A method and system for measuring the size of a combined ladle gate brick

Abstract

The application provides a ladle combined door brick size measurement method and system, and relates to the field of data processing. In the method, a three-dimensional point cloud is collected on the ground reference surface, the key area is cut according to the prior gap center axis and trapezoidal contour of the double bricks, the candidate measurement point cloud is generated, the target brick point cloud dataset is obtained by removing the interference points through multidimensional point cloud purification, the space modeling is performed on the upper surface of the single brick and the ground reference surface respectively to measure the thickness, the key features are positioned by extracting the outer contour edge to obtain the contour size, finally, the thickness and the contour size are corrected by combining the mapping correction parameters of the masonry process, and the target size result which can be directly used for the assembly quality control of the ladle combined door brick is output. By implementing the technical scheme provided by the application, the thickness and the contour size can be obtained at the same time under the complex site conditions, and the automatic measurement accuracy under different process assembly requirements is improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, specifically to a method and system for measuring the dimensions of steel-clad door bricks. Background Technology

[0002] As an important component of the ladle furnace lining, the dimensional accuracy of the ladle lining assembly door brick directly affects the sealing performance and overall structural stability of the furnace lining assembly.

[0003] However, under actual site conditions, bricks used for assembly are typically irregular trapezoidal in shape, and their placement is difficult to strictly control. Their surfaces are also prone to adhering to dust, mortar residue, or impurities. Furthermore, the complex site environment and fast construction pace make it difficult for traditional manual measurement methods to guarantee consistency and accuracy. In addition, existing 3D measurement schemes suffer from problems such as unstable benchmarks, inaccurate contour feature extraction, and a disconnect between thickness and contour measurements in practical applications. This results in measurement results that fail to reflect the actual brick assembly state and cannot meet the assembly adaptation requirements under different masonry processes. These issues make it difficult for existing technologies to achieve high-precision, high-consistency, and high-efficiency measurement of brick dimensions, thus hindering reliable control of steel package assembly quality.

[0004] Therefore, there is an urgent need for a high-precision automatic measurement method that can simultaneously obtain thickness and contour dimensions under complex field conditions and adapt to different process assembly requirements. Summary of the Invention

[0005] This application provides a method and system for measuring the dimensions of steel-clad door bricks, which facilitates the simultaneous acquisition of thickness and contour dimensions under complex site conditions and improves the accuracy of automatic measurement under different process assembly requirements.

[0006] The first aspect of this application provides a method for measuring the dimensions of steel-clad door bricks. The method includes: acquiring three-dimensional point cloud data of two brick bodies placed on a ground reference surface according to a preset arrangement; performing key region clipping processing on the three-dimensional point cloud data, generating a key clipping region by extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour prior of the two brick bodies, and generating candidate measurement point cloud data based on the point cloud within the key clipping region; performing multi-dimensional point cloud purification processing on the candidate measurement point cloud data, separating the effective surface point cloud and interfering point cloud of the two brick bodies by outlier removal based on local density changes and region clustering based on normal vector constraints, to obtain a target brick body point cloud dataset; and performing multi-dimensional point cloud purification processing on the target brick body point cloud data. The process involves performing thickness parameter measurement and processing. This is achieved by spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface, thus obtaining the thickness parameters of the brick. Based on the target brick point cloud dataset, contour dimension measurement and processing are performed. This involves separating the point cloud of the double brick body from the point cloud on the ground reference surface, extracting the outer contour edge, and locating key feature positions within the outer contour edge, thus obtaining the contour dimension parameters of the brick. Finally, based on the brick thickness and contour dimension parameters, a process adaptability correction process is performed. This maps the masonry process conditions to correction parameters, which are then used to correct the brick thickness and contour dimension parameters, outputting the target dimension result for quality control of the steel-clad brick assembly.

[0007] A second aspect of this application provides a steel-clad door brick size measurement system. The system includes an acquisition module and a processing module. The acquisition module acquires three-dimensional point cloud data of two brick bodies placed on a ground reference surface according to a preset arrangement. The processing module performs key region clipping processing on the three-dimensional point cloud data. It generates a key clipping region by extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour prior of the two brick bodies, and generates candidate measurement point cloud data based on the point cloud within the key clipping region. The processing module further performs multi-dimensional point cloud purification processing on the candidate measurement point cloud data. It separates the effective surface point cloud of the two brick bodies from the interfering point cloud through outlier removal based on local density changes and region clustering based on normal vector constraints, obtaining a target brick point cloud dataset. The module is also used to perform thickness parameter measurement processing based on the target brick point cloud dataset. By spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface, the thickness parameter of the brick is obtained. The processing module is also used to perform contour dimension measurement processing based on the target brick point cloud dataset. By separating the point cloud of the double brick body and the point cloud on the ground reference surface and extracting the outer contour edge, and locating the key feature position in the outer contour edge, the contour dimension parameter of the brick is obtained. The processing module is also used to perform process adaptability correction processing based on the brick thickness parameter and the brick contour dimension parameter. The masonry process conditions are mapped to correction parameters so as to correct the brick thickness parameter and the brick contour dimension parameter through the correction parameters, and output the target dimension result for the assembly quality control of the steel ladle brick.

[0008] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method described above.

[0009] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing instructions that, when executed, perform the method described above.

[0010] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring 3D point cloud data covering both brick bodies and the ground reference surface in a single step, a unified spatial coordinate system was established, closely linking the spatial geometry of the bricks with the ground reference information. This avoided the instability of the reference caused by multiple measurements and improved measurement consistency. Key area clipping and candidate point cloud generation ensured that subsequent processing focused only on areas directly related to dimensional measurements, reducing redundant data and improving computational efficiency from the source. Simultaneously, key structures such as the edges and gaps of the bricks were preserved, guaranteeing measurement integrity. Multi-dimensional point cloud purification, through outlier removal and region clustering constrained by normal vectors, effectively eliminated interference from dust, impurities, and sensing errors, achieving a high-purity brick point cloud dataset. This provided a reliable data foundation for thickness and contour measurements, significantly improving measurement accuracy. Thickness parameter measurement eliminated the influence of brick placement deviations by modeling the upper surface of each brick and the ground reference surface separately, ensuring stable and reliable thickness measurements. Contour dimension measurement, through outer contour edge extraction and key feature localization, accurately acquired key dimensions such as the upper base, lower base, and trapezoidal height, forming a continuous and complementary data link between contour and thickness measurements. The process adaptability correction process combines the measured geometric dimensions with the masonry process conditions. By correcting parameters to adjust the thickness and contour dimensions, the output results directly meet the assembly requirements of steel-clad door bricks. This ensures that the measurement results are not only accurate but also adaptable to on-site assembly, enhancing the practical application value of the measurement method. Therefore, it facilitates the simultaneous acquisition of thickness and contour dimensions under complex on-site conditions, improving the accuracy of automatic measurement under different process assembly requirements. Attached Figure Description

[0011] Figure 1 A flowchart illustrating a method for measuring the dimensions of a steel-clad door brick, provided in an embodiment of this application; Figure 2 A schematic diagram of a steel-clad door brick size measurement system provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached figures: 21. Acquisition module; 22. Processing module; 31. Processor; 32. Communication bus; 33. User interface; 34. Network interface; 35. Memory. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0014] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0015] In the description of the embodiments of this 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. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0016] To address the aforementioned technical problems, this application provides a method for measuring the dimensions of steel-clad door bricks, referring to... Figure 1 , Figure 1 This is a flowchart illustrating a method for measuring the dimensions of a steel-clad door brick, provided in an embodiment of this application. The method is applied to a server and includes steps S110 to S160, as follows: S110. Acquire the three-dimensional point cloud data of the double-brick body placed on the ground reference surface according to the preset arrangement.

[0017] Specifically, a server refers to a computing device or system used for centralized management, processing, and storage of measurement data. Its main function is to coordinate the 3D vision acquisition device, store raw point cloud data, perform data preprocessing and subsequent measurement calculations, and output or transmit the results to the user terminal or control system. First, at the steel ladle site, a placement area for the two bricks to be measured is selected, and the two bricks are placed on the ground reference surface according to a preset typical placement method. The preset placement method refers to one or more brick arrangement methods selected based on construction experience and measurement requirements, ensuring that the two bricks are roughly parallel and the gaps are reasonably distributed, thereby guaranteeing that a single acquisition can cover the entire surface of the bricks and the surrounding ground, forming a unified spatial reference.

[0018] Subsequently, a high-precision 3D vision acquisition device, controlled by a server, scans the double-brick body and the ground reference surface. The 3D vision acquisition device consists of structured light, laser, or stereo vision sensors, and its function is to map the surface of the object into a dense point cloud. A point cloud is a set of several 3D coordinate points used to represent the spatial shape and positional relationships of an object, denoted as:

[0019] in They represent the first The coordinates of a point in three-dimensional space. This represents the total number of points collected. The point cloud simultaneously includes the upper surface of the brick, the gap between the two bricks, and ground reference points, providing a unified coordinate system for subsequent thickness and profile measurements.

[0020] To ensure data integrity and accuracy, the server controls the sensors to capture point cloud data in multi-angle or multi-line scanning modes during the acquisition process, and records the sensor pose information, i.e.: in Let the rotation matrix of the sensor in space be denoted as . This represents the sensor's position vector. By performing spatial transformation on the point cloud, the point clouds collected from different viewpoints are aligned in a unified coordinate system, forming a comprehensive point cloud dataset covering the double bricks and the surrounding ground.

[0021] After data acquisition, the server preprocesses the raw point cloud, including removing obvious outliers, interpolating missing regions, and filtering noise. Preprocessing can be achieved using Gaussian filtering, with the following formula:

[0022] in For the first The height value of the point after filtering. For the neighboring region The height value of the point, As weight, Controlling the influence of neighboring points on the smoothing result The distance is the spatial Euclidean distance. This step can suppress environmental interference points and measurement noise, thereby improving the quality of the point cloud.

[0023] Finally, the server stores the processed 3D point cloud data into a unified data structure for subsequent key area clipping, point cloud purification, thickness measurement, and contour dimension measurement, achieving closed-loop automation from data acquisition to measurement and analysis. Throughout the process, the "double brick body" refers to the two bricks to be measured, the ground reference plane is the plane used for thickness reference, and the unified coordinate system ensures consistency between thickness and contour measurements.

[0024] S120. Perform key region clipping processing on the three-dimensional point cloud data. By extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour of the two brick bodies, a key clipping region is generated. Candidate measurement point cloud data is generated based on the point cloud in the key clipping region.

[0025] Specifically, firstly, the acquired 3D point cloud data is subjected to voxelization and rasterization. Voxelization refers to dividing a continuous 3D space into fixed-size cubic units and grouping points falling within the same voxel together to reduce point cloud complexity and facilitate density statistics. In this scheme, the point cloud density within each voxel considers not only the number of points but also the local height variance and normal vector consistency of the point cloud to comprehensively reflect the spatial characteristics of that voxel. The density calculation formula is as follows:

[0026] in, Voxel representation The overall point cloud density, The number of points that fall into the voxel. Voxel volume For the first The height value of each point. The mean height of the point cloud within the voxel. The variance of the entire point cloud height. For the first Point normal vector The average direction of the normal vector within the voxel. and This formula adjusts the weighting coefficients for the influence of height variance and normal vector consistency. It comprehensively evaluates point density, local flatness, and surface orientation consistency, and is used to identify target density areas within the double-brick body and the gaps between the double bricks.

[0027] Subsequently, point cloud clustering and spatial connectivity analysis are performed within the target density point cloud region to extract the central axis of the gap between the two bricks. Point cloud clustering can employ a density clustering method combining weighted Euclidean distance and normal vector similarity. The clustering distance metric formula is as follows:

[0028] in, For point With point The overall spatial distance Let the coordinates of the point be a vector. For the corresponding normal vector, These are the normal vector weight coefficients, used to enhance the role of point cloud orientation consistency in clustering. This clustering method can form continuous clusters in the gap region between two bricks, from which the gap center axis can be extracted to guide the generation of key clipping regions.

[0029] Based on the prior information of the trapezoidal profile of the double-brick body, the central axis of the gap is extended along the direction of the trapezoidal boundary to form the critical clipping region. The trapezoidal profile prior is represented by a set of parameters:

[0030] in, The length of the upper base. The length of the lower base. The height is trapezoidal. The side tilt angle, The allowable deviation coefficient is used to adjust the envelope range of the clipping region. The critical clipping region is defined as a three-dimensional spatial envelope consistent with the central axis and trapezoidal prior parameters, retaining only the point cloud falling within this envelope.

[0031] Finally, the point cloud data falling within the key clipping area is retained to form candidate measurement point cloud data. This candidate measurement point cloud data contains only highly relevant points near the edges of the double bricks and the gaps, providing high-purity input for subsequent multi-dimensional point cloud purification and accurate measurement. Voxelization and comprehensive density calculation provide preliminary constraints for the target area, clustering and spatial connectivity analysis determine the central axis of the gap, trapezoidal contours generate the clipping boundary as a priori, and the clipped candidate point cloud is output, achieving continuous data refinement from the full point cloud to the measurement-related point cloud.

[0032] S130. Perform multi-dimensional point cloud purification processing on the candidate measurement point cloud data. By removing outliers based on local density changes and region clustering based on normal vector constraints, separate the effective surface point cloud and interference point cloud of the double brick body to obtain the target brick point cloud dataset.

[0033] Specifically, firstly, outlier removal based on local density variations is performed on the candidate measured point cloud data. Local density considers not only the number of neighboring points but also height variance, normal vector dispersion, and spatially weighted distance to comprehensively reflect the stability and reliability of points on the local surface. Let the points... The neighborhood of The formula for calculating its comprehensive local density is:

[0034] in, For point The overall local density, It is a spatial coordinate vector. For point Mean height within the neighborhood and This is an adjustment coefficient for distance and altitude. For point normal vectors, Reflects the consistency of the normal vector. Overall density. Below the preset threshold The points are marked as outliers and removed, thereby eliminating abnormal points caused by dust, impurities and sensing errors, and obtaining the point cloud after removing outliers.

[0035] Subsequently, region clustering based on normal vector consistency was performed on the point cloud after outlier removal. The local surface normal vector of each point was obtained from the covariance matrix of its neighboring points through principal component analysis. The calculation yielded:

[0036] in, Pick The eigenvector corresponding to the smallest eigenvalue represents the local plane normal vector. A weighted similarity matrix is ​​constructed based on normal vector consistency and spatial distance.

[0037] in, This is the distance attenuation coefficient. The larger the value, the more likely it is to be a point. and points The points are spatially close and have the same normal vector direction. Using spectral clustering or density clustering methods, the points are divided into multiple region clusters. Clusters with good continuity, consistent normal vectors, and high density are selected as the effective surface point cloud of the double-brick body, while other clusters are regarded as interference point clouds.

[0038] Ultimately, only the valid surface point clouds are retained to form the target brick point cloud dataset. The candidate measurement point clouds are derived from key region clipping, and local density removal reduces noise interference, providing stable input for normal vector consistency clustering. Clustering further distinguishes between valid surfaces and interference points, providing a high-purity, continuous target brick point cloud dataset for thickness and contour dimension measurement.

[0039] S140. Perform thickness parameter measurement processing based on the target brick point cloud dataset. By spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface, the thickness parameters of the brick are obtained.

[0040] Specifically, firstly, the point cloud of the upper surface of a single brick in the target brick point cloud dataset is separated from the point cloud of the ground reference surface. Separation refers to distinguishing the upper surface point cloud from the ground point cloud based on the height distribution characteristics and spatial connectivity of the point clouds. The specific method is based on the point cloud height values... Establish a threshold value based on the known brick thickness range:

[0041] in, For the first point cloud The coordinates of the points The upper limit of the ground reference plane height. The classification results, serving as the lower limit for the height of the brick's upper surface, are used to generate a subset of point clouds for the upper surface of a single brick and a point cloud for the ground reference surface. This step ensures that thickness measurements are based solely on actual brick surface points and reference ground points, improving measurement accuracy.

[0042] Subsequently, a plane fitting was performed on the point cloud on the upper surface of a single brick to establish a spatial model of the upper surface. Plane fitting refers to approximating the spatial distribution of the point cloud on the upper surface with a plane equation, usually using the least squares method. The fitting equation is as follows:

[0043] in, Let the coordinates of the point cloud on the upper surface of the brick be given. and Let be the tilt coefficient of the plane in the X and Y directions. Let be the plane intercept. This is achieved by minimizing the sum of the squared perpendicular distances from all points to the plane:

[0044] Solving for plane parameters This yields a spatial model of the upper surface. Plane fitting can eliminate the influence of minor noise in the point cloud, allowing thickness measurements to be based on the overall surface trend rather than the height of a single point.

[0045] A ground spatial model is established by performing a similar plane fitting on the ground reference surface point cloud. The ground model equations are also as follows:

[0046] in, The slope coefficient of the ground plane. The intercept is used. By minimizing the sum of squared vertical distances from the ground point cloud to the fitted plane, a stable ground reference surface model can be obtained, which can be used as a reference for thickness calculation.

[0047] Finally, based on the spatial height relationship between the upper surface space model and the ground space model, the thickness parameters of the door brick are calculated. Thickness calculation can be performed by finding the upper surface model and the ground model at the same location. Achieve average height difference:

[0048] in, For brick thickness parameters, This represents the number of point clouds on the upper surface. These are the position coordinates of the corresponding point in the X and Y planes. This step eliminates the influence of brick placement deviations on thickness measurement, yielding stable and reliable thickness parameters, and providing an accurate basis for subsequent contour measurement and process correction.

[0049] S150. Perform contour dimension measurement processing based on the target brick point cloud dataset. Separate the point cloud of the double brick body from the ground reference surface point cloud and extract the outer contour edge. Locate the key feature positions in the outer contour edge to obtain the contour dimension parameters of the door brick.

[0050] Specifically, firstly, the point cloud of the two bricks in the target brick point cloud dataset is separated from the point cloud of the ground reference surface. Separation refers to identifying points located within the height range of the upper surface of the brick as part of the two bricks' point cloud, and points below the ground reference height as part of the ground reference surface point cloud, based on point cloud height distribution and spatial connectivity. The points are The height threshold is The separation condition is:

[0051] in, The upper limit of the ground reference plane, This defines the lower boundary of the upper surface of the brick. This step ensures that the contour analysis is performed only on the point cloud of the two brick bodies, avoiding interference from ground points.

[0052] Subsequently, a two-dimensional projection is performed on the point cloud of the double-brick body to form a contour analysis plane. Two-dimensional projection refers to projecting the three-dimensional point cloud onto a horizontal or top-view plane, removing height information, and retaining only the XY plane coordinates for contour boundary extraction. The projection formula is:

[0053] in, These are the coordinates of the projected two-dimensional point. Two-dimensional projection makes the contour boundary features more prominent on the plane, facilitating subsequent edge enhancement processing.

[0054] Point cloud edge enhancement processing is performed on the contour analysis plane, and the candidate edge points are subjected to continuity constraints and structural optimization based on the trapezoidal contour prior to extract the outer contour edges. Edge enhancement processing increases the response value of edge points by calculating the point density gradient or edge response function in the neighborhood of each projected point, as shown in the following formula:

[0055] in, For point Edge response value, For local point cloud density, For density gradient, Let be the angle between the direction of the point's normal vector and the reference direction. This is a direction-weighted function. Combined with prior parameters of the trapezoidal profile:

[0056] in, These are the length of the upper base, the length of the lower base, and the height of the trapezoid. This is the tolerance coefficient used to generate constraint boundaries. Through continuity constraints and structural optimization, only edge points matching the trapezoidal prior are retained, forming the outer contour edge set.

[0057] Finally, key feature positions are located within the outer contour edge to obtain the positions of the upper and lower bottom boundaries and the corresponding trapezoidal height, thereby calculating the dimensions of the door brick contour. Key feature positions are determined by selecting extreme points or centerline points from the edge point set, as expressed by the formula:

[0058] in, Let X be the X coordinates of the upper and lower base edge points. This is the average Y-coordinate of the edge points of the upper and lower bases. This step yields precise contour dimensional parameters, providing a data foundation for subsequent process adaptability adjustments and assembly quality control.

[0059] S160. Based on the thickness parameters and outline dimensions of the cladding bricks, perform process adaptability correction processing, map the masonry process conditions into correction parameters, and correct the thickness parameters and outline dimensions of the cladding bricks through the correction parameters, outputting the target dimension results for the assembly quality control of the steel ladle cladding bricks.

[0060] Specifically, firstly, the dry-laying or wet-laying conditions are identified based on the on-site masonry process. Dry-laying conditions refer to the direct assembly of bricks without the use of mortar for joint filling; wet-laying conditions refer to the presence of a mortar layer during brick assembly, used to adjust joints and enhance sealing. The server or measurement system identifies the current masonry process type based on construction records or on-site settings and determines the necessary correction strategies, providing a process adaptation basis for thickness and profile dimension parameters.

[0061] Subsequently, the masonry process conditions were mapped to correction parameters. These correction parameters included thickness compensation values. and contour size adjustment value This is used to correct the deviation between the measured value and the actual assembly conditions. The thickness compensation value is used to account for the actual assembly gap and mortar thickness of the bricks under dry or wet laying conditions, and the contour dimension adjustment value is used to compensate for the dimensional deviation that may occur in the trapezoidal contour of the bricks during construction. Let the measured thickness parameter be... The contour dimension parameters are The corrected formula is:

[0062] , in, This is the target value after thickness parameter correction. The target value after contour size correction. and It is determined by the masonry process conditions and construction tolerances.

[0063] Finally, by applying correction parameters, the thickness and outline dimensions of the door bricks are transformed into target dimensions for quality control in the assembly of steel-clad door bricks. These target dimensions take into account both on-site masonry conditions and actual assembly requirements, directly guiding brick assembly. Throughout the process, the thickness and outline dimensions originate from previous measurement steps, while the correction parameters provide process adaptation, ensuring that the final target dimensions reflect both measurement accuracy and meet on-site assembly requirements.

[0064] In one possible implementation, an environmental factor is determined based on the correction parameters. This environmental factor includes the thermal expansion and contraction effect caused by temperature changes. The environmental factor is compensated when correcting the thickness parameters and contour dimensions of the door panel to improve the assembly adaptability and measurement accuracy of the target dimensions.

[0065] Specifically, firstly, environmental factors are determined based on the correction parameters. Environmental factors refer to external conditions that may affect the dimensions of the bricks during on-site measurement and assembly, the most important of which is the thermal expansion and contraction effect caused by temperature changes. Temperature changes cause the brick material to expand or contract slightly along its length, width, and thickness, thus affecting the measured thickness and profile dimensional parameters. The current ambient temperature is obtained through on-site temperature sensors or construction records, and combined with the linear expansion coefficient of the material, the estimated impact of environmental factors on the brick dimensions is calculated.

[0066] Subsequently, when calibrating the thickness and outline dimensions of the brickwork, environmental factors are compensated. Compensation involves adding the deviation caused by temperature changes to the measured values, thereby obtaining dimensional parameters that are closer to the actual assembly state. Specifically, the thickness and outline dimensions are adjusted based on the difference between the ambient temperature during measurement and the reference temperature to reflect the true dimensions of the brickwork at the assembly temperature.

[0067] Finally, by applying environmental factor-compensated thickness and profile dimension parameters, target dimensional results for quality control of steel-clad door brick assembly are output. These target dimensional results consider both the original measurements and the adjustments made to the masonry process and environmental factor compensation, thereby improving measurement accuracy and assembly adaptability. This allows the final results to be directly used for on-site assembly decisions and quality control. The entire process ensures the continuity of technical characteristics: measurement data provides the foundation, correction parameters provide process adaptation, and environmental factor compensation ensures that the dimensional results conform to actual construction conditions.

[0068] This application also provides a steel-clad door brick size measurement system, referring to... Figure 2 , Figure 2This is a schematic diagram of a steel-clad door brick size measurement system provided in an embodiment of this application. The system is a server, which includes an acquisition module 21 and a processing module 22. The acquisition module 21 is used to acquire three-dimensional point cloud data of two brick bodies placed on a ground reference surface according to a preset arrangement. The processing module 22 is used to perform key region clipping processing on the three-dimensional point cloud data. By extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour of the two brick bodies, a key clipping region is generated to generate candidate measurement point cloud data based on the point cloud in the key clipping region. The processing module 22 is also used to perform multi-dimensional point cloud purification processing on the candidate measurement point cloud data. By removing outliers based on local density changes and region clustering based on normal vector constraints, the effective surface point cloud of the two brick bodies is separated from the interference point cloud to obtain the target brick body point cloud. The cloud dataset; processing module 22 is also used to perform thickness parameter measurement processing based on the target brick point cloud dataset. By spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface, the thickness parameters of the brick are obtained. Processing module 22 is also used to perform contour dimension measurement processing based on the target brick point cloud dataset. By separating the point cloud of the double brick body and the point cloud on the ground reference surface and extracting the outer contour edge, and locating the key feature positions in the outer contour edge, the contour dimension parameters of the brick are obtained. Processing module 22 is also used to perform process adaptability correction processing based on the brick thickness parameters and the brick contour dimension parameters. The masonry process conditions are mapped to correction parameters so as to correct the brick thickness parameters and the brick contour dimension parameters through the correction parameters, and output the target dimension results for the assembly quality control of the steel ladle brick.

[0069] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0070] This application also provides an electronic device, with reference to... Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 31, at least one network interface 34, a user interface 33, a memory 35, and at least one communication bus 32.

[0071] The communication bus 32 is used to enable communication between these components.

[0072] The user interface 33 may include a display screen and a camera. Optionally, the user interface 33 may also include a standard wired interface and a wireless interface.

[0073] The network interface 34 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0074] The processor 31 may include one or more processing cores. The processor 31 connects to various parts of the server via various interfaces and lines, executing instructions, programs, code sets, or instruction sets stored in the memory 35, and calling data stored in the memory 35 to perform various server functions and process data. Optionally, the processor 31 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 31 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 31 and may be implemented as a separate chip.

[0075] The memory 35 may include random access memory (RAM) or read-only memory. Optionally, the memory 35 may include a non-transitory computer-readable storage medium. The memory 35 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 35 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 35 may also be at least one storage device located remotely from the aforementioned processor 31. Figure 3As shown, the memory 35, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for measuring the dimensions of steel-clad door bricks.

[0076] exist Figure 3 In the electronic device shown, the user interface 33 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 31 can be used to call an application program stored in the memory 35 for measuring the size of a steel-clad door brick. When executed by one or more processors, the electronic device performs one or more methods as described in the above embodiments.

[0077] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0078] This application also provides a non-transitory computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0079] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0081] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0082] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0083] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0084] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for measuring the dimensions of steel-clad door bricks, characterized in that, The method includes: Acquire 3D point cloud data of a double-brick body placed on a ground reference plane according to a preset arrangement; The three-dimensional point cloud data is subjected to key region clipping processing. The key clipping region is generated by extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour of the two brick bodies. Candidate measurement point cloud data is generated based on the point cloud in the key clipping region. Multi-dimensional point cloud purification processing is performed on the candidate measurement point cloud data. By removing outliers based on local density changes and region clustering based on normal vector constraints, the effective surface point cloud and interference point cloud of the double brick body are separated to obtain the target brick point cloud dataset. Based on the target brick point cloud dataset, thickness parameter measurement processing is performed. By spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface, the thickness parameters of the brick are obtained. Based on the target brick point cloud dataset, contour size measurement processing is performed. By separating the point cloud of the double brick body and the point cloud of the ground reference surface and extracting the outer contour edge, and locating the key feature positions in the outer contour edge, the contour size parameters of the door brick are obtained. Based on the thickness parameters and outline dimensions of the cladding bricks, a process adaptability correction process is performed, mapping the masonry process conditions into correction parameters. These correction parameters are then used to correct the thickness and outline dimensions of the cladding bricks, outputting target dimensions for quality control of the steel ladle cladding brick assembly.

2. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The critical region clipping process performed on the 3D point cloud data involves extracting the central axis of the gap between the two bricks and generating a critical clipping region by combining it with the prior trapezoidal contour of the two brick bodies. Candidate measurement point cloud data is then generated based on the point cloud within the critical clipping region. Specifically, this includes: The three-dimensional point cloud data is divided into voxel grids and the point cloud density in each grid is counted to identify the target density point cloud region within a preset range of the double brick body and the gap between the double bricks. Based on the target density point cloud region, the central axis of the gap between the two bricks is extracted through point cloud clustering and spatial connectivity analysis, and the key clipping region is generated by combining the prior information of the trapezoidal contour of the two brick bodies. Point clouds falling within the key clipping region are retained to form candidate measurement point cloud data.

3. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The process of performing multi-dimensional point cloud purification on the candidate measurement point cloud data involves separating the effective surface point cloud from the interfering point cloud of the double-brick body through outlier removal based on local density changes and region clustering based on normal vector constraints, to obtain the target brick point cloud dataset. Specifically, this includes: Outliers in the candidate measurement point cloud data are removed based on local density changes to eliminate abnormal points caused by dust, impurities, and sensing errors, resulting in a point cloud after outlier removal. By calculating the consistency of point cloud normal vectors, the point cloud after removing outliers is clustered into regions, separating the effective surface point cloud of the double brick body from the interfering point cloud, thus forming the target brick body point cloud dataset.

4. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The process of performing thickness parameter measurement processing based on the target brick point cloud dataset involves spatially modeling the point cloud of the upper surface of a single brick and the point cloud of the ground reference surface to obtain the thickness parameters of the brick. Specifically, this includes: Separate the point cloud of the upper surface of a single brick in the target brick point cloud dataset from the point cloud of the ground reference surface; Planar fitting is performed on the point cloud on the upper surface of the single door brick to establish a spatial model of the upper surface; Planar fitting is performed on the ground reference surface point cloud to establish a ground spatial model; Based on the spatial height relationship between the upper surface space model and the ground space model, the thickness parameter of the door brick is calculated.

5. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The process of performing contour size measurement based on the target brick point cloud dataset involves separating the point cloud of the double brick body from the ground reference surface point cloud, extracting the outer contour edge, and locating key feature positions within the outer contour edge to obtain the contour size parameters of the brickwork. Specifically, this includes: Separate the dual-brick body point cloud from the ground reference surface point cloud in the target brick point cloud dataset; The point cloud of the double-brick body is subjected to two-dimensional projection to form a contour analysis plane; Point cloud edge enhancement processing is performed on the contour analysis plane, and the candidate edge points are subjected to continuity constraints and structural optimization in combination with trapezoidal contour priors in order to extract the outer contour edge; Locate the key feature positions corresponding to the upper bottom boundary, lower bottom boundary, and trapezoidal height in the outer contour edge to obtain the contour dimension parameters of the door brick.

6. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The process adaptability correction process based on the thickness parameter and outline dimension parameter of the cladding brick is performed, mapping the masonry process conditions into correction parameters. These correction parameters are then used to correct the thickness and outline dimension parameters of the cladding brick, outputting target dimension results for quality control of the ladle cladding brick assembly. Specifically, this includes: Based on the on-site masonry process conditions, dry masonry conditions or wet masonry conditions are identified, and the masonry process conditions are mapped to correction parameters. The correction parameters include thickness compensation values ​​and contour size adjustment values, which are used to correct the thickness parameters and contour size parameters of the door brick. The correction parameters are used to convert the thickness parameter and the outline dimension parameter of the cladding brick into target dimension results for the assembly quality control of the steel ladle cladding brick.

7. The method for measuring the dimensions of steel-clad door bricks according to claim 1, characterized in that, The method further includes: Based on the correction parameters, environmental factors are determined, including the thermal expansion and contraction effect caused by temperature changes; When correcting the thickness parameter and the outline dimension parameter of the door panel, the environmental factors are compensated to improve the assembly adaptability and measurement accuracy of the target dimension result.

8. A system for measuring the dimensions of steel-clad door bricks, characterized in that, The system is used to perform the steel-clad door brick size measurement method as described in any one of claims 1 to 7, the system comprising an acquisition module and a processing module, wherein... The acquisition module is used to acquire three-dimensional point cloud data of a double-brick body placed on a ground reference surface in a preset arrangement. The processing module is used to perform key region clipping processing on the three-dimensional point cloud data. It generates a key clipping region by extracting the central axis of the gap between the two bricks and combining it with the trapezoidal contour of the two brick bodies, so as to generate candidate measurement point cloud data based on the point cloud in the key clipping region. The processing module is also used to perform multi-dimensional point cloud purification processing on the candidate measurement point cloud data. By removing outliers based on local density changes and region clustering based on normal vector constraints, the effective surface point cloud and interference point cloud of the double brick body are separated to obtain the target brick point cloud dataset. The processing module is also used to perform thickness parameter measurement processing based on the target brick point cloud dataset, and to obtain the thickness parameters of the brick by spatially modeling the point cloud on the upper surface of a single brick and the point cloud on the ground reference surface. The processing module is also used to perform contour size measurement processing based on the target brick point cloud dataset. By separating the double brick body point cloud and the ground reference surface point cloud and extracting the outer contour edge, and locating the key feature position in the outer contour edge, the contour size parameters of the door brick are obtained. The processing module is further configured to perform process adaptability correction processing based on the thickness parameter and the outline dimension parameter of the cladding brick, map the masonry process conditions into correction parameters, and correct the thickness parameter and the outline dimension parameter of the cladding brick through the correction parameters, and output the target dimension result for the assembly quality control of the steel ladle cladding brick.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 7.

Images