Large rotary equipment blade point cloud clamp removing method and system based on self-adaptive template matching

Abstract

The invention provides a large rotary equipment blade point cloud clamp removing method and system based on self-adaptive template matching. According to the method, firstly, large-range outlier removal based on spatial features is carried out, and then refined separation is carried out in combination with standard leaf template point cloud and normal features, so that high-purity leaf body data is obtained. According to the method, the point cloud discrete noise and the clamp are automatically removed, and the point cloud data processing efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of blade clamp removal technology, and in particular to a method and system for removing point cloud clamps from blades of large rotating equipment based on adaptive template matching. Background Technology

[0002] As the core power plant of the modern aviation industry, the performance of aero-engines directly determines the safety, reliability, and economy of aircraft. Among the many key components of an aero-engine, blades bear the core function of energy conversion, and their geometric accuracy and surface quality have a decisive impact on the overall performance of the engine. The manufacturing precision of blades not only relates to the engine's thrust output and fuel efficiency, but also directly affects the engine's service life and safety performance. Therefore, high-precision geometric measurement and quality inspection of blades has become a key technical requirement in the field of aerospace manufacturing.

[0003] With the rapid development of 3D laser scanning and structured light measurement technologies, blade geometry measurement methods based on point cloud data have gradually become mainstream. However, in actual measurement processes, due to the complex shape and relatively thin material of blades, specialized fixture systems must be used to fix and support the blades to ensure the stability and safety of the measurement process. While these fixtures ensure the reliability of the measurement, they also introduce a large amount of non-target area information into the scanned point cloud data, including irrelevant data such as the fixture body, support structure, and surrounding environment. This redundant information not only occupies a considerable proportion of the total data volume but also causes geometric confusion in the blade edge region, seriously affecting the accuracy and reliability of subsequent surface reconstruction, feature extraction, and dimensional detection. Therefore, how to accurately separate and remove background noise from complex point cloud data and extract pure blade geometric information has become a key technical problem that urgently needs to be solved in the precision measurement of blades.

[0004] To address the technical challenge of fixture removal from blade point cloud data, traditional manual segmentation methods are inefficient and prone to human error, while simple geometric segmentation methods struggle to handle complex occlusion situations. Therefore, a point cloud segmentation method based on normal features is proposed. By extracting local geometric features from the point cloud, the geometric differences between the blade surface and the fixture surface can be effectively distinguished. Combined with prior knowledge of standard blade templates, accurate identification and extraction of target blade regions can be achieved, thus laying a reliable data foundation for subsequent precision measurements and quality assessments. Summary of the Invention

[0005] The purpose of this invention is to solve the problems existing in the prior art, and to propose a method and system for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching.

[0006] This invention is achieved through the following technical solution: This invention proposes a method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching, the method comprising: Step 1: First, perform large-scale outlier removal based on spatial features; Step 2: Introduce normal consistency analysis guided by standard template point cloud to achieve high-precision identification and rejection of fixture point cloud.

[0007] Furthermore, in step one, principal component analysis is first performed on the leaf data, projected onto a plane, and a spatial height threshold is set to filter out all points below the spatial height threshold in order to initially remove obvious stray noise point clouds.

[0008] Furthermore, in step one, a density-based spatial clustering method is used to divide the remaining part of the point cloud into regions.

[0009] Furthermore, the density-based spatial clustering method specifically involves identifying the main structural regions by determining whether the number of points in the local neighborhood of the point cloud exceeds a set threshold, and finally retaining the cluster with the most points and the highest density as a candidate point set containing the blade body and the fixture structure.

[0010] Furthermore, in step two, a high-quality template point cloud of a standard blade is constructed. Q={q i } Point cloud to be processed P= {p i } Coarsely register to the template coordinate system.

[0011] Furthermore, in step two, the registration employs the Iterative Closest Point (ICP) algorithm to minimize the Euclidean distance error between the two point sets:

[0012] in, R and t For rotation and translation matrices, q corr(i) for p i In template point cloud Q The corresponding point in the middle.

[0013] Furthermore, after registration is completed, for each target point p i Estimate the unit normal vector using its neighborhood points n i And obtain the normal vector of the corresponding point from the template point cloud. The angle between the two is used as the basis for judgment:

[0014] This included angle reflects the degree of consistency between the point cloud surface orientation and the standard template point cloud.

[0015] Furthermore, set an angle threshold. All points that satisfy the following conditions are defined as outliers, i.e., fixtures or non-blade structures:

[0016] The outliers can be removed from the main point cloud.

[0017] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching.

[0018] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching.

[0019] The beneficial effects of this invention are: This invention addresses the technical challenge of removing fixtures from blade point cloud data and the low efficiency of manual removal. It proposes a method and system for removing fixtures from point cloud data of large rotating equipment blades based on adaptive template matching, which realizes the automatic removal of discrete noise and fixtures in point cloud data and improves the efficiency of point cloud data processing. Attached Figure Description

[0020] To more clearly illustrate the technical solutions 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 embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0021] Figure 1 A schematic diagram of the point cloud for the blade template.

[0022] Figure 2 This is a schematic diagram for scanning to obtain actual measurement data.

[0023] Figure 3 This is a projection of the measured data.

[0024] Figure 4 This is a schematic diagram after removing a large number of outliers.

[0025] Figure 5 Image showing the result after removing fixtures following template matching. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] This invention proposes a method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching. The method first removes outliers over a large range based on spatial features, and then performs fine separation by combining standard blade template point cloud with normal features, thereby obtaining high-purity blade body data.

[0028] Specifically, this invention proposes a blade point cloud fixture removal method based on adaptive template matching, the method comprising: Step 1: First, perform large-scale outlier removal based on spatial features; In step one, in the original point cloud, the desktop and surrounding interference areas are typically distributed in the low Z-axis region with dispersed density. Therefore, it is necessary to first perform principal component analysis on the blade data, project it onto a plane, set a spatial height threshold, and filter out all points below the spatial height threshold to initially remove obvious stray noise from the point cloud.

[0029] In step one, to further eliminate isolated noise and fragment clusters formed during the measurement process, this invention employs a density-based spatial clustering method to divide the remaining part of the point cloud into regions.

[0030] The density-based spatial clustering method specifically involves identifying the main structural regions by determining whether the number of points in a local neighborhood of the point cloud exceeds a set threshold, and finally retaining the cluster with the most points and the highest density as a candidate point set containing the blade body and the fixture structure.

[0031] Although some non-target point clouds have been removed through spatial feature analysis, a large number of blade clamps remain in the point cloud due to their close fit to the blade structure and continuous morphology. Reliable separation based solely on geometric information such as height and density is insufficient. Therefore, a normal consistency analysis guided by a standard template point cloud is introduced to achieve high-precision identification and removal of clamp point clouds.

[0032] Step 2: Introduce normal consistency analysis guided by standard template point cloud to achieve high-precision identification and rejection of fixture point cloud.

[0033] In step two, a high-quality template point cloud of a standard blade is constructed. Q={q i }This template is typically derived from a design CAD model or a reference sample obtained through precise measurement. The point cloud to be processed... P={p i } Coarsely register to the template coordinate system.

[0034] In step two, the registration uses the Iterative Closest Point (ICP) algorithm to minimize the Euclidean distance error between the two point sets:

[0035] in, R and t For rotation and translation matrices, q corr(i) for p i In template point cloud Q The corresponding point in the middle.

[0036] After registration is completed, for each target point p i Estimate the unit normal vector using its neighborhood points n i And obtain the normal vector of the corresponding point from the template point cloud. The angle between the two is used as the basis for judgment:

[0037] This included angle reflects the degree of consistency between the point cloud surface orientation and the standard template point cloud. As a continuous, smooth structure, the blade surface's normal distribution should be consistent with the template height in local areas. In contrast, the fixture surface structure typically exhibits significant abrupt changes and drastic normal variations, resulting in a larger deviation in the included angle.

[0038] Set angle threshold All points that satisfy the following conditions are defined as outliers, i.e., fixtures or non-blade structures:

[0039] The outliers can be removed from the main point cloud.

[0040] Example This invention proposes a blade point cloud fixture removal method based on adaptive template matching. The method utilizes a standard blade point cloud model obtained from a CAD model as a template, such as... Figure 1 As shown. 3D laser scanning or structured light is used to acquire measured point cloud data, such as... Figure 2 and Figure 3 As shown, the data contains discrete noise points and a desktop fixture. Principal component analysis was performed on the measured data, which was then projected onto a plane to determine a height threshold, thereby removing a large number of outliers. The results are shown below. Figure 4As shown in the figure. Finally, adaptive template matching is used to remove the fixture point cloud, and the result is as follows. Figure 5 As shown.

[0041] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching.

[0042] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching.

[0043] The memory in this application embodiment can be volatile memory or non-volatile memory, or it can include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the methods described in this invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0044] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0045] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0046] It should be noted that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as execution by a hardware decoding processor, or as a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0047] The above provides a detailed description of the method and system for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching proposed in this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for removing point cloud fixtures from blades of large rotating equipment based on adaptive template matching, characterized in that, The method includes: Step 1: First, perform large-scale outlier removal based on spatial features; Step 2: Introduce normal consistency analysis guided by standard template point cloud to achieve high-precision identification and rejection of fixture point cloud.

2. The method according to claim 1, characterized in that, In step one, principal component analysis is first performed on the leaf data, which is then projected onto a plane. A spatial height threshold is set, and all points below the spatial height threshold are filtered out to initially remove obvious stray noise point clouds.

3. The method according to claim 2, characterized in that, In step one, a density-based spatial clustering method is used to divide the remaining part of the point cloud into regions.

4. The method according to claim 3, characterized in that, The density-based spatial clustering method specifically involves identifying the main structural regions by determining whether the number of points in a local neighborhood of the point cloud exceeds a set threshold, and finally retaining the cluster with the most points and the highest density as a candidate point set containing the blade body and the fixture structure.

5. The method according to claim 4, characterized in that, In step two, a high-quality template point cloud of a standard blade is constructed. Q={q i } Point cloud to be processed P={p i } Coarsely register to the template coordinate system.

6. The method according to claim 5, characterized in that, In step two, the registration uses the Iterative Closest Point (ICP) algorithm to minimize the Euclidean distance error between the two point sets: in, R and t For rotation and translation matrices, q corr(i) for p i In template point cloud Q The corresponding point in the middle.

7. The method according to claim 6, characterized in that, After registration is completed, for each target point p i Estimate the unit normal vector using its neighborhood points n i And obtain the normal vector of the corresponding point from the template point cloud. The angle between the two is used as the basis for judgment: This included angle reflects the degree of consistency between the point cloud surface orientation and the standard template point cloud.

8. The method according to claim 7, characterized in that, Set angle threshold All points that satisfy the following conditions are defined as outliers, i.e., fixtures or non-blade structures: The outliers can be removed from the main point cloud.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium for storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-8.

Images