Dimension measuring method for cleaning side plate of tire mold

Abstract

The invention provides a size measurement method for cleaning a side plate of a tire mold, and the method comprises the steps: obtaining a point cloud picture through a structured light camera and a mechanical arm; utilizing a point cloud clustering and outer contour point extraction algorithm to determine section point cloud of the side plate from the point cloud picture; the tangent plane of the side plate is a plane formed by intersecting a cutting plane which is perpendicular to the bottom plate where the side plate is located and passes through the circle center of the side plate and the side plate; and fitting by using the tangent plane point cloud to obtain an inflection point of the tangent plane so as to complete size measurement. The invention further provides a size measuring device and equipment for tire mold side plate cleaning and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the fields of laser cleaning and computer vision, and more particularly to a method for dimension measurement for cleaning the side plates of a tire mold. Background Art

[0002] A tire mold is a circular mold with the shape of a tire used to manufacture tires. The tire mold is composed of different components. Generally, it is composed of tread blocks and side plates. The tread block refers to the component with treads on the outer cylindrical surface, and the side plate refers to the side baffle. Generally, a tire mold is composed of 6 - 8 tread blocks and 1 side plate. When the tire mold needs to be cleaned, the worker will disassemble the tire mold and place it on a platform, and then use various methods to clean the tire mold. This process is called offline tire mold cleaning. Automating the offline tire mold cleaning process and reducing the participation of the manual process can not only standardize the operation, reduce the losses caused by misoperation, but also protect workers from working in a dangerous working environment. Summary of the Invention

[0003] In view of the above problems, the present disclosure provides a method for dimension measurement for cleaning the side plates of a tire mold for automated cleaning.

[0004] The present disclosure provides a method for dimension measurement for cleaning the side plates of a tire mold, including: obtaining a point cloud map by using a structured light camera and a robotic arm; determining the cross-sectional point cloud of the side plate from the point cloud map by using a point cloud clustering and outer contour point extraction algorithm; wherein, the cross-section of the side plate is the surface obtained by the intersection of a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate with the side plate; fitting the inflection points of the cross-section by using the cross-sectional point cloud to complete the dimension measurement.

[0005] According to an embodiment of the present disclosure, determining the cross-sectional point cloud of the side plate from the point cloud map by using a point cloud clustering and outer contour point extraction algorithm includes: extracting the side plate point cloud from the point cloud map by point cloud clustering; obtaining the outer contour points of the side plate point cloud by using the outer contour point extraction algorithm; and cutting the side plate point cloud by using the outer contour points to obtain the cross-sectional point cloud of the side plate.

[0006] According to an embodiment of the present disclosure, obtaining the outer contour points of the side plate point cloud by using the outer contour point extraction algorithm includes: for each point in the side plate point cloud, fitting an over-plane by using the points within a preset range from the point; taking the normal vector of the over-plane as the normal vector of the point; removing the points whose included angle between the normal vector and the vertically upward direction is greater than a preset angle; generating a tangent plane perpendicular to the bottom plate where the side plate is located, and translating the tangent plane twice to obtain the tangent points where the tangent plane intersects with both ends of the side plate point cloud respectively.

[0007] According to an embodiment of the present disclosure, using the outer contour points, the side plate point cloud is cut to obtain the section point cloud of the side plate, including: using the outer contour points to generate a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate; extracting the points within a preset distance from the cutting plane as the section point cloud.

[0008] According to an embodiment of the present disclosure, the side plate point cloud is extracted from the point cloud map through point cloud clustering, including: segmenting the point cloud map through point cloud clustering to obtain a plurality of point cloud clusters; using the point cloud cluster with the highest height in the vertical direction as the reference point cloud, and segmenting the reference point cloud according to the preset highest point and lowest point to obtain the side plate point cloud; wherein, the point cloud between the highest point and the lowest point is the side plate point cloud; the point cloud below the lowest point is the bottom plate point cloud.

[0009] According to an embodiment of the present disclosure, using the section point cloud, the inflection points of the section are fitted to complete dimension measurement, including: using the outer contour points obtained by the outer contour point extraction algorithm to determine the outer diameter and the center point of the side plate; extracting the points within a preset range from the highest point in the section point cloud as the inner diameter point cloud of the ring; determining the inner diameter and the outer diameter of the ring according to the shortest distance and the farthest distance between the inner diameter point cloud of the ring and the center point; using the section point cloud to fit the section; using the dynamic programming algorithm to determine the prominent points of the section according to the difference between each point and its adjacent points to determine the inflection points.

[0010] According to an embodiment of the present disclosure, the method further includes: using the measured dimensions to obtain the cleaning trajectory of the side plate, specifically including: storing the coordinates of one of the inflection points at both ends as the coordinates of the starting point into the trajectory sequence; sequentially storing the inflection point coordinates into the trajectory sequence according to the distance from the starting point; rotating the laser cleaning device around the center point of the side plate at the starting point for one week; moving the laser cleaning device along the trajectory sequence by a preset distance and then rotating around the center point for one week; repeating the operation of moving the laser cleaning device along the trajectory sequence by a preset distance and then rotating around the center point for one week until the laser cleaning device moves to the end point of the trajectory sequence.

[0011] The second aspect of the present disclosure provides a dimension measurement device for cleaning the side plate of a tire mold. The device can be used to implement the above method. The device includes: a point cloud acquisition module for obtaining a point cloud map by using a structured light camera and a robotic arm; a point cloud extraction module for determining the section point cloud of the side plate from the point cloud map by using point cloud clustering and the outer contour point extraction algorithm; wherein, the section of the side plate is the surface obtained by the intersection of the plane perpendicular to the bottom plate where the side plate is located and the side plate; an inflection point determination module for using the section point cloud to fit the inflection points of the section to complete dimension measurement.

[0012] A third aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the above-described dimensional measurement method for cleaning the side plates of a tire mold.

[0013] A fourth aspect of the present disclosure further provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the above-described dimensional measurement method for cleaning the side plates of a tire mold.

[0014] According to the dimensional measurement method for cleaning the side plates of a tire mold provided by the present disclosure, point cloud information is automatically collected by a camera and a robotic arm; sectional point clouds are extracted by point cloud clustering and outer contour point extraction. Since the sectional plane is used to characterize the structural features of the side plate according to the geometric characteristics of the side plate, at least partially, the technical problem of manual participation required for side plate cleaning is solved, and the technical effect of improving the automation degree of side plate cleaning is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematically shows a flowchart of a dimensional measurement method for cleaning the side plates of a tire mold according to an embodiment of the present disclosure;

[0016] Figure 2 Schematically shows a schematic diagram of a side plate of a tire mold according to an embodiment of the present disclosure;

[0017] Figure 3 Schematically shows a schematic diagram of a side plate cross-section and key points extracted by a point cloud processing algorithm according to an embodiment of the present disclosure;

[0018] Figure 4 Schematically shows outer contour points collected by an outer contour point collection algorithm and the sectional plane direction of a side plate according to an embodiment of the present disclosure;

[0019] Figure 5 Schematically shows a schematic diagram of generating a laser cleaning trajectory according to an embodiment of the present disclosure;

[0020] Figure 6 Schematically shows a detailed flowchart according to an embodiment of the present disclosure;

[0021] Figure 7 Schematically shows a structural block diagram of a dimensional measurement device for cleaning the side plates of a tire mold according to an embodiment of the present disclosure;

[0022] Figure 8 Schematically shows a block diagram of an electronic device suitable for implementing a dimensional measurement method for cleaning the side plates of a tire mold according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, numerous specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0024] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] In the case of using expressions such as "at least one of A, B, and C, etc.", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0027] The present disclosure provides a computer vision-based automatic dimension measurement method for cleaning the side plates of a tire mold. The dimension information of the side plates of the tire mold can be automatically calculated through computer vision, thereby calculating the laser cleaning trajectory to guide the robot to perform trajectory cleaning on the side plates of the tire mold.

[0028] Figure 1 A flowchart of a dimension measurement method for cleaning the side plates of a tire mold according to an embodiment of the present disclosure is schematically shown, as Figure 1 shown, embodiments of the present disclosure provide a dimension measurement method for cleaning the side plates of a tire mold, including: using a structured light camera and a robotic arm to obtain a point cloud map; using a point cloud clustering and outer contour point extraction algorithm to determine the cross-sectional point cloud of the side plate from the point cloud map; wherein, the cross-section of the side plate is a plane obtained by intersecting the side plate with a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate; using the cross-sectional point cloud to fit the inflection points of the cross-section for completing dimension measurement.

[0029] In this embodiment, an automated tire mold cleaning device generally consists of a six-degree-of-freedom robot, a laser cleaning head, and a structured light camera. The laser cleaning head is carried by the end effector of the robot. The structured light camera is usually fixed on the robotic arm at the end of the robot and is on the same straight line as the laser cleaning head. The general workflow for obtaining a point cloud map is to use the robot to carry the structured light camera to photograph the side plate from top to bottom at 8 fixed positions, obtaining a set of point clouds and the poses of the robot. Transform the point cloud data to the robot coordinate system according to the robot pose, and then splice the point clouds into a complete point cloud map.

[0030] Figure 6 Schematically shows a detailed flowchart according to an embodiment of the present disclosure. For the method of automatically measuring the dimensions of a tire mold side plate, it is necessary to use a robot to carry a structured light camera to collect point cloud information of the tire mold side plate at different positions above the platform. The field of view of the structured light camera completely covers the tire mold side plate. Secondly, process the collected point cloud information based on computer vision. Through a clustering method, separate the tire mold side plate and the bottom plate, and extract non-repeating points on the outer edge of the side plate through an algorithm for collecting outer contour points. Fit a circle with these points to obtain the normal vector of the center of the circle. Use the center of the circle as the center of the side plate and the normal vector of the circle as the normal vector of the side plate. Then, take the direction of the binormal vector of the circle as the reference direction, and extract the point cloud of the side plate in this direction as the sectional point cloud of the side plate. Filter out the redundant points through a filtering method to make the sectional point cloud of the side plate evenly distributed. And rotate the sectional point cloud of the side plate to the xoz plane. Use the DP algorithm (Dynamic Programming) to fit the sectional point cloud of the side plate with a polyline. And use the obtained points as the key points of the side plate. Generate a circular trajectory using the midpoint of the two key points of the extracted side plate, the center of the side plate, and the normal vector of the side plate to guide the robot to perform side plate cleaning.

[0031] Figure 2 Schematically shows a schematic diagram of a tire mold side plate according to an embodiment of the present disclosure; an offline tire mold side plate, as Figure 2 shown. It consists of several toroids with different radii and heights. Its cross-sectional view is as Figure 3 shown. The side plate can be simply regarded as a revolving body formed by rotating the cross-section shown in Figure 3 around the central axis of the side plate by 380 degrees. When using a laser to clean the tire mold side plate, usually only the upper surface is cleaned. Therefore, the positions of the cleaning key points on the upper surface of the side plate can be obtained through the side plate point cloud. Then, through the positions of the cleaning feature points and the central axis of the side plate, a circular cleaning trajectory can be obtained. Then use the robot to carry the laser head to clean the side plate according to the generated cleaning trajectory.

[0032] Through the embodiments of the present disclosure, an automated solution based on computer vision is provided. A robot is carried with a camera to photograph the offline tire mold on the entire working platform, and the corresponding point cloud information is obtained. By processing the point cloud of the offline tire mold, the size and position information of the section plane constituting the side plate of the offline tire mold are obtained. Through this information, the corresponding trajectory is generated. It realizes guiding the robot to carry a laser or plasma cleaning device to clean the offline tire mold, achieving automation.

[0033] Based on the above embodiments, using the point cloud clustering and outer contour point extraction algorithm, the section plane point cloud of the side plate is determined from the point cloud map, including: extracting the side plate point cloud from the point cloud map through point cloud clustering; using the outer contour point extraction algorithm to obtain the outer contour points of the side plate point cloud; using the outer contour points to cut the side plate point cloud to obtain the section plane point cloud of the side plate.

[0034] In this embodiment, the optional clustering algorithms include K-means, DBSCAN, Hierarchical Clustering, etc.

[0035] Through the embodiments of the present disclosure, point cloud clustering can effectively identify and segment each part of the obtained point cloud map, while the outer contour point extraction algorithm can determine the diameter direction of the side plate, ensure obtaining an accurate section plane direction, and thus improve the measurement accuracy.

[0036] Based on the above embodiments, using the outer contour point extraction algorithm to obtain the outer contour points of the side plate point cloud, including: for each point in the side plate point cloud, using the points within a preset range from this point to fit an over-plane; taking the normal vector of the over-plane as the normal vector of the point; removing the points whose included angle between the normal vector and the vertically upward direction is greater than the preset angle; generating a tangent plane perpendicular to the bottom plate where the side plate is located, and translating the tangent plane twice to respectively obtain the tangent points where the tangent plane intersects the two ends of the side plate point cloud.

[0037] In this embodiment, a series of planes with normal vectors perpendicular to the z-axis but different included angles with the x-axis can be generated. Execute multiple times to generate a tangent plane perpendicular to the bottom plate where the side plate is located, translate the tangent plane twice to respectively obtain the tangent points where the tangent plane intersects the two ends of the side plate point cloud, and then remove the repeated points; obtain a more accurate fitting circle based on the multiple tangent points obtained from multiple executions, and obtain the center of the circle, the outer radius of the ring, and the normal vector of the circle. Take the center of the circle as the center of the side plate, and the normal vector of the circle as the normal vector of the side plate. Then, take the direction of the normal vector of the circle as the reference direction, and extract the point cloud of the side plate in this direction as the section plane point cloud of the side plate. Figure 4 Shown are the collected outer edge contour points of the side plate.

[0038] In this embodiment, removing the points whose included angle between the normal vector and the vertically upward direction is greater than a preset angle specifically includes: calculating the normal vectors of all points in the side plate point cloud, and removing the points whose included angle between the normal vector and the z-axis direction is greater than 45 degrees.

[0039] Through the embodiments of the present disclosure, by removing the points whose included angle between the normal vector and the vertically upward direction is greater than a preset angle, the point cloud of the facade is removed to better fit the plane for screening data; through the tangent plane, the outer contour points of the side plate are obtained to support the measurement of the external ring size and provide support for generating the cutting plane.

[0040] Based on the above embodiment, using the outer contour points to cut the side plate point cloud to obtain the sectional point cloud of the side plate includes: using the outer contour points to generate a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate; extracting the points within a preset distance from the cutting plane as the sectional point cloud.

[0041] Figure 4 Schematically shows the outer contour points collected by the outer contour point algorithm according to the embodiments of the present disclosure and the sectional direction of the side plate. As Figure 4 shown, select a certain point among the above-mentioned outer contour points of the side plate as the sectional direction, calculate the plane formed by this direction and the z-axis direction as the cutting plane. Extract the point cloud within a certain threshold from this cutting plane in the side plate point cloud as the sectional point cloud of the side plate. Calculate the point with the largest z value in the sectional point cloud of the side plate, and extract the points within a certain threshold from this z value in the sectional point cloud of the side plate as the inner diameter point cloud of the ring. Determine the inner diameter and outer diameter of the ring according to the points closest to and farthest from the center of the side plate in the inner diameter point cloud of the ring. Divide this section according to the inner edge radius of the ring to obtain the outer sectional point cloud and the inner sectional point cloud. Rotate the outer sectional point cloud to the xoz plane. Sort the point cloud in ascending order along the x-axis direction. Then use the DP algorithm to determine the prominent points in the section. Take these points as the cleaning key points.

[0042] Through the embodiments of the present disclosure, a cutting plane perpendicular to the bottom plate is generated according to the outer contour points, and the point cloud data near the cutting plane is extracted as the sectional point cloud, ensuring that the subsequent dimensional measurement is geometrically accurate and meets the actual requirements.

[0043] Based on the above embodiment, through point cloud clustering, the side plate point cloud is extracted from the point cloud map, including: segmenting the point cloud map through point cloud clustering to obtain multiple point cloud clusters; taking the point cloud cluster with the highest height in the vertical direction as the reference point cloud, and segmenting the reference point cloud according to the preset highest point and lowest point to obtain the side plate point cloud; wherein, the point cloud between the highest point and the lowest point is the side plate point cloud; the point cloud below the lowest point is the bottom plate point cloud.

[0044] In this embodiment, the processing flow of the point cloud map of the tire mold optionally includes: First, the side plate and the bottom plate of the tire mold are segmented by a point cloud clustering method. First, the side plate and the bottom plate of the tire mold are segmented by a point cloud clustering method. Usually, the side plate of the tire mold is placed on the bottom plate. It is necessary to calculate the bounding rectangle of the overall point cloud. The central axis and radius of the segmentation cylinder are calculated through the central axis (usually the z-axis) and the center point of the bounding rectangle. Usually, the radius is set to half of the radius of the bounding rectangle. The point cloud inside the segmentation cylinder is extracted. The minimum z value of these point clouds is obtained. The point cloud of the side plate near a certain threshold of the above z value is taken, and these point clouds are the point cloud of the bottom plate. The point cloud of the bottom plate can be fitted into a plane by the Ransac method. The bottom plate plane and the normal vector are obtained. The overall point cloud is rotated to the positive direction through the bottom plate plane and the normal vector so that the z-axis direction is (0, 0, 1). Then, the side plate point cloud is obtained by threshold segmentation of the overall point cloud according to the center point of the bottom plate.

[0045] In this embodiment, the processing flow of the point cloud map of the tire mold optionally includes: First, the side plate and the bottom plate of the tire mold are segmented by a point cloud clustering method. Usually, the side plate of the tire mold is placed on the bottom plate. Usually, the point cloud with the highest height in the clustered point cloud is found as the reference point cloud. The highest point and the lowest point of the reference point cloud are taken, then the point cloud above the lowest point is identified as the side plate point cloud, and the point cloud below the lowest point is identified as the bottom plate point cloud.

[0046] Through the embodiments of the present disclosure, by clustering and segmenting the point cloud map, the point clouds of the side plate and the bottom plate are identified, and the point cloud of the side plate is further extracted for processing. Confusion is avoided and it is ensured that the measurement data of the side plate only comes from valid point cloud data.

[0047] On the basis of the above embodiments, using the section point cloud, fitting the inflection points of the section for completing dimension measurement includes: determining the outer diameter and the center point of the side plate by using the outer contour points obtained by the outer contour point extraction algorithm; extracting the points within a preset range from the highest point in the section point cloud as the inner diameter point cloud of the ring; determining the inner diameter and the outer diameter of the ring according to the shortest distance and the farthest distance between the inner diameter point cloud of the ring and the center point; fitting the section by using the section point cloud; using the dynamic programming algorithm to determine the points protruding from the section according to the difference between each point and its adjacent points for determining the inflection points.

[0048] Figure 3Schematically shown is a schematic cross-sectional view of a side plate according to an embodiment of the present disclosure and key points extracted by a point cloud processing algorithm. The process of obtaining key points from point cloud data includes the following steps: (1) dividing the overall point cloud into a side plate point cloud and a bottom plate point cloud by a clustering algorithm; (2) adjusting the direction of the side plate point cloud according to the bottom plate point cloud; (3) removing the elevation point cloud according to the normal vector of the point cloud to obtain a plane point cloud; (4) clustering the plane point cloud using a point cloud clustering algorithm; (5) sorting in the z-axis direction to obtain the outermost ring point cloud of the top layer; (6) extracting the outer contour points of the side plate point cloud ring by an outer contour point extraction algorithm, and fitting a circle to obtain the center and normal vector of the side plate; (7) determining a tangent plane with a point in the outer contour points as the direction, and extracting the side plate section point cloud; (8) rotating the side plate section point cloud to the xoz plane; (9) using the DP algorithm to fit the side plate section with a polyline and record the key points therein.

[0049] In this embodiment, the cleaning range of the side plate is uncertain. It must be cleaned from the upper ring surface to the outside, but the inside of the upper ring surface may not need to be cleaned. Therefore, the radius dimension needs to be clarified to adaptively plan the cleaning trajectory. The number of actual cleaning trajectories will also be adjusted according to the laser line width. Sometimes the inflection points obtained by the DP algorithm do not meet the requirements and need to be manually modified.

[0050] It should be noted that the DP algorithm, in point cloud data processing, usually refers to the Dynamic Programming algorithm. Dynamic programming is an algorithmic idea that decomposes complex problems into smaller sub-problems and avoids repeated calculations by recording the solutions of sub-problems. It is widely used in many problems, such as the shortest path, knapsack problem, etc. In the detection of cleaning key points, the DP algorithm is usually used for curve fitting, feature point recognition, and outlier detection. For example, extracting feature points from slice data. Specifically includes: Point cloud slicing: Cutting the point cloud data according to a certain plane, usually by layering according to the Z-axis or a certain fixed direction. Each layer of slice contains a part of the point cloud data. Sorting: Sorting the points in the slice according to a certain feature (for example, the X-axis coordinate or distance), which can facilitate dynamic programming analysis. Dynamic programming detects prominent points: Using the dynamic programming algorithm to identify the "protruding" points in the sorted point cloud slices that are different from the distribution of surrounding points. Dynamic programming usually establishes a "state transition" equation to judge whether it is a prominent point according to the difference between each point and its neighboring points (such as distance, normal vector change, etc.). A common method is to judge the distance difference or curvature difference between adjacent points and the current point.

[0051] Through the embodiments of the present disclosure, by extracting the outer contour points, the outer diameter and the center point of the side plate are determined, and the inflection points of the section are determined through curvature analysis for accurate dimension measurement. The outer dimensions of the side plate and their changes are accurately calculated, and the key features (such as inflection points) in the section can be efficiently identified, which helps to plan the subsequent cleaning path.

[0052] Based on the above embodiments, the method further includes: obtaining the cleaning trajectory of the side plate by using the measured dimensions, specifically including: storing the coordinates of one of the inflection points at both ends as the coordinates of the starting point into the trajectory sequence; sequentially storing the inflection point coordinates into the trajectory sequence according to the distance from the starting point; rotating the laser cleaning device around the center point of the side plate at the starting point for one week; moving the laser cleaning device along the trajectory sequence by a preset distance and then rotating it around the center point for one week; repeating the operation of moving the laser cleaning device along the trajectory sequence by a preset distance and then rotating it around the center point until the laser cleaning device moves to the end point of the trajectory sequence.

[0053] Figure 5 Schematically shows a schematic diagram of generating a laser cleaning trajectory according to an embodiment of the present disclosure, and calculates the cleaning trajectory by using key points, the center of the side plate, and the normal vector of the side plate. The cleaning trajectory is a circle obtained by rotating the center points of two cleaning feature points around the central axis of the side plate for one circle. The cleaning direction of the cleaning trajectory points in the xoz plane is perpendicular to the direction of the two cleaning feature points. The cleaning direction of the cleaning trajectory points in other directions can be obtained by rotating the direction of the cleaning feature points in the xoz plane around the central axis of the side plate by the same angle as the cleaning trajectory points.

[0054] The process of calculating the trajectory information includes the following characteristics: (1) It is a circular trajectory calculated through the midpoint of two adjacent key points, the center of the side plate, and the normal vector of the side plate; (2) When the trajectory is in the xoz plane, its direction vector is perpendicular to the midpoint of the two key points and is in the xoz plane; (3) The direction in other planes is obtained by rotating the direction in the xoz plane by the corresponding angle around the z axis.

[0055] Through the embodiments of the present disclosure, a cleaning trajectory is generated according to the measured dimension information to guide the laser cleaning device to clean the side plate of the mold along a specific path. By automatically generating the cleaning trajectory, the cleaning efficiency of the laser cleaning device can be greatly improved, and the cleaning quality can be ensured.

[0056] Based on the above dimension measurement method for cleaning the side plate of a tire mold, the present disclosure also provides a dimension measurement device for cleaning the side plate of a tire mold. The following will be combined with Figure 7 Describe this device in detail.

[0057] Figure 7 Schematically shows a structural block diagram of a dimension measurement device for cleaning the side plate of a tire mold according to an embodiment of the present disclosure.

[0058] As Figure 7As shown, the dimensional measurement device for cleaning the side plate of a tire mold in this embodiment includes: a point cloud acquisition module for obtaining a point cloud map by using a structured light camera and a robotic arm; a point cloud extraction module for determining the cross-sectional point cloud of the side plate from the point cloud map by using a point cloud clustering and outer contour point extraction algorithm, where the cross-section of the side plate is the surface obtained by the intersection of a plane perpendicular to the bottom plate where the side plate is located and the side plate; and an inflection point determination module for fitting the inflection points of the cross-section by using the cross-sectional point cloud to complete dimensional measurement.

[0059] Figure 8 Schematically shows a block diagram of an electronic device suitable for implementing a dimensional measurement method for cleaning the side plate of a tire mold according to an embodiment of the present disclosure.

[0060] As Figure 8 shown, the electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage section 808 into the random access memory (RAM) 803. The processor 801 can include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application-specific integrated circuit (ASIC)), etc. The processor 801 can also include on-board memory for caching purposes. The processor 801 can include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0061] In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. The processor 801 executes various operations of the method flow according to an embodiment of the present disclosure by executing the programs in the ROM 802 and / or the RAM 803. It should be noted that the program can also be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 can also execute various operations of the method flow according to an embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0062] According to an embodiment of the present disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, and the input / output (I / O) interface 805 is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the I / O interface 805: an input portion 806 including a keyboard, a mouse, etc.; an output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. The drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed so that a computer program read therefrom is installed into the storage portion 808 as needed.

[0063] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0064] An embodiment of the present disclosure also includes a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to cause the computer system to implement the method provided by the embodiments of the present disclosure.

[0065] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiments of the present disclosure may be written in any combination of one or more programming languages. Specifically, these computing programs may be implemented using high-level procedures and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, programming languages such as Java, C++, python, the "C" language, or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0067] Those skilled in the art will appreciate that the features recited in the various embodiments and / or claims of the present disclosure may be combined or combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure may be combined and combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0068] The above describes the embodiments of the present disclosure. However, these embodiments are merely for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. A method for measuring the dimensions of a side plate of a tire mold for cleaning, characterized in that, Including: Using a structured light camera and a robotic arm to obtain a point cloud map; Using a point cloud clustering and outer contour point extraction algorithm to determine the sectional point cloud of the side plate from the point cloud map; wherein, the section of the side plate is the surface obtained by the intersection of a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate with the side plate; Using the sectional point cloud to fit the inflection points of the section for completing dimension measurement.

2. The method according to claim 1, wherein, Using a point cloud clustering and outer contour point extraction algorithm to determine the sectional point cloud of the side plate from the point cloud map, including: Extracting the side plate point cloud from the point cloud map through point cloud clustering; Using an outer contour point extraction algorithm to obtain the outer contour points of the side plate point cloud; Using the outer contour points to cut the side plate point cloud to obtain the sectional point cloud of the side plate.

3. The method according to claim 2, wherein Using an outer contour point extraction algorithm to obtain the outer contour points of the side plate point cloud, including: For each point in the side plate point cloud, using the points within a preset range from this point to fit an over-plane; taking the normal vector of the over-plane as the normal vector of the point; Removing the points whose included angle between the normal vector and the vertically upward direction is greater than a preset angle; Generating a tangent plane perpendicular to the bottom plate where the side plate is located, and translating the tangent plane twice to respectively obtain the tangent points where the tangent plane intersects with both ends of the side plate point cloud.

4. The method according to claim 2, wherein Using the outer contour points to cut the side plate point cloud to obtain the sectional point cloud of the side plate, including: Using the outer contour points to generate a cutting plane perpendicular to the bottom plate where the side plate is located and passing through the center of the side plate; Extracting the points within a preset distance from the cutting plane as the sectional point cloud.

5. The method according to claim 2, wherein Extracting the side plate point cloud from the point cloud map through point cloud clustering, including: Segmenting the point cloud map through point cloud clustering to obtain multiple point cloud clusters; Taking the point cloud cluster with the highest height in the vertical direction as the reference point cloud, and segmenting the reference point cloud according to a preset highest point and lowest point to obtain the side plate point cloud; wherein, the point cloud between the highest point and the lowest point is the side plate point cloud; the point cloud below the lowest point is the bottom plate point cloud.

6. The method according to claim 1, wherein The step of using the sectional point cloud to fit the inflection points of the section for completing dimension measurement includes: Using the outer contour points obtained by the outer contour point extraction algorithm to determine the outer diameter and the center point of the outer ring of the side plate; extracting the points within a preset range from the highest point in the sectional point cloud as the inner ring diameter point cloud; determining the inner diameter and the outer diameter of the ring according to the shortest distance and the farthest distance between the inner ring diameter point cloud and the center point; Using the sectional point cloud to fit the section; Using a dynamic programming algorithm to determine the prominent points of the section according to the difference between each point and its adjacent points for determining the inflection points.

7. The method according to claim 1, wherein The method further includes: Using the measured dimensions to obtain the cleaning trajectory of the side plate, specifically including: Storing the coordinates of one of the inflection points at both ends as the coordinates of the starting point into the trajectory sequence; Sequentially storing the inflection point coordinates into the trajectory sequence according to the distance from the starting point; Moving the laser cleaning device around the center point of the side plate at the starting point for one week; moving the laser cleaning device along the trajectory sequence for a preset distance and then around the center point for one week; Repeatedly executing moving the laser cleaning device along the trajectory sequence for a preset distance and then around the center point for one week until the laser cleaning device moves to the end point of the trajectory sequence.

8. A dimensional measurement device for cleaning the side plate of a tire mold, characterized in that, The device can be used to implement the method described in any one of claims 1 to 7. The device includes: A point cloud acquisition module, configured to obtain a point cloud map by using a structured light camera and a robotic arm; A point cloud extraction module, configured to determine the sectional point cloud of the side plate from the point cloud map by using a point cloud clustering and outer contour point extraction algorithm; wherein, the section of the side plate is a plane obtained by intersecting the plane perpendicular to the bottom plate where the side plate is located with the side plate; An inflection point determination module, configured to fit the inflection points of the section by using the sectional point cloud for completing dimension measurement.

9. An electronic device, comprising: One or more processors; A storage device, configured to store one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the method described in any one of claims 1 to 7.

Images