drilling curve graph is determined based on the morphological influence coefficient, the real-time image and the corresponding image shooting time. The drilling curve graph presents the force distribution of the drill bit during the drilling process, and is compatible with the overall consideration of the morphological influence coefficient, the real-time image and the corresponding image shooting time, thereby ensuring the accuracy of the corresponding drilling curve graph.

[0018] At this time, a binocular vision system is used to perform high-precision three-dimensional scans of the drill bit and the stone body respectively; for drill bit image acquisition, it is recommended to use an industrial-grade CCD camera (resolution not less than 24 million pixels) in combination with structured light projection technology to obtain accurate three-dimensional morphological data; drill bit acquisition: rotate 360° to scan, and acquire an image every 10°, for a total of 36 images, and reconstruct the complete drill bit shape through point cloud stitching; stone body acquisition: use a grid scanning method to divide the stone surface into a 5mm×5mm grid, and collect height, texture and hardness data at each grid point; use a point cloud registration algorithm (such as the ICP algorithm) to align and fuse the acquired images to generate a high-precision three-dimensional model.

[0019] The drill bit's morphology is determined through image recognition of its outer shape. The Canny edge detection algorithm is used to extract the drill bit's outline and identify key parameters such as the drill's diameter, length, and number of cutting edges. The SIFT (Scale-Invariant Feature Transform) algorithm is used to extract wear feature points on the drill bit's surface, such as the degree of cutting edge wear and surface roughness. Based on the extracted features, a support vector machine (SVM) or convolutional neural network (CNN) is used to classify the drill bit's morphology into categories such as "new drill bit," "lightly worn," "moderately worn," and "heavily worn." A drill bit morphology report is generated, including geometric parameters, wear status, and expected service life.

[0020] The stone's morphology is determined through image recognition, and the texture, cracks, and hardness distribution of the stone's surface are analyzed using image processing technology. For example, the roughness of the stone's surface is calculated using a gray-level co-occurrence matrix (GLCM). Based on the color and texture characteristics of the stone image and a regression model trained using historical data, the Mohs hardness of the stone is predicted (e.g., 6-7 for granite and 3-4 for marble). Image segmentation technology is used to identify cracks or cavities within the stone and assess their impact on the drilling process. A stone morphology report is generated, including surface roughness, hardness distribution, and structural characteristics.

[0021] The shape influence coefficient is determined according to the shape of the drill bit and the shape of the stone body. The shape of the drill bit and the shape of the stone body are introduced, multiple operations are performed on the shape of the drill bit and the shape of the stone body, and the shape influence coefficient is output. The calculation formula of the shape influence coefficient (K) is: ; in: : average hardness of the stone; : Material hardness of the drill bit; : Stone surface roughness; : drill surface roughness; : Current wear degree of the drill bit; : The baseline wear degree of a new drill bit; α, β, γ: Weight coefficients, calibrated by experimental data; Based on a large amount of experimental data, the weight coefficients are fitted using multivariate linear regression or neural network; for example, α=0.5, β=0.3, γ=0.2; The output result is the morphological influence coefficient K value, which is used to generate subsequent drilling curve diagrams.

[0022] The drilling curve is determined based on the morphological influence coefficient, real-time image, and corresponding image capture time. The data input is: morphological influence coefficient K; real-time image sequence (e.g., 10 frames per second); image capture timestamp; based on the real-time image, the vibration displacement of the drill tail is calculated using the optical flow algorithm; combined with the morphological influence coefficient K, the vibration displacement is converted into force distribution: ; in: F(t) : t The force at each moment; : t Vibration displacement at the moment; : Elastic modulus of the drill bit material; the calculated force distribution is plotted as a time series graph, with time on the horizontal axis and force on the vertical axis; the output result is a drilling curve graph, which intuitively shows the force distribution of the drill bit during the drilling process.

[0023] refer to Figure 3 In step S12, the specific steps are: S121: collecting various rotational torques of the drill bit during the drilling process, and constructing a corresponding rotational torque distribution map according to the various rotational torques and the shape of the drill bit; S122: Synchronizing the rotational torque distribution graph and the drilling curve graph based on the time dimension, and constructing a torque curve graph of the drill bit based on the rotational torque distribution graph and the drilling curve graph. In this case, the torque curve graph presents the vibration-rotational torque state at each time node; S123: Determine the dynamic area based on the identification of the torque curve of the drill bit, and determine the corresponding torque node according to the dynamic area and the vibration-rotation torque state. Each torque node presents the drilling condition of the drill bit and marks the corresponding wear image.

[0024] In an embodiment of the present application, various rotational torques of the drill bit during the drilling process are collected, and a corresponding rotational torque distribution diagram is constructed based on the various rotational torques and the shape of the drill bit, which is compatible with the overall consideration of the various rotational torques and the shape of the drill bit, thereby ensuring the accuracy of the corresponding rotational torque distribution diagram.

[0025] At this time, a non-contact torque sensor (such as magnetoelastic or optical) is used and installed between the drill spindle and the drive device to avoid signal interference caused by mechanical contact; sampling parameter settings: sampling frequency: 2000Hz (to ensure the capture of high-frequency vibration signals); sampling resolution: 16 bits (torque measurement accuracy of ±0.1N·m); synchronous acquisition: auxiliary parameters such as speed, feed rate, and axial force are recorded simultaneously; a 4th-order Butterworth low-pass filter (cutoff frequency 500Hz) is used, and a wavelet denoising algorithm is applied to retain the effective torque characteristics, and a built-in temperature sensor compensates for temperature drift in real time.

[0026] Data acquisition process: sensor zero point calibration, establishment of the baseline torque value, reading the torque raw data at a fixed time interval (0.5ms), removing outliers (data points exceeding ±3σ), and calculating the torque statistical characteristics within the sliding window (100ms).

[0027] A laser scanner was used to obtain the precise diameter (accuracy ±0.01 mm), and a profilometer was used to measure the cutting edge geometry. For wear assessment, the wear distribution was calculated by comparing it with the initial shape. Simultaneously, the collected torque data was arranged in a time series and corrected using the morphological influence coefficient. The torque change rate was calculated and a three-dimensional distribution plot was created: X-axis: time (0-t); Y-axis: torque value (0-T_max); Z-axis (color): torque change rate (blue = stable, red = drastic changes).

[0028] Optionally, a three-dimensional distribution graph is generated showing: time axis: 0-30 seconds complete drilling process; torque axis: 0-90 N·m range; color mapping: blue area (0-10 N·m / s change rate): stable drilling stage (0-2s, 25-30s); green area (10-20 N·m / s change rate): normal drilling stage (2-8s, 20-25s); yellow area (20-30 N·m / s change rate): transition stage (8-12s, 18-20s); red area (>30 N·m / s change rate): drastic change stage (12-18s).

[0029] Key feature analysis: Initial stage (0-2s): The torque rises rapidly from 0 to 65 N·m, and the rate of change stabilizes at around 15 N·m / s, indicating that the drill bit is cutting in normally; stable stage (2-8s): The torque fluctuates in the range of 65-80 N·m, with a rate of change <10 N·m / s, and the drilling state is stable; drastic change stage (12-18s): The torque fluctuates drastically in the range of 75-85 N·m, with a peak rate of change of 35 N·m / s, corresponding to the period of severe wear of the drill bit; end stage (25-30s): The torque gradually decreases to 45 N·m, indicating that the drill bit is about to penetrate the stone.

[0030] Furthermore, the rotational torque distribution diagram and the drilling curve diagram are synchronized based on the time dimension, and the torque curve diagram of the drill bit is constructed based on the rotational torque distribution diagram and the drilling curve diagram. At this time, the vibration-rotational torque state of each time node is presented in the torque curve diagram, which is compatible with the overall consideration of the rotational torque distribution diagram and the drilling curve diagram, ensuring the accuracy of the torque curve diagram of the drill bit.

[0031] At this time, a high-precision clock synchronization module (accuracy of ±0.1ms) is used to ensure the consistency of the time base of the torque data and image data. Torque data: the original sampling rate is 2000Hz, which is downsampled to 100Hz to improve processing efficiency. Image data: interpolated from 30fps to 100Hz, using cubic spline interpolation to ensure smoothness. The time delay between torque and image features is calculated, and system delays are automatically compensated. At the same time, the time alignment problem in the case of non-uniform sampling is handled.

[0032] Synchronization process: With drilling start time as t=0, create a 30-second time series (0-30s) and resample the torque data and image feature data to the same time point (at 0.01s intervals). Measure and compensate for the system delay between image acquisition and torque acquisition (typically 5-20ms). Verify synchronization accuracy using known events (such as the moment the drill bit contacts the rock).

[0033] Based on the rotational torque distribution diagram and the drilling curve diagram, a torque curve diagram of the drill bit is constructed, and multi-source data is weightedly fused, where: T(t): the fused torque value; T_torque(t): the original torque measurement value; T_image(t): the torque estimate derived from the image features; α(t): the dynamic weight coefficient (0.6-0.9, adaptively adjusted according to data quality); for vibration characteristics, vibration feature extraction: wavelet transform is used to extract the 5-100 Hz vibration component; a 0.5 Hz low-pass filter is used to extract the torque change trend; vibration intensity is calculated, and the RMS value represents the vibration intensity.

[0034] Torque curve construction: horizontal axis: time (0-30s, resolution 0.01s); vertical axis: torque (0-100N·m) and vibration intensity (0-10N·m); data layer: main torque curve (black thick line): shows the change of torque over time; vibration envelope (red area): indicates the vibration intensity range; feature point marking: key events (such as drill contact, penetration, etc.) are marked with special symbols; status area: different background colors are used to indicate different working states.

[0035] State characterization method: Vibration-torque phase space analysis: construct a two-dimensional feature space: the horizontal axis is the torque value, and the vertical axis is the vibration intensity; state clustering: the K-means algorithm is used to divide the data points into five state categories; state transition analysis: calculate the state transition probability matrix; real-time state recognition: where: S(t): state at time t; f: state discriminant function (based on support vector machine training); T(t): torque value; V(t): vibration intensity; dT / dt: torque change rate.

[0036] State coding: State A (green): normal drilling (torque 40-60 N·m, vibration <2 N·m); State B (blue): stable drilling (torque 60-80 N·m, vibration 2-4 N·m); State C (yellow): transition state (torque 80-90 N·m, vibration 4-6 N·m); State D (orange): drastic change (torque 90-100 N·m, vibration 6-8 N·m); State E (red): abnormal state (torque >100 N·m or vibration >8 N·m).

[0037] Optionally, taking granite drilling as an example (drill bit diameter 20mm, rotation speed 800rpm, feed rate 0.2mm / rev): Torque data: 2000Hz sampling, 60,000 data points in 30 seconds; Image data: 30fps, 900 frames in 30 seconds; Time delay measurement: Image acquisition is 12ms delayed than torque acquisition; Interpolation processing: The two sets of data are unified to the 100Hz time axis; Synchronous verification: The moment when the drill bit contacts the stone body appears at t=1.02s in both the torque data and the image data; Data fusion results: The fusion weight α(t) varies between 0.7-0.85; The correlation coefficient between the image-derived torque and the measured torque reaches 0.92; Vibration characteristics: High-frequency vibration (20-50Hz) is significantly enhanced during the wear period; The low-frequency trend reflects the overall working status of the drill bit.

[0038] Vibration-rotation torque state analysis: t=0-1s: startup phase; torque: 0→45 N·m; vibration: 0→1.5 N·m; state: A→B (normal drilling); characteristics: torque rises steadily, vibration is small; t=1-10s: stable drilling phase; torque: 45-75 N·m; vibration: 1.5-3.5 N·m; state: B (stable drilling); characteristics: torque and vibration remain relatively stable; t=10-15s: wear intensification phase; torque: 75→95 N·m; vibration: 3.5→7 N·m; state: →C→D (stable→transition→dramatic change); characteristics: torque continues to rise, vibration significantly intensifies ; t=15-20s: severe wear stage; torque: 90-105N·m; vibration: 6-9N·m; state: D→E (dramatic change→abnormal); characteristics: torque fluctuates violently and vibration exceeds the threshold; t=20-25s: drill bit failure stage; torque: 105→85N·m; vibration: 9→4N·m; state: E→D (abnormal→dramatic change); characteristics: torque drops suddenly and the drill bit is severely damaged; t=25-30s: penetration stage; torque: 85→40N·m; vibration: 4→1N·m; state: D→B→A (dramatic change→stable→normal); characteristics: torque drops rapidly and vibration weakens.

[0039] The torque curve clearly shows the following: the development of drill wear: starting from t=10s, the state gradually deteriorates from B to E; the critical warning point: at t=15s, the drill enters an abnormal state and the machine should be stopped for inspection immediately; the optimal replacement time: t=12-13s (state C) is the best time to replace the drill bit; and drilling efficiency optimization: the feed rate can be appropriately increased at t=5-10s (state B).

[0040] Therefore, the dynamic area is determined based on the identification of the torque curve of the drill bit, and the corresponding torque node is determined according to the dynamic area and the vibration-rotation torque state. Each torque node presents the drilling condition of the drill bit and marks the corresponding wear image, which is compatible with the overall consideration of the identification of the torque curve of the drill bit and ensures the accuracy of the dynamic area.

[0041] At this time, the torque curve of the drill bit was introduced, and the sliding window analysis method was used (window size 2 seconds, step size 0.1 second); the torque change rate within each window was calculated: ΔT / Δt; the dynamic area judgment threshold was set: low dynamic area: |ΔT / Δt|<5N·m / s; medium dynamic area: 5≤|ΔT / Δt|<15N·m / s; high dynamic area: |ΔT / Δt|≥15N·m / s; area boundary detection: wavelet transform is used to identify mutation points; boundary confirmation condition: 3 consecutive sampling points exceed the threshold; each dynamic area calculates: mean, variance, peak, peak-to-valley difference; vibration characteristics: RMS value, peak factor, kurtosis.

[0042] Dynamic area classification standards: Stable area (Class A): torque fluctuation <±5%, vibration <2N·m; Transition area (Class B): torque fluctuation 5-15%, vibration 2-5N·m; Change area (Class C): torque fluctuation 15-30%, vibration 5-8N·m; Severe area (Class D): torque fluctuation >30%, vibration >8N·m; Abnormal area (Class E): torque or vibration exceeds the safety threshold.

[0043] The corresponding torque nodes are determined according to the dynamic area and vibration-rotation torque state. The identification of torque nodes is introduced and multi-feature fusion judgment is performed, where: S_node: node significance score; w1-w4: weight coefficients (0.3, 0.3, 0.2, 0.2 respectively); T_norm: normalized torque value; V_norm: normalized vibration value; ΔT_norm: normalized torque change rate; ΔV_norm: normalized vibration change rate; node type definition: starting node (N_start): drilling start time; stable node (N_stable): low dynamic area center point; turning node (N_turn): dynamic area transition point; peak node (N_peak): local maximum torque point; valley node (N_valley): local minimum torque point; abnormal node (N_abnormal): point exceeding the safety threshold; end node (N_end): drilling end time; node screening conditions: significance score S_node>0.7; local extreme point (within ±0.5 seconds); state change point (dynamic area type change).

[0044] Five frames of images are collected before and after each torque node; image resolution: 1920×1080 pixels; exposure time: automatically adjusted (1 / 1000-1 / 10000 second); wear feature extraction: edge wear measurement: edge detection + sub-pixel analysis; wear area calculation: binarization + pixel statistics; wear morphology classification: normal, mild, moderate, severe, damaged; image tag content: timestamp: accurate to milliseconds; torque value: torque value of the current node; vibration value: vibration value of the current node; wear level: 0-4 levels (0 = normal, 4 = damaged); status code: AE type dynamic area code; warning information: normal, attention, warning, danger.

[0045] Specifically, taking granite drilling as an example (drill bit diameter Φ20mm, rotation speed 800rpm, feed rate 0.2mm / rev): dynamic area recognition results: t0-5s: Class A stable zone; torque range: 45-48N·m; vibration range: 1.2-1.8N·m; characteristics: the drill bit cuts in normally and the wear is slight; t5-10s: Class B transition zone; torque range: 48-65N·m; vibration range: 1.8-3.5N·m; characteristics: the drill bit begins to wear and needs attention; t10-15s: Class C change zone; torque range: 65-85N·m; vibration range: 3.5-6.2N·m; characteristics: wear is intensified and inspection is recommended; t15-20s: Class D severe zone; torque range: 85-105N·m; vibration range: 6.2-9.5N·m; characteristics: severe wear and should be stopped immediately.

[0046] Torque node determination results: N_start (t=0s): starting node; torque: 0 N·m; vibration: 0 N·m; state: before the drill bit contacts the rock; N_stable1 (t=2.5s): stable node; torque: 46.5 N·m; vibration: 1.5 N·m; state: normal drilling; N_turn1 (t=5.2s): turning node; torque: 48.2 N·m; vibration: 1.9 N·m; state: starting to enter the grinding stage Damage period; N_peak1 (t=12.3s): peak node; torque: 78.5N·m; vibration: 5.2N·m; status: moderate wear; N_abnormal (t=16.8s): abnormal node; torque: 98.7N·m; vibration: 8.9N·m; status: severe wear warning; N_end (t=25s): end node; torque: 42.3N·m; vibration: 3.8N·m; status: drilling completed.

[0047] Taking the N_abnormal node (t=16.8s) as an example: Image tag content: Timestamp: 00:00:16.800; Torque value: 98.7N·m; Vibration value: 8.9N·m; Wear level: 3 (severe); Status code: D; Warning information: Dangerous; Wear feature analysis: Cutting edge wear: 0.35mm (allowable value 0.2mm); Wear area: 28% of the total cutting area; Wear morphology: Cutting edge cracking and coating peeling; Handling suggestions: Immediately stop the machine for inspection; Replace the drill bit; Adjust the drilling parameters (reduce the feed rate by 30%).

[0048] refer to Figure 4 In step S13, the specific steps are: S131: collecting a drilling curve graph and corresponding wear images, and determining a first layer curve graph based on matching the drilling curve graph and each wear image in a time dimension; S132: determining a second curve graph based on the matching of the rotational torque distribution graph and the wear image in the time dimension, and constructing a multiple curve graph of the drill bit based on the first curve graph and the second curve graph; S133: In the multiple curve graph of the drill bit, a drilling data set represented by the torque nodes in the multiple curve graph is collected, the drilling strength of the drill bit is determined based on the identification of the drilling data set, and the sub-wear condition of the drill bit corresponding to each torque node is determined based on the drilling strength, shape, and material distribution of the rock body; In an embodiment of the present application, a drilling curve graph and corresponding wear images are collected, and a first-layer curve graph is determined based on the matching of the drilling curve graph and each wear image in the time dimension, which is compatible with the overall consideration of the matching of the drilling curve graph and each wear image in the time dimension, and ensures the accuracy of the first-layer curve graph.

[0049] At this point, drilling curves and corresponding wear images are collected. The following table describes the drilling curve acquisition system: Sensor configuration: A laser displacement sensor (accuracy ±0.01 mm) measures drilling depth in real time. Sampling parameters: 100 Hz sampling rate, 0.01 s recording timestamp accuracy. Data format: An array of time-depth correspondences, such as [(0.00 s, 0.0 mm), (0.01 s, 0.2 mm), …]. Wear image acquisition system: An industrial camera: A 5-megapixel global snapshot camera with a frame rate of 30 fps. Light source: A ring-shaped LED light source (adjustable brightness to avoid reflections). Image preprocessing: Denoising (median filtering), enhancement (contrast stretching), and edge detection (Canny operator). A PLC is used to uniformly control sensor and camera triggering. A GPS timing module ensures time consistency (error < 1 ms). Timestamps are used for naming, such as "drill_20230807_120000_001.tif."

[0050] The dynamic time warping (DTW) algorithm is used to process asynchronous data; the time window is set to a tolerance of ±0.1 seconds; the matching strategy is the nearest neighbor interpolation method; the matching quality assessment includes calculation of the matching success rate (target >95%), time deviation analysis (average deviation should be <0.05s), and outlier detection (abnormal matches are eliminated using the 3σ principle).

[0051] For the first-level curve graph, the curve graph structure is designed as follows: horizontal axis: time axis (0-30 seconds, resolution 0.1 second); left vertical axis: drilling depth (mm, range 0-300mm); right vertical axis: wear degree (%, range 0-100%); dual Y-axis display, distinguished by different colors; drilling depth data: directly use the sensor raw data; wear degree calculation: image processing process: grayscale → binarization → contour extraction → area calculation; wear degree formula: W%=(A_initial-A_current) / A_initial×100%; where A is the effective working area of ​​the drill bit; curve feature extraction: drilling rate: v=Δd / Δt (mm / s); wear change rate: ω=ΔW / Δt (% / s); feature point recognition: use the first-order derivative and second-order derivative to detect inflection points.

[0052] Specifically, the drilling object is granite (Mohs hardness 6.5); the drill bit type is a diamond core drill bit (diameter 100 mm); the drilling parameters are a rotation speed of 800 rpm and a feed rate of 2 mm / s. Drilling curve data segments are collected and synchronized with corresponding wear images. For example, the corresponding wear image (t = 10.0 s) is the image file wear_10.0s.tif. Processing results show a wear area of ​​15.2 mm² (initial area 20.0 mm²), a wear degree of 24%, and time matching results with a successful match rate of 97.3% and an average time deviation of 0.032 s. A first-level curve graph is introduced, as shown in Table 1: Table 1 First level curve

[0053] Drilling stage division: 0-5s: initial stage (stable wear); 5-15s: normal wear stage; 15-20s: accelerated wear stage (needs attention); key characteristic points: t=12.3s: wear rate mutation point (from 3.5% / s to 4.0% / s); t=18.7s: drilling rate drops significantly (from 1.8mm / s to 1.6mm / s).

[0054] Wear trend prediction: Linear regression fit: W%=0.5t+3.2 (R²=0.98); Predicted time to complete wear: t=(100-3.2) / 0.5≈193.6s (replacement required); Operational recommendations: At t=15s: Wear rate exceeds 4% / s, it is recommended to reduce the feed rate to 1.5mm / s; at t=20s: Wear reaches 68%, it is recommended to stop the machine and inspect the drill bit; Optimization plan: Starting at t=10s, gradually reduce the feed rate to extend the drill bit life by approximately 30%.

[0055] Furthermore, a second curve graph is determined based on the matching of the rotational torque distribution graph and the wear image in the time dimension, and a multiple curve graph of the drill bit is constructed based on the first curve graph and the second curve graph, which is compatible with the overall consideration of the matching of the rotational torque distribution graph and the wear image in the time dimension, and ensures the accuracy of the second curve graph.

[0056] At this point, the rotational torque distribution data comes from the torque data collected in step S121, with a sampling frequency of 1000 Hz and a time resolution of 1 ms. The torque data format is: [timestamp, torque value], such as [10.001 s, 45.2 N·m]. The wear image data comes from the image sequence collected in step S131, with each frame having a timestamp and a frame rate of 30 fps. The images have been preprocessed (denoising, enhancement, edge detection), and the wear area percentage (W%) has been extracted.

[0057] The dynamic time warping (DTW) algorithm was used to time-align the torque sequence and image sequence. The matching accuracy was 0.01 seconds, ensuring a one-to-one correspondence between torque changes and wear status. The second-order curve graph was constructed as follows: horizontal axis: time (unit: seconds); vertical axis: torque value (unit: N·m) and wear rate (unit: %). The curve format was a dual-vertical axis curve graph, with torque on the left and wear rate on the right. The data point format was [time, torque, wear rate], such as [10.00s, 45.2N·m, 12.5%].

[0058] Data review of the first-layer curve: from S131, it is a curve showing the change of drilling depth and wear rate over time; data point format: [time, depth, wear rate]; the first-layer curve and the second-layer curve are aligned and fused in the time dimension; the time axis is unified using time interpolation, and the time interval is set to 0.1 second; the format of the fused data is: [t, D(t), T(t), W(t)]; where: tt: time; D(t): drilling depth; T(t): rotational torque; W(t): wear rate.

[0059] Multiple curve chart construction: Use a four-axis coordinate system (or dual Y-axis + color mapping): X-axis: time (seconds); Y1-axis: drilling depth (mm); Y2-axis: torque (N·m); Y3-axis: wear rate (%); Optional: Use color mapping to indicate wear severity (e.g., green → yellow → red).

[0060] Therefore, in the multiple curve diagram of the drill bit, the drilling data set presented by the torque node in the multiple curve diagram is collected, the drilling strength of the drill bit is determined based on the identification of the drilling data set, and the sub-wear conditions of the drill bit corresponding to each torque node are determined based on the drilling strength, shape and material distribution diagram of the drill bit and the stone body. This is compatible with the overall consideration of the drilling strength, shape and material distribution diagram of the drill bit, ensuring the accuracy of the sub-wear conditions of the drill bit corresponding to each torque node. At the same time, the wear image is introduced, which is compatible with the overall consideration of the drilling curve diagram and the corresponding wear image, improving the accuracy of the multiple curve diagram of the drill bit and further accurately controlling the sub-wear conditions of the drill bit.

[0061] At this time, the definition of torque nodes: In the multi-curve graph, a torque node refers to the moment when the torque value changes significantly; the node judgment standard: the torque change rate is greater than 10N·m / s or the torque value exceeds the threshold; the node density: an average of one node is generated every 2 seconds (adjustable according to actual working conditions); each torque node collects the following data: timestamp (accuracy 0.01s).

[0062] Torque value (N·m); drilling depth (mm); wear rate (%); vibration amplitude (g); temperature (℃); data preprocessing: outlier removal: the 3σ criterion is used to remove abnormal data; data normalization: data of different dimensions are normalized to the interval [0,1]; missing value processing: linear interpolation is used to supplement missing data.

[0063] The drilling strength of the drill bit is determined based on the identification of the drilling data set. A multi-parameter weighted scoring method is used to score the drilling strength of the drill bit and divide it into intensity levels: 0-0.3: low intensity (green area); 0.3-0.6: medium intensity (yellow area); 0.6-1.0: high intensity (red area); a sliding window method (window size 5 seconds) is used to calculate the real-time intensity value; the intensity change rate is calculated to predict future intensity changes.

[0064] The sub-wear conditions corresponding to each torque node of the drill bit are determined according to the drilling strength, morphology and material distribution map of the stone body of the drill bit. The drilling strength, morphology and material distribution map of the drill bit are introduced, and the drill bit morphology is parameterized: key morphological parameters: tip angle (°); blade wear width (mm); drill diameter change rate (%); morphological data acquisition: real-time measurement through a machine vision system; stone material distribution map: material classification: granite, limestone, sandstone, etc.; material hardness distribution: using the Mohs hardness scale; material map construction: constructed through pre-drilling geological exploration data; sub-wear condition evaluation model: using a BP neural network model, with input parameters: drilling strength; drill bit morphological parameters; stone material hardness; working time; output parameters: blade wear rate (% / h); drill bit life consumption (%); expected remaining life (min).

[0065] Specifically, taking a granite drilling project as an example, the total drilling time is 20 seconds, and the drilling strength calculation is: torque: 58.5 / 80=0.73; depth: 20.1 / 30=0.67; vibration: 2.8 / 5=0.56; strength score: score=0.5×0.73+0.3×0.67+0.2×0.56=0.68; strength level: high strength (red area); drill bit morphological parameters: tip angle: 118° (original 120°); blade wear width: 0.3mm; drill bit diameter change rate: -0.5%; stone material: type: granite; Mohs hardness: 6.5; neural network evaluation results: blade wear rate: 2.3% / h; drill bit life consumption: 35%; expected remaining life: 45 minutes.

[0066] Key Node Analysis: At t=10s: Drilling Intensity: 0.68 (High Intensity); Sub-Wear: Blade Wear: Primarily Concentrated on the Main Cutting Edge; Wear Pattern: Crater Wear; Wear Cause: High-Intensity Cutting Due to High-Hardness Granite; Recommended Actions: Reduce the Feed Rate to 1.2mm / s; Increase Coolant Flow; Prepare a Spare Drill Bit. Precise analysis in step S133 enables: Accurately assessing drill bit sub-wear under specific operating conditions; providing data support for drill bit design optimization; establishing a drill bit life prediction model (error <15%); optimizing drilling process parameters (increasing efficiency by 30%); and reducing overall costs (reducing drill bit consumption by 40%).

[0067] refer to Figure 5 In step S14, the specific steps are: S141: Collect the shape of the drill bit, determine the shape of the functional parts of the drill bit based on the shape of the drill bit and the drilling condition of the drill bit on the rock body, each functional part shape assumes a corresponding function type, and marks the corresponding wear coefficient; S142: Determine a first sub-wear form based on the functional type corresponding to the functional part form and each sub-wear condition, determine a second sub-wear form map based on the functional type corresponding to the functional part form and the wear coefficient, and determine a wear form map of the drill bit based on the first sub-wear form, the second sub-wear form, and the force distribution map of the drill bit; S143: Determine wear data of the functional part morphology based on the wear morphology diagram of the drill bit and the relative positions of the functional part morphologies, and determine the wear level of each functional part according to a mapping relationship between the wear data and the corresponding wear level.

[0068] In an embodiment of the present application, the shape of the drill bit is collected, and the shape of the functional parts of the drill bit is determined based on the shape of the drill bit and the drilling conditions of the drill bit on the stone body. The shape of each functional part assumes the corresponding function type and is marked with the corresponding wear coefficient, which is compatible with the overall consideration of the shape of the drill bit and the drilling conditions of the drill bit on the stone body, and ensures the accuracy of the shape of the functional parts of the drill bit.

[0069] At this time, the drill bit shape is captured using a high-precision 3D laser scanner (such as the Keyence LJ-V7000 series) with a resolution of up to 0.01mm. The scanning method is non-contact laser scanning to avoid secondary damage to the drill bit. The scanning environment is a constant temperature and humidity laboratory to avoid thermal expansion and contraction errors caused by temperature changes.

[0070] Scanning process: Secure the drill bit on a rotating platform to ensure no shaking during scanning; set scanning parameters: Scanning speed: 30 mm / s; Point cloud density: 1000 points / mm²; Scanning angle: 360° full-range scanning; After scanning, generate high-precision point cloud data and convert it into a 3D model in STL format; Use point cloud processing software (such as Geomagic Control) for denoising and smoothing; Output a complete 3D model of the drill bit for subsequent functional part identification.

[0071] The functional parts of the drill bit mainly include: main cutting edge: undertakes the main cutting function and directly contacts the stone body; secondary cutting edge: assists in cutting and trims the hole wall; tool tip: positioning and guiding; chip groove: removes chips and reduces friction; tool body: provides structural support; based on geometric feature recognition: main cutting edge: identifies the sharpest edge at the front end of the drill bit; secondary cutting edge: identifies the auxiliary edge behind the main cutting edge; tool tip: identifies the vertex at the front end of the drill bit; chip groove: identifies spiral or straight groove structure; tool body: identifies the cylindrical part of the drill bit body; algorithm implementation: use edge detection algorithm (such as Canny edge detection) to extract key edges; combined with curvature analysis, distinguish different functional parts.

[0072] Drilling condition analysis: Based on the force distribution diagram during the drilling process (from step S11), analyze the actual force conditions of each functional part; for example, the main cutting edge is subjected to the greatest force and undertakes the main cutting task; the chip groove is subjected to less force, but must ensure smooth chip discharge.

[0073] The morphology of each functional part assumes the corresponding function type and is marked with the corresponding wear coefficient. Each functional part corresponds to a different function type: main cutting edge: cutting; secondary cutting edge: finishing; tool tip: guiding; chip groove: chip removal; tool body: support; the wear coefficient is calibrated according to historical data or experiments to reflect the wear sensitivity of each functional part during the drilling process; calibration method: through a large number of drilling experiments, the wear rate of each functional part is statistically analyzed; a wear coefficient database is established, for example: main cutting edge: 0.25 (high wear); secondary cutting edge: 0.15; tool tip: 0.20; chip groove: 0.10; tool body: 0.05; wear coefficient marking process: retrieve the wear coefficient of the corresponding drill model from the database; mark the wear coefficient to the corresponding functional part of the three-dimensional model; output the functional part morphology diagram with wear coefficient marking.

[0074] Furthermore, the first sub-wear form is determined according to the functional type corresponding to the functional part form and each sub-wear condition, the second sub-wear form diagram is determined according to the functional type and wear coefficient corresponding to the functional part form, and the wear form diagram of the drill bit is determined based on the first sub-wear form, the second sub-wear form and the force distribution diagram of the drill bit, which is compatible with the overall consideration of the first sub-wear form, the second sub-wear form and the force distribution diagram of the drill bit, thereby ensuring the accuracy of the wear form diagram of the drill bit.

[0075] At this time, each functional part (such as the main cutting edge, secondary cutting edge, tool tip, chip groove, tool body) corresponds to a specific function type (cutting, dressing, guiding, chip removal, support); for example: main cutting edge → cutting function; secondary cutting edge → dressing function; tool tip → guiding function; chip groove → chip removal function; tool body → support function.

[0076] Sub-wear condition refers to the degree of local wear of the drill bit under specific working conditions (such as different torque nodes, different stone materials); the data sources of sub-wear condition are: torque node analysis (such as torque node data in step S133); morphological change analysis (such as morphological changes of functional parts in step S141); force distribution analysis (such as drilling curve diagram in step S112).

[0077] The weighted superposition method is used to perform weighted superposition on the sub-wear conditions of each functional part according to the functional type. The formula is: ; Example of function category weights: Cutting function: 0.4 (most important); Dressing function: 0.2; Guide function: 0.2; Chip removal function: 0.1; Support function: 0.1.

[0078] The second sub-wear morphology diagram is determined based on the functional type and wear coefficient corresponding to the functional part morphology. The wear coefficient is the wear sensitivity of the functional part under specific working conditions (such as the wear coefficient marked in step S141). For example: main cutting edge: 0.25; secondary cutting edge: 0.15; tool tip: 0.20; chip groove: 0.10; tool body: 0.05.

[0079] Using matrix operations, the functional part morphology is multiplied by the wear coefficient to generate a wear distribution matrix; the formula for the second sub-wear morphology diagram is: second sub-wear morphology diagram = functional part morphology matrix × wear coefficient matrix; functional part morphology matrix: rows: functional parts (main cutting edge, secondary cutting edge, tool tip, chip groove, tool body); columns: morphological characteristics (such as length, width, angle, curvature, etc.); wear coefficient matrix: diagonal matrix, the diagonal elements are the wear coefficients of each functional part.

[0080] The wear morphology diagram of the drill bit is determined based on the first sub-wear morphology, the second sub-wear morphology, and the force distribution diagram of the drill bit. The force distribution diagram is the force conditions of various parts of the drill bit during the drilling process (such as the drilling curve diagram in step S112); data sources: torque sensor data; pressure sensor data; vibration sensor data.

[0081] A multi-source data fusion algorithm is used to fuse the first sub-wear morphology, the second sub-wear morphology, and the force distribution map. Formula: wear morphology map = α × first sub-wear morphology + β × second sub-wear morphology + γ × force distribution map. Weight coefficient examples: α = 0.4 (sub-wear condition weight); β = 0.3 (wear coefficient weight); γ = 0.3 (force distribution weight).

[0082] Therefore, the wear data of the functional part morphology is determined based on the wear morphology diagram of the drill bit and the relative position of the functional part morphology, and the wear level of each functional part is determined according to the mapping relationship between the wear data and the corresponding wear level. This is compatible with the overall consideration of the mapping relationship between the wear data and the corresponding wear level, and ensures the accuracy of the wear level of the functional part.

[0083] At this time, the wear morphology map: the output from step S142, contains the wear morphology values ​​of each functional part (such as main cutting edge: 30.148, secondary cutting edge: 18.148, tool tip: 18.148, chip groove: 12.148, tool body: 6.148); image format: grayscale image or heat map, the color depth indicates the degree of wear (dark = high wear).

[0084] Relative position of functional parts: Obtain an accurate geometric model of the drill bit through three-dimensional scanning (such as step S141); mark the spatial coordinates of each functional part in the model (such as the main cutting edge is located at [x1, y1, z1], and the secondary cutting edge is located at [x2, y2, z2]); define the coordinate system: the drill tip is the origin, the axial direction is the Z axis, and the radial direction is the XY plane.

[0085] Wear data extraction method: Use image registration technology to align the wear morphology map with the three-dimensional model; for each functional part, extract the wear morphology value of the corresponding area; formula: wear data = wear morphology value × position weight Wear data = wear morphology value × position weight; Position weight example: drill tip (tool tip): 1.2 (high weight, due to direct contact with the stone); main cutting edge: 1.0; secondary cutting edge: 0.8; chip groove: 0.5; tool body: 0.3.

[0086] Based on experimental data or industry standards, a mapping table between wear data and wear levels is established; for example, a wear level mapping relationship diagram is collected, as shown in Table 2: Table 2 Wear level mapping relationship diagram

[0087] For each functional part, the wear level is determined by querying the mapping table based on its wear data.

[0088] refer to Figure 6 In step S15, the specific steps are: S151: Acquire a drilling path of the drill bit relative to the stone body, determine a remaining drilling path of the stone body based on the drilling path of the drill bit relative to the stone body and the current position of the drill bit relative to the stone body; determine a remaining drilling area of ​​the drill bit based on the detection of the remaining drilling path of the stone body, and determine a remaining drilling workload of the drill bit based on the remaining drilling area of ​​the drill bit, a material distribution map of the stone body, and a shape of the drill bit; S152: Collecting the wear level of the functional parts and marking the actual drilling posture of the drill bit, determining a first optimization level of the drill bit based on the wear level of the functional parts and the remaining drilling workload of the drill bit, and determining a second optimization level of the drill bit based on the wear level of the functional parts and the actual drilling posture of the drill bit; S153: Determine the comprehensive optimization level of the drill bit based on the first optimization level and the second optimization level, match the corresponding optimization method according to the comprehensive optimization level of the drill bit, optimize the current drilling mode of the drill bit along the optimization method, and at the same time, monitor the wear level of the functional parts in real time, and determine the balance relationship of the wear level of each functional part according to the matching coefficient between the wear levels of the functional parts, so as to dynamically control the balance relationship of the wear level of the functional parts according to the optimization of the current drilling mode of the drill bit.

[0089] In an embodiment of the present application, the drilling path of the drill bit relative to the stone body is collected, and the remaining drilling path of the stone body is determined based on the drilling path of the drill bit relative to the stone body and the current position of the drill bit relative to the stone body; the remaining drilling area of ​​the drill bit is determined based on the detection of the remaining drilling path of the stone body, and the remaining drilling workload of the drill bit is determined based on the remaining drilling area of ​​the drill bit, the material distribution map of the stone body and the shape of the drill bit, which is compatible with the overall consideration of the remaining drilling area of ​​the drill bit, the material distribution map of the stone body and the shape of the drill bit, thereby ensuring the accuracy of the remaining drilling workload of the drill bit.

[0090] At this time, a high-precision laser tracker (such as Leica AT960) is used with an accuracy of ±0.01mm; it is equipped with a rotary encoder to record the angular changes of the drill bit during the drilling process; the data acquisition frequency is 100Hz to ensure that the path details are fully recorded; reference points (such as reflective marking points) are preset on the stone surface; the laser tracker tracks the position of the drill bit end in real time; the coordinate sequence of the drill bit in three-dimensional space (such as [x, y, z]) is recorded; and the drill bit posture (pitch angle, yaw angle, roll angle) is recorded synchronously.

[0091] The remaining drilling path of the stone body is determined based on the drilling path of the drill bit relative to the stone body and the current position of the drill bit relative to the stone body. The input data are: completed drilling path: the trajectory from the starting point to the current position; preset drilling path: the complete drilling design path (CAD model or G code); calculation method: remaining drilling path = preset drilling path - completed drilling path; use a path matching algorithm (such as dynamic time warping DTW) to align the completed path and the preset path.

[0092] The remaining drilling area of ​​the drill bit is determined based on the detection of the remaining drilling path of the stone body. Buffer analysis is used to generate a buffer zone with a width of the drill bit diameter with the remaining path as the center line; buffer zone width = drill bit diameter + safety gap (usually 10% of the drill bit diameter); for example: drill bit diameter: 10mm; safety gap: 1mm; buffer zone width: 11mm; remaining path: a straight line segment from (1,0,0.5) to (3,0,1.5); remaining drilling area: a rectangular area with a width of 11mm with the straight line segment as the center; output: a three-dimensional model of the remaining drilling area (STL format or point cloud data).

[0093] Determine the remaining drilling workload of the drill bit based on the remaining drilling area of ​​the drill bit, the material distribution map of the stone body, and the shape of the drill bit. Input data: Remaining drilling area: 3D model; Stone material distribution map: generated by CT scanning or spectral analysis, with the hardness of different materials marked (such as granite: Mohs hardness 7, marble: Mohs hardness 3); Drill bit shape: 3D scan model, with each functional part marked (such as primary cutting edge, secondary cutting edge, chip groove).

[0094] Workload calculation method: Volume calculation: Volume of the remaining drilling area = length × width × height; Example: Length 2m, width 0.011m, height 1m → Volume = 0.022m³; Material weighting: Calculate the proportion of different materials based on the material distribution map; Example: Granite accounts for 70%, marble accounts for 30%; Weighted hardness = (7×0.7)+(3×0.3)=5.8.

[0095] Drill shape correction: Correct the workload based on the wear coefficient of the functional part of the drill bit (such as the wear coefficient of the main cutting edge is 0.8); correction coefficient = 1 / wear coefficient = 1 / 0.8 = 1.25; final workload: workload = volume × weighted hardness × correction coefficient; example: 0.022 × 5.8 × 1.25 = 0.1595 (unit: hardness·volume); output: remaining drilling workload: 0.1595 (hardness·volume); workload distribution map: mark the workload intensity in different areas.

[0096] Furthermore, the wear level of the functional parts is collected and the actual drilling posture of the drill bit is marked. The first optimization level of the drill bit is determined based on the wear level of the functional parts and the remaining drilling workload of the drill bit. The second optimization level of the drill bit is determined based on the wear level of the functional parts and the actual drilling posture of the drill bit. This takes into account the overall consideration of the wear level of the functional parts and the actual drilling posture of the drill bit, ensuring the accuracy of the second optimization level of the drill bit.

[0097] At this time, wear level collection: use a high-precision industrial camera (such as Basler acA2440-75um) with a resolution of 5 million pixels; equip it with a ring light source to ensure uniform image illumination; use image processing software (such as Halcon) to extract wear features.

[0098] Acquisition process: After the drill bit stops, it rotates 360°, capturing images every 10°. The images are preprocessed (denoising and contrast enhancement). Wear characteristics of each functional area (such as edge blunting and coating shedding) are extracted. The wear grade (0-1, where 0 represents no wear and 1 represents complete wear) is calculated based on the wear characteristics.

[0099] Actual drilling posture marking: Use a six-axis posture sensor (such as the Xsens MTi-300) with an accuracy of 0.1°; synchronously record the drill bit's pitch, yaw, and roll angles. Marking process: Install a posture sensor on the drill spindle; record posture data in real time during the drilling process; combine it with the drilling path data to generate a posture-position correspondence.

[0100] The first optimization level of the drill bit is determined based on the wear level of the functional part and the remaining drilling workload of the drill bit. The input data are: wear level of the functional part (such as 0.7 for the main cutting edge); remaining drilling workload (such as 0.1595 hardness·volume).

[0101] Optimization logic: High-wear areas + high workload → the load on this area needs to be reduced; low-wear areas + low workload → the load on this area can be appropriately increased; Optimization goal: Balance the wear of each area and extend the life of the drill bit; Optimization algorithm: Use weighted scoring method: score = wear level × workload weight; workload weight = workload borne by this area / total workload; Optimization direction: High-scoring areas: reduce the speed and feed rate; low-scoring areas: maintain or increase the parameters; Output results: First optimization level: drilling parameter adjustment suggestions (such as speed and feed rate).

[0102] The second optimization level of the drill bit is determined based on the wear level of the functional parts and the actual drilling posture of the drill bit. The input data are: wear level of the functional parts (such as main cutting edge 0.7); actual drilling posture (such as pitch angle 5.0°); optimization logic: high wear parts + non-standard posture → posture adjustment is required; standard posture: pitch angle 0°, yaw angle 0°, roll angle 0°; optimization goal: reduce the impact of non-standard posture on high wear parts, and introduce posture deviation; wear-posture sensitivity: sensitivity = wear level × deviation; optimization direction: high-sensitivity parts: adjust the posture to the standard value; low-sensitivity parts: maintain the current posture; output result: second optimization level: posture adjustment suggestions (such as adjusting the pitch angle).

[0103] Through precise analysis of step S152, the following can be achieved: parameter optimization: dynamically adjusting drilling parameters based on wear level and workload; posture optimization: adjusting the drill bit posture based on wear level and actual posture; wear balance: balancing the wear level of each functional part through optimization; life extension: reducing the load on high-wear parts and extending the service life of the drill bit; efficiency improvement: after optimization, drilling efficiency is improved and downtime is reduced; this optimization method based on multi-source data fusion provides a scientific basis for drill bit wear detection and drilling mode optimization, and is a key link in realizing an intelligent drilling system.

[0104] Therefore, the comprehensive optimization level of the drill bit is determined based on the first optimization level and the second optimization level, and the corresponding optimization method is matched according to the comprehensive optimization level of the drill bit. The current drilling mode of the drill bit is optimized along the optimization method. At the same time, the wear level of the functional parts is monitored in real time, and the balance relationship of the wear level of each functional part is determined according to the matching coefficient between the wear levels of the functional parts. The balance relationship of the wear level of the functional parts is dynamically managed according to the optimization of the current drilling mode of the drill bit, and the overall consideration of the matching coefficient between the wear levels of the functional parts is compatible to ensure the accuracy of the balance relationship of the wear level of the functional parts. At the same time, the accuracy of the wear morphology diagram of the drill bit is improved to determine the wear level of each functional part and improve the accuracy of wear detection of the drill bit.

[0105] At this time, the comprehensive optimization level = the first optimization level + the second optimization level; example: first optimization level: speed reduced by 40%, feed rate reduced by 20%; second optimization level: pitch angle adjusted by 30%, yaw angle adjusted by 20%; comprehensive optimization level: speed: original value × 0.6; feed rate: original value × 0.8; pitch angle: original value × 0.7; yaw angle: original value × 0.8.

[0106] Select the optimization method based on the comprehensive optimization level: Method 1: Parameter optimization (adjusting speed and feed rate); Method 2: Attitude optimization (adjusting pitch angle and yaw angle); Method 3: Hybrid optimization (adjusting parameters and attitude at the same time); Example: Comprehensive optimization level involves parameters and attitude → select Method 3; Adjust drilling parameters and posture in real time; for example: original speed: 1000rpm → after optimization: 600rpm; original feed rate: 5mm / s → after optimization: 4mm / s; original pitch angle: 5° → after optimization: 3.5°; original yaw angle: 10° → after optimization: 8°.

[0107] Monitor the wear level of each functional part in real time; calculate the wear level matching coefficient: [text matching coefficient = 1-frac{text maximum wear level}-text minimum wear level{text maximum wear level}}]; Example: Maximum wear level: L4 (main cutting edge); Minimum wear level: L1 (chip groove, tool body); Matching coefficient = 1-(4-1) / 4 = 0.25; Dynamic adjustment: Matching coefficient < 0.3 → Balance control needs to be strengthened; Adjustment strategy: Reduce the burden on high-wear parts and increase the utilization of low-wear parts.

[0108] See also Figure 7 , Figure 7 : is a schematic diagram of the structural composition of a wear detection system for a drill bit for stone drilling in an embodiment of the present invention; the wear detection system for a drill bit for stone drilling comprises: A real-time image module 21 is used to capture real-time images of the rear end of the drill bit during the drilling process and determine a drilling curve diagram based on the real-time images and the shape of the drill bit; the real-time images are images of the rear end of the drill bit captured by a camera positioned in the radial direction of the rear end of the drill bit, with the midpoint of the camera coinciding with the extension line of the drill bit axis; a wear image module 22 for determining a torque curve of the drill bit based on the rotational torque of the drill bit, and marking corresponding wear images at torque nodes in the torque curve; a sub-wear condition module 23 for determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit; A wear level module 24 is configured to determine the morphology of each functional part based on the morphology of the drill bit, determine a wear morphology map of the drill bit based on the morphology of each functional part and each sub-wear condition, and determine the wear level of each functional part based on the identification of the wear morphology map; The optimization module 25 is used to determine the remaining drilling workload of the drill bit based on the remaining drilling path of the stone body and the shape of the drill bit, and optimize the current drilling mode of the drill bit according to the remaining drilling workload of the drill bit, the wear level of each functional part and the actual drilling posture of the drill bit, so as to dynamically control the balance relationship of the wear level of the functional parts.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for detecting wear of a drill bit for stone drilling, characterized in that: include: A real-time image of the tail of the drill bit during the drilling process is collected, and a drilling curve diagram is determined based on the real-time image and the shape of the drill bit; the real-time image is an image of the tail of the drill bit collected by a camera arranged in a radial extension direction of the tail of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; Determine a torque curve of the drill bit based on the rotational torque of the drill bit, and mark corresponding wear images at torque nodes in the torque curve; Determining a multiplexed graph of the drill bit based on the drilling graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiplexed graph to determine the sub-wear condition of the drill bit; The shapes of various functional parts are determined based on the shape of the drill bit, the wear shape map of the drill bit is determined according to the shapes of various functional parts and various sub-wear conditions, and the wear level of each functional part is determined based on the identification of the wear shape map.

2. The wear detection method of a drill bit based on stone drilling according to claim 1, characterized in that: The method includes collecting a real-time image of the tail of the drill bit during the drilling process, and determining a drilling curve diagram based on the real-time image and the shape of the drill bit; the real-time image is an image of the tail of the drill bit collected by a camera arranged in the radial extension direction of the tail of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis, including: The drilling process of the drill bit on the stone body is monitored in real time. The drill bit drills the stone body while rotating, and a camera set in the radial extension direction of the tail of the drill bit is used to determine the real-time image of the tail of the drill bit during the drilling process. The drilling characteristics of the drill bit at different time stages are determined based on the recognition of each real-time image; the midpoint of the camera coincides with the extension line of the drill bit axis; Images of the drill bit and the stone body are collected, and the shape of the drill bit is determined based on the recognition of the drill bit's external image. The shape of the stone body is determined based on the recognition of the stone body's image. The shape influence coefficient is determined based on the shape of the drill bit and the shape of the stone body. The corresponding drilling curve is determined based on the shape influence coefficient, the real-time image and the corresponding image shooting time. The drilling curve presents the force distribution of the drill bit during the drilling process.

3. The wear detection method of a drill bit based on stone drilling according to claim 1, characterized in that: The method of determining a torque curve of the drill bit based on the rotational torque of the drill bit and marking corresponding wear images at torque nodes in the torque curve graph includes: Collect the various rotational torques of the drill bit during the drilling process, and construct a corresponding rotational torque distribution map based on the various rotational torques and the shape of the drill bit; The rotational torque distribution graph and the drilling curve graph are synchronized based on the time dimension, and the torque curve graph of the drill bit is constructed based on the rotational torque distribution graph and the drilling curve graph. At this time, the torque curve graph presents the vibration-rotational torque state at each time node; The dynamic area is determined based on the identification of the torque curve of the drill bit. The corresponding torque node is determined according to the dynamic area and the vibration-rotation torque state. Each torque node presents the drilling condition of the drill bit and marks the corresponding wear image.

4. The wear detection method of a drill bit based on stone drilling according to claim 1, characterized in that: The step of determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit includes: Collecting a drilling curve graph and corresponding wear images, and determining a first curve graph based on matching the drilling curve graph and each wear image in a time dimension; A second curve graph is determined according to the matching of the rotational torque distribution graph and the wear image in the time dimension, and a multiple curve graph of the drill bit is constructed based on the first curve graph and the second curve graph.

5. The wear detection method of a drill bit based on stone drilling according to claim 4, characterized in that: The method further includes determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit. In the multiple curve diagram of the drill bit, the drilling data set presented by the torque node in the multiple curve diagram is collected, the drilling strength of the drill bit is determined based on the identification of the drilling data set, and the sub-wear conditions of the drill bit corresponding to each torque node are determined based on the drilling strength, shape and material distribution diagram of the drill bit and the stone body.

6. The wear detection method of a drill bit based on stone drilling according to claim 1, characterized in that: The method of determining the morphology of each functional part based on the morphology of the drill bit, determining a wear morphology diagram of the drill bit according to the morphology of each functional part and each sub-wear condition, and determining the wear level of each functional part based on the identification of the wear morphology diagram includes: Collect the shape of the drill bit, and determine the shape of the functional parts of the drill bit according to the shape of the drill bit and the drilling condition of the drill bit on the stone body. Each functional part shape assumes the corresponding function type and marks the corresponding wear coefficient; The first sub-wear form is determined according to the functional type corresponding to the functional part form and each sub-wear condition, the second sub-wear form diagram is determined according to the functional type and wear coefficient corresponding to the functional part form, and the wear form diagram of the drill bit is determined based on the first sub-wear form, the second sub-wear form and the force distribution diagram of the drill bit.

7. The wear detection method of a drill bit based on stone drilling according to claim 6, characterized in that: The method further includes determining the morphology of each functional part based on the morphology of the drill bit, determining a wear morphology map of the drill bit according to the morphology of each functional part and each sub-wear condition, and determining the wear level of each functional part based on the identification of the wear morphology map. The wear data of the functional part morphology is determined based on the wear morphology diagram of the drill bit and the relative positions of the functional part morphology, and the wear level of each functional part is determined according to the mapping relationship between the wear data and the corresponding wear level.

8. The wear detection method of a drill bit based on stone drilling according to claim 1, characterized in that: The wear detection method of the drill bit based on stone drilling also includes: The remaining drilling workload of the drill bit is determined based on the remaining drilling path of the stone body and the shape of the drill bit. The current drilling mode of the drill bit is optimized according to the remaining drilling workload of the drill bit, the wear level of each functional part and the actual drilling posture of the drill bit to dynamically control the balance relationship of the wear level of the functional parts.

9. The wear detection method of a drill bit based on stone drilling according to claim 8, characterized in that: The method of determining the remaining drilling workload of the drill bit based on the remaining drilling path of the stone body and the shape of the drill bit, optimizing the current drilling mode of the drill bit according to the remaining drilling workload of the drill bit, the wear level of each functional part and the actual drilling posture of the drill bit to dynamically control the balance relationship of the wear level of the functional parts includes: Acquire the drilling path of the drill bit relative to the stone body, and determine the remaining drilling path of the stone body based on the drilling path of the drill bit relative to the stone body and the current position of the drill bit relative to the stone body; determine the remaining drilling area of ​​the drill bit based on the detection of the remaining drilling path of the stone body, and determine the remaining drilling workload of the drill bit based on the remaining drilling area of ​​the drill bit, the material distribution map of the stone body, and the shape of the drill bit; Collecting the wear level of the functional parts and marking the actual drilling posture of the drill bit, determining the first optimization level of the drill bit based on the wear level of the functional parts and the remaining drilling workload of the drill bit, and determining the second optimization level of the drill bit based on the wear level of the functional parts and the actual drilling posture of the drill bit; Based on the first optimization level and the second optimization level, the comprehensive optimization level of the drill bit is determined, and the corresponding optimization method is matched according to the comprehensive optimization level of the drill bit. The current drilling mode of the drill bit is optimized along the optimization method. At the same time, the wear level of the functional parts is monitored in real time, and the balance relationship of the wear level of each functional part is determined according to the matching coefficient between the wear levels of the functional parts, so as to dynamically control the balance relationship of the wear level of the functional parts according to the optimization of the current drilling mode of the drill bit.

10. A wear detection system for a drill bit used for drilling a stone hole, characterized in that: The wear detection system for a drill bit for stone drilling is applied to the wear detection method for a drill bit for stone drilling as claimed in any one of claims 1 to 9, and the wear detection system for a drill bit for stone drilling comprises: A real-time image module is used to capture real-time images of the rear end of the drill bit during the drilling process and determine a drilling curve diagram based on the real-time image and the shape of the drill bit; the real-time image is an image of the rear end of the drill bit captured by a camera arranged in the radial extension direction of the rear end of the drill bit, and the midpoint of the camera coincides with the extension line of the drill bit axis; a wear image module, configured to determine a torque curve of the drill bit based on the rotational torque of the drill bit, and mark corresponding wear images at torque nodes in the torque curve; a sub-wear condition module for determining a multiple curve graph of the drill bit based on the drilling curve graph and the corresponding wear image, and determining a drilling data set of the drill bit based on the identification of the multiple curve graph to determine the sub-wear condition of the drill bit; The wear level module is used to determine the shape of each functional part based on the shape of the drill bit, determine the wear shape map of the drill bit according to the shape of each functional part and each sub-wear condition, and determine the wear level of each functional part based on the identification of the wear shape map.

Images