Vision-guided smooth machining path generation method for variable curvature airfoil skin robot

Abstract

The present application belongs to the technical field of processing path planning, and specifically discloses a vision-guided variable curvature airfoil skin robot smooth processing path generation method, the method comprising: collecting three-dimensional point cloud data of the airfoil skin to be processed, preprocessing the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm; mapping the triangular mesh surface point set into a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set, and then obtaining the boundary points of the plane point set in the plane space according to the local neighborhood characteristics of the boundary points, and inversely mapping the boundary points in the plane point set into the surface point set to obtain the airfoil skin boundary contour points; fitting the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtaining processing path points based on the B-spline curve.

Description

Technical Field

[0001] The present application belongs to the technical field of processing path planning, and more specifically, relates to a method for generating a smooth processing path for a variable curvature wing skin robot guided by vision. Background Art

[0002] Airfoil skins are primarily formed using methods such as drawing and milling, and then riveted to the aircraft frame in sections. Because various errors can occur during the manufacturing and assembly process, a machining allowance is typically reserved during the rough skin processing stage, allowing for trimming between adjacent skins during assembly. Currently, a common practice is to remove machining allowances at the assembly location through repeated visual comparisons and manual trimming by skilled workers to ensure that the clearance between adjacent skins meets design requirements. However, this method requires high worker proficiency, is subject to high randomness, is inefficient, and struggles to ensure consistency.

[0003] Compared to traditional CNC machine tools, industrial robots offer a wide machining range, high flexibility, and excellent dexterity, making them ideal for automated trimming of airfoil skins. However, due to the thin walls and weak rigidity of airfoil skins, and the significant deformation after clamping and positioning, machining paths cannot be planned directly using design models. Instead, robotic machining paths can only be generated using on-site measurement points from vision sensors. Existing methods for generating machining paths using measurement points are mostly limited to flat parts with small curvatures. They are unable to directly generate robotic machining paths for airfoil skins or suffer from problems such as low machining path accuracy. Summary of the Invention

[0004] In response to the defects of the prior art, the purpose of this application is to provide a vision-guided method for generating a smooth processing path for a variable-curvature airfoil skin robot, aiming to solve the problem that most of the robot processing path methods in the prior art are only used for planar parts with small curvature, resulting in low accuracy of the robot processing path for generating airfoil skin.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision, comprising:

[0006] Collecting three-dimensional point cloud data of the airfoil skin to be processed, preprocessing the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm;

[0007] Based on the geodesic distance between any two points on the triangular mesh surface, a triangular mesh surface point set is mapped into a plane space to obtain a corresponding plane point set, then boundary points of the plane point set are obtained in the plane space according to local neighborhood features of the boundary points, and the boundary points in the plane point set are inversely mapped into the surface point set to obtain boundary contour points of the airfoil skin;

[0008] Based on the curvature characteristics of the airfoil skin boundary contour points, the airfoil skin boundary contour points are fitted to obtain a B-spline curve, and processing path points are obtained based on the B-spline curve.

[0009] After collecting the three-dimensional point cloud data of the airfoil skin to be processed, the present application performs preprocessing, which filters out noise on the one hand and reduces the density of the measurement data on the other hand. The three-dimensional point cloud data is then converted into a triangular mesh surface for mapping to obtain a corresponding plane point set. The boundary points of the plane point set are obtained in the plane space according to the local neighborhood characteristics of the boundary points, and the boundary contour points of the airfoil skin are obtained by inverse mapping. This is easy to implement, and the boundary contour points of the airfoil skin are fitted by a B-spline curve according to the curvature characteristics of the boundary contour points of the airfoil skin. This not only ensures the smoothness of the processing path and avoids jitter, but also ensures the accuracy of the processing path and improves the processing accuracy.

[0010] According to a vision-guided variable curvature airfoil skin robot smoothing machining path generation method provided in the present application, the point cloud triangulation meshing algorithm is used to convert the three-dimensional point cloud data into a triangulated mesh surface, including:

[0011] The three-dimensional point cloud data is converted into a triangular mesh surface using the Lawson algorithm or the Bowyer-Watson algorithm.

[0012] According to a vision-guided variable curvature airfoil skin robot smoothing machining path generation method provided in the present application, the method maps the triangular mesh surface point set into a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain the corresponding plane point set, including:

[0013] Based on the geodesic distance between any two points on the triangular mesh surface, a multi-dimensional scaling method is used to map the triangular mesh surface point set into a plane space to obtain a corresponding plane point set.

[0014] According to a vision-guided variable curvature airfoil skin robot smoothing machining path generation method provided by the present application, the boundary points of the plane point set are obtained according to the local neighborhood features of the boundary points in the plane space, including:

[0015] Traversing a plane point set Each point in , query with the point The nearest k points , choose any one of the points with dot Composition vector ;

[0016] Vector As the benchmark, traverse the rest of the points with dot Composition vector , and calculate the vector With vector Angle , and calculate the vector With vector If the outer product is positive, then unchanged, if the outer product is negative, then Take its opposite number;

[0017] Record The maximum value and minimum value ,like If the angle is smaller than the preset threshold, the point As the boundary points of a planar point set.

[0018] The present application obtains the boundary points of a plane point set in a plane space according to the angle between each point and the vector formed by its surrounding points, and obtains the boundary contour points of the airfoil skin by inverse mapping. The application is easy to implement, and the size of the angle can be set to different values ​​according to the shape of the airfoil skin, so the application is strong.

[0019] According to a vision-guided variable curvature airfoil skin robot smoothing processing path generation method provided by the present application, the airfoil skin boundary contour points are fitted based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, including:

[0020] Calculate the parameter values ​​and curvature values ​​corresponding to each airfoil skin boundary contour point;

[0021] constructing a characteristic function reflecting geometric characteristics of the airfoil skin based on the parameter value and the curvature value, and calculating a cumulative distribution function based on the characteristic function;

[0022] A knot vector is calculated based on the parameter value, and a fitted B-spline curve is obtained based on the cumulative distribution function and the knot vector.

[0023] This application configures node vectors according to the curvature characteristics of the airfoil skin boundary contour points, and fits the airfoil skin boundary contour points through B-spline curves to ensure the smoothness of the processing path, avoid jitter, and ensure the accuracy of the processing path and improve processing precision.

[0024] According to a vision-guided variable curvature airfoil skin robot smoothing machining path generation method provided in the present application, obtaining machining path points based on the B-spline curve includes:

[0025] The B-spline curve is discretized by using the equal chord length method or the equal residual method to obtain processing path points.

[0026] According to a vision-guided variable curvature airfoil skin robot smoothing machining path generation method provided by the present application, after fitting the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtaining machining path points based on the B-spline curve, the method further includes:

[0027] The processing path point position and the corresponding processing posture are converted into the joint angle of the robot at the processing position point based on the robot inverse kinematics.

[0028] This application uses robot inverse kinematics to convert the processing path point position and the corresponding processing posture into the robot's joint angle at the processing position point, so that the industrial robot can realize automatic cutting of the airfoil skin based on the generated processing path.

[0029] In a second aspect, the present application provides a vision-guided variable curvature airfoil skin robot smoothing processing path generation device, comprising:

[0030] An acquisition module is used to acquire three-dimensional point cloud data of the airfoil skin to be processed, pre-process the data, and convert the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm;

[0031] a boundary extraction module for mapping a triangular mesh surface point set into a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set, then obtaining boundary points of the plane point set based on local neighborhood features of the boundary points in the plane space, and inversely mapping the boundary points in the plane point set into the surface point set to obtain boundary contour points of the airfoil skin;

[0032] A fitting module is used to fit the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtain processing path points based on the B-spline curve.

[0033] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the vision-guided variable curvature wing skin robot smoothing processing path generation method described in the first aspect or any possible implementation of the first aspect.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program. When the computer program runs on a processor, the processor executes the vision-guided variable curvature wing skin robot smoothing processing path generation method described in the first aspect or any possible implementation of the first aspect.

[0035] In a fifth aspect, the present application provides a computer program product, which, when running on a processor, enables the processor to execute the vision-guided variable curvature wing skin robot smoothing processing path generation method described in the first aspect or any possible implementation of the first aspect.

[0036] It can be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0037] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the existing technologies:

[0038] After collecting the three-dimensional point cloud data of the airfoil skin to be processed, preprocessing is performed to filter out noise on the one hand and reduce the density of the measurement data on the other hand. The three-dimensional point cloud data is then converted into a triangular mesh surface for mapping to obtain the corresponding plane point set. The boundary points of the plane point set are obtained in the plane space according to the local neighborhood characteristics of the boundary points. The boundary contour points of the airfoil skin are obtained through inverse mapping, which is easy to implement. According to the curvature characteristics of the boundary contour points of the airfoil skin, the boundary contour points of the airfoil skin are fitted with a B-spline curve, which can not only ensure the smoothness of the processing path and avoid jitter, but also ensure the accuracy of the processing path and improve the processing accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 This is one of the flow charts of the method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision provided in an embodiment of the present application;

[0041] Figure 2 This is a schematic diagram of the principle of obtaining boundary points in a planar point set provided by an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of obtaining the machining path points of an airfoil skin robot using a discrete curve of the equal chord length method provided in an embodiment of the present application;

[0043] Figure 4 Schematic diagram of the structure of a device for generating a smoothing processing path for a variable-curvature airfoil skin robot guided by vision provided in an embodiment of the present application;

[0044] Figure 5It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0046] The term "and / or" as used herein describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. The symbol " / " as used herein indicates that the related objects are in an "or" relationship, for example, A / B means either A or B.

[0047] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0048] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units means two or more processing units, etc.; multiple elements means two or more elements, etc.

[0049] Next, combine Figure 1-Figure 3 The method for generating a smooth processing path for a variable curvature airfoil skin robot guided by vision provided in an embodiment of the present application is introduced.

[0050] Figure 1 : is a flow chart of a method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0051] Step 100: collecting three-dimensional point cloud data of the airfoil skin to be processed, pre-processing the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm;

[0052] Optionally, three-dimensional point cloud data of the airfoil skin to be processed can be collected by using a collection device such as a laser radar or an ultrasonic sensor.

[0053] Optionally, preprocessing methods such as outlier removal, smoothing filtering, or random downsampling can be used to preprocess the 3D point cloud data to remove noise generated during the measurement process and reduce the density of the measurement data.

[0054] The point cloud triangulation algorithm is an algorithm that converts discrete three-dimensional point cloud data into a continuous surface, including Delaunay triangulation, etc. This application does not limit the specific point cloud triangulation algorithm used to convert three-dimensional point cloud data into a triangular mesh surface.

[0055] Step 110: Mapping the triangular mesh surface point set to a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set. Then, obtaining boundary points of the plane point set based on the local neighborhood characteristics of the boundary points in the plane space, and inversely mapping the boundary points in the plane point set to the surface point set to obtain boundary contour points of the airfoil skin.

[0056] The triangular mesh surface is obtained, and the surface point set can be mapped into the plane space based on the geodesic distance between any two points on the surface to obtain the plane point set. The boundary points in the plane space are determined, and the boundary points of the plane point set are obtained according to the local neighborhood characteristics of the boundary points. Then, the boundary points of the plane point set are mapped into the surface point set through inverse mapping to obtain the boundary contour points of the airfoil skin.

[0057] Step 120 : fitting the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtaining processing path points based on the B-spline curve.

[0058] Optionally, the node vectors can be configured according to the curvature characteristics of the airfoil skin boundary contour points, the airfoil skin boundary contour points can be fitted by B-spline curves, and then the airfoil skin robot processing path points can be obtained by curve discretization.

[0059] The present application provides a vision-guided variable curvature airfoil skin robot smooth processing path generation method. After collecting the three-dimensional point cloud data of the airfoil skin to be processed, preprocessing is performed to filter out noise on the one hand and reduce the density of the measurement data on the other hand. The three-dimensional point cloud data is then converted into a triangular mesh surface for mapping to obtain a corresponding plane point set. The boundary points of the plane point set are obtained in the plane space according to the local neighborhood characteristics of the boundary points. The boundary contour points of the airfoil skin are obtained by inverse mapping. The method is easy to implement. According to the curvature characteristics of the boundary contour points of the airfoil skin, the boundary contour points of the airfoil skin are fitted by a B-spline curve. This method can not only ensure the smoothness of the processing path and avoid jitter, but also ensure the accuracy of the processing path and improve the processing accuracy.

[0060] In some embodiments, step 100 specifically includes:

[0061] The Lawson algorithm or Bowyer-Watson algorithm is used to convert 3D point cloud data into triangular mesh surfaces.

[0062] The Lawson algorithm is a local optimization algorithm used to generate two-dimensional Delaunay triangulations. Its core idea is to gradually optimize the triangular mesh by flipping each edge to ensure that the Delaunay criterion is met. The algorithm steps include:

[0063] 1a. Input: a set of two-dimensional points ;

[0064] 2a. Generate an initial triangulation, which can be any simple triangulation, such as a convex hull triangulation or a randomly generated triangle mesh;

[0065] 3a. Local optimization iteration: traverse all edges, check whether they meet the Delaunay condition, and perform flip operations on edges that do not meet the condition;

[0066] 4a. Termination condition: All edges satisfy the Delaunay criterion and the algorithm converges.

[0067] The Bowyer-Watson algorithm is a classic incremental Delaunay triangulation algorithm that dynamically maintains the Delaunay triangulation by inserting points one by one. The algorithm steps include:

[0068] 1b. Input: a set of two-dimensional points ;

[0069] 2b. Initialize the super triangle: Create a triangle large enough to enclose all input points and ensure that all subsequent insertion points are inside the triangle;

[0070] 3b. Insert each point into the current triangulation in turn;

[0071] 4b. Delete all triangles containing super-triangle vertices, leaving the triangle mesh consisting only of the input points.

[0072] Optionally, the Lawson algorithm or the Bowyer-Watson algorithm can be used to convert the three-dimensional point cloud data into a triangular mesh surface to improve the conversion efficiency and practicality.

[0073] In some embodiments, step 110 maps the triangular mesh surface point set to a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set, specifically including:

[0074] Based on the geodesic distance between any two points on the triangular mesh surface, a multi-dimensional scaling method is used to map the triangular mesh surface point set into a plane space to obtain the corresponding plane point set.

[0075] First, assume that the surface point set is , calculate the geodesic distances from some points to other points on the triangular mesh surface, and quickly approximate the matrix consisting of the geodesic distances between each point by multiplying small matrices ,get , its objective function is:

[0076]

[0077] in, is a matrix Any n columns of . If is unknown, transform the above formula into:

[0078]

[0079] in, is a matrix The first n rows of . Solve to get The expression is .

[0080] Then, the surface point set is mapped to the corresponding plane point set using the multidimensional scaling method, and its objective function is:

[0081]

[0082] in, is an s×s matrix, , is the i-th point on the triangular mesh surface With the jth point The geodesic distance, is a s×s centered matrix, and , among which, when hour ,when hour , through the matrix The obtained plane point set can be The geometric center of is moved to the origin of coordinates. Performing eigenvalue decomposition yields:

[0083]

[0084] in, is a diagonal matrix whose diagonal elements are The eigenvalues ​​of are arranged from large to small, and the matrix It is composed of the eigenvectors corresponding to the eigenvalues, and the corresponding plane point set is obtained as follows:

[0085]

[0086] in, for The diagonal matrix consisting of the two largest eigenvalues ​​in , for The matrix consisting of the corresponding eigenvectors in .

[0087] In some embodiments, obtaining the boundary points of the planar point set according to the local neighborhood features of the boundary points in the planar space in step 110 specifically includes:

[0088] Traversing a plane point set Each point in , query and point The nearest k points , choose any one of the points with dot Composition vector ;

[0089] Vector As the benchmark, traverse the rest of the points with dot Composition vector , and calculate the vector With vector Angle , and calculate the vector With vector If the outer product is positive, then unchanged, if the outer product is negative, then Take its opposite number;

[0090] Record The maximum value and minimum value ,like If the angle is smaller than the preset threshold, the point As the boundary points of a planar point set.

[0091] Figure 2 This is a schematic diagram of the principle of obtaining boundary points in a plane point set provided by an embodiment of the present application, such as Figure 2 As shown, traverse the plane point set Each point in , query the k points closest to it , choose any one of the points with dot Composition vector , with vector As the benchmark, traverse the rest of the points with dot Composition vector , calculate the vector With vector Angle , further calculate the vector With vector If the outer product is positive, then unchanged, if the outer product is negative, then Take its opposite number and record The maximum value and minimum value ,like This point can be obtained is the boundary point in the plane point set.

[0092] in, Any point in the plane point set The angle between the vector and the surrounding points. This value can be set according to the geometric shape of the airfoil skin.

[0093] In some embodiments, step 120 specifically includes:

[0094] Calculate the parameter values ​​and curvature values ​​corresponding to each airfoil skin boundary contour point;

[0095] Based on the parameter values ​​and curvature values, a characteristic function that reflects the geometric characteristics of the airfoil skin is constructed, and the cumulative distribution function is calculated based on the characteristic function;

[0096] The knot vectors are calculated based on the parameter values, and a fitted B-spline curve is obtained based on the cumulative distribution function and the knot vectors.

[0097] The specific steps are as follows:

[0098] 1c. Use the cumulative chord length parameterization method to calculate the parameter value corresponding to each airfoil skin boundary contour point :

[0099]

[0100] 2c. Fit the airfoil skin boundary contour points with lower fitting accuracy to obtain the base curve , calculate the curvature value of each airfoil skin boundary contour point for:

[0101]

[0102] in, is the base curve obtained by fitting with lower fitting accuracy, , The base curve In parameter value The first and second derivatives at .

[0103] 3c. Constructing characteristic functions that reflect the geometric characteristics of the airfoil skin , let the characteristic function be at parameter value is the curvature value of the airfoil skin boundary contour point ,Right now: , and then define the continuous characteristic function in the form of piecewise linear interpolation , whose expression is:

[0104]

[0105] 4c. Calculate the characteristic function reflecting the geometric characteristics of the airfoil skin Cumulative distribution function of For dense data, the Newton-Cotes formula is used to calculate the integral:

[0106]

[0107] 5c. Calculate node vector In order to make the endpoints of the B-spline curve coincide with the control points, the k+1 nodes before and after are the same, and the values ​​of the nodes before and after are , , the value of the intermediate node is ,in is the inverse of the cumulative distribution function, The eigenvalues ​​contained in each node are set.

[0108] 6c. Node vectors configured based on the curvature characteristics of the airfoil skin boundary contour points U , the B-spline curve is used to fit the airfoil skin boundary contour points, and its least square fitting expression is:

[0109]

[0110] in,

[0111] ,

[0112] ,

[0113] ,

[0114]

[0115] Where k is the degree of the B-spline curve, is the basis function of the B-spline curve.

[0116] Furthermore, through the control point D and node vectors U The expression of the fitted B-spline curve is:

[0117] .

[0118] In some embodiments, step 120 specifically includes:

[0119] The B-spline curve is discretized using the equal chord length method or the equal residual method to obtain the processing path points.

[0120] Figure 3 Schematic diagram of obtaining the machining path points of the airfoil skin robot by using the discrete curve of the equal chord length method provided in the embodiment of the present application, as shown in FIG. Figure 3 As shown, in one embodiment of the present application, the airfoil skin boundary contour points are fitted to obtain a fitting curve Then, the fitting curve is converted to The smooth robot machining path points of the airfoil skin can be obtained by discretization.

[0121] Alternatively, the equal residual method can be used to fit the curve The smooth robot machining path points of the airfoil skin can be obtained by discretization.

[0122] In some embodiments, after step 120, the method further includes:

[0123] Based on the robot inverse kinematics, the processing path point position and the corresponding processing posture are converted into the joint angle of the robot at the processing position point.

[0124] Robot inverse kinematics is a key technology for achieving precise trajectory planning, obstacle avoidance control, and real-time operation. It aims to solve the motion parameters (such as rotation angle and translation distance) of each joint of the robot based on the target position and posture of the end effector (such as a manipulator, foot, or tool).

[0125] This application uses robot inverse kinematics to convert the processing path point position and the corresponding processing posture into the robot's joint angle at the processing position point, so that the industrial robot can realize automatic cutting of the airfoil skin based on the generated processing path.

[0126] Figure 4 Schematic diagram of the structure of the device for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision provided in an embodiment of the present application. Figure 4 As shown, the system includes an acquisition module 410, a boundary extraction module 420 and a fitting module 430, wherein:

[0127] The acquisition module 410 is used to acquire the 3D point cloud data of the airfoil skin to be processed, pre-process it, and convert the 3D point cloud data into a triangular mesh surface using a point cloud triangulation algorithm;

[0128] Boundary extraction module 420 is used to map the triangular mesh surface point set into a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set, then obtain boundary points of the plane point set based on the local neighborhood characteristics of the boundary points in the plane space, and inversely map the boundary points in the plane point set into the surface point set to obtain the boundary contour points of the airfoil skin;

[0129] The fitting module 430 is used to fit the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtain processing path points based on the B-spline curve.

[0130] It should be understood that the above-mentioned system is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the system are similar to those described in the above-mentioned method. The working process of the system can refer to the corresponding process in the above-mentioned method and will not be repeated here.

[0131] Based on the method in the above embodiment, Figure 5 An example of a physical structure diagram of an electronic device is shown below. Figure 5 As shown, an embodiment of the present application provides an electronic device, which may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the vision-guided variable curvature airfoil skin robot smoothing processing path generation method in the above embodiment.

[0132] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the vision-guided variable curvature airfoil skin robot smoothing processing path generation method described in each embodiment of the present application.

[0133] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the vision-guided variable curvature wing skin robot smoothing processing path generation method in the above embodiment.

[0134] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the vision-guided variable curvature wing skin robot smoothing processing path generation method in the above embodiment.

[0135] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0136] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC.

[0137] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they 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 loaded and executed on a computer, the computer program instructions fully or partially produce the processes or functions described in the embodiments of this application. 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 via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state drive (SSD)).

[0138] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

[0139] It is easy for those skilled in the art to understand that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A vision-guided method for generating smooth machining paths for variable curvature airfoil skin robots, characterized in that: include: Collecting three-dimensional point cloud data of the airfoil skin to be processed, preprocessing the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm; Based on the geodesic distance between any two points on the triangular mesh surface, a triangular mesh surface point set is mapped into a plane space to obtain a corresponding plane point set, then boundary points of the plane point set are obtained in the plane space according to local neighborhood features of the boundary points, and the boundary points in the plane point set are inversely mapped into the surface point set to obtain boundary contour points of the airfoil skin; Fitting the airfoil skin boundary contour points based on curvature characteristics to obtain a B-spline curve, and obtaining processing path points based on the B-spline curve; Obtaining the boundary points of the planar point set according to local neighborhood features of the boundary points in the planar space includes: Traversing a plane point set Each point in , query with the point The nearest k points , choose any one of the points with dot Composition vector ; Vector As the benchmark, traverse the rest of the points with dot Composition vector , and calculate the vector With vector Angle , and calculate the vector With vector If the outer product is positive, then unchanged, if the outer product is negative, then Take its opposite number; Record The maximum value and minimum value ,like If the angle is smaller than the preset threshold, the point As the boundary points of a planar point set.

2. The method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to claim 1 is characterized in that: The method of converting the three-dimensional point cloud data into a triangular mesh surface by using a point cloud triangulation algorithm includes: The three-dimensional point cloud data is converted into a triangular mesh surface using the Lawson algorithm or the Bowyer-Watson algorithm.

3. The method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to claim 1 is characterized in that: The method of mapping the triangular mesh surface point set to a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set includes: Based on the geodesic distance between any two points on the triangular mesh surface, a multi-dimensional scaling method is used to map the triangular mesh surface point set into a plane space to obtain a corresponding plane point set.

4. The method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to claim 1, characterized in that: The step of fitting the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve comprises: Calculate the parameter values ​​and curvature values ​​corresponding to each airfoil skin boundary contour point; constructing a characteristic function reflecting geometric characteristics of the airfoil skin based on the parameter value and the curvature value, and calculating a cumulative distribution function based on the characteristic function; A knot vector is calculated based on the parameter value, and a fitted B-spline curve is obtained based on the cumulative distribution function and the knot vector.

5. The method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to claim 1 or 4, characterized in that: The obtaining of processing path points based on the B-spline curve includes: The B-spline curve is discretized by using the equal chord length method or the equal residual method to obtain processing path points.

6. The method for generating a smooth machining path for a variable curvature airfoil skin robot guided by vision according to claim 1, characterized in that: After fitting the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtaining processing path points based on the B-spline curve, the method further includes: The processing path point position and the corresponding processing posture are converted into the joint angle of the robot at the processing path point position based on the robot inverse kinematics.

7. A vision-guided variable curvature airfoil skin robot smoothing processing path generation device, characterized in that: include: An acquisition module is used to acquire three-dimensional point cloud data of the airfoil skin to be processed, pre-process the data, and convert the three-dimensional point cloud data into a triangular mesh surface using a point cloud triangulation algorithm; a boundary extraction module for mapping a triangular mesh surface point set into a plane space based on the geodesic distance between any two points on the triangular mesh surface to obtain a corresponding plane point set, then obtaining boundary points of the plane point set based on local neighborhood features of the boundary points in the plane space, and inversely mapping the boundary points in the plane point set into the surface point set to obtain boundary contour points of the airfoil skin; A fitting module, configured to fit the airfoil skin boundary contour points based on the curvature characteristics of the airfoil skin boundary contour points to obtain a B-spline curve, and obtain processing path points based on the B-spline curve; The boundary extraction module is specifically used for: Traversing a plane point set Each point in , query with the point The nearest k points , choose any one of the points with dot Composition vector ; Vector As the benchmark, traverse the rest of the points with dot Composition vector , and calculate the vector With vector Angle , and calculate the vector With vector If the outer product is positive, then unchanged, if the outer product is negative, then Take its opposite number; Record The maximum value and minimum value ,like If the angle is smaller than the preset threshold, the point As the boundary points of a planar point set.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the vision-guided variable curvature airfoil skin robot smooth processing path generation method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is enabled to execute the vision-guided variable-curvature airfoil skin robot smoothing processing path generation method according to any one of claims 1 to 6.

Images