Method, system, medium and device for detecting dimensions of weld bead based on point cloud matching

Abstract

SOLUTION: A dimension detection method of a weld bead based on point group matching comprises: a step for acquiring, first point group data of a weld object region before weld which is collected by a three-dimensional laser scanner, and second point group data of a welded region after weld which is collected by the three-dimensional laser scanner; a step for determining point group data of a weld target interest region on the basis of the first point group data and the weld object region; a step for determining point group data of the welded interest region, on the basis of the second point group data and the welded region; a step for matching the point group data of the weld interest region, with point group data of the welded interest region, for acquiring a matching result; a step for extracting a weld bead point group set, on the basis of the matching result; and a step for analyzing the weld bead point group set, on the basis of point group main component analysis method, for acquiring a dimension of each weld bead.EFFECT: As an effect, it is possible to improve, efficiency of reinforcement weld bead detection and accuracy.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present application relates to the technical field of construction work execution, and more particularly to a method, system, medium and device for detecting dimensions of a weld bead based on point cloud matching. [Background technology]

[0002] Steel bars are widely used in the field of national infrastructure construction such as roads, buildings and bridges, especially in the production and construction of the steel cage of diaphragm walls, the steel bars need to be woven into a cage structure according to the design requirements, which is one of the structural forms for reinforcing and supporting diaphragm walls. Its main function is to strengthen the mechanical properties of the diaphragm walls such as bending, shear and compression, and ensure the stability and safety of the diaphragm walls, and the main connection method of the steel bars is welding, and the welding quality of the weld bead determines the performance of the steel cage framework, and at the same time, determines the safety and stability of the entire steel cage.

[0003] The dimension of the weld bead of the rebar is one of the important standards for judging the quality of the weld bead. The traditional method of detecting the weld bead is the appearance detection method, which mainly adopts the manual detection ruler to measure manually. This method is prone to the subjective influence of the detector, so the detection standard is not consistent, which makes the detection result inaccurate. Summary of the Invention [Problem to be solved by the invention]

[0004] The present application provides a method, system, medium and apparatus for detecting weld bead dimensions based on point cloud matching, which can improve the efficiency and accuracy of rebar weld bead detection, thereby ensuring the safety and stability of the entire rebar cage. [Means for solving the problem]

[0005] According to a first aspect, the present application provides a method for detecting dimensions of a weld bead based on point cloud matching, the method comprising: Obtaining first point cloud data of a region to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of a welded region after welding collected by the three-dimensional laser scanner; determining point cloud data of a welding target region of interest based on the first point cloud data and the welding target region; determining point cloud data of a welded region of interest based on the second point cloud data and the welded region; performing point cloud matching on the point cloud data of the welding region of interest with the point cloud data of the welded region of interest to obtain a matching result; Extracting a weld bead point cloud set based on the matching result; and analyzing the weld bead point cloud set based on a point cloud principal component analysis method to obtain dimensions of each weld bead.

[0006] By adopting the above technical solution, a 3D laser scanner is used to collect a first point cloud data of the area to be welded before welding and a second point cloud data of the welded area after welding, and the point cloud data of the area to be welded and the point cloud data of the area to be welded are determined, the point cloud data of the area to be welded and the point cloud data of the area to be welded are point cloud matched with the point cloud data of the area to be welded, a weld bead point cloud set is extracted based on the matching result, and the weld bead point cloud set is further analyzed based on a point cloud principal component analysis method to obtain the dimensions of each weld bead. Compared with the prior art, this can reduce the subjective influence factors of manual measurement and effectively improve the detection accuracy and efficiency of the weld bead.

[0007] Optionally, the step of acquiring first point cloud data of the welded area before welding collected by a three-dimensional laser scanner and second point cloud data of the welded area after welding collected by the three-dimensional laser scanner includes the steps of: adjusting the attitude of the three-dimensional laser scanner based on the weld bead in the welded area so that the weld bead in the welded area is within the measurement range of the three-dimensional laser scanner; acquiring the first point cloud data of the welded area collected by the three-dimensional laser scanner; adjusting the attitude of the three-dimensional laser scanner based on the weld bead in the welded area so that the weld bead in the welded area is within the measurement range of the three-dimensional laser scanner; and acquiring the second point cloud data of the welded area collected by the three-dimensional laser scanner.

[0008] By adopting the above technical solution, the posture of the 3D laser scanner is adaptively adjusted based on the weld bead, so that the weld bead in the area to be welded and the weld bead in the welded area are within the measurement range of the 3D laser scanner, thereby improving the quality and efficiency of weld bead point cloud data detection.

[0009] Optionally, the step of determining point cloud data of a region of interest to be welded based on the first point cloud data and the region to be welded further includes the steps of: denoising and downsampling the first point cloud data to obtain first target point cloud data; estimating a first set of maximum values ​​and a first set of minimum values ​​in three-dimensional coordinate directions of weld bead coordinates in the region to be welded; and determining point cloud data of a region of interest to be welded based on the first set of maximum values, the first set of minimum values ​​and the first target point cloud data.

[0010] By adopting the above technical solution, the first point cloud data can be subjected to noise removal and down-sampling processing to remove noise and redundant information, and the number of point cloud data can be reduced; and by estimating a first maximum value set and a first minimum value set in the three-dimensional coordinate direction of the weld bead coordinates in the welding target area, the welding target area can be refined and controlled, and the accuracy and efficiency of the welding target area detection can be further improved.

[0011] Optionally, the step of determining point cloud data of the welded area of ​​interest based on the second point cloud data and the welded area includes a step of denoising and downsampling the second point cloud data to obtain second target point cloud data, a step of estimating a second set of maximum values ​​and a second set of minimum values ​​in three-dimensional coordinate directions of weld bead coordinates in the welded area, and a step of determining point cloud data of the welded area of ​​interest based on the second set of maximum values, the second set of minimum values ​​and the second target point cloud data.

[0012] By adopting the above technical solution, the second point cloud data can be subjected to noise removal and down-sampling processing to remove noise and redundant information and reduce the number of point cloud data; and by estimating a second maximum value set and a second minimum value set in the three-dimensional coordinate directions of the weld bead coordinates in the welded area, the welded area can be refined and controlled, and the accuracy and efficiency of the welded area detection can be further improved.

[0013] Optionally, the step of point cloud matching the point cloud data of the welding area of ​​interest with the point cloud data of the welded area of ​​interest to obtain a matching result includes a step of point cloud matching the point cloud data of the welded area of ​​interest with the point cloud data of the welded area of ​​interest based on an iterative closest point method, and calculating a posture transformation matrix, and a step of taking the posture transformation matrix as the matching result.

[0014] By adopting the above technical solution, the point cloud data of the welding area of ​​interest is matched with the point cloud data of the welded area of ​​interest, the point cloud data of the two areas is integrated, and a posture transformation matrix is ​​calculated, thereby realizing the alignment and matching between the point clouds, which facilitates the subsequent processing and analysis of the welded area, and improves the accuracy and efficiency of welded area detection.

[0015] Optionally, the step of extracting a weld bead point cloud set based on the matching result includes the steps of: transforming point cloud data of the welded region of interest into the welded target region of interest based on the posture transformation matrix in the matching result; and for any one target point of the welded region of interest, determining point cloud data of the welded region of interest that has the shortest Euclidean distance to the target point, and determining a point of the welded region of interest that corresponds to the point cloud data of the welded region, the shortest Euclidean distance of which is greater than a weld bead extraction threshold, as a weld bead point, thereby obtaining a weld bead point cloud set.

[0016] By adopting the above technical solution, the point cloud data with the shortest distance among the point cloud data of the region of interest to be welded is determined by the Euclidean distance, and the point with the shortest distance is determined as the weld bead point, the Euclidean distance is the distance between points and is an important index for evaluating the matching and alignment effect of point cloud data, and the point corresponding to the point cloud data of the welded region whose shortest Euclidean distance is greater than the weld bead extraction threshold is determined as the weld bead point, and the extraction progress and number of the weld bead points can be controlled, and the detection accuracy and efficiency of subsequent weld beads can be effectively improved.

[0017] Optionally, after the step of analyzing the weld bead point cloud set based on a point cloud principal component analysis method and obtaining dimensions of each weld bead, the method includes a step of respectively comparing the dimensions of each weld bead with a predetermined size range of a standard weld bead, the dimensions of the weld bead including length, width and depth, a step of determining a weld bead whose dimensions do not fit the predetermined size range of the standard weld bead as a rejected weld bead, and a step of determining a weld bead whose dimensions fit the predetermined size range of the standard weld bead as a passed weld bead.

[0018] By adopting the above technical solution, the measured dimensions of the weld bead can be respectively compared with the preset standard weld bead dimension range to obtain the weld bead detection result, which can clearly inform the operator whether the weld bead is acceptable or not, thereby facilitating the subsequent detection and inspection of the weld bead.

[0019] According to a second aspect of the present application, there is provided a weld bead dimension detection system based on point cloud matching, the system comprising: a point cloud data acquisition module for acquiring first point cloud data of a region to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of a welded region after welding collected by the three-dimensional laser scanner; a region of interest acquisition module for determining point cloud data of a welded region of interest based on the first point cloud data and the welded region, and for determining point cloud data of a welded region of interest based on the second point cloud data and the welded region; a point cloud matching module for performing point cloud matching of the point cloud data of the welding region of interest with the point cloud data of the welded region of interest to obtain a matching result; a weld bead point cloud set extraction module for extracting a weld bead point cloud set based on the matching result; a detection report generating module for analyzing the weld bead point cloud set based on a point cloud principal component analysis method to obtain dimensions of each weld bead; and a weld bead dimension generation module for analyzing the weld bead point cloud set based on a point cloud principal component analysis method to obtain dimensions of each weld bead.

[0020] A third aspect of the present application provides a computer storage medium having stored thereon a plurality of instructions, the instructions being suitable to be loaded by a processor to perform the steps of the above method.

[0021] A fourth aspect of the present application provides an electronic device comprising a processor and a memory, wherein a computer program is stored in the memory, the computer program being suitable to be loaded by the processor to perform the steps of the above method. Effect of the Invention

[0022] As described above, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application uses a 3D laser scanner to collect first point cloud data of a welded area before welding and second point cloud data of a welded area after welding, determines the point cloud data of the welded area of ​​interest and the point cloud data of the welded area of ​​interest, performs point cloud matching on the point cloud data of the welded area of ​​interest with the point cloud data of the welded area of ​​interest, extracts a weld bead point cloud set based on the matching result, and further analyzes the weld bead point cloud set based on a point cloud principal component analysis method to obtain the dimensions of each weld bead. Compared with the prior art, this application can reduce the subjective influence factors of manual measurement and effectively improve the detection accuracy and efficiency of weld beads. 2. The present application performs point cloud matching of the point cloud data of the welding area of ​​interest with the point cloud data of the welded area of ​​interest, integrates the point cloud data of the two areas into one, and calculates a posture transformation matrix, thereby realizing the alignment and matching between the point clouds, which facilitates the subsequent processing and analysis of the welded area, and improves the accuracy and efficiency of welded area detection. 3. In the present application, by comparing the measured weld bead dimensions with a preset standard weld bead dimension range, the weld bead detection result can be obtained, and the operator can be clearly informed whether the weld bead is acceptable or not, thereby facilitating the subsequent detection and inspection of the weld bead. [Brief description of the drawings]

[0023] [Figure 1] 1 is a schematic flowchart of a method for detecting dimensions of a weld bead based on point cloud matching provided in an embodiment of the present application. [Diagram 2] FIG. 2 is a schematic diagram of a weld bead detection using a three-dimensional laser scanner provided in an embodiment of the present application. [Diagram 3] 1 is a schematic diagram of a module of a weld bead dimension detection system based on point cloud matching provided in an embodiment of the present application. [Figure 4] 1 is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] In order to enable those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification. Obviously, the described embodiments are only some embodiments of the present application, but not all embodiments.

[0025] In describing the embodiments of the present application, terms such as "for example" or "for example" are used to indicate an example, illustration, or explanation. Any embodiment or design described in the embodiments of the present application as "for example" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, use of terms such as "for example" or "for example" is intended to present the relevant concept in a concrete manner.

[0026] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are merely for descriptive purposes and should not be understood as indicating or implying relative importance or implicitly identifying the technical features shown. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. "Include", "contain", "have" and variations thereof mean "including, but not limited to", unless specifically emphasized otherwise.

[0027] In order to facilitate understanding of the methods and systems provided in the embodiments of the present application, a background of the embodiments of the present application will first be introduced before introducing the embodiments of the present application.

[0028] Steel bars are necessary in construction work, and the steel bars produced in steel mills cannot meet all the needs of construction, so the construction side will use welding to meet the length and strength of the steel bars they need. This operation is common, and can save costs and improve the utilization rate of materials. In particular, in the manufacture and construction of the steel bar cage of underground diaphragm walls, the steel bars need to be assembled into a cage structure according to the design requirements and welded, which is one of the structural forms for reinforcing and supporting underground diaphragm walls.

[0029] The welding quality of the reinforcing bars determines the safety and stability of the entire reinforcing bar cage, and the dimensions of the weld beads of the reinforcing bars are one of the important standards for judging the quality of the weld beads. Conventional methods for detecting weld beads mainly adopt manual appearance detection methods, manually adopt detection rulers to measure manually, and then manually observe and judge. Such methods for detecting weld beads are easily influenced by the subjectivity of the detector, which makes the detection results of the weld beads inaccurate.

[0030] In one embodiment, referring to Fig. 1, a schematic flow chart of a method for detecting dimensions of a weld bead based on point cloud matching is provided, and the method may be implemented by a computer program, or may be implemented by a one-chip microcomputer, or may be executed on a system for detecting dimensions of a weld bead based on point cloud matching. The computer program may be integrated into an application or executed as a standalone tool-type application, and in particular, in an embodiment of the present application, the method may be applied to a control device for photographic lighting, and the method includes steps 10 to 60, and the steps are as follows:

[0031] Step 10: Obtain first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and obtain second point cloud data of the welded area after welding collected by a three-dimensional laser scanner.

[0032] A 3D laser scanner is a surveying device that uses the principle of laser ranging to scan the surface of an object to obtain its 3D coordinate information. It can quickly and accurately obtain the 3D shape information of the object surface. Its working principle is to emit a laser beam, which is reflected after being irradiated on the object surface, and the 3D laser scanner receives the reflected laser signal, and calculates the distance information of the object surface according to the time delay of the signal, thereby obtaining the 3D coordinate information of the object surface. In the embodiment of this application, a 3D laser scanner is used to detect the weld bead.

[0033] Point cloud data is a collection of data in a three-dimensional space consisting of a number of points, each point including a location in space and possibly other attributes. Point cloud data can represent information such as the shape, texture, surface features, etc. of an object or scene. In an embodiment of the present application, the point cloud data may be collected by a three-dimensional laser scanner, where the first point cloud data is a collection of data collected by the three-dimensional laser scanner from an area to be welded before welding, and the second point cloud data is a collection of data collected by the three-dimensional laser scanner from an area to be welded.

[0034] In addition to the above embodiment, as an alternative embodiment, the step of acquiring first point cloud data of the welded area before welding collected by a three-dimensional laser scanner and second point cloud data of the welded area after welding collected by a three-dimensional laser scanner may further include the following steps.

[0035] Step 101: The attitude of the three-dimensional laser scanner is adjusted based on the weld bead in the area to be welded so that the weld bead in the area to be welded is within the measurement range of the three-dimensional laser scanner.

[0036] Step 102: Obtain a first point cloud data of the area to be welded collected by a 3D laser scanner.

[0037] Specifically, before welding, a three-dimensional laser scanner is attached to the area to be welded, and the three-dimensional laser scanner is wirelessly connected to a computer device, and the three-dimensional laser scanner is adjusted and calibrated before measurement to determine parameters such as the measurement range, scanning speed and scanning resolution of the three-dimensional laser scanner. Generally, the scanning range and speed should be adjusted according to the size and shape of the area to be measured to ensure the comprehensiveness and efficiency of scanning. Before measurement, the attitude of the three-dimensional laser scanner should be adjusted based on the weld bead in the area to be welded, so that the weld bead in the area to be welded is within the measurement range of the three-dimensional laser scanner, and it is necessary to ensure that the distance and angle between the three-dimensional laser scanner and the area to be measured are appropriate during scanning, thereby ensuring the comprehensiveness and overlapping degree of scanning, and the specific adjustment parameters can be adjusted by the operator himself.

[0038] Further, after adjusting each parameter, the three-dimensional laser scanner is controlled to start operating, and first point cloud data of the area to be welded is generated based on the data collected by the three-dimensional laser scanner and further based on three-dimensional reconstruction software or point cloud processing software, and the first point cloud data is three-dimensional data consisting of a large number of points and can reflect the shape and characteristics of the area to be welded.

[0039] Step 103: The attitude of the three-dimensional laser scanner is adjusted based on the weld bead in the welded area so that the weld bead in the welded area is within the measurement range of the three-dimensional laser scanner.

[0040] Step 104: Obtain a second point cloud data of the welded area collected by a 3D laser scanner.

[0041] Specifically, a 3D laser scanner is attached to the welded area, and the attitude of the 3D laser scanner is adjusted based on the weld bead in the welded area so that the weld bead in the welded area is within the measurement range of the 3D laser scanner, the specific implementation process can refer to the above step 101, and the description thereof will be omitted here. The 3D laser scanner is controlled to start operating, and second point cloud data of the welded area is generated based on the data collected by the 3D laser scanner and further based on the 3D reconstruction software or point cloud processing software, the second point cloud data is 3D data consisting of a large number of points and can reflect the shape and features of the welded area.

[0042] Step 20: Determine point cloud data of a welding target region of interest based on the first point cloud data and the welding target region.

[0043] Since the scanning area of ​​the 3D laser scanner may be large and there may be scanning overlap, it is necessary to process the first point cloud data to obtain point cloud data of the region of interest to be welded, which reduces the amount of subsequent calculations and thereby improves the efficiency and accuracy of detection. The point cloud data of the region of interest to be welded is the point cloud data within the region finally obtained by performing alignment, division, extraction, etc. of the first point cloud data using point cloud processing software. The point cloud data of the region of interest to be welded includes coordinate information of all points within the region.

[0044] Specifically, the first point cloud data is subjected to noise removal and downsampling to obtain first target point cloud data, a first set of maximum values ​​and a first set of minimum values ​​in the three-dimensional coordinate directions of the weld bead coordinates in the welding target area are estimated, a coordinate range in the three-dimensional coordinate axis direction of the welding target area is determined based on the first set of maximum values ​​and the first set of minimum values, the area formed by the coordinate range is set as the welding target area of ​​interest, the point cloud data of the welding target area is screened, point cloud data whose coordinate values ​​in the three-dimensional coordinate directions of the weld bead point cloud data are within the welding target area of ​​interest are extracted, and the point cloud data of the welding target area of ​​interest is obtained.

[0045] In addition to the above embodiment, as an alternative embodiment, the step of determining the point cloud data of the welding target region of interest based on the first point cloud data and the welding target region may further include the following steps.

[0046] Step 201: The first point cloud data is subjected to noise removal and down-sampling processing to obtain a first target point cloud data.

[0047] Specifically, since there may be some noise or abnormal points in the first point cloud data, a noise removal process is necessary, and the noise removal process may adopt a filter algorithm, such as a Gaussian filter, a median filter, a bilateral filter, etc. These filter algorithms can effectively remove noise and abnormal points and retain useful information in the point cloud data.

[0048] Furthermore, since the first point cloud data usually contains a large number of points, in order to reduce the number and complexity of the point cloud data, it is necessary to perform a downsampling process on the point cloud data after the noise removal process, and the downsampling method can adopt voxel mesh downsampling, random sampling, distance-based sampling, etc. These methods can be optimized based on the distribution and density of the point cloud data, and can obtain the first target point cloud data after downsampling with a certain accuracy.

[0049] Step 202: Estimate a first set of maximum values ​​and a first set of minimum values ​​in three-dimensional coordinate directions of the weld bead coordinates in the region to be welded.

[0050] Specifically, the point cloud data of the region to be welded is divided, and the region where the weld bead is located is extracted from the point cloud data to obtain the weld bead point cloud data. The weld bead point cloud data is processed to obtain coordinate values ​​in three-dimensional coordinate directions of the weld bead point cloud data, i.e., x-axis coordinate value, y-axis coordinate value, and z-axis coordinate value, where the three-dimensional coordinate directions are three mutually perpendicular axes representing a position or direction in space in the embodiment of the present application. In the three-dimensional coordinate system, a position or direction is represented by three axes, which are the X-axis, Y-axis, and Z-axis, respectively, and each axis is perpendicular to a plane perpendicular to it.

[0051] Furthermore, the coordinate values ​​in the x-axis direction, the y-axis direction, and the z-axis direction of the weld bead point cloud data are statistically analyzed to obtain a first maximum value set in the x-axis direction, the y-axis direction, and the z-axis direction, and a first minimum value set in the x-axis direction, the y-axis direction, and the z-axis direction. These can be calculated using a statistical method, such as an extreme difference method, a quantile method, a standard deviation method, etc.

[0052] Step 203: Determine point cloud data of a welding target region of interest based on the first maximum value set, the first minimum value set and the first target point cloud data.

[0053] Specifically, the first target point cloud data is divided into a weld bead area and a non-weld bead area, the point cloud data of the weld bead area is processed, coordinate values ​​in a three-dimensional coordinate direction of the weld bead point cloud data, for example, z-axis coordinate values, are obtained, and a coordinate range in a three-dimensional coordinate direction of the region of interest to be welded is determined based on a first maximum value set and a first minimum value set, the point cloud data of the weld bead area is screened, and the point cloud data of the region of interest to be welded is retained whose coordinate values ​​in the three-dimensional coordinate direction of the weld bead point cloud data are within the region of interest to be welded, thereby obtaining the point cloud data of the region of interest to be welded, that is, obtaining point cloud data with a certain precision and accuracy for subsequent processing and analysis.

[0054] Step 30: Determine point cloud data of a welded region of interest based on the second point cloud data and the welded region.

[0055] Since the scanning area of ​​the 3D laser scanner may be large and there may be a possibility of scanning overlap, it is necessary to process the second point cloud data to obtain the point cloud data of the welded area of ​​interest, which reduces the amount of subsequent calculations and thereby improves the efficiency and accuracy of detection. The point cloud data of the welded area of ​​interest is the point cloud data within the area finally obtained by performing the alignment, division, extraction, etc. of the second point cloud data by the point cloud processing software. The point cloud data of the welded area of ​​interest includes the coordinate information of all points within the area.

[0056] Specifically, the second point cloud data is subjected to noise removal and downsampling to obtain second target point cloud data, a second set of maximum values ​​and a second set of minimum values ​​in the three-dimensional coordinate directions of the weld bead coordinates in the welded area are estimated, a coordinate range in the three-dimensional coordinate axis direction of the welded area is determined based on the second set of maximum values ​​and the second set of minimum values, the area formed by the coordinate range is set as the welded area of ​​interest, the point cloud data of the welded area is screened, and point cloud data whose coordinate values ​​in the three-dimensional coordinate directions of the weld bead point cloud data are within the welded area of ​​interest are extracted, and the point cloud data of the welded area of ​​interest is obtained.

[0057] In addition to the above embodiment, as an alternative embodiment, the step of determining point cloud data of the welded region of interest based on the second point cloud data and the welded region includes: Step 301 of performing noise removal and downsampling on the second point cloud data to obtain second target point cloud data; estimating 302 a second set of maximum values ​​and a second set of minimum values ​​in three-dimensional coordinate directions of the weld bead coordinates in the welded region; The method may further include determining 303 point cloud data of the welded region of interest based on the second set of maximum values, the second set of minimum values ​​and the second target point cloud data.

[0058] Specifically, the above steps 201 to 203 can be referred to for the method of implementing the above steps 301 to 303, and the method of determining the point cloud data of the welded region of interest is the same as the method of determining the point cloud data of the welded region of interest, and will not be described in detail here.

[0059] Step 40: Perform point cloud matching on the point cloud data of the welding region of interest with the point cloud data of the welded region of interest to obtain a matching result.

[0060] Point cloud matching refers to aligning two or more point cloud data to realize alignment and fusion of point cloud data. In the embodiment of the present application, the point cloud data of the region of interest to be welded is matched with the point cloud data of the region of interest that has been welded, the point cloud data of the two regions are integrated, and a posture transformation matrix is ​​calculated, so that the alignment and matching between the point clouds can be realized, which facilitates the subsequent processing and analysis of the welded region, and improves the accuracy and efficiency of the detection of the welded region.

[0061] Specifically, the iterative closest point method is a method for registering and aligning two or more point cloud data, and iteratively optimizes the registration error between the point cloud data until the error is minimized. The point cloud data of the welded region of interest is taken as the reference point cloud, the point cloud data of the region to be welded is taken as the registration target point cloud, one point is selected from the registration target point cloud, a point closest to the selected point is searched for in the reference point cloud, the distance error between the corresponding point pairs between the registration target point cloud and the reference point cloud is calculated, the registration error between the two point cloud data is measured, and the distance error is minimized to optimize the rigid body transformation matrix of the registration target point cloud, so that the position and orientation of the registration target point cloud are closer to the reference point cloud, and the above steps are repeated until the distance error between the point cloud data reaches a preset threshold or the maximum number of iterations is reached. The iterative closest point algorithm is then used to obtain the orientation transformation matrix, the point cloud data of the region to be welded of interest is transformed and aligned with the point cloud data of the welded region of interest, and the orientation transformation matrix is ​​taken as the matching result.

[0062] Step 50: Extract a weld bead point cloud set based on the matching result.

[0063] Specifically, according to the posture transformation matrix in the matching result, each point in the welded region of interest is transformed by the posture transformation matrix, thereby obtaining its corresponding point in the welded region of interest. By sequentially traversing the point cloud data of the welded region of interest, i.e., any one of the target points in the welded region of interest, the Euclidean distance between each point and the target point is calculated, and the point with the smallest distance is selected as the corresponding point, and if the distance is less than or equal to the weld bead extraction threshold, the point cloud data of the welded region corresponding to this point is added to the weld bead point cloud set, thereby obtaining a weld bead point cloud set, which can control the extraction progress and number of weld bead points, and effectively improve the detection accuracy and efficiency of the subsequent weld bead.

[0064] Step 60: Analyze the weld bead point cloud set based on the point cloud principal component analysis method to obtain the dimensions of each weld bead.

[0065] The point cloud principal component analysis method involves projecting point cloud data onto the principal component axes, obtaining the variance and average value in each principal component direction, and thereby obtaining dimensional information in each direction of the point cloud data.

[0066] Specifically, the weld bead point cloud set is converted into a point cloud matrix, and principal component analysis is performed. Each row of the point cloud matrix corresponds to one point, and each column corresponds to one dimension (e.g., X, Y, Z coordinates). The point cloud matrix is ​​subjected to principal component analysis to obtain the variance and average value in each principal component direction. The principal component direction corresponds to the main distribution direction of the point cloud data, and the dimensions of each weld bead in the X, Y, and Z directions can be determined based on the direction and variance information. For example, the standard deviation in each principal component direction can be calculated, thereby obtaining dimensional information of the weld bead in each direction, and the dimensions of the weld bead in the X, Y, and Z directions can respectively correspond to the length, width, and depth of the weld bead.

[0067] Furthermore, after obtaining the dimensions of each weld bead, the dimensions of each weld bead are respectively compared with a preset standard weld bead size range, which may be a manually set standard range of the weld bead length, width, and depth. A weld bead whose dimensions do not conform to the preset standard weld bead size range is determined as a rejected weld bead, and a weld bead whose dimensions conform to the preset standard weld bead size range is determined as a passed weld bead, so that an operator can be clearly informed of whether the weld bead is a pass product, thereby facilitating subsequent detection and inspection of the weld beads.

[0068] The weld beads can further be classified by size, thereby obtaining the number and percentage of weld beads in different size ranges, and at the same time, statistics such as the mean weld bead size, standard deviation, etc. can be calculated to more completely describe the bead size distribution.

[0069] FIG. 2 is a schematic diagram of the weld bead detection by the 3D laser scanner provided in the embodiment of the present application, and the implementation principle of the embodiment of the present application will be described below with reference to FIG. 2. First, the 3D laser scanner is controlled to a pre-welding scanning position, and the attitude of the 3D laser scanner is adjusted so that the weld bead of the welded area is within the measurement range of the 3D laser scanner, to obtain a first point cloud data of the welded area before welding collected by the 3D laser scanner, and the 3D laser scanner is controlled to move to a post-welding scanning position according to a preset moving path 3, and the attitude of the 3D laser scanner is adjusted again so that the weld bead of the welded area is within the measurement range of the 3D laser scanner, to obtain a second point cloud data of the welded area after welding. Based on the first point cloud data and the welded area, the point cloud data of the welded area of ​​interest is determined, and based on the second point cloud data and the welded area, the point cloud data of the welded area of ​​interest is determined. The point cloud data of the welding region of interest is matched with the point cloud data of the welded region of interest to obtain a matching result, a weld bead point cloud set is extracted based on the matching result, the weld bead point cloud set is analyzed based on a point cloud principal component analysis method, and the dimensions of each weld bead are obtained.

[0070] Referring to FIG. 3, a module schematic diagram of a weld bead dimension detection system based on point cloud matching provided in an embodiment of the present application, the weld bead dimension detection system based on point cloud matching may include a point cloud data acquisition module 301, a region of interest acquisition module 302, a point cloud matching module 303, a weld bead point cloud set extraction module 304 and a weld bead dimension generation module 305, where: The point cloud data acquisition module 301 is used to acquire first point cloud data of a welding target area before welding collected by a three-dimensional laser scanner, and second point cloud data of a welded area after welding collected by the three-dimensional laser scanner; a region of interest acquisition module 302 for determining point cloud data of a welded region of interest based on the first point cloud data and the welded region, and for determining point cloud data of a welded region of interest based on the second point cloud data and the welded region; a point cloud matching module 303 for performing point cloud matching of the point cloud data of the welding region of interest with the point cloud data of the welded region of interest to obtain a matching result; The weld bead point cloud set extraction module 304 is used to extract a weld bead point cloud set based on the matching result; A weld bead dimension generation module 305 is used to analyze the weld bead point cloud set based on point cloud principal component analysis to obtain dimensions of each weld bead.

[0071] In addition, the device provided in the above embodiment is exemplified by only dividing the above functional modules when implementing its functions, and in actual application, the above functions are assigned to different functional modules to be completed as necessary, that is, the internal structure of the device is divided into different functional modules to realize all or part of the above-described functions. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process thereof is referred to in detail in the method embodiment, and the description thereof is omitted here.

[0072] The present application further discloses an electronic device. Referring to FIG. 4, FIG. 4 is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 400 may include at least one processor 401, at least one network interface 404, a user interface 403, a memory 405, and at least one communication bus 402.

[0073] Here, a communication bus 402 is used to realize the connection communication between these components.

[0074] Here, the user interface 403 may include a display and a camera, and optionally, the user interface 403 may further include a standard wired interface and a wireless interface.

[0075] Here, the network interface 404 may selectively include a standard wired interface, a wireless interface (eg, a WI-FI interface).

[0076] Here, the processor 401 may include one or more processing cores. The processor 401 connects each part of the entire server using various interfaces and lines, operates or executes instructions, programs, code sets or instruction sets stored in the memory 405, and executes various functions of the server and processes data by calling data stored in the memory 405. Optionally, the processor 401 may be realized in at least one hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 401 may integrate one or more combinations of a central processing unit (CPU), a graphics processing unit (GPU), a modem, etc. Here, the CPU mainly processes an operating system, a user interface, and application programs, etc., the GPU is used to render and draw content that needs to be displayed on a display, and the modem is used to handle wireless communication. As will be appreciated, the modem may be implemented on a single chip rather than being integrated into the processor 401 .

[0077] Here, the memory 405 may include a random access memory (RAM) or a read-only memory. Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 405 may include a storage program area and a storage data area, where the storage program area is used to store instructions for implementing an operating system, instructions for at least one function (e.g., a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, and the storage data area can store data related to the above-mentioned method embodiments. The memory 405 may be at least one storage device that is optionally located remotely from the processor 401. Referring to FIG. 4, the memory 405, which is a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program of the weld bead dimension detection method based on point cloud matching.

[0078] In the electronic device 400 shown in FIG. 4, the user interface 403 is mainly used as an interface for providing input to a user, and the processor 401 may be used to call an application program of a method for detecting dimensions of a weld bead based on point cloud matching stored in the memory 405, which, when executed by one or more processors 401, causes the electronic device 400 to execute one or more of the above-mentioned methods in the above-mentioned embodiments. Note that, for the sake of simplicity, the above-mentioned embodiments of the methods are all expressed as a combination of a series of operations, but a person skilled in the art will recognize that the present application is not limited by the order of operations described, and that according to the present application, certain steps can adopt other orders or be performed simultaneously. Next, a person skilled in the art will recognize that all of the embodiments described in this specification belong to preferred embodiments, and the operations and modules mentioned are not necessarily required for the present application.

[0079] In the above embodiments, the description of each embodiment focuses on its own, and for the parts of an embodiment that are not described in detail, please refer to the relevant descriptions of other embodiments.

[0080] In some embodiments provided in the present application, it should be understood that the disclosed device can be realized in other forms. For example, the above-described device examples are merely illustrative, and the division of units is merely a division in terms of logical functions, and can be divided in other forms when implemented, for example, multiple units or components can be combined or integrated into another system, or some features can not be reflected or executed. In addition, the mutual coupling or direct coupling or communication connection described or discussed can be an indirect connection or communication connection using some interfaces, devices or units, and can be in an electrical form or other form.

[0081] Units described as separate elements may or may not be physically separate, and elements shown as units may be physical units, but may not be physical units, i.e. may be co-located, but may be located in multiple network units. Depending on the needs, only some units or all units may be used to achieve the objectives of the aspects of this embodiment.

[0082] In each embodiment of the present application, each functional unit may be integrated into one processing unit, but each unit may exist as a separate physical component, or two or more units may be integrated into one unit. The integrated units may be realized in the form of hardware or software functional units.

[0083] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable memory. Based on this understanding, the essential or prior art part of the technical solution of the present application or all or part of the technical solution can be expressed in the form of a software product, and the computer software product is stored in a memory and includes some instructions used to make a computer device (such as a personal computer, a server, or a network device) execute all or part of the steps of the method of each embodiment of the present application. The memory includes various media that can store program code, such as a U disk, a mobile hard disk, a magnetic disk, or an optical disk.

[0084] The above are merely illustrative examples of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, all equivalent changes and modifications made based on the teachings of the present disclosure are within the scope of the present disclosure. After reviewing the disclosure of the specification and the practical truth, a person skilled in the art will easily come up with other embodiments of the disclosure.

[0085] This application is intended to cover any variations, uses, or adaptations of the present disclosure, including those that are within the scope of the general principles of the present disclosure, but which are not described in the present disclosure and are within the scope of the common technical knowledge or customary techniques in the art. The specification and examples are to be considered as exemplary only, with the scope and spirit of the present disclosure being limited only by the claims. [Explanation of symbols]

[0086] 301...point cloud data acquisition module, 302...region of interest acquisition module, 303...point cloud matching module, 304...weld bead point cloud set extraction module, 305...weld bead dimension generation module, 400...electronics, 401...processor, 402...communication bus, 403...user interface, 404...network interface, 405...memory.

Claims

1. A method for detecting dimensions of a weld bead based on point cloud matching, comprising: Obtaining first point cloud data of a region to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of a welded region after welding collected by the three-dimensional laser scanner; determining point cloud data of a welding target region of interest based on the first point cloud data and the welding target region; determining point cloud data of a welded region of interest based on the second point cloud data and the welded region; performing point cloud matching on the point cloud data of the welding target region of interest with the point cloud data of the welded region of interest to obtain a matching result; Extracting a weld bead point cloud set based on the matching result; and analyzing the weld bead point cloud set based on a point cloud principal component analysis method to obtain dimensions of each weld bead.

2. The step of acquiring first point cloud data of a welding target area before welding collected by a three-dimensional laser scanner and second point cloud data of a welded area after welding collected by the three-dimensional laser scanner includes: adjusting a posture of the three-dimensional laser scanner based on the weld bead in the region to be welded so that the weld bead in the region to be welded is within a measurement range of the three-dimensional laser scanner; acquiring first point cloud data of the area to be welded collected by the three-dimensional laser scanner; adjusting a posture of the three-dimensional laser scanner based on the weld bead in the welded area so that the weld bead in the welded area is within a measurement range of the three-dimensional laser scanner; and acquiring second point cloud data of the welded area collected by the three-dimensional laser scanner.

3. The step of performing point cloud matching of the point cloud data of the welding target region of interest with the point cloud data of the welded region of interest to obtain a matching result includes: performing point cloud matching of the point cloud data of the welding target region of interest with the point cloud data of the welded region of interest based on an iterative closest point method, and calculating a posture transformation matrix; 2. The method for detecting dimensions of a weld bead based on point cloud matching according to claim 1, further comprising a step of determining the posture transformation matrix as a matching result.

4. The step of extracting a weld bead point cloud set based on the matching result includes: transforming point cloud data of the welded region of interest into the welding target region of interest based on the posture transformation matrix in the matching result; For any one target point of the welded region of interest, 4. The method for detecting dimensions of a weld bead based on point cloud matching according to claim 3, further comprising a step of determining point cloud data having a shortest Euclidean distance to the target point from among the point cloud data of the region of interest of the welding object, and determining as a weld bead point a point corresponding to point cloud data of a welded region from among the region of interest of the welding object, the point having the shortest Euclidean distance greater than a weld bead extraction threshold, thereby obtaining a weld bead point cloud set.

5. After the step of analyzing the weld bead point cloud set based on a point cloud principal component analysis method and obtaining dimensions of each weld bead, comparing the dimensions of each of the weld beads with a preset range of dimensions of a standard weld bead, the dimensions of the weld beads including length, width and depth; determining a weld bead whose size does not conform to a preset size range of a standard weld bead as a rejected weld bead; and determining, as an acceptable weld bead, a weld bead whose size fits within a preset size range of a standard weld bead.

6. A weld bead size detection system based on point cloud matching, comprising: A point cloud data acquisition module (301) for acquiring first point cloud data of a welding target area before welding collected by a three-dimensional laser scanner, and second point cloud data of a welded area after welding collected by the three-dimensional laser scanner; a region of interest acquisition module (302) for determining point cloud data of a welded region of interest based on the first point cloud data and the welded region, and for determining point cloud data of a welded region of interest based on the second point cloud data and the welded region; a point cloud matching module (303) for performing point cloud matching of the point cloud data of the welding target region of interest with the point cloud data of the welded region of interest to obtain a matching result; a weld bead point cloud set extraction module (304) for extracting a weld bead point cloud set based on the matching result; and a weld bead dimension generation module (305) for analyzing the weld bead point cloud set based on a point cloud principal component analysis method and obtaining dimensions of each weld bead.

7. A computer readable storage medium having stored thereon a plurality of instructions, the instructions being suitable, when loaded by a processor, for performing the method according to any one of claims 1 to 5.

8. An electronic device comprising a processor, a memory and a transceiver, the memory being used for storing instructions, the transceiver being used for communicating with other devices, and the processor being used for executing instructions stored in the memory to cause the electronic device to perform a method according to any one of claims 1 to 5.

Images