Automatic machining method, device and equipment for arc-shaped workpiece and storage medium

Through three-dimensional scanning and curvature analysis, reasonable processing paths are generated, and combined with five-axis linkage control and multi-sensor tracking and measurement, the problem of unreasonable machining path planning of arc-shaped workpieces is solved, and processing efficiency and surface quality are improved.

CN118938805AInactive Publication Date: 2024-11-12深圳市华恒五金机械有限公司
View PDF 0 Cites 12 Cited by

Patent Information

Application Number
CN202411299130.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing automated processing methods cannot fully consider the complex curvature changes of arc-shaped workpieces, resulting in unreasonable machining path planning, low efficiency and unstable surface quality.

Method used

Through all-round three-dimensional scanning and curvature analysis, the curvature distribution data of the workpiece surface is obtained, and the asynchronous B-spline curve smoothing process is performed to generate the tool motion trajectory, and five-axis linkage motion control and real-time dynamic compensation are performed during the processing process, combined with multi-sensor fusion Dynamic tracking measurement and multispectral imaging evaluation, real-time adjustment of machining parameters.

Benefits of technology

Ensure the rationality of the machining path, improve the accuracy of the tool movement trajectory, reduce tool wear, and improve machining accuracy and surface quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938805A_ABST
    Figure CN118938805A_ABST
Patent Text Reader

Abstract

The invention provides an automatic machining method, device and equipment for an arc-shaped workpiece and a storage medium, and the method comprises the steps that three-dimensional scanning and curvature analysis are conducted on the arc-shaped workpiece, and curvature distribution data and a self-adaptive segmentation result of the surface of the workpiece are obtained; and according to the data, generating a cutter motion track. And on the basis of the track, machine tool equipment is controlled to conduct machining operation on the arc-shaped workpiece, and meanwhile, an actual machining path is obtained through five-axis linkage motion control and real-time dynamic compensation. And carrying out multi-sensor fusion dynamic tracking measurement on the surface of the workpiece along the actual processing path to obtain real-time contour data. And the surface quality of the workpiece is evaluated according to the real-time contour data, a comprehensive quality score is generated, and machining parameters are adjusted in real time according to the score. According to the method, through three-dimensional scanning and curvature analysis, the curvature data of the surface of the workpiece can be accurately obtained, the reasonability of the machining path is ensured, the tool movement track is more accurate, tool abrasion is reduced, and the machining precision is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of workpiece processing, and in particular to an automated processing method, device, equipment and storage medium for arc-shaped workpieces. Background Art

[0002] In the manufacturing industry, arc-shaped workpieces are widely used in aviation, aerospace, automobiles, molds and other fields. The machining accuracy and surface quality of these workpieces directly affect the performance and service life of the final product. Traditional arc-shaped workpiece machining methods mainly rely on manual operation and two-dimensional machining technology, which have problems such as low machining accuracy, low efficiency, and unstable surface quality.

[0003] In the existing technology, the development of 3D scanning technology and CNC machine tools has provided new possibilities for the automated processing of curved workpieces. 3D scanning technology can obtain all-round surface data of workpieces, and CNC machine tools can perform automated processing based on these data. However, existing automated processing methods often fail to fully consider the complex curvature changes of curved workpieces, resulting in unreasonable processing path planning, severe tool wear, and processing efficiency and surface quality that are still difficult to achieve ideal levels. Summary of the invention

[0004] The main purpose of the present invention is to solve the technical problem that the existing automated processing methods often fail to fully consider the complex curvature changes of arc-shaped workpieces, resulting in unreasonable processing path planning.

[0005] A first aspect of the present invention provides an automated processing method for a curved workpiece, the automated processing method for a curved workpiece comprising: Perform all-round 3D scanning and curvature analysis on the curved workpiece to obtain the curvature distribution data and adaptive segmentation results of the workpiece surface; According to the curvature distribution data and the adaptive segmentation result, the workpiece processing path is subjected to asynchronous B-spline curve smoothing to obtain a tool motion trajectory; Based on the tool motion trajectory, control the corresponding machine tool equipment to perform processing operations on the arc-shaped workpiece, and during the processing of the processing, perform five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool equipment to obtain an actual processing path; Along the actual processing path, multi-sensor fusion dynamic tracking measurement is performed on the workpiece surface to obtain real-time contour data; Based on the real-time profile data, a multi-spectral imaging evaluation is performed on the surface quality of the workpiece to obtain a comprehensive quality score, and the processing parameters of the processing operation are adjusted in real time based on the comprehensive quality score.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the performing omnidirectional three-dimensional scanning and curvature analysis on the arc-shaped workpiece to obtain curvature distribution data and adaptive segmentation results of the workpiece surface includes: Performing multi-angle laser scanning on the surface of the arc-shaped workpiece to obtain point cloud data, wherein the multi-angle laser scanning includes scanning operations at at least three different angles; Performing denoising and gridding processing on the point cloud data to obtain a three-dimensional grid model, and performing curvature calculation on the three-dimensional grid model to obtain the principal curvature and Gaussian curvature of each grid node in the three-dimensional grid model; Generate and calculate curvature distribution data of the workpiece surface according to the principal curvature and Gaussian curvature, and calculate the curvature change rate of each grid node according to the curvature distribution data to obtain a curvature change rate distribution map; According to the curvature change rate distribution map and a preset threshold, a region growing algorithm is used to adaptively segment the workpiece surface to obtain an adaptive segmentation result.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the denoising and meshing processing is performed on the point cloud data to obtain a three-dimensional mesh model, and curvature calculation is performed on the three-dimensional mesh model to obtain the principal curvature and Gaussian curvature of each mesh node in the three-dimensional mesh model, including: Performing noise reduction processing and statistical analysis on the point cloud data to obtain point cloud density distribution, and adaptively sampling the point cloud data according to the point cloud density distribution to obtain uniform point cloud data; Using a preset Delaunay triangulation algorithm to perform gridding processing on the homogenized point cloud data to obtain a three-dimensional grid model, and constructing a local coordinate system for each vertex in the three-dimensional grid model to obtain a neighborhood local representation of each vertex; In the local coordinate system, a quadratic surface fitting is performed on the neighborhood local representation of the corresponding vertex to obtain a local surface equation, and the principal curvature and Gaussian curvature of each mesh node are calculated based on the coefficients of the local surface equation.

[0008] Optionally, in a third implementation of the first aspect of the present invention, performing asynchronous B-spline curve smoothing on the workpiece machining path according to the curvature distribution data and the adaptive segmentation result to obtain the tool motion trajectory includes: Determine the key corner positions of the workpiece processing path according to the curvature distribution data and the adaptive segmentation result, and obtain a set of corners that need to be smoothed, wherein the workpiece processing path includes a tool tip path and tool direction data; For each corner in the corner set, based on local curvature information in the curvature distribution data, two asymmetric B-spline curves are calculated; Inserting the two asymmetric B-spline curves into corresponding corners of the tool tip path and tool direction data corresponding to the corners, respectively, to obtain a first transition curve and a second transition curve segment; According to the first transition curve and the second transition curve segment, the tool tip path and the tool direction data are respectively smoothed to obtain a smoothed tool tip path and a smoothed tool direction data; The tool motion trajectory is obtained by combining the smoothed tool tip path and the smoothed tool direction data.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the step of smoothing the tool tip path and the tool direction data according to the first transition curve and the second transition curve segment to obtain the smoothed tool tip path and the smoothed tool direction data comprises: Performing overlap detection on the first transition curves of adjacent corners to obtain a potential overlap area of ​​the tool tip path, and constructing an optimization model based on the potential overlap area to obtain an optimization objective function of the tool tip path by minimizing the local minimum speed difference at adjacent corners; Solving the optimization objective function of the tool tip path by using an iterative algorithm to obtain a characteristic length of the updated first transition curve, and smoothing the tool tip path according to the characteristic length of the updated first transition curve to obtain a smoothed tool tip path; The tool direction data is converted into the machine tool coordinate system of the machine tool equipment to obtain the tool direction data in the machine tool coordinate system, and an optimization model of the tool direction is constructed according to the tool direction data in the machine tool coordinate system and the second transition curve segment to obtain an optimization objective function of the tool direction; The optimization objective function of the tool direction is solved to obtain the characteristic length of the updated second transition curve segment, and based on the characteristic length of the updated second transition curve segment, the tool direction data in the machine tool coordinate system is smoothed to obtain the smoothed tool direction data.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, based on the tool motion trajectory, controlling the corresponding machine tool equipment to perform processing operations on the arc-shaped workpiece, and during the processing of the processing, performing five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool equipment, and obtaining the actual processing path includes: Performing interpolation processing on the tool motion trajectory to obtain a discrete tool position point sequence, and calculating the motion parameters of each axis of the machine tool equipment according to the discrete tool position point sequence to obtain a motion instruction sequence of each axis of the machine tool equipment; According to the motion instruction sequence, each axis of the machine tool equipment is controlled to perform processing operation on the arc-shaped workpiece, and during the processing operation, the vibration of the machine tool is monitored in real time by using a high-frequency sampling acceleration sensor to obtain the vibration data of the machine tool; According to the machine tool vibration data, a machine tool dynamic error model is constructed to obtain a real-time error compensation amount, and according to the real-time error compensation amount, real-time dynamic compensation is performed on the motion instruction sequence to obtain a compensated axis motion instruction; Controlling the movement of each axis of the machine tool according to the compensated axis movement command, and using a high-precision encoder to record the actual movement state of each axis to obtain actual axis position data; Based on the actual axis position data, the actual spatial position and direction sequence of the tool are obtained through inverse kinematics calculation, and the actual spatial position and direction sequence of the tool are connected into a continuous path to obtain the actual processing path.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, performing multispectral imaging evaluation on the surface quality of the workpiece according to the real-time profile data to obtain a comprehensive quality score, and adjusting the processing parameters of the processing operation in real time according to the comprehensive quality score includes: Perform multi-band spectral imaging on the workpiece surface to obtain multi-spectral image data including visible light, near infrared and ultraviolet bands; Performing image segmentation and feature extraction on the multispectral image data to obtain texture features, gloss features and defect features of the workpiece surface; Fusing the real-time contour data with the texture features, gloss features and defect features to obtain comprehensive surface feature data; Analyzing the comprehensive surface feature data using a pre-trained deep learning model to obtain a quantitative evaluation result of the workpiece surface quality; Calculate the comprehensive score of the workpiece surface quality according to the quantitative evaluation results and the preset quality standard to obtain a comprehensive quality score; Based on the comprehensive quality score, a processing parameter optimization model is constructed to obtain a processing parameter adjustment strategy, and the processing parameters of the processing operation are adjusted in real time according to the processing parameter adjustment strategy.

[0012] A second aspect of the present invention provides an automated processing device for a curved workpiece, the automated processing device for a curved workpiece comprising: Scanning and analysis module, used to perform all-round 3D scanning and curvature analysis on the curved workpiece, and obtain the curvature distribution data and adaptive segmentation results of the workpiece surface; A trajectory smoothing module is used to perform asynchronous B-spline curve smoothing on the workpiece processing path according to the curvature distribution data and the adaptive segmentation result to obtain a tool motion trajectory; A processing module, which is used to control a corresponding machine tool to process the arc-shaped workpiece based on the tool motion trajectory, and during the processing of the processing, perform five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool to obtain an actual processing path; A tracking module, used to perform multi-sensor fusion dynamic tracking measurement on the workpiece surface along the actual processing path to obtain real-time contour data; The adjustment module is used to perform multi-spectral imaging evaluation on the surface quality of the workpiece according to the real-time profile data to obtain a comprehensive quality score, and to adjust the processing parameters of the processing operation in real time according to the comprehensive quality score.

[0013] The third aspect of the present invention provides an automated processing device for arc-shaped workpieces, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via lines; the at least one processor calls the instructions in the memory to enable the automated processing equipment for arc-shaped workpieces to perform the steps of the above-mentioned automated processing method for arc-shaped workpieces.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the above-mentioned method for automated processing of arc-shaped workpieces.

[0015] The above-mentioned automated processing method, device, equipment and storage medium for arc-shaped workpieces obtains the curvature distribution data and adaptive segmentation results of the workpiece surface by performing three-dimensional scanning and curvature analysis on the arc-shaped workpiece. According to the above data, a tool motion trajectory is generated. Based on the trajectory, the machine tool equipment is controlled to perform processing operations on the arc-shaped workpiece. At the same time, the actual processing path is obtained through five-axis linkage motion control and real-time dynamic compensation. The workpiece surface is subjected to multi-sensor fusion dynamic tracking measurement along the actual processing path to obtain real-time contour data. According to the real-time contour data, the surface quality of the workpiece is evaluated, a comprehensive quality score is generated, and the processing parameters are adjusted in real time according to the score. Through three-dimensional scanning and curvature analysis, this method can accurately obtain the curvature data of the workpiece surface, ensure the rationality of the processing path, make the tool motion trajectory more accurate, reduce tool wear, and improve processing accuracy.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of a first embodiment of an automated processing method for arc-shaped workpieces according to an embodiment of the present invention; Figure 2 A schematic diagram of an embodiment of an automated processing device for arc-shaped workpieces according to an embodiment of the present invention; Figure 3 It is a schematic diagram of an embodiment of an automated processing equipment for arc-shaped workpieces in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device end including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or device ends.

[0021] To facilitate understanding of this embodiment, firstly, an automated processing method for a curved workpiece disclosed in an embodiment of the present invention is described in detail. Figure 1 As shown, the method comprises the following steps: 101. Perform all-round three-dimensional scanning and curvature analysis on the arc-shaped workpiece to obtain the curvature distribution data and adaptive segmentation results of the workpiece surface; In one embodiment of the present invention, the all-round three-dimensional scanning and curvature analysis of the curved workpiece to obtain the curvature distribution data and adaptive segmentation results of the workpiece surface includes: performing multi-angle laser scanning on the surface of the curved workpiece to obtain point cloud data, wherein the multi-angle laser scanning includes scanning operations at at least three different angles; performing denoising and gridding on the point cloud data to obtain a three-dimensional mesh model, and performing curvature calculation on the three-dimensional mesh model to obtain the principal curvature and Gaussian curvature of each mesh node in the three-dimensional mesh model; generating and calculating the curvature distribution data of the workpiece surface based on the principal curvature and Gaussian curvature, and calculating the curvature change rate of each mesh node based on the curvature distribution data to obtain a curvature change rate distribution map; based on the curvature change rate distribution map and a preset threshold, using a regional growing algorithm to adaptively segment the workpiece surface to obtain an adaptive segmentation result.

[0022] Specifically, the workpiece needs to be scanned and analyzed in all directions to obtain the curvature distribution data and adaptive segmentation results of the workpiece surface. This process starts with multi-angle laser scanning of the curved workpiece surface, usually at least three different angles are used to scan to ensure that all details of the workpiece surface can be captured. After obtaining the point cloud data, the data needs to be denoised and meshed. The denoising process usually uses a statistical outlier filtering algorithm, which judges and removes noise points based on the average distance from each point to its neighboring points. Subsequently, the point cloud is homogenized using a voxel downsampling method to reduce the amount of data and maintain a uniform distribution of the point cloud. The meshing process uses an improved Ball-Pivoting algorithm, which constructs a triangular mesh by rolling a virtual sphere in the point cloud to obtain an initial three-dimensional mesh model. Next, the curvature of the obtained three-dimensional mesh model is calculated. This step first constructs a local coordinate system for each mesh vertex, where the z axis is aligned with the estimated normal vector of the vertex. Then, in this local coordinate system, a quadratic surface is fitted to the neighborhood of each vertex, and the weighted least squares method is used to obtain the local surface equation. According to the coefficients of this equation, the principal curvature and Gaussian curvature of each grid node can be calculated. With the principal curvature and Gaussian curvature data, the curvature distribution data of the workpiece surface can be generated. In this process, the values ​​of the principal curvature and Gaussian curvature are mapped to a color space to intuitively display the distribution of the curvature. For example, low curvature areas can be represented by cold colors, and high curvature areas can be represented by warm colors, so that the curvature changes on the workpiece surface can be clearly seen. Subsequently, based on this curvature distribution data, the curvature change rate of each grid node is calculated. This step is achieved by comparing the curvature difference between each node and its neighboring nodes, thereby obtaining a curvature change rate distribution map. This distribution map can highlight areas where the curvature changes sharply, which are usually the key feature parts of the workpiece. Finally, using the obtained curvature change rate distribution map and a pre-set threshold, the region growing algorithm is used to adaptively segment the workpiece surface. The region growing algorithm starts from a seed point and gradually adds surrounding points that meet similarity conditions to the current region until there are no more points that meet the conditions. In this process, the curvature change rate is used as the basis for judging similarity, and the preset threshold determines the degree of segmentation.

[0023] Furthermore, the denoising and meshing processing of the point cloud data to obtain a three-dimensional mesh model, and performing curvature calculation on the three-dimensional mesh model to obtain the principal curvature and Gaussian curvature of each mesh node in the three-dimensional mesh model includes: performing denoising and statistical analysis on the point cloud data to obtain a point cloud density distribution, and adaptively sampling the point cloud data according to the point cloud density distribution to obtain homogenized point cloud data; meshing the homogenized point cloud data using a preset Delaunay triangulation algorithm to obtain a three-dimensional mesh model, and constructing a local coordinate system for each vertex in the three-dimensional mesh model to obtain a neighborhood local representation of each vertex; in the local coordinate system, performing quadratic surface fitting on the neighborhood local representation of the corresponding vertex to obtain a local surface equation, and calculating the principal curvature and Gaussian curvature of each mesh node according to the coefficients of the local surface equation.

[0024] Specifically, the noise reduction process usually adopts a statistical outlier filtering algorithm, which determines and removes noise points by calculating the average distance from each point to its neighboring points and setting a threshold. For example, when processing the point cloud data of a complex turbine blade, it may be found that there are some outliers in the edge area of ​​the blade due to the scanning angle, and these points will be effectively removed in this step. Statistical analysis involves calculating the mean and variance of the local point cloud density, which helps to understand the overall distribution characteristics of the point cloud data. Based on this point cloud density distribution, adaptive sampling is performed next. The core idea of ​​adaptive sampling is to downsample in high-density areas and maintain the original point density in low-density areas, thereby obtaining homogenized point cloud data. This process can be achieved through voxel downsampling, in which the size of the voxel is dynamically adjusted according to the local point cloud density. For the turbine blade mentioned above, this means that the number of points may be reduced in the flat area of ​​the blade, while more points are retained in the leading and trailing edge areas where the curvature changes greatly. After obtaining the homogenized point cloud data, the next step is to use the preset Delaunay triangulation algorithm for meshing. The characteristic of Delaunay triangulation is to maximize the minimum angle of the triangle, which helps to avoid generating too narrow and long triangles, thereby improving the quality of the mesh. In actual operation, it is necessary to improve the standard Delaunay algorithm and add a boundary preservation mechanism to ensure that the geometric features can be accurately retained in areas with obvious features such as the edge of the workpiece. Next, a local coordinate system is constructed for each vertex in this three-dimensional mesh model. The purpose of this step is to provide a suitable reference frame for subsequent surface fitting. The construction of the local coordinate system usually takes the vertex as the origin, takes the estimated normal vector as the z-axis, and then selects two orthogonal vectors in the plane perpendicular to the z-axis as the x-axis and y-axis. In this way, each vertex and its surrounding neighborhood points can be represented in this local coordinate system, which is called the local representation of the vertex neighborhood. Under the constructed local coordinate system, the next step is to fit the quadratic surface to the neighborhood of each vertex. The least squares method is used here, and its goal is to find an optimal quadratic surface so that the sum of the squares of the distances from this surface to the neighborhood points is minimized. Finally, based on the coefficients of this local surface equation, the principal curvature and Gaussian curvature of each mesh node can be calculated. The principal curvatures K1 and K2 can be obtained by solving an eigenvalue problem with the coefficients of the local surface equation. They represent the maximum and minimum curvature of the surface at that point. The Gaussian curvature is the product of the two principal curvatures, that is, K = K1 * K2.

[0025] 102. According to the curvature distribution data and the adaptive segmentation results, the workpiece processing path is subjected to asynchronous B-spline curve smoothing to obtain the tool motion trajectory; In one embodiment of the present invention, the asynchronous B-spline curve smoothing is performed on the workpiece processing path according to the curvature distribution data and the adaptive segmentation result to obtain the tool motion trajectory, including: determining the key corner positions of the workpiece processing path according to the curvature distribution data and the adaptive segmentation result, and obtaining a set of corners that need to be smoothed, wherein the workpiece processing path includes a tool tip path and tool direction data; for each corner in the corner set, two asymmetric B-spline curves are calculated based on the local curvature information in the curvature distribution data; the two asymmetric B-spline curves are respectively inserted into the corresponding corners of the tool tip path and the tool direction data corresponding to the corners to obtain a first transition curve and a second transition curve segment; the tool tip path and the tool direction data are respectively smoothed according to the first transition curve and the second transition curve segment to obtain a smoothed tool tip path and a smoothed tool direction data; the tool motion trajectory is obtained by combining the smoothed tool tip path and the smoothed tool direction data.

[0026] Specifically, we first need to use the curvature distribution data and adaptive segmentation results to determine the key corner positions of the workpiece machining path. These corners are usually areas with large curvature changes and have a significant impact on the machining quality. For example, when machining a complex turbine blade, the leading edge, trailing edge, and transition area between the blade body and the blade root may be identified as key corners. By analyzing the curvature changes in these areas, a set of corners that need to be smoothed can be obtained. It is worth noting that the workpiece machining path includes two key components: the tool tip path and the tool orientation data. The tool tip path determines the motion trajectory of the tool in space, while the tool orientation data defines the posture of the tool at each position. Both need to be smoothed to ensure the continuity and accuracy of the machining. For each corner in the corner set, the next step is to calculate two asymmetric B-spline curves based on the local curvature information. The reason for using asymmetric B-spline curves here is to better adapt to the curvature changes in different directions. The calculation process usually involves determining the location and weight of the control points, and these parameters directly affect the shape of the B-spline curve. For example, at the corner of the leading edge of the blade, due to the large change in curvature, more control points may be required to accurately describe the curve shape; while at the corner in the middle of the blade, fewer control points may be required to achieve a satisfactory smoothing effect. The two asymmetric B-spline curves calculated are used to smooth the tool tip path and tool direction data respectively. Inserting these curves into the corresponding corners is a delicate process. For the tool tip path, the B-spline curve directly replaces the original corner segment to form a smooth transition, which is called the first transition curve. For the tool direction data, the B-spline curve is used to adjust the tool posture change to ensure a smooth transition of the tool direction at the corner, which forms the second transition curve segment. The insertion process needs to consider the continuity of the curve, and it is usually required to achieve at least G2 continuity (curvature continuity) to ensure the smoothness of the tool movement during the machining process. For example, at the leading edge corner of the turbine blade, the first transition curve smoothly connects the two adjacent segments of the leading edge, while the second transition curve segment ensures that the direction change of the tool is gradual and smooth when passing through this high curvature area, avoiding machining defects that may be caused by sudden posture changes. Next, the tool tip path and tool direction data are smoothed according to the first transition curve and the second transition curve segment, respectively, to obtain the smoothed tool tip path and smoothed tool direction data. This process essentially merges the original path data with the newly inserted transition curve to ensure the continuity and smoothness of the overall path. Finally, the smoothed tool tip path and the smoothed tool direction data are combined to obtain the final tool motion trajectory. This combination process needs to ensure that the tool tip position and tool direction are synchronized in time and space. For example, when the tool moves along the smoothed leading edge of the blade, its direction should always remain consistent with the local surface normal, while also considering avoiding interference with the workpiece.The advantage of this asynchronous B-spline smoothing method is that it can optimize the tool tip path and tool orientation separately while ensuring the coordination of the two. For complex curved workpieces, such as aircraft engine components, this method can significantly improve machining accuracy and surface quality. For example, when machining turbine blades, the smoothed tool motion trajectory can ensure sufficient machining accuracy in high curvature areas (such as the leading and trailing edges) while maintaining efficient machining speed in the relatively flat middle area of ​​the blade.

[0027] Furthermore, the smoothing of the tool tip path and the tool direction data according to the first transition curve and the second transition curve segment to obtain the smoothed tool tip path and the smoothed tool direction data includes: performing overlap detection on the first transition curves of adjacent corners to obtain a potential overlap area of ​​the tool tip path, and constructing an optimization model according to the potential overlap area, and obtaining an optimization objective function of the tool tip path by minimizing the local minimum speed difference at adjacent corners; solving the optimization objective function of the tool tip path by an iterative algorithm to obtain the characteristic length of the updated first transition curve, and smoothing the tool tip path according to the characteristic length of the updated first transition curve to obtain a smoothed tool tip path; converting the tool direction data to the machine tool coordinate system of the machine tool equipment to obtain the tool direction data in the machine tool coordinate system, and constructing an optimization model of the tool direction according to the tool direction data in the machine tool coordinate system and the second transition curve segment to obtain the optimization objective function of the tool direction; solving the optimization objective function of the tool direction to obtain the characteristic length of the updated second transition curve segment, and smoothing the tool direction data in the machine tool coordinate system based on the characteristic length of the updated second transition curve segment to obtain the smoothed tool direction data.

[0028] Specifically, we first start with overlapping detection of the first transition curves of adjacent corners, with the goal of identifying potential overlapping areas of the tool tip path. Overlap detection usually uses geometric calculation methods, such as calculating the distance function of adjacent transition curves. When the distance is less than a preset threshold, it is considered that there is potential overlap. After identifying the potential overlapping area, the next step is to build an optimization model. The core goal of this model is to minimize the local minimum speed difference between adjacent corners. The purpose of this is to ensure the smooth change of tool speed during the machining process and avoid the machining quality problems that may be caused by sudden acceleration or deceleration. The optimization model is usually expressed as a mathematical function that contains parameters related to the curve shape, length, and speed change. For example, quadratic programming or nonlinear optimization methods can be used to formalize this problem, with the minimization of speed difference as the objective function and the geometric constraints of the curve as the boundary conditions for optimization. With the optimization model, an iterative algorithm is used to solve the optimization objective function of the tool tip path. Commonly used solution methods include gradient descent, Newton method, or quasi-Newton method. This process requires multiple iterations, and each iteration adjusts the parameters of the transition curve until a solution that meets the speed smoothness requirements and does not cause overlap is found. The result of the solution is the characteristic length of the updated first transition curve, which determines the specific shape and range of the transition curve. After obtaining the updated characteristic length, the tool tip path can be finally smoothed. This step usually involves regenerating the B-spline curve, using the updated characteristic length as a control parameter. The newly generated curve will replace the original path segment to form a smoothed tool tip path. At the same time, the processing of the tool direction data is also in progress. First, the tool direction data needs to be converted from the workpiece coordinate system to the machine tool coordinate system of the machine tool equipment. This coordinate conversion process involves the calculation of the rotation matrix, which needs to take into account the specific structure and kinematic characteristics of the machine tool. For example, for a five-axis machining center, this conversion involves the calculation of the angle of the rotation and swing axis of the worktable. In the machine tool coordinate system, based on the converted tool direction data and the second transition curve segment, an optimization model for the tool direction is constructed. The goal of this model is usually to ensure smooth changes in the tool direction while meeting the requirements of machining accuracy. The optimization objective function includes factors such as the rate of change of the tool direction and the deviation from the ideal tool direction. For example, when machining the curved surface of a turbine blade, the optimization of the tool direction needs to take into account the change of the surface normal vector to ensure that the tool always maintains the best cutting angle. Next, the optimization objective function of the tool orientation is solved to obtain the updated characteristic length of the second transition curve segment. This solution process uses an iterative algorithm similar to that used to process the tool tip path, but it needs to consider more constraints, such as avoiding interference between the tool and the workpiece and maintaining a certain cutting angle. Finally, based on the updated characteristic length of the second transition curve segment, the tool orientation data in the machine tool coordinate system is smoothed.This process usually involves interpolation or fitting techniques, such as spherical linear interpolation, to smooth out changes in tool orientation. During processing, special attention needs to be paid to maintaining the continuity of the tool orientation, especially in corners, to avoid surface defects that may be caused by sudden movements of the tool during machining.

[0029] 103. Based on the tool motion trajectory, control the corresponding machine tool equipment to process the arc-shaped workpiece, and during the processing, perform five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool equipment to obtain the actual processing path; In one embodiment of the present invention, based on the tool motion trajectory, the corresponding machine tool equipment is controlled to perform processing on the arc-shaped workpiece, and during the processing, the tool of the machine tool equipment is subjected to five-axis linkage motion control and real-time dynamic compensation to obtain the actual processing path, which includes: interpolating the tool motion trajectory to obtain a discrete tool position point sequence, and calculating the motion parameters of each axis of the machine tool equipment according to the discrete tool position point sequence to obtain a motion instruction sequence of each axis of the machine tool equipment; controlling each axis of the machine tool equipment to perform processing on the arc-shaped workpiece according to the motion instruction sequence, and using high-frequency sampling and arithmetic processing during the processing. The speed sensor monitors the vibration of the machine tool in real time to obtain the vibration data of the machine tool; a dynamic error model of the machine tool is constructed according to the vibration data of the machine tool to obtain the real-time error compensation amount, and the motion instruction sequence is dynamically compensated in real time according to the real-time error compensation amount to obtain the compensated axis motion instruction; the movement of each axis of the machine tool is controlled according to the compensated axis motion instruction, and the actual motion state of each axis is recorded by a high-precision encoder to obtain the actual axis position data; based on the actual axis position data, the actual spatial position and direction sequence of the tool are obtained through inverse kinematics calculation, and the actual spatial position and direction sequence of the tool are connected into a continuous path to obtain the actual processing path.

[0030] Specifically, we first start with interpolation of the tool motion trajectory, with the goal of converting the continuous theoretical trajectory into a discrete sequence of tool position points. Interpolation processing usually uses numerical control (NC) interpolation algorithms, such as linear interpolation, circular interpolation, or spline interpolation, and the specific choice depends on the geometric characteristics of the trajectory. For example, for a complex turbine blade, it may be necessary to combine linear interpolation and high-order spline interpolation to accurately describe its complex surface. After obtaining the discrete sequence of tool position points, the next step is to calculate the motion parameters of each axis of the tool machine. This process involves converting the tool position in the workpiece coordinate system to the position of each axis in the machine tool coordinate system, and the kinematic characteristics of the machine tool need to be considered. For a five-axis machine tool, this usually includes the calculation of three linear axes (X, Y, Z) and two rotary axes (such as A and C axes). Through inverse kinematics calculation, the position of each axis of the machine tool corresponding to each discrete point can be obtained, thereby generating a sequence of motion instructions for each axis of the machine tool. With the motion instruction sequence, the machine tool control system can begin to control the motion of each axis and actually process the arc-shaped workpiece. However, in order to ensure machining accuracy, real-time monitoring and dynamic compensation are also required during the machining process. Here, high-frequency sampling accelerometers are used to monitor machine tool vibration in real time. These sensors are usually installed at key locations such as the spindle or worktable. For example, when machining aircraft engine blades, a three-axis accelerometer may be installed on the spindle to capture vibration information in different directions. These sensors can capture the tiny vibrations of the machine tool at a very high sampling rate (usually several thousand hertz to tens of thousands of hertz), thereby obtaining detailed machine tool vibration data. Based on the obtained machine tool vibration data, the next step is to build a dynamic error model for the machine tool. This model aims to describe the deviation between the actual position and the theoretical position of the machine tool due to factors such as vibration and thermal deformation during the movement of the machine tool. The model is usually constructed using data-driven methods such as time series analysis, neural networks, or Kalman filtering. Through this model, the real-time error compensation amount can be predicted and obtained. After obtaining the error compensation amount, the original motion instruction sequence needs to be compensated in real time and dynamically. This process is usually carried out in the CNC system of the machine tool, and the predicted error compensation amount is superimposed on the original motion instruction to obtain the compensated axis motion instruction. For example, if the model predicts that the X-axis will have a positive deviation of 5 microns at a certain moment, the compensation instruction will add a negative compensation of 5 microns to the original instruction. The movement of each axis of the machine tool is controlled according to the compensated axis motion instruction, and the actual movement status of each axis is recorded using a high-precision encoder. These encoders are usually installed directly on each moving axis of the machine tool and can record the actual position of the axis with a very high resolution (up to nanometers). Through continuous recording, detailed actual axis position data can be obtained. Finally, based on the recorded actual axis position data, the actual spatial position and orientation sequence of the tool in the workpiece coordinate system can be reconstructed through inverse kinematics calculation.This calculation process essentially converts the axis position in the machine coordinate system back to the tool position and orientation in the workpiece coordinate system. For five-axis machine tools, this involves complex geometric transformations that require consideration of the specific structure and kinematic characteristics of the machine tool. After obtaining the actual spatial position and orientation sequence of the tool, these discrete points are connected into a continuous path to obtain the actual processing path. This connection process usually uses spline fitting or other curve fitting techniques to ensure the continuity and smoothness of the path.

[0031] 104. Perform multi-sensor fusion dynamic tracking measurement on the workpiece surface along the actual processing path to obtain real-time contour data; In one embodiment of the present invention, it is first necessary to install multiple types of sensors on the machine tool, generally including laser displacement sensors, contact probes and visual sensors. For example, when processing a complex turbine blade, a high-precision laser displacement sensor can be installed near the spindle to measure the surface profile, while a contact probe can be installed near the tool to verify the key dimensions, and then a high-speed camera can be used to detect surface defects. These sensors move along the actual processing path during the processing process and synchronously collect data on the workpiece surface. The laser displacement sensor can quickly obtain surface profile information, the contact probe can perform precise measurements at specific locations, and the visual sensor can capture surface texture and possible processing defects. These different types of data need to be integrated through sensor fusion algorithms, and commonly used methods include Kalman filtering, Bayesian fusion, etc. The measurement accuracy and characteristics of each sensor need to be considered during the fusion process, such as the high sampling rate of the laser sensor but may be affected by surface reflection, and the high precision of the contact probe but with fewer measurement points. Through multi-sensor fusion, more comprehensive and accurate real-time profile data can be obtained. These data include not only the geometric shape of the workpiece surface, but also surface quality information. For example, when processing aircraft engine blades, the fused data can simultaneously reflect the blade's contour accuracy, surface roughness, and whether there are processing marks or tiny cracks.

[0032] 105. Based on the real-time contour data, multi-spectral imaging is used to evaluate the surface quality of the workpiece to obtain a comprehensive quality score, and the processing parameters of the processing operation are adjusted in real time based on the comprehensive quality score.

[0033] In one embodiment of the present invention, performing multispectral imaging evaluation on the surface quality of the workpiece according to the real-time contour data to obtain a comprehensive quality score, and adjusting the processing parameters of the processing operation in real time according to the comprehensive quality score includes: performing multi-band spectral imaging on the workpiece surface to obtain multispectral image data including visible light, near-infrared and ultraviolet bands; performing image segmentation and feature extraction on the multispectral image data to obtain texture features, gloss features and defect features of the workpiece surface; fusing the real-time contour data with the texture features, gloss features and defect features to obtain comprehensive surface feature data; analyzing the comprehensive surface feature data using a pre-trained deep learning model to obtain a quantitative evaluation result of the workpiece surface quality; calculating the comprehensive score of the workpiece surface quality according to the quantitative evaluation result and preset quality standards to obtain a comprehensive quality score; constructing a processing parameter optimization model based on the comprehensive quality score to obtain a processing parameter adjustment strategy, and adjusting the processing parameters of the processing operation in real time according to the processing parameter adjustment strategy.

[0034] Specifically, first, multi-band spectral imaging is performed on the workpiece surface, which usually involves the use of multiple light sources with different wavelengths and corresponding sensors. For example, when processing a high-precision aircraft engine turbine blade, a visible light camera can be used to capture the macroscopic morphology of the surface, a near-infrared camera can be used to detect possible thermal stress distribution, and an ultraviolet camera can be used to identify tiny surface cracks. These image data in different bands together constitute a rich multispectral image data set. After obtaining the multispectral image data, the next step is to perform image segmentation and feature extraction. Image segmentation can use techniques such as region growing, edge detection, or deep learning segmentation networks to divide the image into different regions. Feature extraction involves calculating various image features, such as texture features (which can use methods such as grayscale co-occurrence matrices or local binary patterns), gloss features (by analyzing surface reflection characteristics), and defect features (such as identifying surface scratches or pits through morphological operations). For example, in the processing of turbine blades, the texture directionality of the blade surface can be extracted to evaluate the processing quality, the surface reflection intensity can be analyzed to judge the finish, and any irregular shapes can be identified to detect potential processing defects. Next, the real-time profile data is fused with the extracted texture features, gloss features, and defect features. This process involves complex data alignment and registration, because data from different sources may have different resolutions and coordinate systems. Data fusion can use methods such as Dempster-Shafer evidence theory or fuzzy logic to integrate different types of data into a comprehensive surface feature dataset. With the comprehensive surface feature data, a pre-trained deep learning model is used for analysis. This model can be a complex convolutional neural network or a system that integrates multiple sub-networks, trained on a large dataset of historical machining data. The input of the model is the comprehensive surface feature data, and the output is the quantitative evaluation result of the workpiece surface quality, including multiple indicators such as surface roughness prediction and defect probability distribution. Based on the quantitative evaluation results and the preset quality standards, the comprehensive score of the workpiece surface quality is calculated. This scoring system can use weighted summation or more complex multi-criteria decision-making methods to integrate various quality indicators into a single score. For example, for turbine blades, different weights may be given to surface roughness, shape accuracy, and defect degree to calculate the final comprehensive quality score. Finally, a machining parameter optimization model is constructed based on the comprehensive quality score. The goal of this model is to find the best combination of machining parameters to improve the current machining quality. This optimization model can be built using techniques such as genetic algorithms, particle swarm optimization, or reinforcement learning. The model takes into account the current machining parameters (such as cutting speed, feed rate, cutting depth, etc.) and the quality score, and outputs a set of optimized parameter recommendations. For example, if the surface roughness of a certain area of ​​the blade is found to exceed the standard, the model will recommend reducing the feed rate or increasing the coolant flow in that area.

[0035] In this embodiment, the curvature distribution data and adaptive segmentation results of the workpiece surface are obtained by performing three-dimensional scanning and curvature analysis on the curved workpiece. Based on the above data, a tool motion trajectory is generated. Based on the trajectory, the machine tool equipment is controlled to perform processing operations on the curved workpiece. At the same time, the actual processing path is obtained through five-axis linkage motion control and real-time dynamic compensation. Multi-sensor fusion dynamic tracking measurement is performed on the workpiece surface along the actual processing path to obtain real-time contour data. According to the real-time contour data, the surface quality of the workpiece is evaluated, a comprehensive quality score is generated, and the processing parameters are adjusted in real time according to the score. Through three-dimensional scanning and curvature analysis, this method can accurately obtain the curvature data of the workpiece surface, ensure the rationality of the processing path, make the tool motion trajectory more accurate, reduce tool wear, and improve processing accuracy.

[0036] The above describes the automatic processing method of the arc-shaped workpiece in the embodiment of the present invention. The following describes the automatic processing device of the arc-shaped workpiece in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an automatic processing device for arc-shaped workpieces includes: The scanning and analysis module 201 is used to perform 3D scanning and curvature analysis on the curved workpiece to obtain curvature distribution data and adaptive segmentation results on the workpiece surface; A trajectory smoothing module 202 is used to perform asynchronous B-spline curve smoothing on the workpiece processing path according to the curvature distribution data and the adaptive segmentation result to obtain a tool motion trajectory; The processing module 203 is used to control the corresponding machine tool equipment to process the arc-shaped workpiece based on the tool motion trajectory, and during the processing of the processing, the tool of the machine tool equipment is subjected to five-axis linkage motion control and real-time dynamic compensation to obtain an actual processing path; Tracking module 204, used to perform multi-sensor fusion dynamic tracking measurement on the workpiece surface along the actual processing path to obtain real-time contour data; The adjustment module 205 is used to perform multi-spectral imaging evaluation on the workpiece surface quality according to the real-time profile data to obtain a comprehensive quality score, and to adjust the processing parameters of the processing operation in real time according to the comprehensive quality score.

[0037] In an embodiment of the present invention, the automated processing device for arc-shaped workpieces runs the automated processing method for arc-shaped workpieces described above, and the automated processing device for arc-shaped workpieces obtains curvature distribution data and adaptive segmentation results of the workpiece surface by performing three-dimensional scanning and curvature analysis on the arc-shaped workpiece. According to the above data, a tool motion trajectory is generated. Based on the trajectory, the machine tool equipment is controlled to perform processing operations on the arc-shaped workpiece, and at the same time, the actual processing path is obtained through five-axis linkage motion control and real-time dynamic compensation. The workpiece surface is subjected to multi-sensor fusion dynamic tracking measurement along the actual processing path to obtain real-time contour data. According to the real-time contour data, the surface quality of the workpiece is evaluated, a comprehensive quality score is generated, and the processing parameters are adjusted in real time according to the score. Through three-dimensional scanning and curvature analysis, this method can accurately obtain the curvature data of the workpiece surface, ensure the rationality of the processing path, make the tool motion trajectory more accurate, reduce tool wear, and improve processing accuracy.

[0038] above Figure 2 The automated processing device for the middle arc-shaped workpiece in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the automated processing equipment for the arc-shaped workpiece in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0039] Figure 3 3 is a schematic diagram of the structure of an automatic processing device for arc-shaped workpieces provided by an embodiment of the present invention. The automatic processing device 300 for arc-shaped workpieces may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more mass storage device terminals) storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 may be temporary storage or permanent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the automatic processing device 300 for arc-shaped workpieces. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the automatic processing device 300 for arc-shaped workpieces to implement the steps of the above-mentioned automatic processing method for arc-shaped workpieces.

[0040] The automatic processing equipment 300 for arc-shaped workpieces may further include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The structure of the automated processing equipment for arc-shaped workpieces shown does not constitute a limitation on the automated processing equipment for arc-shaped workpieces provided by the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0041] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the automated processing method for arc-shaped workpieces.

[0042] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0043] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or 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, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0044] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automated processing method for arc-shaped workpieces, characterized in that: The automated processing method for the arc-shaped workpiece comprises: Perform all-round 3D scanning and curvature analysis on the curved workpiece to obtain the curvature distribution data and adaptive segmentation results of the workpiece surface; According to the curvature distribution data and the adaptive segmentation result, the workpiece processing path is subjected to asynchronous B-spline curve smoothing to obtain a tool motion trajectory; Based on the tool motion trajectory, control the corresponding machine tool equipment to perform processing operations on the arc-shaped workpiece, and during the processing of the processing, perform five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool equipment to obtain an actual processing path; Along the actual processing path, multi-sensor fusion dynamic tracking measurement is performed on the workpiece surface to obtain real-time contour data; Based on the real-time profile data, a multi-spectral imaging evaluation is performed on the surface quality of the workpiece to obtain a comprehensive quality score, and the processing parameters of the processing operation are adjusted in real time based on the comprehensive quality score.

2. The automated processing method for arc-shaped workpieces according to claim 1, characterized in that: The method of performing 3D scanning and curvature analysis on the curved workpiece to obtain curvature distribution data and adaptive segmentation results of the workpiece surface includes: Performing multi-angle laser scanning on the surface of the arc-shaped workpiece to obtain point cloud data, wherein the multi-angle laser scanning includes scanning operations at at least three different angles; Performing denoising and gridding processing on the point cloud data to obtain a three-dimensional grid model, and performing curvature calculation on the three-dimensional grid model to obtain the principal curvature and Gaussian curvature of each grid node in the three-dimensional grid model; Generate and calculate curvature distribution data of the workpiece surface according to the principal curvature and Gaussian curvature, and calculate the curvature change rate of each grid node according to the curvature distribution data to obtain a curvature change rate distribution map; According to the curvature change rate distribution map and a preset threshold, a region growing algorithm is used to adaptively segment the workpiece surface to obtain an adaptive segmentation result.

3. The automated processing method for arc-shaped workpieces according to claim 2, characterized in that: The step of performing denoising and gridding on the point cloud data to obtain a three-dimensional grid model, and performing curvature calculation on the three-dimensional grid model to obtain the principal curvature and Gaussian curvature of each grid node in the three-dimensional grid model includes: Performing noise reduction processing and statistical analysis on the point cloud data to obtain point cloud density distribution, and adaptively sampling the point cloud data according to the point cloud density distribution to obtain uniform point cloud data; Using a preset Delaunay triangulation algorithm to perform gridding processing on the homogenized point cloud data to obtain a three-dimensional grid model, and constructing a local coordinate system for each vertex in the three-dimensional grid model to obtain a neighborhood local representation of each vertex; In the local coordinate system, a quadratic surface fitting is performed on the neighborhood local representation of the corresponding vertex to obtain a local surface equation, and the principal curvature and Gaussian curvature of each mesh node are calculated based on the coefficients of the local surface equation.

4. The automated processing method for arc-shaped workpieces according to claim 1, characterized in that: The step of performing asynchronous B-spline curve smoothing on the workpiece machining path according to the curvature distribution data and the adaptive segmentation result to obtain the tool motion trajectory comprises: Determine the key corner positions of the workpiece processing path according to the curvature distribution data and the adaptive segmentation result, and obtain a set of corners that need to be smoothed, wherein the workpiece processing path includes a tool tip path and tool direction data; For each corner in the corner set, based on local curvature information in the curvature distribution data, two asymmetric B-spline curves are calculated; Inserting the two asymmetric B-spline curves into corresponding corners of the tool tip path and tool direction data corresponding to the corners, respectively, to obtain a first transition curve and a second transition curve segment; According to the first transition curve and the second transition curve segment, the tool tip path and the tool direction data are respectively smoothed to obtain a smoothed tool tip path and a smoothed tool direction data; The tool motion trajectory is obtained by combining the smoothed tool tip path and the smoothed tool direction data.

5. The automated processing method for arc-shaped workpieces according to claim 4, characterized in that: The step of smoothing the tool tip path and the tool direction data according to the first transition curve and the second transition curve segment to obtain the smoothed tool tip path and the smoothed tool direction data comprises: Performing overlap detection on the first transition curves of adjacent corners to obtain a potential overlap area of ​​the tool tip path, and constructing an optimization model based on the potential overlap area to obtain an optimization objective function of the tool tip path by minimizing the local minimum speed difference at adjacent corners; Solving the optimization objective function of the tool tip path by using an iterative algorithm to obtain a characteristic length of the updated first transition curve, and smoothing the tool tip path according to the characteristic length of the updated first transition curve to obtain a smoothed tool tip path; The tool direction data is converted into the machine tool coordinate system of the machine tool equipment to obtain the tool direction data in the machine tool coordinate system, and an optimization model of the tool direction is constructed according to the tool direction data in the machine tool coordinate system and the second transition curve segment to obtain an optimization objective function of the tool direction; The optimization objective function of the tool direction is solved to obtain the characteristic length of the updated second transition curve segment, and based on the characteristic length of the updated second transition curve segment, the tool direction data in the machine tool coordinate system is smoothed to obtain the smoothed tool direction data.

6. The automated processing method for arc-shaped workpieces according to claim 1, characterized in that: Based on the tool motion trajectory, the corresponding machine tool equipment is controlled to perform processing on the arc-shaped workpiece, and during the processing, the tool of the machine tool equipment is subjected to five-axis linkage motion control and real-time dynamic compensation to obtain the actual processing path, which includes: Performing interpolation processing on the tool motion trajectory to obtain a discrete tool position point sequence, and calculating the motion parameters of each axis of the machine tool equipment according to the discrete tool position point sequence to obtain a motion instruction sequence of each axis of the machine tool equipment; According to the motion instruction sequence, each axis of the machine tool equipment is controlled to perform processing operation on the arc-shaped workpiece, and during the processing operation, the vibration of the machine tool is monitored in real time by using a high-frequency sampling acceleration sensor to obtain the vibration data of the machine tool; According to the machine tool vibration data, a machine tool dynamic error model is constructed to obtain a real-time error compensation amount, and according to the real-time error compensation amount, real-time dynamic compensation is performed on the motion instruction sequence to obtain a compensated axis motion instruction; Controlling the movement of each axis of the machine tool according to the compensated axis movement command, and using a high-precision encoder to record the actual movement state of each axis to obtain actual axis position data; Based on the actual axis position data, the actual spatial position and direction sequence of the tool are obtained through inverse kinematics calculation, and the actual spatial position and direction sequence of the tool are connected into a continuous path to obtain the actual processing path.

7. The automated processing method for arc-shaped workpieces according to claim 1, characterized in that: The step of performing multispectral imaging evaluation on the surface quality of the workpiece according to the real-time profile data to obtain a comprehensive quality score, and adjusting the processing parameters of the processing operation in real time according to the comprehensive quality score includes: Perform multi-band spectral imaging on the workpiece surface to obtain multi-spectral image data including visible light, near infrared and ultraviolet bands; Performing image segmentation and feature extraction on the multispectral image data to obtain texture features, gloss features and defect features of the workpiece surface; Fusing the real-time contour data with the texture features, gloss features and defect features to obtain comprehensive surface feature data; Analyzing the comprehensive surface feature data using a pre-trained deep learning model to obtain a quantitative evaluation result of the workpiece surface quality; Calculate the comprehensive score of the workpiece surface quality according to the quantitative evaluation results and the preset quality standard to obtain a comprehensive quality score; Based on the comprehensive quality score, a processing parameter optimization model is constructed to obtain a processing parameter adjustment strategy, and the processing parameters of the processing operation are adjusted in real time according to the processing parameter adjustment strategy.

8. An automated processing device for arc-shaped workpieces, characterized in that: The automatic processing device for arc-shaped workpieces comprises: Scanning and analysis module, used to perform all-round 3D scanning and curvature analysis on the curved workpiece, and obtain the curvature distribution data and adaptive segmentation results of the workpiece surface; A trajectory smoothing module is used to perform asynchronous B-spline curve smoothing on the workpiece processing path according to the curvature distribution data and the adaptive segmentation result to obtain a tool motion trajectory; A processing module, which is used to control the corresponding machine tool equipment to process the arc-shaped workpiece based on the tool motion trajectory, and during the processing of the processing, perform five-axis linkage motion control and real-time dynamic compensation on the tool of the machine tool equipment to obtain an actual processing path; A tracking module, used to perform multi-sensor fusion dynamic tracking measurement on the workpiece surface along the actual processing path to obtain real-time contour data; The adjustment module is used to perform multi-spectral imaging evaluation on the surface quality of the workpiece according to the real-time profile data to obtain a comprehensive quality score, and to adjust the processing parameters of the processing operation in real time according to the comprehensive quality score.

9. An automated processing device for arc-shaped workpieces, characterized in that: The automatic processing equipment for arc-shaped workpieces comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the automated processing equipment for arc-shaped workpieces to execute the steps of the automated processing method for arc-shaped workpieces as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of the automated processing method for arc-shaped workpieces as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Dynamic control method for complex curved surface five-axis numerical control machining tool vector

    CN119596847A

  • Visual guidance variable curvature airfoil skin robot fairing processing path generation method

    CN119871443A

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

    CN119871443B

  • Method and system for processing a tube

    CN120572179A

  • Cold working process parameter optimization and plate rolling control method and system based on artificial intelligence

    CN120734148A