Method and system for cleaning a workpiece prior to inspection

Abstract

The present application provides a kind of cleaning method before workpiece flaw detection, when carrying out cleaning, by stain identification model carries out stain identification, and distributes corresponding cleaning gear, uses dry ice cleaning device to carry out cleaning, and after each cleaning, image is collected and stain identification model is used to identify stain, and the area of still having stain is cleaned again, until there is no stain on the surface of workpiece, to complete the purpose of cleaning.The present application also provides a kind of cleaning system before workpiece flaw detection, applied to the above-mentioned cleaning method before workpiece flaw detection, the position of image acquisition device is adjusted by eight-axis linkage device, and the position of dry ice spray gun is also adjusted by eight-axis linkage device.The beneficial effects of the present application include: it can play the purpose of removing stain, while reducing the waste of dry ice resources.

Description

Technical Field

[0001] This invention relates to the field of workpiece flaw detection technology, and in particular to a cleaning method and system for workpieces before flaw detection. Background Technology

[0002] Workpiece flaw detection involves inspecting workpieces using flaw detection equipment to detect cracks or damage. Before flaw detection, the workpiece surface needs to be cleaned to remove stains. Common cleaning methods include boiling in a washing tank, rinsing with a high-pressure water gun (spraying cleaning agent), and scrubbing with a steel wool pad to remove surface dust, oil, rust, and other stains. High-pressure water spraying and boiling in a washing tank consume large amounts of water, so some companies have begun using dry ice cleaning. Using dry ice generating equipment and a corresponding spray gun, high-pressure air carries dry ice particles and sprays them onto the surface to be cleaned. The dry ice particles rapidly sublimate upon contact with the surface, absorbing a large amount of heat, causing the dirt to freeze, become brittle, and peel off quickly, thus achieving a cleaning effect.

[0003] However, existing dry ice cleaning devices generally use a high setting to ensure thorough cleaning, which results in a significant waste of dry ice resources.

[0004] Therefore, it is necessary to study a cleaning method and system for workpieces before flaw detection in order to solve the above problems or mitigate their impact. Summary of the Invention

[0005] This invention provides a cleaning method for workpieces before flaw detection. It identifies stains using a stain recognition model and assigns corresponding cleaning levels for cleaning. Furthermore, during the operation, it learns and improves the compatibility between the cleaning level and the degree of dirtiness of the stains, thereby effectively solving the above-mentioned problems or mitigating their impact.

[0006] The cleaning method for workpieces before flaw detection according to the present invention includes:

[0007] S100. The workpiece is transported to the cleaning station, and the surface of the workpiece is divided into several areas;

[0008] S200. Acquire images of each of the aforementioned regions on the workpiece using an image acquisition device;

[0009] S300. The stain recognition model identifies whether the image contains stains and the degree of dirtiness of the stains, marks the area corresponding to the image containing stains as a stain area, and outputs the corresponding cleaning level according to the degree of dirtiness of the stains.

[0010] S400. Control the dry ice cleaning device to perform a cleaning operation, and spray dry ice particles onto the stained area according to the cleaning setting;

[0011] S500. After cleaning, the image acquisition device acquires the post-cleaning image of each stain area on the workpiece;

[0012] S600. The stain identification model identifies whether the post-cleaning image has stains. If stains are identified in the post-cleaning image, the corresponding area retains the stain area identifier. Otherwise, the stain area identifier of the corresponding area is cancelled.

[0013] S700. After all post-cleaning images are identified, if there is no stain area, the next step is performed. If there is a stain area, the cleaning level is increased by one level based on the cleaning level of the last cleaning, and the process returns to step S400.

[0014] S800. The workpiece is transported away from the cleaning station.

[0015] In one embodiment, the stain identification model outputs the cleaning level during cleaning by identifying the dirtiness level of the stain. The dirtiness level is divided into 1 to n levels from light to heavy, and the cleaning level is divided into 1 to m levels from low to high in cleaning intensity, where m is greater than n. When the stain identification model is created, the 1 to n levels of the dirtiness level correspond one-to-one to the 1 to n levels of the cleaning level.

[0016] In one embodiment, between steps S700 and S800, the following steps are included:

[0017] S701. Record the initial dirtiness level of each stain area in step S300.

[0018] S702. Record the cleaning level of the last cleaning of each stain area.

[0019] S703. Correspond the initial dirtiness level to the cleaning level of the last cleaning.

[0020] S704. Record the cleaning level corresponding to each level of dirtiness in the stain identification model, replacing the original correspondence.

[0021] In one embodiment, step S200 specifically includes the following steps:

[0022] S201. Control the eight-axis linkage device to access the image acquisition device.

[0023] S202. Adjust the position of the image acquisition device through the eight-axis linkage device, so that the image acquisition device captures images of each area.

[0024] In one embodiment, step S400 specifically includes the following steps:

[0025] S401. Control the eight-axis linkage device to take the dry ice spray gun of the dry ice cleaning device;

[0026] S402. Adjust the position of the dry ice spray gun through the eight-axis linkage device, so that the dry ice spray gun is directed towards any stain area;

[0027] S403. Control the dry ice cleaning device to start according to the corresponding cleaning gear of the stain area, and spray dry ice particles to the stain area;

[0028] S404. Repeat steps S402 and S403 to clean all stain areas.

[0029] Another aspect of the present application also provides a cleaning system before workpiece inspection, which is applied to the workpiece inspection before cleaning method as described above, and the cleaning system comprises:

[0030] A processing mute room is provided with a cleaning station at the center position inside;

[0031] Two eight-axis linkage devices are respectively arranged on both sides of the cleaning station; the eight-axis linkage device comprises a ground rail arranged on one side of the cleaning station, a lifting device arranged on the sliding table of the ground rail, a six-axis mechanical arm arranged on the sliding table of the lifting device, and a main connector arranged at the end of the six-axis mechanical arm;

[0032] A dry ice cleaning device comprises a dry ice generating device and a dry ice spray gun;

[0033] A dustproof device comprises a dustproof box arranged on one side of the ground rail, a first storage rack arranged on the outer side of the dustproof box, and a second storage rack arranged inside the dustproof box; the second storage rack is provided with a second quick-change connector, a second clamp is arranged below the second quick-change connector, and an image acquisition device is clamped by the second clamp; the first storage rack is provided with a first quick-change connector, a first clamp is arranged at one end of the first quick-change connector, and the first clamp is used for clamping the dry ice spray gun; the second quick-change connector and the first quick-change connector can be detachably connected with the main connector;

[0034] A central control device is used for controlling the eight-axis linkage device, the dry ice cleaning device and the image acquisition device.

[0035] In one embodiment, one side wall of the dustproof box is provided with a plug-in slot, a sealing plate is arranged in the plug-in slot, the extension direction of the sealing plate is a first direction, one end of the sealing plate is provided with a return spring, a limiting guide slot is arranged in the middle of the sealing plate and extends in a second direction, two limiting guide columns are arranged at the top of the dustproof box in the first direction, both the limiting guide columns extend in the second direction and penetrate the limiting guide slot.

[0036] In one embodiment, the dustproof box is provided with an avoiding groove at the top end, and the end of the sealing plate away from the reset spring is provided with a guide rubber block, and the end of the guide rubber block away from the reset spring is provided with two guide inclined surfaces.

[0037] In one embodiment, the end of the sealing plate close to the guide rubber block is sleeved with a first sealing rubber ring for sealing the plug-in plate groove, and the top end of the sealing plate is provided with a second sealing rubber ring for sealing the avoiding groove.

[0038] In one embodiment, the dustproof box is in communication with the air outlet of the compressed air device, and the dustproof box is provided with a micro air pump, the air outlet of the micro air pump is in communication with the inside of the dustproof box, and the air inlet of the micro air pump is in communication with the outside air source.

[0039] Compared with the prior art, the cleaning method for workpiece before flaw detection provided by the present application has at least the following beneficial effects:

[0040] In the cleaning method for workpiece before flaw detection, the stain recognition model is used for stain recognition, and the corresponding cleaning gear is distributed, the dry ice cleaning device is used for cleaning, and the image is collected after each cleaning and the stain recognition model is used for stain recognition, the area still having stains is cleaned again until the workpiece surface is free of stains, so that the cleaning purpose is achieved, the cleaning is more sufficient, and manual supplementary cleaning is not required. And the cleaning method of the present application consumes more dry ice only at the initial cleaning, records the cleaning gear corresponding to the current dirt degree each time the workpiece cleaning is completed, and covers the original corresponding relationship in the stain recognition model, so that the cleaning gear is provided by the stain recognition model when the dry ice is used subsequently, the purpose of removing stains is achieved, and the waste of dry ice resources is avoided, and a large amount of dry ice resources can be saved.

[0041] The cleaning system for workpiece before flaw detection provided by the present application has the beneficial effects of the above-mentioned cleaning method for workpiece before flaw detection. In addition, the cleaning system of the present application adjusts the position of the image acquisition device through the eight-axis linkage device, which is convenient for shooting the images of each area of the workpiece surface, adjusts the position of the dry ice spray gun through the eight-axis linkage device, which is convenient for cleaning the stains in each area, and the second storage rack, the first storage rack, the second quick-change connector, the first quick-change connector and the main connector are arranged, so that the end of the eight-axis linkage device can be switched between the image acquisition device and the dry ice spray gun, and the image acquisition device and the dry ice spray gun are convenient to store when not in use. BRIEF DESCRIPTION OF DRAWINGS

[0042] The application will be described in more detail below based on the embodiments and with reference to the drawings.

[0043] Figure 1 is a step flow chart of the cleaning method before workpiece flaw detection of the embodiment of the application;

[0044] Figure 2 is a structural schematic diagram of the cleaning system before workpiece flaw detection of the embodiment of the application;

[0045] Figure 3 is a structural schematic diagram of the eight-axis linkage device of the embodiment of the application;

[0046] Figure 4 is a sectional structural schematic diagram of the dustproof box of the embodiment of the application;

[0047] Figure 5 is a connection structural schematic diagram of the dustproof box and the first storage rack of the embodiment of the application;

[0048] Figure 6 is a structural schematic diagram of the sealing plate of the embodiment of the application.

[0049] In the drawings, the same components use the same reference signs. The drawings are not drawn according to the actual scale.

[0050] Reference signs:

[0051] 1 - processing mute room,

[0052] 2 - cleaning station,

[0053] 3 - dry ice cleaning device, 31 - dry ice generating equipment, 32 - dry ice spray gun,

[0054] 4 - eight-axis linkage device, 41 - ground rail, 42 - lifting device, 43 - six-axis mechanical arm, 44 - main joint, 45 - first quick-change joint, 46 - first clamp, 47 - second quick-change joint, 48 - second clamp,

[0055] 5 - dustproof device, 51 - stand column, 52 - dustproof box, 53 - plugboard slot, 54 - sealing plate, 55 - limiting guide slot,

[0056] 56 - limiting guide column, 57 - return spring, 58 - avoidance slot, 59 - second storage rack, 510 - first storage rack,

[0057] 511 - guide rubber block, 512 - first sealing rubber ring, 513 - second sealing rubber ring, 514 - micro air pump,

[0058] 6 - central control device,

[0059] 7 - image acquisition device. DETAILED DESCRIPTION

[0060] The application will be further described below with reference to the drawings.

[0061] Embodiment 1

[0062] Please refer to Figures 1-6 The workpiece cleaning method before workpiece inspection includes:

[0063] S100. The workpiece is transported to the cleaning station 2, and the surface of the workpiece is divided into several regions.

[0064] The cleaning station 2 is located in the processing quiet room 1, which can reduce noise pollution to the outside. In addition, through the AGV transfer vehicle and the matching workpiece tooling, the workpiece is transported to the designated position, that is, the cleaning station 2, according to the fixed route.

[0065] S200. The image acquisition device 7 acquires images of each region on the workpiece respectively.

[0066] In some examples, step S200 can specifically include the following steps:

[0067] S201. Control the eight-axis linkage device 4 to take the image acquisition device 7;

[0068] S202. Adjust the position of the image acquisition device 7 through the eight-axis linkage device 4, so that the image acquisition device 7 shoots images of each region.

[0069] The image acquisition device 7 uses a 2D camera to directly shoot photos of each region as images for subsequent analysis. The eight-axis linkage device 4 is a mechanism that can adjust the position in multiple directions, including a six-axis mechanical arm 43, the end of which is provided with a main joint 44. The image acquisition device 7 is connected with the second quick-change joint 47, which can be connected through the main joint 44 and the second quick-change joint 47 to achieve the purpose of taking the image acquisition device 7.

[0070] S300. Identify whether the image has stains and the degree of dirt of the stains through the stain identification model, mark the region corresponding to the image with stains as the stain area, and output the corresponding cleaning gear according to the degree of dirt of the stains.

[0071] The stain identification model is created based on the AIVI (Artificial Intelligence Vision Inspection, AIVI for short) vision algorithm, and the creation method specifically includes the following processes:

[0072] W1. Enter the photos of each region of the workpiece; optionally, the photos are manually shot and collected;

[0073] W2. Select a photo, manually frame the stain; the stain as a recognition feature, and the rest as the background;

[0074] W3. The algorithm automatically selects the stain in other photos;

[0075] W4. Manually check each photo to eliminate false frames; that is, part of the background is close to the stain, which will interfere with the algorithm's recognition, so manual training is needed;

[0076] W5. Grade the stains according to their dirtiness, and store the corresponding relationship between each level of dirtiness and a cleaning position;

[0077] W6. Manually select several photos and label the stains in the photos according to their dirtiness;

[0078] W7. The algorithm automatically matches the dirtiness level of the stains in other photos;

[0079] W8. Manually check the dirtiness level of each photo and correct any obvious errors;

[0080] After the above operations are completed, the creation of the stain recognition model is realized, and the accuracy of stain recognition is improved through the model trained manually. Furthermore, new photos can be added to the stain recognition model for multiple training to ensure the accuracy of the recognition.

[0081] In some examples, the stain recognition model outputs the cleaning position during cleaning by recognizing the dirtiness of the stain. The dirtiness is divided into 1 to n levels from light to heavy, and the cleaning position is divided into 1 to m levels from low to high in cleaning intensity, and m is greater than n. When the stain recognition model is created, the 1 to n levels of dirtiness correspond one-to-one to the 1 to n levels of cleaning position.

[0082] Specifically, the dirtiness is set to level 1, level 2, …, level n from light to heavy, and the cleaning position is set to level 1, level 2, …, level n, …, level m from low to high in intensity. When the stain recognition model is created, the 1st, 2nd, …, nth levels of dirtiness correspond one-to-one to the 1st, 2nd, …, nth levels of cleaning position. When the stain recognition model recognizes a stain in an image and matches the corresponding dirtiness, it will further output the corresponding cleaning position. The dry ice cleaning device 3 will clean the area corresponding to the image according to the cleaning position. In addition, the cleaning position includes the amount of dry ice, the injection pressure, and the dry ice flow rate. The higher the level, the larger the above-mentioned parameter values, and the better the cleaning effect.

[0083] S400. Control the dry ice cleaning device 3 to perform cleaning operation, and inject dry ice particles to the stain area according to the cleaning position.

[0084] In some examples, step S400 specifically comprises the following steps:

[0085] S401. Control the eight-axis linkage device 4 to take the dry ice spray gun 32 of the dry ice cleaning device 3;

[0086] S402. Adjust the position of the dry ice spray gun 32 through the eight-axis linkage device 4, so that the dry ice spray gun 32 is directed towards any stain area;

[0087] S403. Control the dry ice cleaning device 3 to start spraying dry ice particles to the stain area according to the corresponding cleaning gear of the stain area;

[0088] S404. Repeat steps S402 and S403 to clean all stain areas.

[0089] Before S401, the eight-axis linkage device 4 is driven by the main joint 44 and the second quick-change joint 47 to adjust the position of the image acquisition device 7, and when the dry ice spray gun 32 is taken, the main joint 44 and the second quick-change joint 47 are disconnected, and the main joint 44 and the first quick-change joint 45 are connected, the dry ice spray gun 32 is connected with the first quick-change joint 45, and the taking of the dry ice spray gun 32 is completed; and according to the dry ice usage parameters, the spraying pressure parameters and the dry ice flow parameters provided by the cleaning gear, the purpose of cleaning the stains is achieved.

[0090] S500. After cleaning, the post-cleaning images of each stain area on the workpiece are acquired by the image acquisition device 7. The acquisition method is the same as that in step S200, but before using the image acquisition device 7, the main joint 44 and the first quick-change joint 45 are disconnected, and the main joint 44 and the second quick-change joint 47 are connected, the storage of the dry ice spray gun 32 and the taking of the image acquisition device 7 are completed.

[0091] S600. Identify whether there are stains in the post-cleaning images through the stain identification model. If stains are identified in the post-cleaning images, the corresponding areas retain the stain area mark, otherwise the stain area mark of the corresponding areas is cancelled. The principle is the same as that in step S300, that is, the post-cleaning images are identified again through the stain identification model, the post-cleaning images that still have stains are identified, the areas corresponding to the post-cleaning images are output, these areas still retain the stain area mark, and cleaning is continued.

[0092] S700. When all the post-cleaning images are identified, if there is no stain area, the next step is executed; if there is a stain area, the cleaning gear at the last cleaning is increased by one level, and step S400 is returned. If there is no stain area, it means that all stains have been cleaned, that is, the cleaning of the workpiece is completed, and if there is a stain area, the cleaning needs to be performed again.

[0093] In some examples, between steps S700 and S800, the following steps are further included:

[0094] S701. Record the initial dirtiness level of each stain area in step S300;

[0095] S702. Record the cleaning level of each stain area when it was last cleaned;

[0096] S703. Correspond the level of initial dirtiness to the cleaning level when it was last cleaned;

[0097] S704. Record the cleaning level corresponding to each level of dirtiness in the stain identification model, covering the original correspondence.

[0098] In short, if a stain is located at level 1, the first cleaning will be performed according to the cleaning level output by the stain identification model, which is level 1, but because the cleaning is not complete, the stain area will be retained and the cleaning level will be increased, i.e. assigned to level 2, and the process will return to step S400 for cleaning. The dry ice cleaning device 3 will perform cleaning again on the stain area according to level 2, and after step S600, detection will be performed again. If it is not clean, the cleaning level will be increased again and the process will return to step S400 until it is clean. Therefore, the cleaning level of the last cleaning is corresponded to the level of initial dirtiness, covering the correspondence in the stain identification model. In this way, learning will be performed at each cleaning and the stain identification model will be updated. Except for the initial cleaning of the workpiece, which will consume more dry ice, subsequent cleanings will be optimized in this way to ensure that each level of dirtiness corresponds to the optimal cleaning level, achieving the purpose of removing stains and not wasting dry ice resources.

[0099] S800. Transport the workpiece away from the cleaning station 2; also through the AGV transfer trolley to transport the workpiece out of the machining quiet room 1.

[0100] In summary, the beneficial effects of the workpiece cleaning method before flaw detection of the present application include:

[0101] When cleaning, stain identification is performed through the stain identification model, and the corresponding cleaning level is assigned. Cleaning is performed using the dry ice cleaning device, and after each cleaning, images are collected and the stain identification model is used to identify stains. Areas with stains are cleaned again until the surface of the workpiece is free of stains to achieve the purpose of cleaning. This way, the cleaning is more thorough and does not require manual re-cleaning. The cleaning method of the present application only consumes more dry ice during the initial cleaning. Each time the workpiece is cleaned, the cleaning level corresponding to the current dirtiness is recorded and the original correspondence in the stain identification model is covered. When using dry ice for subsequent cleaning, the stain identification model will provide a more suitable cleaning level, achieving the purpose of removing stains and not wasting dry ice resources, and saving a large amount of dry ice resources.

[0102] Example 2

[0103] Based on the cleaning method steps of the above embodiment 1, as Figures 2-6 shown, the present application provides a kind of cleaning system before workpiece flaw detection, comprising:

[0104] Processing mute room 1, inside center position is equipped with cleaning station 2;

[0105] Two eight-axis linkage devices 4 are respectively arranged at the two sides of cleaning station 2;Eight-axis linkage device 4 includes ground rail 41 arranged at one side of cleaning station 2, lifting device 42 is arranged on the sliding table of ground rail 41, six-axis mechanical arm 43 is arranged on the sliding table of lifting device 42, and main connector 44 is arranged at the end of six-axis mechanical arm 43;

[0106] Dry ice cleaning device 3 includes dry ice generating equipment 31 and dry ice spray gun 32;

[0107] Dustproof device 5 includes dustproof box 52 arranged at one side of ground rail 41, first storage rack 510 is arranged on the outer side of dustproof box 52, and second storage rack 59 is arranged in dustproof box 52;Second quick-change connector 47 can be placed in second storage rack 59, second clamp 48 is arranged below second quick-change connector 47, and image acquisition device 7 is clamped by second clamp 48;First quick-change connector 45 can be placed in first storage rack 510, first clamp 46 is arranged at one end of first quick-change connector 45, and first clamp 46 is used to clamp dry ice spray gun 32;Second quick-change connector 47 and first quick-change connector 45 can be detachably connected with main connector 44;

[0108] Central control device 6 is used to control eight-axis linkage device 4, dry ice cleaning device 3 and image acquisition device 7.

[0109] As Figure 2 and Figure 3 shown, wherein central control device 6 is the collocation of existing common computer and programmable logic controller, it is common control device, here is not repeated, it can control the sliding table movement of ground rail 41, control the sliding table movement of lifting device 42, control the position adjustment of main connector 44 of six-axis mechanical arm 43, control dry ice cleaning device 3 according to corresponding cleaning gear start, control image acquisition device 7 to shoot the photo of workpiece surface, control main connector 44 and one of second quick-change connector 47 or first quick-change connector 45 are connected, wherein the automatic connection of quick-change connector is prior art, mostly electromagnetic adsorption, here is not repeated.

[0110] In addition, as Figure 2As shown, the dry ice generating device 31 of the dry ice cleaning device 3 is arranged outside the processing silent room 1, facilitating independent replacement and maintenance of the dry ice generating device 31. Further, a dust collector is arranged in the processing silent room 1 to discharge the dust and carbon dioxide generated after cleaning the inside of the processing silent room 1 outside, facilitating workers to enter the processing silent room 1 for maintenance or other operations. The dustproof box 52 is provided with a stand column 51 at the bottom end, and the bottom end of the stand column 51 is connected with the ground of the processing silent room 1 to realize installation of the dustproof box 52, avoiding being placed directly on the ground and being too far from the main joint 44, which is inconvenient for subsequent operations.

[0111] In some examples, as shown in Figure 4 and Figure 5 One side wall of the dustproof box 52 is provided with a plug-in slot 53, and a sealing plate 54 is inserted in the plug-in slot 53. The extension direction of the sealing plate 54 is the first direction, one end of the sealing plate 54 is provided with a return spring 57, and the middle part of the sealing plate 54 is provided with a limiting guide slot 55 penetrating in the second direction. The top end of the dustproof box 52 is provided with two limiting guide columns 56 arranged in the first direction, both of which extend in the second direction and penetrate the limiting guide slot 55.

[0112] Specifically, as shown in Figure 4 and Figure 5 When the image acquisition device 7 needs to be taken during the cleaning operation, the main joint 44 is adjusted to the first storage rack 510 by the six-axis mechanical arm 43, and then the main joint 44 is controlled to be separated from the first quick-change joint 45. Then the main joint 44 is moved to the plug-in slot 53 by the six-axis mechanical arm 43, and the sealing plate 54 is pushed by the main joint 44. The sealing plate 54 is limited by the two limiting guide columns 56, and the sealing plate 54 can move to the left towards the inside of the dustproof box 52 and compress the return spring 57. When the main joint 44 moves to the second storage rack 59, the main joint 44 is controlled to be connected with the second quick-change joint 47, and the taking of the image acquisition device 7 is completed.

[0113] In some examples, as shown in Figure 4 and Figure 5 The top end of the dustproof box 52 is provided with an avoiding slot 58, and the end of the sealing plate 54 away from the return spring 57 is provided with a guide rubber block 511, and the end of the guide rubber block 511 away from the return spring 57 has two guide inclined surfaces.

[0114] Specifically, as shown in Figure 4 and Figure 5As shown, one guide ramp of the guide rubber block 511 extends from the bottom to the middle, and the other guide ramp extends from the top to the middle away from the sealing plate 54. This allows the clearance groove 58 to avoid interference with the movement of the six-axis robotic arm 43 connected to the main connector 44. During retrieval, after the main connector 44 is connected to the second quick-connect connector 47, pulling the main connector 44, the second quick-connect connector 47, and the image acquisition device 7 upwards prevents them from getting stuck due to the lower guide ramp, ensuring normal retrieval of the second quick-connect connector 47 and the image acquisition device 7. During storage, the image acquisition device 7 pushes the sealing plate 54, and when it reaches the position of the second storage rack 59, it moves downwards, also benefiting from the upper guide ramp, ensuring stable storage.

[0115] In some examples, such as Figures 4-6 As shown, a first sealing ring 512 is fitted on one end of the sealing plate 54 near the guide rubber block 511. The first sealing ring 512 is used to seal the insert groove 53. A second sealing ring 513 is provided at the top of the sealing plate 54. The second sealing ring 513 is used to seal the clearance groove 58.

[0116] Specifically, such as Figures 4-6 As shown, after the main connector 44 moves away from the dust box 52, the sealing plate 54 is reset by the reset spring 57, and then the first sealing ring 512 abuts against the inner wall of the insert groove 53, and the second sealing ring 513 abuts against the inner top surface of the dust box 52 and surrounds the clearance groove 58, so as to reduce the entry of external dust into the dust box 52 and achieve a good dustproof effect.

[0117] In some examples, the interior of the dust box 52 is connected to the air outlet of the compressed air device, and a miniature air pump 514 is provided on one side of the dust box 52. The air outlet of the miniature air pump 514 is connected to the interior of the dust box 52, and the air inlet of the miniature air pump 514 is connected to an external air source.

[0118] Compressed air units are commonly used air supply equipment in factories. They supply pressurized gas to various workshops via compressors and other machines, and each workshop uses this pressurized gas as the air source for pneumatic devices such as cylinders or grippers. The cleaning system of this invention introduces the pressurized gas supplied by the compressed air unit into the dustproof box 52, ensuring a slightly positive pressure inside the dustproof box 52. This prevents external dust from entering the dustproof box 52, thus improving the dustproof effect. Furthermore, as... Figure 3 As shown, when the compressed air device is under maintenance or the air supply is temporarily stopped, a suitable amount of gas can be injected into the dustproof box 52 by activating the micro air pump 514 to keep the inside of the dustproof box 52 in a slightly positive pressure state, so as to avoid reducing the dustproof effect.

[0119] In summary, the workpiece cleaning system before the workpiece inspection has the beneficial effects including:

[0120] The cleaning system of the present application adjusts the position of the image acquisition device through the eight-axis linkage device, which is convenient for shooting images of each area of the workpiece surface, and adjusts the position of the dry ice spray gun through the eight-axis linkage device, which is convenient for cleaning stains in each area. In addition, the second storage rack, the first storage rack, the second quick-change connector, the first quick-change connector and the main connector are arranged, so that the end of the eight-axis linkage device can be switched between the image acquisition device and the dry ice spray gun for use, and it is also convenient for storing the image acquisition device and the dry ice spray gun when not in use. Further, the cleaning system of the present application seals the opening of the dustproof box through the sealing plate, the first sealing rubber ring and the second sealing rubber ring, which avoids the entry of external dust into the dustproof box, avoids the attachment of dust on the surface of the image acquisition device, and prevents the shooting image from being unclear. Further, the cleaning system of the present application is provided with and filled with an appropriate amount of air into the dustproof box, which further avoids the entry of external dust into the dustproof box, and has a high dustproof effect.

[0121] Although the present application has been described with reference to the preferred embodiments, various modifications can be made to it without departing from the scope of the present application and equivalent components can be substituted therefor. In particular, the technical features mentioned in each embodiment can be combined in any manner as long as there is no structural conflict. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A cleaning method for workpieces before flaw detection, characterized in that, The cleaning method includes: S100. The workpiece is transported to the cleaning station, and the surface of the workpiece is divided into several areas; S200. Acquire images of each of the aforementioned regions on the workpiece using an image acquisition device; Step S200 specifically includes the following steps: S201. Control the eight-axis linkage device to acquire the image from the image acquisition device; S202. Adjust the position of the image acquisition device using the eight-axis linkage device, so that the image acquisition device can capture images of each of the aforementioned areas; S300. The stain recognition model identifies whether the image contains stains and the degree of dirtiness of the stains, marks the area corresponding to the image containing stains as a stain area, and outputs the corresponding cleaning level according to the degree of dirtiness of the stains. S400. Control the dry ice cleaning device to perform a cleaning operation, and spray dry ice particles onto the stained area according to the cleaning setting; Step S400 specifically includes the following steps: S401. Control the eight-axis linkage device to use the dry ice spray gun of the dry ice cleaning device; S402. Adjust the position of the dry ice spray gun using the eight-axis linkage device, so that the dry ice spray gun is directed toward any stained area; S403. Control the dry ice cleaning device to start according to the cleaning level corresponding to the stained area, and spray dry ice particles into the stained area; S404. Repeat steps S402 and S403 to clean all stained areas; S500. After cleaning, the image acquisition device acquires images of each of the stained areas on the workpiece after cleaning. S600. The stain recognition model identifies whether there are stains in the cleaned image. If stains are identified in the cleaned image, the corresponding area retains the stain area label; otherwise, the stain area label of the corresponding area is canceled. S700. After all the cleaning images have been identified, if there are no stained areas, proceed to the next step; if there are stained areas, increase the cleaning level by one level based on the previous cleaning and return to step S400. S800. Move the workpiece away from the cleaning station; Between step S700 and step S800, the following steps are also included: S701. Record the initial degree of soiling in each of the stained areas described in step S300; S702. Record the cleaning setting used during the last cleaning of each stained area; S703. Match the initial level of dirtiness to the cleaning setting used during the last wash; S704. Record the cleaning level corresponding to each level of dirt into the stain recognition model, overwriting the original correspondence.

2. The cleaning method for workpieces before flaw detection according to claim 1, characterized in that, The stain recognition model identifies the degree of dirtiness of the stain and outputs the cleaning level for cleaning. The degree of dirtiness is divided into levels 1 to n, from light to heavy, and the cleaning level is divided into levels 1 to m, from low to high, where m is greater than n. When the stain recognition model is created, the degree of dirtiness levels 1 to n correspond one-to-one with the cleaning level levels 1 to n.

3. A cleaning system for workpieces before flaw detection, characterized in that, The cleaning system is applied to the cleaning method for workpieces before flaw detection as described in claim 1 or 2, and the cleaning system comprises: The processing room is a soundproof room, with a cleaning station located in the center of the interior. Two eight-axis linkage devices are respectively located on both sides of the cleaning station; each eight-axis linkage device includes a ground rail located on one side of the cleaning station, a lifting device is provided on the slide of the ground rail, a six-axis robotic arm is provided on the slide of the lifting device, and a main connector is provided at the end of the six-axis robotic arm. A dry ice cleaning device, which includes a dry ice generating device and a dry ice spray gun; A dustproof device includes a dustproof box located on one side of the ground rail. A first storage rack is provided on the outer side of the dustproof box, and a second storage rack is provided inside the dustproof box. The second storage rack holds a second quick-connect coupling, and a second clamp is provided below the second quick-connect coupling, which holds an image acquisition device. The first storage rack holds a first quick-connect coupling, and a first clamp is provided at one end of the first quick-connect coupling, which is used to hold the dry ice spray gun. Both the second quick-connect coupling and the first quick-connect coupling can be detachably connected to the main connector. The central control unit is used to control the eight-axis linkage device, the dry ice cleaning device, and the image acquisition device.

4. The cleaning system for workpieces before flaw detection according to claim 3, characterized in that, The dustproof box has a slotted plate on one side wall, and a sealing plate is inserted into the slotted plate. The sealing plate extends in a first direction. A return spring is provided at one end of the sealing plate. A limiting guide groove extending through the middle of the sealing plate in a second direction is provided. Two limiting guide posts are provided at the top of the inside of the dustproof box, arranged in the first direction. Both limiting guide posts extend in the second direction and pass through the limiting guide groove.

5. The cleaning system for workpieces before flaw detection according to claim 4, characterized in that, The dustproof box is provided with an avoidance groove at the top, and the end of the sealing plate away from the reset spring is provided with a guide rubber block, and the end of the guide rubber block away from the reset spring has two guide slopes.

6. The cleaning system for workpieces before flaw detection according to claim 5, characterized in that, A first sealing ring is fitted onto one end of the sealing plate near the guide rubber block, and the first sealing ring is used to seal the insert groove; a second sealing ring is provided at the top of the sealing plate, and the second sealing ring is used to seal the clearance groove.

7. The cleaning system for workpieces before flaw detection according to claim 3, characterized in that, The dustproof box is connected to the air outlet of the compressed air device. A miniature air pump is provided on one side of the dustproof box. The air outlet of the miniature air pump is connected to the inside of the dustproof box, and the air inlet of the miniature air pump is connected to an external air source.

Images