Real-time monitoring optimization system for accurate positioning of key demolition point

Abstract

The invention discloses a real-time monitoring optimization system for accurate positioning of a key dismantling point, particularly relates to the technical field of data processing, and is used for solving the problem of space identification offset caused by mapping dislocation of a multi-modal sensing data structure. The method comprises the following steps: acquiring multi-modal sensing data acquired by a multi-source sensor in a to-be-dismantled area, performing registration processing according to a spatial topology mapping rule, and constructing a structure mapping reference data set; feature extraction and clustering analysis of the structure nodes are carried out to obtain a structure node candidate set; establishing a node deviation coefficient matrix based on the mapping deviation between different sensor coordinate systems, and performing spatial calibration on candidate structure nodes; and finally, based on the matching degree between the structural features of the candidate structural nodes after space calibration and the preset key demolition nodes, identifying the actual key demolition nodes of the to-be-demolited area, and realizing accurate positioning and monitoring optimization of the key demolition points in the high-density structural environment.

Description

Technical Field

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

[0002] During the demolition process of large industrial facilities such as oil refining, accurately identifying key demolition points is the core link to ensure operation safety and efficiency. In the prior art, multi-source sensing means are usually relied on for spatial modeling and structure recognition. However, due to the fact that the data collected by various sensors is based on different reference coordinate systems, there are spatial registration errors. Especially in an environment with complex metal structures and dense nodes, structural mapping misalignment is likely to occur, resulting in misidentifying non-key positions as demolition targets.

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

[0004] To solve the above problems, a technical solution is provided now. Summary of the Invention

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

[0006] To achieve the above object, the present invention provides the following technical solutions:

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

[0008] The data acquisition module acquires multi-modal perception data collected by multi-source sensors within the area to be demolished;

[0009] The mapping registration module performs structural mapping registration processing on the multi-modal perception data according to the spatial topology mapping rules to establish an initial structural mapping reference data set;

[0010] The feature segmentation module performs local structural feature segmentation based on the initial structural mapping reference data set, extracts multi-dimensional structural feature vectors corresponding to each structural node within 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 values of each candidate structural node in different sensor coordinate systems based on the spatial position relationship and neighborhood topological relationship of the candidate structural nodes in the structural node candidate set, and establishes a node deviation coefficient matrix according to the structural mapping deviation values;

[0012] The spatial calibration module performs spatial calibration on each candidate structural node according to the node deviation coefficient matrix;

[0013] The node recognition module identifies the actual key demolition nodes in the area to be demolished based on the matching degree between the spatially calibrated candidate structural nodes and the structural characteristics of the preset key demolition nodes.

[0014] In a preferred embodiment, multi-modal perception data collected by multi-source sensors in the area to be demolished is obtained, specifically:

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

[0016] Use the laser scanning sensor to collect the spatial geometric information of the facilities and equipment in the area to be demolished to obtain spatial geometric point cloud data;

[0017] Use the image acquisition sensor to obtain the surface visual image information of the facilities and equipment in the area to be demolished to obtain image texture data;

[0018] Use the structural stress sensor to collect the structural physical state information of the facilities and equipment in the area to be demolished in real time to obtain structural stress data;

[0019] Perform time synchronization processing on the spatial geometric point cloud data, image texture data and structural stress data to form multi-modal perception data.

[0020] In a preferred embodiment, according to the spatial topology mapping rules, perform structural mapping registration processing on the multi-modal perception data to establish an initial structural mapping reference data set, specifically:

[0021] Based on a unified spatial coordinate reference framework, perform alignment mapping processing of spatial coordinates on the spatial geometric point cloud data and the image texture data to form fused geometric image data;

[0022] Correlate and map the structural stress data with the fused geometric image data according to the spatial topology structure information of the facilities and equipment to form spatial topology structure features;

[0023] Based on the geometric image data and the spatial topology structure features, establish an initial structural mapping reference data set including spatial position features, visual texture features and structural stress features.

[0024] In a preferred embodiment, local structural feature segmentation is performed based on the initial structure mapping reference dataset, multi-dimensional structural feature vectors corresponding to each structural node in the demolition area are extracted, and the multi-dimensional structural feature vectors corresponding to each structural node are grouped and clustered to obtain a candidate set of structural nodes, specifically as follows:

[0025] Perform local area division processing on the initial structure mapping reference dataset to obtain multiple local structural units;

[0026] Extract the spatial coordinate positions, surface visual texture features, and structural stress features corresponding to the facilities and equipment in each local structural unit, and construct multi-dimensional structural feature vectors corresponding to each structural node;

[0027] Group the multi-dimensional structural feature vectors corresponding to each structural node according to spatial topological similarity to obtain a candidate set of structural nodes.

[0028] In a preferred embodiment, based on the spatial position relationship and neighborhood topological relationship of each candidate structural node in the candidate set of structural nodes, calculate the structural mapping deviation values of each candidate structural node in different sensor coordinate systems, and establish a node deviation coefficient matrix according to the structural mapping deviation values, specifically as follows:

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

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

[0031] Arrange the spatial position deviation values of each candidate structural node calculated between different coordinate systems in the order of the serial numbers of the candidate structural nodes to form a node deviation coefficient matrix.

[0032] In a preferred embodiment, perform spatial calibration on each candidate structural node according to 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] Adopt the spatial coordinate compensation method to apply the spatial calibration vector to the spatial coordinate data corresponding to each candidate structural node, and correct the spatial position of each candidate structural node in the initial structure mapping reference dataset;

[0035] Update the spatial position data of all candidate structural nodes in the candidate set of structural nodes to obtain a candidate set of structural nodes with calibrated spatial positions.

[0036] In a preferred embodiment, based on the matching degree between the candidate structural nodes after spatial calibration and the preset structural feature benchmark of the key demolition nodes, the actual key demolition point positions in the area to be demolished are identified. Specifically:

[0037] Pre-establish the standard values of the spatial position features, surface visual texture features, and structural stress features of the key demolition nodes in the area to be demolished, and form a preset structural feature benchmark of the key demolition nodes;

[0038] Calculate the feature difference values between each candidate structural node in the candidate set of structural nodes after spatial calibration and the preset structural feature benchmark of the key demolition nodes respectively;

[0039] According to the feature difference values, calculate the feature matching degrees between each candidate structural node and the preset structural feature benchmark of the key demolition nodes;

[0040] Filter out the candidate structural nodes with feature matching degrees reaching the preset threshold according to the feature matching degrees, mark them as the actual key demolition nodes after spatial position calibration, and generate the accurate spatial position information of the actual key demolition nodes.

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

[0042] By constructing spatial topology mapping rules, the fusion registration of multi-modal data such as laser point cloud, image texture, and structural stress is realized under a unified spatial framework, avoiding recognition deviations caused by inconsistent coordinate systems; combining multi-dimensional structural feature extraction and candidate node clustering improves the extraction efficiency of key nodes in complex structures; introducing a node deviation coefficient matrix and a spatial calibration mechanism effectively suppresses the cumulative error of micro-structure misalignment; finally, through the structural feature matching with the preset key demolition nodes, the accurate identification and spatial position calibration of the actual key demolition nodes are realized, with good scalability and practicability, applicable to demolition scenarios such as high-density and complex-structured petroleum refining devices, etc. While improving the demolition safety, it reduces human recognition errors and significantly improves the overall operation intelligence level and engineering execution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a structural schematic diagram of a real-time monitoring and optimization system for accurate positioning of key demolition points according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] Embodiment

[0046] Figure 1 A real-time monitoring optimization system for precise positioning of key demolition points of the present invention is given, including a data acquisition module, a mapping registration module, a feature segmentation module, a deviation calculation module, a spatial calibration module, and a node recognition module;

[0047] The data acquisition module acquires multi-modal perception data collected by multi-source sensors in the area to be demolished;

[0048] The mapping registration module performs structural mapping registration processing on the multi-modal perception data according to the spatial topology mapping rules, and establishes an initial structural mapping reference data set;

[0049] The feature segmentation module performs local structural feature segmentation based on the initial structural mapping reference data set, extracts multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and performs grouping and clustering on the multi-dimensional structural feature vectors corresponding to each structural node to obtain a structural node candidate set;

[0050] 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 topology relationship of each candidate structural node in the structural node candidate set, and establishes a node deviation coefficient matrix according to the structural mapping deviation values;

[0051] The spatial calibration module performs spatial calibration on each candidate structural node according to the node deviation coefficient matrix;

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

[0053] Specifically, acquiring the multi-modal perception data collected by multi-source sensors in the area to be demolished includes:

[0054] Deploying a laser scanning sensor, an image acquisition sensor, and a structural stress sensor inside the area to be demolished;

[0055] Specifically, to ensure comprehensive information can be obtained in the target area, three types of sensors with different functions are arranged in the area to be demolished. For example, laser scanning sensors are installed at different positions in an oil refinery to be demolished, which are used to capture the building shape, equipment contours, and structural boundaries. At the same time, high-definition image acquisition sensors are installed to obtain detailed textures, such as metal surfaces and oil stain spots. In addition, structural stress sensors are installed to monitor the stress response of equipment under external forces. Multimodal data including spatial geometry, visual texture, and structural stress can be collected.

[0056] Use laser scanning sensors to collect the spatial geometric information of facilities and equipment in the area to be demolished, and obtain spatial geometric point cloud data;

[0057] Specifically, laser scanning sensors mainly use the principle of laser beam ranging to collect three-dimensional point cloud data on the surfaces of buildings and equipment. For example, when a laser scanning sensor measures a section of pipeline, tens of thousands of three-dimensional coordinate data representing each point on the pipeline surface will be obtained. These three-dimensional coordinate data are called spatial geometric point cloud data.

[0058] Use image acquisition sensors to obtain the surface visual image information of facilities and equipment in the area to be demolished, and obtain image texture data;

[0059] Specifically, image acquisition sensors capture high-resolution images through cameras to collect the color and texture information on the exteriors of buildings and equipment. For example, for the scratches and damages on the equipment shell, the images obtained after shooting constitute the image texture data. <L

[0060] Use structural stress sensors to collect the structural physical state information of facilities and equipment in the area to be demolished in real time, and obtain structural stress data;

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

[0062] Perform time synchronization processing on the spatial geometric point cloud data, image texture data, and structural stress data to form multimodal perception data;

[0063] Specifically, time synchronization processing requires correcting the data from different sensors according to a unified timestamp. For example, during data collection, ensure that the laser point cloud, image, and stress data all come from the data collection at the same moment or within the same time interval, which is convenient for data fusion. After time correction, multimodal perception data is obtained.

[0064] Specifically, according to the spatial topology mapping rules, perform structural mapping registration processing on multi-modal perception data to establish an initial structural mapping reference data set, including:

[0065] Based on a unified spatial coordinate reference framework, perform spatial coordinate alignment mapping processing on spatial geometric point cloud data and image texture data to form fused geometric image data;

[0066] Specifically, map the spatial geometric point cloud data collected by the laser scanning sensor and the image texture data collected by the image acquisition sensor into the same spatial coordinate system, and align the spatial geometric point cloud data and the image texture data through coordinate transformation. The spatial geometric point cloud data and the image texture data adopt a unified reference coordinate system, which can be accurately matched in space, so as to form fused data containing geometric shapes and visual details.

[0067] Associate and map the structural stress data with the fused geometric image data according to the spatial topology structure information of the facilities and equipment to form spatial topology structure features;

[0068] Specifically, according to the physical structure characteristics of the facilities and equipment, map the structural stress data to the corresponding areas of the geometric image data. For example, if a steel beam has an obvious contour in the geometric image data, the corresponding stress value is associated within the contour area. Mark the steel beam area in the mapped image, and at the same time project the real-time stress data of the steel beam in the stress sensor onto the steel beam area to form spatial topology structure features containing shape information and stress information.

[0069] Based on the geometric image data and the spatial topology structure features, establish an initial structural mapping reference data set containing spatial position features, visual texture features, and structural stress features;

[0070] Specifically, integrate the processing results of the geometric image data and the spatial topology structure features to construct a data set. Each data unit in the data set contains three levels of information:

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

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

[0073] Structural stress features (stress values or force state data of the facilities and equipment).

[0074] Specifically, based on the initial structural mapping reference data set, perform local structural feature segmentation, extract the multi-dimensional structural feature vectors corresponding to each structural node in the demolition area, and group and cluster the multi-dimensional structural feature vectors corresponding to each structural node to obtain a set of candidate structural nodes, including:

[0075] Perform local area division processing on the initial structure mapping reference dataset to obtain multiple local structure units;

[0076] Specifically, using a space division method, the entire initial structure mapping reference dataset is divided into several independent local areas. Each local area is a local structure unit, representing a part of the area to be demolished with similar positions and similar structural characteristics.

[0077] Exemplarily, in a petroleum refinery to be demolished, it can be divided into multiple small areas by using a grid division method or a density-based clustering method. The point cloud data, image data, and stress data in each area constitute a local structure unit.

[0078] Extract the spatial coordinate positions, surface visual texture features, and structural stress features of the facilities and equipment within each local structure unit, and construct multi-dimensional structure feature vectors corresponding to each structural node;

[0079] Specifically, for each local structure unit: the spatial coordinate position is represented by three-dimensional coordinates, the surface visual texture feature is represented by an image feature descriptor, and the structural stress feature is represented by a stress value.

[0080] Combine the three features extracted within each local structure unit into a comprehensive vector. The comprehensive vector represents the features of a structural node. The combination can be achieved by vector concatenation, arranging the spatial coordinates, image feature descriptors, and stress values in sequence.

[0081] Group the multi-dimensional structure feature vectors corresponding to each structural node according to spatial topological similarity to obtain a candidate set of structural nodes;

[0082] Specifically, for the feature vectors of all structural nodes, use a grouping clustering algorithm, such as K-means clustering or hierarchical clustering, to evaluate the similarity between the feature vectors. The similarity evaluation can be calculated using 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 together. The final structural node grouping result forms a candidate set, that is, the candidate set of structural nodes, and each element in it is a candidate structural node.

[0083] Specifically, based on the spatial position relationship and neighborhood topological relationship of each candidate structural node in the candidate set of structural nodes, calculate the structural mapping deviation values of each candidate structural node in different sensor coordinate systems, and establish a node deviation coefficient matrix according to the structural mapping deviation values, including:

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

[0085] Specifically, each candidate structural node already has spatial position data before calibration. However, due to different measurement methods of different sensors, displacement errors may exist. For example, a laser scanning sensor may provide three-dimensional coordinates with millimeter-level accuracy, while there will be certain errors when an image acquisition sensor converts 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 component after conversion by the image acquisition sensor. Then, square each of these differences and sum them up. Finally, take the square root of the obtained sum to get the Euclidean distance between the two sets of coordinates, which is the deviation value of the spatial position.

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

[0088] Specifically, for each candidate structural node, calculate two sets of deviation values respectively:

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

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

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

[0092] Arrange the spatial position deviation values of each candidate structural node calculated between different coordinate systems in the order of the serial numbers of the structural nodes to form a node deviation coefficient matrix;

[0093] Specifically, organize the deviation values calculated between different sensors for each candidate structural node into a matrix form, 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, perform spatial calibration on each candidate structural node according to 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, according to 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 the spatial coordinates of the structural node. The calibration vector can generally be calculated using the average deviation value. For example, for a certain node, if the deviations in two sensors are C1 and C2 respectively, the calibration vector V can be defined as: V = (C1, C2) / 2; where V represents the calibration vector.

[0097] Using the spatial coordinate compensation method, 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 dataset;

[0098] Specifically, using the spatial coordinate compensation method, add the calculated calibration vector to the spatial coordinates of the original candidate structural node to ensure that the positions of all candidate structural nodes are more accurate after the fusion of different sensor data.

[0099] Update the spatial position data of all candidate structural nodes in the structural node candidate set to obtain a structural node candidate set with calibrated spatial positions;

[0100] Specifically, perform a correction operation on each candidate structural node in the candidate structural node set, and the updated candidate structural node set is the structural node candidate set with calibrated spatial positions, providing accurate spatial positioning data for feature matching.

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

[0102] Pre-establish the standard values of the spatial position features, surface visual texture features, and structural stress features of the key demolition nodes in the area to be demolished to form a preset key demolition node structural feature benchmark;

[0103] Specifically, the preset key demolition nodes are important demolition objects determined in advance according to design drawings, engineering requirements, or professional judgments, and consist of three parts:

[0104] Spatial position features (such as ideal three-dimensional coordinates or geometric distributions)

[0105] Surface visual texture features (such as standard image descriptors, color, and texture information)

[0106] Structural stress features (such as standard stress levels or mechanical parameters).

[0107] These standard values are combined to form a preset key demolition node structural feature benchmark.

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

[0109] Specifically, calculate the differences between the spatial position coordinates of the candidate structural nodes after spatial position calibration and the spatial standard position coordinates of the preset key demolition nodes in each dimension; then, square the differences in these three dimensions respectively; and add up the results of these three squared values to obtain a sum; finally, perform a square root operation on this sum, and the resulting value is the difference value of the spatial position feature. It is used to measure the position offset degree between the candidate structural node and the preset key demolition node in three-dimensional space.

[0110] Convert the visual texture feature representation of the candidate structural node into a texture feature set composed of multiple numerical dimensions; similarly, convert the visual texture standard feature of the preset key demolition node into the same type of feature set. Calculate the cosine similarity between the two feature sets, which is the difference value of the visual texture feature, and is used to measure the matching degree of the appearance texture information between the two candidate structural nodes.

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

[0112] Perform a weighted sum of the various difference values according to their respective importance to obtain the total feature difference value.

[0113] Calculate the feature matching degree between each candidate structural node and the preset key demolition node structural feature benchmark according to the feature difference value;

[0114] Specifically, the calculation formula for the matching degree is: matching degree = 1 - (total feature difference value / maximum allowable feature difference value). Among them, the maximum allowable feature difference value is a preset limit value. When the matching degree is close to 1, it indicates that the candidate node is more similar to the preset key demolition node.

[0115] Select the candidate structural nodes whose feature matching degrees reach the preset threshold according to the feature matching degree, mark them as the actual key demolition nodes after spatial position calibration, and generate the accurate spatial position information of the actual key demolition nodes;

[0116] Specifically, according to the set preset threshold, select the candidate structural nodes that meet the requirements, determine them as the actual key demolition nodes, and output the accurate three-dimensional spatial coordinates and related monitoring information of the actual key demolition nodes to support the precise execution of the demolition operation.

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

[0118] The above formulas are all calculated by taking the numerical values after dimensionlessization. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection 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 combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of 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, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. 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 by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0120] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner 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 to exceed the scope of the present application.

[0121] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0122] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or modules can be in electrical, mechanical, or other forms.

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

[0124] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0125] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or this part 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 enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0126] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0127] Finally, the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A real-time monitoring optimization system for precise positioning of key demolition points, characterized in that, It includes a data acquisition module, a mapping registration module, a feature segmentation module, a deviation calculation module, a spatial calibration module, and a node recognition module; The data acquisition module acquires multi-modal perception data collected by multi-source sensors within the area to be demolished; The mapping registration module performs structural mapping registration processing on the multi-modal perception data according to the spatial topology mapping rules to establish an initial structural mapping reference data set; The feature segmentation module performs local structural feature segmentation based on the initial structural mapping reference data set, extracts the multi-dimensional structural feature vectors corresponding to each structural node within the demolition area, and performs grouping clustering on the multi-dimensional structural feature vectors corresponding to each structural node to obtain a structural node candidate set; 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 topology relationship of each candidate structural node in the structural node candidate set, and establishes a node deviation coefficient matrix according to the structural mapping deviation values; The spatial calibration module performs spatial calibration on each candidate structural node according to the node deviation coefficient matrix; The node recognition module identifies the actual key demolition nodes in the area to be demolished based on the matching degree between the candidate structural nodes after spatial calibration and the structural features of the preset key demolition nodes.

2. The real-time monitoring optimization system for precise positioning of key demolition points according to claim 1, characterized in that, Acquiring the multi-modal perception data collected by multi-source sensors within the area to be demolished, specifically: Deploy laser scanning sensors, image acquisition sensors, and structural stress sensors within the area to be demolished; Use the laser scanning sensor to collect the spatial geometric information of the facilities and equipment within the area to be demolished to obtain spatial geometric point cloud data; Use the image acquisition sensor to obtain the surface visual image information of the facilities and equipment within the area to be demolished to obtain image texture data; Use the structural stress sensor to collect the structural physical state information of the facilities and equipment within the area to be demolished in real time to obtain structural stress data; Perform time synchronization processing on the spatial geometric point cloud data, image texture data, and structural stress data to form multi-modal perception data.

3. The real-time monitoring optimization system for accurate positioning of key demolition points according to claim 2, characterized in that, Performing structural mapping registration processing on the multi-modal perception data according to the spatial topology mapping rules to establish an initial structural mapping reference data set, specifically: Based on a unified spatial coordinate reference framework, perform spatial coordinate alignment mapping processing on the spatial geometric point cloud data and the image texture data to form fused geometric image data; Perform associative mapping on the structural stress data and the fused geometric image data according to the spatial topology structure information of the facilities and equipment to form spatial topology structure features; Based on the geometric image data and the spatial topology structure features, establish an initial structural mapping reference data set including spatial position features, visual texture features, and structural stress features.

4. The real-time monitoring optimization system for precise positioning of key demolition points according to claim 3, wherein Performing local structural feature segmentation based on the initial structural mapping reference data set, extracting the multi-dimensional structural feature vectors corresponding to each structural node within the demolition area, and performing grouping clustering on the multi-dimensional structural feature vectors corresponding to each structural node to obtain a structural node candidate set, specifically: Perform local area division processing on the initial structural mapping reference data set to obtain multiple local structural units; Extract the spatial coordinate positions, surface visual texture features, and structural stress features corresponding to the facilities and equipment within each local structural unit, and construct multi-dimensional structural feature vectors corresponding to each structural node; Group the multi-dimensional structural feature vectors corresponding to each structural node according to spatial topological similarity to obtain a candidate set of structural nodes.

5. The real-time monitoring optimization system for accurate positioning of key demolition points according to claim 4, wherein, Based on the spatial position relationship and neighborhood topological relationship of each candidate structural node in the candidate set of structural nodes, calculate the structural mapping deviation values of each candidate structural node in different sensor coordinate systems, and establish a node deviation coefficient matrix according to the structural mapping deviation values. Specifically: Based on the spatial topological relationship of each candidate structural node in the candidate set of structural nodes, calculate the spatial position deviation values of each candidate structural node between the laser scanning sensor coordinate system and the image acquisition sensor coordinate system respectively; Calculate the spatial position deviation values of each candidate structural node between the laser scanning sensor coordinate system and the structural stress sensor coordinate system respectively; Arrange the spatial position deviation values of each candidate structural node calculated between different coordinate systems in the order of the serial numbers of the candidate structural nodes to form a node deviation coefficient matrix.

6. The real-time monitoring optimization system for precise positioning of key demolition points according to claim 5, characterized in that, Perform spatial calibration on each candidate structural node according to the node deviation coefficient matrix. Specifically: 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; Adopt a spatial coordinate compensation method to apply the spatial calibration vector to the spatial coordinate data corresponding to each candidate structural node, and correct the spatial position of each candidate structural node in the initial structural mapping reference dataset; Update the spatial position data of all candidate structural nodes in the candidate set of structural nodes to obtain a candidate set of structural nodes with calibrated spatial positions.

7. The real-time monitoring optimization system for precise positioning of key demolition points according to claim 6, characterized in that, Based on the matching degree between the candidate structural nodes with calibrated spatial positions and the structural features of the preset key demolition nodes, identify the actual key demolition nodes in the area to be demolished. Specifically: Pre-establish the standard values of the spatial position features, surface visual texture features, and structural stress features of the key demolition nodes in the area to be demolished to form a reference for the structural features of the preset key demolition nodes; Calculate the feature difference values between each candidate structural node in the candidate set of structural nodes with calibrated spatial positions and the reference for the structural features of the preset key demolition nodes respectively; According to the feature difference values, calculate the feature matching degree between each candidate structural node and the reference for the structural features of the preset key demolition nodes; Screen out the candidate structural nodes with feature matching degrees reaching the preset threshold according to the feature matching degrees, mark them as the actual key demolition nodes with calibrated spatial positions, and generate accurate spatial position information of the actual key demolition nodes.

Images