Curved surface workpiece machining three-dimensional reconstruction method and system based on point cloud data

Abstract

The invention discloses a curved surface workpiece processing three-dimensional reconstruction method and system based on point cloud data, and relates to the field of data processing, and the system comprises an acquisition module which is used for adaptively adjusting the scanning path, sampling density and scanning distance parameters of an acquisition device, and driving the acquisition device to obtain workpiece surface point cloud data; the preprocessing module is used for hierarchically dividing the acquired point cloud data according to the curvature change of the curved surface of the workpiece, removing abnormal points in each hierarchy and complementing missing point clouds; according to the method, scanning parameters are flexibly adjusted in combination with workpiece machining area parameters, comprehensive and accurate point cloud data collection is ensured, point cloud processing can be optimized according to curvature, features are accurately extracted, a model is constructed in a layered mode, the integrity of the model is guaranteed through splicing constraint, and it is ensured that the model meets machining requirements through precision verification and correction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a curved workpiece machining three-dimensional reconstruction method and system based on point cloud data. BACKGROUND

[0002] Curved workpieces are parts with curved surfaces, no obvious planes or edges, commonly found in automotive bodies, aircraft engine blades, mold cavities, etc. They need to be processed through numerical control milling, 3D printing, etc. with high precision and surface roughness requirements.

[0003] The invention patent application with application number 202410096929.2 discloses a tool curved surface three-dimensional reconstruction method based on non-contact scanning measurement, including the following steps: step one: tool point cloud data acquisition and preprocessing; tool point cloud data acquisition: use the machine tool servo system to control the line laser scanner to measure the movement, collect multi-position and multi-angle tool point cloud data; tool point cloud data preprocessing: treat three-dimensional point cloud data as two-dimensional data, and sequentially perform missing value, simplification and outlier processing to optimize point cloud quality and improve data usability; step two: tool point cloud data rotation splicing based on tool machining characteristics and rotation measurement movement, splice multiple sets of point cloud data to obtain complete and accurate point cloud data; step three: tool curved surface three-dimensional reconstruction. The application aims to solve the problem of "traditional measurement methods include non-contact offline measurement and contact on-machine measurement. Among them, offline measurement needs to remove the machining tool from the machine tool for detection, which is easy to cause secondary clamping error, machining reference change and other problems, reducing the tool measurement accuracy and efficiency; contact on-machine measurement mostly needs to use probe point-by-point measurement, which is low in measurement efficiency and is limited by the size of the probe, often difficult to meet the high-precision measurement requirements of small tool structures. Overall, the traditional measurement method has low measurement efficiency and limited measurement accuracy."

[0004] However, in the existing curved workpiece sample, collecting the surface parameters of the curved workpiece sample and then constructing the model and manufacturing the curved workpiece according to the model, the existing technology has poor structure parameter collection and modeling accuracy for the curved workpiece sample, resulting in the need for repeated calibration and improvement of the subsequent produced curved workpiece, which is not ideal in efficiency and cost.

[0005] Therefore, we propose a curved workpiece machining three-dimensional reconstruction method and system based on point cloud data. SUMMARY

[0006] In view of the above shortcomings of the prior art, the present application provides a curved workpiece machining three-dimensional reconstruction method and system based on point cloud data, which can effectively solve the problems of the prior art.

[0007] To achieve the above purpose, the present application is realized by the following technical solutions; This invention discloses a three-dimensional reconstruction system for machining curved workpieces based on point cloud data, comprising: The acquisition module adaptively adjusts the scanning path, sampling density, and scanning distance parameters of the acquisition device to drive the acquisition device to acquire point cloud data of the workpiece surface. The preprocessing module divides the acquired point cloud data into layers according to the curvature changes of the workpiece surface, removes outliers within each layer, and completes the missing point cloud. The extraction module receives the layered point cloud data after the missing point cloud is completed, identifies the feature regions of the workpiece surface, and extracts the spatial coordinates and topological relationships of the feature points. The construction module receives the spatial coordinates and topological relationships of the feature points, applies them, constructs local 3D models of each region of the workpiece according to the layered order of the point cloud, establishes splicing constraints between the local 3D models, and splices the local 3D models to obtain the overall 3D model. The verification module compares the constructed overall 3D model with the preset processing accuracy requirements of the workpiece, automatically verifies the accuracy deviations of each region of the model and at splicing points, and marks the out-of-tolerance areas. The output module obtains the verification results, adjusts the parameter format of the overall 3D model based on the verification results, and outputs model data adapted to the surface workpiece processing equipment. During the acquisition module's operation phase, the acquisition equipment is adjusted based on the curvature range, dimensional boundaries, and accuracy level parameters of the preset processing area of ​​the curved workpiece.

[0008] Furthermore, when the acquisition module adaptively adjusts the acquisition device parameters, it first calculates the curvature fluctuation coefficient based on the curvature range of the preset processing area of ​​the curved workpiece: ; In the formula: These are the maximum and minimum curvature values ​​within the preset processing area; The average curvature value within the preset processing area; Then, determine the sampling density adjustment coefficient based on the curvature fluctuation coefficient: when When ≤0.3, λ=1.0, and the sampling density remains the initial reference density. ; When 0.3 < When ≤0.6, The sampling density was adjusted to ; When >0.6, The sampling density was adjusted to ; Based on the preset dimensions, including length, width, height, and accuracy level of the processing area, the scanning distance is calculated. , Indicates the length, width, and height of the dimension boundaries. indicates the accuracy level, and finally the scanning path is planned according to the sampling density D and the scanning distance d: a spiral scanning path is adopted, the geometric center of the preset machining area is taken as the starting point of scanning, the spiral radius of the scanning path gradually increases from 0 to the maximum circumradius of the machining area, and the interval between adjacent spiral circles is strictly equal to d; at the same time, in the process of planning the scanning path, it is judged in real time whether the path covers all the boundary points of the preset machining area, if there are uncovered boundary points, a supplementary scanning path segment parallel to the boundary is added in the corresponding boundary region, and a circular arc transition is adopted at the junction of the supplementary path segment and the main spiral path, and the transition circular arc radius is d / 2, so that the scanning path completely covers the preset machining area and there is no repeated scanning area; wherein, , indicates the surface roughness of the workpiece, indicates the surface form and position tolerance of the workpiece.

[0009] Further, when the preprocessing module divides the collected point cloud data into levels according to the curvature variation of the workpiece surface, the curvature value of the workpiece surface is first divided into n curvature intervals, wherein, the minimum curvature and the maximum curvature of the workpiece surface, respectively, and the difference between adjacent curvature intervals is equal; all the point cloud data is traversed, and the curvature of the surface corresponding to each point cloud data is calculated , and the point cloud data falling into the same curvature interval is classified into the same level, and n point cloud levels are obtained, when removing the abnormal points in each level, for the point cloud data in each level, taking an arbitrary point p, the number of point clouds in the neighborhood of p with a radius of r is searched , the average value and the standard deviation of the number of neighborhood points of all point clouds in the level are calculated , when , it is determined that the point p is an abnormal point and is removed; When the missing point cloud is completed, the point cloud data of the boundary of the missing region is obtained, and the local surface equation of the boundary point cloud is established , the z coordinate of the virtual point is calculated by substituting the virtual point into the local surface equation, so as to complete the completion of the missing point cloud;

[0010] Further, when the extraction module identifies the feature region of the workpiece surface, the normal vector of each point in the layered point cloud data whose missing point cloud is completed , and the normal vector angle between adjacent points is calculated synchronously, indicates the normal vector of the adjacent two points, when When the angle is more than thirty degrees, the area where the corresponding adjacent point is located is marked as a feature region candidate area; The curvature change rate of the point cloud in the feature region candidate area is recalculated , denotes the curvature of the i, j points in the candidate area, denotes the Euclidean distance between the two points, and when > When the angle is more than thirty degrees, the area where the corresponding adjacent point is located is marked as a feature region candidate area; In the stage of extracting the spatial coordinates and topological relationship of the feature points, the spatial coordinates of all points in the feature region are obtained , and an adjacency matrix M of the feature points is constructed, and is subject to: ; In the formula: is an adjacency determination threshold, and is 1.2 times the sampling density of the corresponding level of the feature region, and the topological relationship of the feature points is represented by the adjacency matrix.

[0011] Further, when the construction module applies the spatial coordinates and topological relationship of the feature points to construct the local three-dimensional model of each region of the workpiece, the spatial coordinates of the feature points in each point cloud level corresponding region are used as the basis to fit the local surface by using the moving least squares method, and the fitting function is: ; In the formula: is the final output of the two-dimensional to three-dimensional surface mapping relationship, which is used to represent the surface form of the local region; is the number of feature points participating in fitting; i is the feature point index; is a weight function; is a basis function; , is the distance from the feature point to the point to be fitted, is the influence domain radius; According to the topological relationship adjacency matrix M of the feature points, the connection order of each point in the local surface is determined, and the grid structure of the local three-dimensional model is generated; In the stage of establishing the splicing constraint between the local three-dimensional models, the feature point coordinate deviation , , is the coordinate of the feature point k at the splicing place of the first local model, is the coordinate of the feature point k at the splicing place of the second local model, and the splicing constraint condition is set as , denotes the splicing accuracy threshold, and The value is set to 0.8 times the preset machining accuracy requirement of the workpiece; In the stage of stitching together the local 3D models, the spatial pose of the local 3D models is adjusted so that the coordinate deviation of the feature points at the stitching point meets the stitching constraint conditions, and finally the overall 3D model is constructed.

[0012] Furthermore, when the verification module compares the constructed overall 3D model with the preset machining accuracy requirements of the workpiece, it first selects m verification points on the overall 3D model according to the principle of uniform distribution, and obtains the model coordinates of each verification point. Simultaneously, the coordinates of the workpiece's actual position are obtained through measuring equipment. ; Calculate the accuracy deviation at each verification point ; Calculate the accuracy deviation of all verification points, and then calculate the average and maximum deviations. The average deviation and the maximum deviation are respectively compared with the workpiece's preset machining accuracy requirements. In comparison, when the average deviation is less than or equal to And the maximum deviation is less than or equal to 1.2 times. When the model is deemed to have acceptable accuracy in that region, the average deviation is considered acceptable. Or the maximum deviation is greater than 1.2 times. When this happens, the model is deemed to have out-of-tolerance accuracy in that region; For the model stitching area, additional k verification points are selected on the stitching boundary, and their accuracy deviation is calculated. If there is an accuracy deviation at any of the verification points at the stitching area... Greater than In the case of such a situation, the splicing point is marked as an out-of-tolerance area, and the coordinate range and out-of-tolerance value of the out-of-tolerance area are recorded.

[0013] Furthermore, when the output module adjusts the parameter format of the overall 3D model based on the verification results, if there are no out-of-tolerance parts in the verification results, it directly reads the model data format supported by the surface workpiece processing equipment, converts the overall 3D model into the corresponding format, and adjusts the unit parameters of the model to make the model units consistent with the unit settings of the processing equipment. If the verification results show out-of-tolerance areas, first, based on the coordinate range and out-of-tolerance value of the out-of-tolerance areas, perform local correction on the out-of-tolerance areas of the overall 3D model. When correcting, use the point cloud data of the qualified area around the out-of-tolerance area as a reference, and refit the surface of the out-of-tolerance area. The fitting method is the same as the local surface fitting method in the construction module. After the correction is completed, the precision checking process of the checking module is executed again until there is no out-of-tolerance part in the model, and then the corrected overall three-dimensional model is converted into a model data format suitable for the machining equipment, and when the model data is output, a precision checking report of the model is also output, which includes the number of checking points, the deviation value of each checking point, the correction of the out-of-tolerance part, and the final precision index. The model data format supported by the curved workpiece machining equipment includes STL, IGES, and STEP.

[0014] Further, the output module is further provided with a database, which is used to store the original point cloud data obtained by the acquisition module, the layered point cloud data processed by the preprocessing module, the spatial coordinates and topological relationship data of the feature points obtained by the extraction module, the local three-dimensional model data and the overall three-dimensional model data generated by the construction module, and the precision checking data of the checking module in chronological order. The database has a data correlation index, and the index information includes workpiece number, acquisition time, machining area parameters, precision requirements, and processing time of each module. The workpiece number can be used to quickly retrieve all three-dimensional reconstruction related data corresponding to the workpiece. The database adopts a distributed storage architecture, and different types of data are stored in different storage nodes. The original point cloud data and the processed point cloud data are stored in a high-speed read-write storage node, and the three-dimensional model data and the checking data are stored in a large-capacity storage node. The stored data is stored in an encrypted manner, and the encryption key includes the workpiece number.

[0015] Further, the acquisition module is connected to the preprocessing module and the extraction module through wireless network interaction, the extraction module is connected to the construction module through wireless network interaction, the construction module is connected to the checking module and the output module through wireless network interaction, and the checking module is connected to the output module through wireless network interaction.

[0016] In a second aspect, a curved workpiece machining three-dimensional reconstruction method based on point cloud data includes: Reference workpiece preset machining area parameters, adaptive adjustment of the acquisition device scanning path, sampling density and distance, driving device to obtain surface point cloud data, sampling density is determined according to the curvature fluctuation coefficient, the path adopts spiral and supplements the boundary scanning section;According to the curvature of the surface, the interval is divided into layered point cloud, the number of points in each level neighborhood is removed, the virtual point is generated through the boundary local surface equation, and the missing point cloud is completed;Calculate the point cloud normal vector and the adjacent point angle, mark the candidate area with the angle greater than thirty degrees, determine the feature area combined with the curvature change rate, synchronize the feature point coordinates, and construct the adjacency matrix to represent the topological relationship;Local three-dimensional model is generated by fitting the local surface with the feature point coordinates, the splicing constraint is established, the local model posture is adjusted synchronously to make the deviation meet the constraint, and the overall three-dimensional model is obtained by splicing;Select the check point to compare the model with the actual coordinates of the workpiece, calculate the deviation, judge the area accuracy combined with the preset accuracy, perform additional verification on the splicing part, mark the out-of-tolerance part and related information;When there is no out-of-tolerance, convert the model format and unify the unit, when there is out-of-tolerance, re-verify after correction, and output the model and the accuracy report containing the verification and correction information.

[0017] Compared with the known prior art, the technical scheme provided by the present application has the following beneficial effects: The present application provides a curved surface workpiece machining three-dimensional reconstruction method and system based on point cloud data. In the execution process, the scanning related parameters are adaptively adjusted to obtain the workpiece surface point cloud data, the acquisition is optimized combined with the workpiece preset machining area parameters, the data acquisition pertinence and efficiency are improved, the point cloud data is processed by layering according to the curvature change, the abnormal points are accurately removed and the missing parts are completed, the data quality is guaranteed, the feature area is identified by calculating the point cloud normal vector and the curvature change rate, the adjacency matrix is constructed to determine the topological relationship of the feature points, a precise foundation is laid for model construction, and the local three-dimensional model is constructed according to the layering order, the splicing constraint is established and the posture is adjusted to complete the overall splicing, the model integrity and accuracy are improved, and through the comparison of the model with the actual coordinates of the workpiece by multiple check points, the accuracy is accurately judged and the out-of-tolerance part is marked, finally, the model parameters are adjusted according to the verification result, the local correction is made to the qualified part when there is out-of-tolerance, and various data can be stored in order and support fast retrieval, which provides high-quality model and data support for curved surface workpiece machining. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0019] Figure 1This is a schematic diagram of a 3D reconstruction system for machining curved workpieces based on point cloud data. Figure 2 This is a flowchart illustrating a three-dimensional reconstruction method for machining curved workpieces based on point cloud data. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] The present invention will be further described below with reference to embodiments.

[0022] Example 1: This embodiment presents a 3D reconstruction system for machining curved workpieces based on point cloud data, such as... Figure 1 As shown, it includes: The acquisition module is used to adaptively adjust the scanning path, sampling density and scanning distance parameters of the acquisition device to drive the acquisition device to acquire point cloud data of the workpiece surface; When the acquisition module adaptively adjusts the acquisition device parameters, it first calculates the curvature fluctuation coefficient based on the curvature range of the preset processing area of ​​the curved workpiece: ; In the formula: These are the maximum and minimum curvature values ​​within the preset processing area; The average curvature value within the preset processing area; The above formula uses the maximum curvature value, minimum curvature value and average curvature value within the preset processing area as core parameters. By calculating the difference between the maximum and minimum curvature values ​​and comparing it with the average curvature value, the degree of change in the curvature of the surface in the processing area is quantified. This formula can dynamically identify areas where the curvature of the surface changes gently or dramatically, avoiding data redundancy caused by oversampling in areas with gentle curvature, and also preventing feature loss caused by insufficient sampling in areas with dramatic curvature. Then, determine the sampling density adjustment coefficient based on the curvature fluctuation coefficient: when When ≤0.3, λ=1.0, and the sampling density remains the initial reference density. ; When 0.3 < When ≤0.6, The sampling density was adjusted to ; When >0.6, , the sampling density is adjusted to ; Based on the size boundary length, width, height and accuracy level of the preset machining area, the scanning distance is calculated , The size boundary length, width, height, and accuracy level are represented by The final scanning path is planned according to the sampling density D and the scanning distance d: a spiral scanning path is adopted, the geometric center of the preset machining area is taken as the starting point of scanning, the spiral radius of the scanning path gradually increases from 0 to the maximum circumscribed circle radius of the machining area, and the spacing between adjacent spiral circles is strictly equal to d; At the same time, in the process of scanning path planning, it is judged in real time whether the path covers all the boundary points of the preset machining area, if there are uncovered boundary points, supplementary scanning path segments parallel to the boundary are added in the corresponding boundary area, and a circular arc transition is adopted at the junction of the supplementary path segment and the main spiral path, the transition circular arc radius is d / 2, so that the scanning path completely covers the preset machining area and there is no repeated scanning area; wherein, , The workpiece surface roughness is represented by The workpiece surface form and position tolerance is represented by It should be noted that: The workpiece surface roughness uses a surface roughness instrument to collect the micro profile curve data of the workpiece surface within a specified sampling length, reads the deviation distance (offset) of each point on the profile curve relative to the profile center line, takes the absolute value of all offsets, and calculates the arithmetic mean value to obtain the profile arithmetic mean deviation as the specific value of the surface roughness; The workpiece form and position tolerance (including shape tolerance and position tolerance) is calculated by comparing the actual geometric parameters of the workpiece with the ideal geometric parameters, combined with the tolerance band requirement, such as straightness by measuring the maximum deviation of the actual straight line from the ideal straight line, and position degree by calculating the coordinate deviation of the actual element from the reference element and the compliance degree of the tolerance value; In the calculation formula of the scanning distance, the workpiece surface roughness and the surface form and position tolerance, which are two key indicators affecting the machining precision, are considered comprehensively, and the scanning distance is calculated by integrating them through a specific mathematical relationship. The design idea of this formula is to make the scanning distance reflect the workpiece surface quality requirement, to ensure that the point cloud data obtained by scanning can meet the accuracy requirement of subsequent processing, to avoid the situation that the point cloud data cannot accurately represent the workpiece surface characteristics due to improper scanning distance, to make the determination of scanning distance more scientific and targeted, to automatically calculate the adaptive scanning distance according to the workpiece with different accuracy requirements, and to effectively improve the matching degree of point cloud data and actual workpiece surface characteristics, providing guarantee for high-precision three-dimensional reconstruction; The preprocessing module is used to divide the collected point cloud data into levels according to the curvature change of the workpiece surface, remove abnormal points in each level and complete the missing point cloud. When the preprocessing module divides the collected point cloud data into layers according to the curvature variation of the workpiece surface, it first divides the curvature values ​​of the workpiece surface into n curvature intervals. ,in, These represent the minimum curvature and maximum curvature of the workpiece surface, respectively, and the difference between adjacent curvature intervals. equal; Iterate through all the collected point cloud data and calculate the surface curvature corresponding to each point cloud data. ,Will Point cloud data falling within the same curvature interval are grouped into the same level, resulting in n point cloud levels. When removing outliers within each level, for any point p in the point cloud data of each level, the number of point clouds in its neighborhood of radius r is searched. Calculate the average number of neighborhood points for all point clouds within this level. with standard deviation ,when When the time is right, point p is considered an outlier and is removed. When completing a missing point cloud, for the missing regions formed after removing outliers, the point cloud data of the boundaries of the missing regions is obtained, and the local surface equations of the boundary point cloud are established. By generating virtual points at intervals of 0.5×D within the missing region, and substituting the virtual points into the local surface equation to calculate their z-coordinates, the missing point cloud is completed. Where D represents the sampling density of the corresponding level; It should be noted that, This represents a functional relationship describing the local surface morphology of the missing region. The function is generated by fitting point cloud data of the missing region's boundary. Its function type is determined based on the actual curvature characteristics of the workpiece surface (e.g., a quadratic polynomial function can be used for low-curvature, gently curvature regions, while a spline function can be used for high-curvature, complex regions). The aim is to represent the two-dimensional coordinates (…). ) participate in function operations to obtain This ultimately yields the three-dimensional coordinates (x, y, z). The extraction module is used to receive the layered point cloud data after the missing point cloud is completed, identify the feature regions of the workpiece surface, and extract the spatial coordinates and topological relationships of the feature points. When the extraction module identifies the feature regions of the workpiece surface, it simultaneously calculates the normal vector of each point in the layered point cloud data that has been completed to fill in the missing point cloud. and the angle between the normal vectors of adjacent points. , Represents the normal vector between two adjacent points, when When the angle exceeds 30 degrees, the region containing the corresponding adjacent points is marked as a candidate region for the feature region. Next, calculate the rate of curvature change of the point cloud within the candidate feature region. , curvature of two points i, j in the candidate region, Euclidean distance between two points, when > determine the candidate region as a feature region of the workpiece surface; In the spatial coordinate and topological relationship of the feature point extraction stage, the spatial coordinates of all points in the feature region are obtained , and an adjacency matrix M of the feature points is constructed, and is subject to: ; In the formula: is an adjacency determination threshold, and is 1.2 times the sampling density of the corresponding level of the feature region, and the topological relationship of the feature points is represented by the adjacency matrix; The construction module is used to receive the spatial coordinates and topological relationship of the feature points, apply the spatial coordinates and topological relationship of the feature points, construct local three-dimensional models of each region of the workpiece in the order of point cloud layering, establish splicing constraints between local three-dimensional models, and splice each local three-dimensional model to obtain an overall three-dimensional model; When the construction module applies the spatial coordinates and topological relationship of the feature points to construct local three-dimensional models of each region of the workpiece, first, for each region corresponding to a point cloud level, based on the spatial coordinates of the feature points in the region, a local surface is fitted using the moving least squares method, and the fitting function is: ; In the formula: is the final output of the two-dimensional to three-dimensional surface mapping relationship, used to represent the surface form of the local region; is the number of feature points participating in fitting; i is the feature point index; is a weight function; is a basis function; , is the distance from the feature point to the point to be fitted, is the influence domain radius; The above formula uses the spatial coordinates of the feature points as the basis to construct the fitting function using the moving least squares method. In the function, the contribution of different feature points is weighted by the weight function, and then combined with the basis function, to finally obtain the two-dimensional to three-dimensional surface mapping relationship representing the surface form of the local region. This makes the fitted surface closer to the feature points with larger weights, while taking into account the information of all feature points in the local region, realizes accurate fitting of the local surface, ensures the locality and smoothness of the fitting, avoids distortion of the local surface caused by global fitting, and provides core fitting method support for constructing high-precision local three-dimensional models; According to the topological relationship adjacency matrix M of the feature points, the connection order of each point in the local surface is determined, and the grid structure of the local three-dimensional model is generated; In the stage of establishing splicing constraints between local 3D models, the coordinate deviation of feature points at the splicing point of two adjacent local 3D models is calculated. , , Let k be the coordinates of the feature point k at the junction of the first local model. Let the coordinates of feature point k at the stitching point of the second local model be set, and set the stitching constraint as follows: , This indicates the splicing precision threshold, and The value is set to 0.8 times the preset machining accuracy requirement of the workpiece; In the stage of stitching together the local 3D models, the spatial pose of the local 3D models is adjusted so that the coordinate deviation of the feature points at the stitching point meets the stitching constraint conditions, and the overall 3D model is finally constructed. The verification module is used to compare the constructed overall 3D model with the preset machining accuracy requirements of the workpiece, automatically verify the accuracy deviation of each area and splicing point of the model, and mark the out-of-tolerance parts. When the verification module compares the constructed overall 3D model with the preset machining accuracy requirements of the workpiece, it first selects m verification points on the overall 3D model according to the principle of uniform distribution, and obtains the model coordinates of each verification point. Simultaneously, the coordinates of the workpiece's actual position are obtained through measuring equipment. ; Calculate the accuracy deviation at each verification point ; Calculate the accuracy deviation of all verification points, and then calculate the average and maximum deviations. The average deviation and the maximum deviation are respectively compared with the workpiece's preset machining accuracy requirements. In comparison, when the average deviation is less than or equal to And the maximum deviation is less than or equal to 1.2 times. When the model is deemed to have acceptable accuracy in that region, the average deviation is considered acceptable. Or the maximum deviation is greater than 1.2 times. When this happens, the model is deemed to have out-of-tolerance accuracy in that region; For the model stitching area, additional k verification points are selected on the stitching boundary, and their accuracy deviation is calculated. If there is an accuracy deviation at any of the verification points at the stitching area... Greater than In the case of this, the splicing point is marked as an out-of-tolerance area, and the coordinate range and out-of-tolerance value of the out-of-tolerance area are recorded; The output module is used to obtain the verification results, adjust the parameter format of the overall 3D model based on the verification results, and output model data adapted to the surface workpiece processing equipment. When the output module adjusts the parameter format of the overall three-dimensional model based on the checking result, if there is no out-of-tolerance part in the checking result, the model data format supported by the curved surface workpiece processing equipment is directly read, the overall three-dimensional model is converted into the corresponding format, and the unit parameters of the model are adjusted to make the model unit consistent with the unit setting of the processing equipment; If there is an out-of-tolerance part in the checking result, the out-of-tolerance area of the overall three-dimensional model is first locally corrected according to the coordinate range and the out-of-tolerance value of the out-of-tolerance part. When correcting, the point cloud data of the qualified area around the out-of-tolerance part is taken as the reference to re-fit the surface of the out-of-tolerance area. The fitting method is consistent with the local surface fitting method in the construction module. After the correction is completed, the precision checking process of the checking module is executed again until there is no out-of-tolerance part in the model. Then the corrected overall three-dimensional model is converted into a model data format suitable for the processing equipment. When outputting the model data, a precision checking report of the model is also outputted. The report includes the number of checking points, the deviation value of each checking point, the correction of the out-of-tolerance part, and the final precision index. The model data format supported by the curved surface workpiece processing equipment includes STL, IGES, and STEP. The output module also has a database inside. The database is used to store the original point cloud data obtained by the acquisition module, the layered point cloud data processed by the preprocessing module, the spatial coordinates and topological relationship data of the feature points obtained by the extraction module, the local three-dimensional model data and the overall three-dimensional model data generated by the construction module, and the precision checking data of the checking module in chronological order. Data association indexes are established in the database. The index information includes workpiece number, acquisition time, processing area parameters, precision requirements, and processing time of each module. Through the workpiece number, all three-dimensional reconstruction related data corresponding to the workpiece can be quickly retrieved. The database uses a distributed storage architecture to store different types of data in different storage nodes. The original point cloud data and the processed point cloud data are stored in high-speed read-write storage nodes, and the three-dimensional model data and the checking data are stored in large-capacity storage nodes. The stored data is stored in an encrypted manner. The encryption key includes the workpiece number. During the running stage of the acquisition module, the acquisition equipment is adjusted with reference to the curvature range, size boundary, and precision level parameters of the preset processing area of the curved surface workpiece. The acquisition module is connected to the preprocessing module and the extraction module through wireless network interaction. The extraction module is connected to the construction module through wireless network interaction. The construction module is connected to the checking module and the output module through wireless network interaction. The checking module is connected to the output module through wireless network interaction.

[0023] In the embodiment, the acquisition module runs adaptive adjustment of the scanning path, sampling density and scanning distance parameters of the acquisition device, drives the acquisition device to obtain the point cloud data of the workpiece surface, the preprocessing module is run in the back end, the collected point cloud data is divided into levels according to the curvature change of the workpiece surface, the abnormal points in each level are removed and the missing point cloud is completed, the extraction module receives the layered point cloud data after the missing point cloud is completed, identifies the feature area of the workpiece surface, extracts the spatial coordinates and topological relationship of the feature points, the construction module further receives the spatial coordinates and topological relationship of the feature points, applies the spatial coordinates and topological relationship of the feature points, constructs the local three-dimensional model of each region of the workpiece in the order of point cloud layering, establishes the splicing constraint between the local three-dimensional models, splices the local three-dimensional models to obtain the overall three-dimensional model, and the verification module compares the constructed overall three-dimensional model with the preset machining precision requirement of the workpiece, automatically checks the precision deviation of each region and the splicing of the model and marks the out-of-tolerance parts, and finally the output module obtains the verification result, adjusts the parameter format of the overall three-dimensional model based on the verification result, and outputs the model data suitable for the machining equipment of the curved surface workpiece.

[0024] In the above embodiment, the system flexibly adjusts the scanning parameters in combination with the workpiece machining area parameters during use, ensures comprehensive and accurate point cloud data acquisition, can optimize point cloud processing according to the curvature, accurately extracts features and constructs models in layers, guarantees the integrity of the model through splicing constraints, ensures that the model meets the machining requirements through precision verification and correction, adapts to the format output of the machining equipment, simultaneously stores the full-process data for easy tracing, effectively improves the three-dimensional reconstruction efficiency and precision of the curved surface workpiece, provides reliable data support for subsequent machining, and reduces the risk of machining errors.

[0025] Embodiment 2: In the specific implementation level, based on embodiment 1, the embodiment refers to Figure 2 The curved surface workpiece machining three-dimensional reconstruction system based on point cloud data in embodiment 1 is further specifically described: The curved surface workpiece machining three-dimensional reconstruction method based on point cloud data comprises: Reference is made to the preset machining area parameters of the workpiece, the scanning path, sampling density and distance of the acquisition device are adaptively adjusted, the device is driven to obtain the surface point cloud data, the sampling density is determined according to the curvature fluctuation coefficient, the path adopts a spiral type and a boundary scanning section is supplemented; The point cloud is divided into intervals according to the curvature of the surface, the points with abnormal number of neighborhood points in each level are removed, virtual points are generated through the boundary local surface equation, and the missing point cloud is completed; The normal vector of the point cloud and the included angle between adjacent points are calculated, the candidate area with an included angle greater than thirty degrees is marked, the feature area is determined in combination with the curvature change rate, the coordinates of the feature points are synchronously obtained, and an adjacency matrix is constructed to represent the topological relationship; The local three-dimensional model is generated by fitting a local surface with feature point coordinates, a splicing constraint is established, and the local model posture is adjusted synchronously to make the deviation meet the constraint, and the overall three-dimensional model is spliced; The deviation is calculated by selecting a check point to compare the model with the actual coordinates of the workpiece, the area precision is judged in combination with the preset precision, the splicing part is additionally checked, and the out-of-tolerance part and related information are marked; When there is no out-of-tolerance, the model format is converted and the unit is unified, when there is out-of-tolerance, the model is rechecked after correction, and the model and the precision report containing the check and correction information are output after passing.

[0026] In summary, in the above-mentioned embodiments, the method and system adjust the scanning related parameters adaptively to obtain the workpiece surface point cloud data, optimize the collection in combination with the preset machining area parameters of the workpiece, improve the data acquisition pertinence and efficiency, process the point cloud data in layers according to the curvature change, accurately remove abnormal points and complete the missing part, guarantee the data quality, identify the feature area by calculating the point cloud normal vector and the curvature change rate, construct the adjacency matrix to clarify the topological relationship of the feature points, lay a precise foundation for model construction, construct the local three-dimensional model in the layered order, establish the splicing constraint and adjust the posture to complete the overall splicing, improve the model integrity and accuracy, compare the model with the actual coordinates of the workpiece through multiple check points, accurately judge whether the precision is qualified and mark the out-of-tolerance part, finally adjust the model parameter format according to the check result, locally correct to qualified when there is out-of-tolerance, and can also store various data in order and support fast retrieval, provide high-quality model and data support for curved workpiece machining.

[0027] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements will not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A three-dimensional reconstruction system for machining curved workpieces based on point cloud data, characterized in that, include: The acquisition module is used to adaptively adjust the scanning path, sampling density and scanning distance parameters of the acquisition device to drive the acquisition device to acquire point cloud data of the workpiece surface; The preprocessing module is used to divide the collected point cloud data into layers according to the curvature changes of the workpiece surface, remove abnormal points in each layer, and fill in the missing point cloud. The extraction module is used to receive the layered point cloud data after the missing point cloud is completed, identify the feature regions of the workpiece surface, and extract the spatial coordinates and topological relationships of the feature points. The module is used to receive the spatial coordinates and topological relationships of feature points, apply the spatial coordinates and topological relationships of feature points, construct local 3D models of each region of the workpiece according to the layering order of the point cloud, establish splicing constraints between local 3D models, and splice the local 3D models to obtain the overall 3D model. The verification module is used to compare the constructed overall 3D model with the preset machining accuracy requirements of the workpiece, automatically verify the accuracy deviation of each area and splicing point of the model, and mark the out-of-tolerance parts. The output module is used to obtain the verification results, adjust the parameter format of the overall 3D model based on the verification results, and output model data adapted to the surface workpiece processing equipment. During the acquisition module's operation phase, the acquisition equipment is adjusted based on the curvature range, dimensional boundaries, and accuracy level parameters of the preset processing area of ​​the curved workpiece.

2. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the acquisition module adaptively adjusts the parameters of the acquisition device, it first calculates the curvature fluctuation coefficient based on the curvature range of the preset processing area of ​​the curved workpiece: ； In the formula: These are the maximum and minimum curvature values ​​within the preset processing area; The average curvature value within the preset processing area; Then, determine the sampling density adjustment coefficient based on the curvature fluctuation coefficient: when When ≤0.3, λ=1.0, and the sampling density remains the initial reference density. ; When 0.3 < When ≤0.6, The sampling density was adjusted to ; When >0.6, The sampling density was adjusted to ; Based on the preset dimensions, including length, width, height, and accuracy level of the processing area, the scanning distance is calculated. , Indicates the length, width, and height of the dimension boundaries. The accuracy level is indicated, and the final scanning path is planned according to the sampling density D and the scanning distance d: a spiral scanning path is adopted, with the geometric center of the preset processing area as the scanning starting point. The spiral radius of the scanning path gradually increases from 0 to the maximum circumscribed circle radius of the processing area, and the distance between adjacent spiral loops is strictly equal to d. At the same time, during the scanning path planning process, it is determined in real time whether the path covers all boundary points of the preset processing area. If there are uncovered boundary points, a supplementary scanning path segment parallel to the boundary is added in the corresponding boundary area. The connection between the supplementary path segment and the main spiral path is a rounded transition with a transition arc radius of d / 2, so that the scanning path completely covers the preset processing area and there is no duplicate scanning area. in, , Indicates the surface roughness of the workpiece. This indicates the form and position tolerances of the workpiece surface.

3. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the preprocessing module divides the collected point cloud data into levels according to the curvature changes of the workpiece surface, it first divides the curvature values ​​of the workpiece surface into n curvature intervals. ,in, These represent the minimum curvature and maximum curvature of the workpiece surface, respectively, and the difference between adjacent curvature intervals. equal; Iterate through all the collected point cloud data and calculate the surface curvature corresponding to each point cloud data. ,Will Point cloud data falling within the same curvature interval are grouped into the same level, resulting in n point cloud levels. When removing outliers within each level, for any point p in the point cloud data of each level, the number of point clouds in its neighborhood of radius r is searched. Calculate the average number of neighborhood points for all point clouds within this level. with standard deviation ,when When the time is right, point p is considered an outlier and is removed. When completing a missing point cloud, for the missing regions formed after removing outliers, the point cloud data of the boundaries of the missing regions is obtained, and the local surface equations of the boundary point cloud are established. By generating virtual points at intervals of 0.5×D within the missing region, and substituting the virtual points into the local surface equation to calculate their z-coordinates, the missing point cloud is completed. Where D represents the sampling density of the corresponding level.

4. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the extraction module identifies the feature regions of the workpiece surface, it simultaneously calculates the normal vector of each point in the layered point cloud data that has been completed to fill in the missing point cloud. and the angle between the normal vectors of adjacent points. , Represents the normal vector between two adjacent points, when When the angle exceeds 30 degrees, the region containing the corresponding adjacent points is marked as a candidate region for the feature region. Next, calculate the rate of curvature change of the point cloud within the candidate feature region. , This represents the curvature of points i and j within the candidate region. Represents the Euclidean distance between two points, when > When this happens, the candidate region is determined to be a characteristic region of the workpiece surface; In the stage of extracting the spatial coordinates and topological relationships of feature points, the spatial coordinates of all points within the feature region are obtained. And construct the adjacency matrix M of the feature points, which follows the following: ； In the formula: The threshold for adjacency determination is , and The value is set to 1.2 times the sampling density of the corresponding layer of the feature region, and the topological relationship of the feature points is represented by the adjacency matrix.

5. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the construction module constructs local 3D models of various regions of the workpiece using the spatial coordinates and topological relationships of feature points, it first fits the local surface of each region corresponding to each point cloud level using the spatial coordinates of feature points within that region. The fitting function is as follows: ； In the formula: This is the final output of a two-dimensional to three-dimensional surface mapping relationship, used to characterize the surface morphology of local regions; The number of feature points involved in the fitting; i is the feature point index; For weighting functions; are basis functions; , The distance from the feature point to the point to be fitted. The radius of the influence domain; Based on the adjacency matrix M of the topological relationships of the feature points, the connection order of each point in the local surface is determined, and the mesh structure of the local 3D model is generated. In the stage of establishing splicing constraints between local 3D models, the coordinate deviation of feature points at the splicing point of two adjacent local 3D models is calculated. , , Let k be the coordinates of the feature point k at the junction of the first local model. Let the coordinates of feature point k at the stitching point of the second local model be set, and set the stitching constraint as follows: , This indicates the splicing precision threshold, and The value is set to 0.8 times the preset machining accuracy requirement of the workpiece; In the stage of stitching together the local 3D models, the spatial pose of the local 3D models is adjusted so that the coordinate deviation of the feature points at the stitching point meets the stitching constraint conditions, and finally the overall 3D model is constructed.

6. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the verification module compares the constructed overall 3D model with the preset machining accuracy requirements of the workpiece, it first selects m verification points on the overall 3D model according to the principle of uniform distribution, and obtains the model coordinates of each verification point. Simultaneously, the coordinates of the workpiece's actual position are obtained through measuring equipment. ; Calculate the accuracy deviation at each verification point ; Calculate the accuracy deviation of all verification points, and then calculate the average and maximum deviations. The average deviation and the maximum deviation are respectively compared with the workpiece's preset machining accuracy requirements. In comparison, when the average deviation is less than or equal to And the maximum deviation is less than or equal to 1.2 times. When the model is deemed to have acceptable accuracy in that region, the average deviation is considered acceptable. Or the maximum deviation is greater than 1.2 times. When this happens, the model is deemed to have out-of-tolerance accuracy in that region; For the model stitching area, additional k verification points are selected on the stitching boundary, and their accuracy deviation is calculated. If there is an accuracy deviation at any of the verification points at the stitching area... Greater than In the case of such a situation, the splicing point is marked as an out-of-tolerance area, and the coordinate range and out-of-tolerance value of the out-of-tolerance area are recorded.

7. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, When the output module adjusts the parameter format of the overall 3D model based on the verification results, if there are no out-of-tolerance parts in the verification results, it directly reads the model data format supported by the surface workpiece processing equipment, converts the overall 3D model into the corresponding format, and adjusts the unit parameters of the model to make the model units consistent with the unit settings of the processing equipment. If the verification results show out-of-tolerance areas, first, based on the coordinate range and out-of-tolerance value of the out-of-tolerance areas, perform local correction on the out-of-tolerance areas of the overall 3D model. When correcting, use the point cloud data of the qualified area around the out-of-tolerance area as a reference, and refit the surface of the out-of-tolerance area. The fitting method is the same as the local surface fitting method in the construction module. After the correction is completed, the accuracy verification process of the verification module is executed again until there are no out-of-tolerance parts in the model. Then, the corrected overall 3D model is converted into a model data format that is compatible with the processing equipment. When outputting the model data, the accuracy verification report of the model is also output. The report includes the number of verification points, the deviation value of each verification point, the correction status of out-of-tolerance parts, and the final accuracy index. Among them, the model data formats supported by the surface workpiece processing equipment include STL, IGES, and STEP.

8. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, The output module also contains a database, which is used to store the raw point cloud data acquired by the acquisition module, the layered point cloud data processed by the preprocessing module, the feature point spatial coordinates and topological relationship data obtained by the extraction module, the local three-dimensional model data and the overall three-dimensional model data generated by the construction module, and the accuracy verification data of the verification module in the order of timestamps. The database contains a data association index, which includes workpiece number, acquisition time, processing area parameters, accuracy requirements, and processing time of each module. All 3D reconstruction-related data for a workpiece can be quickly retrieved by workpiece number. The database adopts a distributed storage architecture, storing different types of data on different storage nodes. The original point cloud data and the processed point cloud data are stored on high-speed read and write storage nodes, while the 3D model data and verification data are stored on large-capacity storage nodes. The stored data is stored in an encrypted manner, and the encryption key includes the workpiece number.

9. The three-dimensional reconstruction system for machining curved workpieces based on point cloud data according to claim 1, characterized in that, The acquisition module is interconnected with the preprocessing module and the extraction module via a wireless network. The extraction module is interconnected with the construction module via a wireless network. The construction module is interconnected with the verification module and the output module via a wireless network. The verification module is interconnected with the output module via a wireless network.

10. A method for three-dimensional reconstruction of curved workpiece machining based on point cloud data, wherein the method is an implementation method of the three-dimensional reconstruction system for curved workpiece machining based on point cloud data as described in any one of claims 1-9, characterized in that, include: Based on the preset processing area parameters of the workpiece, the scanning path, sampling density and distance of the acquisition device are adaptively adjusted to drive the device to acquire surface point cloud data. The sampling density is determined according to the curvature fluctuation coefficient, and the path adopts a spiral shape and is supplemented with boundary scanning segments. The point cloud is divided into layers according to the curvature of the surface. Points with abnormal number of neighboring points in each layer are removed. Virtual points are generated by the boundary local surface equation to complete the missing point cloud. Calculate the point cloud normal vector and the angle between adjacent points, mark candidate regions with angles exceeding 30 degrees, determine feature regions by combining the rate of curvature change, simultaneously obtain the coordinates of feature points, and construct an adjacency matrix to represent topological relationships. A local 3D model is generated by fitting the coordinates of feature points to a local surface, a splicing constraint is established, the posture of the local model is adjusted synchronously to make the deviation meet the constraint, and the overall 3D model is obtained by splicing. Select verification points to compare the model with the actual coordinates of the workpiece to calculate the deviation. Combine the preset accuracy to determine the accuracy of the area. Perform additional verification at the splicing point and mark the out-of-tolerance parts and related information. If there are no out-of-tolerance errors, convert the model format and unify the units. If there are out-of-tolerance errors, correct them and re-verify. After passing the verification, output the model and an accuracy report containing verification and correction information.

Images