Component size acceptance method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of constructional engineering, and provides a component size acceptance method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a scene global coordinate of calibration equipment in a detection area under a scene global coordinate system; constructing a fusion rotation matrix for coordinate conversion by using visual image data, attitude data, position data and scene global coordinates acquired by a measurement device; performing coordinate transformation on the three-dimensional point cloud model of the to-be-measured component by using the fusion rotation matrix to obtain a target three-dimensional point cloud model under a scene global coordinate system; and according to the target three-dimensional point cloud model and the original BIM model, obtaining a size acceptance result of the to-be-tested component. A traditional laser tracker is replaced with the combination of the IMU and the UWB, the cost of the component size can be remarkably reduced, meanwhile, the size detection precision can be guaranteed, and the size acceptance efficiency is remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of building engineering technology, and in particular relates to a method, device, electronic equipment and storage medium for accepting component dimensions. Background Technology

[0002] In the field of construction engineering, the dimensional inspection of large components such as steel structures and precast concrete parts upon arrival at the construction site is a crucial step in ensuring construction quality and safety. Currently, while the inspection method based on six-dimensional sensors and laser trackers can achieve high accuracy, it has significant limitations in practical applications: laser trackers are highly sensitive to changes in ambient lighting and object occlusion, and have stringent requirements for environmental stability; at the same time, this method requires the use of a dedicated rigid spherical target array and the establishment of a complex mathematical model during calibration, resulting in time-consuming calibration, high equipment and maintenance costs, and difficulty in meeting the high-frequency and high-efficiency inspection needs of construction sites. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method, apparatus, electronic device and storage medium for accepting component dimensions, so as to solve the above problems.

[0004] This invention provides a method for accepting the dimensions of a component, comprising: determining the scene global coordinates of a calibration device within a detection area in a scene global coordinate system, wherein the scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; acquiring multiple point measurement data of the component to be tested within the detection area using a measuring device, wherein the measuring device includes a structured light scanner and an IMU sensor and a UWB tag integrated on the structured light scanner, and the measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag; constructing a fusion rotation matrix for coordinate transformation based on the visual image data, attitude data, position data, and scene global coordinates; acquiring a three-dimensional point cloud model of the component to be tested within the detection area using the measuring device, and performing coordinate transformation on the three-dimensional point cloud model using the fusion rotation matrix to obtain a target three-dimensional point cloud model in the scene global coordinate system; and obtaining the dimension acceptance result of the component to be tested based on the target three-dimensional point cloud model and the original BIM model.

[0005] In one embodiment of the present invention, determining the scene global coordinates of the calibration device in the scene global coordinate system within the detection area includes: deploying a first preset number of UWB base stations in the detection area; deploying a second preset number of calibration targets in the detection area, wherein each calibration target has at least a third preset number of non-collinear feature points; and obtaining the scene global coordinates of the UWB base stations and each feature point in the scene global coordinate system.

[0006] In one embodiment of the present invention, a fusion rotation matrix for coordinate transformation is constructed based on visual image data, pose data, position data, and scene global coordinates. This includes: integrating the pose data at each point to obtain quaternion pose information of the measuring device at each point; filtering the position data at each point to obtain target position information of the measuring device at each point; extracting the local coordinates of feature points in the local coordinate system of the structured light scanner from the visual image data at each point; determining the target coordinates of the structured light scanner in the scene global coordinate system based on the local coordinates of each feature point in the local coordinate system of the structured light scanner and the scene global coordinates in the scene global coordinate system; and constructing a fusion rotation matrix for coordinate transformation based on the quaternion pose information, target position information, and target coordinates corresponding to each point.

[0007] In one embodiment of the present invention, a fusion rotation matrix for coordinate transformation is constructed based on the quaternion attitude information, target position information, and target coordinates corresponding to each point. This includes: constructing a state vector corresponding to each point based on the quaternion attitude information, target position information, and target coordinates; determining the predicted data corresponding to each point based on the state vector using the dynamic model of the IMU sensor, the UWB ranging model, and the local and global coordinate transformation model; constructing an optimization function with the objective of minimizing the error between the state vector and the predicted data; iteratively calculating the optimization function using a nonlinear optimization algorithm until the optimization function converges to a preset threshold; extracting the target quaternion from the converged state vector, and calculating the fusion rotation matrix based on the target quaternion and the rotation matrix transformation formula.

[0008] In one embodiment of the present invention, a three-dimensional point cloud model of a component to be tested within a detection area is obtained by a measuring device, including: obtaining the material type of the component to be tested; collecting multi-view target data of the component to be tested using a collection strategy and measuring device that matches the material type; and processing the multi-view target data using an iterative nearest point algorithm to obtain a three-dimensional point cloud model of the component to be tested.

[0009] In one embodiment of the present invention, a 3D point cloud model is transformed by a fusion rotation matrix to obtain a target 3D point cloud model in the scene global coordinate system. This includes: acquiring a translation vector obtained by the measuring device from the UWB tag positioning when scanning the component to be measured; and performing coordinate transformation on the 3D point cloud model according to the fusion rotation matrix and the translation vector to obtain a target 3D point cloud model in the scene global coordinate system.

[0010] In one embodiment of the present invention, the method further includes: performing accuracy optimization processing on the target three-dimensional point cloud model, wherein the accuracy optimization processing includes at least one of the following: performing temperature compensation on the size of the target three-dimensional point cloud model based on the material linear expansion coefficient of the component to be measured, the current temperature of the component to be measured, and the design reference temperature; and performing equipment temperature correction on the measurement error based on the temperature error coefficient of the structured light scanner, the current equipment temperature, and the calibration temperature.

[0011] In one embodiment of the present invention, obtaining the dimensional acceptance result of the component to be tested includes: The target 3D point cloud model and the preset original BIM model are converted into the same coordinate system by a fusion rotation matrix, and the deviation value between the target 3D point cloud model and the original BIM model is calculated; based on the deviation value and the preset deviation threshold, the dimensional acceptance result of the component to be tested is generated.

[0012] This invention also provides a component size acceptance device, comprising: a coordinate determination module configured to determine the scene global coordinates of a calibration device within the detection area in the scene global coordinate system, wherein the scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; a data acquisition module configured to acquire multiple point measurement data of the component to be tested within the detection area through a measuring device, wherein the measuring device includes a structured light scanner and an IMU sensor and a UWB tag integrated on the structured light scanner, and the measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag; a matrix construction module configured to construct a fusion rotation matrix for coordinate transformation based on the measurement data of multiple points and the scene global coordinates; a coordinate transformation module configured to acquire a three-dimensional point cloud model of the component to be tested within the detection area through the measuring device, and use the fusion rotation matrix to perform coordinate transformation on the three-dimensional point cloud model to obtain a target three-dimensional point cloud model in the scene global coordinate system; and a result acceptance module configured to obtain the size acceptance result of the component to be tested based on the target three-dimensional point cloud model and the original BIM model.

[0013] The present invention also provides an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to perform the steps of the above-described method.

[0014] The present invention also provides a storage medium comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the storage medium performs the steps of the above-described method.

[0015] The beneficial effects of this technical solution are as follows: First, by determining the scene global coordinates of the calibration equipment within the detection area in the scene's global coordinate system; second, by acquiring measurement data from multiple points within the detection area using measurement equipment, including a structured light scanner and an IMU sensor and UWB tag integrated on the structured light scanner; and third, by constructing a fusion rotation matrix for coordinate transformation based on visual image data, posture data, position data, and scene global coordinates; fourth, by using the fusion rotation matrix to transform the coordinates of the 3D point cloud model of the component under test, obtaining the target 3D point cloud model in the scene's global coordinate system; and fifth, by obtaining the dimensional acceptance results of the component under test based on the target 3D point cloud model and the original BIM model. Firstly, by combining structured light scanning and image analysis, the component under test is converted into a computable 3D point cloud model, which meets the requirements for rapid on-site inspection of large components while ensuring inspection accuracy. Furthermore, by using a combination of IMU and UWB to replace the traditional laser tracker, the detection scene is not limited by space or environment, and the cost of the entire detection system is significantly reduced. Finally, by comparing and analyzing with the BIM model, the difference between the actual dimensions of the component under test and the original design dimensions can be accurately identified, thereby quickly generating dimensional acceptance results. While ensuring testing accuracy, it significantly improves acceptance efficiency.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 This is a schematic flowchart illustrating a method for accepting component dimensions, as shown in an exemplary embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a component size acceptance device shown in an exemplary embodiment of the present invention; Figure 3 A schematic diagram of a computer system suitable for implementing embodiments of the present invention is shown. Detailed Implementation

[0018] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the shape, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0020] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0021] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for accepting component dimensions, as shown in an exemplary embodiment of the present invention. Figure 1 As shown, in an exemplary embodiment, the component size acceptance method includes steps S101 to S105, and each step is described in detail below.

[0022] S101, Determine the scene global coordinates of the calibration device within the detection area in the scene global coordinate system; The scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; Specifically, firstly, based on the characteristics and requirements of the actual engineering scenario, a suitable reference point is selected as the origin of the scene's global coordinate system. This reference point can be a fixed point or a specific location within the engineering scenario. Then, based on this origin, three mutually perpendicular coordinate axes are determined: the X-axis, the Y-axis, and the Z-axis, thereby constructing a three-dimensional scene global coordinate system.

[0023] In some examples, a global coordinate system for the actual engineering scenario can be established based on the BeiDou Navigation Satellite System, the Global Positioning System (GPS), or Building Information Modeling (BIM). In some embodiments, determining the scene global coordinates of the calibration device within the detection area in the scene global coordinate system includes: Deploy a first preset number of ultra-wideband (UWB) base stations within the detection area; deploy a second preset number of calibration targets within the detection area, wherein each calibration target has at least a third preset number of non-collinear feature points; obtain the scene global coordinates of the UWB base stations and each feature point in the scene global coordinate system.

[0024] Specifically, the testing area needs to cover the component to be measured. It should be noted that, since the size, shape and position of the components are different, different testing areas need to be determined according to the test site conditions and the component to be measured.

[0025] It is understandable that after determining the detection area, a first preset number (e.g., 4) of UWB base stations and a second preset number (e.g., 7, 8, etc.) of calibration targets need to be deployed within the detection area. Each calibration target has at least a third preset number (e.g., 3) of non-collinear feature points. This ensures that the position of the calibration target in the scene's global coordinate system can be accurately determined through these feature points.

[0026] It is understandable that UWB base stations are used to transmit and receive ultra-wideband signals, determining location information by measuring the signal's time of flight; calibration targets serve as reference points for known locations, and their feature points are used for precise calibration and alignment. When deploying UWB base stations and calibration targets, it is necessary to ensure a reasonable distribution that covers the entire detection area and avoids mutual interference. For example, four UWB base stations can be deployed at the four corners or suitable locations of the detection area, and a second, predetermined number of calibration targets can be evenly distributed within the detection area.

[0027] In addition, obtaining the scene global coordinates of the UWB base station and each feature point in the scene global coordinate system can be achieved using professional measurement equipment, such as using a total station to measure the scene global coordinates of the UWB base station and each feature point in the scene global coordinate system.

[0028] S102, acquire measurement data of multiple points of the component to be tested within the detection area through measuring equipment.

[0029] The measurement equipment includes a structured light scanner, an inertial measurement unit (IMU) sensor integrated on the structured light scanner, and a UWB tag. The measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag. Specifically, by integrating IMU sensors and UWB tags onto a structured light scanner, the structured light scanner can acquire its own attitude and position data in real time while collecting visual image data, ensuring that the acquired measurement data remains consistent in time and space.

[0030] As we understand it, a structured light scanner emits light of a specific pattern onto the surface of a component under test, then receives the reflected light. It obtains three-dimensional information about the component's surface—i.e., visual image data—based on the deformation of the light rays. An IMU sensor measures the structured light scanner's attitude in three-dimensional space, including rotation angles, providing accurate attitude information for subsequent data processing. UWB tags utilize ultra-wideband signals to determine the structured light scanner's specific position in the scene's global coordinate system, ensuring the spatial positioning accuracy of the measurement data.

[0031] It's worth noting that in the fusion solution of structured light scanner + UWB + IMU, the cost of UWB base stations and IMU sensors is far lower than that of laser trackers. Structured light scanners are also economical 3D acquisition devices, and UWB radio positioning is unaffected by lighting conditions, maintaining stable performance even in complex environments. IMU sensors provide high-precision attitude information, compensating for the shortcomings of single measurement methods. This multi-sensor fusion approach not only ensures measurement accuracy and reliability but also significantly reduces equipment costs and maintenance complexity, making it more suitable for the high-frequency, high-efficiency inspection needs of construction sites.

[0032] Furthermore, during actual measurement, operators or automated robotic arms can control a structured light scanner equipped with an IMU sensor and a UWB tag to scan and measure multiple points of the component under test within the detection area according to a certain path and sampling frequency, obtaining multiple measurement data. For example, the measuring device can be controlled to simultaneously acquire angular velocity and acceleration data of the IMU, position data of the UWB, and visual image data captured by the structured light scanner at at least 20 different known positions and attitudes.

[0033] S103, construct a fusion rotation matrix for coordinate transformation based on visual image data, pose data, position data, and scene global coordinates; Specifically, the data from a structured light scanner exists in a local coordinate system with the device itself as the origin, and this coordinate system changes dynamically as the device moves; while the spatial information required for Building Information Modeling (BIM) and construction management is based on a fixed global scene coordinate system. Without coordinate transformation, there is no unified spatial reference between the measured data and the design model, making it impossible to perform dimensional comparison, deviation analysis, and acceptance judgment.

[0034] In some embodiments, a fusion rotation matrix for coordinate transformation is constructed based on visual image data, pose data, position data, and scene global coordinates, including: The attitude data at each point is integrated to obtain the quaternion attitude information of the measuring device at each point. The position data at each point is filtered to obtain the target position information of the measuring device at each point. The local coordinates of feature points in the local coordinate system of the structured light scanner are extracted from the visual image data of each point. Based on the local coordinates of each feature point in the local coordinate system of the structured light scanner and the scene global coordinates in the scene global coordinate system, the target coordinates of the structured light scanner in the scene global coordinate system are determined. Based on the quaternion attitude information, target position information and target coordinates corresponding to each point, a fusion rotation matrix for coordinate transformation is constructed.

[0035] Specifically, by integrating the attitude data at each point, continuous attitude information can be obtained from the discrete attitude angle change data, thus yielding the quaternion attitude information of the measuring device at each point. It is understandable that quaternion attitude information can represent rotation in three-dimensional space, providing an attitude description for subsequent coordinate transformations.

[0036] In addition, filtering the location data of each point can eliminate noise and errors that may exist during the measurement process, thereby improving the accuracy and stability of the location data.

[0037] Furthermore, extracting the local coordinates of feature points in the local coordinate system of the structured light scanner from the visual image data of each point is the core step of coordinate transformation. As reference points with known locations, the local coordinates of feature points can reflect the three-dimensional information of the component surface in the local coordinate system.

[0038] Then, based on the local coordinates of each feature point in the local coordinate system of the structured light scanner and the scene global coordinate system, the local coordinates of the structured light scanner are converted into the target coordinates in the scene global coordinate system using the correspondence of the same feature points. This initial conversion from the local coordinate system to the scene global coordinate system provides a foundation for the subsequent construction of the fusion rotation matrix.

[0039] Finally, based on the quaternion attitude information, target position information, and target coordinates corresponding to each point, a fusion rotation matrix for coordinate transformation is constructed. This fusion rotation matrix comprehensively considers the attitude, position, and target coordinate information of the measuring device, and can accurately transform the measurement data in the local coordinate system to the global coordinate system of the scene, realizing a unified spatial reference benchmark between the measured data and the design model.

[0040] In some embodiments, a fusion rotation matrix for coordinate transformation is constructed based on the quaternion pose information, target position information, and target coordinates corresponding to each point, including: Based on the quaternion attitude information, initial position information, and target coordinates corresponding to each point, a state vector is constructed for each point. Based on the state vector corresponding to each point, the predicted data corresponding to each point is determined through the dynamic model of the IMU sensor, the UWB ranging model, and the local and global coordinate transformation model. An optimization function is constructed with the goal of minimizing the error between the state vector and the predicted data. The optimization function is iteratively calculated through a nonlinear optimization algorithm until the optimization function converges to a preset threshold. The target quaternion is extracted from the converged state vector, and the fused rotation matrix is ​​calculated according to the transformation formula of the target quaternion and the rotation matrix.

[0041] Specifically, based on the quaternion attitude information, initial position information, and target coordinates corresponding to each point, a state vector is constructed for each point. ( ),in,( ) represents the target coordinates of the structured light scanner in the scene's global coordinate system. ) represents quaternion pose information, ( The value represents the sensor bias, which includes IMU zero bias and UWB ranging bias.

[0042] Then, based on the state vector corresponding to each point, prediction data for each point is obtained through the IMU sensor's dynamic model, UWB ranging model, and local-to-global coordinate transformation model. This prediction data represents the predicted coordinates, predicted attitude data, and predicted position data of each point in the global coordinate system. This process requires decomposition and then integration to complete.

[0043] To better understand this step, some examples are provided below: First, it is necessary to obtain the target coordinates of the structured light scanner in the scene's global coordinate system. Quaternion attitude information (q1,q2,q3,q4), UWB ranging bias b-uwb, IMU zero bias b-imu.

[0044] Then, through three prediction calculations, namely: (1) Calculation of predicted value of UWB ranging: scan position + ranging deviation, to obtain D-prediction; (2) Calculation of predicted IMU angular velocity: The true angular velocity corresponding to the attitude + IMU zero bias is used to obtain W-prediction; (3) Global coordinate prediction of feature points: The feature points of the visual image data are first parsed into local coordinates in the local coordinate system, and then converted into global coordinates through the pose quaternion information + scan position. P-coordinate prediction = (X1, Y1, Z1) Finally, the D-prediction, W-prediction, and P-coordinate prediction are treated as three vectors and combined into an F(X) = [D-prediction, W-prediction, P-coordinate prediction] to obtain the prediction data corresponding to each point.

[0045] Understandably, to minimize the error between the state vector and the predicted data, an optimization function can be constructed. This function aims to adjust the parameters in the state vector to make the predicted data as close as possible to the actual observed data. The specific expression of the optimization function is:

[0046] in, This represents the actual measured value at the i-th point. For the corresponding predicted data, The weights are set according to the sensor accuracy, where n is the number of sensor types.

[0047] Subsequently, nonlinear optimization algorithms, such as the Levenberg-Marquardt algorithm, gradient descent, or their variants, are used to iteratively calculate the optimization function. In each iteration, the algorithm adjusts the state vector based on the current error. The parameter value is set such that E(X) gradually decreases until it converges to the preset threshold.

[0048] Finally, the target quaternion is extracted from the converged state vector, and the fusion rotation matrix is ​​calculated based on the target quaternion and the rotation matrix transformation formula.

[0049] S104. The three-dimensional point cloud model of the component to be measured in the detection area is obtained by measuring equipment, and the coordinate transformation of the three-dimensional point cloud model is performed by fusion rotation matrix to obtain the target three-dimensional point cloud model in the scene global coordinate system. In some embodiments, acquiring a three-dimensional point cloud model of the component under test within the detection area using a measuring device includes: acquiring the material type of the component under test; acquiring multi-view target data of the component under test using a data acquisition strategy and measuring device that matches the material type; and processing the multi-view target data using an iterative nearest point algorithm to obtain a three-dimensional point cloud model of the component under test.

[0050] Specifically, the material type of the component to be measured (e.g., steel structure or concrete) is obtained. A data acquisition strategy matching the material type (e.g., a point cloud density of 100 points / cm² for steel structure or 50 points / cm² for concrete) is used to uniformly scan around the component to be measured with a measuring device to obtain multi-view point cloud data. Combined with the device pose output by UWB+IMU, the multi-view point clouds are aligned by an iterative nearest point algorithm to eliminate overlapping area errors and generate a complete 3D point cloud model of the component. Furthermore, after generating the target 3D point cloud model, the longest and shortest axes can be extracted from the point cloud boundary of the target 3D point cloud model, and linear dimensions such as length, width, and height can be calculated; the covariance matrix can also be calculated from 50-100 points in the spatial neighborhood of the point cloud, and the eigenvalues ​​can be solved. It can also evaluate surface flatness through curvature formula, extract edges from the point cloud of the component under test, detect circular contours using Hough transform, and output the center (a,b) and radius r; which can be used for subsequent comprehensive evaluation of the dimensional accuracy, shape error and surface quality of the component under test.

[0051] In some embodiments, a coordinate transformation is performed on the 3D point cloud model using a fusion rotation matrix to obtain the target 3D point cloud model in the scene's global coordinate system, including: The translation vector obtained by the measuring device from the UWB tag positioning when scanning the component to be measured is acquired; the coordinate transformation of the 3D point cloud model is performed according to the fused rotation matrix and translation vector to obtain the target 3D point cloud model in the scene global coordinate system.

[0052] Specifically, by fusing the spatiotemporal alignment formula of the rotation matrix, the point cloud data is unified to the scene's global coordinate system, ensuring timestamp synchronization. The spatiotemporal alignment formula is as follows:

[0053] in, Point cloud data in global scene coordinates; Point cloud data in a local coordinate system; Translation vector obtained for UWB positioning.

[0054] S105. Based on the target 3D point cloud model and the original BIM model, obtain the dimensional acceptance results of the component to be tested.

[0055] In some embodiments, the method further includes: The accuracy optimization process for the target 3D point cloud model includes at least one of the following: temperature compensation for the dimensions of the target 3D point cloud model based on the linear expansion coefficient of the material of the component under test, the current temperature of the component under test, and the design reference temperature; and equipment temperature correction for measurement errors based on the temperature error coefficient of the structured light scanner, the current equipment temperature, and the calibration temperature.

[0056] Then, based on the material of the component to be tested (steel or concrete), the measured dimensions are corrected using the coefficient of thermal expansion to eliminate the influence of temperature deviation. The calculation formula is as follows:

[0057] in, These are the actual dimensions after temperature compensation. The original measured dimensions for testing; The design dimension is α; α is the coefficient of linear expansion of the material (for steel, take...). Concrete Aluminum alloy , This is the design reference temperature.

[0058] In addition, measurement errors caused by fluctuations in the equipment's operating temperature can be corrected using the equipment measurement error temperature compensation formula. The calculation formula is as follows:

[0059] The actual dimensions are after correction for errors caused by equipment temperature variations; k is the equipment temperature error coefficient, which is 0.01~0.03 / m for structured light scanners. ℃, The current equipment temperature. The calibration temperature during equipment calibration; Furthermore, in one embodiment of this application, the final error after fusing fixed and mobile data can be calculated based on the fusion accuracy optimization formula. Through comprehensive error evaluation, error interference removal, guidance of raw data acquisition, optimization of calibration, and data preprocessing algorithms, the detection accuracy can be improved to the millimeter level. The fusion accuracy optimization formula is as follows:

[0060] It is the final fusion error. It is the error of fixed data; It's an error in the moving data.

[0061] In some embodiments, obtaining the dimensional acceptance results of the component under test includes: The target 3D point cloud model and the preset original BIM model are converted into the same coordinate system by a fusion rotation matrix, and the deviation value between the target 3D point cloud model and the original BIM model is calculated; based on the deviation value and the preset deviation threshold, the dimensional acceptance result of the component to be tested is generated.

[0062] Specifically, the target 3D point cloud model and the original BIM model can be unified into a coordinate system by quaternion transformation of the fusion rotation matrix, and the deviation of each feature value, linear dimension deviation, and hole size deviation can be calculated. Based on the deviation value and a preset deviation threshold, a heatmap is used to directly display the deviation distribution. For example, the heatmap generation rule is based on deviation. >10mm is red, 10mm and above >5mm is yellow. ≤5mm is green; In addition, when there is a conflict between the installation conditions of the component to be tested and the BIM design model, a comprehensive geometric deviation assessment is performed between the component and the actual 3D model of the site to help determine whether the component meets the acceptance conditions.

[0063] According to the technical solution provided in this application, the global coordinates of the calibration equipment within the detection area in the scene global coordinate system are determined. Measurement data from multiple points in the detection area are acquired using a measuring device, which includes a structured light scanner and an IMU sensor and UWB tag integrated on the structured light scanner. A fusion rotation matrix for coordinate transformation is constructed based on visual image data, posture data, position data, and scene global coordinates. The fusion rotation matrix is ​​used to transform the coordinates of the 3D point cloud model of the component under test, resulting in a target 3D point cloud model in the scene global coordinate system. Based on the target 3D point cloud model and the original BIM model, the dimensional acceptance result of the component under test is obtained. First, by combining structured light scanning and image analysis, the component under test is converted into a computable 3D point cloud model, which meets the requirements for rapid entry inspection of large components while ensuring inspection accuracy. Furthermore, the combination of IMU and UWB replaces the traditional laser tracker, making the inspection scene unrestricted by space and environment, while significantly reducing the cost of the entire inspection system. Finally, by comparing and analyzing with the BIM model, the difference between the actual size of the component under test and the original design size can be accurately identified, thereby quickly generating the dimensional acceptance result. While ensuring testing accuracy, it significantly improves acceptance efficiency.

[0064] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the process of the embodiments of this application.

[0065] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0066] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0067] Figure 2 This is a schematic diagram illustrating the structure of a component size acceptance device according to an exemplary embodiment of the present invention. Figure 2 As shown, the exemplary component size acceptance device includes: The coordinate determination module 201 is configured to determine the scene global coordinates of the calibration device within the detection area in the scene global coordinate system, wherein the scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; The data acquisition module 202 is configured to acquire multiple point measurement data of the component to be measured within the detection area through a measurement device, wherein the measurement device includes a structured light scanner and an IMU sensor and a UWB tag integrated on the structured light scanner, and the measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag. The matrix construction module 203 is configured to construct a fusion rotation matrix for coordinate transformation based on measurement data from multiple points and global scene coordinates. The coordinate transformation module 204 is configured to acquire the three-dimensional point cloud model of the component to be measured within the detection area through the measuring device, and to perform coordinate transformation on the three-dimensional point cloud model using the fusion rotation matrix to obtain the target three-dimensional point cloud model in the scene global coordinate system. The result acceptance module 205 is configured to obtain the dimensional acceptance results of the component to be tested based on the target 3D point cloud model and the original BIM model.

[0068] In some embodiments, the coordinate determination module 201 is further configured to deploy a first preset number of UWB base stations within the detection area; deploy a second preset number of calibration targets within the detection area, wherein each calibration target has at least a third preset number of non-collinear feature points; and obtain the scene global coordinates of the UWB base stations and each feature point in the scene global coordinate system.

[0069] In some embodiments, the matrix construction module 203 is further configured to perform integral processing on the attitude data of each point to obtain the quaternion attitude information of the measuring device at each point; perform filtering processing on the position data of each point to obtain the target position information of the measuring device at each point; extract the local coordinates of feature points in the local coordinate system of the structured light scanner from the visual image data of each point; determine the target coordinates of the structured light scanner in the scene global coordinate system based on the local coordinates of each feature point in the local coordinate system of the structured light scanner and the scene global coordinates in the scene global coordinate system; and construct a fusion rotation matrix for coordinate transformation based on the quaternion attitude information, target position information and target coordinates corresponding to each point.

[0070] In some embodiments, the matrix construction module 203 is further configured to: construct a state vector corresponding to each point based on the quaternion attitude information, target position information, and target coordinates corresponding to each point; determine the predicted data corresponding to each point based on the state vector corresponding to each point through the dynamic model of the IMU sensor, the UWB ranging model, and the local and global coordinate transformation model; construct an optimization function with the goal of minimizing the error between the state vector and the predicted data; iteratively calculate the optimization function through a nonlinear optimization algorithm until the optimization function converges to a preset threshold; extract the target quaternion from the converged state vector, and calculate the fused rotation matrix based on the target quaternion and the rotation matrix transformation formula.

[0071] In some embodiments, the coordinate transformation module 204 is further configured to acquire the material type of the component to be measured, acquire multi-view target data of the component to be measured using an acquisition strategy and measurement device that matches the material type, and process the multi-view target data through an iterative nearest point algorithm to obtain a three-dimensional point cloud model of the component to be measured.

[0072] In some embodiments, the coordinate transformation module 204 is further configured to acquire the translation vector obtained by the measuring device from the UWB tag positioning when scanning the component to be measured; and to perform coordinate transformation on the three-dimensional point cloud model according to the fused rotation matrix and translation vector to obtain the target three-dimensional point cloud model in the scene global coordinate system.

[0073] In some embodiments, the result acceptance module 205 is further configured to perform accuracy optimization processing on the target three-dimensional point cloud model. The accuracy optimization processing includes at least one of the following: performing temperature compensation on the dimensions of the target three-dimensional point cloud model based on the material linear expansion coefficient of the component under test, the current temperature of the component under test, and the design reference temperature; and performing equipment temperature correction on the measurement error based on the temperature error coefficient of the structured light scanner, the current equipment temperature, and the calibration temperature.

[0074] In some embodiments, the result acceptance module 205 is further configured to convert the target 3D point cloud model and the preset original BIM model into the same coordinate system through a fusion rotation matrix, and calculate the deviation value between the target 3D point cloud model and the original BIM model; and generate the size acceptance result of the component to be tested based on the deviation value and the preset deviation threshold.

[0075] According to the apparatus provided in this application embodiment, the global coordinates of the calibration device within the detection area in the scene global coordinate system are determined; measurement data of multiple points in the detection area are acquired using a measuring device, which includes a structured light scanner and an IMU sensor and UWB tag integrated on the structured light scanner; a fusion rotation matrix for coordinate transformation is constructed based on visual image data, posture data, position data, and scene global coordinates; the coordinates of the three-dimensional point cloud model of the component under test are transformed using the fusion rotation matrix to obtain the target three-dimensional point cloud model in the scene global coordinate system; and the dimensional acceptance result of the component under test is obtained based on the target three-dimensional point cloud model and the original BIM model. First, by combining structured light scanning and image analysis, the component under test is converted into a computable three-dimensional point cloud model, which can meet the requirements of rapid entry inspection of large components while ensuring inspection accuracy; furthermore, the combination of IMU and UWB replaces the traditional laser tracker, making the inspection scene unrestricted by space and environment, while significantly reducing the cost of the entire inspection system; finally, by comparing and analyzing with the BIM model, the difference between the actual size and the original design size of the component under test can be accurately identified, thereby quickly generating the dimensional acceptance result. While ensuring testing accuracy, it significantly improves acceptance efficiency.

[0076] Embodiments of the present invention also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the methods provided in the above embodiments.

[0077] Figure 3 A schematic diagram of a computer system suitable for implementing embodiments of the present invention is shown. It should be noted that... Figure 3 The computer system 300 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0078] like Figure 3As shown, the computer system 300 includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 302 or programs loaded from storage portion 308 into Random Access Memory (RAM) 303. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 305.

[0079] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 304 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0080] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs various functions defined in the system of the present invention.

[0081] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0083] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0084] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer's processor, causes the computer to perform the method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0085] Another aspect of the present invention provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods described in the various embodiments above.

[0086] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the steps of the present invention.

Claims

1. A method for accepting the dimensions of a component, characterized in that, The Determine the scene global coordinates of the calibration device within the detection area in the scene global coordinate system, wherein the scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; The measurement device acquires multiple point measurement data of the component under test within the detection area. The measurement device includes a structured light scanner and an IMU sensor and a UWB tag integrated on the structured light scanner. The measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag. Based on the visual image data, the pose data, the position data, and the scene global coordinates, a fusion rotation matrix for coordinate transformation is constructed; The measuring device acquires a three-dimensional point cloud model of the component to be measured within the detection area, and the fusion rotation matrix is ​​used to perform coordinate transformation on the three-dimensional point cloud model to obtain a target three-dimensional point cloud model in the scene global coordinate system. Based on the target 3D point cloud model and the original BIM model, the dimensional acceptance results of the component to be tested are obtained.

2. The method according to claim 1, characterized in that, The determination of the scene global coordinates of the calibration device within the detection area in the scene global coordinate system includes: A first predetermined number of UWB base stations are deployed within the detection area; A second preset number of calibration targets are deployed within the detection area, wherein each of the calibration targets has at least a third preset number of non-collinear feature points; Obtain the scene global coordinates of the UWB base station and each feature point in the scene global coordinate system.

3. The method according to claim 2, characterized in that, The step of constructing a fusion rotation matrix for coordinate transformation based on the visual image data, the pose data, the position data, and the scene global coordinates includes: The attitude data at each point is integrated to obtain the quaternion attitude information of the measuring device at each point. The position data at each point is filtered to obtain the target position information of the measuring device at each point. Extract the local coordinates of the feature points in the local coordinate system of the structured light scanner from the visual image data of each point; Based on the local coordinates of each feature point in the local coordinate system of the structured light scanner and the scene global coordinates in the scene global coordinate system, the target coordinates of the structured light scanner in the scene global coordinate system are determined. Based on the quaternion attitude information, target position information, and target coordinates corresponding to each point, a fusion rotation matrix for coordinate transformation is constructed.

4. The method according to claim 3, characterized in that, The step of constructing a fusion rotation matrix for coordinate transformation based on the quaternion pose information, the target position information, and the target coordinates corresponding to each point includes: Based on the quaternion attitude information, the target position information, and the target coordinates corresponding to each point, a state vector corresponding to each point is constructed. Based on the state vector corresponding to each point, the predicted data corresponding to each point is determined through the dynamic model of the IMU sensor, the UWB ranging model, and the local and global coordinate transformation model. Construct an optimization function with the objective of minimizing the error between the state vector and the predicted data; The optimization function is iteratively calculated using a nonlinear optimization algorithm until the optimization function converges to a preset threshold. The target quaternion is extracted from the converged state vector, and the fused rotation matrix is ​​calculated based on the target quaternion and the rotation matrix transformation formula.

5. The method according to claim 1, characterized in that, The step of acquiring a three-dimensional point cloud model of the component to be measured within the detection area using the measuring device includes: The material type of the component under test is obtained, and multi-view target data of the component under test is collected using a data acquisition strategy and the measuring device that matches the material type. The multi-view target data is processed by the iterative nearest point algorithm to obtain a three-dimensional point cloud model of the component under test.

6. The method according to claim 1, characterized in that, The step of using the fusion rotation matrix to perform coordinate transformation on the 3D point cloud model to obtain the target 3D point cloud model in the scene's global coordinate system includes: The translation vector obtained by the measuring device from the UWB tag positioning when scanning the component under test is acquired; Based on the fused rotation matrix and the translation vector, the coordinate transformation of the 3D point cloud model is performed to obtain the target 3D point cloud model in the scene global coordinate system.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: The target 3D point cloud model is subjected to accuracy optimization processing, which includes at least one of the following: Based on the material linear expansion coefficient of the component under test, the current temperature of the component under test, and the design reference temperature, temperature compensation is performed on the dimensions of the target three-dimensional point cloud model. Based on the temperature error coefficient of the structured light scanner, the current device temperature, and the calibration temperature, the measurement error is corrected by device temperature.

8. The method according to claim 7, characterized in that, The process of obtaining the dimensional acceptance results of the component under test includes: The target 3D point cloud model and the preset original BIM model are converted into the same coordinate system by a fusion rotation matrix, and the deviation value between the target 3D point cloud model and the original BIM model is calculated. Based on the deviation value and the preset deviation threshold, the dimensional acceptance result of the component to be tested is generated.

9. A component dimension acceptance device, characterized in that, The The coordinate determination module is configured to determine the scene global coordinates of the calibration device within the detection area in the scene global coordinate system, wherein the scene global coordinate system is a reference coordinate system determined based on the actual engineering scene; The data acquisition module is configured to acquire multiple point measurement data of the component to be measured within the detection area through a measurement device, wherein the measurement device includes a structured light scanner and an IMU sensor and a UWB tag integrated on the structured light scanner, and the measurement data includes visual image data acquired by the structured light scanner, attitude data of the structured light scanner determined by the IMU sensor, and position data of the structured light scanner determined by the UWB tag. The matrix construction module is configured to construct a fusion rotation matrix for coordinate transformation based on measurement data from multiple points and the global coordinates of the scene. The coordinate transformation module is configured to acquire a three-dimensional point cloud model of the component to be measured within the detection area through the measuring device, and to perform coordinate transformation on the three-dimensional point cloud model using the fusion rotation matrix to obtain a target three-dimensional point cloud model in the scene global coordinate system. The result acceptance module is configured to obtain the dimensional acceptance result of the component to be tested based on the target 3D point cloud model and the original BIM model.

10. An electronic device, characterized in that, include: One or more processors and a memory, the memory storing a computer program that, when executed by the one or more processors, causes the device to perform the steps of the method as described in any one of claims 1 to 8.

Images