Robot automatic polishing method, robot equipment, computer equipment and medium

Abstract

The present invention discloses a robot automatic grinding method, which performs the following steps through a computer device: S1. Point cloud acquisition: moving the robot to a preset position, and using a three-dimensional point cloud camera to shoot and acquire a point cloud; S2. Acquiring a grinding and polishing path: selecting an area of ​​interest on the acquired point cloud, setting a nearest neighbor search radius r, and acquiring multiple groups of path points based on self-selected points in the area of ​​interest to obtain a processable path; S3. Estimate the position of the path points based on the multiple groups of path points in the processable path; S4. Implementing robot grinding: importing the above-obtained path into the robot device to complete the corresponding grinding and repair. The present invention combines a variety of point cloud acquisition technologies and preprocessing algorithms, and with the help of the geometric characteristics of aircraft engine sealing parts, can more accurately and stably estimate the contact posture of the sanding machine and the path points, thereby effectively solving the problems of over-grinding and over-cutting in the process of sealing parts repair.

Description

Technical Field

[0001] The present invention relates to the technical field of grinding processing, and in particular to a robot automatic grinding method for a sealing part of an aviation engine, a robot device, a computer device and a storage medium. Background Art

[0002] As the heart of modern aircraft, the performance of aircraft engines directly affects the overall efficiency and safety of the aircraft. Aircraft engine seals are key components used to improve engine efficiency and performance. Seals are mainly used to limit or reduce gas leakage and ensure that airflow flows in specific channels, thereby maximizing combustion efficiency and overall engine performance. Such components are usually installed around turbines, compressors or other rotating parts to optimize engine performance by reducing gas leakage from high-pressure areas to low-pressure areas. In order to adapt to the extreme working environment inside aircraft engines, such as high temperature, high pressure and high-speed rotation conditions, these components must have high temperature resistance and wear resistance to cope with extreme working environments. Therefore, seals are usually made of high temperature and wear-resistant materials.

[0003] Currently, in the aviation industry, the production, manufacturing, and maintenance of sealing parts are mainly completed through traditional manual polishing. This process involves using tools such as sandpaper and abrasive paste to finely process the surface of the part until the required dimensional accuracy and smoothness are achieved. It is highly dependent on the operator's experience and technical level. In addition, to ensure that each sealing part meets strict quality standards, the entire polishing process is often time-consuming and requires frequent inspection and adjustment.

[0004] However, this manual operation-based method has many limitations: first, since it relies entirely on manpower, the production efficiency is relatively low and requires high manpower and time costs; second, long-term engagement in such high-intensity repetitive labor can easily cause harm to the physical health of practitioners; finally, human factors can easily introduce errors, affecting the quality and consistency of the final product.

[0005] To this end, this application specifically proposes a robot automatic polishing method to solve the above technical problems. Summary of the Invention

[0006] The main purpose of the present invention is to provide a robot automatic polishing method and robot equipment to solve the technical problems raised in the background technology.

[0007] The present invention adopts the following technical solutions to solve the above technical problems:

[0008] A robot automatic polishing method, which performs the following steps by computer equipment:

[0009] S1. Point cloud acquisition: Move the robot to the preset position and use the 3D point cloud camera to capture the point cloud.

[0010] S2. Obtaining the polishing path: Selecting a region of interest on the acquired point cloud, setting the nearest neighbor search radius r, and obtaining multiple sets of path points based on self-selected points in the region of interest to obtain a machinable path;

[0011] S3. estimating the pose of the path points based on the multiple groups of path points of the processable path;

[0012] S4. Implement robotic polishing: Import the above-obtained path into the robotic device to complete the corresponding polishing and repair.

[0013] Preferably, the specific operation steps of using a three-dimensional point cloud camera to obtain a point cloud in step S1 include: presetting the homogeneous coordinates of the point in the point cloud to be p1=(x1, y1, z1, 1), then each point p in the neighborhood P i The coordinates of (x i ,y i ,z i ,i),According to the hand-eye calibration matrix M, obtain the coordinates p of the point cloud in the world coordinate system w

[0014] p w =Mp

[0015] in R is the basic rotation matrix of the camera pose, l is the basic translation matrix of the camera, and p is the point in the neighborhood P.

[0016] Preferably, the specific operation steps of obtaining the path points in step S2 include:

[0017] S21. Select a point in the selected region of interest, perform a nearest neighbor search with a radius of r, and calculate the centroid of the search result as the first path point: where x i ,y i , z i is the coordinate of the i-th point in the neighborhood.

[0018] S22. Exclude the search neighborhood in step S21 from the region of interest to avoid duplication;

[0019] S23. Repeat the above steps S21 and S22 until the region of interest is empty;

[0020] S24. Use the minimum spanning tree algorithm to sort the path points to obtain the optimal processable path of the robot.

[0021] Preferably, the specific operation steps of estimating the position and posture of the path point in step S3 include:

[0022] S31. Use the gradient descent method to perform tangential estimation of the path point pose to improve the smoothness of the polishing path. The specific steps include:

[0023] The preset tangent vector t to be calculated is (t x ,t y ,t z ), the normal vector set corresponding to the neighborhood P of point p1 is N, where N=(n p |p∈P);

[0024] The optimization objective function is set as:

[0025]

[0026] Where n is the number of normal vectors in the set N;

[0027] Preset the learning rate and starting position, use the gradient descent algorithm to get the tangent t, and normalize t:

[0028]

[0029] S32. Get the normal vector and approach vector of the path point tool coordinates

[0030] Based on the tangent vector t=(t x ,t y ,t z ), determine a plane passing through point p1 = (x1, y1, z1);

[0031] Project the normal vector set N onto the plane to obtain the normal vector projection set N′ and normalize the vectors in N′ to ensure that the normal vectors are perpendicular to T;

[0032] Based on the high sampling rate of point cloud data, the vectors in N′ are uniformly distributed, so the average value N of the vectors in N′ is calculated. t , and then normalize, where:

[0033] Approach vector O by N t Cross-product T gives:

[0034] A robotic device is used to perform any of the above-mentioned robotic automatic grinding methods to achieve sealing part grinding. The device body includes a six-axis robot, a rigid grinding and polishing belt machine, a flexible grinding and polishing belt machine, an industrial camera and an electric spindle, and the industrial camera is installed on the electric spindle.

[0035] In another aspect, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0036] On the other hand, the present invention further discloses a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0037] As can be seen from the above technical solution, the present invention provides a robot automatic polishing method. Compared with the prior art, the present invention has the following advantages:

[0038] 1. To address the lack of an automatic polishing solution for aviation turbine engine seals, the present invention utilizes a point cloud normal estimation algorithm to obtain the normal vector of a point cloud. According to the geometric features of aviation turbine engine seals, a polishing posture estimation method based on normal vectors and geometric features is proposed, thereby estimating the robot's polishing posture, effectively avoiding over-grinding and over-cutting during the polishing process of aviation turbine engine seals, and improving the polishing accuracy and surface quality.

[0039] 2. The present invention combines a variety of point cloud acquisition technologies and preprocessing algorithms, and with the help of the geometric characteristics of aircraft engine sealing parts, can more accurately and stably estimate the contact posture between the sanding machine and the path points, thereby effectively solving the problems of over-grinding and over-cutting during the sealing parts repair process.

[0040] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. Of course, it is not necessary to achieve all of the above-mentioned advantages simultaneously in order to implement any product of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 Schematic diagram of the overall process of the method of the present invention;

[0043] Figure 2 This is a schematic diagram of the tool posture effect at the path point of the present invention;

[0044] Figure 3 A schematic diagram of the three-dimensional structure of the grinding and polishing system of the robot device of the present invention;

[0045] That Figure 3 middle:

[0046] 1. Six-axis robot; 2. Rigid abrasive belt grinding and polishing machine; 3. Flexible abrasive belt grinding and polishing machine; 4. Industrial camera; 5. Electric spindle. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0048] In the embodiment, see Figures 1 to 3 .

[0049] like Figure 1 As shown. In response to the lack of an automatic polishing solution for aviation turbine engine seals, the embodiment of the present invention proposes a robotic automatic polishing method for aviation engine seals based on point clouds. The method uses a computer device to perform the following steps:

[0050] S1. Point cloud acquisition: Move the robot to a preset suitable position and use a 3D point cloud camera to capture the point cloud. The specific steps of using a 3D point cloud camera to capture the point cloud include: the homogeneous coordinates of the preset point cloud midpoint are p1 = (x1, y1, z1, 1), then each point p in the neighborhood P is i The coordinates of (x i ,y i ,z i ,i),According to the hand-eye calibration matrix M, obtain the coordinates p of the point cloud in the world coordinate system w

[0051] p w =M

[0052] in R is the basic rotation matrix of the camera pose, l is the basic translation matrix of the camera, and p is the point in the neighborhood P;

[0053] S2. Obtaining the polishing path: Select an area of ​​interest on the acquired point cloud, set the nearest neighbor search radius r, and obtain multiple sets of path points based on the points selected in the area of ​​interest to obtain a machinable path. The specific steps for obtaining the path points include:

[0054] S21. Select a point in the selected region of interest, perform a nearest neighbor search with a radius of r, and calculate the centroid of the search result as the first path point: where x i ,yi , z i is the coordinate of the i-th point in the neighborhood.

[0055] S22. Exclude the search neighborhood in step S21 from the region of interest to avoid duplication;

[0056] S23. Repeat the above steps S21 and S22 until the region of interest is empty;

[0057] S24. Use the minimum spanning tree algorithm (MST) to sort the path points to obtain the optimal processable path of the robot;

[0058] S3. Based on multiple groups of path points on the processable path, the pose of the path points is estimated. The tool pose effect on the path points is as follows: Figure 2 As shown in the figure, various postures are planned to fit the base of the sealing part well to prevent over-grinding and over-cutting. The specific steps for estimating the posture of the path point include:

[0059] S31. Use the gradient descent method to perform tangential estimation of the path point pose to improve the smoothness of the polishing path. The specific steps include:

[0060] The preset tangent vector t to be calculated is (t x ,t y ,t z ), the normal vector set corresponding to the neighborhood P of point p1 is N, where N=(n p |p∈P);

[0061] The optimization objective function is set as:

[0062]

[0063] Where n is the number of normal vectors in the set N;

[0064] Preset the learning rate and starting position, use the gradient descent algorithm to get the tangent t, and normalize t:

[0065]

[0066] S32. Get the normal vector and approach vector of the path point tool coordinates

[0067] Based on the tangent vector t=(t x ,t y ,t z ), determine a plane passing through point p1 = (x1, y1, z1);

[0068] Project the normal vector set N onto the plane to obtain the normal vector projection set N′ and normalize the vectors in N′ to ensure that the normal vectors are perpendicular to T;

[0069] Based on the high sampling rate of point cloud data, the vectors in N′ are uniformly distributed, so the average value N of the vectors in N′ is calculated. t , and then normalize, where:

[0070] Approach vector O by N t Cross-product T gives:

[0071] S4. Implement robotic polishing: Import the above-obtained path into the robotic device to complete the corresponding polishing and repair.

[0072] In summary, this method uses the point cloud normal estimation algorithm to obtain the normal vector of the point cloud. According to the geometric characteristics of the aviation turbine engine seals, a grinding posture estimation method based on the normal vector and geometric characteristics is proposed. The grinding posture of the robot is estimated with the help of the point cloud, which effectively avoids over-grinding and over-cutting in the grinding and polishing project of aviation turbine engine seals, and improves the grinding and polishing accuracy and surface quality.

[0073] On the other hand, the present invention also discloses a robot device for executing the above-mentioned robot automatic grinding method to realize the sealing part grinding operation, and the point cloud acquisition device and the robot grinding and polishing device loaded therein are highly versatile, specifically as follows Figure 3 As shown, the main body of the robot device includes a six-axis robot 1, a rigid grinding and polishing belt machine 2, a flexible grinding and polishing belt machine 3, an industrial camera 4 and an electric spindle 5. The industrial camera 4 is installed on the electric spindle 5, wherein:

[0074] The six-axis robot 1 is used to clamp the aero-engine sealing component and adjust the stable posture of the aero-engine sealing component;

[0075] The rigid grinding and polishing belt machine 2 and the flexible grinding and polishing belt machine 3 are used for grinding and repairing the sealing parts of the aircraft engine;

[0076] After the electric spindle 5 moves to the specified position, the industrial camera 4 can obtain multiple sets of image data of the partial area, thereby constructing image point cloud data, which can be used to execute steps S1-S3 of the robot automatic polishing method in the above embodiment.

[0077] Therefore, the proposed robotic grinding method and robotic equipment, when used in conjunction with each other, can combine multiple point cloud acquisition technologies and preprocessing algorithms, leveraging the geometric characteristics of aircraft engine seals to accurately and stably estimate the contact posture between the belt sander and the path points. This can effectively address over-grinding and overcutting issues during seal repair.

[0078] In another aspect, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0079] On the other hand, the present invention further discloses a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0080] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the robot automatic polishing methods in the above embodiments.

[0081] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above method.

[0082] The embodiment of the present application further provides an electronic device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus.

[0083] Memory for storing computer programs;

[0084] The processor is used to implement the above-mentioned robot automatic polishing method when executing the program stored in the memory.

[0085] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industrial Standard Architecture (EISA) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

[0086] The communication interface is used for communication between the above electronic device and other devices.

[0087] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Alternatively, the memory may be at least one storage device located away from the processor.

[0088] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0089] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0091] In addition, it should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0092] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or schemes in which A and B are satisfied at the same time. In addition, in the embodiments of the present invention, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

Claims

1. A robot automatic polishing method, characterized in that: Follow these steps on your computer: S1. Point cloud acquisition: Move the robot to the preset position and use the 3D point cloud camera to capture the point cloud. S2. Obtaining the polishing path: Selecting a region of interest on the acquired point cloud, setting the nearest neighbor search radius r, and obtaining multiple sets of path points based on self-selected points in the region of interest to obtain a machinable path; S3. estimating the pose of the path points based on the multiple groups of path points of the processable path; S4. Implementing robotic polishing: Import the above-obtained path into the robotic device to complete the corresponding polishing repair; The specific operation steps of using a three-dimensional point cloud camera to obtain a point cloud in step S1 include: presetting the homogeneous coordinates of the midpoint of the point cloud to be , then the neighborhood Points in The coordinates are , according to the hand-eye calibration matrix , get the point cloud coordinates Coordinates in the world coordinate system ,have: in, is the basic rotation matrix of the camera pose, is the basic translation matrix of the camera, Neighborhood points within; The specific operation steps for estimating the position and posture of the path point in step S3 include: S31. Use the gradient descent method to perform tangential estimation of the path point pose to improve the smoothness of the polishing path. The specific steps include: Preset the tangent vector to be calculated for ,point Neighborhood The corresponding normal vector set is ,in ; The optimization objective function is set as: in For collection The number of normal vectors in ; Preset the learning rate and starting position, and use the gradient descent algorithm to get the tangent , and will Unitization: S32. Get the normal vector and approach vector of the path point tool coordinates: Based on the tangent vector , determine a passing point plane; Set the normal vector Project onto the plane to get the set of normal vector projections and will The vectors in the normalization are normalized to ensure that the normal vector is consistent with perpendicular to each other; Based on the high sampling rate of point cloud data, preset The vectors are evenly distributed, so the calculation The mean of the vector , and then normalize, where: Depend on Cross product get: is the approach vector.

2. The robot automatic polishing method according to claim 1, characterized in that: The specific operation steps for obtaining the path points in step S2 include: S21. Select a point in the selected region of interest, perform a nearest neighbor search with a radius of r, and calculate the centroid of the search result as the first path point: in , , The first The coordinates of the points; S22. Exclude the search neighborhood in step S21 from the region of interest to avoid duplication; S23. Repeat the above steps S21 and S22 until the region of interest is empty; S24. Use the minimum spanning tree algorithm to sort the path points to obtain the optimal processable path of the robot.

3. A robotic device for performing the robotic automatic grinding method according to any one of claims 1 to 2 to grind sealing parts, characterized in that: The main body of the equipment comprises a six-axis robot (1), a rigid grinding and polishing belt machine (2), a flexible grinding and polishing belt machine (3), an industrial camera (4) and an electric spindle (5), wherein the industrial camera (4) is mounted on the electric spindle (5).

4. A computer-readable storage medium, characterized in that A computer program is stored, and when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 2.

5. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 2.

Images