Method for detecting profile of double notch blade of precision forged blade inlet and exhaust edge and related equipment

Abstract

The application relates to the technical field of aero-engine blade detection, and discloses a precision-forged blade inlet and outlet edge double-gap blade profile detection method and related equipment, which accurately describes the relationship between the inlet and outlet edges in an independent coordinate system and bidirectional progressive fitting through improved DBSCAN clustering algorithm and double-domain decoupling strategy, effectively processes point cloud data containing noise points, realizes regional decoupling to reduce the influence of coupling error on profile detection, guarantees the smoothness of the fitting curve, avoids the emergence of conditions such as curvature mutation which do not conform to the actual blade shape, and finally solves the technical problems of multi-gap coupling error, forging surface noise point interference and data correlation loss existing in the profile detection process.

Description

Technical Field

[0001] This invention relates to the field of precision forging technology for aero-engines, specifically to a method and related equipment for detecting the profile of a double-notch airfoil on the inlet and outlet sides of a precision forged blade. Background Technology

[0002] In the manufacturing process of aero-engines, the surface accuracy of precision-forged blades has a crucial impact on engine performance, and the contour measurement of the double-notch region on the inlet / exhaust sides is one of the key steps to ensure blade surface accuracy. However, the contour measurement of the double-notch region on the inlet / exhaust sides faces a series of technical bottlenecks in precision-forged blade surface inspection. These problems severely affect the accuracy and efficiency of the inspection, specifically including the following:

[0003] Multi-notch coupling interference: When inspecting the contour of the double-notch region on the inlet / exhaust side, existing methods (such as coordinate measuring machine discrete sampling) introduce coupling errors when processing the point cloud data of this region. This coupling error arises from the complex double-notch structure of the inlet / exhaust side and the mutual influence between the notches. When the inlet / exhaust side is inspected simultaneously, this coupling error is further amplified, with a maximum deviation reaching 0.1 mm. This means that in actual inspection, the measurement result may deviate from the true value by 0.1 mm. For components with extremely high precision requirements, such as precision-forged blades for aero-engines, such deviation is unacceptable.

[0004] Lack of Data Correlation: Current commercial software lacks topological correlation analysis for data in double-gap regions. Topological correlation analysis is crucial for understanding the relationship between the intake / exhaust edge data. Due to this lack of analysis, a high error rate (greater than 8%) occurs when matching intake / exhaust edge data. This means that during data processing, the intake / exhaust edge data cannot be accurately matched and integrated, thus affecting the accuracy of the overall contour detection.

[0005] The algorithm lacks adaptability: the existing RANSAC algorithm has limitations in handling regions with abrupt changes in hypercurvature (when the curvature difference is greater than 0.1 mm). -1 In some cases, the fitting residual is too large. The fitting residual is a crucial indicator of the algorithm's fitting performance. In this scenario, the algorithm's fitting residual exceeds 0.1 mm, failing to meet ASME standards. This indicates that the existing algorithm cannot effectively fit data when dealing with the unique curvature variation in the double-notch region of the forged blade's inlet / outlet edges, thus affecting the accuracy of the profile detection.

[0006] The published literature, "Research on the Inspection of Blade Forging Surfaces" (Aerospace Manufacturing Technology, 2022, Vol. 65), points out that during the forging inspection process, the point cloud distortion rate can reach as high as 12% due to the influence of plastic deformation. This high point cloud distortion rate further illustrates the complex situation faced in the inspection of precision-forged blade surfaces, thus requiring the development of specialized compensation algorithms to solve these problems. Summary of the Invention

[0007] In order to overcome the defects of the prior art, the present invention aims to provide a method and related equipment for detecting the profile of a double-notch airfoil on the intake and exhaust sides of a precision forged blade, so as to solve the technical problems of multi-notch coupling error, noise interference on the surface of the forging, and lack of data correlation in the profile detection process.

[0008] This invention is achieved through the following technical solution:

[0009] In a first aspect, the present invention provides a method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides, comprising:

[0010] Obtain measured point cloud data after radius compensation;

[0011] The measured point cloud data is preprocessed to obtain valid point cloud data;

[0012] Based on the effective point cloud data, a mathematical model of the intake / exhaust edge is constructed to decouple the region and obtain the intake / exhaust edge data respectively;

[0013] The data of the inlet / outlet sides are subjected to bidirectional progressive fitting, and the updated and optimized data are used to generate the profile detection results. Based on the profile detection results, the profile of the double-notch airfoil of the inlet and outlet sides of the precision forged blade is detected.

[0014] Preferably, in the step of obtaining the measured point cloud data after radius compensation, the measured point cloud data is obtained by detecting the surface of the double-notch airfoil on the inlet and outlet sides of the precision-forged blade.

[0015] Preferably, in the step of preprocessing the measured point cloud data to obtain effective point cloud data, the measured point cloud data is preprocessed by an improved DBSCAN clustering algorithm, wherein the preprocessing includes hardened layer noise removal and plastic deformation compensation.

[0016] Preferably, the parameters of the improved DBSCAN clustering algorithm are Eps = 0.05mm and MinPts = 6.

[0017] Preferably, in the step of constructing a mathematical model of the intake / exhaust edge based on the effective point cloud data for region decoupling, the weights of the mathematical models of the intake / exhaust edge are allocated according to the characteristics of the intake / exhaust edge, wherein the weight of the intake edge is set in the range of 0-1, and the weight of the exhaust edge is set in the range of 0-1.

[0018] Preferably, when performing regional decoupling of the mathematical model of the intake / exhaust side, the region is divided and identification thresholds for the intake and exhaust sides are set, and the intake / exhaust side data are obtained respectively through the identification thresholds.

[0019] Preferably, the step of performing bidirectional progressive fitting on the intake / exhaust edge data to obtain the fitted data is as follows:

[0020] The intake edge contour curve is obtained by using a forward iteration method and the LM algorithm for fitting.

[0021] The exhaust edge is fitted using an inverse iteration method and the LM algorithm to obtain the contour curve of the exhaust edge;

[0022] The contour curves of the intake and exhaust sides are updated and optimized by cross-domain residual verification after iteration, and the contour detection results are generated.

[0023] Secondly, the present invention also provides a precision forged blade inlet and outlet edge double-notch airfoil profile detection system, comprising:

[0024] The data acquisition module is used to acquire measured point cloud data after radius compensation;

[0025] The data preprocessing module is used to preprocess the measured point cloud data to obtain effective point cloud data;

[0026] The region decoupling module is used to construct a mathematical model of the intake / exhaust edges based on the effective point cloud data to decouple the regions and obtain the intake / exhaust edge data respectively.

[0027] The data fitting and optimization module is used to perform bidirectional progressive fitting on the data of the inlet / outlet sides and update the optimized profile detection results. Based on the profile detection results, the profile of the double-notch airfoil of the inlet and outlet sides of the precision forged blade is detected.

[0028] Thirdly, the present invention also provides a mobile terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for detecting the profile of double-notch airfoil at the inlet and outlet edges of precision forged blades.

[0029] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for detecting the profile of a double-notch airfoil at the inlet and outlet edges of a precision-forged blade.

[0030] Compared with the prior art, the present invention has the following beneficial technical effects:

[0031] This invention provides a method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet edges. By employing an improved DBSCAN clustering algorithm, it effectively processes noisy point cloud data, significantly improving the data quality. The use of a dual-domain decoupling strategy more accurately describes the relationship between the inlet and outlet edges in independent coordinate systems, effectively achieving region decoupling and reducing the impact of coupling errors on profile detection. The use of bidirectional progressive fitting ensures the smoothness of the fitted curve, avoiding abrupt changes in curvature that do not conform to the actual blade shape.

[0032] Furthermore, this invention reduces the simultaneous detection time for both notches to 1.3 times that of single-sided detection. This means that in actual production testing, detection efficiency can be greatly improved, detection time costs reduced, and production efficiency increased.

[0033] Furthermore, by performing bidirectional progressive fitting and updating the optimized profile detection results, the error rate in the inlet / outlet edge matching is effectively reduced, resulting in high-precision detection results. This is of great significance for the quality control of precision forged blades for aero-engines, and can ensure that the surface accuracy of the blades meets the stringent engineering requirements. Attached Figure Description

[0034] Figure 1 This is a flowchart of the method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides.

[0035] Figure 2 This is a schematic diagram of the fitting of the intake side blade profile of the precision forged blade of the present invention;

[0036] Figure 3 This is a schematic diagram of the profile fitting of the exhaust edge blade of the precision forged blade of the present invention;

[0037] Figure 4 This is a schematic diagram of the profile and upper and lower limit data of the lower intake side blade of the precision forged blade of the present invention;

[0038] Figure 5 This is a schematic diagram of the lower exhaust edge profile and upper and lower limit data of the precision forged blade of the present invention;

[0039] Figure 6 This is a schematic diagram of the precision forged blade inlet and outlet double-notch airfoil profile detection system of the present invention;

[0040] In the diagram: 1. Data acquisition module; 2. Data preprocessing module; 3. Region decoupling module; 4. Data fitting and optimization module. Detailed Implementation

[0041] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0043] The purpose of this invention is to provide a method and related equipment for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides, so as to solve the technical problems of multi-notch coupling error, noise interference on the surface of the forging, and lack of data correlation in the profile detection process.

[0044] The present invention will now be described in further detail with reference to the accompanying drawings:

[0045] Example 1

[0046] See Figure 1 In one embodiment of the present invention, a method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides is provided, comprising:

[0047] Step 1: Obtain the measured point cloud data after radius compensation;

[0048] Specifically, measured point cloud data was obtained by inspecting the surface of the double-notch airfoil at the inlet and outlet edges of the precision-forged blade.

[0049] Step 2: Preprocess the measured point cloud data to obtain valid point cloud data;

[0050] Specifically, the measured point cloud data is preprocessed by improving the DBSCAN clustering algorithm, which includes hardening layer noise removal and plastic deformation compensation.

[0051] The parameters of the improved DBSCAN clustering algorithm are Eps = 0.05mm and MinPts = 6.

[0052] This algorithm, through specific parameter settings, can effectively process noisy point cloud data. After processing by this algorithm, the noise filtering rate can reach ≥95%, greatly improving the quality of point cloud data.

[0053] In this embodiment, layered filtering is performed, with the first step including hardening layer noise removal:

[0054] stage1=enhanced_dbscan(points,eps=0.05*(1+0.0023*47),min_samples=8);

[0055] The second layer includes plastic deformation compensation:

[0056] stage2=apply_plastic_compensation(stage1,delta=0.12,T=120);

[0057] In this embodiment, the output is valid point cloud data with a noise content of ≤5%. This indicates that the quality of the point cloud data is significantly improved after noise-reducing point cloud preprocessing, meeting the data quality requirements of subsequent contour detection.

[0058] Step 3: Construct a mathematical model of the intake / exhaust edges based on the effective point cloud data to decouple the regions and obtain the intake / exhaust edge data respectively;

[0059] Specifically, the weights of the mathematical models for the intake and exhaust sides are allocated based on their characteristics, with the intake side weighted at 0.55 and the exhaust side weighted at 0.45. This weight allocation is derived from a comprehensive consideration of the importance of the intake and exhaust sides in the overall blade structure, as well as their own geometric characteristics.

[0060] The mathematical model formula for the intake / exhaust edge is as follows:

[0061] W ex =1-W in

[0062] Among them, W in: The weight of the intake edge in the independent coordinate system, used to establish independent coordinate systems for the intake / exhaust edges to achieve region decoupling. After comprehensively considering the importance and geometric characteristics of the intake / exhaust edges in the blade structure, the value is taken as 0.55. W ex The weight of the exhaust edge in the independent coordinate system is given by W. ex =1-W in Confirmed, the value is 0.45. κ in The local curvature of the intake side is used in calculating the intake side weight W. 进气边 The parameters. κ ex Local curvature of the exhaust edge, used to calculate the exhaust edge weight W. ex It also participates in the intake side weight W in The calculation.

[0063] By using a mathematical model of the intake / exhaust edges, the relationship between the intake / exhaust edges in an independent coordinate system can be described more accurately, thereby effectively achieving region decoupling and reducing the impact of coupling errors on contour detection.

[0064] In this embodiment, the mathematical model of the inlet / outlet edge is initialized and aligned, and the improved ICP algorithm is executed. The feature weights are assigned as follows: leading edge weight 0.6, exhaust edge weight 0.3, and leaf back / pot weight 0.1. KD-Tree is used to accelerate the nearest point search.

[0065] In this embodiment, the data is in .asc format with a data density of 200 points / mm. 2 This data format and density are determined based on actual testing needs and equipment characteristics, and can meet subsequent processing requirements.

[0066] When performing region segmentation, it is necessary to set recognition thresholds for the air intake and exhaust edges. For the air intake edge, the recognition threshold is set to a curvature ≥ 0.08mm. -1 ,like Figure 2 As shown; for the exhaust edge, the recognition threshold is set to a curvature ≥ 0.07mm. -1 These thresholds were determined through the analysis of a large number of precision-forged blade samples and by considering the geometric characteristics of the inlet / exhaust edges. They can accurately distinguish the inlet / exhaust edges from the overall data, laying the foundation for the subsequent dual-domain decoupling strategy.

[0067] Step 4: Perform bidirectional progressive fitting on the data of the inlet / outlet sides, and update and optimize to generate the profile detection results. Based on the profile detection results, complete the detection of the profile of the double-notch blade at the inlet and outlet sides of the precision forged blade.

[0068] Specifically, for the air intake edge, a forward iterative approach is adopted, using the LM algorithm for fitting, where μ = 0.005. This parameter value is determined based on the specific data characteristics and fitting requirements of the air intake edge, ensuring that the true contour curve is effectively approximated during the forward iterative process.

[0069] For the exhaust side, a reverse iteration method is used, also employing the LM algorithm, but here μ = 0.008. This parameter is set to take into account the differences in geometry and data distribution between the exhaust side and the intake side. By adjusting the μ value, the characteristics of the exhaust side are adapted to ensure the accuracy of the reverse iteration.

[0070] During the bidirectional progressive fitting process, cross-domain residual verification is performed every 5 iterations. The verification threshold is set to ΔRMS ≤ 0.005 mm. This periodic verification mechanism can promptly detect and correct any deviations that may occur between the intake and exhaust sides during the fitting process, ensuring that the entire fitting process proceeds in the accurate direction.

[0071] Specifically, this embodiment employs a bidirectional progressive fitting method to process the intake / exhaust side data; fitting operations for the intake side (using forward iteration) and the exhaust side (using backward iteration) are performed simultaneously. During this process, a cross-domain residual check is performed every 5 iterations. This iterative and check approach can promptly detect and correct any deviations that may occur during the fitting process.

[0072] Its convergence conditions include two aspects: first, the spatial residual needs to be ≤0.02mm, which ensures the accuracy of the fitting result in spatial location; second, the curvature gradient must be continuous (C 2 The condition of "continuous" ensures the smoothness of the fitted curve from a mathematical perspective, avoiding situations such as abrupt changes in curvature that do not conform to the actual blade shape.

[0073] Specifically, in the iterative optimization process, the first step is a dynamic interruption strategy: adaptive segmentation based on curvature and error. The specific formula is as follows:

[0074] Mathematical principles:

[0075] 1. Curvature mutation detection:

[0076] △κ i =||κ i+1 -κ i ||>τ k (τ k =0.1mm -1 )

[0077] 2. Error accumulation judgment:

[0078]

[0079] Where, Δκ i The change in curvature at the i-th point is expressed by ||κ|| i+1 -k i The value is calculated and used to determine whether a curvature abrupt change occurs. k i κ: The curvature at the i-th point. i+1 τ: The curvature at the (i+1)th point. κ Curvature abrupt change threshold, with a value of 0.1mm. -1 At that time, it was determined that a curvature abrupt change occurred at the i-th point. k: Starting point index, used as the starting position when calculating the accumulated error. m: The range of points used to determine the accumulated error. τ ∈ Error accumulation judgment threshold, such as τ ∈ =0.02mm, used to determine whether the cumulative error from the point to the fitting endpoint exceeds the allowable range. j: loop variable, traversing the range from k to k+m, used to calculate the cumulative error. f(j): the point on the fitted curve corresponding to point j.

[0080] Secondly, incremental fitting: retaining the condition number of the Jacobian matrix from the previous fitting, the LM algorithm is used to update the parameters (damping factor μ = 0.01), as shown in the following formula:

[0081] Improvements to the LM algorithm:

[0082] 1. Adaptive updating of damping factor:

[0083]

[0084] (n=2, initial μ=0.01)

[0085] 2. Jacobian matrix reuse:

[0086] J k+1 =J k +△J where||△J|| F <∈

[0087] Where, μ k : The damping factor in the k-th iteration, used to control the convergence characteristics of the Levenberg-Marquardt (LM) algorithm, with an initial value of μ0 = 0.01. k+1 : The damping factor in the (k+1)th iteration, based on μ k Its value is determined by the validity of the gradient descent direction in the current iteration. J: Represents the partial derivative of the residual function with respect to the parameters, with a dimension of m×n (m is the number of data points, n is the number of parameters). r: Residual vector, representing the difference between the model's predicted values ​​and the actual observed values, with a dimension of m×1. ||J Tr‖: Norm of the product of the transpose of the Jacobian matrix and the residual vector (usually the L2 norm), used to measure the effectiveness of the gradient descent direction in the current iteration. η: Adjustment factor, with a value of 2, used to control the increase or decrease of the damping factor μ.

[0088] This embodiment establishes a versioned data storage structure and implements a differential storage mechanism, reducing storage overhead per iteration by 72%.

[0089] In this embodiment, the results are output according to the above, generating a profile report conforming to the GBT 1958-2017 standard and outputting a traceable iterative process chain (including 6σ process capability analysis).

[0090] Example 2

[0091] See Figures 2 to 3 In one embodiment of the present invention, a schematic diagram of contour fitting for a method for detecting the profile of a double-notch airfoil at the inlet and outlet edges of a precision-forged blade is provided:

[0092] Figure 2 for Figure 1 A schematic diagram of the profile fitting of the intake side blade of the precision-forged blade generated from the data collected by the method;

[0093] Figure 3 for Figure 1 A schematic diagram of the contour fitting of the exhaust edge blade shape of the precision forged blade generated from the collected data;

[0094] Example 3

[0095] See Figures 4 to 5 In one embodiment of the present invention, measured comparative data of a method for detecting the profile of a double-notch airfoil at the inlet and outlet edges of a precision-forged blade are provided:

[0096] Figure 4 The existing method shows that the upper and lower limits of the actual measured data of the intake edge are 0.276 mm and -0.012 mm, respectively. After the improvement of this method, the upper and lower limits of the actual measured data of the intake edge are 0.190 mm and -0.005 mm, respectively.

[0097] Figure 5 The existing method shows that the upper and lower limits of the actual measured data of the intake side are 0.190 mm and -0.012 mm, respectively. After the improvement of this method, the upper and lower limits of the actual measured data of the intake side are 0.150 mm and 0.000 mm, respectively.

[0098] In summary, this invention provides a method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides. By employing an improved DBSCAN clustering algorithm, it can effectively process noisy point cloud data, significantly improving the quality of the point cloud data. The use of a dual-domain decoupling strategy can more accurately describe the relationship between the inlet and outlet sides in independent coordinate systems, thereby effectively achieving region decoupling and reducing the impact of coupling errors on profile detection. The use of bidirectional progressive fitting ensures the smoothness of the fitted curve, avoiding abrupt changes in curvature and other deviations from the actual blade shape.

[0099] Example 4

[0100] according to Figure 6 As shown, this embodiment provides a double-notch airfoil profile detection system for precision-forged blades at the inlet and outlet edges, including:

[0101] Data acquisition module 1 is used to acquire measured point cloud data after radius compensation;

[0102] Data preprocessing module 2 is used to preprocess the measured point cloud data to obtain effective point cloud data;

[0103] The region decoupling module 3 is used to construct a mathematical model of the intake / exhaust edge based on the effective point cloud data to perform region decoupling and obtain the intake / exhaust edge data respectively;

[0104] The data fitting and optimization module 4 is used to perform bidirectional progressive fitting on the data of the inlet / outlet sides and update the optimized profile detection results. Based on the profile detection results, the profile of the double-notch blade of the inlet and outlet sides of the precision forged blade is detected.

[0105] Example 5

[0106] The present invention also provides a mobile terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, such as a program for detecting the profile of a double-notch airfoil at the inlet and outlet edges of a precision-forged blade.

[0107] When the processor executes the computer program, it implements the steps of the above-described method for detecting the profile of the double-notch airfoil at the inlet and outlet edges of precision-forged blades, for example:

[0108] Obtain measured point cloud data after radius compensation;

[0109] The measured point cloud data is preprocessed to obtain valid point cloud data;

[0110] Based on the effective point cloud data, a mathematical model of the intake / exhaust edge is constructed to decouple the region and obtain the intake / exhaust edge data respectively;

[0111] The data of the inlet / outlet sides are subjected to bidirectional progressive fitting, and the updated and optimized data are used to generate the profile detection results. Based on the profile detection results, the profile of the double-notch airfoil of the inlet and outlet sides of the precision forged blade is detected.

[0112] Alternatively, when the processor executes the computer program, it implements the functions of each module in the above system, for example:

[0113] Data acquisition module 1 is used to acquire measured point cloud data after radius compensation;

[0114] Data preprocessing module 2 is used to preprocess the measured point cloud data to obtain effective point cloud data;

[0115] The region decoupling module 3 is used to construct a mathematical model of the intake / exhaust edge based on the effective point cloud data to perform region decoupling and obtain the intake / exhaust edge data respectively;

[0116] The data fitting and optimization module 4 is used to perform bidirectional progressive fitting on the data of the inlet / outlet sides and update the optimized profile detection results. Based on the profile detection results, the profile of the double-notch blade of the inlet and outlet sides of the precision forged blade is detected.

[0117] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the mobile terminal.

[0118] For example, the computer program can be divided into a data acquisition module 1, a data preprocessing module 2, a region decoupling module 3, and a data fitting and optimization module 4;

[0119] The specific functions of each module are as follows:

[0120] Data acquisition module 1 is used to acquire measured point cloud data after radius compensation;

[0121] Data preprocessing module 2 is used to preprocess the measured point cloud data to obtain effective point cloud data;

[0122] The region decoupling module 3 is used to construct a mathematical model of the intake / exhaust edge based on the effective point cloud data to perform region decoupling and obtain the intake / exhaust edge data respectively;

[0123] The data fitting and optimization module 4 is used to perform bidirectional progressive fitting on the data of the inlet / outlet sides and update the optimized profile detection results. Based on the profile detection results, the profile of the double-notch blade of the inlet and outlet sides of the precision forged blade is detected.

[0124] The mobile terminal can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The mobile terminal may include, but is not limited to, a processor and memory.

[0125] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the mobile terminal, connecting various parts of the mobile terminal via various interfaces and lines.

[0126] The memory can be used to store the computer program and / or module. The processor implements various functions of the mobile terminal by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.

[0127] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function (such as sound playback or image playback). The data storage area may store data created based on the use of the phone (such as audio data or a phonebook). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMediaCards (SMC), Secure Digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0128] Example 6

[0129] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for detecting the profile of a double-notch airfoil at the inlet and outlet sides of a precision-forged blade.

[0130] If the modules / units integrated in the mobile terminal are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0131] Based on this understanding, all or part of the processes in the above method can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above-described aggregated reinforcement learning resource scheduling method. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form.

[0132] The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0133] It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides, characterized in that, include: Obtain measured point cloud data after radius compensation; The measured point cloud data is preprocessed to obtain valid point cloud data; Based on the effective point cloud data, a mathematical model of the intake / exhaust edge is constructed to decouple the region and obtain the intake / exhaust edge data respectively; In the step of constructing a mathematical model of the intake / exhaust edge based on the effective point cloud data to decouple the region, the weights of the mathematical model of the intake / exhaust edge are allocated according to the characteristics of the intake / exhaust edge. The mathematical model formula for the intake / exhaust edge is as follows: in, This represents the weight of the intake edge in an independent coordinate system. The weight of the exhaust edge in the independent coordinate system; This refers to the local curvature of the air intake edge; The local curvature of the exhaust edge; The data of the inlet / outlet sides are subjected to bidirectional progressive fitting, and the updated and optimized data are used to generate the profile detection results. Based on the profile detection results, the profile of the double-notch airfoil of the inlet and outlet sides of the precision forged blade is detected. The optimization process employs a forward iteration method on the intake side and a reverse iteration method on the exhaust side. During the iterative optimization process, a dynamic interruption strategy is used: adaptive segmentation is performed based on curvature and error, with the specific formula as follows: in, For the first The change in curvature at each point; For the first Curvature at each point; For the first Curvature at each point; The curvature abrupt change threshold is set to a value of [value missing]. ; Index of the starting point; Used to determine the range of points for accumulated calculation errors; The threshold for error accumulation is used to determine the error. This is used to determine whether the cumulative error from the point to the fitting endpoint exceeds the allowable range; For loop variables; For points The points on the corresponding fitted curve.

2. The method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides according to claim 1, characterized in that, In the step of obtaining the measured point cloud data after radius compensation, the measured point cloud data is obtained by detecting the surface of the double-notch airfoil on the inlet and outlet sides of the precision-forged blade.

3. The method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides according to claim 1, characterized in that, In the step of preprocessing the measured point cloud data to obtain effective point cloud data, the measured point cloud data is preprocessed by an improved DBSCAN clustering algorithm, wherein the preprocessing includes hardened layer noise removal and plastic deformation compensation.

4. The method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides according to claim 3, characterized in that, The parameters of the improved DBSCAN clustering algorithm are Eps = 0.05mm and MinPts = 6.

5. The method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides according to claim 1, characterized in that, When performing region decoupling of the mathematical model of the intake / exhaust side, the region is divided and the identification thresholds of the intake and exhaust sides are set. The intake / exhaust side data are obtained by using the identification thresholds.

6. The method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides according to claim 1, characterized in that, The specific process for obtaining fitted data by performing bidirectional progressive fitting on the intake / exhaust side data is as follows: The intake edge contour curve is obtained by using a forward iteration method and the LM algorithm for fitting. The exhaust edge is fitted using an inverse iteration method and the LM algorithm to obtain the contour curve of the exhaust edge; The contour curves of the intake and exhaust sides are updated and optimized by cross-domain residual verification after iteration, and the contour detection results are generated.

7. A system for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides, characterized in that, A method for detecting the profile of a precision-forged blade with double notches on the inlet and outlet sides, based on any one of claims 1-6, includes: The data acquisition module is used to acquire measured point cloud data after radius compensation; The data preprocessing module is used to preprocess the measured point cloud data to obtain effective point cloud data; The region decoupling module is used to construct a mathematical model of the intake / exhaust edges based on the effective point cloud data to decouple the regions and obtain the intake / exhaust edge data respectively. The data fitting and optimization module is used to perform bidirectional progressive fitting on the data of the inlet / outlet sides and update the optimized profile detection results. Based on the profile detection results, the profile of the double-notch airfoil of the inlet and outlet sides of the precision forged blade is detected.

8. A mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for detecting the profile of the double-notch air intake and exhaust sides of precision forged blades as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for detecting the profile of the double-notch airfoil at the inlet and outlet sides of the precision forged blade as described in any one of claims 1 to 6.

Images