A visual detection-based punching positioning method and system for a processing device

Abstract

The application provides a processing equipment punching positioning method and system based on visual detection, and relates to the technical field of numerical control visual punching positioning. The method comprises the following steps: performing coaxiality calibration on a workpiece, collecting geometric data of a workpiece reference hole and position data of a machine tool rotating center, and establishing a coordinate mapping relationship between a workpiece reference coordinate system and a machine tool coordinate system; performing pre-alignment positioning on a first pin hole, collecting a multi-exposure fusion image of the first pin hole, extracting a sub-pixel edge feature, and outputting position deviation data; correcting a hole position topology relationship model and generating a full hole position automatic detection sequence, performing full hole position cycle detection, and outputting a position deviation data set; performing error fusion correction on the data set to generate a numerical control processing instruction set, driving a processing equipment to sequentially complete drilling and reaming processing, thereby realizing workpiece automatic alignment and online visual detection, fusing multi-source error real-time compensation, significantly improving positioning accuracy and processing efficiency, and guaranteeing consistency and stability of batch processing.

Description

Technical Field

[0001] This invention relates to the field of CNC vision-based drilling and positioning technology, and in particular to a method and system for drilling and positioning in processing equipment based on vision inspection. Background Technology

[0002] In aerospace, energy equipment, and other fields, the machining accuracy of the circumferential pin holes in guide components directly affects the assembly performance and operational reliability of the entire machine. These components typically require micron-level precision in hole coaxiality and position.

[0003] In traditional machining methods, the coaxiality calibration of the workpiece and the machine tool's rotation center relies on manual operation. This is not only cumbersome and time-consuming, but also difficult to control due to random deviations introduced by manual operation, easily leading to excessive hole position deviations. Furthermore, existing machining methods cannot detect and compensate for dynamic errors such as deformation during machine tool operation and tool wear in real time; the continuous accumulation of these errors will disrupt machining consistency. In addition, traditional inspection is mostly offline, only conducted after machining is completed. By the time defective products are produced, time and material losses have already occurred, making it impossible to achieve closed-loop management of the machining process.

[0004] Therefore, it is necessary to provide a method and system for drilling and positioning in processing equipment based on vision inspection to solve the above-mentioned technical problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a visual inspection-based drilling positioning method and system for processing equipment. This system solves the problems of traditional circumferential hole processing technology, which relies on manual alignment, resulting in low positioning accuracy and processing efficiency. It also addresses the inability to compensate for clamping deviations, machine tool deformation, and tool wear errors in real time, making it difficult to ensure consistency in batch processing and the accuracy of finished products.

[0006] This invention provides a method for drilling and positioning in a processing equipment based on vision inspection, the method comprising: The workpiece is calibrated for coaxiality, and the geometric data of the workpiece reference hole and the position data of the machine tool rotation center are collected to establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system. Based on the coordinate mapping relationship, the first pin hole is pre-aligned and positioned, a multi-exposure fusion image of the first pin hole is acquired and sub-pixel edge features are extracted, and the positional deviation data of the first pin hole is output. Based on the position deviation data of the first pin hole, the hole position topology model is corrected and an automatic detection sequence of all holes is generated. The full hole position cyclic detection is performed and the position deviation dataset of all pin holes is output. The position deviation dataset of all pin holes is fused and corrected using multi-source error fusion to generate a set of CNC machining instructions that includes machine tool coordinate axis compensation and tool offset compensation, which drives the machining equipment to complete drilling and reaming in sequence.

[0007] Preferably, the step of calibrating the coaxiality of the workpiece, collecting the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, and establishing the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system includes: The vision guard on the spindle side of the control machine tool is automatically opened to acquire the front and side images of the workpiece reference hole, extract the center coordinates, diameter and axis perpendicularity of the workpiece reference hole, and generate the geometric data of the workpiece reference hole. The machine tool table is rotated three different angles in sequence. At each angle, the center coordinates of the workpiece reference hole are collected. The position coordinates of the machine tool rotation center are determined by the three-point circle method, and the position data of the machine tool rotation center is output. Based on the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, the clamping position of the workpiece is adjusted until the coaxiality error between the center of the workpiece reference hole and the machine tool rotation center is less than a preset coaxiality threshold, and the workpiece reference coordinate system with the center of the workpiece reference hole as the origin is established. Based on the origin coordinates and coordinate axis directions of the workpiece reference coordinate system, and combined with the inherent parameters of the machine tool coordinate system, the coordinate transformation matrix between the workpiece reference coordinate system and the machine tool coordinate system is calculated, and the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system is established.

[0008] Preferably, the step of pre-aligning and positioning the first pin hole based on the coordinate mapping relationship, acquiring a multi-exposure fusion image of the first pin hole and extracting sub-pixel edge features, and outputting the positional deviation data of the first pin hole includes: Based on the coordinate mapping relationship, the coordinates of the first pin hole are converted into a rotation angle in the machine tool coordinate system, and the machine tool table is driven to rotate to the rotation angle to pre-align and position the first pin hole; The light source controller of the vision system adjusts the brightness and illumination angle of the ring light source, and sequentially acquires three original images of the first pin hole with different exposures. The original images are then processed using multi-exposure fusion technology to generate the multi-exposure fused image. After performing grayscale conversion, median filtering, and edge detection on the multi-exposure fusion image, the sub-pixel edge features of the first pin hole are extracted, and the center coordinates of the first pin hole are obtained by fitting using the least squares method. The difference between the center coordinates of the first pin hole and the preset theoretical center coordinates is calculated to obtain the X-axis position deviation, Y-axis position deviation and rotation angle deviation of the first pin hole, and the position deviation data of the first pin hole is output.

[0009] Preferably, the step of correcting the hole position topology model based on the position deviation data of the first pin hole and generating an automatic detection sequence for all pin holes, performing cyclic detection of all pin holes, and outputting a dataset of position deviations for all pin holes includes: Based on the positional distribution and circumferential arrangement of all pin holes on the workpiece, a topological relationship model of the hole positions is established, and the offset and rotation of the topological relationship model of the hole positions are corrected according to the positional deviation data of the first pin hole. According to the revised hole position topology model, the machine tool table rotation angle, vision system photo triggering timing and image sampling resolution corresponding to each pin hole are calculated sequentially to generate the full hole position automatic detection sequence. The full hole position automatic detection sequence is executed to perform full hole position cyclic detection, that is, drive the machine tool table to rotate and index successively, trigger the vision system to acquire multi-exposure fusion images and extract sub-pixel edge features at each pin hole, and calculate the position deviation data of each pin hole in real time. Perform topological consistency verification on the positional deviation data of all pin holes, remove abnormal deviation data that do not conform to the hole spacing rules and circumferential distribution rules, and output the positional deviation dataset of all pin holes.

[0010] Preferably, the step of performing full-hole position cyclic detection according to the full-hole position automatic detection sequence, that is, driving the machine tool table to rotate and index successively, triggering the vision system to acquire multi-exposure fused images and extract sub-pixel edge features at each pin hole, and calculating the position deviation data of each pin hole in real time, includes: According to the full hole position automatic detection sequence, drive the machine tool table to rotate to the current pin hole, trigger the vision system to acquire the multi-exposure fusion image and extract the sub-pixel edge features; Calculate the current pin hole position deviation data and perform trend analysis with the previous pin hole position deviation data to determine whether there is a systematic position deviation; If the systemic positional deviation is determined to exist, the rotation angle of the machine tool table and the timing of the vision system's photo capture are corrected in real time for all subsequent pin holes, and the remaining part of the full hole position automatic detection sequence is updated. Repeat the above steps until all pin holes have been inspected.

[0011] Preferably, the step of performing multi-source error fusion correction on the position deviation dataset of all pin holes to generate a CNC machining instruction set including machine tool coordinate axis compensation and tool offset compensation includes: Analyze the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole in the position deviation data of all pin holes, and calculate the basic compensation amount of the machine tool X-axis, machine tool Y-axis, and machine tool rotation axis corresponding to each pin hole; Temperature data of the machine tool spindle and guide rail are collected, and the basic compensation amount is corrected for thermal deformation error using a thermal deformation error model to obtain the compensation amount of the machine tool coordinate axis. Retrieve the current tool wear data from the tool life management system, calculate the tool radius wear and tool length wear, and generate the corresponding tool offset compensation amount; The machine tool coordinate axis compensation amount and the tool offset compensation amount are integrated into the CNC machining program, the machining sequence of each pin hole is adjusted, the CNC machining instruction set is generated and sent to the machine tool CNC system.

[0012] Preferably, the step of analyzing the position deviation data of all pin holes includes the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole, and calculating the basic compensation amount of the machine tool X-axis, machine tool Y-axis, and machine tool rotation axis corresponding to each pin hole, including: The X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole are classified into random error compensation amount and systematic error compensation amount; The systematic error compensation amounts of all pin holes are weighted and averaged to generate global compensation coefficients for all pin holes. The random error compensation amount for each pin hole is processed separately to generate a local compensation amount corresponding to each pin hole; The global compensation coefficient corresponding to all pin holes is superimposed with the local compensation amount corresponding to each pin hole to obtain the basic compensation amount of the machine tool X-axis, the machine tool Y-axis and the machine tool rotary axis corresponding to each pin hole.

[0013] Preferably, the driving processing equipment sequentially completes drilling and reaming, including: According to the CNC machining instruction set, the machine tool is driven to automatically change the drilling tool and drill the first pin hole. After drilling is completed, the vision system is controlled to visually inspect the hole position and calculate the actual position deviation and hole diameter deviation after drilling. If the actual position deviation and the hole diameter deviation after drilling are within the preset position deviation allowable range and the preset size deviation allowable range, respectively, the machine tool will automatically change the reamer and perform reaming on the hole. After the reaming is completed, the quality of the reamed hole is inspected online. If the online visual inspection result is unqualified, the reamer offset is adjusted and the reaming is repeated until all holes are qualified.

[0014] A vision-based inspection-based drilling positioning system for processing equipment, the system comprising: The coordinate mapping module is used to calibrate the coaxiality of the workpiece, collect the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, and establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system. The single-hole positioning module is used to pre-align and position the first pin hole based on the coordinate mapping relationship, acquire a multi-exposure fusion image of the first pin hole and extract sub-pixel edge features, and output the position deviation data of the first pin hole. The full-hole detection module is used to correct the hole position topology model based on the position deviation data of the first pin hole and generate an automatic full-hole detection sequence, perform full-hole cyclic detection and output the position deviation dataset of all pin holes; The driving machining module is used to perform multi-source error fusion correction on the position deviation dataset of all pin holes, generate a set of CNC machining instructions including machine tool coordinate axis compensation and tool offset compensation, and drive the machining equipment to complete drilling and reaming in sequence.

[0015] Compared with related technologies, the visual inspection-based drilling positioning method and system for processing equipment provided by this invention has the following advantages: This invention establishes a coordinate mapping relationship between the workpiece's reference coordinate system and the machine tool's coordinate system by calibrating the workpiece's coaxiality and collecting the geometric data of the workpiece's reference hole and the position data of the machine tool's rotation center. Based on this coordinate mapping relationship, the first pin hole is pre-aligned and positioned. A multi-exposure fusion image of the first pin hole is collected, and sub-pixel edge features are extracted to output the position deviation data of the first pin hole. The hole position topology model is corrected based on the position deviation data of the first pin hole, and an automatic detection sequence for all holes is generated. The automatic detection sequence for all holes is executed, and the position deviation dataset of all pin holes is output. Multi-source error fusion correction is performed on the position deviation dataset of all pin holes to generate a CNC machining instruction set that includes machine tool coordinate axis compensation and tool offset compensation. This instruction drives the machining equipment to sequentially complete drilling and reaming, thereby achieving automatic workpiece alignment and online visual inspection. By fusing multi-source error real-time compensation, a closed-loop machining control is formed, significantly improving positioning accuracy and machining efficiency, and ensuring the consistency and stability of batch processing.

[0016] This invention, based on online visual inspection technology, achieves automatic coaxiality calibration of workpieces and precise positioning of pin holes, replacing manual alignment processes and significantly improving positioning accuracy and processing efficiency. Employing adaptive imaging technology, it effectively avoids interference from metal surface reflections, improving the accuracy and stability of hole feature extraction. By constructing a hole topology model and dynamically optimizing the detection path, it achieves fully automated cyclic inspection of all hole positions, greatly optimizing inspection efficiency. Comprehensive compensation for multiple errors related to clamping, machine tools, and cutting tools effectively offsets the impact of dynamic errors, ensuring consistency in batch processing. Integrating online quality verification throughout the processing process forms a closed-loop control system, promptly identifying and correcting processing deviations, reducing scrap losses. This invention is suitable for batch processing of high-precision parts such as guides, significantly improving processing quality and production stability, and possesses significant engineering application value and industry promotion significance. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a vision-based inspection-based drilling and positioning method for a processing equipment, provided as an embodiment of the present invention; Figure 2 A system block diagram of a vision-based inspection-based drilling and positioning system for processing equipment is provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 The diagram shown is a flowchart of a vision-based inspection-based drilling and positioning method for processing equipment, provided by an embodiment of the present invention. Figure 1The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S4 are detailed as follows: S1. Perform coaxiality calibration on the workpiece, and collect the geometric data of the workpiece reference hole and the position data of the machine tool rotation center to establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system.

[0020] The process of calibrating the coaxiality of the workpiece, collecting the geometric data of the workpiece's reference hole and the position data of the machine tool's rotation center, and establishing the coordinate mapping relationship between the workpiece's reference coordinate system and the machine tool coordinate system includes: The vision guard on the spindle side of the control machine tool is automatically opened to acquire the front and side images of the workpiece reference hole, extract the center coordinates, diameter and axis perpendicularity of the workpiece reference hole, and generate the geometric data of the workpiece reference hole. The machine tool table is rotated three different angles in sequence. At each angle, the center coordinates of the workpiece reference hole are collected. The position coordinates of the machine tool rotation center are determined by the three-point circle method, and the position data of the machine tool rotation center is output. Based on the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, the clamping position of the workpiece is adjusted until the coaxiality error between the center of the workpiece reference hole and the machine tool rotation center is less than a preset coaxiality threshold, and the workpiece reference coordinate system with the center of the workpiece reference hole as the origin is established. Based on the origin coordinates and coordinate axis directions of the workpiece reference coordinate system, and combined with the inherent parameters of the machine tool coordinate system, the coordinate transformation matrix between the workpiece reference coordinate system and the machine tool coordinate system is calculated, and the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system is established.

[0021] In practical applications, the vision system is implemented based on the integrated vision system on the spindle side of the machining equipment. The CCD guide camera, adjustable ring light source and lens of the vision system are fixedly installed on the spindle box of the machine tool, maintaining a fixed distance from the center of the spindle and the optical axis is parallel to the Z-axis of the machine tool. It is equipped with a vision protective cover that can be automatically opened and closed to isolate cutting fluid and chip contamination.

[0022] An opening command is sent to the vision shield, which automatically retracts to reveal the optical inspection window. The ring light source controller outputs illumination light with a preset brightness and angle, triggering the CCD camera to simultaneously acquire front and side views of the workpiece's reference hole using a head-up inspection method. The acquired images are preprocessed to extract the edge contour features of the reference hole, and the center coordinates, diameter, and axis perpendicularity parameters of the reference hole are calculated to generate its geometric data.

[0023] Then, an indexing command is sent to the machine tool's CNC system, driving the machine tool's rotary table to rotate sequentially by three non-coincident preset angles. At each rotary station, a CCD camera is triggered to acquire images of the reference holes and extract their center coordinates. Based on the set of reference hole center coordinates obtained at the three different rotation angles, the actual rotation center coordinates of the machine tool's rotary table are calculated using the three-point circle method. The machine tool's rotation center position data is then output, eliminating the installation deviation between the theoretical and actual rotation center of the table.

[0024] The coordinates of the reference hole center are compared with the actual rotation center coordinates of the machine tool to calculate the coaxiality error. If the error exceeds the preset coaxiality threshold, a clamping adjustment prompt is output to guide the operator to adjust the clamping position of the workpiece on the tooling fixture. The above detection and calculation process is repeated until the coaxiality error meets the requirements. A workpiece reference coordinate system is established with the calibrated reference hole center as the coordinate origin and the radial and axial directions of the workpiece as the coordinate axes.

[0025] By combining the inherent origin parameters and coordinate axis directions of the machine tool coordinate system, as well as the fixed installation offset between the vision system and the spindle center, the rotation and translation transformation parameters between the workpiece reference coordinate system and the machine tool coordinate system are calculated, generating a coordinate transformation matrix. This matrix establishes a one-to-one mapping relationship between the two coordinate systems, achieving a unified conversion between vision inspection coordinates and machine tool machining coordinates.

[0026] S2, based on the coordinate mapping relationship, pre-align and position the first pin hole, acquire the multi-exposure fusion image of the first pin hole and extract sub-pixel edge features, and output the position deviation data of the first pin hole.

[0027] The process of pre-aligning and positioning the first pin hole based on the coordinate mapping relationship, acquiring a multi-exposure fusion image of the first pin hole and extracting sub-pixel edge features, and outputting the positional deviation data of the first pin hole includes: Based on the coordinate mapping relationship, the coordinates of the first pin hole are converted into a rotation angle in the machine tool coordinate system, and the machine tool table is driven to rotate to the rotation angle to pre-align and position the first pin hole; The light source controller of the vision system adjusts the brightness and illumination angle of the ring light source, and sequentially acquires three original images of the first pin hole with different exposures. The original images are then processed using multi-exposure fusion technology to generate the multi-exposure fused image. After performing grayscale conversion, median filtering, and edge detection on the multi-exposure fusion image, the sub-pixel edge features of the first pin hole are extracted, and the center coordinates of the first pin hole are obtained by fitting using the least squares method. The difference between the center coordinates of the first pin hole and the preset theoretical center coordinates is calculated to obtain the X-axis position deviation, Y-axis position deviation and rotation angle deviation of the first pin hole, and the position deviation data of the first pin hole is output.

[0028] Based on the established coordinate transformation matrix, the theoretical coordinates of the first pin hole in the workpiece's reference coordinate system are converted into the rotation angle of the rotary table in the machine tool coordinate system. An indexing command is sent to the machine tool's CNC system to drive the rotary table to rotate precisely to the target angle, so that the first pin hole enters the center area of ​​the CCD guide camera's field of view, achieving coarse pre-alignment and positioning of the first pin hole and eliminating large-scale positional deviations caused by rough workpiece clamping.

[0029] Control commands are sent to the light source controller of the vision system to adjust the output brightness and vertical illumination angle of the ring light source (the ring light source has an adjustable mounting structure) according to the material characteristics of the workpiece surface. The CCD-guided camera is then sequentially triggered to acquire the first pin hole's original images at low, medium, and high exposure levels. The industrial control computer's built-in multi-exposure fusion algorithm performs pixel-level fusion processing on the three original images, generating a high-contrast multi-exposure fused image that simultaneously preserves highlight and shadow details and eliminates interference from metal surface reflections. This solves the problem of feature extraction failure caused by surface reflections on the guide's metal parts.

[0030] The multi-exposure fused images are sequentially preprocessed with grayscale conversion, median filtering for noise reduction, and edge detection to remove noise interference such as cutting fluid residue and chips. A sub-pixel edge extraction algorithm is used to obtain the continuous sub-pixel-level edge contour of the first pin hole, overcoming the limitations of the camera's physical pixel resolution. The sub-pixel edge contour is then fitted with a circle using the least squares method to obtain the actual center coordinates of the first pin hole, achieving micron-level accuracy in hole position feature extraction.

[0031] The actual center coordinates of the first pin hole obtained from the fitting are compared with the preset theoretical center coordinates. The positional deviations of the first pin hole in the X-axis and Y-axis directions of the machine tool coordinate system, as well as the overall rotational angle deviation of the workpiece, are calculated. These deviation data are then integrated to generate and output the positional deviation dataset of the first pin hole.

[0032] S3, based on the position deviation data of the first pin hole, correct the hole position topology model and generate an automatic detection sequence for all holes, perform full hole position cyclic detection and output the position deviation dataset of all pin holes.

[0033] The process of correcting the hole position topology model based on the position deviation data of the first pin hole and generating an automatic detection sequence for all pin holes, performing cyclic detection of all pin holes, and outputting a dataset of position deviations for all pin holes includes: Based on the positional distribution and circumferential arrangement of all pin holes on the workpiece, a topological relationship model of the hole positions is established, and the offset and rotation of the topological relationship model of the hole positions are corrected according to the positional deviation data of the first pin hole. According to the revised hole position topology model, the machine tool table rotation angle, vision system photo triggering timing and image sampling resolution corresponding to each pin hole are calculated sequentially to generate the full hole position automatic detection sequence. The full hole position automatic detection sequence is executed to perform full hole position cyclic detection, that is, drive the machine tool table to rotate and index successively, trigger the vision system to acquire multi-exposure fusion images and extract sub-pixel edge features at each pin hole, and calculate the position deviation data of each pin hole in real time. Perform topological consistency verification on the positional deviation data of all pin holes, remove abnormal deviation data that do not conform to the hole spacing rules and circumferential distribution rules, and output the positional deviation dataset of all pin holes.

[0034] Based on the uniform distribution and fixed angular interval of the circumferential pin holes in guide-type workpieces, a hole topology model is constructed, which includes the theoretical relative positions of all pin holes, hole numbering, and topological connection relationships. This model defines the inherent geometric constraints between each pin hole. The positional deviation data of the first pin hole is used as a global correction value to simultaneously correct the overall translational and rotational offsets of the hole topology model, eliminating systematic positional deviations caused by workpiece clamping and ensuring precise matching between the model and the actual workpiece clamping state.

[0035] Based on the revised hole topology model, the target rotation angle of the machine tool rotary table corresponding to each pin hole is calculated sequentially. Combining the image acquisition response delay of the vision system and the table positioning stabilization time, the visual image capture triggering timing for each pin hole is determined, and the corresponding image sampling resolution is set according to the nominal diameter of the pin hole and the required detection accuracy. These parameters are then integrated according to the hole machining sequence to generate an automatic full-hole detection sequence that can perform all pin hole detections at once, eliminating the need for manual setting of detection parameters for each hole.

[0036] The system sends a sequence of automatic hole detection commands to the CNC system of the machine tool, driving the rotary table to complete the rotation indexing and positioning locking sequentially. At each pin hole detection station, the vision system is simultaneously triggered to perform multi-exposure fusion image acquisition and sub-pixel edge feature extraction operations, repeating the high-precision feature extraction process of the first pin hole, and calculating and storing the positional deviation data corresponding to each pin hole in real time, thereby achieving unmanned automatic detection of all holes.

[0037] Based on the geometric constraint rules defined by the hole position topology model, a topology consistency check is performed on the position deviation data of all pin holes. The actual spacing between adjacent pin holes is verified one by one to ensure it conforms to the theoretical spacing tolerance, and the actual centers of all pin holes are located on the same circumferential trajectory. Abnormal deviation data that do not conform to the hole spacing and circumferential distribution rules due to interference such as residual chips and cutting fluid reflection are removed. All the verified pin hole position deviation data are integrated into a complete position deviation dataset and output.

[0038] The step of performing full-hole position cyclic detection according to the full-hole position automatic detection sequence involves driving the machine tool table to rotate and index successively, triggering the vision system to acquire multi-exposure fused images and extract sub-pixel edge features at each pin hole, and calculating the position deviation data of each pin hole in real time, including: According to the full hole position automatic detection sequence, drive the machine tool table to rotate to the current pin hole, trigger the vision system to acquire the multi-exposure fusion image and extract the sub-pixel edge features; Calculate the current pin hole position deviation data and perform trend analysis with the previous pin hole position deviation data to determine whether there is a systematic position deviation; If the systemic positional deviation is determined to exist, the rotation angle of the machine tool table and the timing of the vision system's photo capture are corrected in real time for all subsequent pin holes, and the remaining part of the full hole position automatic detection sequence is updated. Repeat the above steps until all pin holes have been inspected.

[0039] A pre-generated automatic detection sequence for all hole positions is loaded, and an indexing control command is sent to the machine tool's CNC system. This drives the machine tool's rotary table to precisely rotate according to the target rotation angle corresponding to the current pin hole in the sequence and complete the positioning and locking. After the table vibration decays, the CCD guide camera and ring light source on the spindle side are synchronously triggered to execute the same multi-exposure fusion image acquisition process as the first pin hole, obtaining a high-contrast, clear image of the current pin hole. The acquired image is then preprocessed with grayscale conversion, median filtering, and edge detection. A sub-pixel edge extraction algorithm is used to obtain the continuous edge contour of the current pin hole, and the actual center coordinates of the current pin hole are obtained by least squares fitting.

[0040] The difference between the actual center coordinates of the current pin hole and the corresponding theoretical center coordinates in the corrected hole position topology model is calculated to obtain the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of the current pin hole. The position deviation data of the current pin hole is then compared with the position deviation data of the previously detected pin hole to determine whether there is a systematic position deviation caused by the accumulation of indexing errors of the machine tool rotary table, minor slippage of the workpiece clamping, or thermal drift of the vision system.

[0041] If trend analysis determines the existence of a systematic positional deviation, a deviation compensation coefficient is calculated based on the rate of change of continuous pin hole deviations. Using this compensation coefficient as a basis, the target rotation angle of the machine tool rotary table corresponding to all remaining pin holes in the full-hole automatic detection sequence is corrected in real time. Simultaneously, considering the dynamic response characteristics of the table and the image acquisition delay of the vision system, the timing of visual image capture for the remaining pin holes is adjusted. The corrected parameters are then updated to the remaining part of the full-hole automatic detection sequence, replacing the original fixed detection parameters.

[0042] Repeat the steps of table rotation indexing, image acquisition and feature extraction, deviation calculation and trend analysis, and dynamic correction of the detection sequence until all circumferential pin holes on the workpiece have been detected.

[0043] This dynamic correction mechanism can effectively offset the systematic errors that gradually accumulate during the detection process, and avoid the failure of feature extraction caused by the pin hole deviating too much from the center of the camera's field of view, thus ensuring the accuracy and reliability of the detection results for all holes.

[0044] S4, perform multi-source error fusion correction on the position deviation dataset of all pin holes, generate a set of CNC machining instructions including machine tool coordinate axis compensation and tool offset compensation, and drive the machining equipment to complete drilling and reaming in sequence.

[0045] The multi-source error fusion correction is performed on the position deviation dataset of all pin holes to generate a CNC machining instruction set that includes machine tool coordinate axis compensation and tool offset compensation, including: Analyze the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole in the position deviation data of all pin holes, and calculate the basic compensation amount of the machine tool X-axis, machine tool Y-axis, and machine tool rotation axis corresponding to each pin hole; Temperature data of the machine tool spindle and guide rail are collected, and the basic compensation amount is corrected for thermal deformation error using a thermal deformation error model to obtain the compensation amount of the machine tool coordinate axis. Retrieve the current tool wear data from the tool life management system, calculate the tool radius wear and tool length wear, and generate the corresponding tool offset compensation amount; The machine tool coordinate axis compensation amount and the tool offset compensation amount are integrated into the CNC machining program, the machining sequence of each pin hole is adjusted, the CNC machining instruction set is generated and sent to the machine tool CNC system.

[0046] The dataset of all pin hole position deviations after topology consistency verification is analyzed, and the X-axis position deviation, Y-axis position deviation, and rotation angle deviation corresponding to each pin hole are extracted. Based on the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system, the above deviations are converted into basic compensation amounts for the machine tool's X-axis, Y-axis, and rotation axes. These basic compensation amounts are used to offset the translational and rotational deviations generated during workpiece clamping.

[0047] Real-time temperature data of the machine tool spindle and guideways are collected. A pre-built and self-learning optimized thermal deformation error model is called to calculate the dynamic impact of spindle thermal expansion and guideway thermal deformation on the machining coordinates. This impact is then superimposed on the basic compensation amount, and thermal deformation error correction is applied to the basic compensation amount to obtain the final machine tool coordinate axis compensation amount, thus eliminating the systematic dynamic errors caused by temperature field changes during continuous machine tool operation.

[0048] Retrieve current tool status data from the tool life management system, including the cumulative cutting time, number of holes machined, and historical wear records for drilling tools and reamers. Based on a preset tool wear pattern model, calculate the current radius wear and length wear of the tool, and generate corresponding tool radius offset compensation and tool length offset compensation to offset dimensional errors caused by cutting wear during tool use.

[0049] The machine tool coordinate axis compensation and tool offset compensation are integrated into the standard CNC machining program hole by hole. The machining sequence of each pin hole is adjusted according to the compensated coordinates to avoid machine tool motion interference. The generated CNC machining instruction set is sent to the machine tool CNC system through the IO card in the equipment hardware list, providing precise machining control parameters for subsequent drilling and reaming processes, realizing automated closed-loop control from detection to machining.

[0050] The analysis of the positional deviation data of all pin holes includes the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole. The basic compensation amounts for the machine tool X-axis, Y-axis, and rotation axis corresponding to each pin hole are calculated, including: The X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole are classified into random error compensation amount and systematic error compensation amount; The systematic error compensation amounts of all pin holes are weighted and averaged to generate global compensation coefficients for all pin holes. The random error compensation amount for each pin hole is processed separately to generate a local compensation amount corresponding to each pin hole; The global compensation coefficient corresponding to all pin holes is superimposed with the local compensation amount corresponding to each pin hole to obtain the basic compensation amount of the machine tool X-axis, the machine tool Y-axis and the machine tool rotary axis corresponding to each pin hole.

[0051] Load the dataset of all pin hole position deviations after topology consistency verification, and extract the X-axis position deviation, Y-axis position deviation, and rotation angle deviation for each hole. Based on the error generation mechanism and distribution characteristics, these deviation data are decoupled and classified into systematic error compensation quantities and random error compensation quantities. Among them, the systematic error compensation quantity is the common unidirectional deviation that exists in all pin holes, mainly caused by the overall workpiece clamping offset and the initial indexing error of the machine tool rotary table; the random error compensation quantity is the discrete deviation unique to a single pin hole, mainly caused by the machining error of the datum hole and the pre-cast deviation of a single pin hole.

[0052] A weighted average is applied to the systematic error compensation amounts of all pin holes to generate a global compensation coefficient applicable to all pin holes. The weighting coefficient is positively correlated with the detection confidence of the pin hole, which in turn is positively correlated with image contrast and edge continuity. That is, pin holes with better image quality and clearer edge features have higher detection confidence and correspondingly higher weighting coefficients. This weighted averaging effectively suppresses the impact of low-quality image detection results on the global compensation accuracy, improving the robustness of systematic error compensation.

[0053] The random error compensation for each pin hole is calculated and processed individually. For the random error components of the X-axis, Y-axis and rotation axis of each pin hole, combined with the nominal dimensional tolerance and machining accuracy requirements of the pin hole, error threshold filtering and smoothing correction are performed to eliminate abnormal data points that exceed the preset random error threshold. This generates a unique local compensation amount for each pin hole to offset the discrete machining deviation of a single pin hole and ensure the independent compensation accuracy of each hole position.

[0054] The global compensation coefficient is superimposed on the local compensation amounts for each pin hole along the X, Y, and rotary axes, respectively, to obtain the basic compensation amounts for the machine tool's X-axis, Y-axis, and rotary axes for each pin hole. These basic compensation amounts comprehensively cover both the overall systematic deviations and the discrete random deviations of individual hole positions generated during workpiece clamping.

[0055] The driving processing equipment sequentially completes drilling and reaming processes, including: According to the CNC machining instruction set, the machine tool is driven to automatically change the drilling tool and drill the first pin hole. After drilling is completed, the vision system is controlled to visually inspect the hole position and calculate the actual position deviation and hole diameter deviation after drilling. If the actual position deviation and the hole diameter deviation after drilling are within the preset position deviation allowable range and the preset size deviation allowable range, respectively, the machine tool will automatically change the reamer and perform reaming on the hole. After the reaming is completed, the quality of the reamed hole is inspected online. If the online visual inspection result is unqualified, the reamer offset is adjusted and the reaming is repeated until all holes are qualified.

[0056] The generated CNC machining instruction set is transmitted to the machine tool's CNC system via an I / O card. After parsing the instructions, the CNC system drives the machine tool's automatic tool changer to retrieve the drilling tool from the tool magazine, completing the automatic setting of tool clamping, spindle speed, and feed parameters. The cutting fluid system is activated, and the machine tool spindle and rotary table move in tandem according to the compensated machine tool coordinates and tool offset parameters to perform drilling on the first pin hole. After machining, the spindle automatically retracts the tool, the cutting fluid system stops working, and the drilling process is complete.

[0057] The system automatically opens the vision shield, triggering the spindle-side CCD-guided camera to perform multi-exposure fusion image acquisition on the drilled hole position. A sub-pixel edge extraction algorithm is used to obtain the edge contour features of the drilled hole. The actual center coordinates and inner diameter of the drilled hole are calculated using least squares fitting, and then the difference is calculated with the theoretical center coordinates and nominal hole diameter to obtain the actual positional deviation and hole diameter deviation. After inspection, the vision shield automatically closes to isolate cutting fluid and chip contamination during the machining process.

[0058] The system compares the actual positional deviation after drilling with the preset allowable range for positional deviation, and the hole diameter deviation with the preset allowable range for dimensional deviation. If both deviations are within the allowable range, the system determines that the drilling process is qualified, drives the machine tool's automatic tool changer to replace the reamer, retrieves the tool offset compensation amount corresponding to the reamer, and performs reaming machining on the hole position according to the corrected machining coordinates. If the deviation exceeds the allowable range, a machining abnormality alarm is triggered, prompting the operator to check for tool wear or machine tool status problems, and the drilling process is re-executed after correction.

[0059] After the reaming is completed, the vision system performs online visual inspection of the reamed hole quality again, extracting the hole diameter, roundness error, and positional deviation characteristics, and comparing them with the preset reaming quality standards. If the inspection result is unqualified, the system automatically analyzes the cause of the deviation, adjusts the radius offset and length offset of the reamer, re-executes the reaming process, and inspects again. This processing and inspection process is repeated until all drilling and reaming processes for the pin holes have passed inspection, achieving automated processing of the guide pin holes and ensuring the final processing accuracy of the guide pin holes.

[0060] like Figure 2The diagram shown is a system block diagram of a vision-based inspection-based drilling and positioning system for processing equipment, according to an embodiment of the present invention. The system includes: The coordinate mapping module is used to calibrate the coaxiality of the workpiece, collect the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, and establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system. The single-hole positioning module is used to pre-align and position the first pin hole based on the coordinate mapping relationship, acquire a multi-exposure fusion image of the first pin hole and extract sub-pixel edge features, and output the position deviation data of the first pin hole. The full-hole detection module is used to correct the hole position topology model based on the position deviation data of the first pin hole and generate an automatic full-hole detection sequence, perform full-hole cyclic detection, and output the position deviation dataset of all pin holes. The driving machining module is used to perform multi-source error fusion correction on the position deviation dataset of all pin holes, generate a set of CNC machining instructions including machine tool coordinate axis compensation and tool offset compensation, and drive the machining equipment to complete drilling and reaming in sequence.

[0061] Figure 2 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0062] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor performs the steps of a vision-based inspection-based drilling and positioning method for a processing device as described in any of the preceding claims.

[0063] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein... The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0064] Processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0065] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0066] When the memory 32 is a device independent of the processor 31, the device may further include: Bus 33 is used to connect the memory 32 and the processor 31.

[0067] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of a vision-based inspection-based drilling and positioning method for a processing equipment as described in any of the preceding claims.

[0068] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0069] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0070] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for drilling and positioning in a processing equipment based on vision inspection, characterized in that, The method includes: The workpiece is calibrated for coaxiality, and the geometric data of the workpiece reference hole and the position data of the machine tool rotation center are collected to establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system. Based on the coordinate mapping relationship, the first pin hole is pre-aligned and positioned, a multi-exposure fusion image of the first pin hole is acquired and sub-pixel edge features are extracted, and the positional deviation data of the first pin hole is output. Based on the position deviation data of the first pin hole, the hole position topology model is corrected and an automatic detection sequence of all holes is generated. The full hole position cyclic detection is performed and the position deviation dataset of all pin holes is output. The position deviation dataset of all pin holes is fused and corrected using multi-source error fusion to generate a set of CNC machining instructions that includes machine tool coordinate axis compensation and tool offset compensation, which drives the machining equipment to complete drilling and reaming in sequence.

2. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 1, characterized in that, The process of calibrating the coaxiality of the workpiece, collecting the geometric data of the workpiece's reference hole and the position data of the machine tool's rotation center, and establishing the coordinate mapping relationship between the workpiece's reference coordinate system and the machine tool coordinate system includes: The vision guard on the spindle side of the control machine tool is automatically opened to acquire the front and side images of the workpiece reference hole, extract the center coordinates, diameter and axis perpendicularity of the workpiece reference hole, and generate the geometric data of the workpiece reference hole. The machine tool table is rotated three different angles in sequence. At each angle, the center coordinates of the workpiece reference hole are collected. The position coordinates of the machine tool rotation center are determined by the three-point circle method, and the position data of the machine tool rotation center is output. Based on the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, the clamping position of the workpiece is adjusted until the coaxiality error between the center of the workpiece reference hole and the machine tool rotation center is less than a preset coaxiality threshold, and the workpiece reference coordinate system with the center of the workpiece reference hole as the origin is established. Based on the origin coordinates and coordinate axis directions of the workpiece reference coordinate system, and combined with the inherent parameters of the machine tool coordinate system, the coordinate transformation matrix between the workpiece reference coordinate system and the machine tool coordinate system is calculated, and the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system is established.

3. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 1, characterized in that, The process of pre-aligning and positioning the first pin hole based on the coordinate mapping relationship, acquiring a multi-exposure fusion image of the first pin hole and extracting sub-pixel edge features, and outputting the positional deviation data of the first pin hole includes: Based on the coordinate mapping relationship, the coordinates of the first pin hole are converted into a rotation angle in the machine tool coordinate system, and the machine tool table is driven to rotate to the rotation angle to pre-align and position the first pin hole; The light source controller of the vision system adjusts the brightness and illumination angle of the ring light source, and sequentially acquires three original images of the first pin hole with different exposures. The original images are then processed using multi-exposure fusion technology to generate the multi-exposure fused image. After performing grayscale conversion, median filtering, and edge detection on the multi-exposure fusion image, the sub-pixel edge features of the first pin hole are extracted, and the center coordinates of the first pin hole are obtained by fitting using the least squares method. The difference between the center coordinates of the first pin hole and the preset theoretical center coordinates is calculated to obtain the X-axis position deviation, Y-axis position deviation and rotation angle deviation of the first pin hole, and the position deviation data of the first pin hole is output.

4. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 1, characterized in that, The process of correcting the hole position topology model based on the position deviation data of the first pin hole and generating an automatic detection sequence for all pin holes, performing cyclic detection of all pin holes, and outputting a dataset of position deviations for all pin holes includes: Based on the positional distribution and circumferential arrangement of all pin holes on the workpiece, a topological relationship model of the hole positions is established, and the offset and rotation of the topological relationship model of the hole positions are corrected according to the positional deviation data of the first pin hole. According to the revised hole position topology model, the machine tool table rotation angle, vision system photo triggering timing and image sampling resolution corresponding to each pin hole are calculated sequentially to generate the full hole position automatic detection sequence. The full hole position automatic detection sequence is executed to perform full hole position cyclic detection, that is, drive the machine tool table to rotate and index successively, trigger the vision system to acquire multi-exposure fusion images and extract sub-pixel edge features at each pin hole, and calculate the position deviation data of each pin hole in real time. Perform topological consistency verification on the positional deviation data of all pin holes, remove abnormal deviation data that do not conform to the hole spacing rules and circumferential distribution rules, and output the positional deviation dataset of all pin holes.

5. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 4, characterized in that, The step of performing full-hole position cyclic detection according to the full-hole position automatic detection sequence involves driving the machine tool table to rotate and index successively, triggering the vision system to acquire multi-exposure fused images and extract sub-pixel edge features at each pin hole, and calculating the position deviation data of each pin hole in real time, including: According to the full hole position automatic detection sequence, drive the machine tool table to rotate to the current pin hole, trigger the vision system to acquire the multi-exposure fusion image and extract the sub-pixel edge features; Calculate the current pin hole position deviation data and perform trend analysis with the previous pin hole position deviation data to determine whether there is a systematic position deviation; If the systemic positional deviation is determined to exist, the rotation angle of the machine tool table and the timing of the vision system's photo capture are corrected in real time for all subsequent pin holes, and the remaining part of the full hole position automatic detection sequence is updated. Repeat the above steps until all pin holes have been inspected.

6. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 1, characterized in that, The multi-source error fusion correction is performed on the position deviation dataset of all pin holes to generate a CNC machining instruction set that includes machine tool coordinate axis compensation and tool offset compensation, including: Analyze the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole in the position deviation data of all pin holes, and calculate the basic compensation amount of the machine tool X-axis, machine tool Y-axis, and machine tool rotation axis corresponding to each pin hole; Temperature data of the machine tool spindle and guide rail are collected, and the basic compensation amount is corrected for thermal deformation error using a thermal deformation error model to obtain the compensation amount of the machine tool coordinate axis. Retrieve the current tool wear data from the tool life management system, calculate the tool radius wear and tool length wear, and generate the corresponding tool offset compensation amount; The machine tool coordinate axis compensation amount and the tool offset compensation amount are integrated into the CNC machining program, the machining sequence of each pin hole is adjusted, the CNC machining instruction set is generated and sent to the machine tool CNC system.

7. The method for drilling and positioning in a processing equipment based on vision inspection according to claim 6, characterized in that, The analysis of the positional deviation data of all pin holes includes the X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole. The basic compensation amounts for the machine tool X-axis, Y-axis, and rotation axis corresponding to each pin hole are calculated, including: The X-axis position deviation, Y-axis position deviation, and rotation angle deviation of each pin hole are classified into random error compensation amount and systematic error compensation amount; The systematic error compensation amounts for all pin holes are weighted and averaged to generate global compensation coefficients for all pin holes. The random error compensation amount for each pin hole is processed separately to generate a local compensation amount corresponding to each pin hole; The global compensation coefficient corresponding to all pin holes is superimposed with the local compensation amount corresponding to each pin hole to obtain the basic compensation amount of the machine tool X-axis, the machine tool Y-axis and the machine tool rotary axis corresponding to each pin hole.

8. The method for drilling and positioning of processing equipment based on vision inspection according to claim 1, characterized in that, The driving processing equipment sequentially completes drilling and reaming processes, including: According to the CNC machining instruction set, the machine tool is driven to automatically change the drilling tool and drill the first pin hole. After drilling is completed, the vision system is controlled to visually inspect the hole position and calculate the actual position deviation and hole diameter deviation after drilling. If the actual position deviation and the hole diameter deviation after drilling are within the preset position deviation allowable range and the preset size deviation allowable range, respectively, the machine tool will automatically change the reamer and perform reaming on the hole. After the reaming is completed, the quality of the reamed hole is inspected online. If the online visual inspection result is unqualified, the reamer offset is adjusted and the reaming is repeated until all holes are qualified.

9. A drilling positioning system for processing equipment based on vision inspection, characterized in that, The system, applicable to a vision-based inspection-based drilling positioning method for processing equipment as described in any one of claims 1-8, comprises: The coordinate mapping module is used to calibrate the coaxiality of the workpiece, collect the geometric data of the workpiece reference hole and the position data of the machine tool rotation center, and establish the coordinate mapping relationship between the workpiece reference coordinate system and the machine tool coordinate system. The single-hole positioning module is used to pre-align and position the first pin hole based on the coordinate mapping relationship, acquire a multi-exposure fusion image of the first pin hole and extract sub-pixel edge features, and output the position deviation data of the first pin hole. The full-hole detection module is used to correct the hole position topology model based on the position deviation data of the first pin hole and generate an automatic full-hole detection sequence, perform full-hole cyclic detection and output the position deviation dataset of all pin holes; The driving machining module is used to perform multi-source error fusion correction on the position deviation dataset of all pin holes, generate a set of CNC machining instructions including machine tool coordinate axis compensation and tool offset compensation, and drive the machining equipment to complete drilling and reaming in sequence.

Images