Laser cleaning method and system suitable for complex special-shaped component

Abstract

The invention relates to the technical field of laser cleaning, in particular to a laser cleaning method and system suitable for a complex special-shaped component, and the method comprises the following steps: building a three-dimensional grid model of the complex special-shaped component; based on the three-dimensional grid model, segmentation is carried out according to the vertical direction and the horizontal direction in sequence in consideration of curvature changes of the surface of the complex special-shaped component, and corresponding segmentation models are obtained; generating laser cleaning path nodes based on the segmentation model, and performing iterative calculation according to a selected optimization algorithm to generate an optimal laser cleaning path; and a laser is driven to conduct cleaning operation along the optimal laser cleaning path, in the operation process, the laser cleaning effect is monitored synchronously, and relevant control parameters are dynamically adjusted according to the laser cleaning effect, so that the cleaning effect is ensured. By means of the method, efficient, uniform and lossless cleaning of the surfaces of the complex special-shaped components can be achieved.

Description

Technical Field

[0001] This invention relates to the field of laser cleaning technology, and specifically to a laser cleaning method and system suitable for complex irregularly shaped components. Background Technology

[0002] Complex, irregularly shaped components, such as aircraft engine blades, automobile engine cylinder heads, and molds, are currently widely used in high-precision manufacturing. The surfaces of these components typically possess intricate geometries and minute features. Due to their complex shapes and precise manufacturing requirements, surface cleaning processes are particularly crucial. Currently, traditional cleaning techniques, such as chemical cleaning, primarily utilize chemical methods and reagents to remove dirt from the surfaces of these complex components. However, this method struggles to achieve effective cleaning without damaging the surface.

[0003] Laser cleaning technology is an advanced surface cleaning method that uses a high-energy laser beam to irradiate the surface of an object, causing impurities and contaminants to evaporate or peel off rapidly through optical and thermal effects. However, laser cleaning technology still faces the following challenges when processing complex and irregularly shaped components:

[0004] 1. Uneven laser cleaning: Due to the diversity of surface geometry of complex irregular components, traditional laser path planning methods are difficult to cover all areas, resulting in uneven cleaning effect;

[0005] 2. Low cleaning efficiency: Precise path planning and control on the surface of complex irregular components requires a large amount of computing resources, resulting in low cleaning efficiency.

[0006] 3. Risk of surface damage: Improper adjustment of laser power and scanning speed may lead to over-cleaning or damage to the surface.

[0007] Therefore, in order to address the above problems, it is necessary to propose a new and efficient laser cleaning method for the surface of complex irregular components to achieve efficient, uniform and non-destructive cleaning results. Summary of the Invention

[0008] To achieve efficient, uniform, and non-destructive cleaning of complex, irregularly shaped components, the present invention aims to provide a laser cleaning method and system suitable for such components. The specific technical solution adopted is as follows:

[0009] Firstly, this application discloses a laser cleaning method applicable to complex irregularly shaped components, the method comprising:

[0010] S1. Establish a three-dimensional mesh model of complex irregular components;

[0011] S2. Based on the three-dimensional mesh model, the mesh is divided sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model.

[0012] S3. Generate the laser cleaning path nodes based on the segmentation model, and perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path;

[0013] S4. Drive the laser to perform cleaning operations along the optimal laser cleaning path, and monitor the laser cleaning effect simultaneously during the operation, and dynamically adjust the relevant control parameters accordingly to ensure the cleaning effect.

[0014] Furthermore, in step S1, establishing the three-dimensional mesh model of the complex irregular component includes:

[0015] S11. Obtain point cloud data of the surface of complex irregular-shaped components;

[0016] S12. Calculate the centroid coordinates based on all points in the point cloud data. For each point in the point cloud data, calculate its distance to the centroid, and remove points whose centroid distance is greater than a preset threshold as noise points from the point cloud data.

[0017] S13. The orientation of the point cloud is adjusted based on the PCA principal component analysis method, and the surface reconstruction technology is used to generate the corresponding three-dimensional mesh model.

[0018] Further, in step S2, based on the three-dimensional mesh model, the model is sequentially divided according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain a corresponding segmentation model, including:

[0019] S21. In the vertical direction, based on the vertical cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the three-dimensional mesh model is divided according to the height direction to obtain multiple vertical slices with consistent levels.

[0020] S22. Based on each of the vertical slices, perform circular projection transformation to obtain the corresponding projection transformation slices;

[0021] S23. In the horizontal direction, based on the horizontal cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the obtained projection transformation slices are divided to obtain corresponding horizontal slices.

[0022] S24. Based on each level slice, the corresponding segmentation model is obtained.

[0023] Furthermore, in step S2, when analyzing the curvature changes of the surface of complex irregular-shaped components, the method further includes:

[0024] For each point on the three-dimensional mesh model, curvature analysis is performed using discrete differential geometry.

[0025] Based on the obtained curvature analysis results, a corresponding curvature distribution map is generated, and based on the curvature distribution map, high curvature regions and flat regions are identified and divided.

[0026] Furthermore, in step S3, generating the laser cleaning path nodes based on the segmentation model and performing iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path includes:

[0027] S31. Based on the segmentation model, the cleaning surface is discretized into multiple key points, and these key points are used as path nodes for laser cleaning.

[0028] S32. Construct a path planning model and perform iterative calculations using the selected optimization algorithm. During the calculation process, set up a multi-scan method for complex areas to perform path planning.

[0029] S33. Determine the shortest path through all key points, and after smoothing the shortest path, use it as the optimal laser cleaning path.

[0030] Furthermore, in step S4, during the operation, the laser cleaning effect is monitored synchronously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect, including:

[0031] S41. Obtain cleaning parameters monitored by a preset high-precision optical sensor, wherein the cleaning parameters include at least one of laser reflected light intensity and surface temperature;

[0032] S42. Based on the cleaning parameters, the relevant control parameters are dynamically adjusted through a preset control strategy to ensure the cleaning effect. The relevant control parameters include at least one of laser power, scanning speed, and path planning parameters.

[0033] Secondly, this application discloses a laser cleaning system suitable for complex irregularly shaped components. The system includes a three-dimensional mesh model construction module, a model segmentation module, a laser cleaning path planning module, and a cleaning operation control module, wherein:

[0034] The three-dimensional mesh model construction module is used to build a three-dimensional mesh model of complex irregular components;

[0035] The model segmentation module is used to segment the three-dimensional mesh model sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model.

[0036] The laser cleaning path planning module is used to generate laser cleaning path nodes based on the segmentation model, and to perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path.

[0037] The cleaning operation control module is used to drive the laser to perform cleaning operations along the optimal laser cleaning path. During the operation, the laser cleaning effect is monitored simultaneously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect.

[0038] Thirdly, this application discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the laser cleaning method applicable to complex irregularly shaped components.

[0039] Fourthly, this application discloses a laser cleaning device suitable for complex irregularly shaped components, including a communication interface, a memory, a communication bus, and a processor, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0040] The memory is used to store computer programs;

[0041] When the processor executes the program stored in the memory, it implements the steps of the laser cleaning method applicable to complex irregularly shaped components.

[0042] The present invention has the following beneficial effects:

[0043] 1. By establishing a three-dimensional mesh model of complex irregular components, the shape and surface features of the complex irregular components can be accurately reflected, providing an accurate basis for subsequent segmentation and path planning.

[0044] 2. During the segmentation process, not only the vertical and horizontal directions are considered, but special attention is also paid to the curvature changes of the surface of complex irregular components. This helps to generate a segmentation model that better fits the actual shape of the complex irregular components, thereby improving the accuracy and comprehensiveness of the cleaning path.

[0045] 3. By using a segmentation model to generate path nodes for laser cleaning and iteratively calculating through an optimization algorithm, the shortest or optimal path passing through all key points can be found. This optimized path can significantly reduce the ineffective movement of the laser and improve cleaning efficiency.

[0046] 4. During the cleaning process, the laser cleaning effect is monitored simultaneously, and the relevant control parameters of the laser are dynamically adjusted based on the monitoring results. This real-time adjustment mechanism ensures consistent and high-quality cleaning results, avoiding problems such as incomplete or over-cleaning caused by improper parameters. Attached Figure Description

[0047] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a laser cleaning method for complex irregularly shaped components, provided as an embodiment of the present invention;

[0049] Figure 2 This is a system structure diagram of a laser cleaning system for complex irregularly shaped components, provided as an embodiment of the present invention. Detailed Implementation

[0050] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a laser cleaning method and system suitable for complex irregular-shaped components proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0052] The following description, in conjunction with the accompanying drawings, details a specific solution for a laser cleaning method and system applicable to complex irregularly shaped components provided by the present invention.

[0053] Please see Figure 1 The diagram illustrates a flowchart of a laser cleaning method for complex irregularly shaped components according to an embodiment of the present invention. The method includes:

[0054] Step S1: Establish a three-dimensional mesh model of the complex irregular component.

[0055] Specifically, this application will acquire point cloud data of complex irregular components and construct a corresponding three-dimensional mesh model based on the point cloud data. For specific implementation details, please refer to the following embodiments, which will not be described in detail here.

[0056] Step S2: Based on the three-dimensional mesh model, the model is divided sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model.

[0057] Specifically, in the vertical direction, this application automatically divides the 3D mesh model of complex irregular components into multiple vertical slices with consistent height, based on the vertical cleaning range of the laser. The segmentation algorithm considers local curvature variations on the surface of the complex irregular components to ensure uniformity in height for each vertical slice. Then, for each vertical slice, this application performs a ring projection transformation (the specific transformation method can be found in subsequent embodiments). Currently, this is mainly based on the horizontal scanning range of the laser, further dividing the vertical slice into multiple horizontal segments. This ring segmentation process considers surface curvature variations to ensure uniform coverage on the horizontal plane.

[0058] Step S3: Generate path nodes for laser cleaning based on the segmentation model, and perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path.

[0059] Specifically, for each path node, this application will utilize a selected optimization algorithm (such as...) The algorithm (including genetic algorithm) generates the optimal laser cleaning path. The optimization algorithm considers factors such as surface curvature, slice shape, and cleaning parameters (e.g., laser power, scanning speed) to ensure the path's rationality and the uniformity of cleaning.

[0060] Step S4: Drive the laser along the optimal laser cleaning path to perform the cleaning operation. During the operation, monitor the laser cleaning effect simultaneously and dynamically adjust the relevant control parameters accordingly to ensure the cleaning effect.

[0061] Specifically, during the laser cleaning operation, this application utilizes a high-precision optical sensor to monitor the laser cleaning effect in real time. Specifically, this application receives parameters such as laser reflected light intensity and surface temperature monitored by the high-precision optical sensor, and dynamically adjusts relevant control parameters such as laser power, scanning speed, and path planning based on this received monitoring data to ensure the stability and consistency of the cleaning effect.

[0062] As described above, the laser cleaning method disclosed in this application, applicable to complex irregular-shaped components, accurately reflects the shape and surface features of these components by establishing a three-dimensional mesh model, providing a precise basis for subsequent segmentation and path planning. During segmentation, not only vertical and horizontal directions are considered, but special attention is paid to the curvature changes of the complex irregular-shaped component's surface. This helps generate a segmentation model that more closely matches the actual shape of the component, thereby improving the accuracy and comprehensiveness of the cleaning path. The segmentation model is used to generate path nodes for laser cleaning, and iterative calculations using optimization algorithms can find the shortest or optimal path passing through all key points. This optimized path significantly reduces the ineffective movement of the laser, improving cleaning efficiency. During the cleaning operation, the laser cleaning effect is monitored synchronously, and the relevant control parameters of the laser are dynamically adjusted based on the monitoring results. This real-time adjustment mechanism ensures the consistency and high quality of the cleaning effect, avoiding problems such as incomplete or over-cleaning due to improper parameters.

[0063] In one embodiment, step S1, establishing the three-dimensional mesh model of the complex irregular component, includes:

[0064] Step S11: Obtain point cloud data of the surface of complex irregular-shaped components.

[0065] Specifically, this application uses a high-precision 3D scanner to perform a full-range scan of the surface of complex irregular-shaped components, obtaining corresponding point cloud data. This point cloud data covers every surface detail of the complex irregular-shaped components and has high spatial resolution. It should be noted that during the scanning process, various factors may need to be considered, such as scanning angle, scanning distance, and lighting conditions, to ensure the integrity and accuracy of the data.

[0066] Furthermore, the generation of point cloud data is not limited to physical scanning instruments. It can also use deep learning-based 3D reconstruction technology. Specifically, this method involves inputting multi-angle image data of the surface of a complex irregular component (usually photos taken from different angles by a camera), and then using a deep learning model to perform 3D reconstruction, ultimately obtaining the corresponding point cloud data.

[0067] Step S12: Calculate the centroid coordinates based on all points in the point cloud data. For each point in the point cloud data, calculate its distance to the centroid, and remove points whose centroid distance is greater than a preset threshold as noise points.

[0068] Specifically, based on all points in the point cloud data, this application calculates the centroid coordinates using a weighted average method. It should be noted that the centroid is the geometric center of all points in the point cloud, and its coordinates are a weighted average of all point coordinates. After determining the centroid, for each point in the point cloud data, its Euclidean distance to the centroid is calculated. Finally, a preset threshold is set (this threshold can be set according to the specific conditions of the point cloud data; this application does not impose specific limitations), and when a point's distance to the centroid is determined to be greater than this threshold, it is considered a noise point, and all points identified as noise are removed from the point cloud, thus completing the initial point cloud denoising process.

[0069] Step S13: Adjust the orientation of the point cloud based on the PCA principal component analysis method, and use surface reconstruction technology to generate the corresponding three-dimensional mesh model.

[0070] Specifically, this application uses Principal Component Analysis (PCA) to adjust the orientation of the point cloud, aligning its principal directions with the coordinate axes. Furthermore, if two point clouds require alignment, ICP or other registration techniques are used to find the optimal transformation between them. Finally, a surface reconstruction algorithm (such as Poisson reconstruction) is used to convert the point cloud data into a 3D mesh model.

[0071] In the above embodiments, on the one hand, by centering the data on the centroid and filtering out noise points far from the centroid, the quality of the point cloud data can be significantly improved. On the other hand, the PCA principal component analysis method is used to adjust the orientation of the point cloud so that its main feature directions are aligned with the coordinate axes. This standardization process helps to simplify subsequent data analysis and processing.

[0072] In one embodiment, step S2, based on the three-dimensional mesh model, sequentially dividing it according to the vertical and horizontal directions and considering the curvature changes of the complex irregular component surface to obtain a corresponding segmentation model, includes:

[0073] Step S21: In the vertical direction, based on the vertical cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the three-dimensional mesh model is divided according to the height direction to obtain multiple vertical slices with consistent levels.

[0074] Specifically, this application identifies the maximum dimension of the 3D mesh model in the height direction, and then divides this maximum dimension into multiple height segments according to the vertical cleaning range of the laser. Each height segment corresponds to a vertical slice. This processing method ensures that each vertical slice remains uniform in the height direction, meaning that the height of each vertical slice is approximately equal and within the effective processing range of the laser.

[0075] It should be noted that during the segmentation process, this application analyzes the local curvature changes of the complex irregular component surface. For areas with large curvature, a high-precision segmentation algorithm (such as a recursive subdivision method) is used for finer segmentation. This means that in the height direction, the thickness of the vertical slices will be dynamically adjusted according to the curvature of the complex irregular component surface, rather than a simple equidistant segmentation.

[0076] Step S22: Based on each of the vertical slices, perform a circular projection transformation to obtain the corresponding projection transformation slices.

[0077] Specifically, this application performs a circular projection transformation on each vertical slice, mapping the vertical slice onto a two-dimensional plane in a circular or similar form. The specific principle includes: First, determining a projection center, which depends on the projection requirements. Then, mapping the points on the vertical slice onto the two-dimensional projection plane using a projection transformation matrix. Finally, the resulting projection can be optimized, for example, by adjusting projection parameters to eliminate potential distortions.

[0078] Step S23: In the horizontal direction, based on the horizontal cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the obtained projection transformation slices are divided to obtain corresponding horizontal slices.

[0079] Specifically, the horizontal cleaning range refers to the maximum area that the laser can effectively clean in the horizontal direction. It's important to note that before horizontal slicing, the curvature variation of the complex, irregularly shaped component surface needs to be analyzed, as curvature variations affect the laser cleaning effect. Therefore, for areas with greater curvature, smaller horizontal slices are considered to ensure cleaning quality; while for flat areas, larger horizontal slices can be used to improve cleaning efficiency. Finally, based on the laser's horizontal cleaning range and the curvature variation of the complex, irregularly shaped component surface, each projection transformation slice is further divided into multiple horizontal slices, ensuring that the width of some horizontal slices can adapt to the laser's cleaning range, while also taking into account the impact of curvature variations on the cleaning effect.

[0080] Step S24: Based on each horizontal slice, obtain the corresponding segmentation model.

[0081] Specifically, after the 3D mesh model is vertically divided into multiple horizontal slices, each horizontal slice represents a two-dimensional cross-section of the original 3D mesh model at a preset height. To process these horizontal slices more effectively, this application constructs a corresponding segmentation model based on these horizontal slices.

[0082] In one embodiment, this application also considers refining each horizontal slice after segmentation to ensure that the boundaries of the horizontal slices precisely match the surface features of the complex irregular component. The boundary optimization steps include smoothing and transition processing to avoid boundary effects or cleaning dead zones during the cleaning process.

[0083] In the above embodiments, by analyzing the curvature changes of the surface of complex irregular components and slicing them according to height and horizontal direction, it can be ensured that the laser can accurately target the area to be cleaned during the laser cleaning process, avoiding accidental damage or omission to parts that do not need to be cleaned.

[0084] In one embodiment, in step S2, when analyzing the curvature changes of the surface of complex irregular components, the method further includes: performing curvature analysis for each point on the three-dimensional mesh model using discrete differential geometry; generating a corresponding curvature distribution map based on the obtained curvature analysis results; and identifying and dividing high curvature regions and flat regions based on the curvature distribution map.

[0085] Specifically, this application uses discrete differential geometry to calculate the principal curvature and Gaussian curvature of each point on the 3D mesh model. These curvature analysis results can then be stored in an appropriate data structure for subsequent analysis. For generating the curvature distribution map, this application selects a suitable tool for 3D data visualization, such as VTK or Paraview, and uses color to map the curvature values ​​to different colors, thereby generating an intuitive curvature distribution map. Subsequently, this application sets appropriate thresholds to distinguish between high-curvature regions and flat regions. It should be noted that for high-curvature regions, this application considers using a high-precision subdivision algorithm (such as a recursive subdivision method) to subdivide them into smaller meshes to improve subdivision accuracy. For flat regions, a coarse subdivision method (such as a mesh simplification algorithm) is considered to reduce computational complexity and improve processing efficiency.

[0086] In one embodiment, step S3, which involves generating laser cleaning path nodes based on the segmentation model and performing iterative calculations according to a selected optimization algorithm to generate the optimal laser cleaning path, includes:

[0087] Step S31: Based on the segmentation model, the cleaning surface is discretized into multiple key points, and these key points are used as path nodes for laser cleaning.

[0088] Specifically, when selecting key points on the cleaning surface, it should be ensured that these points can fully cover the cleaning surface, and the distance between adjacent points remains constant. Based on this, this application chooses the equal-area discretization method to select key points. This method specifically divides the cleaning surface into multiple regions of equal area, and uses the center point of each region as the key point. It should be noted that the discretized key points serve as path nodes for laser cleaning. These nodes not only represent the positional information during the cleaning process but also determine the trajectory and sequence of laser cleaning.

[0089] Step S32: Construct a path planning model and perform iterative calculations using the selected optimization algorithm. During the calculation process, a multi-scan method is set for path planning in complex areas.

[0090] Specifically, this application employs path planning based on path nodes. Algorithms, genetic algorithms. Among them, The core idea of ​​the algorithm lies in combining actual cost and heuristic estimation to efficiently search for the optimal path in a graph. Specifically, it calculates the estimated total distance from the current node to the target node through an evaluation function; the genetic algorithm simulates biological evolution processes such as natural selection, heredity, and mutation. In this process, individuals in the population continuously evolve through operations such as fitness evaluation, selection, crossover (hybridization), and mutation, eventually approaching the optimal solution. Since this application does not involve improvements to these algorithms, they will not be discussed in detail here. Furthermore, the complex regions here encompass areas that are difficult to clean, such as high-curvature areas or parts with thick surface deposits. For these areas, this application sets up a multi-scan approach for path planning, removing surface contaminants layer by layer to ensure thorough cleaning.

[0091] Step S33: Determine the shortest path through all key points, and after smoothing the shortest path, use it as the optimal laser cleaning path.

[0092] Specifically, after determining the shortest path, this application also performs a smoothing process. The purpose of this smoothing process is mainly to reduce the vibration and abrupt changes of the laser during its movement, thereby ensuring the stability and continuity of the cleaning process. Since this application does not involve the optimization of the path smoothing process, it will not be elaborated here.

[0093] In one embodiment, this application further optimizes the path to avoid repeated cleaning or missed cleaning in local areas. The optimization methods include: using intelligent algorithmic judgment to ensure that each area is cleaned only once, avoiding resource waste and time consumption caused by repeated cleaning.

[0094] In the above embodiments, iterative calculations using a selected optimization algorithm can find the shortest path through all key points. This optimization calculation method can significantly improve cleaning efficiency and reduce cleaning time. Furthermore, for complex areas, a multi-scan approach is used for path planning. This method ensures that contaminants in complex areas are thoroughly cleaned, avoiding omissions or incomplete cleaning, thereby improving overall cleaning quality.

[0095] In one embodiment, in step S4, during the operation, the laser cleaning effect is monitored synchronously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect, including:

[0096] Step S41: Obtain cleaning parameters monitored by a preset high-precision optical sensor, wherein the cleaning parameters include at least one of laser reflected light intensity and surface temperature.

[0097] Step S42: Based on the cleaning parameters, the relevant control parameters are dynamically adjusted through a preset control strategy to ensure the cleaning effect. The relevant control parameters include at least one of laser power, scanning speed, and path planning parameters.

[0098] Based on steps S41 and S42, it should be noted that the dynamic adjustment of relevant control parameters through a preset control strategy includes: when the reflected light intensity is consistently below a preset threshold, indicating that the current laser power is insufficient to effectively remove dirt, the laser power will be appropriately increased to improve cleaning efficiency. Conversely, when the reflected light intensity suddenly increases or the surface temperature approaches the safe upper limit, the laser power will be reduced to prevent overheating or damage to the material. Furthermore, regarding path planning adjustments, this application dynamically adjusts the scanning path of the laser beam based on real-time data feedback, for example, prioritizing areas with low reflected light intensity (i.e., heavier dirt) or avoiding temperature-sensitive areas. And when it is detected that certain areas have poor cleaning results due to special materials or structures, the rescanning path will be planned or the cleaning strategy adjusted to improve the cleaning effect.

[0099] Please refer to Figure 2 This application discloses a laser cleaning system suitable for complex irregularly shaped components. The system includes a three-dimensional mesh model construction module, a model segmentation module, a laser cleaning path planning module, and a cleaning operation control module, wherein:

[0100] The three-dimensional mesh model construction module is used to build a three-dimensional mesh model of complex irregular components;

[0101] The model segmentation module is used to segment the three-dimensional mesh model sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model.

[0102] The laser cleaning path planning module is used to generate laser cleaning path nodes based on the segmentation model, and to perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path.

[0103] The cleaning operation control module is used to drive the laser to perform cleaning operations along the optimal laser cleaning path. During the operation, the laser cleaning effect is monitored simultaneously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect.

[0104] In one embodiment, the above modules are also used to implement the method as described in any of the foregoing embodiments.

[0105] As described above, the laser cleaning system disclosed in this application, applicable to complex irregular-shaped components, accurately reflects the shape and surface features of these components by establishing a three-dimensional mesh model, providing a precise foundation for subsequent segmentation and path planning. During segmentation, not only vertical and horizontal directions are considered, but special attention is paid to the curvature changes of the complex irregular-shaped component's surface. This helps generate a segmentation model that more closely matches the actual shape of the component, thereby improving the accuracy and comprehensiveness of the cleaning path. The segmentation model is used to generate path nodes for laser cleaning, and iterative calculations using optimization algorithms can find the shortest or optimal path through all key points. This optimized path significantly reduces the ineffective movement of the laser, improving cleaning efficiency. During the cleaning operation, the laser cleaning effect is monitored synchronously, and the relevant control parameters of the laser are dynamically adjusted based on the monitoring results. This real-time adjustment mechanism ensures the consistency and high quality of the cleaning effect, avoiding problems such as incomplete or over-cleaning due to improper parameters.

[0106] This application also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the laser cleaning method applicable to complex irregularly shaped components.

[0107] As can be seen from the above, the computer-readable storage medium disclosed in this application can accurately reflect the shape and surface features of complex irregular components by establishing a three-dimensional mesh model, providing an accurate basis for subsequent segmentation and path planning. During the segmentation process, not only the vertical and horizontal directions are considered, but special attention is paid to the curvature changes of the complex irregular component's surface. This helps generate a segmentation model that more closely matches the actual shape of the complex irregular component, thereby improving the accuracy and comprehensiveness of the cleaning path. The segmentation model is used to generate path nodes for laser cleaning, and iterative calculations through optimization algorithms can find the shortest or optimal path through all key points. This optimized path can significantly reduce the ineffective movement of the laser and improve cleaning efficiency. During the cleaning operation, the laser cleaning effect is monitored synchronously, and the relevant control parameters of the laser are dynamically adjusted based on the monitoring results. This real-time adjustment mechanism ensures the consistency and high quality of the cleaning effect, avoiding problems such as incomplete or over-cleaning due to improper parameters.

[0108] This application also discloses a laser cleaning device suitable for complex irregular-shaped components, including a communication interface, a memory, a communication bus, and a processor, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0109] The memory is used to store computer programs;

[0110] When the processor executes the program stored in the memory, it implements the steps of the laser cleaning method applicable to complex irregularly shaped components.

[0111] As can be seen from the above, the laser cleaning equipment disclosed in this application, applicable to complex irregular-shaped components, can accurately reflect the shape and surface features of the components by establishing a three-dimensional mesh model, providing an accurate basis for subsequent segmentation and path planning. During the segmentation process, not only the vertical and horizontal directions are considered, but special attention is paid to the curvature changes of the complex irregular-shaped component's surface. This helps generate a segmentation model that more closely matches the actual shape of the component, thereby improving the accuracy and comprehensiveness of the cleaning path. The path nodes for laser cleaning are generated using the segmentation model, and iterative calculations are performed through optimization algorithms to find the shortest or optimal path through all key points. This optimized path can significantly reduce the ineffective movement of the laser and improve cleaning efficiency. During the cleaning operation, the laser cleaning effect is monitored synchronously, and the relevant control parameters of the laser are dynamically adjusted based on the monitoring results. This real-time adjustment mechanism ensures the consistency and high quality of the cleaning effect, avoiding problems such as incomplete or over-cleaning due to improper parameters.

[0112] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A laser cleaning method suitable for complex irregularly shaped components, characterized in that, The method includes: S1. Establish a three-dimensional mesh model of complex irregular components; S2. Based on the three-dimensional mesh model, the mesh is divided sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model. S3. Generate the laser cleaning path nodes based on the segmentation model, and perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path; S4. Drive the laser to perform cleaning operations along the optimal laser cleaning path, and monitor the laser cleaning effect simultaneously during the operation, and dynamically adjust the relevant control parameters accordingly to ensure the cleaning effect.

2. The method according to claim 1, characterized in that, In step S1, establishing a three-dimensional mesh model of the complex irregular component includes: S11. Obtain point cloud data of the surface of complex irregular-shaped components; S12. Calculate the centroid coordinates based on all points in the point cloud data. For each point in the point cloud data, calculate its distance to the centroid, and remove points whose centroid distance is greater than a preset threshold as noise points from the point cloud data. S13. The orientation of the point cloud is adjusted based on the PCA principal component analysis method, and the surface reconstruction technology is used to generate the corresponding three-dimensional mesh model.

3. The method according to claim 1, characterized in that, In step S2, based on the three-dimensional mesh model, the model is sequentially divided according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model, including: S21. In the vertical direction, based on the vertical cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the three-dimensional mesh model is divided according to the height direction to obtain multiple vertical slices with consistent levels. S22. Based on each of the vertical slices, perform circular projection transformation to obtain the corresponding projection transformation slices; S23. In the horizontal direction, based on the horizontal cleaning range of the laser, and after analyzing and determining the curvature change of the surface of the complex irregular component, the obtained projection transformation slices are divided to obtain corresponding horizontal slices. S24. Based on each level slice, the corresponding segmentation model is obtained.

4. The method according to claim 3, characterized in that, In step S2, when analyzing the curvature changes of the surface of complex irregular-shaped components, the method further includes: For each point on the three-dimensional mesh model, curvature analysis is performed using discrete differential geometry. Based on the obtained curvature analysis results, a corresponding curvature distribution map is generated, and high curvature regions and flat regions are identified and divided based on the curvature distribution map.

5. The method according to claim 1, characterized in that, In step S3, generating laser cleaning path nodes based on the segmentation model and performing iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path includes: S31. Based on the segmentation model, the cleaning surface is discretized into multiple key points, and these key points are used as path nodes for laser cleaning. S32. Construct a path planning model and perform iterative calculations using the selected optimization algorithm. During the calculation process, set up a multi-scan method for complex areas to perform path planning. S33. Determine the shortest path through all key points, and after smoothing the shortest path, use it as the optimal laser cleaning path.

6. The method according to claim 1, characterized in that, In step S4, during the operation, the laser cleaning effect is monitored synchronously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect, including: S41. Obtain cleaning parameters monitored by a preset high-precision optical sensor, wherein the cleaning parameters include at least one of laser reflected light intensity and surface temperature; S42. Based on the cleaning parameters, the relevant control parameters are dynamically adjusted through a preset control strategy to ensure the cleaning effect. The relevant control parameters include at least one of laser power, scanning speed, and path planning parameters.

7. A laser cleaning system suitable for complex irregular-shaped components, characterized in that, The system includes a 3D mesh model construction module, a model segmentation module, a laser cleaning path planning module, and a cleaning operation control module, wherein: The three-dimensional mesh model construction module is used to build a three-dimensional mesh model of complex irregular components; The model segmentation module is used to segment the three-dimensional mesh model sequentially according to the vertical and horizontal directions, taking into account the curvature changes of the complex irregular component surface, to obtain the corresponding segmentation model. The laser cleaning path planning module is used to generate laser cleaning path nodes based on the segmentation model, and to perform iterative calculations according to the selected optimization algorithm to generate the optimal laser cleaning path. The cleaning operation control module is used to drive the laser to perform cleaning operations along the optimal laser cleaning path. During the operation, the laser cleaning effect is monitored simultaneously, and relevant control parameters are dynamically adjusted accordingly to ensure the cleaning effect.

8. A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the laser cleaning method applicable to complex irregularly shaped components.

9. A laser cleaning device suitable for complex irregularly shaped components, comprising a communication interface, a memory, a communication bus, and a processor, wherein, The processor, communication interface, and memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes the program stored in the memory, it implements the steps of the laser cleaning method applicable to complex irregularly shaped components.

Images