Steel truss girder quality detection method and device, electronic equipment and storage medium

Abstract

The invention provides a steel truss girder quality detection method and device, electronic equipment and a storage medium, and relates to the technical field of engineering detection. The method comprises the steps that the position of each scanning site is determined according to size information of a steel truss girder and scanning parameters of a three-dimensional scanning device; determining the position of each target according to the position of each scanning site and a preset target setting strategy; obtaining point cloud data sets scanned by the three-dimensional scanning device at the scanning sites, and registering the point cloud data sets according to the point cloud data corresponding to the target to obtain a point cloud model of the steel truss girder; and constructing a three-dimensional model of the steel truss girder based on the point cloud model, performing feature extraction on the three-dimensional model to obtain target features, and obtaining a quality detection result based on the target features. According to the method, efficient reverse modeling and three-dimensional reconstruction are carried out on the steel truss girder, the automation level of quality detection is effectively improved, errors and time cost of manual measurement are reduced, and the efficiency and accuracy of quality detection of the steel truss girder are improved.

Description

Technical Field

[0001] The present invention relates to the field of engineering detection technology, and in particular to a steel truss quality detection method, device, electronic equipment and storage medium. Background Art

[0002] Large steel trusses are now widely used in major engineering projects such as highway and railway bridges. The safety and stability of their structures are directly related to the overall quality and service life of the project. Quality inspection of steel trusses can promptly identify deviations during manufacturing and installation, preventing structural safety hazards caused by deformation or accumulated errors. This improves the overall reliability and durability of the project, ensuring construction quality and safe operation.

[0003] Currently, after steel trusses are manufactured, quality inspections are typically performed manually. However, this method is not only time-consuming and labor-intensive, but also highly susceptible to the operator's experience and technical level, resulting in large errors and low inspection efficiency. Summary of the Invention

[0004] The problem solved by the present invention is how to improve the efficiency and accuracy of steel truss girder quality inspection.

[0005] In order to solve the above problems, the present invention provides a steel truss quality detection method, comprising:

[0006] Determine the position of each scanning station based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device;

[0007] Determining the position of each target according to the position of each scanning station and a preset target setting strategy; wherein the preset target setting strategy includes that adjacent scanning stations share at least one target;

[0008] Acquire each point cloud data set scanned by a three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss;

[0009] A three-dimensional model of the steel truss is constructed based on the point cloud model, feature extraction is performed on the three-dimensional model to obtain target features, and quality inspection results of the steel truss are obtained based on the target features.

[0010] Optionally, the dimension information includes a first dimension in a span direction, a second dimension in a length direction, and a third dimension in a height direction of the steel truss; the scanning parameters include a field of view angle; the scanning sites include a transverse scanning site and a longitudinal scanning site; and determining the position of each scanning site based on the acquired dimension information of the steel truss and the scanning parameters of the three-dimensional scanning device includes:

[0011] Determine the linear distances between the transverse scanning station and the longitudinal scanning station and the steel truss according to the scanning parameters and the preset station setting strategy;

[0012] determining height positions of the transverse scanning station and the longitudinal scanning station along the height direction according to the third size;

[0013] Determining a lateral position of the lateral scanning station along the span direction according to a first target interval and the first size; wherein the first target interval is determined based on the third size and is less than twice a theoretical scanning radius; and the theoretical scanning radius is determined based on the straight-line distance and the field of view angle;

[0014] The longitudinal position of the longitudinal scanning station along the length direction is determined according to a second target interval; wherein the second target interval is determined based on the second size and is less than twice the theoretical scanning radius.

[0015] Optionally, the scanning parameters further include an effective measurement distance; and the preset station setting strategy includes:

[0016] The theoretical scanning radius of the three-dimensional scanning device at each scanning site is smaller than the effective measurement distance.

[0017] Optionally, the steel truss includes a chord and a web; and the preset targeting strategy includes:

[0018] At least one target is set in the overlapping area, and multiple targets are set around the preset node; wherein the overlapping area includes the overlapping part corresponding to the theoretical scanning area of ​​the three-dimensional scanning device at the adjacent scanning station, and the theoretical scanning area is determined based on the theoretical scanning radius; the preset node includes the intersection of the chord and the web.

[0019] Optionally, registering each of the point cloud data sets according to the point cloud data corresponding to the target in each of the point cloud data sets to obtain the point cloud model of the steel truss includes:

[0020] Extracting point cloud data corresponding to the target from the point cloud data set, and determining the geometric center coordinates of the target based on the point cloud data corresponding to the target;

[0021] The spatial coordinate systems of the point cloud data sets are aligned using the geometric center coordinates corresponding to the same target, and the point cloud data sets corresponding to the adjacent scanning stations are iteratively registered to obtain the point cloud model.

[0022] Optionally, the target feature includes a planar structural feature; and obtaining the quality inspection result of the steel truss based on the target feature includes:

[0023] Sampling each of the point cloud data corresponding to the plane structure feature to obtain a point cloud data group, and fitting an ideal plane corresponding to the plane structure feature based on the point cloud data group;

[0024] The target distance between each point cloud data in the point cloud data group and the ideal plane is determined respectively. When the difference between the maximum value of the target distance and the minimum value of the target distance exceeds a preset difference threshold, the quality inspection result is that the flatness of the planar structural feature is insufficient.

[0025] Optionally, the target feature further includes a vertical structural feature; and obtaining the quality inspection result of the steel truss based on the target feature further includes:

[0026] When a vertical structural feature intersecting with the planar structural feature is identified from the three-dimensional model, determining a plane normal vector corresponding to the planar structural feature;

[0027] When the angle between the plane normal vector and the preset gravity direction is greater than a preset angle threshold, the quality detection result is that the perpendicularity between the planar structural feature and the vertical structural feature is insufficient.

[0028] In the present invention, the location of each scanning station is determined based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device. This helps improve the rationality of the scanning station setup and lays the foundation for subsequent high-quality 3D modeling. Furthermore, the present invention determines the location of each target based on the location of each scanning station and a preset targeting strategy. The preset targeting strategy includes adjacent scanning stations sharing at least one target, providing a reliable reference for the spatial correspondence between point cloud datasets corresponding to different scanning stations and improving the accuracy and reliability of subsequent point cloud registration. Because adjacent scanning stations share at least one target, the point cloud datasets acquired by the 3D scanning device at adjacent scanning stations can include point cloud data corresponding to at least one identical target. Based on this, after acquiring each point cloud dataset scanned by the 3D scanning device at each scanning station, the present invention can register each point cloud dataset based on the point cloud data corresponding to the targets in each point cloud dataset, thereby ensuring that the resulting point cloud model of the steel truss accurately reflects the outer contour information of the steel truss. By constructing a three-dimensional model of the steel truss based on the obtained point cloud model, it is possible to achieve reverse modeling and three-dimensional reconstruction of the steel truss, and then quickly, accurately and comprehensively grasp the actual situation of the steel truss. On this basis, the present invention performs feature extraction on the three-dimensional model, and can obtain accurate and reliable quality inspection results of the steel truss based on the extracted target features. Compared with the method of relying on manual measurement and experience for quality assessment, the present invention effectively improves the automation level of quality inspection through reasonable scanning site planning, target setting strategy, efficient point cloud alignment, three-dimensional modeling and feature extraction, reduces the error and time cost of manual measurement, and comprehensively improves the efficiency and accuracy of steel truss quality inspection.

[0029] The present invention also provides a steel truss girder quality detection device, comprising:

[0030] A site determination module, which is used to determine the position of each scanning site based on the acquired dimensional information of the steel truss and the scanning parameters of the three-dimensional scanning device;

[0031] a target determination module, configured to determine the position of each target based on the position of each scanning station and a preset targeting strategy; wherein the preset targeting strategy includes that adjacent scanning stations share at least one target;

[0032] a point cloud registration module, configured to obtain each point cloud data set scanned by the three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss;

[0033] A quality inspection module is used to construct a three-dimensional model of the steel truss based on the point cloud model, extract features from the three-dimensional model to obtain target features, and obtain quality inspection results of the steel truss based on the target features.

[0034] The advantages of the steel truss quality inspection device provided by the present invention and the steel truss quality inspection method compared with the prior art are basically the same, and will not be repeated here.

[0035] The present invention also provides an electronic device, comprising a memory and a processor;

[0036] The memory is used to store computer programs;

[0037] The processor is configured to implement the steel truss quality inspection method as described above when executing the computer program.

[0038] The advantages of the electronic device provided by the present invention and the steel truss quality detection method compared with the prior art are basically the same, and will not be repeated here.

[0039] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steel truss quality detection method as described above is implemented.

[0040] The advantages of the computer-readable storage medium provided by the present invention and the steel truss quality inspection method compared with the prior art are basically the same, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the process of the steel truss quality inspection method according to an embodiment of the present invention;

[0042] Figure 2 Schematic diagram of the structure of a steel truss quality inspection device according to an embodiment of the present invention;

[0043] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0045] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0046] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0047] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0048] like Figure 1 As shown, an embodiment of the present invention provides a steel truss girder quality inspection method, comprising the following steps:

[0049] S1: Determine the position of each scanning station based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device.

[0050] Specifically, in this embodiment, the dimensional information of the steel truss can be determined based on the design information of the steel truss (such as drawing information, etc.), and may include information such as the total length (such as longitudinal length), span (such as lateral width), and height (such as total height) of the steel truss. In this embodiment, by evaluating light interference factors such as lighting conditions and weather conditions at the location of the steel truss, a suitable three-dimensional scanning device (such as a three-dimensional laser scanner) can be selected and scanning parameters of the three-dimensional scanning device can be obtained. The scanning parameters may include parameters such as the effective measurement distance and field of view of the scanning device.

[0051] In one embodiment, after obtaining the size information of the steel truss and the scanning parameters of the three-dimensional scanning device, the position of each scanning station can be determined based on this. For example, the number of layers of the scanning station can be determined first according to the total height of the steel truss. When the total height is greater than the preset height (such as 8 meters), the number of layers of the scanning station can be multiple layers, otherwise one layer of scanning station can be set. The straight-line distance between the scanning station and the steel truss can be determined based on the effective measurement distance (such as the straight-line distance can be 0.8 times the effective measurement distance). On this basis, the theoretical scanning diameter of the three-dimensional scanning device (i.e., twice the theoretical scanning radius) can be determined based on the straight-line distance and the scanning parameters, and the target spacing between the scanning stations can be determined based on the theoretical scanning diameter. For example, 0.8 times the theoretical scanning diameter can be selected as the target spacing between adjacent scanning stations, thereby ensuring that the point cloud data of the steel truss can be fully acquired.

[0052] S2: Determine the position of each target according to the position of each scanning station and a preset target setting strategy; wherein the preset target setting strategy includes that adjacent scanning stations share at least one target.

[0053] Specifically, the target indicated in this embodiment can be set in the area where the steel truss is located to provide a reference for the subsequent registration of the point cloud data set. In this embodiment, the preset targeting strategy includes adjacent scanning stations sharing at least one target (that is, the three-dimensional scanning device can respectively collect point cloud data corresponding to at least one identical target at two adjacent scanning stations). The position of each target can be determined according to the position of each scanning station and the preset targeting strategy. For example, the difference between the theoretical scanning radius of the three-dimensional scanning device and the target spacing between adjacent scanning devices can be determined to obtain the target difference. A circular area with the center point of the two adjacent scanning stations as the center and half the target difference as the radius is used as the target area. At least one target is arranged in the target area to ensure that adjacent scanning stations share at least one target.

[0054] S3: Acquire each point cloud data set scanned by the three-dimensional scanning device at each scanning station, and align each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss.

[0055] Specifically, after determining the location of the scanning station and the location of the target, a three-dimensional scanning device can be used to scan the outer contour of the steel truss, thereby obtaining all the point cloud data obtained by the three-dimensional scanning device at each scanning station, obtaining each point cloud data set, and extracting the point cloud data corresponding to the target from the point cloud data set. For example, the target can be a planar target with a specific pattern (such as a checkerboard), and existing pattern recognition algorithms (such as template matching or edge detection) can be used to identify the point cloud data corresponding to the target. On this basis, the point cloud data of the target center point can be marked (such as uniquely numbering it) to locate the target.

[0056] In one embodiment, after obtaining the point cloud data corresponding to the target in each point cloud dataset, since adjacent scanning stations share at least one target, the point cloud datasets corresponding to the adjacent scanning stations can include point cloud data corresponding to at least one identical target, and the point cloud datasets can be aligned based on this. For example, each target can be numbered, and the target three-dimensional coordinates of the geometric center point of the target can be determined. Based on the target three-dimensional coordinates, the point cloud datasets corresponding to the targets with the same number are aligned in the spatial coordinate system, thereby achieving preliminary alignment of the point cloud datasets. On this basis, the adjacent point cloud datasets can be iteratively aligned using the ICP (Iterative Closest Point) algorithm based on the three-dimensional coordinates of the point cloud data corresponding to the determined targets, and then a point cloud model in the same spatial coordinate system can be obtained.

[0057] Optionally, before registering each point cloud dataset, outliers such as isolated points, overlapping points, and error points can be removed to achieve noise reduction. Based on this, filtering parameters can be set according to the steel truss's dimensional information and accuracy requirements to filter the point cloud dataset. This not only preserves the true structural information of the steel truss, but also helps streamline the outline point cloud data and improve modeling efficiency.

[0058] S4: Construct a three-dimensional model of the steel truss based on the point cloud model, extract features from the three-dimensional model to obtain target features, and obtain quality inspection results of the steel truss based on the target features.

[0059] Specifically, after obtaining a point cloud model of the steel truss, a 3D model of the steel truss can be constructed based on the point cloud model. For example, the existing MLS (Moving Least Squares) algorithm can be used to eliminate irregularities in the point cloud on the steel truss surface, improving the surface quality of the 3D model. Furthermore, existing smooth surface reconstruction algorithms can be used to transform the point cloud datasets corresponding to the steel truss's outer contour into a 3D model of the steel truss.

[0060] In one embodiment, the target features can be set in advance according to the quality inspection requirements. For example, if the overall dimensional deviation of the steel truss needs to be detected, the target features can be the overall dimensions of the steel truss (such as longitudinal length, total span, and total height, etc.). After obtaining the three-dimensional model of the steel truss, the three-dimensional model can be feature extracted to obtain the target features, and the quality inspection results of the steel truss can be obtained based on the target features. For example, assuming that the target features include the overall dimensions of the steel truss, the measurement tools configured in the three-dimensional software can be called to obtain the overall dimensional information of the three-dimensional model and compare it with the dimensional information of the steel truss. When the dimensional deviation exceeds the preset deviation, the quality inspection result of the steel truss can be the overall dimensional deviation.

[0061] In this embodiment, the positions of each scanning station are determined based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device. This helps improve the rationality of the scanning station configuration and lays the foundation for subsequent high-quality 3D modeling. Furthermore, this embodiment determines the positions of each target based on the location of each scanning station and a preset targeting strategy. The preset targeting strategy includes adjacent scanning stations sharing at least one target. This provides a reliable reference for the spatial correspondence between point cloud datasets corresponding to different scanning stations, thereby improving the accuracy and reliability of subsequent point cloud registration. Because adjacent scanning stations share at least one target, the point cloud datasets acquired by the 3D scanning device at adjacent scanning stations will include point cloud data corresponding to at least one common target. Based on this, after acquiring the point cloud datasets scanned by the 3D scanning device at each scanning station, the point cloud datasets can be registered based on the point cloud data corresponding to the targets in each point cloud dataset, thereby ensuring that the resulting point cloud model of the steel truss accurately reflects the outer contour information of the steel truss. By constructing a three-dimensional model of the steel truss based on the obtained point cloud model, reverse modeling and three-dimensional reconstruction of the steel truss can be achieved, thereby quickly, accurately and comprehensively understanding the actual situation of the steel truss. On this basis, feature extraction is performed on the three-dimensional model, and accurate and reliable quality inspection results of the steel truss can be obtained based on the extracted target features. Compared with the method of relying on manual measurement and experience for quality assessment, this embodiment effectively improves the automation level of quality inspection through reasonable scanning site planning, target setting strategy, efficient point cloud alignment, three-dimensional modeling and feature extraction, reduces the error and time cost of manual measurement, and comprehensively improves the efficiency and accuracy of steel truss quality inspection.

[0062] Optionally, the dimension information includes a first dimension in a span direction, a second dimension in a length direction, and a third dimension in a height direction of the steel truss; the scanning sites include a transverse scanning site and a longitudinal scanning site; and determining a position of each scanning site based on the acquired dimension information of the steel truss and scanning parameters of the three-dimensional scanning device includes:

[0063] Determine the linear distances between the transverse scanning station, the longitudinal scanning station and the steel truss according to the scanning parameters and the preset station setting strategy;

[0064] determining height positions of the transverse scanning station and the longitudinal scanning station along the height direction according to the third dimension;

[0065] Determining a lateral position of a lateral scanning station along a span direction based on a first target interval and a first dimension; wherein the first target interval is determined based on a third dimension and is less than twice a theoretical scanning radius; and the theoretical scanning radius is determined based on a straight-line distance and scanning parameters;

[0066] The longitudinal position of the longitudinal scanning station along the length direction is determined according to the second target interval; wherein the second target interval is determined based on the second size and is less than twice the theoretical scanning radius.

[0067] Specifically, in this embodiment, the first dimension of the steel truss in the span direction, the second dimension in the length direction, and the third dimension in the height direction can be obtained based on the design information of the steel truss (e.g., design drawings). In this embodiment, the scanning stations include transverse scanning stations and longitudinal scanning stations. The transverse scanning stations represent scanning stations along the span direction of the steel truss, and the longitudinal scanning stations represent scanning stations along the length direction of the steel truss.

[0068] In one embodiment, the straight-line distances between the horizontal scanning station and the longitudinal scanning station and the steel truss can be determined based on the scanning parameters and the preset station setting strategy. For example, in this embodiment, the scanning parameters may include the effective measurement distance of the three-dimensional scanning device, and the effective measurement distance can be directly used as the straight-line distance between the scanning station and the steel truss. On this basis, the theoretical scanning radius can be determined based on the straight-line distance between the scanning station and the steel truss and the field of view angle. For example, assuming that the effective measurement distance is 10 meters and the field of view angle is 90°. Then the product of the tangent value corresponding to half of the field of view angle (i.e., 45°) and the straight-line distance is the radius of the theoretical scanning area (i.e., 10 meters).

[0069] In one embodiment, the third dimension of the steel truss girder's height may include the bottom elevation (i.e., the height between the bottom surface of the steel truss girder and the ground). The height positions of the transverse and longitudinal scanning stations along the height direction can be determined based on the third dimension. For example, the height of the scanning station can be a preset multiple (e.g., 1.3 times) of the bottom elevation, and the height positions of the scanning stations can be determined based on this.

[0070] In one embodiment, the first dimension in the span direction of the steel truss may include the total span of the steel truss, and the first target interval may be determined based on the third dimension and be less than twice the theoretical scanning radius. The lateral position of the lateral scanning station along the span direction can be determined based on the first target interval and the first dimension. For example, assuming that the third dimension is the bottom elevation (such as 6m) and the theoretical scanning radius is 5m. Then the first target interval may be greater than the bottom elevation and less than twice the theoretical scanning radius (such as the first target interval is 1.5 times the bottom elevation, i.e. 9m). On this basis, starting from one end of the steel truss, a lateral scanning station is set at every 1.5 times the bottom elevation along the span direction of the steel truss. Thus, the lateral position of each lateral scanning station along the span direction can be determined based on the first target interval and the first dimension.

[0071] In one embodiment, the second dimension along the length of the steel truss beam can include the total length of the steel truss beam. The second target interval can be determined based on the second dimension and be less than twice the theoretical scanning radius. For example, the total length can be divided into multiple sub-lengths, and the sub-length closest to, but less than, twice the theoretical scanning radius is selected as the second target interval. Based on this, starting from one end of the steel truss beam, a longitudinal scanning station is set at every second target interval along the length of the steel truss beam. Thus, the longitudinal position of each longitudinal scanning station along the length can be determined based on the second target interval.

[0072] In this embodiment, the position of each transverse scanning station is determined based on three factors: the transverse position of the transverse scanning station along the span direction, the linear distance between the transverse scanning station and the steel truss, and the height position of the transverse scanning station along the height direction. Furthermore, the position of each longitudinal scanning station is determined based on three factors: the longitudinal position of the longitudinal scanning station along the length direction, the linear distance between the longitudinal scanning station and the steel truss, and the height position of the longitudinal scanning station along the height direction, ensuring the accuracy of each scanning station's position. Specifically, this embodiment first determines the linear distances between the transverse and longitudinal scanning stations and the steel truss based on scanning parameters and a preset station setup strategy. This helps ensure that the steel truss to be scanned is within the accuracy range of the 3D scanning equipment, thereby improving the reliability and accuracy of point cloud data acquisition. Furthermore, the height positions of the transverse and longitudinal scanning stations along the height direction are determined based on the third dimension in the height direction. This helps ensure that the scanning stations cover the height range of the steel truss and avoid missing information at critical height levels. After determining the linear distance and height position, this embodiment determines the lateral position of the transverse scanning stations along the span direction based on the first target interval (determined based on the third dimension and less than twice the theoretical scanning radius) and the first dimension. This improves the rationality of the distribution of the scanning stations in the span direction while ensuring full coverage of the span area within the effective operating range of the 3D scanning device. Simultaneously, this embodiment determines the longitudinal position of the longitudinal scanning stations along the length direction based on the second target interval (determined based on the second dimension and less than twice the theoretical scanning radius). This not only improves the rationality of the distribution of the scanning stations in the length direction, but also ensures effective coverage of the effective operating range of the 3D scanning device in the length direction, thereby comprehensively improving the rationality of the scanning station configuration.

[0073] Optionally, the scanning parameters also include an effective measurement distance; the preset station setting strategies include:

[0074] The theoretical scanning radius of the three-dimensional scanning device at each scanning station is smaller than the effective measurement distance.

[0075] Specifically, the scanning parameters referred to in this embodiment also include an effective measurement distance, which indicates the maximum distance that the three-dimensional scanning device can theoretically reliably and accurately measure to the object being measured (such as a steel truss). The preset station setting strategy in this embodiment includes that the theoretical scanning radius of the three-dimensional scanning device at each scanning station is less than the effective measurement distance, and the straight-line distance can be determined based on the effective measurement distance and the field of view angle. For example, assuming that the effective measurement distance is 12 meters and the field of view angle is 90°, the theoretical scanning radius needs to be less than 12 meters. Since the theoretical scanning radius is equal to the product of the tangent value corresponding to half the field of view angle (i.e., 45°) and the straight-line distance, it can be determined that the straight-line distance needs to be less than 12 meters.

[0076] In this embodiment, when the theoretical scanning radius is less than the effective measurement distance, the energy loss from laser emission to reflection from the target object (i.e., the steel truss) back to the 3D scanning device is within a controllable range, effectively capturing a reflected light signal of sufficient intensity. This helps avoid signal loss or misjudgment due to laser energy attenuation, maintains high measurement accuracy, and reduces measurement errors caused by excessive distance. This ensures the accuracy and reliability of the point cloud datasets acquired by each scanning station, providing a precise and effective data foundation for subsequent 3D modeling, quality inspection, and other tasks, and improving the reliability of quality inspection results.

[0077] Optionally, the steel truss includes a chord and a web; the preset targeting strategy includes:

[0078] At least one target is set in the overlapping area, and multiple targets are set around the preset nodes; wherein the overlapping area includes the overlapping portion corresponding to the theoretical scanning area of ​​the three-dimensional scanning device at adjacent scanning stations, and the theoretical scanning area is determined based on the theoretical scanning radius; the preset nodes include the intersection of the chord and the web.

[0079] Specifically, in this embodiment, the steel truss may include components such as a chord and a web. In this embodiment, the preset node includes the intersection of the chord and the web, which can be obtained in advance based on the design drawings of the steel truss. The intersection position can be mapped to the coordinate system where the scanning station is located based on the size information of the steel truss, thereby obtaining the position of the preset node. After determining the position of each scanning station, the theoretical scanning area of ​​each three-dimensional scanning device (such as the circular area corresponding to the theoretical scanning radius) can be determined based on the theoretical scanning radius of the three-dimensional scanning device, and the overlapping part corresponding to the theoretical scanning area at two adjacent scanning stations can be determined to obtain the overlapping area. Since at least one target is set in each overlapping area, the position of the target can be determined based on the position of the overlapping area. In addition, multiple targets can also be set around the preset node. For example, four targets are set symmetrically with the position of the preset node as the center.

[0080] In this embodiment, placing at least one target in the overlapping area ensures that point cloud data corresponding to at least one target appears in the point cloud datasets acquired by adjacent scanning stations. This provides an accurate common reference point for stitching point cloud data from adjacent theoretical scanning areas, ensuring precise alignment of point cloud datasets acquired by each scanning station. Furthermore, since pre-set nodes, such as the intersection of the chord and web, are critical connection points in steel trusses, placing multiple targets around these pre-set nodes helps improve the accuracy and reliability of the point cloud data at these nodes, thereby enhancing the accuracy and reliability of the point cloud model.

[0081] Optionally, each point cloud data set is registered according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss, including:

[0082] Extracting point cloud data corresponding to the target from the point cloud data set, and determining the geometric center coordinates of the target based on the point cloud data of the target;

[0083] The spatial coordinate system of each point cloud dataset is aligned using the geometric center coordinates corresponding to the same target, and the point cloud datasets corresponding to adjacent scanning stations are iteratively registered to obtain a point cloud model.

[0084] Specifically, the target referred to in this embodiment can be a spherical target or a checkerboard target. The target usually has characteristics that are easy to identify (such as high reflectivity). The point cloud data corresponding to the target can be extracted from the point cloud data set. For example, a target with high reflectivity can be used in this embodiment. Since the reflection intensity between the background (such as a steel truss) and the target is relatively large, a reflection intensity threshold can be set. When the reflection intensity corresponding to the point cloud data is greater than this threshold, the point cloud data can be associated with the target to obtain the point cloud data corresponding to the target. After determining the point cloud data corresponding to the area where the target is located, an optimization algorithm such as the least squares method can be used to determine the geometric center coordinates.

[0085] In one embodiment, after determining the geometric center coordinates corresponding to each target, the point cloud data corresponding to the target can be extracted from the point cloud dataset, and the spatial coordinate system of each point cloud dataset can be aligned using the geometric center coordinates corresponding to the same target. For example, the spatial coordinate system in which any point cloud dataset is located can be selected as the reference coordinate system, and other point cloud datasets containing the same geometric center coordinates as the point cloud dataset can be obtained as the point cloud dataset to be aligned. The geometric center coordinates corresponding to the same target can be used to transform the coordinates of the point cloud dataset to be aligned, and the position and direction of each point cloud data to be aligned in the point cloud dataset to be aligned can be adjusted to align it to the reference coordinate system. This cycle is repeated, and the remaining point cloud datasets are respectively aligned to the reference coordinate system to achieve spatial coordinate system alignment. On this basis, the existing point cloud processing platform (such as Cyclone 3DR, etc.) can be used to iteratively align adjacent point cloud datasets containing the same target based on the point cloud data corresponding to the target area using the ICP algorithm, and finally generate a complete point cloud model in the reference coordinate system.

[0086] In this embodiment, the geometric center coordinates of the target are determined based on its point cloud data, which helps provide a precise feature reference point for the subsequent registration of the point cloud dataset. These coordinates can effectively represent the target's exact position in space. On this basis, the spatial coordinate systems of each point cloud dataset are aligned using the geometric center coordinates corresponding to the same target. Using these precise coordinates as a reference, the point cloud datasets acquired by different scanning stations are converted to a unified spatial coordinate system, eliminating the coordinate system differences between the point cloud datasets caused by the different scanning station locations, laying the foundation for the fusion of the various point cloud datasets. Based on this, the point cloud datasets corresponding to adjacent scanning stations are iteratively aligned. Based on the aligned coordinate system, the matching degree between adjacent datasets is further optimized through an iterative algorithm, so that the point cloud data can be more accurately connected in terms of details and overall form, thereby ensuring that the point cloud model can accurately reflect the overall outline of the steel truss.

[0087] Optionally, the target feature includes a planar structural feature; and the quality inspection result of the steel truss is obtained based on the target feature, including:

[0088] Sampling each point cloud data corresponding to the plane structure feature to obtain a point cloud data group, and fitting an ideal plane corresponding to the plane structure feature based on the point cloud data group;

[0089] The target distance between each point cloud data in the point cloud data group and the ideal plane is determined respectively. When the difference between the maximum value of the target distance and the minimum value of the target distance exceeds a preset difference threshold, the quality inspection result is that the flatness of the plane structure feature is insufficient.

[0090] Specifically, the planar structural features referred to in this embodiment represent regions or portions with two-dimensional flatness in a three-dimensional model. Planar structural features can be directly identified and extracted using built-in analysis tools in three-dimensional processing platforms (such as AutoCAD and SolidWorks). In this embodiment, the planar structural features referred to in this embodiment represent characteristic regions within a point cloud dataset consisting of points that are approximately located on the same plane, rather than being completely flat in the absolute physical sense. After extracting the planar structural features from the three-dimensional model, the corresponding point cloud data in the point cloud model can be determined based on the position of the planar structural features in the spatial coordinate system. Thus, the point cloud data corresponding to the planar structural features can be sampled from the point cloud model to obtain a point cloud dataset. For example, the existing PCA (Principal Component Analysis) algorithm can be used to estimate the normal vectors of each point cloud data point. The point cloud data can then be clustered based on the normal vectors to obtain the point cloud data corresponding to the planar structural features, which can then be used as a clustered point cloud dataset. Based on this, the clustered point cloud dataset can be sampled to obtain a point cloud dataset. After obtaining the point cloud data set, an ideal plane corresponding to the planar structural features can be fitted based on the point cloud data set (eg, fitting the ideal plane using the existing least squares method).

[0091] In one embodiment, a target distance between each point cloud data point in the point cloud data set and the ideal plane can be determined based on its spatial coordinates in the reference coordinate system. The maximum and minimum values ​​of the target distances are selected, and the difference between the two is determined. When the difference between the two exceeds a preset difference threshold, the quality inspection result is that the flatness of the planar structural feature is insufficient.

[0092] In this embodiment, point cloud data corresponding to planar structural features are sampled from a point cloud model to obtain a point cloud data set. An ideal plane is then fitted based on this data set, providing an accurate reference for flatness testing of planar structural features of steel trusses. The ideal plane fitting, based on the actual sampled point cloud data set, can reflect the theoretical shape of the planar structure. On this basis, the target distance between each point in the point cloud data set and the ideal plane is determined. By quantifying the distance of each point to the ideal plane, the flatness of the planar structural feature is converted into a measurable numerical indicator. When the difference between the maximum and minimum target distances exceeds a preset difference threshold, it indicates a large fluctuation range in the target distances between each point in the point cloud data set and the ideal plane, indicating insufficient flatness of the planar structural feature. Thus, the quality inspection method employed in this embodiment can objectively and accurately reflect the degree of deviation between the actual and ideal shapes of the planar structure in steel trusses, thereby improving the accuracy of quality inspection results.

[0093] Optionally, the target feature further includes a vertical structural feature; and obtaining a quality inspection result of the steel truss based on the target feature further includes:

[0094] When a vertical structural feature intersecting with a planar structural feature is identified from the three-dimensional model, a plane normal vector corresponding to the planar structural feature is determined;

[0095] When the angle between the plane normal vector and the preset gravity direction is greater than a preset angle threshold, the quality inspection result is that the perpendicularity between the plane structural feature and the vertical structural feature is insufficient.

[0096] Specifically, in this embodiment, the vertical structural features are represented in the three-dimensional model as extending in the vertical direction, and presenting a certain boundary or contour geometry in the horizontal direction, rather than being completely vertical in the absolute physical sense. The extraction method of the vertical structural features is basically the same as the extraction method of the planar structural features, and will not be discussed here. After identifying the planar structural features and the vertical structural features, the minimum distance between the geometric boundary of the vertical structural features (such as endpoints, edge lines or end faces) and the planar structural features can be obtained. When the minimum distance is 0, it can be said that the planar structural features intersect with the vertical structural features.

[0097] In one embodiment, when a vertical structural feature intersecting with a planar structural feature is identified from a three-dimensional model, the plane normal vector corresponding to the planar structural feature can be determined. For example, the coordinates of at least three vertices corresponding to the planar structural feature can be obtained in the three-dimensional model, and two vectors can be constructed using the coordinates corresponding to any two vertices. The plane normal vector corresponding to the plane defined by the three points can be obtained based on the cross-multiplication of the two vectors. The angle between the plane normal vector and the preset gravity direction is determined, and it is determined whether the angle is greater than a preset angle threshold. If so, the quality inspection result is that the verticality between the planar structural feature and the vertical structural feature is insufficient. If not, the quality inspection result is that the verticality between the planar structural feature and the vertical structural feature meets the quality requirements.

[0098] In this embodiment, steel trusses are widely used as load-bearing components in large-scale projects such as bridges due to their excellent load-bearing capacity, light weight, good stability, and bending resistance. However, during the manufacturing process, steel trusses may experience shape and position deviations due to factors such as welding deformation and splicing errors. This often leads to problems such as inaccurate joint connection when splicing with other steel trusses, which in turn affects the stability, load-bearing capacity, and seismic performance of the overall structure, and may even cause catastrophic failure.

[0099] When the present embodiment identifies a vertical structural feature that intersects with a planar structural feature from a three-dimensional model, it provides a key directional parameter for the verticality detection between the two by determining the plane normal vector corresponding to the planar structural feature, and intuitively reflects the directional characteristics of the planar structural feature. On this basis, the present embodiment quantifies the degree of deviation of the planar structural feature from the vertical direction by obtaining the angle between the plane normal vector and the preset gravity direction, thereby indirectly judging the verticality between the planar structural feature and the vertical structural feature. When the angle is greater than the preset angle threshold, the quality inspection result is determined to be insufficient verticality between the planar structural feature and the vertical structural feature. The quality inspection method based on precise angle comparison provided by the present embodiment converts the verticality problem between the planar structural feature and the vertical structural feature into a clear numerical judgment standard, which is conducive to avoiding errors caused by subjective evaluation. It helps to timely discover its potential manufacturing errors and assembly risks, and thus helps to ensure the stability and safety of the steel truss.

[0100] like Figure 2 As shown, an embodiment of the present invention provides a steel truss girder quality inspection device 200, comprising:

[0101] A site determination module 210 is used to determine the position of each scanning site based on the acquired dimensional information of the steel truss and the scanning parameters of the three-dimensional scanning device;

[0102] A target determination module 220 is configured to determine the position of each target based on the position of each scanning station and a preset targeting strategy; wherein the preset targeting strategy includes adjacent scanning stations sharing at least one target;

[0103] a point cloud registration module 230 for acquiring each point cloud data set scanned by the three-dimensional scanning device at each scanning station, and registering each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss;

[0104] The quality inspection module 240 is configured to construct a three-dimensional model of the steel truss based on the point cloud model, extract features from the three-dimensional model to obtain target features, and obtain quality inspection results of the steel truss based on the target features.

[0105] The steel truss quality inspection device and the steel truss quality inspection method provided in this embodiment can produce substantially the same technical effects, which will not be described in detail here.

[0106] like Figure 3 As shown, an electronic device 300 provided by an embodiment of the present invention includes a memory 310 and a processor 320; the memory 310 is used to store computer programs; the processor 320 is used to implement the steel truss quality detection method as described above when executing the computer program.

[0107] In other words, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when executing the computer program:

[0108] Determine the position of each scanning station based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device;

[0109] Determining the position of each target according to the position of each scanning station and a preset target setting strategy; wherein the preset target setting strategy includes that adjacent scanning stations share at least one target;

[0110] Acquire each point cloud data set scanned by a three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss;

[0111] A three-dimensional model of the steel truss is constructed based on the point cloud model, feature extraction is performed on the three-dimensional model to obtain target features, and quality inspection results of the steel truss are obtained based on the target features.

[0112] The electronic equipment provided in this embodiment and the steel truss quality detection method can produce basically the same technical effects, which will not be described in detail here.

[0113] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned steel truss quality detection method is implemented.

[0114] In other words, a non-volatile computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following operations:

[0115] Determine the position of each scanning station based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device;

[0116] Determining the position of each target according to the position of each scanning station and a preset target setting strategy; wherein the preset target setting strategy includes that adjacent scanning stations share at least one target;

[0117] Acquire each point cloud data set scanned by a three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss;

[0118] A three-dimensional model of the steel truss is constructed based on the point cloud model, feature extraction is performed on the three-dimensional model to obtain target features, and quality inspection results of the steel truss are obtained based on the target features.

[0119] The computer-readable storage medium provided in this embodiment and the steel truss quality inspection method can produce substantially the same technical effects, which will not be described in detail here.

[0120] An electronic device 300 that can serve as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 300 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0121] The electronic device 300 includes a computing unit that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0122] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM). In this application, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present invention. In addition, the functional units in the various embodiments of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit. The above-mentioned integrated units can be implemented in the form of hardware or software functional units.

[0123] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A steel truss quality inspection method, characterized in that: include: Determine the position of each scanning station based on the acquired dimensional information of the steel truss and the scanning parameters of the 3D scanning device; Determining the position of each target according to the position of each scanning station and a preset target setting strategy; wherein the preset target setting strategy includes that adjacent scanning stations share at least one target; Acquire each point cloud data set scanned by a three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss; A three-dimensional model of the steel truss is constructed based on the point cloud model, feature extraction is performed on the three-dimensional model to obtain target features, and quality inspection results of the steel truss are obtained based on the target features.

2. The steel truss girder quality inspection method according to claim 1, characterized in that: The dimension information includes a first dimension in a span direction, a second dimension in a length direction, and a third dimension in a height direction of the steel truss; the scanning parameters include a field of view angle; the scanning sites include a transverse scanning site and a longitudinal scanning site; and determining the position of each scanning site based on the acquired dimension information of the steel truss and the scanning parameters of the three-dimensional scanning device includes: Determine the linear distances between the transverse scanning station and the longitudinal scanning station and the steel truss according to the scanning parameters and the preset station setting strategy; determining height positions of the transverse scanning station and the longitudinal scanning station along the height direction according to the third size; Determining a lateral position of the lateral scanning station along the span direction according to a first target interval and the first size; wherein the first target interval is determined based on the third size and is less than twice a theoretical scanning radius; and the theoretical scanning radius is determined based on the straight-line distance and the field of view angle; The longitudinal position of the longitudinal scanning station along the length direction is determined according to a second target interval; wherein the second target interval is determined based on the second size and is less than twice the theoretical scanning radius.

3. The steel truss girder quality inspection method according to claim 2, characterized in that: The scanning parameters also include an effective measurement distance; the preset station setting strategy includes: The theoretical scanning radius of the three-dimensional scanning device at each scanning site is smaller than the effective measurement distance.

4. The steel truss girder quality inspection method according to claim 2, characterized in that: The steel truss includes a chord and a web; the preset targeting strategy includes: At least one target is set in the overlapping area, and multiple targets are set around the preset node; wherein the overlapping area includes the overlapping part corresponding to the theoretical scanning area of ​​the three-dimensional scanning device at the adjacent scanning station, and the theoretical scanning area is determined based on the theoretical scanning radius; the preset node includes the intersection of the chord and the web.

5. The steel truss quality inspection method according to claim 1, characterized in that: The registering each of the point cloud data sets according to the point cloud data corresponding to the target in each of the point cloud data sets to obtain the point cloud model of the steel truss comprises: Extracting point cloud data corresponding to the target from the point cloud data set, and determining the geometric center coordinates of the target based on the point cloud data corresponding to the target; The spatial coordinate systems of the point cloud data sets are aligned using the geometric center coordinates corresponding to the same target, and the point cloud data sets corresponding to the adjacent scanning stations are iteratively registered to obtain the point cloud model.

6. The steel truss girder quality inspection method according to claim 1, characterized in that: The target feature includes a planar structural feature; and obtaining the quality inspection result of the steel truss based on the target feature includes: Sampling each of the point cloud data corresponding to the plane structure feature to obtain a point cloud data group, and fitting an ideal plane corresponding to the plane structure feature based on the point cloud data group; The target distance between each point cloud data in the point cloud data group and the ideal plane is determined respectively. When the difference between the maximum value of the target distance and the minimum value of the target distance exceeds a preset difference threshold, the quality inspection result is that the flatness of the planar structural feature is insufficient.

7. The steel truss quality inspection method according to claim 6, characterized in that: The target feature further includes a vertical structural feature; and obtaining the quality inspection result of the steel truss based on the target feature further includes: When a vertical structural feature intersecting with the planar structural feature is identified from the three-dimensional model, determining a plane normal vector corresponding to the planar structural feature; When the angle between the plane normal vector and the preset gravity direction is greater than a preset angle threshold, the quality detection result is that the perpendicularity between the planar structural feature and the vertical structural feature is insufficient.

8. A steel truss quality inspection device, characterized in that: include: A site determination module, which is used to determine the position of each scanning site based on the acquired dimensional information of the steel truss and the scanning parameters of the three-dimensional scanning device; a target determination module, configured to determine the position of each target based on the position of each scanning station and a preset targeting strategy; wherein the preset targeting strategy includes that adjacent scanning stations share at least one target; a point cloud registration module, configured to obtain each point cloud data set scanned by the three-dimensional scanning device at each scanning station, and register each point cloud data set according to the point cloud data corresponding to the target in each point cloud data set to obtain a point cloud model of the steel truss; A quality inspection module is used to construct a three-dimensional model of the steel truss based on the point cloud model, extract features from the three-dimensional model to obtain target features, and obtain quality inspection results of the steel truss based on the target features.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the steel truss quality detection method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the steel truss quality detection method according to any one of claims 1 to 7 is implemented.

Images