Splice plate bolt hole positioning method and device, electronic equipment and storage medium

Abstract

The invention provides a splice plate bolt hole positioning method and device, electronic equipment and a storage medium, and relates to the technical field of steel structure splicing, and the splice plate bolt hole positioning method comprises the steps: carrying out the feature extraction of obtained bolt hole point cloud data of a steel structure splicing part, and obtaining a bolt hole feature region; and on the basis of a preset bolt hole size threshold value, fitting is performed according to the bolt hole feature region to determine the bolt hole position in the splice plate. The accurate position information of the bolt hole in the splice plate is obtained by fitting the extracted bolt hole feature region, and the positioning efficiency of the bolt hole in the splice plate can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of steel structure splicing, and in particular to a method, a device, an electronic device and a storage medium for locating bolt holes of a splicing plate. Background Art

[0002] In the field of modern construction and engineering, steel structures are widely used due to their superior mechanical properties and ease of construction. Among them, bolted splicing plates, as one of the main connection methods of steel structures, play a vital role. The advantages of bolted splicing are high connection strength, simple assembly process and detachableness, which are suitable for the construction of various complex structures.

[0003] However, with the continuous expansion and complexity of engineering projects, the positioning requirements for large-area bolt-group spliced ​​plates are becoming increasingly higher. Traditional positioning methods mainly rely on manual measurement and marking, which is not only time-consuming and labor-intensive, but also prone to positioning errors, affecting the positioning efficiency of the spliced ​​plates. Summary of the invention

[0004] The problem solved by the invention is how to improve the positioning efficiency of bolt holes in a spliced ​​plate.

[0005] In order to solve the above problems, the present invention provides a method, device, electronic device and storage medium for locating bolt holes in a spliced ​​plate.

[0006] In a first aspect, the present invention provides a method for locating bolt holes in a spliced ​​plate, comprising:

[0007] Perform feature extraction on the obtained bolt hole point cloud data of the steel structure splicing part to obtain the bolt hole feature area;

[0008] Based on a preset bolt hole size threshold, the bolt hole feature area is fitted to determine the bolt hole position in the spliced ​​plate.

[0009] Optionally, before extracting features from the acquired bolt hole point cloud data of the steel structure splicing part, the method further includes:

[0010] Performing laser scanning on the splicing parts of the steel structure to obtain initial point cloud data of the splicing parts of the steel structure;

[0011] The initial point cloud data is denoised to obtain the bolt hole point cloud data.

[0012] Optionally, the performing denoising processing on the initial point cloud data to obtain the bolt hole point cloud data includes:

[0013] Taking any point in the initial point cloud data as the center point and a preset radius threshold as the radius, determining the neighborhood range of the center point;

[0014] Determine whether the central point is a noise point according to the distribution of the distance from the central point to each point in the corresponding neighborhood;

[0015] The initial point cloud data from which all the noise points are removed is determined as the bolt hole point cloud data.

[0016] Optionally, judging whether the central point is a noise point according to the distribution of the distance from the central point to each point in the corresponding neighborhood range includes:

[0017] Determine the distance from each point in the neighborhood to the center point as the adjacent point distance;

[0018] Determine the adjacent point distance threshold according to all the adjacent point distances;

[0019] When all the adjacent point distances are less than or equal to the adjacent point distance threshold, it is determined that the central point is not the noise point; otherwise, it is determined that the central point is the noise point.

[0020] Optionally, the adjacent point distance threshold satisfies:

[0021]

[0022] Wherein, T is the adjacent point distance threshold, N is the number of adjacent point distances, d i is the distance between the i-th adjacent points, and k is a preset constant.

[0023] Optionally, the step of extracting features from the acquired bolt hole point cloud data of the steel structure joint to obtain a bolt hole feature area includes:

[0024] The bolt hole point cloud data is divided into regions based on a clustering algorithm to obtain the bolt hole feature region corresponding to each bolt hole.

[0025] Optionally, the fitting of the bolt hole feature area to determine the bolt hole position in the spliced ​​plate based on a preset bolt hole size threshold comprises:

[0026] Determine the radius of the fitting circle according to the bolt size threshold;

[0027] Fitting the characteristic area according to the fitting circle radius to obtain a bolt hole fitting circle;

[0028] The position corresponding to the bolt hole fitting circle is determined as the bolt hole position in the splicing plate.

[0029] In a second aspect, the present invention provides a bolt hole positioning device for a spliced ​​plate, comprising:

[0030] An extraction module performs feature extraction on the acquired point cloud data of the bolt holes at the joints of the steel structure to obtain a feature area of ​​the bolt holes;

[0031] The fitting module fits the bolt hole feature area based on a preset bolt hole size threshold to determine the bolt hole position in the spliced ​​plate.

[0032] In a third aspect, the present invention provides an electronic device, including a memory and a processor;

[0033] The memory is used to store computer programs;

[0034] The processor is used to implement the method for locating bolt holes in the splicing plate as described in the first aspect when executing the computer program.

[0035] In a fourth aspect, 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 method for locating bolt holes in a spliced ​​plate as described in the first aspect is implemented.

[0036] The beneficial effects of the splicing plate bolt hole positioning method, device, electronic device and storage medium of the present invention are as follows: by performing feature extraction on the bolt hole point cloud data of the steel structure splicing part, the bolt hole feature area can be accurately identified. Compared with the traditional detection method, the point cloud data can provide richer three-dimensional information, avoiding misjudgment caused by the limitations of two-dimensional images, and fitting the bolt hole feature area based on the preset bolt hole size threshold can further quickly obtain a more accurate and reliable bolt hole position, thereby improving the bolt hole positioning efficiency, helping to ensure that the bolts are accurately installed in the correct hole position during the steel structure splicing process, and improving the connection accuracy and stability of the steel structure splicing. In addition, the use of point cloud data to determine the position of bolt holes can greatly improve the speed of locating bolt holes. Compared with traditional manual detection methods, which often require a lot of time and manpower and are easily affected by subjective factors of detection personnel, the present invention can quickly process point cloud data of a large number of bolt holes through feature extraction and fitting algorithms of point cloud data of splicing parts of steel structures, and determine the accurate positions of all bolt holes in a short time, thereby effectively improving the positioning efficiency of bolt holes of splicing plates. By splicing steel structures with splicing plates, construction efficiency can be significantly improved and construction period can be shortened. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a process of locating bolt holes in a spliced ​​plate according to an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of the fitting effect of bolt hole point cloud data according to an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the structure of a splicing plate according to an embodiment of the present invention;

[0040] Figure 4 It is a structural schematic diagram of a bolt hole positioning device for a spliced ​​plate according to an embodiment of the present invention;

[0041] Figure 5 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with 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 interpreted as being limited to the embodiments described herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0043] 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.

[0044] 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 "based at least in part 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.

[0045] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0046] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0047] In view of the problems existing in the above-mentioned related technologies, the present embodiment provides a method, device, electronic device and storage medium for locating bolt holes in a spliced ​​plate.

[0048] In the related technology, in the construction of steel structures, splicing plates (also called connecting plates or joint plates) play a vital role. They are mainly used to connect and fix different steel components to ensure the stability and safety of the structure. Connection function: splicing plates are used to connect two or more steel beams, columns or other components together to form an integral structure. Through the splicing plate, the load can be effectively transferred from one component to another to ensure the bearing capacity of the structure. It can also increase the stiffness and stability of the connection to prevent the structure from deformation or instability during use. For example, beam-column connection: in the steel structure frame, columns and beams are the main load-bearing components. The splicing plate can connect the ends of the beams to the columns to form a stable frame structure. In high-rise steel structure buildings, H-beams are connected to box columns through splicing plates. The bolts on the splicing plates can transmit the bending moment, shear force and axial force of the beam ends, so that the beams and columns work together to jointly bear the gravity, wind load and earthquake effects of the building structure.

[0049] like Figure 1 As shown, an embodiment of the present invention provides a method for locating bolt holes in a spliced ​​plate, comprising:

[0050] S100, extracting features from the acquired point cloud data of bolt holes at the joints of the steel structure to obtain bolt hole feature areas.

[0051] Specifically, the point cloud data is composed of many discrete three-dimensional coordinate points, which reflect the surface morphology of the steel structure joints. The bolt holes show specific geometric features in them. In the feature extraction process, the local geometric properties of the point cloud are comprehensively analyzed to calculate the curvature of each point. Due to its concave structural characteristics, the points in the characteristic area of ​​the bolt hole usually show curvature characteristics different from the surrounding areas. By setting a suitable curvature threshold, the point set of suspected bolt holes can be preliminarily screened out. At the same time, the normal vector of the point is also an important consideration. The normal vector at the edge of the bolt hole will change significantly, which can further narrow the possible bolt hole feature area range. The bolt hole feature area can also be determined by statistical methods, model matching methods, and training convolutional neural networks. Among them, the statistical methods include point cloud density analysis: by calculating the point cloud density of the local area, the bolt hole feature area usually has a higher point cloud density, and the density threshold can be set accordingly to screen out possible areas; principal component analysis: principal component analysis is performed on the point cloud near the bolt hole to determine the main change direction and characteristics of the point cloud. If it meets the bolt hole characteristics, it may be a feature area. The model matching-based method includes constructing a bolt hole model: constructing an ideal bolt hole three-dimensional model, matching it with the point cloud data, adjusting the position and posture to make the model close to the point cloud, and determining the feature area; template matching: preparing a bolt hole point cloud template, comparing the similarity with the acquired point cloud data, and determining it as a feature area if it exceeds the threshold. The method based on deep learning: training a convolutional neural network includes training the network with a large number of labeled bolt hole point cloud data samples so that it can automatically identify the bolt hole feature area in the new point cloud data; Generative Adversarial Network (GAN): through adversarial training, using a discriminator to determine whether the point cloud data to be analyzed is a bolt hole feature area. By determining the bolt hole feature area, more accurate data information of the bolt hole can be obtained, thereby providing accurate data support for the bolt hole position in the splicing plate. In addition, by comparing multiple bolt hole feature areas, the consistency and symmetry of the steel structure splicing parts can be detected, and potential installation problems or structural defects can be discovered in time.

[0052] S200: Based on a preset bolt hole size threshold, the bolt hole feature area is fitted to determine the bolt hole position in the spliced ​​plate.

[0053] Specifically, the preset bolt hole size threshold is determined according to the bolt specifications and design requirements used in the steel structure splicing parts, and these thresholds generally include the diameter range, depth range, etc. of the bolt hole. The obtained bolt hole feature area is fitted according to the bolt hole size threshold. The fitting process mainly uses mathematical models and algorithms to approximate the actual shape and position of the bolt hole, even if the final fitting result matches the bolt hole size threshold and the actual position of the bolt hole, thereby determining the position of the corresponding bolt hole in the splicing plate according to the bolt hole position.

[0054] Furthermore, for the diameter fitting of the bolt hole, a circular fitting algorithm can be used. In the bolt hole feature area, a certain number of points or all points are selected. These points can be points determined as suspected bolt hole edges through the previous feature extraction process. These points are fitted into a circle using the least squares method and other methods. The position and size of the bolt hole on the plane of the splicing plate are determined by the circular parameters obtained by fitting, such as the coordinates of the center of the circle and the radius. If the radius obtained by fitting meets the bolt hole size threshold, that is, the fitted circle obtained by fitting matches the actual bolt size, then it can be determined that the fitted circle represents a bolt hole. Furthermore, the depth fitting of the bolt hole can be performed. The point cloud distribution in the vertical direction in the feature area can be analyzed. By calculating the number and distribution of points at different height levels, the depth range of the bolt hole can be determined. If the depth also meets the preset threshold requirements, it can be further confirmed that this position is indeed a bolt hole. In the entire fitting process, it may be necessary to process multiple bolt hole feature areas one by one. For a large area bolt group splicing plate, there may be multiple bolt holes, and it is necessary to ensure that each bolt hole can be accurately fitted and determined. In order to improve the accuracy of fitting, multiple fitting and optimization methods can be used. For example, you can perform multiple circular fittings on different feature areas, and then take the average or use other statistical methods to determine the final bolt hole position. At the same time, you can also combine other geometric features and constraints, such as the relative position relationship between bolt holes, the overall shape of the splicing plate, etc., to further verify and optimize the fitting results. By presetting the bolt hole size threshold and fitting in combination with the bolt hole feature area, the position of the bolt hole in the splicing plate can be determined more accurately, providing an important basis for the installation and quality inspection of steel structures.

[0055] In this embodiment, by extracting the features of the bolt hole point cloud data at the splicing part of the steel structure, the bolt hole feature area can be accurately identified. Compared with the traditional detection method, the point cloud data can provide richer three-dimensional information, avoiding the misjudgment caused by the limitations of the two-dimensional image, and fitting the bolt hole feature area based on the preset bolt hole size threshold can further quickly obtain a more accurate and reliable bolt hole position, improve the positioning efficiency of the bolt hole, and help to ensure that the bolt is accurately installed at the correct hole position during the steel structure splicing process, and improve the connection accuracy and stability of the steel structure splicing. In addition, using point cloud data to determine the bolt hole position can greatly improve the positioning speed of the bolt hole. Compared with the traditional manual detection method, it often takes a lot of time and manpower, and is easily affected by the subjective factors of the detection personnel. By extracting the features of the point cloud data at the splicing part of the steel structure and the fitting algorithm, the point cloud data of a large number of bolt holes can be quickly processed, and the accurate position of all bolt holes can be determined in a short time, which effectively improves the positioning efficiency of the bolt holes of the splicing plate. The splicing of the steel structure by the splicing plate can significantly improve the construction efficiency and shorten the construction period.

[0056] Optionally, before extracting features from the acquired bolt hole point cloud data of the steel structure splicing part, the method further includes:

[0057] Performing laser scanning on the splicing parts of the steel structure to obtain initial point cloud data of the splicing parts of the steel structure;

[0058] The initial point cloud data is denoised to obtain the bolt hole point cloud data.

[0059] Specifically, a high-precision and high-resolution 3D laser scanner is used to emit a laser beam to the joint of the steel structure, measure the time or phase of the laser beam from emission to reflection, and determine the spatial position of the surface point of the steel structure, thereby obtaining a large amount of point cloud data. These data contain the 3D shape information of the joint of the steel structure, including the contour information of the bolt hole group. During the scanning process, it is necessary to ensure that the distance and angle between the laser scanner and the bolt hole group remain stable to obtain accurate contour point cloud data. Scanning can be performed from multiple angles to obtain complete information on the joint of the steel structure. For complex joints of the steel structure, multiple scans are performed, and the scan data is spliced ​​and fused to obtain more complete point cloud data. Before scanning, it is necessary to ensure that the scanning parameters suitable for different surface characteristics are selected, and the position and angle of the scanner are reasonably set to ensure the integrity and accuracy of the scanning coverage. The non-contact measurement advantages of laser scanning technology can avoid damage to fragile or sensitive parts and ensure the high quality and reliability of data.

[0060] Furthermore, use professional point cloud data processing software, such as visual laser radar data analysis software (cyclone 3DR) or topology transfer tool software (Wrap). Import the initial point cloud data into the software, use the denoising function in the software, select the appropriate denoising algorithm and parameters, and process the initial point cloud data. Specific denoising algorithms may include filtering algorithms (such as Gaussian filtering and median filtering, etc.), statistical analysis, regional segmentation and other algorithms, which can be used to remove obvious noise points, identify and remove abnormal points, and process noise points in the area. After removing the noise points, the point cloud data obtained is the bolt hole point cloud data, which more accurately reflects the shape and position characteristics of the bolt hole group at the splicing part of the steel structure.

[0061] In this optional embodiment, initial point cloud data is obtained from laser scanning of the splicing parts of the steel structure, and more accurate bolt hole point cloud data is obtained through denoising processing, providing a reliable foundation for subsequent feature extraction, bolt hole positioning, and the production and installation of splicing plates.

[0062] Optionally, the performing denoising processing on the initial point cloud data to obtain the bolt hole point cloud data includes:

[0063] Taking any point in the initial point cloud data as the center point and a preset radius threshold as the radius, determining the neighborhood range of the center point;

[0064] Determine whether the central point is a noise point according to the distribution of the distance from the central point to each point within the neighborhood;

[0065] The initial point cloud data from which all the noise points are removed is determined as the bolt hole point cloud data.

[0066] Specifically, a point is randomly selected from the initial point cloud data as the center point, and the neighborhood range of the center point is determined with a preset radius threshold as the radius. The setting of this radius threshold can be determined according to the characteristics of the steel structure splicing part, the scanning accuracy, and the needs of subsequent processing. For example, when the size of the bolt hole group is relatively small and the characteristics of the bolt hole need to be accurately identified, the radius threshold may be set relatively small to ensure that the neighborhood range can accurately reflect the point cloud distribution around the bolt hole. On the contrary, when the size of the bolt hole group is relatively large, the radius threshold can be set relatively large.

[0067] Furthermore, the distance from the center point to each point in the neighborhood is calculated, and the distribution of these distances is analyzed. Whether the center point is a noise point is determined based on the distribution of the distances. If the distance from the center point to most points in the neighborhood is significantly different from the expected distribution, for example, if the number of points with too large or too small distances is large and exceeds the normal range, then the center point can be considered to be a noise point, and the center point determined to be a noise point is removed from the initial point cloud data. After judging all center points and removing noise points, the remaining initial point cloud data is used as bolt hole point cloud data.

[0068] In this optional embodiment, by screening and removing noise points, bolt hole point cloud data that can more accurately reflect the characteristics of the bolt hole groups in the splicing parts of the steel structure is obtained, thereby improving the precision and accuracy of subsequent bolt hole positioning, and providing a more reliable foundation for subsequent feature extraction, bolt hole positioning, and the production and installation of splicing plates.

[0069] It should be noted that the characteristics of the steel structure surface and environmental factors during the scanning process may cause noise points to be generated. For example, dust in the environment, light interference, or the roughness of the steel structure surface may cause the scanned point cloud data to contain some points that do not match the actual structure. By using this method to determine whether the center point is a noise point, the influence of these noise points can be effectively removed, so that the bolt hole point cloud data obtained by subsequent processing can more accurately reflect the true shape and position characteristics of the bolt hole group at the splicing part of the steel structure.

[0070] Optionally, judging whether the central point is a noise point according to the distribution of the distance from the central point to each point in the corresponding neighborhood range includes:

[0071] Determine the distance from each point in the neighborhood to the center point as the adjacent point distance;

[0072] Determine the adjacent point distance threshold according to all the adjacent point distances;

[0073] When all the adjacent point distances are less than or equal to the adjacent point distance threshold, it is determined that the central point is not the noise point; otherwise, it is determined that the central point is the noise point.

[0074] Optionally, the adjacent point distance threshold satisfies:

[0075]

[0076] Wherein, T is the adjacent point distance threshold, N is the number of adjacent point distances, d i is the distance between the i-th adjacent points, and k is a preset constant.

[0077] Specifically, for the selected center point, the distance from each point in its neighborhood to the center point is determined as the adjacent point distance, so that the spatial relationship between the center point and each point in the neighborhood is reflected by the distance of all adjacent points, that is, the calculated distance is used to measure the degree of proximity between them, and the adjacent point distance threshold corresponding to the center point is calculated according to the distance of all adjacent points. Compare each adjacent point distance with the adjacent point distance threshold. When all adjacent point distances are less than or equal to the adjacent point distance threshold, that is, the distance from the point in the domain to the center point is within a certain reasonable range, indicating that the relationship between the center point and the surrounding points is relatively normal and conforms to the overall distribution law of the data, so the center point is judged not to be a noise point. Otherwise, when there is an adjacent point distance greater than the distance threshold, this means that there are some points around the center point whose distance to it exceeds the normal range. This center point may be isolated or its relationship with the surrounding points does not conform to the overall data distribution, so the center point is judged to be a noise point.

[0078] In this optional embodiment, noise points are determined by the distribution of distances from the center point to points in the neighborhood, so that noise points in the bolt hole point cloud data can be identified more accurately. Points in the initial point cloud data that have abnormal distances from surrounding points can be quickly and accurately determined as noise points, avoiding the impact of these abnormal points on subsequent point cloud data analysis and processing, thereby effectively improving the efficiency of obtaining the bolt hole positions of the spliced ​​plate through point cloud data.

[0079] Optionally, the step of extracting features from the acquired bolt hole point cloud data of the steel structure joint to obtain a bolt hole feature area includes:

[0080] The bolt hole point cloud data is divided into regions based on a clustering algorithm to obtain the bolt hole feature region corresponding to each bolt hole.

[0081] Specifically, for the bolt hole point cloud data, the spatial coordinate information of each point is extracted as the input feature of the clustering algorithm. The coordinate information reflects the position of the point in three-dimensional space. The bolt hole point cloud data is calculated using the selected clustering algorithm, such as the partitioning clustering algorithm (K-Means) or the density-based clustering algorithm (Density-Based Spatial Clustering ofApplications with Noise, DBSCAN). Taking K-Means as an example, after multiple iterations, the data points are divided into different clusters, and each cluster represents a potential bolt hole feature area. In the DBSCAN algorithm, different clusters formed according to density connectivity also correspond to different bolt hole feature areas. Since the bolt holes are relatively independent point cloud sets with a certain density in space, density clustering can effectively distinguish them, thereby obtaining the bolt hole feature area corresponding to each bolt hole. After clustering is completed, these feature areas are sorted. For example, the point cloud data in the area can be reorganized according to the identification, which is convenient for the subsequent extraction of feature information such as the shape and size of each bolt hole feature area.

[0082] In this optional embodiment, after dividing the bolt hole point cloud data into characteristic areas corresponding to each bolt hole, each area can be analyzed and processed independently, avoiding the complex calculations and large amounts of data redundancy that may occur when the entire point cloud data is processed globally, effectively reducing the amount of calculation and improving the overall efficiency of data processing.

[0083] Optionally, the fitting of the bolt hole feature area to determine the bolt hole position in the spliced ​​plate based on a preset bolt hole size threshold comprises:

[0084] Determine the radius of the fitting circle according to the bolt size threshold;

[0085] Fitting the characteristic area according to the fitting circle radius to obtain a bolt hole fitting circle;

[0086] The position corresponding to the bolt hole fitting circle is determined as the bolt hole position in the splicing plate.

[0087] Specifically, the bolt size threshold is predetermined based on known bolt specifications or design requirements, and includes the radius of the bolt hole, so that the radius of the bolt hole is used as the fitting circle radius. For example, if the bolt size threshold is given in the form of a diameter, the fitting circle radius can be simply obtained by dividing the diameter value by 2. The determined fitting circle radius ensures that the size of the fitting circle matches the size of the actual bolt hole to a certain extent, so that the subsequent fitting operation is more in line with the actual situation of the bolt hole.

[0088] Furthermore, if Figure 2 As shown in the figure, the bolt hole fitting circle is obtained by fitting the points in the bolt hole feature area. First, the bolt hole feature area divided according to the determined fitting circle radius is fitted. For each point cloud data point in the bolt hole feature area, the radius of the fitting circle is used as a constraint condition, and a circle that best represents the distribution of these point clouds is found by the least squares method. The goal of the least squares method is to minimize the sum of the squares of the distances from each point in the feature area to the fitting circle, and the center position of the fitting circle and the points on the circle are continuously adjusted to minimize the sum of the squares of the distances, thereby obtaining a circle that is closest to the point cloud distribution in the bolt hole feature area, namely, the bolt hole fitting circle. Since the fitting circle is a mathematical approximation of the bolt hole feature area, it represents the approximate position and shape of the bolt hole in the splicing plate. The position of each bolt hole in the splicing plate can be directly determined according to the center position of all bolt hole fitting circles, and the position of the fitting circle itself also represents the position of the bolt hole on the splicing platform. The mathematical model (fitting circle) abstracted from the point cloud data is linked to the actual splicing plate structure, that is, the position of the bolt hole in the splicing plate is determined by the position of each bolt hole fitting circle.

[0089] In this optional embodiment, the bolt hole is fitted by determining the radius of the fitting circle according to the bolt size threshold, which can make full use of the size information of the bolt. Since this radius is determined based on the actual bolt size, the fitted bolt hole fitting circle can more accurately reflect the actual position and shape of the bolt hole.

[0090] Optionally, the method further comprises:

[0091] Generate a splicing plate drawing according to all the bolt hole positions;

[0092] The splicing plates at the splicing parts of the steel structure are manufactured according to the splicing plate drawings.

[0093] Specifically, the software integrates the bolt hole position data, plans the layout according to the shape of the splicing plate, draws the splicing plate outline, marks the bolt holes at the corresponding coordinate positions (circular symbols can be used, etc.), and marks the diameter and other specifications, overall and hole spacing dimensions, tolerances, so as to obtain the splicing plate drawing with bolt hole positions, such as Figure 3 The figure shows the splicing plate drawing generated according to the bolt hole position. According to the splicing plate drawing, the selected splicing plate material (usually steel) is cut into appropriate sizes. The bolt holes are processed according to the markings in the splicing plate drawing using appropriate equipment to ensure tolerance. Galvanize or paint according to surface treatment requirements, and finally conduct a comprehensive quality inspection. Qualified ones are used for steel structure splicing.

[0094] In this optional embodiment, a splicing plate of corresponding size and shape is accurately manufactured using a splicing plate drawing with bolt hole position information to ensure that it fits the bolt hole group at the splicing part of the steel structure. The precisely matched splicing plates can effectively improve the accuracy and stability of the bolt group splicing plates, thereby ensuring the safety and reliability of the overall structure.

[0095] like Figure 4 As shown, a bolt hole positioning device 400 for a spliced ​​plate provided in an embodiment of the present invention includes:

[0096] The acquisition module 410 is used to extract features from the acquired point cloud data of the bolt holes at the joints of the steel structure to obtain feature areas of the bolt holes;

[0097] The adjustment module 420 is used to fit the bolt hole feature area based on a preset bolt hole size threshold to determine the bolt hole position in the splicing plate.

[0098] The bolt hole locating device of the splicing plate of this embodiment is used to implement the splicing plate bolt hole locating method described above, and its advantages over the prior art are the same as the advantages of the splicing plate bolt hole locating method described above over the prior art, which will not be repeated here.

[0099] like Figure 5 As shown, an electronic device 500 provided by an embodiment of the present invention includes a memory 510 and a processor 520; the memory 510 is used to store a computer program; the processor 520 is used to implement the above-mentioned method for locating bolt holes in a splicing plate when executing the computer program.

[0100] In other words, an electronic device 500 includes a memory 510 and a processor 520 coupled to the memory 510; the memory 510 is configured to store a computer program; and the processor 520 is configured to perform the following operations when executing the computer program:

[0101] Perform feature extraction on the obtained bolt hole point cloud data of the steel structure splicing part to obtain the bolt hole feature area;

[0102] Based on a preset bolt hole size threshold, the bolt hole feature area is fitted to determine the bolt hole position in the spliced ​​plate.

[0103] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for locating bolt holes in a spliced ​​plate is implemented.

[0104] In other words, a non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following operations:

[0105] Perform feature extraction on the obtained bolt hole point cloud data of the steel structure splicing part to obtain the bolt hole feature area;

[0106] Based on a preset bolt hole size threshold, the bolt hole feature area is fitted to determine the bolt hole position in the spliced ​​plate.

[0107] An electronic device 500 that can be used 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 500 is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 500 can also represent various forms of mobile devices, such as personal digital processing, 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.

[0108] The electronic device 500 includes a computing unit, which 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 the operation of the device 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.

[0109] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and 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. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0110] 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 method for locating bolt holes in a spliced ​​plate, characterized in that: include: Perform feature extraction on the obtained bolt hole point cloud data of the steel structure splicing part to obtain the bolt hole feature area; Based on a preset bolt hole size threshold, the bolt hole feature area is fitted to determine the bolt hole position in the spliced ​​plate.

2. The method for locating bolt holes in a splicing plate according to claim 1, characterized in that: Before extracting the features of the obtained bolt hole point cloud data of the steel structure splicing part, it also includes Performing laser scanning on the splicing parts of the steel structure to obtain initial point cloud data of the splicing parts of the steel structure; The initial point cloud data is denoised to obtain the bolt hole point cloud data.

3. The method for locating bolt holes in a spliced ​​plate according to claim 2, characterized in that: The step of performing denoising on the initial point cloud data to obtain the bolt hole point cloud data includes: Taking any point in the initial point cloud data as the center point and a preset radius threshold as the radius, determining the neighborhood range of the center point; Determine whether the central point is a noise point according to the distribution of the distance from the central point to each point in the corresponding neighborhood; The initial point cloud data from which all the noise points are removed is determined as the bolt hole point cloud data.

4. The method for locating bolt holes in a spliced ​​plate according to claim 3, characterized in that: The determining whether the central point is a noise point according to the distribution of the distances from the central point to each point in the corresponding neighborhood range includes: Determine the distance from each point in the neighborhood to the center point as the adjacent point distance; Determine the adjacent point distance threshold according to all the adjacent point distances; When all the adjacent point distances are less than or equal to the adjacent point distance threshold, it is determined that the central point is not the noise point; otherwise, it is determined that the central point is the noise point.

5. The method for locating bolt holes in a spliced ​​plate according to claim 4, characterized in that: The neighbor point distance threshold satisfies: Wherein, T is the adjacent point distance threshold, N is the number of adjacent point distances, d i is the distance between the i-th adjacent points, and k is a preset constant.

6. The method for locating bolt holes in a spliced ​​plate according to claim 1, characterized in that: The feature extraction of the obtained bolt hole point cloud data of the steel structure splicing part to obtain the bolt hole feature area includes: The bolt hole point cloud data is divided into regions based on a clustering algorithm to obtain the bolt hole feature region corresponding to each bolt hole.

7. The method for locating bolt holes in a spliced ​​plate according to claim 1, characterized in that: The step of fitting the bolt hole feature area based on a preset bolt hole size threshold to determine the bolt hole position in the spliced ​​plate includes: Determine the radius of the fitting circle according to the bolt size threshold; Fitting the characteristic area according to the fitting circle radius to obtain a bolt hole fitting circle; The position corresponding to the bolt hole fitting circle is determined as the bolt hole position in the splicing plate.

8. A bolt hole positioning device for a spliced ​​plate, characterized in that: include: An extraction module performs feature extraction on the acquired point cloud data of the bolt holes at the joints of the steel structure to obtain a feature area of ​​the bolt holes; The fitting module fits the bolt hole feature area based on a preset bolt hole size threshold to determine the bolt hole position in the spliced ​​plate.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to implement the method for locating bolt holes in a splicing plate as described in 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 a processor, the method for locating bolt holes in a spliced ​​plate as described in any one of claims 1 to 7 is implemented.

Images