Hot forging marking system, method, device and equipment

Abstract

The application discloses a hot forging piece marking system, method, device and equipment, and relates to the technical field of forging piece marking. The system comprises a marking robot, a visual sensor system and a central scheduling and data processing end. The visual sensor system is used for acquiring scanning point cloud data of an actual forging piece. The central scheduling and data processing end is used for acquiring forging piece identification information, first three-dimensional model data and scanning point cloud data of the actual forging piece. The first three-dimensional model data and the scanning point cloud data are subjected to spatial registration to acquire second three-dimensional model data of the actual forging piece under a preset spatial coordinate system and to acquire a first candidate marking area. The first candidate marking area is subjected to screening to acquire a target marking area and send the target marking area to the marking robot. The end of the marking robot is fixed with a marking die, and the marking robot can complete forging surface marking. The application can realize automatic marking of a forging piece in a hot state, reduce manual operation, and improve marking efficiency and operation safety.

Description

Technical Field

[0001] This application relates to the field of marking technology for forgings, and in particular to a marking system, method, apparatus and equipment for hot forgings. Background Technology

[0002] Large forgings, especially in the field of high-end equipment manufacturing, such as aircraft main load-bearing frames and engine turbine disks, are core components of high-end equipment. After forging, they must be permanently marked immediately in a hot state (usually above 700°C) (such as work order number + ingot section number) to achieve full life cycle quality traceability from raw materials to finished products.

[0003] However, existing technologies rely heavily on manual hand-held pneumatic marking machines, which operate in harsh environments (high temperature and high noise). The marking position, depth, and clarity all depend on the worker's experience, resulting in poor consistency and low efficiency.

[0004] Therefore, there is an urgent need for a hot forging marking system, method, device and equipment that can reduce manual intervention. Summary of the Invention

[0005] The purpose of this application is to provide a hot forging marking system, method, apparatus and equipment to realize automatic marking of forgings in a hot state, reduce manual operation, and improve marking efficiency and operational safety.

[0006] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a hot forging marking system, comprising: The hot forging marking system includes a marking robot, a vision sensor system, and a central scheduling and data processing terminal, wherein: The vision sensor system includes a 3D scanner, which is used to acquire scanned point cloud data of the actual forging. The central scheduling and data processing terminal is used for: Obtain the forging identification information, the first three-dimensional model data, and the scanned point cloud data of the actual forging; Spatial registration is performed between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system; A first candidate marking area is obtained based on the second three-dimensional model data and the forging identification information; the first candidate marking area is filtered to obtain the target marking area; the coordinates of the target marking area are sent to the marking robot. The marking robot has a marking mold fixed at its end, and the marking robot is used to control the end to move to the target area to complete the marking on the forging surface.

[0007] Optionally, the hot forging marking system further includes a manual terminal, and the vision sensor system further includes a thermal imaging sensor; wherein The thermal imaging sensor is used to acquire thermal imaging data of the target marking area. The central scheduling and data processing terminal is used to obtain the temperature level of the target marking area based on the thermal imaging data, and to obtain the corresponding material parameters based on the temperature level. The manual terminal is used to obtain the forging identification information and material parameters to remind staff to replace the corresponding marking mold.

[0008] Secondly, this application provides a method for marking hot forgings, including: Obtain the forging identification information, first three-dimensional model data, and scanned point cloud data of the actual forging; Spatial registration is performed between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system; The first candidate marking area is obtained based on the second three-dimensional model data and the forging identification information, and the first candidate marking area is filtered to obtain the target marking area.

[0009] Optionally, the first three-dimensional model data includes a processing identifier, which indicates whether a point or region in the first three-dimensional model data is processable. The step of obtaining the first candidate marking region based on the second three-dimensional model data includes: The dimension to be marked is obtained based on the forging identification information; Obtain the first projection image of the second 3D model on the first preset plane; Traverse the first projected image and select areas on the first projected image whose size is the size to be marked and whose corresponding processing marks all indicate that they can be processed as the first candidate marking areas.

[0010] Optionally, the step of filtering the first candidate marking regions to obtain the target marking region includes: Based on the second 3D model data, a local curvature cloud map of the first candidate marking region is obtained. The first candidate marking region is then filtered according to the local curvature cloud map to obtain a second candidate marking region. The curvature index of the second candidate marking region is obtained based on the local curvature cloud map. The higher the curvature index, the higher the flatness of the second candidate marking region. Based on the target reachability analysis of the second candidate marking area by the marking robot, it is determined whether the end of the marking robot can reach the second candidate marking area, and the second candidate marking area that cannot be reached is filtered out to obtain the third candidate marking area; Visual analysis is performed on the local 3D model of the third candidate marking region based on preset observation points to obtain a first viewing angle. The third candidate marking regions with the first viewing angle less than the preset angle are filtered out to obtain a fourth candidate marking region. The viewing angle index of the fourth candidate marking region is obtained based on the first viewing angle. The higher the viewing angle index, the more significant the location of the fourth candidate marking region. Based on the forging identification, a local stress cloud map of the fourth candidate marking area is obtained. If there is a stress value greater than a preset stress value in the local stress cloud map, the corresponding fourth candidate marking area is filtered out to obtain a fifth candidate marking area. The stress index of the fifth candidate marking area is obtained based on the local stress cloud map. The higher the stress index, the lower the possibility of deformation of the fifth candidate marking area. A comprehensive index is obtained by weighting the visual angle index, the stress index, and the curvature index, and the fifth candidate marking area with the highest comprehensive index is selected as the target marking area.

[0011] Optionally, the step of filtering the first candidate marking region based on the local curvature cloud map to obtain the second candidate marking region includes: Based on the local curvature cloud map, the curvature change gradient of the first candidate marking region is obtained, and the first candidate marking regions with curvature change gradients greater than preset change gradients are filtered out; for the filtered first candidate marking regions, the first candidate marking regions with curvature absolute values ​​greater than preset absolute values ​​are filtered out to obtain the second candidate marking regions. The step of obtaining the curvature index of the second candidate marking region based on the local curvature cloud map includes: Obtain the absolute value of the average curvature value of the local curvature cloud map of the second candidate marking region, and perform maximum normalization on the absolute value to obtain the curvature index.

[0012] Optionally, the step of performing visual analysis on the local 3D model of the first candidate marking area based on preset observation points to obtain the first viewing angle includes: Obtain multiple sampling points in the local 3D model; The line connecting the preset observation point to the sampling point is obtained based on the preset spatial coordinate system; Obtain the second visible angle between the connecting line and the second preset plane; The smallest angle among the second viewing angles is selected as the first viewing angle.

[0013] Optionally, after filtering the first candidate marking areas to obtain the target marking area, the hot forging marking method further includes: The thermal imaging data of the target marking area is acquired, the temperature level of the target marking area is obtained based on the thermal imaging data, the corresponding material parameters are obtained based on the temperature level, and the forging identification information and material parameters are sent to the manual terminal to remind the staff to change the corresponding marking mold.

[0014] Thirdly, this application provides a marking device for hot forgings, comprising: The acquisition module is used to acquire the forging identification information, first three-dimensional model data and scanned point cloud data of the actual forging; The registration module is used to spatially register the first three-dimensional model data with the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system. The positioning module is used to obtain a first candidate marking area based on the second three-dimensional model data and the forging identification information, and to filter the first candidate marking area to obtain the target marking area.

[0015] Fourthly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the hot forging marking method described in any one of the above.

[0016] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the hot forging marking method described in any one of the above descriptions.

[0017] Sixthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the hot forging marking method described above.

[0018] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a hot forging marking system, method, apparatus, and equipment. It acquires scanned point cloud data of the actual forging through a 3D scanner, spatially registers the scanned point cloud with a first 3D model to determine the target marking area, and uses a marking robot to mark the forging surface, thereby realizing automatic marking of forgings in a hot state, reducing manual operation, and improving marking efficiency and operational safety. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A schematic diagram of a hot forging marking system provided in an embodiment of this application; Figure 2 A schematic flowchart illustrating a hot forging marking method provided in an embodiment of this application; Figure 3 for Figure 2 A detailed flowchart of step 203; Figure 4 This is a schematic diagram of preset observation points and sampling points provided in an embodiment of this application; Figure 5 A functional module schematic diagram of a hot forging marking device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0021] Figure label: 101-Central dispatch and data processing terminal; 102-Marking robot; 103-Vision sensor system; 104-Fixture; 105-Manual terminal; 106-Actual forging; 107-Space to be marked. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be noted that the terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention 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 so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0024] It should be noted that "at the time of..." in the embodiments of this application can be either at the instant when a certain situation occurs, or for a period of time after the occurrence of a certain situation. The embodiments of this application do not make specific limitations on this.

[0025] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] This application provides a hot forging marking system, such as... Figure 1 As shown, it includes a marking robot 102, a vision sensor system 103, and a central scheduling and data processing terminal 101, wherein: The vision sensor system 103 includes a 3D scanner for acquiring scanned point cloud data of the actual forging 106; Central dispatch and data processing terminal 101 is used for: Acquire the forging identification information, first three-dimensional model data and scanned point cloud data of the actual forging 106; perform spatial registration between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging 106 in a preset spatial coordinate system; The first candidate marking area is obtained based on the second three-dimensional model data and forging identification information. The first candidate marking area is then filtered to obtain the target marking area. The coordinates of the target area are then sent to the marking robot 102. The marking robot 102 has a marking mold fixed at its end. The marking robot 102 is used to control the end to move to the target area to complete the marking of the forging surface.

[0027] Furthermore, the hot forging marking system also includes a manual terminal 105, and the vision sensor system 103 includes a thermal imaging sensor; wherein Thermal imaging sensors are used to acquire thermal imaging data of the target marking area. The central dispatch and data processing terminal 101 is used to obtain the temperature level of the target marking area based on thermal imaging data, and to obtain the corresponding material parameters based on the temperature level. The manual terminal 105 is used to obtain forging identification information and material parameters to remind staff to change the corresponding marking mold.

[0028] Furthermore, the thermal imaging sensor is an infrared thermal imager and / or a hyperspectral camera; Furthermore, the marking robot 102 adopts existing multi-degree-of-freedom industrial robots and control modules, and fixes a marking head (preferably a fiber laser marking head) at the end of the robot.

[0029] Furthermore, the actual forging 106 is fixed in the marking space 107 by a rotatable fixture 104. If the first candidate marking area or the target marking area is not obtained according to the method of this application, the central scheduling and data processing terminal 101 can send a rotation command to the rotatable fixture 104. After the rotatable fixture 104 rotates by a preset angle in response to the rotation command, the central scheduling and data processing terminal 101 re-obtains the scanned point cloud data of the actual forging 106 according to the 3D scanner and obtains the target marking area according to the method of this application.

[0030] Furthermore, the central dispatch and data processing terminal 101 also includes a data storage system, which can store the data that the central dispatch and data processing terminal 101 needs to process. The data storage system can be set up separately, integrated into the central dispatch and data processing terminal 101, or placed in the cloud or on other servers.

[0031] Specifically, this application provides a hot forging marking system that acquires scanned point cloud data of the actual forging 106 using a 3D scanner, spatially registers the scanned point cloud with a first 3D model to determine the target marking area, and uses a marking robot 102 to mark the forging surface, thereby achieving automatic marking of the forging in a hot state, reducing manual operation, and improving marking efficiency and operational safety.

[0032] The hot forging marking method provided in this application embodiment can be applied to, for example... Figure 1 The central scheduling and data processing terminal of the hot forging marking system shown is as follows: Figure 2 The method includes steps 201 to 203. Wherein: Step 201: Obtain the forging identification information, first three-dimensional model data, and scanned point cloud data of the actual forging; Specifically, the central dispatch and data processing terminal pre-stores standard three-dimensional digital model files (first three-dimensional model data) of all forging products as well as forging marking information; Step 202: Spatial registration is performed between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in the preset spatial coordinate system; Specifically, the standard spatial coordinate system of the marking robot is used as the preset spatial coordinate system. The scanned point cloud data is transformed into first point cloud data under the preset spatial coordinate system. The first point cloud data is spatially registered with the first 3D model to obtain the spatial pose transformation matrix of the first 3D model. Based on the spatial pose transformation matrix, the first 3D model is transformed into a second 3D model. The second 3D model contains the position information of the actual forging in the preset spatial coordinate system.

[0033] Furthermore, existing spatial registration algorithms can be used to spatially register the first point cloud data and the first 3D data; As one embodiment, the ICP (Iterative Closest Point) algorithm can be used for spatial registration to obtain the spatial pose transformation matrix. The spatial pose transformation matrix is ​​a 4x4 homogeneous coordinate transformation matrix, which describes the data information for x-axis translation, x-axis rotation, y-axis translation, y-axis rotation, z-axis translation, and z-axis rotation. The product of the points of the first 3D model and the spatial pose transformation matrix T can obtain the points in the preset spatial coordinate system to obtain the second 3D model. The spatial pose transformation matrix T specifically includes: ; Wherein, the rotation matrix R 3×3 In the middle, r 11 r 21 and r 31 The components of a point projected onto the x-axis of the original coordinate system (the coordinate system of the first 3D model) in the preset spatial coordinate system along the x-axis, y-axis, and z-axis directions, r. 12 r 22 and r 32 The component of the x-axis, the component along the y-axis, and the component along the z-axis of a point projected onto the preset spatial coordinate system from the y-axis of the original coordinate system. 13 r 23 and r 33 The translation vector T is the component of the z-axis of a point in the original coordinate system projected onto the x-axis, y-axis, and z-axis of the preset spatial coordinate system. 3×1 In the middle, t x t y and t z These represent the translation amounts from the original coordinate system to the preset spatial coordinate system along the x-axis, y-axis, and z-axis, respectively.

[0034] Step 203: Obtain the first candidate marking area based on the second three-dimensional model data and forging identification information, and filter the first candidate marking area to obtain the target marking area.

[0035] Specifically, the forging identification information includes the forging identification (e.g., ID number). By looking up the forging marking information mapping table corresponding to the forging identification, the part drawing number, work order number, and ingot section number of the forging can be obtained. The part drawing number, work order number, and ingot section number are combined to form the marking identification. The first candidate marking area is obtained based on the marking identification and the second and third-dimensional model data, and the target marking area is further filtered to obtain the target marking area.

[0036] In another exemplary embodiment of this application, in order to select a suitable marking area as the target marking area from the first candidate marking area, the target marking area is made flatter, making the marking easier to detect when applied to that area, reducing the probability of deformation of the forging, and ensuring the marking robot path is reachable, thereby improving the marking success rate. Figure 3 As shown, step 203 above is replaced by steps 301 to 307: Step 301: Obtain the size to be marked based on the forging identification information, and obtain the first projection image of the second three-dimensional model on the first preset plane; Specifically, the forging identification information includes the forging identification. By looking up the forging marking information mapping table corresponding to the forging identification, the part drawing number, work order number, and ingot section number of the forging can be obtained. The part drawing number, work order number, and ingot section number are combined to form the marking identification. Specifically, the size to be marked is obtained based on the marking identifier, which includes multiple characters. The length of the size to be marked is obtained by multiplying the number of characters by the preset length, and the preset height of the characters is the height of the length of the size to be marked.

[0037] Specifically, the first preset plane is a plane perpendicular to the marking direction of the marking robot; As one example, such as Figure 1 The spatial coordinate system shown is the standard coordinate system of the marking robot. With the negative z-axis as the marking direction of the robot, the xOy plane can be selected as the first preset plane, or a plane that is perpendicular to the marking direction and passes through the axis of the rotatable fixture can be selected as the first preset plane.

[0038] Step 302: Traverse the first projection image and select areas on the first projection image whose size is the size to be marked and whose corresponding processing marks all indicate that they can be processed as the first candidate marking areas.

[0039] Specifically, the first three-dimensional model data includes processing identifiers, which are used to indicate whether points or regions in the first three-dimensional model data are processable.

[0040] For example, the first 3D model data includes custom machining allowance attributes, finishing surface labels, and no-marking-area labels. Based on the size to be marked, the first projected image is traversed, and areas without no-marking-area labels and with a size equal to the size to be marked are selected as the first candidate marking areas.

[0041] Specifically, the coordinates of the first candidate marking region on the first projection image are two-dimensional coordinates. For example, if the negative direction of the z-axis is the first preset plane, then the coordinates of the first candidate marking region on the first projection image are coordinates on the plane xOy. Based on the coordinates on xOy, the coordinates corresponding to the z-axis in the second three-dimensional data can be obtained, and a local three-dimensional model of the first candidate marking region can be obtained.

[0042] Step 303: Obtain the local curvature cloud map of the first candidate marking region based on the second three-dimensional model data; filter the first candidate marking region based on the local curvature cloud map to obtain the second candidate marking region; obtain the curvature index of the second candidate marking region based on the local curvature cloud map; wherein, the higher the curvature index, the higher the flatness of the second candidate marking region. Specifically, the curvature change gradient of the first candidate labeling region is obtained based on the local curvature cloud map, and the first candidate labeling region with a curvature change gradient greater than the preset change gradient is screened out; for the screened first candidate labeling regions, the first candidate labeling regions with a curvature resolution value greater than the preset absolute value are screened out to obtain the second candidate labeling region. Specifically, iterate through each pixel value of the first candidate marking region, calculate the curvature change gradient of the point based on the curvature of the point and its neighboring points, and if there is a curvature change gradient greater than the preset change gradient, filter out the corresponding candidate marking region. Specifically, the curvature gradient can be used to determine whether the first candidate marking region has a "break" or "discontinuity". Since the first candidate marking region is obtained from the first projection image in a certain direction, the first candidate marking region is mapped in the second three-dimensional model data and may include two different parts. Therefore, there may be a "break" or "discontinuity", which means that the first candidate marking region does not belong to a certain surface. The curvature gradient can be used to identify and extract the region.

[0043] Specifically, for the first candidate marking area remaining after screening, we consider that the first candidate marking area belongs to a single surface, and we determine whether the area is flat by using a local curvature cloud map.

[0044] As a method that implements local curvature contour mapping to display the degree of curvature at each point, the smaller the curvature, the closer the area is to flatness. Positive curvature indicates a convex surface, while negative curvature indicates a concave surface. Therefore, the first candidate marking areas with curvature absolute values ​​greater than a preset absolute value are further filtered out, i.e., the first candidate marking areas that are severely convex or severely concave are filtered out, and the remaining first candidate marking areas are used as the second candidate marking areas.

[0045] Similarly, the flatness of the second candidate marking region is measured by the absolute value of the average curvature value of the local curvature cloud map. Since the smaller the absolute value of the average curvature, the flatter the plane, the absolute value is normalized to a very large value (so that the smaller the value, the larger the index should be mapped) to obtain the curvature index.

[0046] Step 304: Based on the target reachability analysis of the second candidate marking area by the marking robot, determine whether the end of the marking robot can reach the second candidate marking area, and filter out the second candidate marking area that cannot be reached to obtain the third candidate marking area. Specifically, mature robot modules all include corresponding reachability analysis functions, which can directly call internal modules for analysis. The local 3D model of the second candidate marking area is sent to the marking robot. The marking robot performs reachability and path analysis based on the environmental perception module, and eliminates the second candidate marking area that the robot end cannot reach to obtain the third candidate marking area.

[0047] Step 305: Perform visual analysis on the local 3D model of the third candidate marking area based on the preset observation point to obtain the first viewing angle; filter out the third candidate marking areas with the first viewing angle smaller than the preset angle to obtain the fourth candidate marking area; obtain the viewing angle index of the fourth candidate marking area based on the first viewing angle; wherein, the higher the viewing angle index, the more significant the location of the fourth candidate marking area. Specifically, such as Figure 4 Multiple sampling points in the local 3D model are obtained (they can be randomly obtained or a preset number of sampling points can be obtained evenly distributed). Based on the preset spatial coordinate system, the line connecting the preset observation point to the sampling point is obtained. Similarly, the preset observation point can be set to one or more. The second visible angle between the line and the second preset plane is obtained. The smallest angle among the second visible angles is selected as the first visible angle.

[0048] The second preset plane is a plane perpendicular to the marking direction. The first visible angle is in the range of 0° to 90°. The smaller the first visible angle, the less likely the mark will be to be noticed if it is placed in that area. Therefore, a preset angle is set. If the first visible angle is less than the preset angle, the third candidate marking area is eliminated.

[0049] Furthermore, it is determined whether the connecting line intersects with the second 3D model data. If there is an intersection, it is determined that if the label is placed in this area, it is easily obscured by other parts of the model. The third candidate labeling area is also eliminated, and the fourth candidate labeling area is finally obtained.

[0050] Furthermore, for the fourth candidate labeling area, the first viewing angle is normalized and used as the viewing angle index for that area.

[0051] Step 306: Obtain the local stress cloud map of the fourth candidate marking area based on the forging identification. If there is a stress value greater than the preset stress value in the local stress cloud map, filter out the corresponding fourth candidate marking area to obtain the fifth candidate marking area; obtain the stress index of the fifth candidate marking area based on the local stress cloud map; wherein, the higher the stress index, the less likely the fifth candidate marking area is to deform. Specifically, a preset stress cloud map is obtained based on the forging identification. The preset stress cloud map is obtained by finite element analysis based on the first three-dimensional model. Similarly, the local stress cloud map of the third candidate marking area can be obtained based on the spatial pose transformation matrix (converted into data in the preset spatial coordinate system).

[0052] Specifically, threshold screening is performed based on the local stress cloud map. The greater the stress, the more likely it is to exceed the material limit, making deformation or fracture more likely. If there is a stress value greater than the preset stress value in the local stress cloud map, the corresponding fourth candidate marking area is removed, and the remaining fourth candidate marking areas are used as the fifth candidate marking areas. As another embodiment, it is also possible to obtain an area with a stress value greater than a preset value, obtain the area ratio of the area in the third candidate marking area, and when the area ratio exceeds the preset ratio value, remove the corresponding fourth candidate marking area to obtain the fifth candidate marking area.

[0053] For the fifth candidate marking area after screening, since the smaller the stress, the less likely the deformation and fracture will occur, the corresponding stress index is obtained according to the local stress cloud map to reflect the stress distribution of the entire area. The higher the stress index, the less likely the candidate marking area will be deformed.

[0054] As one embodiment, the average stress value of the local stress cloud map is obtained, and the average stress value is subjected to maximum normalization (so that the smaller the value, the larger the index should be mapped) as the stress index.

[0055] Specifically, the screening conditions in steps 304 to 306 do not have a strict sequential relationship.

[0056] Step 307: Obtain a comprehensive index based on the weighted average of the viewing angle index, stress index, and curvature index, and select the fifth candidate marking area with the highest comprehensive index as the target marking area.

[0057] Specifically, the higher the comprehensive index, the flatter the area will be when the mark is applied, the easier it will be to spot the mark, the lower the probability of deformation of the forging, and the more accessible the marking robot path will be.

[0058] Furthermore, if no candidate marking area is obtained according to the steps in steps 302 to 306, a rotation command can be sent to the rotatable fixture. The rotatable fixture responds to the rotation command by rotating a preset angle, then reacquires the scanned point cloud data and returns to step 202 until the target marking area is obtained.

[0059] In another exemplary embodiment of this application, since the marking effect is easily affected by factors such as temperature when the forging is in a hot state, different materials should be selected according to different temperatures and other conditions. After step 203 or 307 above, the method may further include the following step 401: Step 401: Obtain thermal imaging data of the target marking area, obtain the temperature level of the target marking area based on the thermal imaging data, obtain the corresponding material parameters based on the temperature level, and send the forging identification information and material parameters to the manual terminal to remind the staff to change the corresponding marking mold.

[0060] Furthermore, after marking is completed, the image information of the marked mark is acquired, and text recognition is performed on the image information to verify whether the marked content is correct, as well as to obtain the corresponding clarity and contrast to ensure the accuracy of the marking.

[0061] As one example, the material parameters are used to indicate the material of the marking mold. The material parameters include three types: 300M steel (a type of low-alloy ultra-high-strength steel), TC4 (a type of titanium alloy), and GH4169 (a type of precipitation-strengthened nickel-based high-temperature alloy). Specifically, the temperature rating is obtained based on a temperature index, which can be the average temperature of the target marking area, or a weighted average of the average, maximum, and minimum temperatures of the target marking area. The temperature rating is determined based on the range of the temperature index, and the material parameters are determined based on the mapping relationship between the temperature rating and the material parameters. As one example, if the temperature index is between 700°C and 900°C, the corresponding temperature level is determined as T1, and the corresponding material parameter is 300M. If the corresponding temperature index is between 800°C and 900°C, the temperature level is determined as T2, and the corresponding material parameter is TC4. If the corresponding temperature index is between 900°C and 1000°C, the temperature level is determined as T3, and the corresponding material parameter is GH4169.

[0062] Example 1 Take the hot marking of the main landing gear of a certain type of domestically produced large aircraft on the forging production line as an example.

[0063] According to the obtained marking instructions, the marking format to be marked is: "Main landing gear - drawing number A - spindle section number 202603120001".

[0064] Step 201 is executed to obtain forging identification information, first three-dimensional model data (three-dimensional data saved by retrieving forging identification information, in this embodiment it is a STEP format three-dimensional model) and scan point cloud data of the newly produced landing gear (surface temperature about 900°C) by quickly scanning it using a blue light three-dimensional scanner.

[0065] Based on the analysis of the first three-dimensional model data, the drawing number was determined to be "Structural Member_A", thus determining the marking identifier and the size of the marking frame as 120cm×160cm.

[0066] In step 202, the translation vectors (ΔX, ΔY, ΔZ) and rotation matrix R are calculated through ICP registration. The first 3D model data is then converted into second 3D model data using the translation vectors (ΔX, ΔY, ΔZ) and rotation matrix R.

[0067] By executing steps 301 to 307, the joint marking robot performs steps such as region selection, curvature analysis and selection, target accessibility analysis based on robot path, visual analysis and selection, and stress analysis and selection of the projected image. Through comprehensive evaluation, the target marking area is obtained and the center point coordinates (X=1250.3mm, Y=455.7mm, Z=320.1mm) and normal attitude (A=-5.2°, B=0.8°, C=180.0°, where A, B, and C are the Euler angles of the marking head attitude, A is the rotation angle around the X-axis; B is the rotation angle around the Y-axis; and C is the rotation angle around the Z-axis) are sent to the marking robot.

[0068] Step 401 involves selecting the material "300M steel" based on the average temperature of the target marking area (900℃) obtained from thermal imaging data. This information is then sent to the human terminal. Upon receiving the instruction to begin marking from the human terminal, the marking is completed by a marking robot. The marking robot is configured with the following parameters: power 120W, speed 800mm / s, frequency 60kHz, and positive defocus 2mm. The laser completes the clear marking within 30 seconds according to these parameters.

[0069] After marking is completed, a vision camera fixed above the workstation takes a picture, and the image processing software decodes the QR code, which contains "202603120001_Structural Member_A". Decoding is successful. Simultaneously, the algorithm evaluates the marker contrast to be 0.85 (threshold > 0.7), deeming it acceptable. The central unit encapsulates data such as "successful marking, timestamp, parameters, quality inspection image, and decoding result," completing a full intelligent marking cycle.

[0070] This application provides a marking method and system for hot forgings, which includes the following technical effects: It achieves automated marking from task initiation to completion, reduces manual intervention, frees workers from harsh environments, eliminates human error, and improves the accuracy of marking.

[0071] By spatial registration and joint marking robot to perform region selection, curvature analysis and selection, target accessibility analysis based on robot path, visual analysis and selection, and stress analysis and selection of projected images, and through comprehensive evaluation of indicators, the surface area that can avoid subsequent machining surfaces and high stress areas, and has gentle curvature and a wide field of view is selected as the target marking area, thereby improving the success rate of automated marking.

[0072] The higher the overall index, the flatter the area will be when the mark is applied, making the mark easier to spot, reducing the probability of deformation of the forging, and ensuring that the marking robot path is reachable.

[0073] By dynamically adjusting marking parameters based on real-time temperature, the marking quality fluctuations caused by temperature fluctuations are overcome, ensuring clear and durable markings under various working conditions.

[0074] The method described in this application can lay the foundation for building a complete and reliable quality traceability data chain, lean manufacturing, and quality analysis.

[0075] Based on the same inventive concept, this application also provides a hot forging marking device for implementing the hot forging marking method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more hot forging marking device embodiments provided below can be found in the limitations of the hot forging marking method described above, and will not be repeated here.

[0076] In one exemplary embodiment, such as Figure 5 As shown, a marking device for hot forgings is provided, comprising: The acquisition module is used to acquire the forging identification information, first three-dimensional model data and scanned point cloud data of the actual forging; The registration module is used to spatially register the first three-dimensional model data with the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system. The positioning module is used to obtain the first candidate marking area based on the second three-dimensional model data and forging identification information, and to filter the first candidate marking area to obtain the target marking area.

[0077] As an optional implementation, the first 3D model data includes processing identifiers, which indicate whether points or regions in the first 3D model data are processable. The positioning module is used to: Obtain the marking dimensions based on the forging identification information; Obtain the first projection image of the second 3D model on the first preset plane; Traverse the first projected image and select areas on the first projected image whose size is the size to be marked and whose corresponding processing marks all indicate that they can be processed as the first candidate marking areas.

[0078] As an optional implementation, the positioning module is used for: Based on the second 3D model data, a local curvature cloud map of the first candidate marking region is obtained. The first candidate marking region is then filtered based on the local curvature cloud map to obtain a second candidate marking region. The curvature index of the second candidate marking region is obtained based on the local curvature cloud map. The higher the curvature index, the higher the flatness of the second candidate marking region. Based on the target reachability analysis of the second candidate marking area by the marking robot, it is determined whether the end of the marking robot can reach the second candidate marking area. The second candidate marking area that cannot be reached is screened out to obtain the third candidate marking area. Visual analysis is performed on the local 3D model of the third candidate marking region based on preset observation points to obtain the first viewing angle. The third candidate marking regions with the first viewing angle smaller than the preset angle are filtered out to obtain the fourth candidate marking region. The viewing angle index of the fourth candidate marking region is obtained based on the first viewing angle. The higher the viewing angle index, the more significant the location of the fourth candidate marking region. The local stress cloud map of the fourth candidate marking area is obtained based on the forging identification. If there is a stress value greater than the preset stress value in the local stress cloud map, the corresponding fourth candidate marking area is screened out to obtain the fifth candidate marking area. The stress index of the fifth candidate marking area is obtained based on the local stress cloud map. Among them, the higher the stress index, the less likely the fifth candidate marking area is to be deformed. A comprehensive index is obtained by weighting the visual angle index, stress index, and curvature index, and the fifth candidate marking area with the highest comprehensive index is selected as the target marking area.

[0079] As an optional implementation, the positioning module is also used for: The curvature change gradient of the first candidate marking region is obtained based on the local curvature cloud map. The first candidate marking region with a curvature change gradient greater than the preset change gradient is removed. For the first candidate marking region after removal, the first candidate marking region with a curvature absolute value greater than the preset absolute value is removed to obtain the second candidate marking region. The curvature index of the second candidate labeling region is obtained based on the local curvature cloud map, including: Obtain the absolute value of the average curvature value of the local curvature cloud map of the second candidate marking region, and perform maximum normalization on the absolute value to obtain the curvature index.

[0080] As an optional implementation, the positioning module is also used for: Obtain multiple sampling points in a local 3D model; Obtain the connection between the preset observation point and the sampling point based on the preset spatial coordinate system; Obtain the second visible angle between the connecting line and the second preset plane; The smallest angle among the second visible angles is selected as the first visible angle.

[0081] As an optional implementation, the positioning module is also used for: Acquire thermal imaging data of the target marking area, obtain the temperature level of the target marking area based on the thermal imaging data, obtain the corresponding material parameters based on the temperature level, and send the forging identification information and material parameters to the manual terminal to remind the staff to change the corresponding marking mold.

[0082] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a hot-forging marking method.

[0083] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0084] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0085] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0086] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0088] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0089] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. In summary, the content of this specification should not be construed as a limitation of this application.

Claims

1. A marking system for hot forgings, characterized in that, The hot forging marking system includes a marking robot, a vision sensor system, and a central scheduling and data processing terminal, wherein: The vision sensor system includes a 3D scanner, which is used to acquire scanned point cloud data of the actual forging. The central scheduling and data processing terminal is used for: Obtain the forging identification information, the first three-dimensional model data, and the scanned point cloud data of the actual forging; Spatial registration is performed between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system; A first candidate marking area is obtained based on the second three-dimensional model data and the forging identification information; the first candidate marking area is filtered to obtain the target marking area; the coordinates of the target marking area are sent to the marking robot. The marking robot has a marking mold fixed at its end, and the marking robot is used to control the end to move to the target marking area to complete the marking of the forging surface.

2. The hot forging marking system according to claim 1, characterized in that, The hot forging marking system also includes a manual terminal, and the vision sensor system also includes a thermal imaging sensor; wherein: The thermal imaging sensor is used to acquire thermal imaging data of the target marking area; The central scheduling and data processing terminal is used to obtain the temperature level of the target marking area based on the thermal imaging data, and to obtain the corresponding material parameters based on the temperature level. The manual terminal is used to obtain the forging identification information and the material parameters to remind the staff to replace the corresponding marking mold.

3. A method for marking hot forgings, characterized in that, The hot forging marking method includes: Obtain the forging identification information, first three-dimensional model data, and scanned point cloud data of the actual forging; Spatial registration is performed between the first three-dimensional model data and the scanned point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system; The first candidate marking area is obtained based on the second three-dimensional model data and the forging identification information, and the first candidate marking area is filtered to obtain the target marking area.

4. The marking method for hot forgings according to claim 3, characterized in that, The first three-dimensional model data includes machining identifiers, which indicate whether a point or region in the first three-dimensional model data is machinable. The step of obtaining the first candidate marking region based on the second three-dimensional model data and the forging identifier information includes: The dimension to be marked is obtained based on the forging identification information; Obtain the first projection image of the second 3D model on the first preset plane; Traverse the first projected image and select areas on the first projected image whose size is the size to be marked and whose corresponding processing marks all indicate that they can be processed as the first candidate marking areas.

5. The marking method for hot forgings according to claim 3, characterized in that, The step of filtering the first candidate marking region to obtain the target marking region includes: Based on the second 3D model data, a local curvature cloud map of the first candidate marking region is obtained. The first candidate marking region is then filtered according to the local curvature cloud map to obtain a second candidate marking region. The curvature index of the second candidate marking region is obtained based on the local curvature cloud map. The higher the curvature index, the higher the flatness of the second candidate marking region. Based on the target reachability analysis of the second candidate marking area by the marking robot, it is determined whether the end of the marking robot can reach the second candidate marking area, and the second candidate marking area that cannot be reached is filtered out to obtain the third candidate marking area; Visual analysis is performed on the local 3D model of the third candidate marking region based on preset observation points to obtain a first viewing angle. The third candidate marking regions with the first viewing angle less than the preset angle are filtered out to obtain a fourth candidate marking region. The viewing angle index of the fourth candidate marking region is obtained based on the first viewing angle. The higher the viewing angle index, the more significant the location of the fourth candidate marking region. Based on the forging identification information, a local stress cloud map of the fourth candidate marking area is obtained. If there is a stress value greater than a preset stress value in the local stress cloud map, the corresponding fourth candidate marking area is filtered out to obtain a fifth candidate marking area. The stress index of the fifth candidate marking area is obtained based on the local stress cloud map. The higher the stress index, the lower the possibility of deformation of the fifth candidate marking area. A comprehensive index is obtained by weighting the visual angle index, the stress index, and the curvature index, and the fifth candidate marking area with the highest comprehensive index is selected as the target marking area.

6. The marking method for hot forgings according to claim 5, characterized in that, The step of filtering the first candidate marking region based on the local curvature cloud map to obtain the second candidate marking region includes: Based on the local curvature cloud map, the curvature change gradient of the first candidate marking region is obtained, and the first candidate marking regions with curvature change gradients greater than preset change gradients are filtered out; for the filtered first candidate marking regions, the first candidate marking regions with curvature absolute values ​​greater than preset absolute values ​​are filtered out to obtain the second candidate marking regions. The step of obtaining the curvature index of the second candidate marking region based on the local curvature cloud map includes: Obtain the absolute value of the average curvature value of the local curvature cloud map of the second candidate marking region, and perform maximum normalization on the absolute value to obtain the curvature index.

7. The marking method for hot forgings according to claim 5, characterized in that, The step of obtaining a first viewing angle by visually analyzing the local 3D model of the third candidate marking area based on preset observation points includes: Obtain multiple sampling points in the local 3D model; The line connecting the preset observation point to the sampling point is obtained based on the preset spatial coordinate system; Obtain the second visible angle between the connecting line and the second preset plane; The smallest angle among the second viewing angles is selected as the first viewing angle.

8. The marking method for hot forgings according to claim 3, characterized in that, After selecting the target marking area from the first candidate marking areas, the hot forging marking method further includes: Acquire thermal imaging data of the target marking area, obtain the temperature level of the target marking area based on the thermal imaging data, obtain the corresponding material parameters based on the temperature level, and send the forging identification information and the material parameters to the manual terminal to remind the staff to replace the corresponding marking mold.

9. A marking device for hot forgings, characterized in that, The hot forging marking device includes: The acquisition module is used to acquire the forging identification information, first three-dimensional model data and scanned point cloud data of the actual forging; The registration module is used to spatially register the first three-dimensional model data and the point cloud data to obtain the second three-dimensional model data of the actual forging in a preset spatial coordinate system; The positioning module is used to obtain a first candidate marking area based on the second three-dimensional model data and the forging identification information, and to filter the first candidate marking area to obtain the target marking area.

10. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the hot forging marking method according to any one of claims 3-8.

Images