Processing method and device, electronic equipment and medium

Abstract

The invention provides a processing method and device, electronic equipment and a medium, and relates to the technical field of visual guidance processing, and the method comprises the steps: determining the path point curvature of each path point according to the processing path information of a processed workpiece obtained through preprocessing; according to the path point curvature of each path point, clustering to obtain a plurality of primitive decomposition nodes, and distributing each path point to the plurality of primitive decomposition nodes to obtain a plurality of path primitives; performing testability analysis of path conversion on line laser of a processing device for processing a workpiece based on the plurality of path elements; when the machining device has testability, the machining device is controlled to machine the machined workpiece according to the multiple path elements, fine disassembly of the machining path is achieved, testability analysis of line laser path conversion is carried out based on the path elements, and when the testability of the machining device is guaranteed, the machining device is accurately controlled to work. And the machining precision and efficiency are improved.

Description

Technical Field

[0001] This disclosure relates to the field of visually guided processing technology, and in particular to a processing method, apparatus, electronic device and medium. Background Technology

[0002] In the field of intelligent manufacturing, visual guidance is a means of deep integration of computer vision technology and automated processing. It uses visual sensors to collect images or depth information of the workpiece, and through algorithm analysis and path planning, guides the equipment to complete high-precision operations. Edge processing is an important process in the manufacturing industry for the specific treatment of the edges of workpieces. It is widely used in the manufacturing fields of sheet metal, mechanical parts, etc., and covers a variety of processes such as beveling and edge trimming.

[0003] Current vision-guided processing solutions in related technologies mainly acquire images or depth information of the object to be processed through vision sensors, and combine them with algorithm analysis and path planning to guide measurement or processing equipment to complete high-precision operations.

[0004] However, the processing schemes of related technologies lack edge analysis based on path primitive decomposition, resulting in insufficiently refined path planning and affecting processing accuracy and efficiency. Summary of the Invention

[0005] This disclosure provides a processing method, apparatus, electronic device, and medium to solve problems in related technologies. By determining the curvature of path points, clustering primitive decomposition nodes, and allocating path primitives, it achieves a fine decomposition of the processing path and conducts a measurability analysis of line laser path conversion based on path primitives. Under the premise of ensuring the measurability of the processing device, it accurately controls the processing device to perform operations, effectively solving the problem of imprecise path planning in related technologies, significantly improving processing accuracy and efficiency, and providing a more efficient and reliable technical path for vision-guided edge processing technology.

[0006] The first aspect of this disclosure provides a processing method, which includes: determining the path point curvature of each path point based on the processing path information of the workpiece obtained through preprocessing; clustering multiple primitive decomposition nodes based on the path point curvature of each path point, and assigning each path point to the multiple primitive decomposition nodes to obtain multiple path primitives; performing a testability analysis on the path conversion of the line laser of the processing device for the workpiece based on the multiple path primitives; and controlling the processing device to process the workpiece according to the multiple path primitives when the processing device is testable.

[0007] In some embodiments of this disclosure, determining the path point curvature of each path point based on the preprocessed workpiece processing path information includes: obtaining a set of path points corresponding to the processing path information based on the preprocessed workpiece processing path information; and determining the path point curvature of each path point based on the path point set.

[0008] In some embodiments of this disclosure, determining the path point curvature of each path point based on the path point set includes: obtaining the set of nearest neighbor path points of the first path point in the path point set, and constructing a nearest neighbor matrix of the first path point based on the first path point and the set of nearest neighbor path points; and decomposing the nearest neighbor matrix of the first path point based on a preset decomposition algorithm to obtain the path point curvature of the first path point.

[0009] In some embodiments of this disclosure, clustering multiple primitive decomposition nodes based on the path point curvature of each path point includes: determining multiple curvature-weighted center points corresponding to the path point set based on the path point curvature of each path point; and determining multiple primitive decomposition nodes based on the distance between each path point and the multiple curvature-weighted center points.

[0010] In some embodiments of this disclosure, the measurability analysis of path conversion of the line laser of the processing device for processing workpiece based on multiple path primitives includes: adjusting the safety angle of the processing device to obtain the target measurement range of the processing device; determining the edge processing type according to the processing sequence based on the target measurement range and multiple path primitives; and performing a measurability analysis of path conversion of the line laser of the processing device according to the edge processing type.

[0011] In some embodiments of this disclosure, adjusting the safety angle of the processing device to obtain the target measurement range of the processing device includes: establishing a measurement range model of the processing device; and adjusting the safety angle of the processing device according to the measurement range model to obtain the target measurement range of the processing device.

[0012] In some embodiments of this disclosure, controlling the processing device to process the workpiece according to multiple path primitives includes: determining the rate of change of the processing device at each path point; and sending an alarm based on the rate of change of each path point and a rate of change threshold at each path point, and controlling the processing device to stop processing.

[0013] In some embodiments of this disclosure, an alarm is pushed and the processing device is controlled to stop processing based on the rate of change of each path point and the rate of change threshold of each path point. The previous method includes: establishing a uniform edge processing model based on multiple primitive decomposition nodes, determining the target allowable rate of change of each path point; and determining the rate of change threshold of each path point based on the target allowable rate of change.

[0014] A second aspect of this disclosure provides a processing apparatus, the apparatus comprising:

[0015] The determining unit is used to determine the path point curvature of each path point based on the machining path information of the workpiece obtained from preprocessing.

[0016] The decomposition unit is used to cluster multiple primitive decomposition nodes based on the path point curvature of each path point, and to assign each path point to multiple primitive decomposition nodes to obtain multiple path primitives.

[0017] The analysis unit is used to perform measurability analysis of the path transformation of the line laser of the processing device for processing workpieces based on multiple path primitives.

[0018] A processing unit is used to control the processing device to process the workpiece according to multiple path elements when the processing device is measurable.

[0019] A third aspect of this disclosure provides an electronic device including: a processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, performs the method described in the first aspect of this disclosure.

[0020] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first aspect of this disclosure.

[0021] A fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the methods described in the first aspect of this disclosure.

[0022] In summary, according to the processing method proposed in this disclosure, the path point curvature of each path point is determined based on the processing path information of the workpiece obtained through preprocessing. Multiple primitive decomposition nodes are clustered based on the path point curvature of each path point, and each path point is assigned to these nodes to obtain multiple path primitives. Based on these multiple path primitives, a testability analysis of the path conversion of the line laser of the processing device is performed. When the processing device is testable, it is controlled to process the workpiece according to the multiple path primitives, achieving a fine decomposition of the processing path. Furthermore, a testability analysis of the line laser path conversion is conducted based on the path primitives. This ensures the testability of the processing device while precisely controlling its operation, significantly improving processing accuracy and efficiency, and providing a more efficient and reliable processing path for vision-guided edge processing technology.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0025] Figure 1 A flowchart of a processing method provided in an embodiment of this disclosure;

[0026] Figure 2 A flowchart of another processing method provided in this disclosure embodiment;

[0027] Figure 3 An edge processing centerline laser camera imaging device is provided as an embodiment of this disclosure;

[0028] Figure 4 This is a schematic diagram illustrating the measurability analysis of a workpiece transitioning from a straight line to an arc, provided in an embodiment of this disclosure.

[0029] Figure 5 A schematic diagram illustrating the measurability analysis of a workpiece's circular arc to a straight line, provided in an embodiment of this disclosure;

[0030] Figure 6 This is a schematic diagram illustrating the measurability analysis during arc cutting, provided as an embodiment of the present disclosure.

[0031] Figure 7 A schematic diagram illustrating a specific processing method provided in an embodiment of this disclosure;

[0032] Figure 8 This is a schematic diagram of the structure of a processing apparatus provided in an embodiment of the present disclosure;

[0033] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0034] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments are described below with reference to the accompanying drawings.

[0035] In the field of intelligent manufacturing, vision guidance is a means of deeply integrating computer vision technology with automated processing. It guides measurement or processing equipment to complete high-precision operations by combining image or depth information of the object being processed acquired by vision sensors with algorithm analysis and path planning. Edge processing is an important process in manufacturing, referring to specific treatments applied to the edges of workpieces to meet functional, aesthetic, or connection requirements. This type of processing is widely used in sheet metal, mechanical parts, composite materials, and mold manufacturing, including processes such as beveling, edge trimming, and planing.

[0036] In recent years, with the increasing demands for intelligence and efficiency in the industrial processing of major equipment by intelligent manufacturing, traditional manual operation and single machine tool processing methods have become insufficient to meet the production needs of complex and precision products. To address this challenge, the introduction of intelligent equipment has become a key trend, among which machine vision measurement technology has emerged as a crucial means to improve operational efficiency. As the core of intelligent autonomous decision-making in processing systems, vision-guided perception systems have gradually improved equipment inspection and error monitoring processes that previously required manual intervention, significantly enhancing system efficiency and safety. Therefore, designing a processing system based on a vision-guided perception system is a core challenge in current industrial intelligent manufacturing.

[0037] Edge machining is a critical process in the manufacturing of complex components for major equipment, specifically including beveling, edge trimming, and planing. Manual edge machining suffers from low efficiency and large errors, while robotic edge machining has limitations in application scope and measurability. Especially for various types of large-sized irregularly shaped workpieces, the "scan-then-machine" approach requires significantly more time and cannot handle unexpected events during machining. The "scan-while-machine" approach requires consideration of the detector's ability to follow the machining tool.

[0038] Currently, vision-guided processing solutions still treat the measurement system as an auxiliary measurement tool, and its system intelligence advantages are not fully integrated with the processing system. The system structure design and structured light vision measurement technology of related technologies have laid a good framework foundation for intelligent edge processing in industry. However, it places extremely high demands on the overall structural design of the hardware and software systems and the intelligent configuration of algorithms. These technologies mainly acquire images or depth information of the processing object through vision sensors, combined with algorithm analysis and path planning, to guide measurement or processing equipment to complete high-precision operations.

[0039] However, the processing methods in the related technologies still have the following drawbacks:

[0040] 1) The lack of edge analysis based on path primitive decomposition in related technologies results in insufficiently refined path planning, affecting processing accuracy and efficiency;

[0041] 2) The installation of the processing equipment in the relevant technologies has not been optimized, the measurement range is limited, and when processing large or complex workpieces, incomplete visual coverage is likely to occur, reducing processing accuracy;

[0042] 3) Related technologies do not perform global measurability analysis on features such as notches on the workpiece edge, which can easily lead to machining errors;

[0043] 4) The processing speed control of related technologies is insufficient, and there is a lack of real-time speed monitoring. Improper speed can easily lead to a decline in processing quality.

[0044] To address the aforementioned issues, the processing method disclosed herein acquires known edge processing path information, determines the curvature of path points, and clusters them to obtain path primitives. This achieves refined edge analysis based on path primitive decomposition, effectively improving the accuracy of path planning and thus enhancing processing precision and efficiency. Utilizing the simple geometric structures of multiple types of path primitives, a vision-guided edge processing scheme is constructed, transforming the overall problem into a transfer problem between primitives. In the process of path conversion measurability analysis of the line laser processing device, this disclosure optimizes the installation angle of the processing device, maximizes the measurement range, abandons the single angle of structured light cameras in related technologies, expands measurement capabilities, and avoids a decrease in processing precision due to incomplete visual coverage. Simultaneously, through global measurability analysis and velocity threshold protection detection, the measurable edge surface types are constrained, enhancing processing stability and predicting the operation process, reducing the failure rate, and ensuring processing quality.

[0045] The processing method provided in this application will be described in detail below with reference to the accompanying drawings.

[0046] Figure 1 A flowchart illustrating a processing method provided in an embodiment of this disclosure. Figure 1 As shown, the processing method includes steps 101-104.

[0047] Step 101: Determine the path point curvature of each path point based on the machining path information of the workpiece obtained from preprocessing.

[0048] In the embodiments of this disclosure, path information of a workpiece with a given edge is obtained, and a linear point cloud set of edge-dense three-dimensional point cloud path is obtained, based on the curvature information of each path point.

[0049] Here, path point curvature is a quantitative representation of the degree of curvature at a point on the path. In two-dimensional space, this disclosure can calculate the rate of change of the tangent direction of the curve at that point to obtain the curvature; in three-dimensional space, this disclosure needs to consider the change of the normal vector of the surface.

[0050] A linear point cloud is a collection of points that are discretely distributed in space. These points are obtained by 3D scanning of the workpiece edge, and adjacent points are connected by line segments to form a continuous processing path.

[0051] The curvature of path points reflects the geometric characteristics of a path. For example, the curvature of a straight section is 0, while the curvature of an arc is inversely proportional to its radius. This disclosure provides a basis for identifying path primitives, such as straight lines and arcs, by determining the curvature of path points.

[0052] Step 102: Based on the path point curvature of each path point, cluster to obtain multiple primitive decomposition nodes, and assign each path point to multiple primitive decomposition nodes to obtain multiple path primitives.

[0053] In the embodiments of this disclosure, local path mutation point information is obtained as path primitive decomposition nodes through a preset clustering algorithm, resulting in path primitives primarily composed of straight lines and arcs. The preset clustering algorithm refers to an adaptive quadratic clustering algorithm. That is, this disclosure can randomly select a starting point for clustering, obtain cluster centers through an adaptive quadratic clustering algorithm, and repeat the operation until no new cluster centers appear within multiple iterations. At this point, the set of all cluster centers becomes the primitive decomposition nodes, and different path primitives are obtained by assigning path points between different primitive decomposition nodes.

[0054] In this context, primitive decomposition nodes refer to points on the path where the curvature changes abruptly. These points serve as boundaries between different types of path primitives, such as the connection points between straight lines and arcs. Path primitives are the basic building blocks of a path, primarily consisting of straight lines and arcs. Adaptive quadratic clustering is an algorithm that first performs preliminary clustering and then optimizes the clustering results based on curvature characteristics.

[0055] In this disclosure, since different processing strategies are applicable to different types of path primitives, it is necessary to decompose the path. This clustering algorithm can automatically identify locations with significant curvature changes, i.e., path decomposition nodes, and then divide the path into multiple path primitives with consistent geometric properties.

[0056] Step 103: Based on multiple path primitives, perform a testability analysis on the path conversion of the line laser of the processing device for processing the workpiece.

[0057] In the embodiments of this disclosure, the target measurement range of the camera in the processing device is calculated based on the transformation between the path primitives B obtained above. The processing device refers to the vision guidance system, and the target measurement range refers to the maximum measurement range of the camera. The distance between the camera and the processing point is known, and the linear motion of different primitives at the decomposition nodes has different requirements on the camera measurement range. Based on the maximum measurement requirement, the camera measurement model is optimized. By adjusting the installation angle, the system is optimized within the measurable range to achieve the theoretical maximum measurement range L of the camera and meet the overall edge measurement range requirements.

[0058] Based on the maximum measurement range after camera optimization, analyze all edge processing types in the path primitives, calculate the local maximum measurement requirements, and give the maximum range requirements for path measurement for all edge processing type conversions. By analyzing the primitives classified as straight lines and various types of arcs, determine whether the camera measurement system meets the visual guidance requirements for the edge processing of the workpiece.

[0059] Among these, the measurability analysis of path transitions assesses whether the machining device can continuously track the machining point as it transitions from one path element to the next. The machining device, or vision guidance system, is a system that uses a camera to monitor the machining position in real time, thereby providing positioning information for the machining tool. The maximum measurement range of the camera refers to the maximum spatial range that the camera can clearly image given its installation position and angle.

[0060] In this disclosure, when the machining tool transitions between different primitives, such as from a straight line to an arc, the position and angle of the path point relative to the camera change. Therefore, it is necessary to calculate the camera's measurement range requirements for this path transition and to ensure that the path point remains within the camera's measurement range throughout the entire machining path by optimizing the camera's mounting parameters.

[0061] Step 104: When the processing device is measurable, control the processing device to process the workpiece according to multiple path elements.

[0062] In the embodiments of this disclosure, after the measurability analysis is completed and it is confirmed that the processing device meets the measurability performance in the workpiece edge processing process, the processing tool in the processing device is controlled to operate at a constant speed along the transformation sequence of the path primitives until all path primitive iteration detection operations are completed.

[0063] Among them, measurability means that the path points can be effectively observed by the camera throughout the entire processing process, and there will be no situation that exceeds the camera's measurement range.

[0064] After confirming that the camera can track the machining path throughout the entire process, the machining tools in the machining device can perform machining according to the pre-decomposed path primitives. Because the geometric characteristics within the same primitive are consistent, a uniform speed machining method can be adopted, which helps to ensure the stability of machining quality.

[0065] In summary, according to the processing method proposed in this disclosure, the path point curvature of each path point is determined based on the processing path information of the workpiece obtained through preprocessing. Multiple primitive decomposition nodes are clustered based on the path point curvature of each path point, and each path point is assigned to these nodes to obtain multiple path primitives. Based on these multiple path primitives, a testability analysis of the path conversion of the line laser of the processing device is performed. When the processing device is testable, it is controlled to process the workpiece according to the multiple path primitives, achieving a fine decomposition of the processing path. Furthermore, a testability analysis of the line laser path conversion is conducted based on the path primitives. This ensures the testability of the processing device while precisely controlling its operation, significantly improving processing accuracy and efficiency, and providing a more efficient and reliable processing path for vision-guided edge processing technology.

[0066] Figure 2 A flowchart of another processing method provided by an embodiment of this disclosure is further illustrated. Based on Figure 1 The illustrated embodiment further explains steps 101 and 102 in step 103. Figure 2 This may include the following steps:

[0067] Step 201: Based on the processing path information of the workpiece obtained from preprocessing, obtain the set of path points corresponding to the processing path information.

[0068] In the embodiments of this disclosure, the present disclosure can extract all discrete coordinate points constituting the path from the obtained processing path information by performing preliminary data processing on the workpiece (such as CAD model analysis, trajectory planning algorithm calculation, etc.), forming an ordered set of points (i.e. the path point set in this disclosure). Each point in the set represents a position node on the processing path, which is used for subsequent path analysis, motion control or simulation verification and other operations.

[0069] Step 202: Determine the path point curvature of each path point based on the set of path points.

[0070] In embodiments of this disclosure, the nearest neighbor set of a first path point in a set of path points can be obtained, and a nearest neighbor matrix of the first path point can be constructed based on the first path point and the nearest neighbor set. The nearest neighbor matrix of the first path point is then decomposed using a preset decomposition algorithm to obtain the path point curvature of the first path point. Here, the first path point refers to any randomly selected path point in the set of path points. This disclosure requires that the path point curvature of each path point in the set be calculated using the above method.

[0071] Specifically, this disclosure can obtain a set of linear point clouds along a dense 3D point cloud path (i.e., a set of path points) and calculate the curvature of each path point.

[0072] For example, to obtain path point p i The set of nearest neighbor path points P in the path point set E ′ ={p n |‖p n -p i ||≤r p}, thus constructing path point p i The nearest neighbor matrix M:

[0073]

[0074] Where m is the set of nearest neighbor path points P ′ The number of point clouds, point p i ∈E, r p For x iThe neighborhood radius of the set of nearest neighbor path points, p n It is the nearest neighbor path point in this neighborhood, with a neighborhood radius r. p All points within the range form the set of nearest neighbor path points.

[0075] Then, the nearest neighbor matrix M = UDV is decomposed using the singular value decomposition algorithm (i.e., the default decomposition algorithm in this disclosure). T D is a diagonal matrix, and U and V are both unitary matrices. The eigenvalues ​​of the diagonal elements in the sorted D are obtained as λ_1>λ_2>λ_3. The minimum value λ_3 is the point cloud curvature of the current path point, i.e., the curvature of the path point.

[0076] Step 203: Determine multiple curvature-weighted center points corresponding to the path point set based on the path point curvature of each path point.

[0077] In embodiments of this disclosure, a path point from any set of path points E can be randomly initialized as the starting p. s and its corresponding set of nearest neighbor path points p n And obtain the path point p according to the method in step 201 above. s curvature C i Calculate the curvature-weighted centers within the set of all path points.

[0078] Step 204: Based on the distance between each path point and multiple curvature weighted center points, determine multiple primitive decomposition nodes, and assign each path point to multiple primitive decomposition nodes to obtain multiple path primitives.

[0079] In embodiments of this disclosure, the nearest path point p to the curvature-weighted center point can be selected. m The new cluster center is selected. The algorithm terminates and outputs the cluster center, i.e., the primitive decomposition node, when the offset between the new cluster center and the previous cluster center is less than a preset offset threshold.

[0080] After obtaining the primitive decomposition node corresponding to one of the path points, return to randomly initialize one of the path points in the arbitrary set E as the starting p. s and the set of nearest path points p n And calculate the curvature C through its corresponding path points. i The corresponding primitive decomposition node is determined again. When no new primitive decomposition node can be obtained after a preset number of iterations (e.g., 10 times), the clustering ends.

[0081] Step 205: Adjust the safety angle of the processing device to obtain the target measurement range of the processing device.

[0082] In the embodiments of this disclosure, a measurement range model of the processing device can be established; based on the measurement range model, the safety angle of the processing device is adjusted to obtain the target measurement range (i.e., the maximum measurement range) of the processing device.

[0083] like Figure 3 The image shown is a line laser camera imaging device for edge processing provided in this disclosure. The edge processing line laser camera imaging device consists of a line laser generator and a line laser camera. Ignoring the angle between the two, the measurement of the workpiece is as follows... Figure 3 As shown in (a), the measurement geometry model of the vertically installed structure can be simplified to... Figure 3 (b) Wherein, the laser emission and reception point of the line laser camera imaging device is point A, the line laser field of view is trapezoid BCED, the far field of view is BC, the near field of view is DE, the measurement range is the distance DF between the far field of view and the near field of view, the perpendicular bisector is the distance AG from point A to the far field of view, the angle θ between DC and BC, and the angle between AG and CD. The maximum measurement range L of the line laser camera imaging device. When the type of line laser camera is determined, the field of view length and measurement distance are fixed and known, i.e., the near field of view length a = |DE|, the far field of view length c = |BC|, the distance from point A to the near field of view b, and the distance from point A to the far field of view d. Under vertical installation, the maximum measurement range L is the far field of view |BC|.

[0084] Based on the structured light camera measurement model (i.e. measurement range model) established above, the optimal installation angle of the camera is adjusted. Since the parameters of the line laser camera imaging device are fixed, if it is necessary to expand the maximum measurement range L, the installation angle of the line laser camera imaging device can be optimized so that the angle between the perpendicular bisector and the workpiece is α, that is, |CD| is the maximum measurement range L.

[0085] Therefore, considering the maximum measurement range L, there are two cases: |BC| and |CD|. The larger of the two should be taken. Figure 3 (b) can be calculated That is, to judge The relationship with 1. When Right now When |CD|≤|BC|, L=|BC|; when Right now When |CD|>|BC|, When |CD| is greater than |BC|, the improved installation angle of the line laser camera described above can expand the field of view for visually guided edge processing measurements.

[0086] It can also be calculated using lengths a, b, c, and d. When |CD| is greater than |BC|, that is At this time, by improving the installation angle of the line laser camera as described above, the field of view for vision-guided edge processing measurement can be expanded. The distance from the line laser camera to the workpiece plane is then...

[0087] Step 206: Based on the target measurement range and multiple path primitives, determine the edge processing type according to the processing sequence.

[0088] In the embodiments of this disclosure, the maximum measurement range L is obtained through the above-described camera optimization, and the edge type, i.e. the edge processing type, is determined according to the processing order by classifying different paths obtained by path primitive decomposition.

[0089] Step 207: Perform a testability analysis on the path conversion of the line laser of the processing device according to the edge processing type.

[0090] In the embodiments of this disclosure, the disclosure can classify and discuss the conversion between straight lines and arcs in edge processing type, analyze the followability of line laser on workpieces with different edge shapes, confirm the measurability of the edge conversion, and perform measurability analysis (i.e., followability analysis) on all path conversions until the measurability analysis of all path conversions is completed.

[0091] In one optional embodiment of this disclosure, the detection path is used to determine whether the edge conforms to the curve from a straight line. For ease of analysis, the analysis can be simplified to two cases: the curve is a circle or an ellipse. The analysis of the concave and convex curves is similar. The limit measurement range requirement of the processing device is then calculated.

[0092] In one optional embodiment of this disclosure, when detecting whether the workpiece edge conforms to the transition from an arc to a straight line, the analysis is simplified to two cases: the arc is a circle and an ellipse. The line laser camera guides the movement, and the cutting tool follows, moving along the edge where the cutting tool is located. When the change angle is ≥90°, the line laser camera cannot image on the workpiece, creating a sudden change with the subsequent straight-line cutting. Therefore, only the case where the change angle is <90° is considered. The limit measurement range requirements of the processing device are calculated.

[0093] In one optional embodiment of this disclosure, when the detection path conforms to the workpiece and the workpiece edges move on the arc, the analysis of both circular and elliptical cases can be simplified, and the limit measurement range requirements of the processing device can be calculated.

[0094] Preferably, detecting whether the path conforms to the edge changing from a straight line to an arc specifically involves:

[0095] The detection path checks whether the edge follows a straight line to an arc. For ease of analysis, the analysis can be simplified to two cases: the arc is a circle and an ellipse. The cases for concave and convex arcs are similar. The following images all show concave arcs. Figure 4The diagram shown illustrates a measurability analysis of a workpiece transitioning from a straight line to an arc, as provided in this disclosure. To ensure the maximum measurement range does not exceed the workpiece edge, multiple scenarios are considered. These scenarios include a circle radius of r, an ellipse with a major axis of 2a, a minor axis of 2b, a chord length of 2x, a line laser distance of d from the cutting point, and a distance L from the point the line laser needs to scan to the cutting direction. min We will classify and discuss the types of arcs:

[0096] a. such as Figure 4 As shown in (a), when the transformation angle is 90°, i.e. the straight line passes through the center of the circle, the maximum measurement range of the linear laser must be satisfied. The maximum measurement range L of the line laser when the convex arc change angle is 90° is consistent with this case.

[0097] b. Figure 4 As shown in (b), when the change angle is <90°, the maximum measurement range of the line laser must be satisfied. The maximum measurement range L of the line laser when the convex arc change angle is less than 90° is consistent with this case.

[0098] c. For example Figure 4 As shown in (c), when the transformation angle is >90°, the maximum measurement range of the line laser must be satisfied. The maximum measurement range L of a line laser when the convex arc transformation angle is >90° is consistent with this case.

[0099] d. such as Figure 4 As shown in (d), when the change angle is 90°, the maximum measurement range of the line laser needs to be satisfied. The maximum measurement range L of the line laser when the convex arc change angle is 90° is consistent with this case.

[0100] e. such as Figure 4 As shown in (e), when the change angle is <90°, the maximum measurement range of the line laser must be satisfied. The maximum measurement range L of the line laser when the convex arc change angle is less than 90° is consistent with this case.

[0101] f. such as Figure 4 As shown in (f), when the transformation angle is >90°, the maximum measurement range of the line laser must be satisfied. The maximum measurement range L of a line laser when the convex arc transformation angle is >90° is consistent with this case.

[0102] Preferably, the detection path conforms to the workpiece, and the workpiece edges move on the arc. Specifically, this means:

[0103] A simplified model of the workpiece edge transitions from an arc to a straight line. The analysis covers two cases: arcs that are circles and ellipses. The cases for concave and convex arcs are similar. Figure 5The figure shows a schematic diagram of the measurable analysis of the circular arc to the straight line of the workpiece provided by the present disclosure.

[0104] To ensure that the maximum measurement range does not exceed the edge of the workpiece, various situations are considered during the cutting process of the arc to the straight line transformation angle. Among them, the radius of the circle is r, the length of the long axis of the ellipse is 2a, the length of the short axis is 2b, the chord length is 2x, the distance from the line laser to the cutting point is d, and the distance from the point that the line laser needs to scan to the cutting direction is L min :

[0105] 1. The maximum measurement range of the line laser required for the circle to the straight line

[0106] 2. In the case of the ellipse to the straight line, a coordinate system is established with the center of the ellipse. The abscissa of the transformation point from the arc to the straight line is x0, and the maximum measurement range of the line laser required

[0107] Preferably, to detect whether the detection path conforms to the workpiece, the edges of the workpiece move on the arc specifically as:

[0108] When analyzing that the edges of the workpiece move on the arc, the analysis of the two cases of the circle and the ellipse can be simplified. For example Figure 6 The figure shows a schematic diagram of the measurable analysis during the arc cutting provided by the present disclosure. Here, two solutions are given for the two categories of the circle and the arc:

[0109] a. During the arc cutting process, to ensure that the maximum measurement range does not exceed the edge of the workpiece, for the circle, it needs to satisfy Therefore and r > d;

[0110] b. For the ellipse, it needs to satisfy d < a and d < b.

[0111] Step 208, when the processing device has measurability, control the processing device to process the workpiece according to multiple path elements.

[0112] In the embodiment of the present disclosure, the present disclosure can fit the path points p in the path point set E point by point c The tangent slope is k c . Calculate the tangent direction measurement point p of the cutting point p c +k c *D perpendicular to the intersection point p of the path E c *D perpendicular to the intersection point p of the path E m . Detect that the distance from p m to the tangent satisfies the maximum measurement range of the processing device, and determine that the processing device has measurability.

[0113] When the control processing device processes the workpiece according to multiple path elements, this disclosure needs to determine the rate of change of the processing device at each path point; based on the rate of change of each path point and the rate of change threshold of each path point, an alarm is pushed and the processing device is controlled to stop processing.

[0114] The process of triggering an alarm and stopping the processing device based on the rate of change and a threshold value for each path point includes: establishing a uniform edge processing model based on multiple primitive decomposition nodes; determining the target allowable rate of change (i.e., the maximum allowable rate of change) for each path point; and determining the rate of change threshold for each path point based on the target allowable rate of change. The rate of change threshold for each path point can be K times the target allowable rate of change for each path point. K can be set according to actual conditions and is not limited in this embodiment.

[0115] In summary, this disclosure addresses the challenge of determining the machining status for edge milling of workpiece notches (referring to welding of automotive sheet metal) after initial preprocessing (path point set sampling). By introducing a line laser-guided sensing and measurement system, the system can proactively perceive the measurement status ahead of the cutting point, ensuring real-time adjustments to system decisions and preventing errors from jeopardizing the overall machining process. Therefore, the system can independently complete the milling task without human intervention. This overcomes the limitations of related edge machining methods, which suffer from insufficient manual efficiency and weak decision-making capabilities of dedicated machines. It eliminates the need for handling detection tasks and error termination. Utilizing vision-guided measurement, it achieves excellent results in various edge milling models, particularly in workpiece edge milling where other methods struggle to achieve advantages.

[0116] based on Figure 1 , Figure 2 The illustrated embodiments, such as Figure 7 As shown, this disclosure provides a schematic diagram of a specific processing method.

[0117] Reference Figure 7 This disclosure obtains the machining path information of a workpiece with a given edge (refer to...). Figure 3 (Gap path), obtain the set of path points corresponding to the gap path. Based on the set of path points, determine the path point curvature of each path point. According to the path point curvature of each path point, obtain local path abrupt change point information as path primitive decomposition nodes through an adaptive quadratic clustering algorithm, and obtain path primitives including lines and arcs as the main types.

[0118] Adjust the safety angle of the processing device to obtain the maximum measurement range of the processing device; based on the maximum measurement range and multiple path primitives, determine the edge processing type according to the processing sequence; according to the edge processing type, perform a measurability analysis on the path conversion of the line laser of the processing device, calculate the local maximum measurement requirement, give the maximum range requirement of path measurement for all types of conversion, and analyze whether the camera measurement system meets the visual guidance requirements for the edge processing of the workpiece by analyzing the primitives classified as straight lines and various types of arcs.

[0119] After the above measurability analysis is completed and the vision-guided system is confirmed to meet the measurability requirements of the workpiece edge processing process, a robot uniform-speed edge processing model is established based on all path primitives, and the change rate threshold of path points is calculated. When any path point is detected to be greater than its corresponding change rate threshold, an error is reported and the processing system is stopped immediately to ensure operational safety. When no error command is detected, the processing tool in the processing device will operate at a uniform speed along the transformation sequence of the path primitives until all primitive iterations are completed.

[0120] Corresponding to the methods provided in the above embodiments, this disclosure also provides a processing apparatus. Since the apparatus provided in this disclosure corresponds to the methods provided in the above embodiments, the implementation of the methods is also applicable to the apparatus provided in this embodiment, and will not be described in detail in this embodiment.

[0121] Figure 8 This is a schematic diagram of the structure of a processing apparatus 800 provided in an embodiment of this disclosure. Figure 8 As shown, the processing apparatus includes:

[0122] The determining unit 810 is used to determine the path point curvature of each path point based on the machining path information of the workpiece obtained from preprocessing.

[0123] Decomposition unit 820 is used to cluster multiple primitive decomposition nodes based on the path point curvature of each path point, and to assign each path point to multiple primitive decomposition nodes to obtain multiple path primitives.

[0124] Analysis unit 830 is used to perform measurability analysis of the path conversion of the line laser of the processing device for processing workpieces based on multiple path primitives;

[0125] The machining unit 840 is used to control the machining device to process the workpiece according to multiple path elements when the machining device is measurable.

[0126] In some embodiments of this disclosure, the determining unit 810 is configured to: obtain a set of path points corresponding to the processing path information based on the processing path information of the preprocessed workpiece; and determine the path point curvature of each path point based on the set of path points.

[0127] In some embodiments of this disclosure, the determining unit 810 is configured to: obtain the set of nearest neighbor path points of the first path point in the path point set, and construct the nearest neighbor matrix of the first path point based on the first path point and the set of nearest neighbor path points; decompose the nearest neighbor matrix of the first path point based on a preset decomposition algorithm to obtain the path point curvature of the first path point.

[0128] In some embodiments of this disclosure, the decomposition unit 820 is configured to: determine multiple curvature-weighted center points corresponding to the path point set based on the path point curvature of each path point; and determine multiple primitive decomposition nodes based on the distance between each path point and the multiple curvature-weighted center points.

[0129] In some embodiments of this disclosure, the analysis unit 830 is used to: adjust the safety angle of the processing device to obtain the target measurement range of the processing device; determine the edge processing type according to the processing sequence based on the target measurement range and multiple path primitives; and perform a measurability analysis of the path conversion of the line laser of the processing device according to the edge processing type.

[0130] In some embodiments of this disclosure, the analysis unit 830 is used to: establish a measurement range model of the processing device; and adjust the safety angle of the processing device according to the measurement range model to obtain the target measurement range of the processing device.

[0131] In some embodiments of this disclosure, the processing unit 840 is configured to: determine the rate of change of the processing device at each path point; and, based on the rate of change of each path point and a threshold value for the rate of change of each path point, send an alarm and control the processing device to stop processing.

[0132] In some embodiments of this disclosure, the processing unit 840 is configured to: push an alarm based on the rate of change of each path point and a rate of change threshold of each path point and control the processing device to stop processing, wherein a uniform edge processing model is established based on multiple primitive decomposition nodes before determining the target allowable rate of change of each path point; and determine the rate of change threshold of each path point based on the target allowable rate of change.

[0133] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0134] Figure 9This is a block diagram illustrating an electronic device 900 for implementing the above-described processing method according to an exemplary embodiment. For example, the electronic device 900 may be a mobile phone, computer, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0135] Reference Figure 9 The electronic device 900 may include a communication interface 901, capable of interacting with other devices; a processor 902, connected to the communication interface 901 to enable interaction with other devices, used to execute the methods provided by one or more of the above-described technical solutions when running a computer program; and a memory 903, on which the computer program is stored. Specifically, the specific processing procedure of the processor 902 can refer to the processing methods described in the above embodiments of this disclosure.

[0136] Of course, in practical applications, the various components in electronic device 900 are coupled together through bus system 904. It can be understood that bus system 904 is used to realize the connection and communication between these components. In addition to a data bus, bus system 904 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 9 The general labeled all buses as Bus System 904.

[0137] The memory 903 in this embodiment is used to store various types of data to support the operation of the electronic device 900. Examples of such data include any computer program used to operate on the electronic device 900.

[0138] The methods disclosed in the embodiments of this application can be applied to processor 902, or implemented by processor 902. Processor 902 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 902 or by instructions in the form of software. The processor 902 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 902 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 903. Processor 902 reads the information in memory 903 and combines its hardware to complete the steps of the aforementioned method.

[0139] In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0140] Embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the processing methods described in the above embodiments of this disclosure.

[0141] Embodiments of this disclosure also provide a computer program product, including a computer program that is executed by a processor using the processing methods described in the above embodiments of this disclosure.

[0142] Embodiments of this disclosure also provide a chip including one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of an electronic device and send signals to the processors, the signals including computer instructions stored in the memory, which, when executed by the processor, cause the electronic device to perform the processing methods described in the above embodiments of this disclosure.

[0143] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0144] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0145] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0146] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0147] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0148] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0149] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0150] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A processing method, characterized in that, The method includes: Based on the machining path information of the workpiece obtained from preprocessing, determine the path point curvature of each path point; Based on the path point curvature of each path point, multiple primitive decomposition nodes are clustered to obtain multiple primitive decomposition nodes, and each path point is assigned to the multiple primitive decomposition nodes to obtain multiple path primitives; Based on the multiple path primitives, a testability analysis of the path conversion of the line laser of the processing device for processing the workpiece is performed. When the processing device is measurable, the processing device is controlled to process the workpiece according to the plurality of path primitives.

2. The method according to claim 1, characterized in that, The step of determining the path point curvature of each path point based on the machining path information of the workpiece obtained through preprocessing includes: Based on the processing path information of the workpiece obtained from preprocessing, obtain the set of path points corresponding to the processing path information; Based on the set of path points, the path point curvature of each path point is determined.

3. The method according to claim 2, characterized in that, The determination of the path point curvature for each path point based on the set of path points includes: Obtain the set of nearest neighbor path points of the first path point in the set of path points, and construct the nearest neighbor matrix of the first path point based on the first path point and the set of nearest neighbor path points; Based on a preset decomposition algorithm, the nearest neighbor matrix of the first path point is decomposed to obtain the path point curvature of the first path point.

4. The method according to claim 1, characterized in that, The step of clustering multiple primitive decomposition nodes based on the path point curvature of each path point includes: Based on the path point curvature of each path point, determine multiple curvature-weighted center points corresponding to the set of path points; The plurality of primitive decomposition nodes are determined based on the distance between each path point and the plurality of curvature-weighted center points.

5. The method according to claim 1, characterized in that, The measurability analysis of the path conversion of the line laser of the processing device for processing the workpiece based on the multiple path primitives includes: Adjust the safety angle of the processing device to obtain the target measurement range of the processing device; Based on the target measurement range and the multiple path primitives, the edge processing type is determined according to the processing sequence; Based on the edge processing type, a testability analysis is performed on the path conversion of the line laser of the processing device.

6. The method according to claim 5, characterized in that, The adjustment of the safety angle of the processing device to obtain the target measurement range of the processing device includes: Establish a measurement range model for the processing device; Based on the measurement range model, the safety angle of the processing device is adjusted to obtain the target measurement range of the processing device.

7. The method according to claim 1, characterized in that, The control of the processing device to process the workpiece according to the plurality of path primitives includes: Determine the rate of change of the processing device at each path point; An alarm is triggered based on the rate of change of each path point and the threshold value of the rate of change of each path point, and the processing device is controlled to stop processing.

8. A processing apparatus, characterized in that, The device includes: The determining unit is used to determine the path point curvature of each path point based on the machining path information of the workpiece obtained from preprocessing. The decomposition unit is used to cluster multiple primitive decomposition nodes based on the path point curvature of each path point, and to assign each path point to the multiple primitive decomposition nodes to obtain multiple path primitives. An analysis unit is used to perform a testability analysis of the path conversion of the line laser of the processing device for processing the workpiece based on the multiple path primitives. A processing unit is used to control the processing device to process the workpiece according to the plurality of path primitives when the processing device is measurable.

9. An electronic device, characterized in that, include: A processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, performs the method of any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images