A metal workpiece machining quality on-line detection system and control method

Abstract

The application discloses a metal workpiece processing quality online detection system and a control method, relates to the technical field of metal workpiece online detection, and improves the problems of image recognition misjudgment, high false alarm rate and influence on continuous operation of a production line caused by temporary adhesion of chips on the surface of a metal workpiece during processing, and comprises a detection platform, a clamping positioning mechanism, a posture adjusting mechanism, an image acquisition mechanism, an image processing module and a judgment module; the posture adjusting mechanism drives the clamping positioning mechanism to drive the metal workpiece to perform multi-posture conversion, the image processing module performs coordinate registration on detection images collected under different postures based on reference features of the metal workpiece, and consistency analysis is performed on the position, contour, area, direction and existing state of a candidate defect region in multiple detections, so that temporary attached chips and real processing defects are distinguished. The application has the effects of reducing the false alarm rate, improving the processing defect recognition accuracy, improving the online detection stability and the continuous operation efficiency of the production line.

Description

Technical Field

[0001] This application relates to the field of online inspection technology for metal workpieces, and in particular to an online inspection system and control method for the processing quality of metal workpieces. Background Technology

[0002] During machining processes such as turning, milling, drilling, and stamping, metal workpieces typically generate a large amount of ribbon-like, filamentous, or fragmented chips, along with residual cutting fluid, lubricating oil, and other media on the workpiece surface. With the development of intelligent manufacturing, more and more production lines are adopting online vision inspection systems to automatically identify machining quality issues such as scratches, pits, burrs, and cracks on the surface of metal workpieces, replacing manual inspection and improving production efficiency.

[0003] However, in actual online inspection, some chips can temporarily adhere to the surface of the metal workpiece under the influence of oil, or accumulate in local areas to form obstructions. Their contours, textures, and projected shadows are highly similar to real defects, making them easily misidentified as processing defects by image recognition algorithms. Currently, compressed air purging or fixed-parameter image recognition methods are commonly used to reduce interference. However, for oily chips with strong adhesion, a single air purging is insufficient to completely remove them, while directly increasing the recognition threshold may lead to missed detection of real, minute defects. When the inspection system misidentifies chips as scratches, burrs, or pits, it frequently triggers alarms, requiring shutdowns for re-inspection and even manual intervention; this not only reduces the continuous operating efficiency of the production line but also increases the cost of false alarms and equipment downtime.

[0004] Furthermore, due to the randomness and temporality of chip locations, images acquired at the same location at different times may show significant changes. Existing detection processes lack targeted processing mechanisms for suspected chip interference areas, failing to effectively distinguish between temporary attachments and genuine machining defects. Therefore, there is an urgent need for an online inspection system and control method for metal workpiece machining quality, capable of identifying, re-inspecting, and judging chip adhesion interference online, in order to reduce false alarm rates and improve the stability and reliability of online inspection. Summary of the Invention

[0005] To address the issues of misidentification of defects, frequent shutdowns for re-inspection, and impact on production line continuity and inspection efficiency caused by temporary chip adhesion during existing online inspection of metal workpieces, this application provides an online inspection system and control method for the processing quality of metal workpieces.

[0006] This application provides an online inspection system and control method for the processing quality of metal workpieces, adopting the following technical solution: An online inspection system for the processing quality of metal workpieces includes an inspection platform, a clamping and positioning mechanism, an attitude adjustment mechanism, an image acquisition mechanism, an image processing module, and a judgment module. The clamping and positioning mechanism is installed on the detection platform, the attitude adjustment mechanism is connected to the clamping and positioning mechanism, and the image acquisition mechanism is set towards the clamping and positioning mechanism. The determination module controls the image acquisition mechanism to acquire a first detection image of the metal workpiece in its initial posture. The determination module also controls the posture adjustment mechanism to drive the clamping and positioning mechanism to change the posture of the metal workpiece and acquire a second detection image. The image processing module performs coordinate registration on the first and second detection images based on the reference features of the metal workpiece, identifies candidate defect regions in the first detection image, and compares the target feature retention status of the candidate defect regions at the corresponding positions after registration. Based on the positional changes, contour changes, area changes, orientation changes, or existence status changes of the target features in at least two detection images, it comprehensively determines whether it belongs to attached chips. If the target features remain consistent, it is determined to be a processing defect, and the detection result is output accordingly.

[0007] Preferably, the attitude adjustment mechanism includes a rotary drive component, which drives the clamping and positioning mechanism to rotate around a preset axis, so that the metal workpiece switches between a first attitude and a second attitude, and the clamping reference of the metal workpiece remains unchanged during the two acquisition processes.

[0008] Preferably, the attitude adjustment mechanism further includes a tilt drive component and a micro-vibration execution unit. The tilt drive component drives the clamping and positioning mechanism to tilt relative to the detection platform at a preset angle to form a detection attitude under different gravitational directions. The micro-amplitude vibration actuator can generate vibrations with adjustable duration, amplitude, or frequency, and drive the clamping and positioning mechanism to generate micro-amplitude vibrations after the metal workpiece has completed its rotation or tilting action.

[0009] Preferably, the image processing module extracts at least one of the positioning holes, outer contour edges, processing reference surfaces, or preset marks of the metal workpiece as registration references, and establishes a one-to-one correspondence between the first detection image and the second detection image based on the registration references.

[0010] Preferably, after the judgment module completes the acquisition of the second detection image, it controls the posture adjustment mechanism to drive the metal workpiece to undergo a posture change different from the second posture, and controls the image acquisition mechanism to acquire the third detection image; the image processing module establishes the coordinate correspondence between the third detection image and the first detection image respectively, and performs consistency analysis on the target features based on the three detection results.

[0011] Preferably, the image processing module calculates the position coordinates, contour boundary, area parameter, and orientation parameter in three detection images for the same target area. When at least one parameter changes, the corresponding target is marked as a movable target; when all parameters remain the same, the corresponding target is marked as a fixed target, and the processing defect judgment result is output.

[0012] A control method for an online inspection system for the processing quality of metal workpieces includes the following steps: Step S1: The clamping and positioning mechanism fixes the metal workpiece and acquires the first detection image of the metal workpiece in its initial state; Step S2: Identify candidate defect regions in the first detection image and record the position of the candidate defect regions in the metal workpiece reference coordinate system; Step S3: The attitude adjustment mechanism drives the metal workpiece to change to the first detection attitude, acquires the second detection image, and performs coordinate registration between the second detection image and the first detection image; Step S4: The attitude adjustment mechanism drives the metal workpiece to change to the second detection attitude, acquires the third detection image, and performs coordinate registration between the third detection image and the first detection image; Step S5: Compare the position information, contour and morphological change features of the candidate defect region in the first detection image, the second detection image and the third detection image. Based on the comparison results, distinguish between temporary attached chips and inherent processing defects of the metal workpiece, and output the detection results containing defect classification information.

[0013] In summary, this application includes at least one of the following beneficial effects: 1. This application controls the attitude adjustment mechanism to drive the metal workpiece to switch between different detection attitudes, and combines image registration technology to perform corresponding analysis on multiple acquired images. Based on the changes in the position, contour, area, direction and existence state of the candidate defect area in different detection images, a comprehensive judgment is made. This can effectively distinguish between temporary attached chips and real processing defects, reduce the situation where chips are misidentified as scratches, pits or burrs, and thus reduce the false alarm rate of online detection. 2. In addition, micro-amplitude vibration assistance is introduced during the attitude transition process, which makes it easier for strip-shaped chips, filamentous chips, or fragmented chips adhered to by cutting fluid or lubricating oil to slip, flip, or fall off. This increases the probability of temporary attachments changing state in multiple inspections. Combined with consistency analysis under the reference coordinate system of the metal workpiece, it improves the ability to distinguish between attached chips and inherent defects of the metal workpiece, enhances the accuracy of inspection results, and improves the automation level of online inspection of metal workpiece processing quality and the continuous operation efficiency of the production line. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the structure for online detection of metal workpiece processing quality in this embodiment of the present application; Figure 2 This is a flowchart of the online detection and control method for the processing quality of metal workpieces in this embodiment of the present application.

[0015] Explanation of reference numerals in the attached drawings: 1. Detection platform; 2. Clamping and positioning mechanism; 3. Image acquisition mechanism; 4. Attitude adjustment mechanism; 41. Rotary drive assembly; 411. Slewing bearing; 42. Tilting drive assembly; 421. Bracket; 422. Mounting plate; 43. Micro-amplitude vibration actuator; 431. Vibration driver. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0019] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0020] In addition, the term "multiple" should mean two or more.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments. Example

[0022] This application discloses an online inspection system for the processing quality of metal workpieces, including an inspection platform 1, a clamping and positioning mechanism 2, an attitude adjustment mechanism 4, an image acquisition mechanism 3, an image processing module, and a judgment module.

[0023] The inspection platform 1 serves as the installation base for the online inspection equipment. The clamping and positioning mechanism 2 is installed on the inspection platform 1 and is used to clamp and position the metal workpiece to be inspected. The clamping and positioning mechanism 2 uses a combination of positioning pins and clamping blocks to fix the metal workpiece, ensuring that the metal workpiece maintains a consistent clamping datum throughout the inspection process and avoiding coordinate deviations caused by repeated positioning.

[0024] The attitude adjustment mechanism 4 is connected to the clamping and positioning mechanism 2 to drive the clamping and positioning mechanism 2 to change the overall attitude of the metal workpiece while maintaining the clamping relationship between the metal workpiece and the clamping and positioning mechanism 2. The attitude adjustment mechanism 4 includes a rotary drive assembly 41, a tilt drive assembly 42, and a micro-amplitude vibration execution unit 43. The rotary drive assembly 41 includes a servo motor, a reducer, a rotary shaft, and a slewing bearing 411. One end of the rotary shaft is connected to the reducer, and the other end is rotatably connected to the detection platform 1. The rotary shaft is fixedly connected to the inner ring of the slewing bearing 411. The outer ring of the slewing bearing 411 is fixedly installed on the detection platform 1. The servo motor drives the rotary shaft to rotate via the reducer, which in turn drives the inner ring of the slewing bearing 411 to rotate around the vertical axis. The tilt drive assembly 42 is fixedly installed on the rotating part of the slewing bearing 411, so that the tilt drive assembly 42 can rotate synchronously with the slewing bearing 411, realizing the attitude switching of the clamping and positioning mechanism 2 and the metal workpiece in the horizontal direction.

[0025] Specifically, the tilt drive assembly 42 includes a bracket 421, a mounting plate 422 for mounting the clamping and positioning mechanism 2, and a bolt rotatably connected to the bracket 421. The bottom of the bracket 421 is fixedly connected to the inner ring of the slewing bearing 411. One side of the mounting plate 422 is fixed to the bolt, which passes through the bracket 421, with one end threaded into the bracket 421. A hole for the bolt's threaded connection is provided on one side of the bracket 421. For easy adjustment, a block is fixed to one end of the bolt, with sufficient clearance between the block and the vibration actuator 431 below. When the bolt rotates, it drives the entire mounting plate 422 and the clamping and positioning mechanism 2 to rotate along the bolt's axis, thereby causing the clamping and positioning mechanism 2 to form a preset tilt angle relative to the detection platform 1, and causing the metal workpiece to change its spatial posture.

[0026] The micro-amplitude vibration actuator 43 is fixedly mounted on the bracket 421, including a vibration driver 431 and an exciter fixed to the bracket 421. The vibration driver 431 can be any one of an eccentric vibration motor, an electromagnetic vibrator, or a piezoelectric vibrator, and drives the exciter to generate micro-amplitude vibrations with adjustable duration, amplitude, and frequency. After the metal workpiece completes its rotation or tilting action, the micro-amplitude vibration is transmitted to the metal workpiece through the clamping and positioning mechanism 2, causing the ribbon-like chips, filamentous chips, or fragmented chips attached to the surface of the metal workpiece to shift, flip, or detach, without changing the clamping relationship of the metal workpiece relative to the clamping and positioning mechanism 2.

[0027] The image acquisition mechanism 3 is fixedly installed above the inspection platform 1, and its visual range covers the area to be inspected. It acquires inspection images under different postures of the metal workpiece. The image processing module is communicatively connected to the image acquisition mechanism 3. It extracts stable features such as positioning holes, outer contours of the metal workpiece, processing reference edges or preset marks from the acquired images, establishes a unified reference coordinate system for the metal workpiece, and completes coordinate registration between different inspection images.

[0028] At the start of the inspection, the judgment module controls the image acquisition mechanism 3 to acquire the first inspection image of the metal workpiece in its initial state. The image processing module analyzes the first inspection image, identifies candidate defect regions, and records the position coordinates, contour boundaries, area parameters, and orientation parameters of the candidate defect regions in the metal workpiece's reference coordinate system.

[0029] Subsequently, the judgment module controls the attitude adjustment mechanism 4 to drive the clamping and positioning mechanism 2 to rotate the metal workpiece to the first detection posture, and controls the image acquisition mechanism 3 to acquire the second detection image. After the rotation is completed, the micro-amplitude vibration execution unit 43 applies short-term micro-amplitude vibration to the clamping and positioning mechanism 2, making it easier for the strip-shaped chips, filamentous chips, or fragmented chips attached to the surface of the metal workpiece to slip, flip, or detach under the influence of gravity and inertia, while the metal workpiece itself does not undergo significant displacement.

[0030] Subsequently, the judgment module further controls the attitude adjustment mechanism 4 to change the metal workpiece to the second detection attitude, and restarts the micro-amplitude vibration execution unit 43, and then the image acquisition mechanism 3 acquires the third detection image. The image processing module maps the second and third detection images to the metal workpiece reference coordinate system respectively, and establishes a one-to-one correspondence with the first detection image.

[0031] For each candidate defect region in the first detection image, the image processing module calculates its position change, contour change, area change, orientation change, and existence state change in the three detection images. When at least one parameter changes, or the target disappears in subsequent detection images, the determination module identifies it as a movable target, i.e., temporarily attached chips; when all the above parameters remain basically consistent, it is determined to be a fixed target, i.e., a surface defect such as scratches, pits, or burrs formed by actual processing, and the final detection result is output.

[0032] By utilizing the stability of real machining defects in the reference coordinate system of the metal workpiece and the characteristic that attached chips are prone to positional changes under posture changes and micro-vibrations, the structure effectively distinguishes between temporary attached chips and real machining defects, thereby reducing the false alarm rate and improving the accuracy of online detection and the continuous operation capability of the production line. Example

[0033] This embodiment discloses a control method based on the online metal processing quality detection system of Embodiment 1, the execution process of which is as follows: Step S1: The metal workpiece to be inspected is transported to the inspection platform 1, and the clamping and positioning mechanism 2 completes the positioning and clamping to establish the reference coordinate system of the metal workpiece; then the image acquisition mechanism 3 is controlled to acquire the first inspection image of the metal workpiece in its initial state.

[0034] Step S2: The image processing module analyzes the first detection image, extracts stable features such as positioning holes, outer contour edges or machining reference surfaces of the metal workpiece, and identifies candidate defect areas. At the same time, it records the position, contour boundary, area parameters and orientation parameters of the candidate defect areas in the reference coordinate system of the metal workpiece.

[0035] Step S3: The judgment module controls the attitude adjustment mechanism 4 to drive the metal workpiece to change to the first detection attitude. The rotation drive assembly 41 drives the clamping and positioning mechanism 2 to rotate around a preset rotation axis. A bolt drives the clamping and positioning mechanism 2 to swing, thereby changing the spatial orientation of the metal workpiece. After the attitude adjustment is completed, the micro-vibration execution unit 43 is activated to cause the clamping and positioning mechanism 2 to generate micro-vibrations of a preset frequency and amplitude, thereby increasing the probability of slippage or detachment of attached chips. Subsequently, the image acquisition mechanism 3 is controlled to acquire the second detection image, and coordinate registration between the first and second detection images is completed based on the reference features of the metal workpiece.

[0036] Step S4: The judgment module controls the attitude adjustment mechanism 4 again to drive the metal workpiece to change to a second detection attitude different from the first detection attitude, and applies micro-vibration again; after the vibration is completed, the third detection image is acquired and mapped to the metal workpiece reference coordinate system to complete coordinate registration with the first detection image.

[0037] Step S5: The image processing module compares the changes in position, contour, area, orientation, and presence status of each candidate defect region in the first, second, and third detection images. When the target shifts position, changes contour, changes area, changes orientation, or disappears during the three detection processes, it is determined to be a temporary attached chip; when the target remains consistent, it is determined to be an inherent machining defect of the metal workpiece.

[0038] Finally, the judgment module generates a detection report based on the analysis results, cancels the defect alarm for targets determined to be temporary attached chips, outputs the corresponding defect category, location coordinates and detection information for targets determined to be real processing defects, and can send corresponding quality control instructions to the production line.

[0039] The working principle of this embodiment is based on the physical characteristic that "real machining defects remain stable relative to the reference coordinates of the metal workpiece, while temporary attached chips are prone to changes in position or shape under the assistance of posture changes and micro-vibration." Through multi-posture image acquisition, reference coordinate registration, and target consistency analysis, it is possible to reliably distinguish between attached chips and real machining defects, thereby effectively reducing the false alarm rate, reducing unnecessary downtime for inspection, and improving the stability of online detection and the continuous operation efficiency of the production line.

[0040] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An online inspection system for the processing quality of metal workpieces, characterized in that: It includes a detection platform (1), a clamping and positioning mechanism (2), an attitude adjustment mechanism (4), an image acquisition mechanism (3), an image processing module, and a judgment module; Among them, the clamping and positioning mechanism (2) is installed on the detection platform (1), the posture adjustment mechanism (4) is connected to the clamping and positioning mechanism (2) through transmission, and the image acquisition mechanism (3) is set towards the clamping and positioning mechanism (2); The judgment module controls the image acquisition mechanism (3) to acquire the first detection image of the metal workpiece in its initial posture. The judgment module also controls the posture adjustment mechanism (4) to drive the clamping and positioning mechanism (2) to acquire the second detection image after the posture of the metal workpiece changes. The image processing module performs coordinate registration of the first detection image and the second detection image according to the reference features of the metal workpiece, identifies the candidate defect area in the first detection image, and compares the target feature retention status of the candidate defect area at the corresponding position after registration. Based on the position change, contour change, area change, direction change or existence status change of the target feature in at least two detection images, it comprehensively determines whether it belongs to attached chips. If the target features remain consistent, it is determined to be a processing defect, and the detection result is output accordingly.

2. The online inspection system for the processing quality of metal workpieces according to claim 1, characterized in that: The attitude adjustment mechanism (4) includes a rotation drive component (41), which drives the clamping and positioning mechanism (2) to rotate around a preset axis, so that the metal workpiece switches between the first attitude and the second attitude, and the clamping reference of the metal workpiece remains unchanged during the two acquisition processes.

3. The online inspection system for the processing quality of metal workpieces according to claim 2, characterized in that: The attitude adjustment mechanism (4) also includes a tilt drive component (42) and a micro-vibration execution unit (43). The tilt drive component (42) drives the clamping and positioning mechanism (2) to tilt at a preset angle relative to the detection platform (1) to form a detection attitude under different gravity directions. The micro-amplitude vibration actuator (43) can generate vibrations with adjustable duration, amplitude or frequency, and drive the clamping and positioning mechanism (2) to generate micro-amplitude vibrations after the metal workpiece has completed its rotation or tilting action.

4. The online inspection system for the processing quality of metal workpieces according to claim 1, characterized in that: The image processing module extracts at least one of the positioning holes, outer contour edges, machining reference surfaces, or preset marks of the metal workpiece as registration references, and establishes a one-to-one correspondence between the first detection image and the second detection image based on the registration references.

5. The online inspection system for the processing quality of metal workpieces according to claim 1, characterized in that: After the judgment module completes the acquisition of the second detection image, it controls the posture adjustment mechanism (4) to drive the metal workpiece to undergo a posture change different from the second posture, and controls the image acquisition mechanism (3) to acquire the third detection image; the image processing module establishes the coordinate correspondence between the third detection image and the first detection image respectively, and performs consistency analysis on the target features based on the three detection results.

6. The online inspection system for the processing quality of metal workpieces according to claim 5, characterized in that: The image processing module calculates the position coordinates, contour boundary, area parameters, and orientation parameters in three detection images for the same target area. When at least one parameter changes, the corresponding target is marked as a movable target; when all parameters remain the same, the corresponding target is marked as a fixed target, and the processing defect judgment result is output.

7. A control method for an online inspection system for the processing quality of metal workpieces according to any one of claims 1 to 6, characterized in that, Includes the following steps: Step S1: The clamping and positioning mechanism (2) fixes the metal workpiece and acquires the first detection image of the metal workpiece in its initial state; Step S2: Identify candidate defect regions in the first detection image and record the position of the candidate defect regions in the metal workpiece reference coordinate system; Step S3: The attitude adjustment mechanism (4) drives the metal workpiece to change to the first detection attitude, acquires the second detection image, and performs coordinate registration between the second detection image and the first detection image; Step S4: The posture adjustment mechanism (4) drives the metal workpiece to change to the second detection posture, acquires the third detection image, and performs coordinate registration between the third detection image and the first detection image; Step S5: Compare the position information, contour and morphological change features of the candidate defect region in the first detection image, the second detection image and the third detection image. Based on the comparison results, distinguish between temporary attached chips and inherent processing defects of the metal workpiece, and output the detection results containing defect classification information.

Images