Blade type part laser cladding repair adaptive path planning method and system

Abstract

The present application relates to laser cladding technology, in particular to a kind of vane parts laser cladding repair adaptive path planning method and system.Control line laser profile scanner is scanned according to certain path to workpiece, and the topography point cloud under line laser profile scanner coordinate system is obtained;The coordinates of the topography point cloud under line laser profile scanner coordinate system are converted into the coordinates of the topography point cloud of laser cladding equipment coordinate system;Topography point cloud of laser cladding equipment coordinate system is filtered and denoised to avoid the influence of the noise of line laser profile scanner on the accuracy of point cloud algorithm;Principal component analysis or normal analysis is used to fit central NURBS curve;According to the machining step set by user, point is taken on NURBS curve, and the path point coordinates used for machining program are obtained, cladding process parameters are added, and machining program is generated.The machining efficiency and machining quality of laser cladding technology in repairing damaged parts are improved, and batch production in similar vane repair field is realized.

Description

Technical Field

[0001] This invention relates to laser cladding technology, and in particular to an adaptive path planning method and system for laser cladding repair of blade-type parts. Background Technology

[0002] Aero-engine turbine blades operate in extreme environments of high temperature, high speed, and high pressure. The blade tip is susceptible to damage due to aerodynamic loads, thermal fatigue, wear, corrosion, and impact. To restore the aerodynamic shape of the blade, laser cladding technology is used to add metal powder to the blade tip surface. This powder is melted and deposited layer by layer by a high-energy laser to form a new blade tip structure. This method offers advantages such as precise shape control, a small heat-affected zone, and high metallurgical bonding strength.

[0003] Before using laser cladding equipment to repair deformed and damaged blades, it is necessary to prepare the processing path and parameter instruction program (such as G-code) that the laser cladding equipment can execute. The program is generally generated by processing the digital model of the workpiece through computer-aided manufacturing software.

[0004] Due to blade deformation and damage, the original digital model of the blade could no longer match the actual workpiece, leading to significant errors during machining. This invention uses a line laser profile scanner to scan the workpiece, acquiring surface point cloud data, identifying the workpiece's contour lines and centerline features, adding process parameters for batch cladding, and generating machining instructions recognizable by a CNC system or other control system to complete the laser cladding repair of the workpiece. This invention is applied to the field of laser cladding repair of damaged blades, such as the tip repair of aero-turbine blades.

[0005] Traditional laser cladding equipment typically relies on machine vision or human judgment for path planning when repairing damaged parts, manually and roughly editing the processing program to complete the workpiece repair. This method is inefficient, produces poor processing quality, and is difficult to meet the needs of large-scale production.

[0006] Existing technologies, such as the invention patent with publication number CN118789012A, disclose an adaptive repair system for turbine blade tips based on in-machine measurement. This system is an adaptive system for grinding and repairing blade tips. The patent uses the margin optimization module to detect the blade tip profile of the turbine blade, obtain blade tip detection data, and adjust the blade tip processing steps along the axial direction according to the blade tip detection data to obtain an optimized blade tip processing step. Based on the adjusted turbine blade processing path, the blade tip profile of the turbine blade is processed through the optimized blade tip processing step.

[0007] This patent has the following technical problems: (1) The method of manually and roughly editing the processing program to repair damaged parts by using human eyes or machine vision is inefficient, has poor processing quality, and is difficult to meet the needs of large-scale production; (2) It is difficult to ensure the consistency of the size and precision of the processing area, which can easily cause fluctuations in the mechanical properties of the blade; (3) It is difficult to avoid both over-cladding and under-cladding, and it is even more difficult to ensure a seamless and smooth natural transition between the processing area and the non-processing area, thus leaving obvious overlap marks in the junction area, which greatly increases the difficulty of the post-processing process after the blade is clad. Summary of the Invention

[0008] To address the aforementioned technical problems, this invention provides an adaptive path planning method and system for laser cladding repair of blade-type parts. It improves upon existing technologies, overcomes the difficulty in meeting the needs of large-scale production, avoids excessive and insufficient cladding, and achieves efficient, accurate, and automatic generation of processing programs, thereby improving cladding accuracy and efficiency.

[0009] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0010] In a first aspect, the present invention provides an adaptive path planning method for laser cladding repair of blade-type parts, comprising the following steps:

[0011] S1 scans the workpiece:

[0012] The scanner is controlled to scan the workpiece along a certain path to obtain the topographic point cloud in the scanner coordinate system;

[0013] S2 coordinate system transformation:

[0014] The topographic point cloud obtained by S1 is converted into a topographic point cloud in the coordinate system of the laser cladding equipment;

[0015] S3 Feature Recognition:

[0016] S3.1 Filtering and Noise Reduction Processing:

[0017] The topographic point cloud of the coordinate system of the laser cladding equipment is filtered and denoised.

[0018] S3.2 Fitting the central NURBS curve:

[0019] When the repair program needs to be generated according to the topographic centerline, principal component analysis is used:

[0020] After filtering and noise reduction, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the change trend of the topographic point cloud. The topographic point cloud is segmented according to the change trend, and the centroid μ of each segment is calculated to fit the central NURBS curve.

[0021] When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used:

[0022] After filtering and noise reduction, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve.

[0023] S4 generates the processing program:

[0024] Based on the processing step size set by the user, points are selected on the NURBS curve. The offsets of the laser cladding equipment and scanner in the laser cladding equipment coordinate system, which have been calibrated by the system, are added to obtain the coordinates of the path points used in the processing program. The cladding process parameters are then added to generate the processing program.

[0025] Preferably, the conversion process described in S2 is as follows:

[0026] The coordinates (X1, Z1) of the topographic point cloud in the scanner coordinate system, combined with the scanning starting point (X0, Y0, Z0), are converted into the coordinates (X2, Y2, Z2) of the topographic point cloud in the laser cladding equipment coordinate system. The coordinate calculation formula is as follows:

[0027] X2 = X0 + X1,

[0028] Y2 = Y0 + i*Δd,

[0029] Z2 = Z0 + Z1,

[0030] Where i is the sequence number of the contour line, and Δd is the spacing between each contour line.

[0031] Preferably, the filtering in step S3 is a combination of statistical filtering, voxel filtering, and conditional filtering, wherein the steps of statistical filtering are as follows:

[0032] For a given point pi, its neighborhood is {pj} (j∈N(pi)), where N(pi) is the set containing point pi and other points within a certain range around it.

[0033] Calculate the neighborhood mean:

[0034]

[0035] Calculate the standard deviation:

[0036]

[0037] Identifying noise points: If the distance ||pi-μi|| from point pi to the mean of its neighborhood is greater than a certain threshold, and this distance is much greater than the standard deviation σi, then pi is considered a noise point.

[0038] Preferably, the principal component analysis process described in S3.1 is as follows:

[0039] Data centralization: For each point pi = (xi, yi, zi) in the topographic point cloud, calculate the centroid μ = (μx, μy, μz) and decentralize it: pi' = pi - μ;

[0040] Calculate the covariance matrix C:

[0041]

[0042] Where N is the number of points in the topography point cloud, and pi′ is the centered coordinate of the i-th point in the topography point cloud;

[0043] Calculate eigenvalues ​​and eigenvectors: The eigenvalues ​​and eigenvectors of the covariance matrix C are calculated by solving the characteristic equation Cv = λv. Each eigenvector v represents the principal component direction of the topographic point cloud, that is, the direction with the greatest change in the data.

[0044] Principal component selection: The most important principal component is selected based on the magnitude of the eigenvalue λ, and the eigenvector with the largest eigenvalue is the direction of the principal component.

[0045] Preferably, the normal analysis process described in S3.2 is as follows:

[0046] Normal estimation:

[0047] After decentering each point in the topographic point cloud, the covariance matrix C of the point in its neighborhood is calculated, and the covariance matrix C is decomposed into eigenvalues ​​and eigenvectors. The eigenvector with the smallest eigenvalue is the estimated normal direction of the point.

[0048] Calculate the included angle of the normal at each point:

[0049] For point p i and adjacent point p j The formula for calculating the angle θij between their normals is as follows:

[0050] cos(θij)=n i *n j

[0051] Where, n i and n j They are points p i and point p j The direction of the normal;

[0052] Boundary point detection:

[0053] When point p i When the normal of a point is not the same as the normal of most points in its neighborhood, that is, when the angle between the normals is large, then p is considered to be... iIt is a boundary point, and the extracted outer contour points are used to fit the center NURBS curve.

[0054] Preferably, the segmentation process described in S3.1 is as follows: according to the change trend angle threshold, points whose principal component direction angle difference between adjacent points does not exceed the change trend angle threshold are grouped into one category.

[0055] Secondly, the present invention provides an adaptive path planning system for laser cladding repair of blade-type parts, comprising:

[0056] Workpiece scanning module:

[0057] Used to control the scanner to scan the workpiece along a certain path and obtain the topographic point cloud in the scanner coordinate system;

[0058] Coordinate system transformation module:

[0059] Used to convert the topographic point cloud acquired by the scanning workpiece module into a topographic point cloud in the coordinate system of the laser cladding equipment;

[0060] Feature recognition module:

[0061] Includes a filtering and noise reduction submodule and a center NURBS curve fitting submodule;

[0062] Filtering and noise reduction submodule:

[0063] Used for filtering and noise reduction of the topographic point cloud of the laser cladding equipment coordinate system to avoid the impact of scanner noise on the accuracy of the point cloud algorithm;

[0064] Central NURBS curve fitting submodule:

[0065] Used for principal component analysis or normal analysis of the filtered and denoised topographic point cloud;

[0066] When the repair program needs to be generated according to the topographic centerline, principal component analysis is used:

[0067] After filtering and noise reduction, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the change trend of the topographic point cloud. The topographic point cloud is segmented according to the change trend, and the centroid μ of each segment is calculated to fit the central NURBS curve.

[0068] When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used:

[0069] After filtering and noise reduction, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve.

[0070] Machining program generation module:

[0071] The system uses the NURBS curve to select points according to the user-defined processing step size, adds the offset of the laser cladding equipment and scanner in the laser cladding equipment coordinate system that has been calibrated by the system, obtains the coordinates of the path points used in the processing program, adds cladding process parameters, and generates the processing program.

[0072] Thirdly, the present invention provides an adaptive path planning device for laser cladding repair of blade-type parts, comprising:

[0073] A scanner and a laser cladding equipment, wherein the scanner is mounted on the motion axis of the laser cladding equipment so that it can move synchronously with the axis and is fixed in relative position to the cladding device of the laser cladding equipment;

[0074] One or more processors;

[0075] Storage device for storing one or more programs;

[0076] When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method as described in any one of claims 1-7.

[0077] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the methods described in the first aspect above.

[0078] The above technical solution has the following advantages or beneficial effects:

[0079] This invention identifies the shape features of the workpiece to be repaired by scanning, and generates a specific processing program for each different damaged deformation. The scanning and identification accuracy is extremely high. Compared with human eyes or machine vision, the processing program generated by this invention is closer to the actual workpiece, the transition between the processed area and the unprocessed area is smoother, and there are no obvious overlapping marks. It realizes adaptive trajectory processing for damaged workpieces with different deformations, and has high dimensional accuracy and consistency.

[0080] This invention improves the processing efficiency and quality when using laser cladding technology to repair damaged parts or other parts where processing programs cannot be obtained quickly, by using a scanner and point cloud graphics algorithm on a laser cladding device to adaptively identify the workpiece processing trajectory and generate the processing program used by the device. This enables mass production in fields such as blade repair.

[0081] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0082] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in the invention and should not be construed as limiting the scope of the invention.

[0083] Figure 1 A flowchart of an adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention;

[0084] Figure 2 A flowchart illustrating the steps of a preferred embodiment of the adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention;

[0085] Figure 3 This is a graphical flowchart of a preferred embodiment of the adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention;

[0086] Figure 4 An overall framework diagram of an adaptive path planning system for laser cladding repair of blade-type parts provided by the present invention;

[0087] Figure 5 is an implementation example of an adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention. Detailed Implementation

[0088] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0089] This invention first provides an adaptive path planning method for laser cladding repair of blade-type parts, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0090] S1 scans the workpiece:

[0091] The scanner is controlled to scan the workpiece along a certain path. The scanner is a line laser profile scanner. The path is related to the number of rows and columns of the multi-station (the number of rows and columns are settable variable parameters). The path scans row by row in a "Z" shape to obtain the shape point cloud in the coordinate system of the line laser profile scanner.

[0092] S2 coordinate system transformation:

[0093] The topographic point cloud obtained by S1 is converted into a topographic point cloud in the coordinate system of the laser cladding equipment;

[0094] S3 Feature Recognition:

[0095] S3.1 Filtering and Noise Reduction Processing:

[0096] The topographic point cloud of the coordinate system of the laser cladding equipment is filtered and denoised.

[0097] S3.2 Fitting the central NURBS curve:

[0098] Perform principal component analysis or normal analysis on the filtered and denoised topographic point cloud;

[0099] S4 generates the processing program:

[0100] Based on the processing step size set by the user, points are selected on the NURBS curve to obtain the coordinates of the path points used in the processing program. Then, cladding process parameters are added to generate the processing program.

[0101] By scanning and identifying the shape features of the workpiece to be repaired, a specific processing program is generated for each different damaged deformation. The scanning and identification accuracy is extremely high. Compared with human eyes or machine vision, the generated processing program is closer to the actual workpiece, and the transition between the processed area and the unprocessed area is smoother with no obvious overlap marks. Adaptive trajectory processing is achieved for damaged workpieces with different deformations, and the dimensional accuracy is highly consistent.

[0102] Figure 2 This is a flowchart illustrating a preferred embodiment of the adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention. Figure 2 As shown, according to an embodiment of the adaptive path planning method for laser cladding repair of blade-type parts according to the present invention, the specific implementation steps of a preferred embodiment of the aforementioned step S1 are as follows:

[0103] S1.1 line laser contour scanner settings include exposure time, resolution, and other parameters;

[0104] S1.2 Sends the starting coordinates, scanning distance, and scanning speed of the scanning motion to the motion system of the laser cladding equipment;

[0105] The S1.3 line laser contour scanner starts scanning as follows: Figure 5a The workpiece processing area shown is the area to be repaired.

[0106] S1.4 The control line laser contour scanner scans the workpiece along a certain path. The path is related to the number of rows and columns of the multi-station (the number of rows and columns are settable variable parameters). The path scans line by line in a "Z" shape and sends an IO signal after reaching the starting position.

[0107] After receiving the I0 signal, the S1.5 line laser contour scanner begins to record contour information;

[0108] After the motion system of the S1.6 laser cladding equipment completes its motion, it sends a scanning stop signal to the system.

[0109] After receiving the scanning stop signal, the S1.7 system stops recording contour information using the line laser contour scanner.

[0110] S1.8 When machining a single workpiece, the system acquires contour data from the line laser contour scanner and begins point cloud algorithm processing; when machining multiple workpieces, the entire row of point clouds is decomposed into point clouds for each workpiece; thus, the topographic point cloud in the coordinate system of the line laser contour scanner described in step S1 is obtained, i.e., as shown in the figure. Figure 5b The topographic point cloud obtained from the scan is shown.

[0111] Figure 3 This is a graphical flowchart of a preferred embodiment of the adaptive path planning method for laser cladding repair of blade-type parts provided by the present invention; according to the graphical flowchart, the graphical algorithm includes:

[0112] Step S2 Coordinate System Transformation: The coordinates (X1, Z1) of the topographic point cloud obtained in the line laser contour scanner coordinate system in S1, combined with the scanning starting point (X0, Y0, Z0), are converted into the coordinates (X2, Y2, Z2) of the topographic point cloud in the laser cladding equipment coordinate system. The coordinate calculation formula is as follows:

[0113] X2 = X0 + X1,

[0114] Y2 = Y0 + i*Δd,

[0115] Z2 = Z0 + Z1,

[0116] Where i is the sequence number of the contour line, and Δd is the spacing between each contour line.

[0117] Step S3 Feature Recognition:

[0118] S3.1 Filtering and Noise Reduction Processing:

[0119] The topographic point cloud of the laser cladding equipment coordinate system is filtered and denoised to avoid the impact of noise from the line laser profile scanner on the accuracy of the point cloud algorithm.

[0120] The noise of the line laser profiler includes: sensor noise, optical noise, and transmission noise.

[0121] In this embodiment, the selected filtering method is to perform voxel filtering, statistical filtering and conditional filtering in sequence. In actual application, it is not limited to this filtering method. Any one or more combinations of filtering methods can be selected.

[0122] The steps of statistical filtering are as follows:

[0123] For a given point pi, its neighborhood is {pj} (j∈N(pi)), where N(pi) is the set containing point pi and other points within a certain range around it.

[0124] Calculate the neighborhood mean:

[0125]

[0126] Calculate the standard deviation:

[0127]

[0128] Identifying noise points: If the distance ||pi-μi|| from point pi to the mean of its neighborhood is greater than a certain threshold, and this distance is much greater than the standard deviation σi, then pi is considered a noise point.

[0129] The contour points of the laser cladding equipment coordinate system are segmented by Euclidean clustering to obtain the point cloud of the processing area morphology;

[0130] Euclidean clustering segmentation is a clustering method based on Euclidean distance. Its core idea is to group closely spaced sample points into one class, while grouping more distant sample points into different classes. It is primarily used to divide samples in a dataset into several clusters, minimizing the distance between samples within the same cluster and maximizing the distance between samples in different clusters. Euclidean clustering segmentation is highly effective in processing spatial data, especially in the analysis and processing of point cloud data.

[0131] S3.2 Fitting the central NURBS curve:

[0132] Depending on the type of workpiece being processed, users can freely choose whether the workpiece repair program needs to be generated based on the center line of the shape or the outer contour line of the shape.

[0133] When the repair program needs to be generated according to the topographic centerline, principal component analysis is used:

[0134] After filtering and denoising, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the trend of change in the topographic point cloud. According to the angle threshold of the trend of change, points whose angle difference of the principal component direction does not exceed the angle threshold of the trend of change are grouped into one class, thus segmenting the topographic point cloud according to the trend of change. The centroid μ of each segment is calculated (the centroid is calculated in the same way as the neighborhood mean described in S3), which is used to fit the center NURBS curve (based on the interpolation method, a smooth NURBS curve is calculated through a set of target points composed of centroid μ, so that the curve passes through these points as accurately as possible); NURBS curve fitting is achieved by constructing a smooth curve defined by multiple control points, weights, node vectors and basis functions.

[0135] The principal component analysis process is as follows:

[0136] Data centralization: For each point pi = (xi, yi, zi) in the topographic point cloud, calculate the centroid μ = (μx, μy, μz) and decentralize it: pi' = pi - μ;

[0137] Calculate the covariance matrix C:

[0138]

[0139] Where N is the number of points in the topographic point cloud, and pi′ is the centered coordinate of the i-th point in the topographic point cloud; the calculated covariance matrix C is a 3×3 matrix, because the topographic point cloud is in three-dimensional space, and each element Cij of the covariance matrix C represents the covariance between feature i and feature j.

[0140] Calculate eigenvalues ​​and eigenvectors: The eigenvalues ​​and eigenvectors of the covariance matrix C are calculated by solving the characteristic equation Cv = λv. Each eigenvector v represents the principal component direction of the topographic point cloud, that is, the direction with the greatest change in the data.

[0141] Principal component selection: The most important principal component is selected based on the magnitude of the eigenvalue λ, and the eigenvector with the largest eigenvalue is the direction of the principal component.

[0142] When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used:

[0143] After filtering and denoising, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve.

[0144] The normal analysis process is as follows:

[0145] Normal estimation:

[0146] After decentering each point in the topographic point cloud, the covariance matrix C of the point in its neighborhood is calculated, and the covariance matrix C is decomposed into eigenvalues ​​and eigenvectors. The eigenvector with the smallest eigenvalue is the estimated normal direction of the point.

[0147] Calculate the included angle of the normal at each point:

[0148] For point p i and adjacent point p j The formula for calculating the angle θij between their normals is as follows:

[0149] cos(θij)=n i *n j

[0150] Where, n i and n j They are points p i and point p j The direction of the normal;

[0151] Boundary point detection:

[0152] When point p i When the normal of a point is not the same as the normal of most points in its neighborhood, that is, when the angle between the normals is large, then p is considered to be... i It is a boundary point, and the extracted outer contour points are used to fit the center NURBS curve.

[0153] Step S4 generates the machining program:

[0154] Points are taken on the NURBS curve according to the user-defined processing step size. These points are then added to the offsets of the laser cladding equipment and the line laser contour scanner in the laser cladding equipment coordinate system, calibrated by the system, to obtain the coordinates of the path points used in the processing program. For example... Figure 5c The calculated machining trajectory shown is used to add cladding process parameters and generate a machining program.

[0155] like Figure 2 As shown, after generating the processing program in step S4, the following steps are also included: When processing a single workpiece, the trajectory points and the process parameter formula for cladding processing are sent to the laser cladding equipment, including parameters such as laser power and cladding speed; when processing multiple workpieces, it is determined whether the current row number is less than the total number of rows in the station. If yes, steps S1-S4 are repeated; if no, the trajectory points and the process parameter formula for cladding processing are sent to the laser cladding equipment, including parameters such as laser power and cladding speed.

[0156] On the other hand, embodiments of the present invention provide an adaptive path planning system for laser cladding repair of blade-type parts. Figure 4 This is an overall framework diagram of an adaptive path planning system for laser cladding repair of blade-type parts according to an embodiment of the present invention. Figure 4 As shown, an adaptive path planning system for laser cladding repair of blade-type parts according to an embodiment of the present invention includes:

[0157] Workpiece scanning module:

[0158] Used to control a line laser profile scanner to scan a workpiece along a certain path, and obtain the shape point cloud in the coordinate system of the line laser profile scanner;

[0159] Coordinate system transformation module:

[0160] Used to convert the topographic point cloud acquired by the scanning workpiece module into a topographic point cloud in the coordinate system of the laser cladding equipment;

[0161] Feature recognition module:

[0162] Includes a filtering and noise reduction submodule and a center NURBS curve fitting submodule;

[0163] Filtering and noise reduction submodule:

[0164] Used to filter and reduce noise in the topographic point cloud of the coordinate system of laser cladding equipment, so as to avoid the impact of noise from the line laser profile scanner on the accuracy of the point cloud algorithm;

[0165] Central NURBS curve fitting submodule:

[0166] Used for principal component analysis or normal analysis of the filtered and denoised topographic point cloud;

[0167] When the repair program needs to be generated according to the topographic centerline, principal component analysis is used:

[0168] After filtering and noise reduction, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the change trend of the topographic point cloud. The topographic point cloud is segmented according to the change trend, and the centroid μ of each segment is calculated to fit the central NURBS curve.

[0169] When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used:

[0170] After filtering and noise reduction, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve.

[0171] Machining program generation module:

[0172] The system uses points on the NURBS curve according to the user-defined processing step size, adds the offsets of the laser cladding equipment and the line laser contour scanner in the laser cladding equipment coordinate system (which have been calibrated by the system), obtains the coordinates of the path points used in the processing program, adds cladding process parameters, and generates the processing program.

[0173] In one possible design, the structure of the laser cladding workpiece adaptive path planning device includes a processor and a memory, the memory being used to store programs that support the laser cladding workpiece adaptive path planning device in executing the above-described laser cladding workpiece adaptive path planning method, and the processor being configured to execute the programs stored in the memory.

[0174] This invention also provides an adaptive path planning device for laser cladding repair of blade-like parts, comprising:

[0175] A line laser profile scanner and a laser cladding equipment, wherein the line laser profile scanner is mounted on the motion axis of the laser cladding equipment so that it can move synchronously with the axis and is fixed in relative position to the cladding device of the laser cladding equipment;

[0176] One or more processors;

[0177] Storage device for storing one or more programs;

[0178] When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method as described in any one of claims 1-7.

[0179] This invention also provides a computer-readable storage medium storing a computer program, characterized in that the program, when executed by a processor, implements any of the methods described above.

[0180] The above technical solution has the following advantages or beneficial effects: By using a line laser contour scanner and combining it with a point cloud graphic algorithm on a laser cladding equipment, the present invention can adaptively identify the workpiece processing trajectory and generate a processing program for the equipment, thereby improving the processing efficiency and quality when using laser cladding technology to repair damaged parts or other parts for which processing programs cannot be obtained quickly, and realizing mass production in fields such as blade repair.

[0181] In the description of this specification, references to terms such as "an embodiment," "a preferred embodiment," "an example," "a specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0182] 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.

[0183] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered 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 processor-including system, 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 (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0184] It should be understood that various parts 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.

[0185] 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, it includes one or a combination of the steps of the method embodiments. Since the device implementation corresponds to the method implementation, the description of the device implementation is relatively brief, and the relevant description can be found by referring to the description of the method implementation.

[0186] 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 can be a read-only memory, a disk, or an optical disk, etc.

[0187] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An adaptive path planning method for laser cladding repair of blade-type parts, characterized in that: Includes the following steps: S1 scans the workpiece: The scanner is controlled to scan the workpiece along a certain path to obtain the topographic point cloud in the scanner coordinate system; S2 coordinate system transformation: The topographic point cloud obtained by S1 is converted into a topographic point cloud in the coordinate system of the laser cladding equipment; S3 Feature Recognition: S3.1 Filtering and Noise Reduction Processing: The topographic point cloud of the coordinate system of the laser cladding equipment is filtered and denoised. S3.2 Fitting the central NURBS curve: When the repair program needs to be generated according to the topographic centerline, principal component analysis is used: After filtering and noise reduction, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the change trend of the topographic point cloud. The topographic point cloud is segmented according to the change trend, and the centroid μ of each segment is calculated to fit the central NURBS curve. When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used: After filtering and noise reduction, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve. S4 generates the processing program: Based on the processing step size set by the user, points are selected on the NURBS curve. The offsets of the laser cladding equipment and scanner in the laser cladding equipment coordinate system, which have been calibrated by the system, are added to obtain the coordinates of the path points used in the processing program. The cladding process parameters are then added to generate the processing program.

2. The adaptive path planning method for laser cladding repair of blade-type parts as described in claim 1, characterized in that: The conversion process described in S2 is as follows: The coordinates (X1, Z1) of the topographic point cloud in the scanner coordinate system, combined with the scanning starting point (X0, Y0, Z0), are converted into the coordinates (X2, Y2, Z2) of the topographic point cloud in the laser cladding equipment coordinate system. The coordinate calculation formula is as follows: X2 = X0 + X1, Y2 = Y0 + i*Δd, Z2 = Z0 + Z1, Where i is the sequence number of the contour line, and Δd is the spacing between each contour line.

3. The adaptive path planning method for laser cladding repair of blade-type parts as described in claim 1, characterized in that: The filtering method described in S3 can be any combination of statistical filtering, voxel filtering, and conditional filtering. The steps of statistical filtering are as follows: For a given point pi, its neighborhood is {pj} (j∈N(pi)), where N(pi) is the set containing point pi and other points within a certain range around it. Calculate the neighborhood mean: Calculate the standard deviation: Identifying noise points: If the distance ||pi-μi|| from point pi to the mean of its neighborhood is greater than a certain threshold, and this distance is much greater than the standard deviation σi, then pi is considered a noise point.

4. The adaptive path planning method for laser cladding repair of blade-type parts as described in claim 1, characterized in that: The principal component analysis process described in S3 is as follows: Data centralization: For each point pi = (xi, yi, zi) in the topographic point cloud, calculate the centroid μ = (μx, μy, μz) and decentralize it: pi' = pi - μ; Calculate the covariance matrix C: Where N is the number of points in the topography point cloud, and pi′ is the centered coordinate of the i-th point in the topography point cloud; Calculate eigenvalues ​​and eigenvectors: The eigenvalues ​​and eigenvectors of the covariance matrix C are calculated by solving the characteristic equation Cv = λv. Each eigenvector v represents the principal component direction of the topographic point cloud, that is, the direction with the greatest change in the data. Principal component selection: The most important principal component is selected based on the magnitude of the eigenvalue λ, and the eigenvector with the largest eigenvalue is the direction of the principal component.

5. The adaptive path planning method for laser cladding repair of blade-type parts as described in claim 1, characterized in that: The normal analysis process described in S3.2 is as follows: Normal estimation: After decentering each point in the topographic point cloud, the covariance matrix C of the point in its neighborhood is calculated, and the covariance matrix C is decomposed into eigenvalues ​​and eigenvectors. The eigenvector with the smallest eigenvalue is the estimated normal direction of the point. Calculate the included angle of the normal at each point: For point p i and adjacent point p j The formula for calculating the angle θij between their normals is as follows: cos(θij)=n i *n j Where, n i and n j They are points p i and point p j The direction of the normal; Boundary point detection: When point p i When the normal of a point is not the same as the normal of most points in its neighborhood, that is, when the angle between the normals is large, then p is considered to be... i It is a boundary point, and the extracted outer contour points are used to fit the center NURBS curve.

6. The adaptive path planning method for laser cladding repair of blade-type parts as described in claim 1, characterized in that: The segmentation process described in S3.1 is as follows: according to the change trend angle threshold, points whose principal component direction angle difference between adjacent points does not exceed the change trend angle threshold are grouped into one category.

7. An adaptive path planning system for laser cladding repair of blade-type parts, characterized in that, include: Workpiece scanning module: Used to control the scanner to scan the workpiece along a certain path and obtain the topographic point cloud in the scanner coordinate system; Coordinate system transformation module: Used to convert the topographic point cloud acquired by the scanning workpiece module into a topographic point cloud in the coordinate system of the laser cladding equipment; Feature recognition module: Includes a filtering and noise reduction submodule and a center NURBS curve fitting submodule; Filtering and noise reduction submodule: Used for filtering and noise reduction of the topographic point cloud of the laser cladding equipment coordinate system to avoid the impact of scanner noise on the accuracy of the point cloud algorithm; Central NURBS curve fitting submodule: Used for principal component analysis or normal analysis of the filtered and denoised topographic point cloud; When the repair program needs to be generated according to the topographic centerline, principal component analysis is used: After filtering and noise reduction, principal component analysis is performed on each point in its neighborhood. The direction of the principal component of each point indicates the direction of the change trend of the topographic point cloud. The topographic point cloud is segmented according to the change trend, and the centroid μ of each segment is calculated to fit the central NURBS curve. When the workpiece repair program needs to be generated based on the outer contour lines of the shape, normal analysis is used: After filtering and noise reduction, the normal of each point in the topographic point cloud is calculated. Boundary points are determined according to the normal angle, and the extracted outer contour points are used to fit the central NURBS curve. Machining program generation module: The system uses points on the NURBS curve according to the user-defined processing step size, adds the offsets of the laser cladding equipment and scanner in the laser cladding equipment coordinate system (which have been calibrated by the system), obtains the coordinates of the path points used in the processing program, adds cladding process parameters, and generates the processing program.

8. An adaptive path planning device for laser cladding repair of blade-type parts, comprising: A scanner and a laser cladding equipment, wherein the scanner is mounted on the motion axis of the laser cladding equipment so that it can move synchronously with the axis and is fixed in relative position to the cladding device of the laser cladding equipment; One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method as described in any one of claims 1-7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images