A real-time monitoring and optimization system for precise location of key demolition points

Abstract

This invention discloses a real-time monitoring and optimization system for precise positioning of key demolition points, specifically relating to the field of data processing technology. It addresses the spatial identification offset problem caused by misalignment in the mapping of multimodal sensing data structures. The system acquires multimodal sensing data collected by multiple sensors within the area to be demolished, performs registration processing based on spatial topology mapping rules, and constructs a structural mapping benchmark dataset. It then performs feature extraction and cluster analysis of structural nodes to obtain a candidate set of structural nodes. A node deviation coefficient matrix is ​​established based on the mapping deviation between different sensor coordinate systems, and the candidate structural nodes are spatially calibrated. Finally, based on the matching degree between the spatially calibrated candidate structural nodes and the structural features of preset key demolition nodes, the actual key demolition nodes in the area to be demolished are identified, achieving precise positioning and monitoring optimization of key demolition points in high-density structural environments.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a real-time monitoring and optimization system for precise positioning of key demolition points. Background Technology

[0002] In the dismantling of large industrial facilities such as oil refining plants, accurate identification of critical dismantling points is a core element in ensuring operational safety and efficiency. Existing technologies typically rely on multi-source sensing methods for spatial modeling and structural identification. However, because the data collected by various sensors are based on different reference coordinate systems, spatial registration errors exist. This is especially prone to structural mapping misalignment in environments with complex metal structures and dense nodes, leading to the misidentification of non-critical locations as dismantling targets.

[0003] Traditional spatial correction methods cannot effectively eliminate the cumulative effect of such micro-deviations, resulting in inaccurate positioning and a high risk of misjudgment in the demolition monitoring system, making it difficult to meet the actual needs of high-precision demolition operations.

[0004] To address the aforementioned problems, a technical solution is provided. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a real-time monitoring and optimization method and system for precise positioning of key demolition points to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A real-time monitoring and optimization system for precise positioning of key demolition points includes a data acquisition module, a mapping and registration module, a feature segmentation module, a deviation calculation module, a spatial calibration module, and a node identification module.

[0008] The data acquisition module acquires multimodal sensing data collected by multiple source sensors within the area to be demolished;

[0009] The mapping and registration module performs structural mapping and registration processing on the multimodal sensing data according to the spatial topology mapping rules, and establishes an initial structural mapping benchmark dataset;

[0010] The feature segmentation module performs local structural feature segmentation based on the initial structural mapping benchmark dataset, extracts the multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and groups and clusters the multi-dimensional structural feature vectors corresponding to each structural node to obtain a candidate set of structural nodes.

[0011] The deviation calculation module calculates the structural mapping deviation value of each candidate structural node in different sensor coordinate systems based on the spatial positional relationship and neighborhood topology relationship of each candidate structural node in the candidate structural node set, and establishes a node deviation coefficient matrix based on the structural mapping deviation value.

[0012] The spatial calibration module performs spatial calibration on each candidate structure node based on the node deviation coefficient matrix.

[0013] The node identification module identifies the actual key demolition nodes in the area to be demolished based on the matching degree between the structural features of the candidate structural nodes after spatial calibration and the preset key demolition nodes.

[0014] In a preferred embodiment, acquiring multimodal sensing data collected by multiple source sensors within the area to be demolished specifically involves:

[0015] Deploy laser scanning sensors, image acquisition sensors, and structural stress sensors in the area to be demolished;

[0016] The spatial geometric information of facilities and equipment in the area to be demolished is collected using laser scanning sensors to obtain spatial geometric point cloud data;

[0017] Image acquisition sensors are used to acquire surface visual image information of facilities and equipment in the area to be demolished, and image texture data is obtained.

[0018] Structural stress sensors are used to collect real-time information on the structural physical state of facilities and equipment in the area to be demolished, thereby obtaining structural stress data;

[0019] Spatial geometric point cloud data, image texture data, and structural stress data are processed in time synchronization to form multimodal sensing data.

[0020] In a preferred embodiment, the multimodal sensing data is subjected to structure mapping registration processing according to spatial topology mapping rules to establish an initial structure mapping benchmark dataset, specifically as follows:

[0021] Based on a unified spatial coordinate reference framework, spatial geometric point cloud data and image texture data are aligned and mapped using spatial coordinates to form fused geometric image data.

[0022] The structural stress data and the fused geometric image data are correlated and mapped according to the spatial topology information of the facilities and equipment to form spatial topology features.

[0023] Based on geometric image data and spatial topological features, an initial structural mapping benchmark dataset is established, which includes spatial location features, visual texture features, and structural stress features.

[0024] In a preferred embodiment, local structural feature segmentation is performed based on the initial structural mapping benchmark dataset. Multidimensional structural feature vectors corresponding to each structural node within the demolition area are extracted, and these multidimensional structural feature vectors are grouped and clustered to obtain a candidate set of structural nodes. Specifically:

[0025] The initial structure mapping benchmark dataset is divided into local regions to obtain multiple local structural units.

[0026] Extract the spatial coordinates, surface visual texture features, and structural stress features of the facilities and equipment within each local structural unit, and construct a multi-dimensional structural feature vector for each structural node.

[0027] The multidimensional structural feature vectors corresponding to each structural node are grouped according to spatial topological similarity to obtain a candidate set of structural nodes.

[0028] In a preferred embodiment, based on the spatial positional relationships and neighborhood topological relationships of each candidate structural node in the candidate structural node set, the structural mapping deviation value of each candidate structural node in different sensor coordinate systems is calculated, and a node deviation coefficient matrix is ​​established based on the structural mapping deviation value, specifically:

[0029] Based on the spatial topological relationship of each candidate structural node in the candidate set of structural nodes, the spatial position deviation value of each candidate structural node between the laser scanning sensor coordinate system and the image acquisition sensor coordinate system is calculated respectively.

[0030] Calculate the spatial position deviation of each candidate structural node between the laser scanning sensor coordinate system and the structural stress sensor coordinate system;

[0031] The spatial position deviation values ​​of each candidate structural node calculated between different coordinate systems are arranged according to the candidate structural node number to form a node deviation coefficient matrix.

[0032] In a preferred embodiment, spatial calibration is performed on each candidate structure node based on the node deviation coefficient matrix, specifically as follows:

[0033] Based on the spatial position deviation values ​​of each candidate structural node in the node deviation coefficient matrix, determine the spatial calibration vector corresponding to each candidate structural node;

[0034] A spatial coordinate compensation method is adopted to apply the spatial calibration vector to the spatial coordinate data corresponding to each candidate structure node, thereby correcting the spatial position of each candidate structure node in the initial structure mapping benchmark dataset.

[0035] Update the spatial location data of all candidate structural nodes in the candidate structural node set to obtain the spatially calibrated candidate structural node set.

[0036] In a preferred embodiment, the actual key demolition point locations in the area to be demolished are identified based on the matching degree between the spatially calibrated candidate structural nodes and the preset key demolition node structural feature benchmarks. Specifically:

[0037] Pre-establish standard values ​​for the spatial location characteristics, surface visual texture characteristics, and structural stress characteristics of key demolition nodes in the area to be demolished, forming a pre-set structural characteristic benchmark for key demolition nodes;

[0038] Calculate the feature difference value between each candidate structural node in the spatially calibrated candidate set and the preset key demolition node structural feature benchmark;

[0039] Based on the feature difference values, calculate the feature matching degree between each candidate structural node and the preset key demolition node structural feature benchmark;

[0040] Candidate structural nodes whose feature matching degree reaches a preset threshold are selected based on feature matching degree, and marked as actual key demolition nodes after spatial location calibration, thereby generating accurate spatial location information of the actual key demolition nodes.

[0041] The technical effects and advantages of the real-time monitoring and optimization system for precise positioning of key demolition points according to the present invention are as follows:

[0042] By constructing spatial topology mapping rules, multimodal data such as laser point clouds, image textures, and structural stress are fused and registered under a unified spatial framework, avoiding recognition deviations caused by inconsistencies in coordinate systems. Combining multidimensional structural feature extraction and candidate node clustering improves the efficiency of extracting key nodes in complex structures. Introducing a node deviation coefficient matrix and spatial calibration mechanism effectively suppresses the cumulative error of microstructure misalignment. Finally, by matching the structural features with preset key demolition nodes, accurate identification and spatial location calibration of actual key demolition nodes are achieved. It has good scalability and practicality, and is suitable for demolition scenarios such as high-density, complex-structured oil refining units. While improving demolition safety, it reduces human identification errors and significantly improves the overall intelligence level of operations and engineering execution efficiency. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the structure of a real-time monitoring and optimization system for precise positioning of key demolition points according to the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0045] Example

[0046] Figure 1 This invention presents a real-time monitoring and optimization system for precise positioning of key demolition points, comprising a data acquisition module, a mapping and registration module, a feature segmentation module, a deviation calculation module, a spatial calibration module, and a node identification module;

[0047] The data acquisition module acquires multimodal sensing data collected by multiple source sensors within the area to be demolished;

[0048] The mapping and registration module performs structural mapping and registration processing on the multimodal sensing data according to the spatial topology mapping rules, and establishes an initial structural mapping benchmark dataset;

[0049] The feature segmentation module performs local structural feature segmentation based on the initial structural mapping benchmark dataset, extracts the multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and groups and clusters the multi-dimensional structural feature vectors corresponding to each structural node to obtain a candidate set of structural nodes.

[0050] The deviation calculation module calculates the structural mapping deviation value of each candidate structural node in different sensor coordinate systems based on the spatial positional relationship and neighborhood topology relationship of each candidate structural node in the candidate structural node set, and establishes a node deviation coefficient matrix based on the structural mapping deviation value.

[0051] The spatial calibration module performs spatial calibration on each candidate structure node based on the node deviation coefficient matrix.

[0052] The node identification module identifies the actual key demolition nodes in the area to be demolished based on the matching degree between the structural features of the candidate structural nodes after spatial calibration and the preset key demolition nodes.

[0053] Specifically, acquiring multimodal sensing data collected by multiple sources of sensors within the area to be demolished includes:

[0054] Deploy laser scanning sensors, image acquisition sensors, and structural stress sensors in the area to be demolished;

[0055] Specifically, to ensure comprehensive information is obtained within the target area, three types of sensors with different functions are deployed in the area to be demolished. For example, laser scanning sensors are installed at different locations within an oil refinery to capture the building's shape, equipment outlines, and structural boundaries; high-definition image acquisition sensors are installed to capture detailed textures, such as metal surfaces and oil stains; in addition, structural stress sensors are installed to monitor the stress response of the equipment under external forces. This allows for the acquisition of multimodal data including spatial geometry, visual texture, and structural stress.

[0056] The spatial geometric information of facilities and equipment in the area to be demolished is collected using laser scanning sensors to obtain spatial geometric point cloud data;

[0057] Specifically, laser scanning sensors primarily utilize the principle of laser beam ranging to collect three-dimensional point cloud data of the surfaces of buildings and equipment. For example, when a laser scanning sensor measures a section of pipe, it obtains tens of thousands of three-dimensional coordinate data representing various points on the pipe's surface. This three-dimensional coordinate data is called spatial geometric point cloud data.

[0058] Image acquisition sensors are used to acquire surface visual image information of facilities and equipment in the area to be demolished, and image texture data is obtained.

[0059] Specifically, image acquisition sensors capture high-resolution images using cameras, collecting color and texture information about the exterior of buildings and equipment. For example, images of scratches or damage on equipment casings can be captured to form image texture data.

[0060] Structural stress sensors are used to collect real-time information on the structural physical state of facilities and equipment in the area to be demolished, thereby obtaining structural stress data;

[0061] Specifically, structural stress sensors use strain gauges to monitor stress and strain changes inside or on the surface of buildings and facilities in real time. For example, at joints, slight deformations may occur due to external forces, and the values ​​provided by the structural stress sensor are the structural stress data.

[0062] Spatial geometric point cloud data, image texture data, and structural stress data are processed in time synchronization to form multimodal sensing data;

[0063] Specifically, time synchronization processing requires correcting data from different sensors to a unified timestamp. For example, during data acquisition, it's essential to ensure that laser point clouds, images, and stress data all originate from data collected at the same time or within the same time interval, facilitating data fusion. After time correction, multimodal sensing data is obtained.

[0064] Specifically, based on spatial topology mapping rules, structural mapping registration is performed on multimodal sensing data to establish an initial structural mapping benchmark dataset, including:

[0065] Based on a unified spatial coordinate reference framework, spatial geometric point cloud data and image texture data are aligned and mapped using spatial coordinates to form fused geometric image data.

[0066] Specifically, the spatial geometric point cloud data acquired by the laser scanning sensor and the image texture data acquired by the image acquisition sensor are mapped to the same spatial coordinate system, and the spatial geometric point cloud data and image texture data are aligned through coordinate transformation. By using a unified reference coordinate system for the spatial geometric point cloud data and image texture data, they can be accurately matched in space, thereby forming fused data that includes geometric shapes and visual details.

[0067] The structural stress data and the fused geometric image data are correlated and mapped according to the spatial topology information of the facilities and equipment to form spatial topology features.

[0068] Specifically, based on the physical structural characteristics of the facilities and equipment, structural stress data is mapped to corresponding areas of geometric image data. For example, if a steel beam has a clear outline in the geometric image data, the corresponding stress value is associated within the outline area. The steel beam area is marked in the mapped image, and the real-time stress data of the steel beam from the stress sensor is simultaneously projected onto the steel beam area, forming a spatial topological feature that includes both shape and stress information.

[0069] Based on geometric image data and spatial topological features, an initial structural mapping benchmark dataset is established, which includes spatial location features, visual texture features, and structural stress features.

[0070] Specifically, the processing results of geometric image data and spatial topological features are integrated to construct a dataset. Each data unit in the dataset contains three levels of information:

[0071] Spatial location characteristics (including the three-dimensional coordinate information of facilities and equipment)

[0072] Visual texture features (image or color texture information of the surface of facilities and equipment)

[0073] Structural stress characteristics (stress values ​​or stress state data of facilities and equipment).

[0074] Specifically, based on the initial structure mapping benchmark dataset, local structure feature segmentation is performed to extract multi-dimensional structure feature vectors corresponding to each structure node within the demolition area. These multi-dimensional structure feature vectors are then grouped and clustered to obtain a candidate set of structure nodes, including:

[0075] The initial structure mapping benchmark dataset is divided into local regions to obtain multiple local structural units.

[0076] Specifically, using a spatial partitioning method, the entire initial structure mapping benchmark dataset is divided into several independent local regions. Each local region is a local structural unit, representing a portion of the area to be demolished that has similar location and structural features.

[0077] For example, in an oil refinery to be demolished, it can be divided into multiple small regions using a grid partitioning method or a density-based clustering method. The point cloud data, image data, and stress data in each region constitute a local structural unit.

[0078] Extract the spatial coordinates, surface visual texture features, and structural stress features of the facilities and equipment within each local structural unit, and construct a multi-dimensional structural feature vector for each structural node.

[0079] Specifically, for each local structural unit: the spatial coordinate position is represented by three-dimensional coordinates, the surface visual texture features are represented by image feature descriptors, and the structural stress features are represented by stress values.

[0080] The three features extracted from each local structural unit are combined into a composite vector. The composite vector represents the features of a structural node. The combination can be achieved by concatenating vectors, arranging the spatial coordinates, image feature descriptors, and stress values ​​in sequence.

[0081] The multidimensional structural feature vectors corresponding to each structural node are grouped according to spatial topological similarity to obtain a candidate set of structural nodes;

[0082] Specifically, a grouping clustering algorithm, such as K-means clustering or hierarchical clustering, is applied to the feature vectors of all structural nodes to evaluate the similarity between feature vectors. Similarity evaluation can use Euclidean distance or cosine similarity. For example, if the Euclidean distance between the feature vectors of two structural nodes is less than a preset distance threshold, the structural nodes are considered similar and can be grouped into the same group. The final grouping results of the structural nodes form a candidate set, where each element is a candidate structural node.

[0083] Specifically, based on the spatial positional relationships and neighborhood topological relationships of each candidate structural node in the candidate structural node set, the structural mapping deviation value of each candidate structural node in different sensor coordinate systems is calculated. A node deviation coefficient matrix is ​​then established based on the structural mapping deviation value, including:

[0084] Based on the spatial topological relationship of each candidate structural node in the candidate set of structural nodes, the spatial position deviation value of each candidate structural node between the laser scanning sensor coordinate system and the image acquisition sensor coordinate system is calculated respectively.

[0085] Specifically, each candidate structural node already possesses its spatial position data prior to calibration. However, due to differences in the measurement methods of various sensors, displacement errors may exist. For instance, a laser scanning sensor may provide three-dimensional coordinates with millimeter-level accuracy, while an image acquisition sensor will introduce certain errors when converting to three-dimensional coordinates. Therefore, it is necessary to calculate the coordinate deviation of the same candidate structural node in the laser scanning coordinate system and the image acquisition coordinate system.

[0086] First, calculate the difference between each coordinate component in the three-dimensional coordinates obtained by the laser scanning sensor and the corresponding coordinate components after conversion by the image acquisition sensor. Then, sum the squares of these differences respectively, and finally take the square root of the sum to obtain the Euclidean distance between the two sets of coordinates, which is the deviation value of the spatial position.

[0087] Calculate the spatial position deviation of each candidate structural node between the laser scanning sensor coordinate system and the structural stress sensor coordinate system;

[0088] Specifically, for each candidate structure node, two sets of deviation values ​​are calculated:

[0089] One set represents the deviation between the laser scanning sensor and the image acquisition sensor;

[0090] The other group is the deviation between the laser scanning sensor and the structural stress sensor.

[0091] If D1 represents the first set of deviations and D2 represents the second set of deviations, these two sets of values ​​reflect the displacement consistency of the same candidate structural node across different sensor systems.

[0092] The spatial position deviation values ​​of each candidate structural node calculated between different coordinate systems are arranged according to the structural node number to form a node deviation coefficient matrix.

[0093] Specifically, the deviation values ​​calculated for each candidate structural node between different sensors are organized into a matrix, where the rows of the matrix correspond to different candidate structural nodes, and the columns of the matrix correspond to the spatial position deviation values ​​between different sensors.

[0094] Specifically, spatial calibration is performed on each candidate structure node based on the node deviation coefficient matrix, including:

[0095] Based on the spatial position deviation values ​​of each candidate structural node in the node deviation coefficient matrix, determine the spatial calibration vector corresponding to each candidate structural node;

[0096] Specifically, based on the node deviation coefficient matrix, each structural node has a set of spatial position deviation values. A calibration vector can be calculated for each structural node to correct its spatial coordinates. The calibration vector can generally be calculated using the average deviation value. For example, for a certain node, if the deviations in the two sensors are C1 and C2 respectively, then the calibration vector V can be defined as: V = (C1, C2) / 2; where V represents the calibration vector.

[0097] A spatial coordinate compensation method is adopted to apply the spatial calibration vector to the spatial coordinate data corresponding to each candidate structure node, thereby correcting the spatial position of each candidate structure node in the initial structure mapping benchmark dataset.

[0098] Specifically, a spatial coordinate compensation method is used to add the calculated calibration vector to the spatial coordinates of the original candidate structure nodes, ensuring that the positions of all candidate structure nodes are more accurate after the fusion of data from different sensors.

[0099] Update the spatial location data of all candidate structural nodes in the candidate structural node set to obtain the spatially calibrated candidate structural node set.

[0100] Specifically, a correction operation is performed on each candidate structural node in the candidate structural node set. The updated candidate structural node set is the spatially calibrated candidate structural node set, which provides accurate spatial positioning data for feature matching.

[0101] Specifically, based on the matching degree between the structural features of the spatially calibrated candidate structural nodes and the preset key demolition nodes, the actual key demolition nodes in the area to be demolished are identified, including:

[0102] Pre-establish standard values ​​for the spatial location characteristics, surface visual texture characteristics, and structural stress characteristics of key demolition nodes in the area to be demolished, forming a pre-set structural characteristic benchmark for key demolition nodes;

[0103] Specifically, the pre-defined key demolition nodes are important demolition targets identified in advance based on design drawings, engineering requirements, or professional judgment, and consist of three parts:

[0104] Spatial location characteristics (e.g., ideal three-dimensional coordinates or geometric distribution)

[0105] Surface visual texture features (e.g., standard image descriptors, color, and texture information)

[0106] Structural stress characteristics (e.g., standard stress levels or mechanical parameters).

[0107] These standard values, when combined, constitute the pre-defined key demolition node structural feature benchmarks.

[0108] Calculate the feature difference value between each candidate structural node in the spatially calibrated candidate set and the preset key demolition node structural feature benchmark;

[0109] Specifically, the difference between the spatial coordinates of the candidate structural nodes after spatial calibration and the standard spatial coordinates of the preset key demolition nodes is calculated in each dimension. Then, the differences in each of these three dimensions are squared. Finally, the square root of this sum is applied, and the result is the difference value of the spatial position feature. This value is used to measure the degree of positional offset between the candidate structural nodes and the preset key demolition nodes in three-dimensional space.

[0110] The visual texture features of candidate structural nodes are converted into a texture feature set consisting of multiple numerical dimensions; similarly, the visual texture standard features of the preset key demolition nodes are also converted into a feature set of the same type. The cosine similarity between the two feature sets is calculated, which is the difference value of the visual texture features and is used to measure the degree of matching between the two candidate structural nodes in terms of appearance texture information.

[0111] Obtain the stress response values ​​of candidate structural nodes and the standard values ​​of stress characteristics of preset key demolition nodes during the monitoring process; calculate the absolute value of the difference between the stress response value and the standard value of stress characteristics, which is the difference value of structural stress characteristics, used to reflect the degree of deviation between the actual stress state and the design reference.

[0112] The total feature difference value is obtained by weighting and summing the differences according to their respective importance.

[0113] Based on the feature difference values, calculate the feature matching degree between each candidate structural node and the preset key demolition node structural feature benchmark;

[0114] Specifically, the matching degree is calculated using the formula: Matching Degree = 1 - (Total Feature Difference Value / Maximum Allowable Feature Difference Value). The maximum allowable feature difference value is a pre-set limit. When the matching degree is close to 1, it indicates that the candidate node is more similar to the preset key demolition node.

[0115] Candidate structural nodes whose feature matching degree reaches a preset threshold are selected based on feature matching degree, and marked as actual key demolition nodes after spatial location calibration, thereby generating accurate spatial location information of actual key demolition nodes.

[0116] Specifically, based on the preset threshold, candidate structural nodes that meet the requirements are selected and identified as actual key demolition nodes. The accurate three-dimensional spatial coordinates and related monitoring information of the actual key demolition nodes are output to support the precise execution of demolition operations.

[0117] The preset threshold is set based on the statistical distribution of the matching degree of the key node identification results in historical demolition projects. By calculating the matching degree of multiple confirmed key demolition nodes and their corresponding preset structural features, the matching degree distribution range is obtained. Combined with the manual annotation results, the lower limit of the matching degree is analyzed to determine a minimum matching degree value that can stably distinguish between key nodes and non-key nodes.

[0118] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0119] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0120] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0123] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0125] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium 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 described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0127] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A real-time monitoring and optimization system for precise positioning of critical demolition points, characterized in that, The data acquisition module, the mapping registration module, the feature segmentation module, the deviation calculation module, the spatial calibration module, and the node identification module are included. The data acquisition module acquires multi-modal perception data collected by multiple sensors in the area to be demolished, specifically as follows: Laser scanning sensors, image acquisition sensors, and structural stress sensors are deployed within the area to be demolished. The laser scanning sensors are used to collect spatial geometric information of facilities and equipment in the area to be demolished, obtaining spatial geometric point cloud data. The image acquisition sensors are used to acquire surface visual image information of facilities and equipment in the area to be demolished, obtaining image texture data. The structural stress sensors are used to collect real-time structural physical state information of facilities and equipment in the area to be demolished, obtaining structural stress data. The spatial geometric point cloud data, the image texture data, and the structural stress data are time-synchronized to form multi-modal perception data. The mapping registration module performs structural mapping registration processing on the multi-modal perception data according to spatial topological mapping rules, establishing an initial structural mapping reference dataset, specifically as follows: Based on a unified spatial coordinate reference framework, the spatial geometric point cloud data and the image texture data are aligned and mapped in spatial coordinates to form fused geometric image data. The structural stress data and the fused geometric image data are associated and mapped according to the spatial topological structure information of the facilities and equipment, forming spatial topological structure features. Based on the geometric image data and the spatial topological structure features, an initial structural mapping reference dataset containing spatial position features, visual texture features, and structural stress features is established. The feature segmentation module performs local structural feature segmentation based on the initial structural mapping reference dataset, extracts multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and groups and clusters the multi-dimensional structural feature vectors corresponding to each structural node to obtain a candidate set of structural nodes. The deviation calculation module calculates the structural mapping deviation values of each candidate structural node in different sensor coordinate systems based on the spatial position relationship and neighborhood topological relationship of each candidate structural node in the candidate set of structural nodes, and establishes a node deviation coefficient matrix based on the structural mapping deviation values. The spatial calibration module performs spatial calibration on each candidate structural node based on the node deviation coefficient matrix. The node identification module identifies the actual key demolition nodes of the area to be demolished based on the matching degree between the spatially calibrated candidate structural nodes and the structural features of the preset key demolition nodes.

2. The real-time monitoring and optimization system for precise positioning of key demolition points according to claim 1, characterized in that, The feature segmentation module performs local structural feature segmentation based on the initial structural mapping reference dataset, extracts multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and groups and clusters the multi-dimensional structural feature vectors corresponding to each structural node to obtain a candidate set of structural nodes, specifically as follows: The initial structural mapping reference dataset is divided into multiple local structural units. The spatial coordinate positions, surface visual texture features, and structural stress features of the facilities and equipment in each local structural unit are extracted to construct multi-dimensional structural feature vectors corresponding to each structural node. The multi-dimensional structural feature vectors corresponding to each structural node are grouped according to spatial topological similarity to obtain a candidate set of structural nodes.

3. The real-time monitoring and optimization system for precise positioning of a key removal point according to claim 2, wherein, Based on the spatial position relationship and neighborhood topological relationship of each candidate structural node in the candidate structural node set, the structural mapping deviation values of each candidate structural node in different sensor coordinate systems are calculated, and a node deviation coefficient matrix is established according to the structural mapping deviation values, specifically: Based on the spatial topological relationship of each candidate structural node in the candidate structural node set, the spatial position deviation values of each candidate structural node between the laser scanning sensor coordinate system and the image acquisition sensor coordinate system are calculated respectively; The spatial position deviation values of each candidate structural node between the laser scanning sensor coordinate system and the structural stress sensor coordinate system are calculated respectively; The spatial position deviation values of each candidate structural node calculated between different coordinate systems are arranged according to the serial number of the candidate structural node to form a node deviation coefficient matrix.

4. The real-time monitoring and optimization system for precise positioning of a key removal point according to claim 3, wherein, According to the node deviation coefficient matrix, the spatial calibration of each candidate structural node is carried out, specifically: Based on the spatial position deviation values of each candidate structural node in the node deviation coefficient matrix, the spatial calibration vector corresponding to each candidate structural node is determined; The spatial coordinate compensation method is used to apply the spatial calibration vector to the spatial coordinate data corresponding to each candidate structural node to correct the spatial position of each candidate structural node in the initial structural mapping reference data set; The spatial position data of all candidate structural nodes in the candidate structural node set is updated to obtain the spatial position calibrated candidate structural node set.

5. The real-time monitoring and optimization system for precise positioning of a key removal point according to claim 4, wherein, Based on the matching degree between the spatial calibrated candidate structural node and the structural features of the preset key demolition node, the actual key demolition node of the region to be demolished is identified, specifically: The spatial position feature, surface visual texture feature and structural stress feature standard value of the key demolition node in the region to be demolished are established in advance to form a preset key demolition node structural feature reference; The feature difference values between each candidate structural node in the spatial calibrated candidate structural node set and the preset key demolition node structural feature reference are calculated respectively; According to the feature difference values, the feature matching degrees between each candidate structural node and the preset key demolition node structural feature reference are calculated; According to the feature matching degree, the candidate structural node whose feature matching degree reaches the preset threshold is screened out and marked as the actual key demolition node after spatial position calibration to generate the accurate spatial position information of the actual key demolition node.

Images