Blade manufacturing method, device, electronic equipment and storage medium

Abstract

This application provides a blade manufacturing method, apparatus, electronic device, and storage medium, relating to the field of reverse engineering technology for turbomachinery. The method includes: acquiring multi-point cloud data of multiple blades of the same specification and marking the multi-point cloud data; interpolating, filtering, and fusing the marked multi-point cloud data to obtain blade fused point cloud data; establishing a reverse design model for multiple blades based on the blade fused point cloud data; determining the deviation between the blade output data of the reverse design model and the blade fused point cloud data; and manufacturing multiple blades using the blade output data when the deviation is within a preset deviation range. This application, by constructing multi-point cloud fused data for blades, completes the reverse design of blades and the verification and comparison with the multi-point cloud data of blades, reducing the impact of initial blade manufacturing errors on reverse design and improving the efficiency and accuracy of blade reverse design.

Description

Technical Field

[0001] This application relates to the field of reverse engineering technology for turbomachinery, specifically to a blade manufacturing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Turbomachinery is an energy conversion device widely used in fluid transport, pipeline pressurization, industrial drive, and thermal power generation, playing a vital role in modern industrial production. As the core component of turbomachinery, the blades play crucial roles in energy conversion, fluid guidance, and reducing frictional losses; their design and dimensional accuracy have a decisive impact on the performance and reliability of the turbomachinery.

[0003] Reverse engineering is the process of analyzing and studying existing products to understand their structure, function, and principles, thereby replicating or improving those products. Reverse engineering plays a crucial role in the manufacturing of turbomachinery blades, especially when original design data is unavailable, such as in cases of product discontinuation or technological blockades, where blade repair, replacement, spare parts stockpiling, or optimization are necessary. In such situations, reverse engineering is one of the few feasible methods.

[0004] Current blade reverse engineering methods generally involve first scanning existing blades to obtain 3D point cloud data, then performing reverse modeling based on the 3D point cloud data to obtain a 3D model of the blade, and finally designing blade engineering drawings based on the 3D model. However, the 3D point cloud scanning data obtained by this method includes errors introduced during the blade manufacturing process, and the manufacturing error values ​​have a certain degree of dispersion and uncertainty. Therefore, it is impossible to directly restore the original design state of the blade from the point cloud data. Application content

[0005] In view of the above problems, this application provides a blade manufacturing method, apparatus, electronic device and storage medium.

[0006] This application provides a blade manufacturing method, comprising: acquiring multi-point cloud data of multiple blades of the same specification and marking the multi-point cloud data; interpolating, filtering and fusing the marked multi-point cloud data to obtain blade fused point cloud data; establishing a reverse design model for multiple blades based on the blade fused point cloud data; determining the deviation between the blade output data of the reverse design model and the blade fused point cloud data; and manufacturing multiple blades using the blade output data when the deviation is within a preset deviation range.

[0007] According to an embodiment of this application, obtaining multi-point cloud data of multiple blades of the same specification includes: sequentially performing laser scanning on multiple blades to obtain point cloud data of each blade; performing coordinate transformation and spatial alignment on the multiple point cloud data to obtain multi-point cloud data of multiple blades.

[0008] According to an embodiment of this application, the process of interpolating, filtering, and fusing the labeled multi-key cloud data to obtain blade fused point cloud data includes: interpolating the labeled multi-key cloud data to obtain a new multi-key cloud dataset; filtering the new multi-key cloud dataset to determine whether the filtered new multi-key cloud dataset meets a preset fusion standard; relabeling the new multi-key cloud dataset that meets the preset fusion standard; and fusing multiple relabeled new multi-key cloud datasets to obtain blade fused point cloud data.

[0009] According to an embodiment of this application, interpolating the labeled multi-point cloud data to obtain a new multi-point cloud dataset includes: sampling the labeled multi-point cloud data to obtain multiple point cloud data of the labeled multi-point cloud data; obtaining the neighborhood plane normal vector of the multiple data points using the least squares method; determining the intersection points of the neighborhood plane normal vector and the multiple point cloud data using an interpolation algorithm; and forming a set of the multiple intersection points and the multiple data points as the new multi-point cloud dataset.

[0010] According to an embodiment of this application, the screening of new multi-key cloud datasets and the determination of whether the screened new multi-key cloud data meets the preset fusion criteria include: determining the number of new intersection points and new point cloud data points in the new multi-key cloud datasets that meet the preset screening tolerance range; and when the number of new point cloud data points is equal to the maximum number of new intersection points, the new point cloud data points are regarded as new multi-key cloud data that meet the fusion criteria.

[0011] According to an embodiment of this application, establishing a reverse design model for multiple blades based on blade fusion point cloud data includes: sequentially performing data alignment, filtering, data completion, and feature extraction on the blade fusion point cloud data; and using the feature-extracted blade fusion point cloud data for modeling to obtain a reverse design model for multiple blades.

[0012] According to an embodiment of this application, when the deviation is not within the preset deviation range, the blade output data of the reverse design model is corrected using a preset correction amount; and multiple blades are manufactured using the corrected blade output data.

[0013] Another aspect of this application provides a blade manufacturing apparatus, comprising: a data acquisition module for acquiring multi-point cloud data of multiple blades of the same specification and marking the multi-point cloud data; a data fusion module for interpolating, filtering, and fusing the marked multi-point cloud data to obtain blade fused point cloud data; a model building module for establishing a reverse design model for multiple blades based on the blade fused point cloud data; and a blade manufacturing module for determining the deviation between the blade output data of the reverse design model and the blade fused point cloud data, and manufacturing multiple blades using the blade output data when the deviation is within a preset deviation range.

[0014] In another aspect, this application also provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0015] In another aspect, this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0016] The blade manufacturing method, apparatus, electronic equipment, and storage medium provided in this application can achieve the following beneficial effects:

[0017] By constructing multi-point cloud fusion data of blades, and then using the fused point cloud data of blades to complete the reverse design of blades, as well as the verification and comparison between the reverse design model and the multi-point cloud data of blades, the impact of the initial manufacturing error of blades on reverse design is reduced, thereby improving the efficiency and accuracy of blade reverse design. Attached Figure Description

[0018] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0019] Figure 1 A flowchart illustrating a blade manufacturing method according to an embodiment of this application is shown schematically.

[0020] Figure 2 The flowchart illustrates a process for sequentially interpolating, filtering, and fusing multi-key cloud data after each labeling, according to an embodiment of this application.

[0021] Figure 3 A schematic block diagram of a blade manufacturing apparatus according to an embodiment of this application is shown.

[0022] Figure 4 A block diagram schematically illustrates an electronic device suitable for implementing a blade manufacturing method according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0024] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0026] Figure 1 A flowchart illustrating a blade manufacturing method according to an embodiment of this application is shown schematically.

[0027] like Figure 1 As shown, the blade manufacturing method of this embodiment includes steps S1 to S4.

[0028] In step S1, multi-point cloud data of multiple blades of the same specification are acquired and the multi-point cloud data is marked.

[0029] For example, the root section, leading edge, trailing edge, inner back arc, and cross section of multiple blades are of the same specification.

[0030] For example, multi-point cloud data of multiple blades of the same specification can be obtained by using laser scanning technology, ray scanning technology, coordinate measurement technology, etc.

[0031] For example, multi-point cloud data can be labeled by calculating the point cloud curvature or normal vector difference of multi-point cloud data to segment different regions, or by using a neural network model to perform semantic segmentation of the point cloud of multi-point cloud data.

[0032] In step S2, the marked multi-point cloud data are interpolated, filtered, and fused sequentially to obtain the blade fused point cloud data.

[0033] Interpolating the marked multi-point cloud data can more accurately capture the manufacturing deviations between different blades, while also reducing the amount of point cloud data in the multi-point cloud data, significantly reducing the memory usage and computational load of the multi-point cloud data.

[0034] Filtering the interpolated multi-point cloud data can significantly eliminate the impact of manufacturing errors, making the multi-point cloud data closer to the actual design values ​​of the blade.

[0035] By fusing the filtered multi-key cloud data and traversing and fusing multi-key cloud data points at different locations, a complete point cloud data that closely approximates the blade's design state can be constructed, which can reduce data errors caused by manufacturing, wear, and other factors in different blades.

[0036] In step S3, a reverse design model for multiple blades is established based on the fused point cloud data of the blades.

[0037] By fusing point cloud data of the blades, multi-point point cloud data that is close to the design state of the blades is integrated to establish a reverse design model for the blades.

[0038] In step S4, the deviation between the blade output data of the reverse design model and the blade fused point cloud data is determined. When the deviation is within the preset deviation range, multiple blades are manufactured using the blade output data.

[0039] The blade manufacturing method based on this embodiment verifies and compares the reverse design model of the blade by fusing point cloud data of the blade. This can reduce the impact of the initial manufacturing error of the blade on the reverse design model and improve the efficiency and accuracy of the reverse design model of the blade.

[0040] In the embodiments of this application, multiple blades are sequentially laser-scanned to obtain point cloud data for each blade. Coordinate transformation and spatial alignment are performed on the multiple point cloud data to obtain multi-point point cloud data for multiple blades.

[0041] By sequentially scanning multiple blades of the same specification using a laser scanning device, coordinate transformation and spatial alignment are completed, and multi-point cloud data of multiple blades are obtained.

[0042] For example, one or more laser scanning devices, including handheld and fixed scanning devices based on time-of-flight, triangulation, and handhold laser principles, can be used to perform laser scanning on each leaf.

[0043] Based on the blade manufacturing method of this embodiment, the blade point cloud data is sequentially scanned by laser to perform coordinate transformation and spatial alignment, ensuring that the spatial coordinate positions of the multi-point cloud data of the blade are consistent and reducing the error of multi-point cloud data interpolation processing.

[0044] Figure 2 The flowchart illustrating the interpolation, filtering, and fusion process for each marked multi-key cloud data according to an embodiment of this application is shown.

[0045] like Figure 2 As shown, in some embodiments, the above-described operation S2 may further include operations S21 to S24.

[0046] In step S21, the labeled multi-point cloud data is interpolated to obtain a new multi-point cloud dataset.

[0047] Multi-point cloud data includes point cloud data for each blade, and each blade's point cloud data includes multiple independent point clouds. Each independent point cloud includes multiple data points. Interpolation is performed on the multi-point cloud data to obtain multiple data point sets including multiple data points. The labeled multiple data point sets are used as new multi-point cloud data.

[0048] In step S22, the new multi-key cloud dataset is filtered to determine whether the filtered new multi-key cloud dataset meets the preset fusion standard.

[0049] Based on the screening tolerance, the new multi-key cloud dataset is screened to determine whether the screened new multi-key cloud data meets the fusion standard of multi-key cloud data.

[0050] In step S23, the new multi-key cloud dataset that meets the preset fusion criteria is relabeled.

[0051] In step S24, multiple relabeled new multi-point cloud datasets are fused to obtain leaf fused point cloud data.

[0052] The blade manufacturing method based on this embodiment improves the accuracy of blade fusion data by re-labeling multi-point cloud data through label weighted filtering and removing point cloud data that does not meet the fusion standard.

[0053] In this embodiment of the application, interpolating the labeled multi-key cloud data to obtain a new multi-key cloud dataset includes: interpolating the labeled multi-key cloud data to obtain multiple point cloud data of the labeled multi-key cloud data; obtaining the neighborhood plane normal vector of the multiple point cloud data using the least squares method; determining the intersection point of the neighborhood plane normal vector and the multiple point cloud data using the interpolation algorithm; and forming a set of the multiple intersection points and the multiple point cloud data as the new multi-key cloud dataset.

[0054] For example, to obtain the first Independent point cloud of each leaf point cloud data dot clouds include Data points, multiple key cloud data have Point cloud According to point clouds Point cloud data points Point cloud data points are determined using the least squares method. Normal vector of the plane containing the neighborhood Calculate the normal vector With point clouds intersection storage point and all intersections Forming a point set ,in, , set of points As a new key cloud data.

[0055] For example, calculating the normal vector With point clouds Inner distance point cloud data points The intersection point of the plane formed by the three nearest points is taken as the intersection point. .

[0056] The blade manufacturing method based on this embodiment enhances the characteristics of curvature abrupt change regions such as the leading and trailing edges of the blade by fitting the neighborhood plane normal vector, thereby reducing edge errors.

[0057] For example, new multi-key cloud data that meets preset fusion standards is relabeled for each point set. The following relationship must be satisfied.

[0058]

[0059] In the formula, For the number of independent point clouds, Intersection with point set Distance between other points in the middle, The preset screening tolerance, Intersection The intersections must be within the preset screening tolerance range. For point cloud data points The number of point cloud data included within the preset filtering tolerance range is satisfied.

[0060] In the embodiments of this application, the screening of new multi-key cloud datasets and the determination of whether the screened new multi-key cloud datasets meet the preset fusion criteria include: determining the number of new intersections contained in the new point cloud data within the preset screening tolerance range in the new multi-key cloud datasets; and when the number of new intersections is the maximum number, using the new point cloud data as the new multi-key cloud dataset that meets the fusion criteria.

[0061] For each new multi-key cloud dataset, compute points In selecting tolerance Number of data points included in the range ;judge Does it meet the requirements? The data points that meet the requirements will be used as the new multi-key cloud data that meets the fusion standard.

[0062] In the embodiments of this application, the fused point cloud data of the blades is sequentially subjected to data alignment, filtering, data completion and feature extraction. The fused point cloud data of the blades after feature extraction is used to build a model to obtain the reverse design model of multiple blades.

[0063] The multi-key cloud fusion data, after interpolation and filtering, is input into 3D reverse modeling software to construct a reverse design model.

[0064] The blade manufacturing method based on this embodiment avoids the ghosting problem of multi-blade fusion and reduces the error generated by the measured blade by sequentially performing data alignment, filtering, data completion and feature extraction on the fused point cloud data of the blade.

[0065] In this embodiment of the application, the blade output data of the reverse design model includes: blade root section data, blade leading edge data, blade trailing edge data, blade inner back arc data, number of blades, and blade section radius.

[0066] In this embodiment of the application, when the deviation is not within the preset deviation range, the blade output data of the reverse design model is corrected using a preset correction amount; and multiple blades are manufactured using the corrected blade output data.

[0067] For example, the allowable data deviation for the blade shape (leading edge data, trailing edge data, inner back arc data, etc.) is 0.08 mm, the allowable data deviation for the blade root (blade root cross-section data, etc.) is 0.05 mm, and the allowable data deviation for the blade (number of blades, blade cross-sectional radius, etc.) is 0.12 mm.

[0068] If the deviation between the blade output data of the reverse design model and the multi-key cloud data of multiple blades before fusion is not within the preset deviation range, the reverse 3D model of the blade is corrected through deviation iteration. The deviation iteration is to calculate the correction amount of the reverse model from the deviation value.

[0069] The blade manufacturing method based on this embodiment corrects the blade output data of the reverse design model by a preset correction amount, accurately correcting the blade output data that does not meet the preset deviation range, and avoiding affecting the blade output data that meets the preset deviation range.

[0070] Based on the above-described blade manufacturing method, this application also provides a blade manufacturing apparatus. The following will be combined with... Figure 3 The device is described in detail.

[0071] Figure 3 A schematic block diagram of a blade manufacturing apparatus according to an embodiment of this application is shown.

[0072] like Figure 3As shown, the blade manufacturing apparatus 300 in this embodiment includes a data acquisition module 310, a data fusion module 320, a model building module 330, and a blade manufacturing module 340.

[0073] The data acquisition module 310 is used to acquire multi-point cloud data of multiple blades of the same specification and to mark the multi-point cloud data. In one embodiment, the data acquisition module 310 can be used to perform step S1 described above, which will not be repeated here.

[0074] The data fusion module 320 is used to sequentially interpolate, filter, and fuse the labeled multi-point cloud data to obtain fused leaf point cloud data. In one embodiment, the data fusion module 320 can be used to perform step S2 described above, which will not be repeated here.

[0075] The model building module 330 is used to establish a reverse design model for multiple blades based on the fused point cloud data of the blades. In one embodiment, the model building module 330 can be used to perform step S3 described above, which will not be repeated here.

[0076] The blade manufacturing module 340 is used to determine the deviation between the blade output data of the reverse design model and the blade fused point cloud data. When the deviation is within a preset deviation range, multiple blades are manufactured using the blade output data. In one embodiment, the blade manufacturing module 340 can be used to perform step S4 described above, which will not be repeated here.

[0077] According to embodiments of this application, any multiple modules among the data acquisition module 310, data fusion module 320, model building module 330, and blade manufacturing module 340 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this application, at least one of the data acquisition module 310, data fusion module 320, model building module 330, and blade manufacturing module 340 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the data acquisition module 310, data fusion module 320, model building module 330, and blade manufacturing module 340 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0078] Figure 4 A block diagram schematically illustrates an electronic device suitable for implementing a blade manufacturing method according to an embodiment of this application.

[0079] like Figure 4 As shown, an electronic device 400 according to an embodiment of this application includes a processor 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage portion 408 into a random access memory (RAM) 403. The processor 401 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 401 may also include onboard memory for caching purposes. The processor 401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0080] RAM 403 stores various programs and data required for the operation of electronic device 400. Processor 401, ROM 402, and RAM 403 are interconnected via bus 404. Processor 401 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 402 and / or RAM 403. It should be noted that the programs may also be stored in one or more memories other than ROM 402 and RAM 403. Processor 401 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0081] According to embodiments of this application, the electronic device 400 may further include an input / output (I / O) interface 405, which is also connected to a bus 404. The electronic device 400 may also include one or more of the following components connected to the input / output (I / O) interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output (I / O) interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 410 as needed so that computer programs read from it can be installed into the storage section 408 as needed.

[0082] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0083] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 402 and / or RAM 403 and / or one or more memories other than ROM 402 and RAM 403 described above.

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0085] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined or combined in various ways without departing from the spirit and teachings of this application. All such combinations or combinations fall within the scope of this application.

[0086] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Without departing from the scope of this application, those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A method for manufacturing blades, characterized in that, include: Acquire multi-point cloud data of multiple blades of the same specification, and mark the multi-point cloud data; The marked multi-point cloud data is interpolated, filtered, and fused to obtain the fused point cloud data of the blades. The step of sequentially interpolating, filtering, and fusing the labeled multi-key cloud data to obtain blade fused point cloud data includes: interpolating the labeled multi-key cloud data to obtain a new multi-key cloud dataset; filtering the new multi-key cloud dataset to determine whether the filtered new multi-key cloud dataset meets a preset fusion standard; relabeling the new multi-key cloud datasets that meet the preset fusion standard; and fusing multiple relabeled new multi-key cloud datasets to obtain the blade fused point cloud data. The step of interpolating the labeled multi-point cloud data to obtain a new multi-point cloud dataset includes: sampling the labeled multi-point cloud data to obtain multiple point cloud data of the labeled multi-point cloud data; obtaining the neighborhood plane normal vector of the multiple point cloud data using the least squares method; determining the intersection point of the neighborhood plane normal vector and the multiple point cloud data using an interpolation algorithm; and forming a set of the multiple intersection points and the multiple point cloud data as the new multi-point cloud dataset. Based on the fused point cloud data of the blades, a reverse design model is established for the multiple blades; The deviation between the blade output data of the reverse design model and the blade fused point cloud data is determined. When the deviation is within a preset deviation range, the blade output data is used to manufacture the multiple blades.

2. The method according to claim 1, characterized in that, The acquisition of multi-focus cloud data for multiple blades of the same specification includes: The multiple blades are sequentially laser-scanned to obtain point cloud data for each blade; Coordinate transformation and spatial alignment are performed on multiple point cloud data to obtain multi-point point cloud data of the multiple blades.

3. The method according to claim 1, characterized in that, The new multi-key cloud dataset is screened to determine whether it meets the preset fusion criteria, including: Determine the number of new intersection points contained in the new point cloud data within the preset filtering tolerance range in the new multi-key cloud dataset; When the number of new intersection points is at its maximum, the new point cloud data is used as a new multi-point cloud dataset that meets the fusion criteria.

4. The method according to claim 1, characterized in that, The step of establishing a reverse design model for the multiple blades based on the fused point cloud data of the blades includes: The fused point cloud data of the blades is sequentially subjected to data alignment, filtering, data completion, and feature extraction. The inverse design model of the multiple blades is obtained by using the fused point cloud data of the blades after feature extraction.

5. The method according to claim 1, characterized in that, The method further includes: When the deviation is not within the preset deviation range, the blade output data of the reverse design model is corrected using a preset correction amount; The multiple blades are manufactured using the corrected blade output data.

6. A blade manufacturing apparatus, characterized in that, include: The data acquisition module is used to acquire multi-point cloud data of multiple blades of the same specification and to mark the multi-point cloud data. The data fusion module is used to interpolate, filter, and fuse the labeled multi-key cloud data to obtain blade fused point cloud data. The process of interpolating, filtering, and fusing the labeled multi-key cloud data to obtain blade fused point cloud data includes: interpolating the labeled multi-key cloud data to obtain a new multi-key cloud dataset; filtering the new multi-key cloud dataset to determine whether it meets a preset fusion standard; relabeling the new multi-key cloud datasets that meet the preset fusion standard; and fusing multiple relabeled new multi-key cloud datasets to obtain the blade fused point cloud data. The step of interpolating the labeled multi-point cloud data to obtain a new multi-point cloud dataset includes: sampling the labeled multi-point cloud data to obtain multiple point cloud data of the labeled multi-point cloud data; obtaining the neighborhood plane normal vector of the multiple point cloud data using the least squares method; determining the intersection point of the neighborhood plane normal vector and the multiple point cloud data using an interpolation algorithm; and forming a set of the multiple intersection points and the multiple point cloud data as the new multi-point cloud dataset. The model building module is used to establish a reverse design model for the multiple blades based on the fused point cloud data of the blades. The blade manufacturing module is used to determine the deviation between the blade output data of the reverse design model and the blade fused point cloud data. When the deviation is within a preset deviation range, the multiple blades are manufactured using the blade output data.

7. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 5.

Images