Aircraft part round hole and end face cooperative detection method, device, equipment and medium

Abstract

The application discloses an aviation part round hole and end face cooperative detection method, device, equipment and medium, and relates to the aviation part detection field.The method comprises the following steps: performing outlier elimination on the surface three-dimensional point cloud data of the target aviation part by using the 3σ criterion, and obtaining a round hole effective point set and an end face effective point set; based on a double-thread parallel computing architecture, a first thread is used to perform iterative optimization on the round hole effective point set based on the linear least square method and the 3σ criterion, a round hole fitting result is obtained, a second thread is used to extract an end face plane normal vector based on the end face effective point set and the minimum eigenvalue method of the covariance matrix, and an end face fitting result is obtained; based on the fitting result, a normal error component in a three-dimensional round center vector is eliminated by using a vector projection method, so that the projection round center distance and the eccentricity of the nested round hole in the end face plane are calculated, and the concentricity of the nested round hole is evaluated.The application can realize the aviation part round hole and end face cooperative detection in a non-damage, accurate and efficient manner.

Description

Technical Field

[0001] This application relates to the field of aerospace component inspection, and in particular to a method, apparatus, equipment and medium for the coordinated inspection of circular holes and end faces of aerospace components. Background Technology

[0002] For the intelligent manufacturing industry of high-end aerospace equipment, the geometrical and positional tolerances of components directly determine the assembly reliability and service safety of the entire machine. The accuracy requirements for the diameter of circular holes, the flatness of end faces, and the concentricity of nested holes have been raised to the micrometer level. Traditional inspection technologies typically employ contact measurement methods, such as coordinate measuring machines (CMMs). Although these methods achieve the required static measurement accuracy, they have inherent drawbacks: contact probes are prone to scratching the precision-machined surfaces of aerospace components, causing irreversible damage; and the single-point serial measurement mode is extremely inefficient, with the inspection of a single part taking tens of minutes, making it unsuitable for the stringent requirements of online, high-speed inspection in aerospace production lines. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, equipment, and medium for the coordinated inspection of circular holes and end faces of aerospace components, which can achieve the coordinated inspection of circular holes and end faces of aerospace components in a non-destructive, accurate, and efficient manner.

[0004] To achieve the above objectives, this application provides the following solution.

[0005] In a first aspect, this application provides a method for the coordinated inspection of circular holes and end faces of aerospace components, comprising the following steps.

[0006] The surface three-dimensional point cloud data of the target aerospace component is acquired, and outliers are removed from the surface three-dimensional point cloud data using the 3σ criterion to obtain the effective point set of the circular hole and the effective point set of the end face.

[0007] Based on a dual-thread parallel computing architecture, the first thread iteratively optimizes the effective point set of the circular hole using the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. The second thread, which starts synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end face fitting result of the target aerospace component.

[0008] For nested circular holes, based on the hole fitting results and the end face fitting results, the vector projection method is used to eliminate the normal error component in the three-dimensional center vector. Based on the three-dimensional center vector with the normal error component eliminated, the projected center distance and eccentricity of the nested circular holes in the end face plane are calculated. Concentricity evaluation is performed based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

[0009] In one embodiment, after obtaining the concentricity assessment result of the target aerospace component, the aerospace component circular hole and end face collaborative inspection method further includes: verifying the accuracy of the circular hole fitting result, the end face fitting result, and the nested circular hole concentricity assessment result based on the preset form and position tolerance standard of the target aerospace component, and outputting the inspection report and product qualification judgment result of the target aerospace component according to the accuracy verification result, the circular hole fitting result, the end face fitting result, and the nested circular hole concentricity assessment result.

[0010] In one embodiment, outliers are removed from the surface three-dimensional point cloud data using the 3σ criterion to obtain the effective point set for the circular hole and the effective point set for the end face. Specifically, this includes: based on the surface three-dimensional point cloud data, using a point cloud segmentation algorithm to extract the edge two-dimensional discrete point set corresponding to the circular hole feature and the three-dimensional spatial discrete point set corresponding to the end face feature; and using the 3σ criterion to remove outliers from the edge two-dimensional discrete point set and the three-dimensional spatial discrete point set to obtain the effective point set for the circular hole and the effective point set for the end face.

[0011] In one embodiment, the effective point set of the circular hole is iteratively optimized based on the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. Specifically, this includes: transforming the ideal planar circle equation into a linear equation to obtain a linear circle equation; constructing a least squares objective function with the goal of minimizing the sum of squared residuals of the effective points of the circular hole; calculating the partial derivatives of the least squares objective function with respect to the linear parameters in the linear circle equation and setting the partial derivatives to 0 to construct a system of three linear equations; and solving the optimal linear equations using matrix inversion or Cramer's rule based on the effective point set of the circular hole and the system of three linear equations. The parameters are as follows: Calculate the optimal center coordinates and optimal radius based on the optimal linear parameters; calculate the radial deviation from each valid point of the hole to the fitted circle based on the optimal center coordinates and optimal radius; use the 3σ criterion to remove valid points of the hole whose radial deviation is greater than a set deviation value from the set of valid points of the hole; if the radial deviation converges, determine the optimal center coordinates and optimal radius corresponding to the set of valid points of the hole after removal as the hole fitting result; if the radial deviation does not converge, re-solve the optimal linear parameters based on the set of valid points of the hole after removal and the ternary linear equation system until the radial deviation converges.

[0012] In one embodiment, the end-face plane normal vector is extracted based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end-face fitting result of the target aerospace component. Specifically, this includes: calculating the centroid coordinates of the effective point set of the end face; constructing a decentralized vector based on the centroid coordinates; constructing a 3×3 symmetric covariance matrix based on the decentralized vector; performing eigenvalue decomposition on the symmetric covariance matrix to obtain the eigenvalue decomposition result; extracting the eigenvector corresponding to the minimum eigenvalue based on the eigenvalue decomposition result, and determining the extracted eigenvector as the end-face plane normal vector; determining the end-face plane equation based on the end-face plane normal vector and the centroid coordinates; the end-face fitting result includes: the end-face plane normal vector and the end-face plane equation.

[0013] In one embodiment, based on the hole fitting results of the nested circular holes and the end face fitting results, a vector projection method is used to eliminate the normal error component in the three-dimensional center vector. The projected center distance and eccentricity of the nested circular holes in the end face plane are calculated based on the three-dimensional center vector with the normal error component eliminated. Specifically, this includes: constructing a three-dimensional center vector based on the center coordinates in the hole fitting results of the nested circular holes; calculating the projection vector of the three-dimensional center vector in the end face plane based on the three-dimensional center vector and the end face plane normal vector in the end face fitting results, and determining the projection vector as the three-dimensional center vector with the normal error component eliminated; calculating the magnitude of the three-dimensional center vector with the normal error component eliminated, and determining the magnitude as the projected center distance of the nested circular holes in the end face plane; and calculating the eccentricity based on the projected center distance and the radius in the hole fitting results of the nested circular holes.

[0014] In one embodiment, concentricity evaluation is performed based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component. Specifically, this includes: determining whether the eccentricity is within a set eccentricity range and whether the projected center distance meets set nesting constraints to complete the concentricity evaluation and obtain the concentricity evaluation result of the nested circular holes of the target aerospace component; the set eccentricity range is... , For eccentricity, The radius of the larger circle in the nested circular hole. The radius of the smaller circle within the nested circular hole; the nesting constraint condition is set as follows: , This is the distance between the centers of the projected circles.

[0015] Secondly, this application provides a device for the coordinated inspection of circular holes and end faces of aerospace components, including the following modules.

[0016] The three-dimensional point cloud data acquisition and preprocessing module is used to acquire the surface three-dimensional point cloud data of the target aerospace parts, and to remove outliers from the surface three-dimensional point cloud data using the 3σ criterion to obtain the effective point set of the circular hole and the effective point set of the end face.

[0017] The dual-threaded parallel feature fitting module is used to perform iterative optimization of the effective point set of the circular hole based on the dual-threaded parallel computing architecture. The first thread performs iterative optimization based on the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. The second thread, which starts synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end face fitting result of the target aerospace component.

[0018] The nested circular hole concentricity evaluation module is used to, for nested circular holes, based on the hole fitting results and the end face fitting results, use vector projection to eliminate the normal error component in the three-dimensional circular center vector, calculate the projected center distance and eccentricity of the nested circular hole in the end face plane based on the three-dimensional circular center vector with the normal error component eliminated, and perform concentricity evaluation based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

[0019] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the method for coordinated detection of circular holes and end faces of aerospace components as described above.

[0020] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for coordinated detection of circular holes and end faces of aerospace components as described above.

[0021] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method, apparatus, equipment, and medium for the collaborative detection of circular holes and end faces of aerospace components. It achieves collaborative detection of circular holes and end faces of aerospace components based on surface three-dimensional point cloud data. This non-contact method realizes non-destructive detection. Based on a dual-thread parallel computing architecture, the first thread and the second thread are used for synchronous fitting of the circular holes and end faces. The overall detection time is the maximum of the two threads' times, rather than the cumulative time of a serial architecture, thus improving detection efficiency. The first thread iteratively optimizes the effective point set of the circular holes based on the linear least squares method and the 3σ criterion, improving the robustness of the circular hole fitting. The second thread extracts the normal vector of the end face plane based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix, improving the stability of the end face fitting. The vector projection method is used to eliminate the normal error component in the three-dimensional circle center vector. Based on the three-dimensional circle center vector with the normal error component eliminated, the projected center distance and eccentricity of the nested circular holes in the end face plane are calculated, thereby evaluating concentricity. This eliminates the influence of errors and improves the accuracy of concentricity evaluation. Therefore, this application can achieve non-destructive, accurate and efficient collaborative inspection of circular holes and end faces of aerospace components. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating the method for collaborative detection of circular holes and end faces of aerospace components provided in an embodiment of this application.

[0024] Figure 2 This is an overall flowchart illustrating a specific implementation process of the method for collaborative detection of circular holes and end faces of aerospace components provided in this application.

[0025] Figure 3 This is a schematic diagram of the process for acquiring and preprocessing three-dimensional point cloud data provided in an embodiment of this application.

[0026] Figure 4 This is a schematic diagram of the process for robust fitting correction of circular holes provided in an embodiment of this application.

[0027] Figure 5 This is a schematic diagram illustrating the end-face fitting principle based on the minimum eigenvalue method, provided for an embodiment of this application.

[0028] Figure 6 A schematic diagram of the vector projection principle for calculating the concentricity of nested circular holes provided in an embodiment of this application.

[0029] Figure 7 This is a schematic diagram illustrating the accuracy verification and result output provided in the embodiments of this application.

[0030] Figure 8 A schematic diagram of the functional modules of the aerospace component circular hole and end face co-detection device provided in the embodiments of this application.

[0031] Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0034] The relevant 3D vision inspection technology faces four major unresolved technical bottlenecks in the inspection of aerospace parts, making it impossible to simultaneously meet the requirements of aerospace-grade inspection accuracy and real-time online inspection on the production line. The specifics are as follows.

[0035] Poor robustness of circular hole fitting: Point cloud data collected in industrial fields generally have a large number of outlier noise points and missing edge points. Traditional least squares circle fitting algorithms are highly sensitive to outliers and lack effective outlier removal and fitting closed-loop optimization mechanisms, resulting in measurement deviations of circle center and radius parameters that exceed aerospace-grade tolerance requirements, leading to extremely poor robustness.

[0036] Insufficient stability of end face plane fitting: When the amount of point cloud data is insufficient and there is noise interference, the traditional three-point method and the conventional least squares plane fitting method cannot effectively extract accurate plane normal vectors. They are highly sensitive to outliers, and the normal vector solution is prone to distortion, which leads to the complete failure of subsequent form and position tolerance calculation results.

[0037] The concentricity assessment has a fundamental error: related technologies directly calculate the distance between the centers in three-dimensional space to assess the concentricity of nested circular holes, without eliminating the normal error component perpendicular to the end face. This results in the assessment results failing to accurately reflect the actual geometric deviation within the end face plane, which is seriously out of sync with the actual working conditions required for aerospace assembly.

[0038] Detection efficiency and accuracy cannot be simultaneously achieved: related technologies generally adopt a serial execution architecture of "circular hole fitting - end face fitting - concentricity calculation", which is time-consuming and cannot simultaneously meet the micron-level detection accuracy of aerospace parts and the real-time requirements of online production line detection.

[0039] Non-contact 3D vision inspection is the mainstream development direction in the current field of aerospace precision inspection. It can achieve non-destructive, high-speed, full-size inspection and is the core method to replace traditional contact measurement.

[0040] In one exemplary embodiment, such as Figure 1 As shown, a method for the coordinated inspection of circular holes and end faces of aerospace components is provided, including the following steps.

[0041] Step 101: Obtain the surface three-dimensional point cloud data of the target aerospace component, and use the 3σ criterion to remove outliers from the surface three-dimensional point cloud data to obtain the effective point set of the circular hole and the effective point set of the end face.

[0042] Step 102: Based on a dual-thread parallel computing architecture, the first thread iteratively optimizes the effective point set of the circular hole using the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. The second thread, which starts synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end face fitting result of the target aerospace component.

[0043] Step 103: For nested circular holes, based on the hole fitting results and the end face fitting results, the vector projection method is used to eliminate the normal error component in the three-dimensional center vector. Based on the three-dimensional center vector with the normal error component eliminated, the projected center distance and eccentricity of the nested circular holes in the end face plane are calculated. Concentricity evaluation is performed based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

[0044] In another exemplary embodiment of this application, after step 103, the method for co-inspection of circular holes and end faces of aerospace components further includes: verifying the accuracy of the circular hole fitting result, the end face fitting result, and the concentricity evaluation result of the nested circular holes based on the preset geometric tolerance standards of the target aerospace component; and outputting an inspection report and product qualification judgment result of the target aerospace component based on the accuracy verification result, the circular hole fitting result, the end face fitting result, and the concentricity evaluation result of the nested circular holes.

[0045] In another exemplary embodiment of this application, step 101 specifically includes: based on the surface three-dimensional point cloud data, using a point cloud segmentation algorithm to extract the edge two-dimensional discrete point set corresponding to the circular hole feature and the three-dimensional spatial discrete point set corresponding to the end face feature; using the 3σ criterion to remove outliers from the edge two-dimensional discrete point set and the three-dimensional spatial discrete point set to obtain the effective point set of the circular hole and the effective point set of the end face.

[0046] In another exemplary embodiment of this application, in step 102, the effective point set of the circular hole is iteratively optimized based on the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. Specifically, this includes: transforming the ideal plane circle equation into a linear equation to obtain a linear circle equation; constructing a least squares objective function with the goal of minimizing the sum of squared residuals of the effective points of the circular hole; calculating the partial derivatives of the least squares objective function with respect to the linear parameters in the linear circle equation and setting the partial derivatives to 0 to construct a system of three linear equations; and using matrix inversion or Cramer's rule to solve the problem based on the effective point set of the circular hole and the system of three linear equations. The optimal linear parameters are obtained; the optimal center coordinates and optimal radius are calculated based on the optimal linear parameters; the radial deviation from each effective point of the hole to the fitted circle is calculated based on the optimal center coordinates and the optimal radius; the effective points of the holes with radial deviations greater than a set deviation value are removed from the effective point set of the holes using the 3σ criterion; if the radial deviation converges, the optimal center coordinates and optimal radius corresponding to the removed effective point set of holes are determined as the hole fitting result; if the radial deviation does not converge, the optimal linear parameters are solved again based on the removed effective point set of holes and the ternary linear equation system until the radial deviation converges.

[0047] In another exemplary embodiment of this application, step 102, extracting the end-face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end-face fitting result of the target aerospace component, specifically includes: calculating the centroid coordinates of the effective point set of the end face; constructing a decentralized vector based on the centroid coordinates; constructing a 3×3 symmetric covariance matrix based on the decentralized vector; performing eigenvalue decomposition on the symmetric covariance matrix to obtain the eigenvalue decomposition result; extracting the eigenvector corresponding to the minimum eigenvalue based on the eigenvalue decomposition result, and determining the extracted eigenvector as the end-face plane normal vector; determining the end-face plane equation based on the end-face plane normal vector and the centroid coordinates; the end-face fitting result includes: the end-face plane normal vector and the end-face plane equation.

[0048] In another exemplary embodiment of this application, in step 103, based on the hole fitting result of the nested circular holes and the end face fitting result, the vector projection method is used to eliminate the normal error component in the three-dimensional center vector. Based on the three-dimensional center vector with the normal error component eliminated, the projected center distance and eccentricity of the nested circular holes in the end face plane are calculated. Specifically, this includes: constructing a three-dimensional center vector according to the center coordinates in the hole fitting result of the nested circular holes; calculating the projection vector of the three-dimensional center vector in the end face plane according to the three-dimensional center vector and the end face plane normal vector in the end face fitting result, and determining the projection vector as the three-dimensional center vector with the normal error component eliminated; calculating the magnitude of the three-dimensional center vector with the normal error component eliminated, and determining the magnitude as the projected center distance of the nested circular holes in the end face plane; and calculating the eccentricity according to the projected center distance and the radius in the hole fitting result of the nested circular holes.

[0049] In another exemplary embodiment of this application, step 103, performing a concentricity evaluation based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component, specifically includes: determining whether the eccentricity is within a set eccentricity range and whether the projected center distance meets a set nesting constraint condition to complete the concentricity evaluation and obtain the concentricity evaluation result of the nested circular holes of the target aerospace component; the set eccentricity range is... , For eccentricity, The radius of the larger circle in the nested circular hole. The radius of the smaller circle within the nested circular hole; the nesting constraint condition is set as follows: , This is the distance between the centers of the projected circles.

[0050] The collaborative detection method for circular holes and end faces of aerospace components in this embodiment is a non-contact detection method implemented based on a dual-thread parallel architecture. It is particularly suitable for online high-precision detection of aerospace components with core features such as circular holes and end faces, such as aero-engine flanges, fuselage connectors, and landing gear mounting seats. Specifically, three-dimensional point cloud data of the aerospace component surface is collected, and outlier points are removed using the 3σ criterion to obtain the effective point sets for the circular holes and end faces. Based on the dual-thread parallel architecture, the first thread uses the linear least squares method combined with the 3σ criterion for iterative optimization to complete the robust fitting correction of the circular hole parameters. The second thread extracts the optimal normal vector of the end face based on the minimum eigenvalue method of the covariance matrix to complete the accurate fitting of the end face plane. Based on the vector projection method, the normal error component in the three-dimensional circular center vector is eliminated, and the projection center distance and eccentricity of the nested circular holes in the end face plane are calculated to complete the accurate assessment of concentricity. This embodiment improves the overall inspection cycle time by more than 30% through dual-thread parallel computing. It solves the industry pain points of noise interference and concentricity assessment distortion in industrial sites by using closed-loop fitting algorithm and vector projection method. It realizes high-precision, high-robustness and high-efficiency collaborative inspection of circular holes and end face features of aerospace parts, and can be widely adapted to online inspection scenarios in aerospace production lines.

[0051] The following is a more specific embodiment, which provides a more detailed explanation of the implementation process of the above-mentioned method for the coordinated detection of circular holes and end faces of aerospace components.

[0052] Figure 2 The overall process of the collaborative detection method is shown below.

[0053] S1, 3D point cloud data acquisition and preprocessing.

[0054] like Figure 3 As shown, the surface three-dimensional point cloud data of the aviation component to be inspected (i.e., the target aviation component) is collected by a three-dimensional vision sensor. The point cloud segmentation algorithm is used to extract the edge two-dimensional discrete point set corresponding to the feature of the circular hole to be inspected and the three-dimensional spatial discrete point set corresponding to the feature of the end face to be inspected. The 3σ criterion is used to remove outliers from the edge two-dimensional discrete point set and the three-dimensional spatial discrete point set respectively, and to remove the gross error points generated during the measurement process, so as to obtain the effective point set of the circular hole and the effective point set of the end face.

[0055] S2, dual-thread parallel feature fitting.

[0056] Based on a dual-thread parallel computing architecture, two independent computing threads are started simultaneously to complete the parallel fitting of the circular hole feature and the end face feature. The two threads are independently addressed and data is isolated. After the fitting is completed, the data is synchronized. The overall detection cycle is the maximum value of the time taken by the two threads, rather than the sum of the time taken by the serial architecture, as detailed below.

[0057] The first thread implements robust fitting correction for circular holes: Based on the effective point set of the circular holes, the nonlinear circular equation is transformed into a system of linear equations by using the linear least squares method to solve for the initial fitting value. Combined with the 3σ criterion, radial deviation outliers are iteratively eliminated, and finally the optimal center coordinates and optimal radius parameters of the circular hole to be detected are obtained.

[0058] The second thread achieves accurate fitting of the end face normal vector: Based on the effective point set of the end face, the centroid of the point cloud is calculated and a decentralized three-dimensional covariance matrix is ​​constructed. The eigenvector corresponding to the smallest eigenvalue is extracted by eigenvalue decomposition as the optimal normal vector of the plane. The optimal plane equation of the end face is obtained by combining the centroid coordinates.

[0059] S3, accurate assessment of the concentricity of nested circular holes.

[0060] For the nested circular holes on the same end face, based on the three-dimensional center coordinates of the large and small circles obtained by fitting in the first thread of step S2, and combined with the end face plane normal vector obtained by solving in the second thread of step S2, the vector projection method is used to eliminate the normal error component in the three-dimensional center vector, and the projection center distance of the two circles in the end face plane is calculated. Finally, the eccentricity of the nested circular holes is calculated to complete the concentricity assessment.

[0061] S4, Accuracy Verification and Result Output.

[0062] Based on the pre-set geometric tolerance standards for aerospace components, the accuracy of the hole fitting results, end face fitting results (i.e., end face flatness results), and nested hole concentricity evaluation results is verified, and the final inspection report and product qualification judgment results are output.

[0063] The specific steps for removing outliers from the two-dimensional discrete points on the edge of the circular hole using the 3σ criterion in step S1 are as follows.

[0064] (1) Calculate the mean coordinates of n original discrete points. The calculation formula is as follows.

[0065] .

[0066] Let x be the x-coordinate of the i-th discrete point. Let be the ordinate of the i-th discrete point.

[0067] (2) Calculate the distance deviation from each discrete point to the mean coordinate. The calculation formula is as follows.

[0068] .

[0069] (3) Calculate the mean of the distance deviation with standard deviation The calculation formula is as follows.

[0070] .

[0071] (4) Eliminate those that meet the requirements The outliers are identified, and the effective point set of the circular hole is obtained.

[0072] For the three-dimensional discrete point set of the end face, the same logic is used to calculate the 3σ interval of the three-dimensional spatial distance deviation to complete the outlier removal.

[0073] Among them, such as Figure 4 As shown, the specific steps for the first thread to implement robust fitting correction of the circular hole in step S2 are as follows.

[0074] (1) Linearization of the circle equation: The ideal plane circle equation is linearized. Expand and deform, let the linear parameter , , The equation can be transformed into a linear equation as follows.

[0075] .

[0076] in, Let the coordinates be the center of the circle. Let be the radius of the circle.

[0077] (2) Construct the least squares objective function, and minimize the sum of squared residuals of all effective points. The expression of the least squares objective function is as follows.

[0078] .

[0079] in, The number of points in the effective point set of the circular hole. For valid point coordinates, The objective function is the least squares function.

[0080] (3) For the objective function with respect to the linear parameters respectively Find the partial derivatives and set them to zero to construct a system of three linear equations. Solve the system using matrix inversion or Cramer's rule to obtain the optimal linear parameters. , , The optimal center coordinates are obtained by reverse calculation. With the optimal radius .

[0081] .

[0082] (4) Iterative optimization: Calculate the radial deviation from each valid point to the fitted circle. Then, the 3σ criterion is used again to remove outliers with excessive radial deviation. Steps (1) and (2) are repeated to complete the iterative optimization until the radial deviation converges, and the final optimal parameters of the circular hole are obtained, which is the result of the circular hole fitting.

[0083] Among them, the end-face fitting principle based on the minimum eigenvalue method is as follows: Figure 5 As shown, combined with Figure 5 The specific steps for the precise fitting of the end face normal vector implemented by the second thread in step S2 are as follows.

[0084] (1) Calculate the centroid coordinates of the effective point set on the end face. .

[0085] .

[0086] in, The number of points in the effective point set of the end face. For the effective point set of the end face i The point is at x Values ​​in the axial direction, For the effective point set of the end face i The point is at y Values ​​in the axial direction, For the effective point set of the end face i The point is at z Values ​​in the axial direction.

[0087] (2) Construct a decentralized vector This eliminates the interference of planar position on the solution of normal vector.

[0088] .

[0089] (3) Construct a 3×3 symmetric covariance matrix .

[0090] .

[0091] Where T represents transpose.

[0092] The expansion of the symmetric covariance matrix is ​​as follows.

[0093] .

[0094] (4) For the covariance matrix Perform eigenvalue decomposition to obtain ,in This is an eigenvalue diagonal matrix, where the diagonal elements are the eigenvalues ​​arranged in descending order. , This is the corresponding eigenvector matrix.

[0095] (5) Extract the minimum eigenvalue The corresponding eigenvectors serve as the optimal normal vectors of the fitting plane. .

[0096] (6) The general equation of the plane is derived based on the plane point normal equation.

[0097] Point-normal form equation: .

[0098] make Thus, the general equation of the plane is obtained: .

[0099] The vector projection principle for calculating the concentricity of nested circular holes is as follows: Figure 6 As shown, combined with Figure 6 Step S3 achieves accurate evaluation of the concentricity of nested circular holes. The specific steps are as follows.

[0100] (1) Determine the basic parameters: the three-dimensional center of the great circle The three-dimensional center of the small circle radius of the great circle small circle radius End face plane normal vector .

[0101] (2) Construct the three-dimensional circle center vector: .

[0102] (3) Calculate the projection vector of the center vector onto the end face plane, eliminate the normal error component, and obtain the three-dimensional center vector after eliminating the normal error component. It is represented as follows.

[0103] .

[0104] in For vector dot product, It is the square of the magnitude of the normal vector.

[0105] (4) Calculate the magnitude of the projection vector to obtain the distance between the centers of the projection circles. .

[0106] (5) Calculate the eccentricity And verify nested constraints. The legal range of values ​​for the corresponding eccentricity is: .

[0107] (6) Based on the preset geometric tolerance standards, determine whether the eccentricity is qualified and complete the concentricity assessment.

[0108] The dual-threaded parallel computing architecture in step S2 is implemented using the std::thread multi-threaded library of C++11 or above, or based on FPGA hardware acceleration. The first thread executes the entire process of circular hole fitting, and the second thread executes the entire process of end face fitting synchronously. The two-threaded computing process has no data dependency and no serial waiting time.

[0109] Finally, the accuracy verification and result output are as follows: Figure 7 As shown.

[0110] The method for co-inspecting circular holes and end faces of aerospace components in this embodiment has the following advantages.

[0111] (1) Significantly improve the robustness and anti-interference ability of circular hole fitting: This application constructs a closed-loop framework of "3σ outlier removal + least squares fitting + iterative optimization", which effectively eliminates the gross error and noise interference of point cloud in industrial field, solves the pain point of traditional algorithm being sensitive to outliers, and the measurement accuracy of circular hole parameters can reach the micrometer level, which fully meets the tolerance requirements of aerospace parts.

[0112] (2) Significantly improves the stability and accuracy of end face fitting: This application uses the minimum eigenvalue method based on the eigenvalue decomposition of the covariance matrix to extract the plane normal vector. Compared with the traditional fitting method, the sensitivity to outliers is reduced by 40%, and the average deviation of plane fitting can reach 0.01mm, which meets the industry accuracy standard of coordinate measuring machine and solves the pain point of unstable fitting in complex industrial environments.

[0113] (3) Completely solve the problem of distortion in concentricity assessment results: This application uses vector projection method to eliminate the normal error component in the three-dimensional circle center vector, so that the concentricity assessment results fully reflect the real geometric deviation in the end face plane. Compared with the traditional three-dimensional distance calculation method, the assessment accuracy is improved by 75%, which is completely matched with the actual working conditions of aviation assembly.

[0114] (4) Achieving a balance between high precision and high efficiency: The dual-thread parallel computing architecture developed in this application realizes the synchronous calculation of hole fitting and end face fitting, which improves the overall inspection cycle by more than 30%, and the inspection time of a single part can be controlled within 50ms. While ensuring micron-level inspection accuracy, it fully meets the real-time requirements of online inspection in aviation production lines.

[0115] Based on the same inventive concept, this application also provides an aerospace component circular hole and end face collaborative detection device for implementing the above-mentioned aerospace component circular hole and end face collaborative detection method. The solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more aerospace component circular hole and end face collaborative detection device embodiments provided below can be found in the limitations of the aerospace component circular hole and end face collaborative detection method above, and will not be repeated here.

[0116] In one exemplary embodiment, such as Figure 8 As shown, a device for the coordinated inspection of circular holes and end faces of aerospace components is provided, comprising the following modules.

[0117] The three-dimensional point cloud data acquisition and preprocessing module 801 is used to acquire the surface three-dimensional point cloud data of the target aerospace parts, and to remove outliers from the surface three-dimensional point cloud data using the 3σ criterion to obtain the effective point set of the circular hole and the effective point set of the end face.

[0118] The dual-threaded parallel feature fitting module 802 is used to perform iterative optimization of the effective point set of the circular hole based on the linear least squares method and the 3σ criterion in a dual-threaded parallel computing architecture to obtain the circular hole fitting result of the target aerospace component. The second thread, which is started synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end face fitting result of the target aerospace component.

[0119] The nested circular hole concentricity evaluation module 803 is used to, for nested circular holes, based on the hole fitting results and the end face fitting results, use vector projection to eliminate the normal error component in the three-dimensional circle center vector, calculate the projected circle center distance and eccentricity of the nested circular hole in the end face plane based on the three-dimensional circle center vector with the normal error component eliminated, and perform concentricity evaluation based on the projected circle center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

[0120] As an optional implementation, the dual-threaded parallel feature fitting module 802 incorporates a robust circular hole fitting unit and an end face normal vector fitting unit. The robust circular hole fitting unit executes the first thread, and the end face normal vector fitting unit executes the second thread. The robust circular hole fitting unit and the end face normal vector fitting unit simultaneously complete the parallel fitting of the circular hole and end face features, and simultaneously obtain the circular hole fitting result and end face fitting result of the target aerospace component.

[0121] This application achieves high-precision and high-efficiency collaborative detection of circular holes and end face features of aerospace components. It solves the problems of insufficient accuracy and poor robustness in circular hole fitting caused by point cloud noise interference in industrial environments, achieving closed-loop robust solution of the center and radius parameters; it addresses the high sensitivity of traditional plane fitting methods to outliers and distortion in normal vector calculation in industrial environments, achieving stable and high-precision fitting of the end face plane; it solves the problem of result distortion caused by normal error in the concentricity assessment of nested holes, achieving accurate assessment of true geometric deviations in the plane; it overcomes the problems of long processing time and low efficiency in serial detection architectures, significantly shortening the detection cycle while maintaining micron-level detection accuracy, adapting to the online detection needs of aerospace production lines; and it solves the problem of demanding measurement environments that prevent stable operation in industrial environments with vibration, dust, and temperature variations, making it widely applicable.

[0122] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 9 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores circular hole fitting results, end face fitting results, and concentricity evaluation results of nested circular holes. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for the collaborative detection of circular holes and end faces of aerospace components.

[0123] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment to which the present application is applied. Specific computer equipment may include, for example, [the following is a list of possible additional structures]. Figure 9 The embodiments show more or fewer components, combinations of certain components, or different component arrangements. In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, which the processor executes to implement the steps in the above-described method embodiments.

[0124] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0125] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0126] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0127] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, etc., and are not limited to these.

[0128] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for the coordinated inspection of circular holes and end faces of aerospace components, characterized in that, include: The surface three-dimensional point cloud data of the target aerospace component is acquired, and outliers are removed from the surface three-dimensional point cloud data using the 3σ criterion to obtain the effective point set of the circular hole and the effective point set of the end face. Based on a dual-thread parallel computing architecture, the first thread iteratively optimizes the effective point set of the circular hole using the linear least squares method and the 3σ criterion to obtain the circular hole fitting result of the target aerospace component. The second thread, which is started synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix to obtain the end face fitting result of the target aerospace component. For nested circular holes, based on the hole fitting results and the end face fitting results, the vector projection method is used to eliminate the normal error component in the three-dimensional center vector. Based on the three-dimensional center vector with the normal error component eliminated, the projected center distance and eccentricity of the nested circular holes in the end face plane are calculated. Concentricity evaluation is performed based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

2. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, After obtaining the concentricity assessment results of the target aerospace components, the following is also included: Based on the pre-set geometric tolerance standards of the target aerospace component, the accuracy of the hole fitting results, the end face fitting results, and the concentricity evaluation results of the nested holes is verified. Based on the accuracy verification results, the hole fitting results, the end face fitting results, and the concentricity evaluation results of the nested holes, the inspection report and product qualification judgment results of the target aerospace component are output.

3. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, Outlier removal from the surface 3D point cloud data is performed using the 3σ criterion to obtain the effective point set for the circular hole and the effective point set for the end face, specifically including: Based on the surface three-dimensional point cloud data, a point cloud segmentation algorithm is used to extract the edge two-dimensional discrete point set corresponding to the circular hole feature and the three-dimensional spatial discrete point set corresponding to the end face feature. Outlier points are removed from the two-dimensional discrete point set of the edge and the three-dimensional discrete point set using the 3σ criterion to obtain the effective point set of the circular hole and the effective point set of the end face.

4. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, The effective point set of the circular hole is iteratively optimized based on the linear least squares method and the 3σ criterion to obtain the circular hole fitting results of the target aerospace component, specifically including: Transforming the equation of the ideal plane circle into a linear equation yields the linear circle equation; A least-squares objective function is constructed with the goal of minimizing the sum of squared residuals at the effective points of the circular hole; By taking the partial derivatives of the least squares objective function with respect to the linear parameters in the linear circle equation and setting the partial derivatives to 0, a system of three linear equations is constructed. Based on the effective point set of the circular hole and the three-element linear equation system, the optimal linear parameters are obtained by matrix inversion or Cramer's rule. Calculate the optimal center coordinates and optimal radius based on the optimal linear parameters; Based on the optimal center coordinates and the optimal radius, the radial deviation from each effective point of the circular hole to the fitted circle is calculated. The 3σ criterion is used to remove the effective points of the circular holes whose radial deviation is greater than the set deviation value. If the radial deviation converges, the optimal center coordinates and optimal radius corresponding to the set of effective points of the removed circular holes are determined as the fitting result of the circular holes. If the radial deviation does not converge, the optimal linear parameters are solved again based on the set of effective points of the removed circular holes and the three-variable linear equation system until the radial deviation converges.

5. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, Based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix, the normal vector of the end face plane is extracted to obtain the end face fitting result of the target aerospace component, specifically including: Calculate the centroid coordinates of the effective point set on the end face; Construct a decentralized vector based on the centroid coordinates; Construct a 3×3 symmetric covariance matrix based on the decentralized vector; The symmetric covariance matrix is ​​subjected to eigenvalue decomposition to obtain the eigenvalue decomposition results; Based on the eigenvalue decomposition results, the eigenvector corresponding to the minimum eigenvalue is extracted, and the extracted eigenvector is determined as the normal vector of the end face plane. The equation of the end face plane is determined based on the end face plane normal vector and the centroid coordinates; the end face fitting result includes: the end face plane normal vector and the end face plane equation.

6. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, Based on the fitting results of the nested circular holes and the fitting results of the end face, the vector projection method is used to eliminate the normal error component in the three-dimensional circle center vector. Based on the three-dimensional circle center vector with the normal error component eliminated, the projection center distance and eccentricity of the nested circular holes in the end face plane are calculated, specifically including: Construct a three-dimensional center vector based on the center coordinates of the nested circular holes in the hole fitting results; The projection vector of the three-dimensional circle center vector in the end face plane is calculated based on the three-dimensional circle center vector and the end face plane normal vector in the end face fitting result. The projection vector is then determined as the three-dimensional circle center vector to eliminate the normal error component. Calculate the modulus of the three-dimensional center vector that eliminates the normal error component, and determine the modulus as the projection center distance of the nested circular hole in the end face plane; The eccentricity is calculated based on the distance between the projected circles and the radius in the fitting result of the nested circular holes.

7. The method for coordinated detection of circular holes and end faces of aerospace components according to claim 1, characterized in that, Based on the projected center distance and the eccentricity, a concentricity evaluation is performed to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component, specifically including: By determining whether the eccentricity is within a set eccentricity range and whether the projected center distance meets the set nesting constraint conditions, the concentricity evaluation is completed, and the concentricity evaluation result of the nested circular holes of the target aerospace component is obtained; the set eccentricity range is... , For eccentricity, The radius of the larger circle in the nested circular hole. The radius of the smaller circle within the nested circular hole; the nesting constraint condition is set as follows: , This is the distance between the centers of the projected circles.

8. A device for the coordinated inspection of circular holes and end faces of aerospace components, characterized in that, include: The three-dimensional point cloud data acquisition and preprocessing module is used to acquire the surface three-dimensional point cloud data of the target aerospace parts, and use the 3σ criterion to remove outliers from the surface three-dimensional point cloud data to obtain the effective point set of the circular hole and the effective point set of the end face. The dual-threaded parallel feature fitting module is used to perform iterative optimization of the effective point set of the circular hole based on the linear least squares method and the 3σ criterion, based on the dual-threaded parallel computing architecture, to obtain the circular hole fitting result of the target aerospace component. The second thread, which is started synchronously with the first thread, extracts the end face plane normal vector based on the effective point set of the end face and the minimum eigenvalue method of the covariance matrix, to obtain the end face fitting result of the target aerospace component. The nested circular hole concentricity evaluation module is used to, for nested circular holes, based on the hole fitting results and the end face fitting results, use vector projection to eliminate the normal error component in the three-dimensional circular center vector, calculate the projected center distance and eccentricity of the nested circular hole in the end face plane based on the three-dimensional circular center vector with the normal error component eliminated, and perform concentricity evaluation based on the projected center distance and the eccentricity to obtain the concentricity evaluation result of the nested circular holes of the target aerospace component.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the method for coordinated detection of circular holes and end faces of aerospace components according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for coordinated detection of circular holes and end faces of aerospace components as described in any one of claims 1-7.

Images