Precisely-forged blade intake and exhaust edge double-notch blade profile tolerance detection method and related equipment

Abstract

The invention relates to the technical field of aero-engine blade detection, and discloses a precision forging blade intake and exhaust edge double-notch blade profile tolerance detection method and related equipment, and the method comprises the steps: employing an improved DBSCAN clustering algorithm, employing a double-domain decoupling strategy to accurately describe the relation of intake / exhaust edges in an independent coordinate system, and carrying out the bidirectional progressive fitting, according to the method, point cloud data containing noisy points are effectively processed, regional decoupling is achieved, the influence of coupling errors on profile tolerance detection is reduced, the smoothness of a fitting curve is guaranteed, the situation that curvature sudden change and the like do not conform to the actual blade shape is avoided, and the accuracy of profile tolerance detection is improved. And finally, the technical problems of multi-notch coupling errors, forge piece surface noise interference and data relevance deficiency in the profile tolerance detection process are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of precision forging of aircraft engines, and in particular to a method for detecting the profile of a double-notch blade profile on the intake and exhaust edges of a precision forged blade and related equipment. Background Art

[0002] During the manufacturing process of aircraft engines, the surface accuracy of precision-forged blades plays a crucial role in engine performance. Profiling the double-notch area on the inlet and exhaust edges is a key step in ensuring blade surface accuracy. During precision-forged blade surface inspection, profiling the double-notch area on the inlet and exhaust edges faces a series of technical bottlenecks that severely impact inspection accuracy and efficiency, including the following:

[0003] Multi-notch coupling interference: When detecting the contour of the double-notch area on the intake / exhaust edge, existing methods (such as discrete sampling of a three-coordinate machine) will produce coupling errors when processing the point cloud data of this area. This coupling error is caused by the complex double-notch structure of the intake / exhaust edge and the mutual influence between the various notches. When the intake / exhaust edges are inspected at the same time, this coupling error will be further amplified, and the maximum deviation can reach 0.1mm. This means that in actual inspection, the measurement results may deviate from the true value by 0.1mm. For components such as aircraft engine precision forging blades that require extremely high precision, such deviations are unacceptable.

[0004] Lack of Data Correlation: Current commercial software lacks topological correlation analysis when processing data in double-notch areas. Topological correlation analysis is crucial for understanding the relationship between intake and exhaust edge data. This lack of analysis results in high errors in intake and exhaust edge data matching, exceeding 8%. This means that during data processing, the intake and exhaust edge data cannot be accurately aligned and integrated, affecting the accuracy of the overall profile measurement.

[0005] Insufficient algorithm adaptability: The existing RANSAC algorithm is not good at processing double curvature mutation areas (when the curvature difference is greater than 0.1mm). -1 When the algorithm is used (for example, the finite element model), the fitting residual is too large. The fitting residual is a key indicator of the algorithm's fitting performance. In this case, the fitting residual exceeds 0.1mm, failing to meet ASME standards. This indicates that existing algorithms cannot effectively fit the data for the unique curvature variation found in the double-notched area of the inlet and exhaust edges of precision-forged blades, thus affecting the accuracy of profile detection.

[0006] The published literature, "Research on Blade Forging Surface Inspection" (Aerospace Manufacturing Technology, 2022, Vol. 65), indicates that during forging inspection, point cloud distortion can reach as high as 12% due to plastic deformation. This high point cloud distortion further illustrates the complexities of precision forged blade surface inspection, necessitating the development of specialized compensation algorithms to address these issues. Summary of the Invention

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

[0008] The present invention is achieved through the following technical solutions:

[0009] In a first aspect, the present invention provides a method for detecting the profile of a double-notched blade profile on the intake and exhaust edges of a precision forged blade, comprising:

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

[0011] Preprocessing the measured point cloud data to obtain valid point cloud data;

[0012] Constructing a mathematical model of the intake / exhaust edge according to the effective point cloud data to perform regional decoupling, and obtaining intake / exhaust edge data respectively;

[0013] The inlet / exhaust edge data is bidirectionally progressively fitted, and the contour detection results are generated after updating and optimization. The contour detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade is completed based on the contour detection results.

[0014] Preferably, in the step of obtaining the radius-compensated measured point cloud data, the measured point cloud data is obtained by detecting the double-notched blade profile surface of the precision-forged blade inlet and exhaust edges.

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

[0016] Preferably, the parameters of the improved DBSCAN clustering algorithm are Eps=0.05mm, 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 regional decoupling, the weight of the mathematical model of the intake / exhaust edge is allocated according to the characteristics of the intake / exhaust edge, wherein the weight setting range of the intake edge is 0-1, and the weight setting range of the exhaust edge is 0-1.

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

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

[0020] The forward iteration method is used on the intake side, and the LM algorithm is used to fit the contour curve of the intake side;

[0021] The exhaust edge is fitted by reverse iteration and LM algorithm to obtain the exhaust edge contour curve;

[0022] The contour curves of the intake side and the exhaust side are iteratively subjected to cross-domain residual verification to complete the update optimization and generate the contour detection results.

[0023] In a second aspect, the present invention further provides a system for detecting the profile of a double-notched blade profile on the intake and exhaust edges of a precision forged blade, comprising:

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

[0025] A data preprocessing module, configured to preprocess the measured point cloud data to obtain valid point cloud data;

[0026] A regional decoupling module is used to construct a mathematical model of the intake / exhaust edge according to the effective point cloud data to perform regional decoupling and obtain intake / exhaust edge data respectively;

[0027] The data fitting optimization module is used to perform bidirectional progressive fitting on the inlet / exhaust edge data, and to generate the contour detection results after updating and optimization. The contour detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade is completed based on the contour detection results.

[0028] In a third aspect, the present invention also provides a mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for detecting the double-notch blade profile of the inlet and exhaust edges of a precision-forged blade are implemented as described above.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for detecting the double-notch blade profile of the inlet and exhaust edges of a precision-forged blade as described above.

[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 double-notched blade on the intake and exhaust edges of a precision-forged blade. By employing an improved DBSCAN clustering algorithm, it effectively processes noisy point cloud data, significantly improving its quality. A dual-domain decoupling strategy more accurately describes the relationship between the intake and exhaust edges in independent coordinate systems, effectively achieving regional decoupling and reducing the impact of coupling errors on profile detection. Bidirectional progressive fitting ensures the smoothness of the fitting curve, avoiding sudden changes in curvature that deviate from the actual blade shape.

[0032] Furthermore, the present invention shortens the time required for simultaneous double-notch detection to 1.3 times that of single-notch detection, which means that in actual production testing, detection efficiency can be greatly improved, detection time costs can be reduced, and production efficiency can be improved.

[0033] Furthermore, by performing bidirectional progressive fitting and updating the optimization, the contour detection results are generated. This result effectively reduces the error rate in the intake / exhaust edge matching and obtains high-precision detection results. It is of great significance for the quality control of precision forged blades of aircraft engines and can ensure that the surface accuracy of the blades meets strict engineering requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of the method for detecting the profile of a double-notch blade profile on the intake and exhaust edges of a precision forged blade according to the present invention;

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

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

[0037] Figure 4 Schematic diagram of the lower inlet edge blade profile and upper and lower limit data of the precision forged blade of the present invention;

[0038] Figure 5 Schematic diagram of the blade profile and upper and lower limit data of the lower outlet edge of the precision forged blade of the present invention;

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

[0040] In the figure: 1. Data acquisition module; 2. Data preprocessing module; 3. Regional decoupling module; 4. Data fitting optimization module. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

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

[0044] The present invention is described in further detail below with reference to the accompanying drawings:

[0045] Example 1

[0046] See also Figure 1 In one embodiment of the present invention, a method for detecting the profile of a double-notched blade on the inlet and exhaust edges of a precision forged blade is provided, comprising:

[0047] Step 1: Obtaining radius-compensated measured point cloud data;

[0048] Specifically, measured point cloud data is obtained by detecting the double-notch blade surface at the inlet and exhaust edges of the precision forged blade.

[0049] Step 2: preprocessing 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, where the preprocessing includes hardening layer noise removal and plastic deformation compensation.

[0051] Among them, the parameters of the improved DBSCAN clustering algorithm are Eps=0.05mm, MinPts=6.

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

[0053] In this embodiment, layered filtering is performed, the first of which includes hardening layer noise removal:

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

[0055] The second layer includes compensation for plastic deformation:

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

[0057] In this embodiment, the output is valid point cloud data, in which the noise content is ≤5%. This shows that after the anti-noise point cloud preprocessing, the quality of the point cloud data has been significantly improved and can meet the data quality requirements of the subsequent contour detection.

[0058] Step 3: constructing a mathematical model of the intake / exhaust edge based on the valid point cloud data to perform regional decoupling and obtain intake / exhaust edge data respectively;

[0059] Specifically, the weights of the mathematical models for the intake and exhaust edges are assigned based on their characteristics, with the intake edge weighted at 0.55 and the exhaust edge weighted at 0.45. This weighting is based on a comprehensive consideration of multiple factors, including the importance of the intake and exhaust edges in the overall blade structure and their geometric characteristics.

[0060] The mathematical model formula of 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 the intake / exhaust edge independent coordinate system to achieve regional decoupling. After comprehensively considering the importance of the intake / exhaust edge in the blade structure and geometric characteristics and other factors, the value is set to 0.55. ex : The weight of the exhaust edge in the independent coordinate system, represented by W ex =1-W in Determine, the value is 0.45. in : The local curvature of the intake edge is used to calculate the intake edge weight W 进气边 Parameters. ex : Local curvature of the exhaust edge, used to calculate the exhaust edge weight W ex , and also participates in the intake edge weight W in Calculation.

[0063] Through the mathematical model of the intake / exhaust edge, the relationship between the intake / exhaust edges in the independent coordinate system can be described more accurately, thereby effectively achieving regional decoupling and reducing the impact of coupling errors on profile detection.

[0064] In this embodiment, the mathematical models of the intake / exhaust edges are 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 blade back / basin weight 0.1; KD-Tree is used to accelerate the nearest point search.

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

[0066] When performing region segmentation, it is necessary to set the recognition threshold of the intake edge and the exhaust edge. For the intake edge, the recognition threshold is set to curvature ≥ 0.08mm -1 ,like Figure 2 As shown; for the exhaust edge, the recognition threshold is set to curvature ≥ 0.07mm -1 These thresholds were determined by analyzing a large number of precision-forged blade samples and considering the geometric characteristics of the intake and exhaust edges. They can accurately distinguish the intake and 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 inlet / exhaust edge data, and generate the contour detection results after updating and optimization. According to the contour detection results, complete the detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade.

[0068] Specifically, for the inlet edge, a forward iteration approach was used to fit the contour using the LM algorithm, with μ = 0.005. This parameter value was determined based on the specific data characteristics and fitting requirements of the inlet edge, ensuring that the true contour curve was effectively approximated during the forward iteration process.

[0069] For the exhaust edge, a reverse iteration approach was used, also using the LM algorithm, but with μ = 0.008. This parameter was set to account for differences in geometry and data distribution between the exhaust and intake edges. By adjusting μ to accommodate the characteristics of the exhaust edge, the accuracy of the reverse iteration was ensured.

[0070] During the bidirectional progressive fitting process, a cross-domain residual check is performed every five iterations. The check threshold is set to ΔRMS ≤ 0.005mm. This regular check mechanism promptly detects and corrects any deviations that may occur during the fitting process on the intake and exhaust sides, ensuring that the entire fitting process proceeds accurately.

[0071] Specifically, this embodiment uses a bidirectional progressive fitting method to process the intake and exhaust data. Fitting operations are performed simultaneously on the intake side (using forward iteration) and the exhaust side (using reverse iteration). During this process, a cross-domain residual check is performed every five iterations. This iterative and check approach allows for timely detection and correction of potential deviations during the fitting process.

[0072] The convergence conditions include two aspects: first, the spatial residual needs to meet ≤ 0.02 mm, which ensures the accuracy of the fitting results in space; second, the curvature gradient must be continuous (C 2 This condition ensures the smoothness of the fitting curve from a mathematical point of view and avoids situations such as sudden changes in curvature that do not conform to the actual blade shape.

[0073] Specifically, during the iterative optimization process, the strategy is first dynamically interrupted: adaptive segmentation is performed 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] Among them, Δκ i : The curvature change at the i-th point, calculated by ‖κ i+1 -k i ‖ is calculated and used to determine whether a sudden change in curvature occurs. k i : The curvature of the i-th point. κ i+1 : The curvature of the i+1th point. τ κ : Curvature mutation threshold, the value is 0.1mm -1 , when, it is determined that a sudden change in curvature occurs at the i-th point. k: Starting point index, used as the starting position when calculating error accumulation. m: Used to determine the range of points for calculating error accumulation. τ ∈ : Error accumulation judgment threshold, such as τ ∈ = 0.02 mm, 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 fitting curve corresponding to point j.

[0080] Secondly, incremental fitting: retain the Jacobian matrix condition number of the previous fitting and use the LM algorithm to update the parameters (damping factor μ = 0.01). The specific formula is as follows:

[0081] LM algorithm improvements:

[0082] 1. Adaptive update 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] Among them, μ k : Damping factor for the kth iteration, used to control the convergence characteristics of the Levenberg-Marquardt (LM) algorithm, with an initial value of μ0 = 0.01. k+1 : Damping factor for the k+1th iteration, according to μ k Its value is determined by the effectiveness of the gradient descent direction of 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 prediction value and the actual observation value, with a dimension of m×1. ‖J Tr‖: The 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 of the current iteration. η: An adjustment factor, set to 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 the storage overhead of a single iteration by 72%.

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

[0090] Example 2

[0091] See also Figures 2 to 3 In one embodiment of the present invention, a profile fitting schematic diagram of a method for detecting the profile of a double-notched blade profile on the intake and exhaust edges of a precision forged blade is provided:

[0092] Figure 2 for Figure 1 Method: Schematic diagram of the contour fitting of the inlet edge of the precision forged blade generated by collecting data;

[0093] Figure 3 for Figure 1 Methods: Schematic diagram of the contour fitting of the exhaust edge of the precision forged blade generated by collecting data;

[0094] Example 3

[0095] See also Figures 4 and 5 In one embodiment of the present invention, there is provided a method for detecting the profile of a double-notch blade on the intake and exhaust edges of a precision forged blade, and comparative data thereof:

[0096] Figure 4 The upper and lower limits of the actual measurement data of the lower air intake side of the existing method are 0.276mm and -0.012mm respectively. The upper and lower limits of the actual measurement data of the lower air intake side of the improved method are 0.190mm and -0.005mm respectively.

[0097] Figure 5 The upper and lower limits of the actual measurement data of the lower air intake side of the existing method are 0.190mm and -0.012mm respectively. After the improved method, the upper and lower limits of the actual measurement data of the lower air intake side are 0.150mm and 0.000mm respectively.

[0098] In summary, the present invention provides a method for detecting the profile of a double-notched blade on the intake and exhaust edges of a precision-forged blade. By employing an improved DBSCAN clustering algorithm, it effectively processes noisy point cloud data, significantly improving its quality. A dual-domain decoupling strategy more accurately describes the relationship between the intake and exhaust edges in independent coordinate systems, effectively achieving regional decoupling and reducing the impact of coupling errors on profile detection. Bidirectional progressive fitting ensures the smoothness of the fitting curve, avoiding sudden changes in curvature that deviate from the actual blade shape.

[0099] Example 4

[0100] according to Figure 6 As shown, this embodiment provides a system for detecting the profile of a double-notched blade profile on the inlet and exhaust edges of a precision-forged blade, comprising:

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

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

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

[0104] The data fitting optimization module 4 is used to perform bidirectional progressive fitting on the inlet / exhaust edge data, and to generate the contour detection results after updating and optimization, and to complete the detection of the double-notch blade profile contour of the inlet and exhaust edges of the precision forged blade based on the contour detection results.

[0105] Example 5

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

[0107] When the processor executes the computer program, the steps of the method for detecting the profile of the double-notched blade profile at the inlet and exhaust edges of the precision-forged blade are implemented, for example:

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

[0109] Preprocessing the measured point cloud data to obtain valid point cloud data;

[0110] Constructing a mathematical model of the intake / exhaust edge according to the effective point cloud data to perform regional decoupling, and obtaining intake / exhaust edge data respectively;

[0111] The inlet / exhaust edge data is bidirectionally progressively fitted, and the contour detection results are generated after updating and optimization. The contour detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade is completed based on the contour detection results.

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

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

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

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

[0116] The data fitting optimization module 4 is used to perform bidirectional progressive fitting on the inlet / exhaust edge data, and to generate the contour detection results after updating and optimization, and to complete the detection of the double-notch blade profile contour of the inlet and exhaust edges of the precision forged blade based on the contour detection results.

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

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

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

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

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

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

[0123] The data fitting optimization module 4 is used to perform bidirectional progressive fitting on the inlet / exhaust edge data, and to generate the contour detection results after updating and optimization, and to complete the detection of the double-notch blade profile contour of the inlet and exhaust edges of the precision forged blade based on the contour detection results.

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

[0125] The processor may be a central processing unit (CPU), or other general-purpose processors, 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, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.

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

[0127] The memory may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0128] Example 6

[0129] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method for detecting the double-notch blade profile of the inlet and exhaust edges of a precision-forged blade.

[0130] If the module / unit integrated in the mobile terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0131] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned method by means of a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned method for scheduling aggregated reinforcement learning resources. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form.

[0132] The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, 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 can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do 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, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for detecting the profile of a double-notch blade on the intake and exhaust edges of a precision forged blade, characterized in that: include: Obtain measured point cloud data after radius compensation; Preprocessing the measured point cloud data to obtain valid point cloud data; Constructing a mathematical model of the intake / exhaust edge according to the effective point cloud data to perform regional decoupling, and obtaining intake / exhaust edge data respectively; The inlet / exhaust edge data is bidirectionally progressively fitted, and the contour detection results are generated after updating and optimization. The contour detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade is completed based on the contour detection results.

2. A method for detecting the profile of a double-notch blade profile of a precision forged blade intake and exhaust edges according to claim 1, characterized in that: In the step of obtaining the radius-compensated measured point cloud data, the measured point cloud data is obtained by detecting the double-notched blade profile surface at the inlet and exhaust edges of the precision-forged blade.

3. The method for detecting the profile of double-notch blade profile of the intake and exhaust edges of a precision forged blade according to claim 1, characterized in that: In the step of preprocessing the measured point cloud data to obtain valid point cloud data, the measured point cloud data is preprocessed by using an improved DBSCAN clustering algorithm, wherein the preprocessing includes hardening layer noise removal and plastic deformation compensation.

4. A method for detecting the profile of a double-notch blade profile of a precision forged blade intake and exhaust edges according to claim 1, characterized in that: The parameters of the improved DBSCAN clustering algorithm are Eps=0.05mm, MinPts=6.

5. The method for detecting the profile of double-notch blade profile of the inlet and exhaust edges of a precision forged blade according to claim 1, characterized in that: In the step of constructing a mathematical model of the intake / exhaust edge based on the valid point cloud data for regional decoupling, the weights of the mathematical model of the intake / exhaust edge are assigned according to the characteristics of the intake / exhaust edge, wherein the weight setting range of the intake edge is 0-1, and the weight setting range of the exhaust edge is 0-1.

6. A method for detecting the profile of a double-notch blade on the intake and exhaust edges of a precision forged blade according to claim 1, characterized in that: When performing regional decoupling of the mathematical model of the intake / exhaust side, the region is segmented, and identification thresholds of the intake side and the exhaust side are set, and the intake / exhaust side data are obtained respectively through the identification thresholds.

7. The method for detecting the profile of double-notch blade profile of the inlet and exhaust edges of a precision forged blade according to claim 1, characterized in that: In the step of performing bidirectional progressive fitting on the intake / exhaust edge data to obtain fitting data, the specific process is as follows: The forward iteration method is used on the intake side, and the LM algorithm is used to fit the contour curve of the intake side; The exhaust edge is fitted by reverse iteration and LM algorithm to obtain the exhaust edge contour curve; The contour curves of the intake side and the exhaust side are iteratively subjected to cross-domain residual verification to complete the update optimization and generate the contour detection results.

8. A double-notch blade profile detection system for precision forged blade intake and exhaust edges, characterized in that: include: A data acquisition module is used to obtain measured point cloud data after radius compensation; A data preprocessing module, configured to preprocess the measured point cloud data to obtain valid point cloud data; A regional decoupling module is used to construct a mathematical model of the intake / exhaust edge according to the effective point cloud data to perform regional decoupling and obtain intake / exhaust edge data respectively; The data fitting optimization module is used to perform bidirectional progressive fitting on the inlet / exhaust edge data, and to generate the contour detection results after updating and optimization. The contour detection of the double-notch blade profile of the inlet and exhaust edges of the precision forged blade is completed based on the contour detection results.

9. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for detecting the profile of the double-notch blade profile at the inlet and exhaust edges of a precision-forged blade are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the profile of the double-notched blade profile at the inlet and exhaust edges of a precision forged blade as claimed in any one of claims 1 to 7 are implemented.

Images