Electromagnetic adsorption type drilling actuator capable of achieving automatic feeding and automatic drilling method

Abstract

The invention provides an electromagnetic adsorption type drilling actuator capable of achieving automatic feeding and an automatic drilling method, and relates to the technical field of intelligent machining. The electromagnetic adsorption type drilling actuator comprises a drilling machine body, a connecting support, a feeding system, an electromagnetic adsorption device, an image sensing unit and a control system; the connecting support is slidably connected with the drilling machine body and fixedly connected with the tail end of the mechanical arm. The feeding system is fixedly arranged on the connecting bracket; a moving part of the feeding system is fixedly connected with the drilling machine body; the electromagnetic adsorption device is fixedly arranged on the connecting support, and the adsorption face of the electromagnetic adsorption device faces the feeding direction of the drilling machine body. The image sensing unit is fixedly arranged on the drilling machine body; and the control system is electrically connected with the drilling machine body, the feeding system, the electromagnetic adsorption device and the image sensing unit. A visual module is integrated on the aspect of the device, an executing mechanism with the real-time environment sensing capacity is constructed, and cooperative control of precise feeding transmission and self-adaptive adsorption is achieved through modular design.

Description

Technical Field

[0001] This invention relates to the field of intelligent machining technology, and more specifically, to an electromagnetic adsorption drilling actuator with automatic feed and an automatic drilling method. Background Technology

[0002] In the field of automated processing of ferromagnetic materials, existing drilling devices generally adopt a structural design combining electromagnetic adsorption and mechanical transmission. However, key functional modules are missing: Regarding the device itself, while traditional magnetic drills can achieve basic adsorption and fixation, the feed system largely relies on manual adjustment or open-loop motor control, lacking a high-precision displacement feedback mechanism, resulting in insufficient drilling depth control accuracy. Simultaneously, existing equipment lacks an integrated visual perception unit, and drilling point calibration relies entirely on manual visual alignment, making it difficult to adapt to the needs of complex surface feature recognition. Regarding drilling methods, conventional drilling processes use preset programs to control the feed rate, but do not consider the drill bit wear variables caused by differences in material hardness, easily leading to over-drilling or under-drilling defects. Although some research has attempted to introduce machine vision-assisted positioning, limitations such as the sensitivity of traditional image processing algorithms to lighting and poor robustness of feature extraction result in a high false recognition rate in practical applications, failing to meet industrial-grade accuracy requirements.

[0003] Based on the shortcomings of the existing technology, there is an urgent need for an electromagnetic adsorption drilling actuator with automatic feed and an automatic drilling method. Summary of the Invention

[0004] The purpose of this invention is to provide an automatically feeding electromagnetic adsorption drilling actuator and method to improve the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0005] In a first aspect, this application provides an automatically feedable electromagnetic adsorption type drilling actuator, comprising: a drilling rig body, a connecting bracket, a feeding system, an electromagnetic adsorption device, an image sensing unit, and a control system; the connecting bracket is slidably connected to the drilling rig body and fixedly connected to the end of a robotic arm; the feeding system is fixedly mounted on the connecting bracket, the moving part of the feeding system is fixedly connected to the drilling rig body, and drives the drilling rig body to move linearly on the connecting bracket; the electromagnetic adsorption device is fixedly mounted on the connecting bracket, the adsorption surface of the electromagnetic adsorption device facing the feeding direction of the drilling rig body; the image sensing unit is fixedly mounted on the drilling rig body; and the control system is fixedly mounted on the connecting bracket and electrically connected to the drilling rig body, the feeding system, the electromagnetic adsorption device, and the image sensing unit, respectively.

[0006] Furthermore, the drilling rig body includes a housing, a rack, a slider, a power assembly, a chuck, and a drill bit. The power assembly is fixedly disposed inside the housing. The drill bit is fixedly connected to the output shaft of the power assembly through the chuck. The housing is fixedly connected to the slider, and the slider assembly is fixedly connected to the rack.

[0007] Furthermore, the connecting bracket includes a guide rail, a first connecting bracket, a second connecting bracket, a third connecting bracket, and a fourth connecting bracket. The first connecting bracket is disposed below the slider, and the guide rail is fixedly disposed on the first connecting bracket, with the guide rail cooperating with the slider. The second bracket is fixedly disposed below the first bracket, and the feeding system is fixedly disposed inside the second bracket. The third bracket is perpendicular to the first bracket and fixedly connected to the electromagnetic adsorption device. The fourth bracket is disposed between the second bracket and the third bracket and is fixedly connected to the second bracket and the third bracket.

[0008] Furthermore, the feeding system includes a feeding motor and a transmission assembly. The transmission assembly is fixedly mounted on the connecting bracket, and the output end of the transmission assembly engages with the rack. The motor drives the rack to perform linear reciprocating motion through the transmission assembly.

[0009] Furthermore, the transmission assembly includes a first pinion, a first large gear, a first shaft, a second pinion, a second large gear, a second shaft, and a third large gear. The first pinion is fixedly connected to the output shaft of the feed motor. The first shaft and the second shaft are both fixedly mounted on the connecting bracket and are parallel to each other. The two ends of the first shaft are fixedly connected to the first large gear and the second pinion, respectively. The second large gear and the third large gear are fixedly mounted on the second shaft. The first large gear meshes with the first pinion, the second large gear meshes with the first large gear, and the third large gear meshes with the rack.

[0010] Secondly, this application provides an automatic drilling method, comprising:

[0011] Acquire image information of the target drilling area, wherein the image information is a depth image and an RGB image containing the drilling task stamp mark;

[0012] Image alignment is performed based on the image information to obtain registered image data;

[0013] Target recognition is performed based on the registered image data to obtain the pixel coordinates of the target drilling point and the drilling size parameters;

[0014] Based on the pixel coordinates, a coordinate transformation is performed to obtain the three-dimensional spatial coordinates of the drilling point;

[0015] Motion planning is performed based on the three-dimensional spatial coordinates and the borehole size parameters to generate a set of borehole operation instructions;

[0016] Closed-loop control is performed based on the drilling operation instruction set to obtain the drilling results.

[0017] The beneficial effects of this invention are as follows:

[0018] This invention utilizes controllable shock waves generated by low-frequency pulse discharge to effectively excite vibrations in the pores of the ore layer, promoting the shedding of blockages in the pores and significantly improving the permeability of sandstone uranium deposits. This invention allows for flexible settings and adjustments based on actual geological parameters to ensure optimal permeability enhancement under different ore layer conditions.

[0019] This invention integrates a vision module into the device, constructing an actuator with real-time environmental perception capabilities. Through modular design, it achieves coordinated control of precision feed transmission and adaptive adsorption. At the level of automatic drilling methods, it develops a target recognition algorithm based on deep learning to achieve high-precision extraction and spatial positioning of complex surface features. It dynamically optimizes control parameters by combining material properties, establishes a multivariable coupled control model of drilling depth-feed speed-drill bit rotation speed, and introduces a dual closed-loop evaluation mechanism for drilling quality. Through secondary imaging and feature analysis, it achieves online detection of drilling parameters and process self-optimization, significantly improving the system's adaptability and operational consistency under complex working conditions. Attached Figure Description

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a schematic diagram of the structure of the automatically feeding electromagnetic adsorption drilling actuator described in an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of the drilling rig body structure as described in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the connecting bracket structure described in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the feeding system structure described in an embodiment of the present invention;

[0025] Figure 5 This is a flowchart of the automatic drilling method described in an embodiment of the present invention.

[0026] The diagram shows the following components: 1. Drill rig body; 11. Housing; 12. Rack; 13. Slider; 14. Power assembly; 15. Chuck; 16. Drill bit; 2. Connecting bracket; 21. Guide rail; 22. First connecting bracket; 23. Second connecting bracket; 24. Third connecting bracket; 25. Fourth connecting bracket; 3. Feed system; 31. Feed motor; 32. Transmission assembly; 321. First pinion; 322. First gear; 323. First shaft; 324. Second pinion; 325. Second gear; 326. Second shaft; 327. Third gear; 4. Electromagnetic adsorption device; 5. Image sensing unit; 6. Control system. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides an electromagnetic adsorption-type drilling actuator with automatic feed capability, such as... Figure 1As shown, the system includes: a drilling rig body, a connecting bracket, a feeding system, an electromagnetic adsorption device, an image sensing unit, and a control system. The connecting bracket is slidably connected to the drilling rig body and fixedly connected to the end of the robotic arm. The sliding cooperation between the drilling rig body and the connecting bracket, combined with the fixed end of the robotic arm, forms a composite motion mechanism, ensuring equipment rigidity while providing multi-dimensional posture adjustment capabilities. The feeding system is fixedly mounted on the connecting bracket, and its moving part is fixedly connected to the drilling rig body, driving the drilling rig body to move linearly on the connecting bracket. The electromagnetic adsorption device is fixedly mounted on the connecting bracket, with its adsorption surface facing the feeding direction of the drilling rig body. The image sensing unit... The sensing unit is fixedly mounted on the drilling rig body. The image sensing unit is coaxially mounted with the drilling rig body. Through field-of-view optimization, it realizes blind-spot-free monitoring of the drilling point. At the same time, the image sensing unit collects and processes the image information during the drilling operation, thereby realizing image analysis such as drilling positioning, drilling depth identification, and drilling quality assessment. The control system is fixedly mounted on the connecting bracket and electrically connected to the drilling rig body, the feed system, the electromagnetic adsorption device, and the image sensing unit. The distributed architecture design of the control system realizes real-time fusion processing of multi-source signals (visual / force / pose), and constructs a closed-loop control link of "perception-decision-execution".

[0031] Preferably, the drilling rig body includes a housing, a rack, a slider, a power assembly, a chuck, and a drill bit. The power assembly is fixedly disposed inside the housing, and the drill bit is fixedly connected to the output shaft of the power assembly via the chuck. The housing is fixedly connected to the slider, and the slider assembly is fixedly connected to the rack. It should be noted that the drilling rig body features a stepped drill bit design with multi-stage cutting edges, which reduces the torque and axial force required for drilling while providing the hardware foundation for automatic drilling of different hole diameters.

[0032] Preferably, the connecting bracket includes a guide rail, a first connecting bracket, a second connecting bracket, a third connecting bracket, and a fourth connecting bracket. The first connecting bracket is disposed below the slider, and the guide rail is fixedly disposed on the first connecting bracket, with the guide rail and slider cooperating with each other. The second bracket is fixedly disposed below the first bracket, and the feeding system is fixedly disposed inside the second bracket. The third bracket is disposed perpendicular to the first bracket and is fixedly connected to it by an electromagnetic adsorption device. The fourth bracket is disposed between the second and third brackets and is fixedly connected to both the second and third brackets. The connecting bracket adopts an appropriate modular design to ensure the rationality of its structure, achieving both strength and lightweight design, and facilitating manufacturing while ensuring precision and ease of disassembly.

[0033] Preferably, the feeding system includes a feeding motor and a transmission assembly. The transmission assembly is fixedly mounted on the connecting bracket. The output end of the transmission assembly engages with the rack. The motor drives the rack to perform linear reciprocating motion through the transmission assembly.

[0034] Preferably, the transmission assembly includes a first pinion, a first large gear, a first shaft, a second pinion, a second large gear, a second shaft, and a third large gear. The first pinion is fixedly connected to the output shaft of the feed motor. The first shaft and the second shaft are both fixedly mounted on the connecting bracket and are parallel to each other. The two ends of the first shaft are fixedly connected to the first large gear and the second pinion, respectively. The second large gear and the third large gear are fixedly mounted on the second shaft. The first large gear meshes with the first pinion, the second large gear meshes with the first large gear, and the third large gear meshes with the rack.

[0035] Example 2:

[0036] This embodiment provides an automatic drilling method.

[0037] like Figure 5 As shown, this method includes steps S100 to S600.

[0038] Step S100: Obtain image information of the target drilling area. The image information is a depth image and an RGB image containing the drilling task stamp mark.

[0039] Step S200: Align the images according to the image information to obtain the registered image data;

[0040] Specifically, before aligning and fusing the RGB and depth images, the RGB and depth images are first aligned. The steps are as follows:

[0041] Step S210: Based on the intrinsic parameters of the depth camera, transform the depth pixel coordinate system to the depth camera coordinate system;

[0042] Let the pixel coordinates in the depth pixel coordinate system be (u d ,v d The intrinsic parameter matrix of the depth camera is M. d Pixel (u) d ,v d The value of ) is the perpendicular distance from the spatial point corresponding to the pixel to the depth camera, which is the z-coordinate of the spatial point in the depth camera coordinate system. dc The pixel coordinates (u) can be calculated. d ,v d In the three-dimensional coordinates (X) of the depth camera coordinate system dc ,Y dc Z dc The calculation formula is:

[0043]

[0044] Among them, u d and v d X represents the x and y coordinates of a pixel in the depth camera coordinate system. dcand Y dc Z represents the horizontal and vertical physical coordinates. dc These are the coordinates in the depth direction.

[0045] Step S220: Based on the extrinsic parameters of the depth camera and the RGB camera, transform the depth camera coordinate system to the RGB camera coordinate system;

[0046] Let the extrinsic parameter matrices of the depth camera and the RGB camera be... Its coordinates in the RGB camera coordinate system are obtained through coordinate transformation (X). rc ,Y rc Z rc The coordinate transformation relationship is as follows:

[0047]

[0048] in, It is a rotation matrix; X is the rotation vector; rc Y rc and Z rc The x-coordinate, y-coordinate, and depth coordinates of the target point under the RGB camera.

[0049] Step S230: Based on the intrinsic parameters of the RGB camera, transform the RGB camera coordinate system to the RGB pixel coordinate system;

[0050] Let the intrinsic parameter matrix of the RGB camera be M. r The pixel point in the RGB pixel coordinate system is (u r ,v r This allows us to obtain the coordinates (X, Y) in the RGB camera coordinate system. rc ,Y rc Z rc ) in the RGB pixel coordinate system (u r ,v r ):

[0051]

[0052] Among them, u r and v r These are the x and y coordinates of the pixel in the depth camera coordinate system.

[0053] Based on the above steps, it can be concluded that in an RGB image (u r ,v r The depth value corresponding to the pixel coordinates is in the depth image (u d ,v d The pixel value of coordinate Z dc .

[0054] Step S230: Fusion of RGB image and depth image;

[0055] Assuming the conversion ratio between depth pixels and length units (meters) is r, the 3D point cloud coordinates (x, y, x) of the target location feature point in the camera coordinate system can be obtained by fusing the pixel values ​​of the corresponding positions in the depth image and the target location feature point. sc ,y sc ,z sc The formula for the fusion process is as follows:

[0056]

[0057] Among them, u0 r v0 r fx r and fy r These are the intrinsic parameters of an RGB camera; x sc y sc and z sc This represents the x-coordinate, y-coordinate, and depth coordinates of the target location feature point in the camera coordinate system.

[0058] Step S300: Perform target recognition based on the registered image data to obtain the pixel coordinates of the target drilling point and the drilling size parameters;

[0059] Step S400: Perform coordinate transformation based on pixel coordinates to obtain the three-dimensional spatial coordinates of the drilling point;

[0060] Step S500: Perform motion planning based on three-dimensional spatial coordinates and drilling size parameters to generate a drilling operation instruction set;

[0061] Step S600: Perform closed-loop control based on the drilling operation instruction set to obtain the drilling results.

[0062] Further, step S300 includes steps S310 to S330.

[0063] Step S310: Target region detection processing is performed based on the RGB components in the registered image data. The bounding box coordinates containing the stamp region are generated using the YOLO model, and the initial pixel coordinates of the target drilling point are output using a spatial optimization algorithm.

[0064] This step performs stamp region detection based on an improved YOLO architecture, preferably the CS_YOLO model. It reduces computational complexity by introducing depthwise separable convolutions and employs a feature pyramid network to fuse multi-scale contextual information, enhancing robustness to local occlusion and illumination changes. A spatial optimization algorithm combines non-maximum suppression and bounding box regression correction to eliminate overlapping detection boxes and improve localization accuracy, outputting precise initial pixel coordinates.

[0065] Step S320: Extract text parameters based on bounding box coordinates. By cropping the specified sub-image region of the seal and applying optical character recognition technology, the drilling size parameters are obtained.

[0066] Understandably, within the bounding box area, an attention-based OCR model is used for text recognition: a convolutional neural network extracts local features of characters, a recurrent neural network models the contextual dependencies of character sequences, and a connection-time classification decoding outputs structured drilling parameters. This scheme effectively handles complex situations such as irregular character arrangement and uneven character spacing in seals through dynamic character segmentation technology.

[0067] Step S330: Perform spatial coordinate verification processing based on the initial pixel coordinates and the registered depth image. Correct the initial coordinates by establishing depth constraints and output the pixel coordinates.

[0068] It should be noted that this step employs a joint depth-space verification mechanism: First, a depth confidence map is constructed based on the registered depth image, and connected regions conforming to a preset thickness range are selected using a region growing algorithm. Then, a gradient descent search is performed within the initial coordinate neighborhood to find stable points with continuous depth and gentle gradient changes. This technique effectively suppresses depth measurement anomalies caused by surface reflections, oil contamination, and other interferences, ensuring spatial consistency of the output coordinates.

[0069] The three-stage processing from step S310 to step S330 forms a cascaded optimization process, which improves parameter accuracy while maintaining the real-time performance of the algorithm, thus meeting the online operation requirements of industrial scenarios.

[0070] Further, step S400 includes steps S410 to S430.

[0071] Step S410: Based on the pixel coordinates, obtain the depth measurement value of the corresponding position through bilinear interpolation algorithm, and construct the homogeneous coordinate transformation relationship from pixel coordinate system to camera coordinate system by combining the camera intrinsic parameter matrix, so as to obtain the three-dimensional coordinates of the target point in the camera coordinate system.

[0072] This process unifies the scale factor through homogeneous coordinate transformation, eliminates nonlinear distortions caused by perspective projection, and provides geometrically consistent initial data for subsequent coordinate transformations.

[0073] Step S420: Perform spatial coordinate transformation based on camera coordinate system coordinates. Using the rigid body transformation relationship described by the camera extrinsic parameter matrix, convert the three-dimensional coordinates in the camera coordinate system into spatial coordinates in the world coordinate system.

[0074] Understandably, this step utilizes a rigid body transformation described by an extrinsic parameter matrix to convert point cloud data in the camera coordinate system to the world coordinate system. Preferably, the spatial pose relationship is represented by a Lie group SE(3), preserving the rigid body characteristics (distance and angle invariance) during the transformation process and ensuring the spatial alignment accuracy of data from different sensors.

[0075] Step S430: Perform a transformation of the robot arm base coordinate system based on the world coordinate system coordinates, align the coordinate systems using the hand-eye calibration matrix, and output the operable three-dimensional space coordinates in the robot arm base coordinate system.

[0076] Preferably, this step eliminates singularities and abrupt errors in coordinate transformation through quaternion interpolation and smoothing filtering, outputting operable coordinates that conform to the kinematic constraints of the robotic arm. This multi-level transformation architecture effectively suppresses cumulative errors caused by factors such as equipment vibration and thermal deformation by introducing an online compensation mechanism for sensor calibration parameters, enabling the final positioning accuracy to reach the level of repeatability of the robotic arm and meeting the requirements of high-precision drilling operations.

[0077] Further, step S500 includes steps S510 to S530.

[0078] Step S510: Perform drill bit parameter matching processing based on the borehole size parameters. By establishing a stepped drill bit size database, determine the drill bit specification parameters and feed depth parameters corresponding to the target borehole diameter.

[0079] Understandably, this step involves constructing a hierarchical database of stepped drill bit dimensions and employing a fuzzy matching algorithm to associate the target hole diameter with drill bit specification parameters. By establishing a mapping model between drill bit geometry (such as cutting edge length and tip angle) and material removal rate, combined with feed depth constraints (such as minimum step size), the optimal drill bit combination and layered cutting parameters are dynamically selected to solve the efficiency bottleneck problem of traditional single-drill bit solutions when machining large-diameter holes.

[0080] Step S520: Perform motion path planning based on three-dimensional spatial coordinates, calculate the angle parameters of each joint through the inverse kinematics model of the robotic arm, and generate a sequence of motion trajectory points;

[0081] It should be noted that this step is based on the inverse kinematics model of the robotic arm, converting the three-dimensional spatial coordinates into joint angle spatial trajectories. An obstacle avoidance algorithm is introduced to generate a collision-free path point sequence in Cartesian space, and the joint motion curves are smoothed to eliminate mechanical vibrations caused by sudden velocity changes, ensuring the smoothness of the drilling process.

[0082] Step S530: Based on the motion trajectory point sequence, drill bit specification parameters and feed depth parameters, control commands are synthesized, and material property parameters are integrated to construct a control model, generating a drilling operation command set that includes speed curves, feed rate and feedback detection points.

[0083] Understandably, this step involves designing a multivariable coupled control model. This model integrates real-time material hardness detection data (such as hardness estimation based on cutting force feedback), drill bit wear parameters (assessed through vibration spectrum analysis), and preset process parameters to construct an adaptive PID controller. This model dynamically adjusts the feed rate curve and spindle speed to generate a set of operating instructions that includes force-position hybrid control commands, process monitoring points, and anomaly handling strategies.

[0084] Further, step S600 includes steps S610 to S630.

[0085] Step S610: Perform dynamic feed control processing according to the drilling operation instruction set, adjust the motion parameters of the drilling equipment in real time by constructing an adaptive PID control model, and output the drilling completion signal.

[0086] Understandably, this step employs a fuzzy adaptive PID control model, fusing real-time data from multiple sensors such as spindle torque and feed resistance to dynamically adjust the speed-feed coupling relationship. By establishing a cutting force-material removal rate state observer, abnormal conditions during the machining process (such as drill wear or sudden changes in material hardness) are identified, triggering a parameter self-tuning algorithm to ensure a constant cutting load under varying conditions and output a stable drilling completion signal.

[0087] Step S620: Perform quality inspection based on the drilling completion signal. By collecting hole feature data, extract the geometric features of the hole using an image segmentation algorithm, and calculate the actual drilling size parameters using a least squares circle fitting algorithm.

[0088] It should be noted that this step involves acquiring multi-angle images of the holes using a binocular vision system and employing a U-Net network for pixel-level hole contour segmentation. Anti-reflective filtering preprocessing and morphological post-processing are introduced to eliminate interference from metal surface reflections and extract edge point sets. A weighted least squares circle fitting algorithm, combined with an outlier removal mechanism, is applied to accurately calculate geometric parameters such as hole diameter and roundness, outputting robust actual size data.

[0089] Step S630: Make a quality assessment decision based on the actual borehole size parameters, calculate the comprehensive deviation index by establishing a multi-dimensional assessment model, and trigger the re-drilling process when the deviation exceeds the allowable threshold; otherwise, output the drilling results.

[0090] Preferably, this step uses geometric features extracted from hole image segmentation (including position offset, hole diameter deviation, roundness error, etc.) to dynamically allocate weight coefficients for each quality indicator and establish a comprehensive quality scoring model. A fuzzy inference mechanism is used to transform quantitative parameters into quality level assessments. When the comprehensive score is lower than a preset threshold, a coordinate correction is generated based on the position offset. Combined with the hole diameter error, the drill bit specifications and feed parameters are adjusted, and the motion control system is linked to perform secondary drilling. This solution overcomes the limitations of traditional single-threshold judgment, accurately identifying complex quality defects (such as position offset accompanied by hole diameter deviation) through multi-dimensional coupling analysis. Combined with case matching technology in the process knowledge base, the optimal repair strategy is intelligently selected, improving the drilling pass rate while reducing redundant processing times.

[0091] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An electromagnetic adsorption-type drilling actuator with automatic feed capability, characterized in that, include: Drilling rig body (1); The connecting bracket (2) is slidably connected to the drilling rig body (1) and fixedly connected to the end of the robotic arm; The feed system (3) is fixedly mounted on the connecting bracket (2). The moving part of the feed system (3) is fixedly connected to the drilling rig body (1) and drives the drilling rig body (1) to move linearly on the connecting bracket (2). An electromagnetic adsorption device (4) is fixedly installed on the connecting bracket (2), with the adsorption surface of the electromagnetic adsorption device (4) facing the feed direction of the drilling rig body (1). An image sensing unit (5) is fixedly mounted on the drilling rig body (1); The control system (6) is fixedly mounted on the connecting bracket (2) and is electrically connected to the drilling rig body (1), the feeding system (3), the electromagnetic adsorption device (4) and the image sensing unit (5) respectively.

2. The automatically feedable electromagnetic adsorption drilling actuator according to claim 1, characterized in that: The drilling rig body (1) includes a housing (11), a rack (12), a slider (13), a power assembly (14), a chuck (15), and a drill bit (16). The power assembly (14) is fixedly disposed inside the housing (11). The drill bit (16) is fixedly connected to the output shaft of the power assembly (14) through the chuck (15). The housing (11) is fixedly connected to the slider (13), and the slider assembly is fixedly connected to the rack (12).

3. The automatically feedable electromagnetic adsorption drilling actuator according to claim 2, characterized in that: The connecting bracket (2) includes a guide rail (21), a first connecting bracket (2), a second connecting bracket (23), a third connecting bracket (24), and a fourth connecting bracket (25). The first connecting bracket (2) is disposed below the slider (13). The guide rail (21) is fixedly disposed on the first connecting bracket (2). The guide rail (21) cooperates with the slider (13). The second bracket is fixedly disposed below the first bracket. The feeding system (3) is fixedly disposed inside the second bracket. The third bracket is perpendicular to the first bracket and is fixedly connected to the electromagnetic adsorption device (4). The fourth bracket is disposed between the second bracket and the third bracket and is fixedly connected to the second bracket and the third bracket.

4. The automatically feedable electromagnetic adsorption drilling actuator according to claim 2, characterized in that: The feeding system (3) includes a feeding motor (31) and a transmission assembly (32). The transmission assembly (32) is fixedly mounted on the connecting bracket (2). The output end of the transmission assembly (32) cooperates with the rack (12). The motor drives the rack (12) to perform linear reciprocating motion through the transmission assembly (32).

5. The automatically feedable electromagnetic adsorption drilling actuator according to claim 4, characterized in that: The transmission assembly (32) includes a first pinion (321), a first gear (322), a first shaft (323), a second pinion (324), a second gear (325), a second shaft (326), and a third gear (327). The first pinion (321) is fixedly connected to the output shaft of the feed motor (31). The first shaft (323) and the second shaft (326) are both fixedly mounted on the connecting bracket (2) and are parallel to each other. The two ends of the first shaft (323) are fixedly connected to the first gear (322) and the second pinion (324) respectively. The second gear (325) and the third gear (327) are fixedly mounted on the second shaft (326). The first gear (322) meshes with the first pinion (321), the second gear (325) meshes with the first gear (322), and the third gear (327) meshes with the rack (12).

6. An automatic drilling method, characterized in that, The method uses the automatically feedable electromagnetic adsorption drilling actuator according to any one of claims 1-5, and the method includes: Acquire image information of the target drilling area, wherein the image information is a depth image and an RGB image containing the drilling task stamp mark; Image alignment is performed based on the image information to obtain registered image data; Target recognition is performed based on the registered image data to obtain the pixel coordinates of the target drilling point and the drilling size parameters; Based on the pixel coordinates, a coordinate transformation is performed to obtain the three-dimensional spatial coordinates of the drilling point; Motion planning is performed based on the three-dimensional spatial coordinates and the borehole size parameters to generate a set of borehole operation instructions; Closed-loop control is performed based on the drilling operation instruction set to obtain the drilling results.

7. The automatic drilling method according to claim 6, characterized in that, Target recognition is performed based on the registered image data to obtain the pixel coordinates of the target borehole location and borehole size parameters, including: The target region is detected based on the RGB components in the registered image data. The bounding box coordinates containing the stamp region are generated using the YOLO model, and the initial pixel coordinates of the target drilling point are output using a spatial optimization algorithm. Based on the bounding box coordinates, text parameters are extracted and processed. By cropping a specified sub-image region of the seal and applying optical character recognition technology, the drilling size parameters are obtained. Spatial coordinate verification is performed based on the initial pixel coordinates and the registered depth image. The initial coordinates are corrected by establishing depth constraints, and the pixel coordinates are output.

8. An automatic drilling method according to claim 6, characterized in that, Coordinate transformation based on the pixel coordinates includes: Based on the pixel coordinates, the depth measurement value at the corresponding position is obtained through bilinear interpolation algorithm. Combined with the camera intrinsic parameter matrix, a homogeneous coordinate transformation relationship from the pixel coordinate system to the camera coordinate system is constructed to obtain the three-dimensional coordinates of the target point in the camera coordinate system. Based on the camera coordinate system coordinates, a spatial coordinate transformation is performed. Through the rigid body transformation relationship described by the camera extrinsic parameter matrix, the three-dimensional coordinates in the camera coordinate system are converted into spatial coordinates in the world coordinate system. The robot arm base coordinate system is transformed based on the world coordinate system coordinates. The coordinate system is aligned by the hand-eye calibration matrix, and the operable three-dimensional space coordinates in the robot arm base coordinate system are output.

9. An automatic drilling method according to claim 6, characterized in that, Motion planning based on the three-dimensional spatial coordinates and the borehole size parameters includes: Based on the borehole size parameters, drill bit parameter matching processing is performed. By establishing a stepped drill bit size database, the drill bit specification parameters and feed depth parameters corresponding to the target borehole diameter are determined. Motion path planning is performed based on the three-dimensional spatial coordinates. The angle parameters of each joint are calculated using the inverse kinematics model of the robotic arm, and a sequence of motion trajectory points is generated. Control commands are synthesized based on the motion trajectory point sequence, the drill bit specification parameters, and the feed depth parameters, and a control model is constructed by integrating material property parameters to generate a drilling operation command set that includes speed curves, feed rate, and feedback detection points.

10. An automatic drilling method according to claim 6, characterized in that, Closed-loop control is performed based on the aforementioned drilling operation instruction set to obtain drilling results, including: Dynamic feed control is performed according to the drilling operation instruction set. The motion parameters of the drilling equipment are adjusted in real time by constructing an adaptive PID control model, and a drilling completion signal is output. Quality inspection is performed based on the drilling completion signal. Hole feature data is collected, and the geometric features of the holes are extracted using an image segmentation algorithm. The actual drilling size parameters are then calculated using a least squares circle fitting algorithm. Quality assessment decisions are made based on the actual borehole size parameters. A multi-dimensional assessment model is established to calculate the comprehensive deviation index. When the deviation exceeds the allowable threshold, the re-drilling process is triggered; otherwise, the drilling result is output.

Images