A method, system and medium for early warning of urban building deformation

Abstract

The present invention provides an early warning method, system and medium for urban building deformation, which relate to the field of building monitoring technology. The present invention systematically integrates building design data and real-time monitoring data, uses a GIS platform to build an accurate three-dimensional visualization model, and assigns accurate three-dimensional position coordinates to each monitoring node, thereby ensuring accurate spatial mapping of monitoring data and solving the problems of inaccurate data integration and spatial positioning in traditional methods. By creating a regular grid in the three-dimensional model and adopting the inverse distance weighted interpolation technology to accurately estimate the deformation values ​​of the evaluation nodes, the spatial analysis capability of the deformation data is improved, and the overall and local deformation characteristics of the building can be comprehensively reflected. By normalizing the deformation values ​​of the evaluation nodes, calculating the relative deformation values, and marking the risk level of abnormal evaluation points in combination with the density distribution index, the multi-dimensional evaluation of the deformation risk of the building structure is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of building monitoring, and in particular to an early warning method, system and medium for urban building deformation. Background Art

[0002] With the rapid development of urbanization, high-rise buildings and complex structures have become increasingly prominent in city skylines. However, as buildings grow in height and structural complexity, the challenges to their safety and stability also increase significantly. Throughout their service life, buildings are often affected by a variety of external and internal factors, including earthquakes, strong winds, foundation settlement, construction quality issues, and material degradation. These factors can cause varying degrees of structural deformation. If not monitored and addressed promptly, these can lead to structural instability, crack expansion, or even collapse, resulting in significant casualties and property damage. Therefore, effectively monitoring and assessing the deformation of urban buildings and providing timely warnings of potential risks have become crucial issues in ensuring urban safety.

[0003] Currently, structural deformation monitoring of buildings mainly relies on traditional sensor networks and data processing methods. These methods typically involve installing total stations, GPS systems, inclinometers, strain gauges, and other equipment to obtain deformation data such as displacement and strain at each monitoring node in the building. At the same time, data collection and processing often utilize independent and decentralized systems, lacking a unified platform for integrated analysis. Furthermore, existing technologies have limitations in data visualization, often relying on two-dimensional charts or simple three-dimensional models, making it difficult to intuitively reflect the overall and local deformation of the building. In terms of risk assessment, traditional methods often employ empirical formulas or single indicators, lacking in-depth analysis of the spatial distribution of deformation data and its correlation, resulting in insufficient accuracy and reliability in early warnings.

[0004] However, existing technologies still have many shortcomings in practical applications. First, the layout of sensors is often not reasonable enough, resulting in incomplete data collection and difficulty in fully reflecting the deformation characteristics of buildings. Secondly, data processing efficiency is low, especially in large-scale data integration and real-time analysis, where there are bottlenecks, which affects the response speed of the early warning system. In addition, traditional risk assessment methods have difficulty in effectively integrating multi-source and multi-type deformation data, and cannot fully consider the spatial distribution and dynamic changes of deformation, resulting in inaccurate identification of high-risk areas and abnormal deformation points. Therefore, there is an urgent need for a technical solution that integrates advanced three-dimensional visualization modeling, precise data mapping and efficient risk assessment algorithms to improve the accuracy and efficiency of building deformation monitoring and risk assessment and make up for the shortcomings of existing technologies.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide an early warning method, system and medium for urban building deformation to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An early warning method for urban building deformation, comprising the following steps:

[0009] Obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, construct a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node within the 3D visualization model;

[0010] At the same time, the deformation value of each monitoring node is obtained, and the deformation value of each monitoring node is mapped to the three-dimensional position coordinates of the monitoring node. A regular grid is created in the three-dimensional visualization model, and each grid intersection is used as an evaluation node. The three-dimensional position coordinates of the evaluation node are obtained and numbered.

[0011] Use inverse distance weighted interpolation to interpolate the deformation value of each evaluation node, obtain the estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation value of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation value of the evaluation node;

[0012] Set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes in the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the abnormal assessment point with a risk level according to the density distribution index, and set the risk weight;

[0013] Based on the distribution density of all marked abnormal assessment points in the three-dimensional visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, an early warning assessment model is constructed to generate the deformation risk index of the building to be assessed. Whether to issue an early warning is determined based on the deformation risk index.

[0014] Furthermore, the method of constructing a three-dimensional visualization model is:

[0015] Architectural design data is obtained through building information models or computer-aided design drawings. The architectural design data is converted into a software format that conforms to 3D modeling using Autodesk Revit or AutoCAD software, unifying the coordinate system of geographic spatial data;

[0016] Select ArcGIS Pro or QGIS as the GIS platform, import the processed building model and geographic data into the GIS platform, mark the location of key monitoring nodes, and obtain the 3D position coordinates of each monitoring node;

[0017] The key structural nodes serving as the monitoring nodes include the junction of columns and beams, the midpoint of the contact portion between floor slabs and beams, and the intersection of shear walls and frame structures. When allocating three-dimensional position coordinates, the lowest point located on the easternmost and southernmost sides of the building to be evaluated is used as the origin, and a Cartesian coordinate system is constructed with the east-west direction as the x-axis, the north-south direction as the y-axis, and the direction perpendicular to the ground as the z-axis.

[0018] Furthermore, the deformation value of each monitoring node is the stress value of the monitoring node, the size and range of the grid are set, a regular grid is generated according to the analysis requirements, the building to be evaluated is covered, the grid intersection is extracted as the evaluation node, and its three-dimensional position coordinates are recorded. The grid is a three-dimensional grid.

[0019] Furthermore, the deformation value of each evaluation node is interpolated using inverse distance weighted interpolation, and the formula for obtaining the estimated value of the deformation value of each evaluation node is:

[0020]

[0021] Among them, Z j represents the estimated value of the deformation value of the j-th evaluation node, Y i represents the deformation value of the i-th monitoring node, I represents the total number of monitoring nodes, d ij represents the distance between the jth evaluation node and the ith monitoring node, i is the number of the monitoring node, j is the number of the evaluation node, (x i ,y i , z i ) represent the three-dimensional position coordinates of the i-th monitoring node, (x j ,y j , z j ) represent the three-dimensional position coordinates of the j-th evaluation node.

[0022] Furthermore, the method for normalizing the estimated values ​​of the deformation values ​​of all evaluation nodes is as follows:

[0023] Get the estimated values ​​of the deformation values ​​of all evaluation nodes, and calculate the maximum and minimum values ​​of the estimated values ​​of the deformation values ​​of all evaluation nodes, specifically:

[0024] Z max = max [Z1, Z2, ..., Z j ,…,Z n ]

[0025] Z min =min[Z1, Z2, ..., Z j ,…,Z n ]

[0026] Among them, Z max and Z min They represent the maximum and minimum values ​​of the estimated deformation values ​​of all evaluation nodes, Z j represents the estimated value of the deformation value of the j-th evaluation node before normalization, j represents the number of the evaluation node, and n represents the total number of evaluation nodes;

[0027] The estimated values ​​of the deformation values ​​of all evaluation nodes are scaled to the range of [0, 1], specifically:

[0028]

[0029] Zg j Represents the estimated value of the normalized deformation value of the j-th evaluation node.

[0030] Furthermore, the formula for calculating the relative deformation value of each evaluation node is:

[0031]

[0032] Among them, Xd j Represents the relative deformation value of the jth evaluation node. When identifying abnormal evaluation points, if Xd j ≥By, then the corresponding evaluation node is judged as an abnormal evaluation node, B y is the relative deformation threshold;

[0033] When calculating the density distribution index of each abnormal evaluation point, the neighborhood range is set to Where x represents the side length of the constructed three-dimensional grid, and the calculation is centered on the abnormal evaluation node. The relative deformation values ​​of all evaluation nodes in the spherical area of ​​radius are calculated, and the average is calibrated as the density distribution index of the corresponding abnormal evaluation node;

[0034] When marking the risk level of abnormal assessment points according to the density distribution index, if Md j ≥0.8By, the abnormal assessment node is marked as the first risk node. If 0.8By>Md j >0.4By, then the abnormal assessment node is marked as the second risk node. If 0.4By≥Md j , then the abnormal assessment node is marked as the third risk node, Md j represents the density distribution index of the j-th evaluation node;

[0035] When setting risk weights, the risk weight of the first risk node is set to α, the risk weight of the second risk node is set to β, and the risk weight of the third risk node is set to γ, α>β>γ>0, and α+β+γ=1.

[0036] Furthermore, the formula for constructing the early warning assessment model is:

[0037]

[0038] Among them, Fx represents the deformation risk index of the building to be evaluated, m represents the number of abnormal evaluation nodes, M represents the number of evaluation nodes, Xd1 p and P represent the relative deformation value of the pth first risk node and the total number of first risk nodes, respectively. q and Q represent the relative deformation value of the qth second risk node and the number of second risk nodes, respectively. w and W represent the relative deformation value of the wth third risk node and the number of third risk nodes, respectively. When Fx ≥ Fxy, a building deformation warning is issued, and Fxy represents the deformation risk threshold.

[0039] The present invention further provides an early warning system for urban building deformation, which is used to implement the above-mentioned early warning method for urban building deformation, including:

[0040] The model building module is used to obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, build a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node in the 3D visualization model;

[0041] The deformation monitoring module is used to simultaneously obtain the deformation value of each monitoring node, map the deformation value of each monitoring node to the 3D position coordinates of the monitoring node, create a regular grid within the 3D visualization model, use each grid intersection as an evaluation node, obtain the 3D position coordinates of the evaluation node, and number them;

[0042] A node screening module is used to interpolate the deformation value of each evaluation node using inverse distance weighted interpolation, obtain an estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation values ​​of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation values ​​of the evaluation nodes;

[0043] The neighborhood analysis module is used to set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes in the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the abnormal assessment point with a risk level according to the density distribution index, and set the risk weight;

[0044] The early warning analysis module is used to build an early warning assessment model based on the distribution density of all marked abnormal assessment points in the three-dimensional visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, to generate the deformation risk index of the building to be assessed, and determine whether to issue an early warning based on the deformation risk index.

[0045] The present invention further provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned early warning method for urban building deformation can be implemented.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] This method systematically integrates building design data with real-time monitoring data, constructs an accurate 3D visualization model using a GIS platform, and assigns precise 3D coordinates to each monitoring node. This process ensures accurate spatial mapping of monitoring data, resolving the issues of inaccurate data integration and spatial positioning in traditional methods. By creating a regular grid within the 3D model and employing inverse distance weighted interpolation to accurately estimate the deformation values ​​of the evaluation nodes, the spatial analysis capabilities of deformation data are effectively enhanced, enabling a more comprehensive reflection of the overall and local deformation characteristics of the building.

[0048] This method normalizes the deformation values ​​of assessment nodes, calculates relative deformation values, and uses a density distribution index to assign risk levels to abnormal assessment points. This enables a multi-dimensional assessment of building deformation risk. This not only improves the accuracy and detail of risk identification, but also enhances the response speed and reliability of the early warning system. The early warning assessment model, based on the distribution density, relative deformation values, and risk weights of abnormal assessment points, dynamically generates a building deformation risk index, accurately determining whether a warning signal is needed. This enables efficient and accurate monitoring and risk assessment of building deformation, providing timely warnings of potential structural issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0050] Figure 2 Schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0052] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0053] Example:

[0054] See also Figure 1 , the present invention provides a technical solution:

[0055] An early warning method for urban building deformation, comprising the following steps:

[0056] Step 1: Obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, construct a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node in the 3D visualization model.

[0057] In this embodiment, the method for constructing a three-dimensional visualization model is:

[0058] Architectural design data is obtained through building information models or computer-aided design drawings. The architectural design data is converted into a software format that conforms to 3D modeling using Autodesk Revit or AutoCAD software, unifying the coordinate system of geographic spatial data;

[0059] Select ArcGIS Pro or QGIS as the GIS platform, import the processed building model and geographic data into the GIS platform, mark the location of key monitoring nodes, and obtain the 3D position coordinates of each monitoring node;

[0060] The key structural nodes serving as the monitoring nodes include the junction of columns and beams, the midpoint of the contact portion between floor slabs and beams, and the intersection of shear walls and frame structures. When allocating three-dimensional position coordinates, the lowest point located on the easternmost and southernmost sides of the building to be evaluated is used as the origin, and a Cartesian coordinate system is constructed with the east-west direction as the x-axis, the north-south direction as the y-axis, and the direction perpendicular to the ground as the z-axis.

[0061] Architectural design data usually comes from building information models (BIM) or computer-aided design (CAD) drawings. These data contain detailed information such as the building's structure, dimensions, and materials. Using professional software such as Autodesk Revit or AutoCAD, the design data can be converted into a software format suitable for 3D modeling. This step ensures the integrity and accuracy of the data and lays the foundation for subsequent 3D modeling. In order to use it on the GIS platform, the architectural design data needs to be converted into a format compatible with the 3D modeling software. This includes exporting the data into commonly used file formats such as OBJ, FBX, etc. At the same time, it is necessary to ensure that the coordinate system of the geospatial data is unified so that it matches the data of the building model. This allows the location of the building to be accurately located on the GIS platform.

[0062] ArcGIS Pro or QGIS are commonly used GIS platforms for integrating and analyzing spatial data. Import the pre-processed building model and related geographic data into the selected platform. GIS platforms provide powerful tools for visualizing and analyzing the building model, enabling intuitive spatial representation of design data. In the 3D visualization model, identify and annotate key structural nodes, such as the junctions between columns and beams, the midpoints of floor-slab-beam contact, and the intersections between shear walls and the frame structure. These nodes are crucial for structural health monitoring. Assign 3D coordinates to each node to ensure its accurate positioning within the model. When assigning coordinates to monitoring nodes, establish a Cartesian coordinate system with the lowest, easternmost, and southernmost points of the building as the origin. The east-west x-axis is the east-west direction, the north-south direction is the y-axis, and the z-axis is perpendicular to the ground. This coordinate system allows each node's position to be accurately described using 3D coordinates, providing a reliable data foundation for subsequent monitoring and analysis. This method ensures that the 3D positions of all monitoring nodes are accurately mapped within the model, providing accurate data support for building deformation monitoring.

[0063] In building structures, the junctions between columns and beams, the midpoints of the contact areas between floor slabs and beams, and the intersections between shear walls and the frame structure are crucial nodes. These junctions are critical for load bearing and force transmission within a building structure. Columns are typically vertical components, bearing vertical loads, while beams are horizontal components, primarily bearing bending moments and shear forces. Loads are transferred from beams to columns at these junctions, subjecting these nodes to complex mechanical stresses. Monitoring these junctions can help identify structural deformation or damage caused by loads or geological changes. The junctions between floor slabs and beams are also a key focus for structural deformation monitoring. The floor slab carries the building's operational loads and distributes them to the beams. The midpoint of the contact area can be considered the center of load transfer from the floor slab to the beams. Monitoring changes in the position of this midpoint can reveal deflection or deformation in the floor slab, which is crucial for preventing cracking or failure. The junctions between shear walls and the frame structure are crucial for resisting horizontal loads. Shear walls enhance the building's resistance to lateral forces, such as wind and seismic forces, while the frame structure provides overall stability. At these junctions, shear walls transfer horizontal loads to the frame, making their structural integrity critical. Monitoring these junctions can help prevent building deformation or collapse due to horizontal loads.

[0064] In building structures, the junction between a column and a beam is the point where a vertical column (or column) connects to a horizontal beam (usually a load-bearing beam). Floors are typically horizontally placed panels that carry the building's operational loads, while beams support the floor and transfer the loads to the columns. The midpoint of the contact between the floor and beam is the point where the floor meets the beam along its width. Shear walls are walls used in buildings to increase their ability to resist horizontal loads, typically wind and seismic forces. Frame structures, composed of columns and beams, provide the building's primary skeleton. The intersection of shear walls and frame structures is the node where they connect to the frame (columns and beams). Monitoring nodes are the primary pathways for structural force transmission, and their mechanical properties directly impact the overall stability of the building. Due to the unique loads and stresses they carry, these nodes are particularly sensitive to deformation and can provide early warning signals. In building design and construction, these nodes are clearly defined and easy to mark and monitor in 3D models.

[0065] Step 2: Simultaneously obtain the deformation value of each monitoring node, and map the deformation value of each monitoring node to the three-dimensional position coordinates of the monitoring node. Create a regular grid in the three-dimensional visualization model, use each grid intersection as an evaluation node, obtain the three-dimensional position coordinates of the evaluation node, and number them.

[0066] In this embodiment, the deformation value of each monitoring node is the stress value of the monitoring node. The size and range of the grid are set, and a regular grid is generated according to the analysis requirements to cover the building to be evaluated. The grid intersection is extracted as the evaluation node, and its three-dimensional position coordinates are recorded. The grid is a three-dimensional grid.

[0067] Sensors, such as strain gauges or accelerometers, are installed at building monitoring nodes. These devices can monitor structural stress and deformation in real time. The sensor data acquisition system should be synchronized to ensure simultaneous acquisition of deformation data from all monitoring nodes. The 3D position coordinates of each monitoring node have been previously calibrated in the 3D model. The acquired deformation values ​​are combined with the corresponding node coordinates to form data pairs, ensuring that the deformation values ​​accurately match the node's 3D spatial information. In the 3D visualization model, the mesh size and coverage are set based on the building's size and structural complexity. The mesh density should be adjusted to the required analysis accuracy, ensuring sufficient detail to represent all parts of the building. A regular mesh is generated using 3D modeling software that supports mesh generation and editing, allowing users to customize mesh parameters. Intersection points are extracted from the generated regular mesh and serve as evaluation nodes. The position of each evaluation node is determined by its 3D coordinates. These nodes are evenly distributed throughout the building structure to provide a comprehensive evaluation benchmark.

[0068] Each assessment node is assigned a unique number to facilitate subsequent tracking and analysis. The numbering system can be based on the grid row and column order or customized according to specific analysis requirements. These assessment nodes can be used as a reference for comprehensive evaluation of the building's stress distribution and potential deformation.

[0069] The specific parameters for setting up a 3D grid depend on the building's size, structural complexity, and monitoring and analysis requirements. First, the building's total length, width, and height must be known. For example, a building might be 100 meters long, 50 meters wide, and 30 meters high. The density of the grid determines the accuracy of the analysis and the amount of data that can be processed. Generally, the grid size should be adjusted based on the building's importance and the required monitoring accuracy. For example, if critical areas of the building require higher accuracy, a denser grid can be used in these areas. Let's assume we decide to use a grid intersection every 5 meters for the initial assessment of the entire structure. This means a grid of 5 meters in length, width, and height. This would create 20 grid cells (100 meters / 5 meters), 10 grid cells (50 meters / 5 meters) in width, and 6 grid cells (30 meters / 5 meters) in height, resulting in a total of 1,200 evaluation nodes. Smaller grids (such as 1 meter) provide higher accuracy and are suitable for critical areas requiring detailed monitoring. Larger grids (such as 5 meters) are used for overall structural analysis, reducing computational effort and making them suitable for holistic health monitoring.

[0070] Step 3: Use inverse distance weighted interpolation to interpolate the deformation value of each evaluation node, obtain the estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation value of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation value of the evaluation node.

[0071] For each evaluation node, an estimated deformation value is calculated using inverse distance weighted interpolation (IDW). IDW is a distance-based interpolation method where data points closer to the node have a greater influence on the node. Specifically, the deformation value of the node to be estimated is a weighted average of the deformation values ​​of surrounding known monitoring nodes, with the weights inversely proportional to the distance. By setting an appropriate power parameter, the influence of distance can be controlled. This method is simple and computationally efficient, making it suitable for monitoring building deformation with spatial correlation.

[0072] Normalization converts deformation values ​​to a relative scale for easier comparison and analysis. Typically, the deformation value is subtracted from the minimum deformation value and then divided by the range (maximum minus minimum) to normalize it to between 0 and 1. Calculating the relative deformation value for each evaluation node allows identification of differences in deformation levels, effectively comparing the states of different nodes.

[0073] By setting a threshold for the normalized relative deformation values, abnormal assessment points outside the normal range can be identified. These points may reflect potential structural problems, such as excessive deformation or stress concentration. This method can quickly locate areas that may pose safety hazards. Interpolation can be used to obtain estimated values ​​of deformation data in areas lacking monitoring nodes, improving the accuracy of overall monitoring. Normalization and calculation of relative deformation values ​​enable rapid identification of abnormal areas, facilitating timely maintenance and management. Interpolation improves the coverage of assessment nodes and data integrity, making the monitoring plan more comprehensive. Rapid identification of abnormal assessment points helps to detect potential structural problems early and reduce safety risks.

[0074] In this embodiment, the deformation value of each evaluation node is interpolated using inverse distance weighted interpolation, and the formula for obtaining the estimated value of the deformation value of each evaluation node is:

[0075]

[0076] Among them, Z j represents the estimated value of the deformation value of the j-th evaluation node, Y i represents the deformation value of the i-th monitoring node, I represents the total number of monitoring nodes, d ij represents the distance between the jth evaluation node and the ith monitoring node, i is the number of the monitoring node, j is the number of the evaluation node, (xi ,y i , z i ) represent the three-dimensional position coordinates of the i-th monitoring node, (x j ,y j , z j ) represent the three-dimensional position coordinates of the j-th evaluation node.

[0077] Using a weighted average, the known deformation values ​​of surrounding monitoring nodes are used for interpolation. The contribution of each monitoring node to the evaluation node is inversely proportional to the distance between them; closer distances contribute more. This method assumes that spatially close neighbors have a more significant influence on a location, and therefore assigns greater weight to closer monitoring nodes. This setup effectively captures spatial variability in the structure and provides reasonable estimates for unmonitored locations.

[0078] The weight is calculated using the inverse square of the distance, a choice that further amplifies the influence of nearby nodes over distant nodes. This design is based on the theory of spatial correlation, where geographical or spatial phenomena often have the characteristic that adjacent or closely spaced points often have more similar characteristics. Using this weight form, the deformation state of the environment surrounding the assessment node can be more accurately reflected, thereby improving the accuracy of the interpolation estimate and providing a mathematically concise and computationally efficient method to estimate the deformation state of unknown points in the building structure. Through the design of the inverse distance weight, the interpolation process takes into account both the simplicity of calculation and the practical significance of the estimation results. At the same time, this interpolation method does not require the assumption of the specific form of the deformation field, is highly adaptable, and is suitable for deformation monitoring of irregular or complex structures, enabling the monitoring system to maintain good assessment capabilities even when node coverage is insufficient.

[0079] Furthermore, the method for normalizing the estimated values ​​of the deformation values ​​of all evaluation nodes is as follows:

[0080] Get the estimated values ​​of the deformation values ​​of all evaluation nodes, and calculate the maximum and minimum values ​​of the estimated values ​​of the deformation values ​​of all evaluation nodes, specifically:

[0081] Z max = max [Z1, Z2, ..., Z j ,…,Z n ]

[0082] Z min =min[Z1, Z2, ..., Z j ,…,Z n ]

[0083] Among them, Z max and Z minThey represent the maximum and minimum values ​​of the estimated deformation values ​​of all evaluation nodes, Z j represents the estimated value of the deformation value of the j-th evaluation node before normalization, j represents the number of the evaluation node, and n represents the total number of evaluation nodes;

[0084] The estimated values ​​of the deformation values ​​of all evaluation nodes are scaled to the range of [0, 1], specifically:

[0085]

[0086] Zg j Represents the estimated value of the normalized deformation value of the j-th evaluation node.

[0087] By normalizing the estimated deformation values ​​to the range of [0, 1], a unified scale is created for subsequent analysis and comparison. By calculating the maximum and minimum deformation values ​​of all evaluated nodes, the entire deformation range can be obtained. The purpose of normalization is to eliminate the influence of absolute values ​​so that the deformation values ​​of different nodes can be compared on the same platform. Normalization ensures that the deformation estimate of each evaluated node is converted into a relative proportion. In this way, even if there are large differences in the original deformation values ​​of different nodes, these differences are compressed into the range of [0, 1] after normalization, making it easier to identify nodes that are abnormally deformed relative to the overall situation. At this point, any node with a normalized value close to 1 shows more significant deformation than other nodes.

[0088] The technical benefit of using this normalization method is that it supports subsequent anomaly detection and pattern recognition, allowing the monitoring system to quickly identify potential problem areas. By eliminating interference caused by absolute value differences between different nodes, normalization helps reveal relative changes and trends in structural deformation. This approach not only simplifies the data analysis process but also improves the sensitivity and reliability of the overall system, ensuring accurate deformation identification and early warning in complex building monitoring environments.

[0089] Step 4: Set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes within the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the risk level of the abnormal assessment point according to the density distribution index, and set the risk weight.

[0090] In step 4, a neighborhood range is set with the abnormal assessment point as the center. Usually, this range can be adjusted flexibly with a fixed radius or according to specific circumstances. The neighborhood range is used to determine which assessment nodes' relative deformation values ​​need to be included in the calculation of the density distribution index of the abnormal assessment point. Taking the center point as the benchmark, all nodes within the set radius are included in its neighborhood range. This neighborhood selection method can effectively use spatial correlation to analyze the deformation characteristics of the local area. Once the neighborhood range is determined, obtaining the relative deformation values ​​of all assessment nodes within this range is a crucial step. After collecting these relative deformation values, the risk level of the abnormal assessment point is evaluated by the density distribution index. The density distribution index can be defined as the weighted average or cumulative value of the relative deformation values ​​of all nodes in the neighborhood. According to the density, it is judged whether the deformation of the local area is concentrated. Such calculations can reveal the degree of deformation aggregation within the set range, thereby providing a basis for subsequent risk assessment.

[0091] Finally, based on the calculated density distribution index, each abnormal assessment point is marked with a risk level, and a corresponding risk weight is set. The higher the density distribution index, the more significant the deformation of the point and its surrounding area, and the higher the risk level. Setting risk weights helps to take corresponding measures for points of different risk levels in subsequent processing. The advantage of this processing method is that it can not only identify single abnormal points, but also evaluate the risk situation of the entire area, making the monitoring system more comprehensive and refined. Compared with the existing technology, this method improves the ability and accuracy to identify potential risks by introducing spatial density analysis. In this patent solution, this step promotes the intelligent decision-making ability of the monitoring system through detailed risk assessment and marking, enabling it to more effectively deal with complex building safety issues.

[0092] In this embodiment, the formula for calculating the relative deformation value of each evaluation node is:

[0093]

[0094] Among them, Xd j Represents the relative deformation value of the jth evaluation node. When identifying abnormal evaluation points, if Xd j ≥By, the corresponding evaluation node is determined to be an abnormal evaluation node, and By is the relative deformation threshold.

[0095] By calculating the relative deformation value of each evaluation node, the abnormal evaluation point is identified, Zg j represents the normalized deformation value, and is the average value of the deformation values ​​of all evaluated nodes. By calculating the difference between the deformation value of each node and the average value and normalizing it as a ratio relative to the average value, the formula can quantify the degree of deviation of each node from the overall deformation level. This embodiment provides a quantitative method to evaluate the degree of abnormal deformation of each node. By calculating the relative deformation value that deviates from the average level, the system can identify nodes whose deformation significantly exceeds the normal level. If the relative deformation value of a node is greater than or equal to the set threshold, it means that the deformation of the node is significantly different from the overall trend, and it is therefore marked as an abnormal evaluation point. This method can effectively screen out nodes that may face higher risks and provide more accurate anomaly detection.

[0096] This approach not only considers the deformation of individual nodes but also incorporates the overall deformation context, thus avoiding misjudgments due to abnormal individual values. Compared to simple absolute value judgments, this relative deviation analysis is more sensitive and accurate, and can better identify potential structural problems. Within the overall solution, this step provides a reliable data foundation for subsequent detailed risk analysis, enabling the system to more rationally allocate resources and implement targeted monitoring and maintenance measures.

[0097] The specific value of the relative deformation threshold is usually determined by the specific application scenario and engineering requirements. A reasonable threshold can be determined through statistical analysis and historical data. Analysis of a large amount of normal deformation data shows that the relative deformation value of the vast majority of nodes is less than 0.2. In this case, the threshold can be set to 0.2 to ensure that most normal nodes are not mistakenly identified as abnormal.

[0098] Setting By to 0.2 is based on an analysis of the statistical characteristics of normal deformation data. Analysis of past normal operation data indicates that the relative deformation values ​​of most nodes vary within this range. Therefore, setting the threshold to 0.2 effectively captures nodes whose deformation values ​​significantly exceed the normal range, avoiding false positives due to normal fluctuations.

[0099] The threshold of 0.2 was chosen to provide a sufficient safety margin. This value represents a 20% deviation from the average deformation level, meaning that an anomaly occurs when the deformation of a node exceeds this deviation. This deviation setting is typically derived through theoretical calculations and engineering experience to ensure that potential safety hazards are not missed when identifying anomalies, while also not placing an excessive alarm burden on the system. The threshold of 0.2 strikes a balance between sensitivity and stability. A lower threshold may lead to excessive sensitivity and excessive false alarms, while a higher threshold may cause some true anomalies to be overlooked. 0.2 is a reasonable intermediate value that can effectively identify anomalies while avoiding excessive false alarms due to normal deformation fluctuations. The specific threshold selection should also consider factors such as the characteristics of the specific project, material properties, and the operating environment. 0.2 is only an example value based on general technical principles and may need to be adjusted according to specific circumstances in actual applications.

[0100] Furthermore, when calculating the density distribution index of each abnormal evaluation point, the neighborhood range is set to Where x represents the side length of the constructed three-dimensional grid, and the calculation is centered on the abnormal evaluation node. The relative deformation values ​​of all evaluation nodes in the spherical area with a radius of , and the average is calculated, and the average is calibrated as the density distribution index of the corresponding abnormal evaluation node.

[0101] The density distribution index is a comprehensive metric used to assess deformation or anomalies in the area surrounding a node. It reflects the overall deformation characteristics of an area by summarizing the relative deformation of multiple nodes within a specific radius. A larger density distribution index indicates more significant relative deformation of the node and its surrounding area. A higher density distribution index indicates the potential for higher deformation or stress concentration near the node.

[0102] The density distribution index is calculated based on the spherical area centered on the abnormal evaluation node to ensure a comprehensive analysis of the space around the evaluation node. As the radius of the spherical region, it can cover a wider area than a simple grid neighborhood, thus capturing the relative deformation of the surrounding area. This setting allows analysis to be not limited to directly adjacent nodes, but to consider the influence of a wider range, helping to identify potential structural anomalies. By summarizing the relative deformation values ​​of all nodes within this spherical region and calculating their average, the overall deformation characteristics of the region can be effectively captured. The density distribution index, as a quantitative indicator of this regional deformation characteristic, provides a detailed view of the surrounding environment for each abnormal node. This regional average calculation helps smooth out the extreme deformation values ​​that may exist in individual nodes, making anomaly detection more robust.

[0103] It can help identify the overall deformation trend of a local area, rather than just the condition of a single abnormal point. This multi-node comprehensive analysis enhances the accuracy of anomaly detection because it considers the possible spread and impact of anomalies in a larger area. By identifying the deformation patterns of surrounding nodes, engineers can more comprehensively understand the health status of the structure and take more targeted repair and reinforcement measures to select the best solution. The radius is mainly used to effectively cover all directly adjacent nodes in a three-dimensional grid. In a three-dimensional grid, each node has multiple adjacent nodes, including directly adjacent nodes and nodes in the diagonal direction. By setting the radius of the spherical area to It is guaranteed to include nodes in the diagonal direction whose maximum distance from the center point is exactly This setup can effectively cover eight surrounding sampling points.

[0104] It can capture a wider range of spatial deformation information, especially in complex three-dimensional structures where deformation may not be uniformly distributed. By taking into account the nodes on the diagonal, the density distribution index can more accurately reflect the deformation state of the surrounding area, rather than just the state of the directly adjacent nodes. This is very important for identifying abnormal patterns in complex structures because anomalies may affect the structure in multiple directions at the same time. Overall, this radius setting method enhances the depth and accuracy of anomaly detection. By covering a more comprehensive neighborhood range, engineers can more comprehensively analyze the state of the structure and identify problem points that may affect the overall stability of the structure. This comprehensive coverage of three-dimensional space helps provide more reliable structural health monitoring results.

[0105] When marking the risk level of abnormal assessment points according to the density distribution index, if Md j ≥0.8By, the abnormal assessment node is marked as the first risk node. If 0.8By>Md j >0.4By, then the abnormal assessment node is marked as the second risk node. If 0.4By≥Md j , then the abnormal assessment node is marked as the third risk node, Md j represents the density distribution index of the j-th evaluation node;

[0106] When setting risk weights, the risk weight of the first risk node is set to α, the risk weight of the second risk node is set to β, and the risk weight of the third risk node is set to γ, α>β>γ>0, and α+β+γ=1

[0107] This method of assigning risk levels and weightings to abnormal assessment nodes aims to effectively identify and address potential structural risks through a refined classification system and weighting. Using a density distribution index to determine risk levels helps identify abnormal nodes of varying severity, clearly categorizing them into first, second, and third risk levels. This classification provides project managers with a simple and effective tool to quickly assess and prioritize the highest-risk nodes. This risk level reflects varying levels of concern for structural safety. A first-risk node is designated as the highest risk, meaning its density distribution index indicates that relative deformation is approaching or reaching the upper limit of the structural tolerance. This situation typically requires immediate attention and possible intervention. A second-risk node is in an intermediate state, potentially indicating potential problems but not yet reaching a critical state. A third-risk node carries the lowest risk, typically indicating that the structure remains relatively stable at its current deformation level. This classification helps decision-makers allocate resources appropriately, focusing more resources and attention on higher-risk nodes to improve the safety and stability of the entire system.

[0108] To further refine risk management, different risk weights are set to provide a quantitative risk metric for each risk level. This approach allows for a clearer distinction between the influence of different types of risk nodes in subsequent analysis and decision-making. For example, α = 0.5, β = 0.3, and γ = 0.2 can be set, reflecting a high level of attention paid to the highest risk nodes, giving them half the total weight to emphasize their importance. Second-tier risk nodes are given less weight, but still maintain some attention, while third-tier risk nodes are given the lowest weight, indicating that their impact is relatively small under the current assessment. This weighting approach ensures a balanced allocation of resources and attention, consistent with the prioritization principle commonly used in risk management.

[0109] Step 5: Based on the distribution density of all marked abnormal assessment points in the 3D visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, an early warning assessment model is constructed to generate a deformation risk index for the building to be assessed. Whether to issue an early warning is determined based on the deformation risk index.

[0110] In this embodiment, the formula for constructing the early warning assessment model is:

[0111]

[0112] Among them, Fx represents the deformation risk index of the building to be evaluated, m represents the number of abnormal evaluation nodes, M represents the number of evaluation nodes, Xd1 p and P represent the relative deformation value of the pth first risk node and the total number of first risk nodes, respectively. qand Q represent the relative deformation value of the qth second risk node and the number of second risk nodes, respectively. w and W represent the relative deformation value of the wth third risk node and the number of third risk nodes, respectively. When Fx ≥ Fxy, a building deformation warning is issued, and Fxy represents the deformation risk threshold.

[0113] By calculating the deformation risk index, the need for warnings is determined. This model comprehensively considers the distribution density, relative deformation value, and risk weight of different risk nodes to provide a comprehensive risk assessment. First, a preliminary risk density index is obtained by calculating the ratio of the number of abnormal assessment nodes to the total number of assessment nodes. This reflects the density of abnormal assessment nodes in the entire model and is an important basis for assessing the overall risk level.

[0114] Next, the risk weight is combined with the relative deformation value of each type of risk node for weighted summation, aiming to distinguish the different contributions of nodes with different risk levels to the overall risk. The deformation of the first risk node has the greatest impact on the risk index because its corresponding weight is the highest. The natural logarithm function and the exponential function are used to process the combination of these parameters. The natural logarithm function is used to compress a large range of data, making the risk index easier to manage and interpret, while the exponential function is used to amplify the subtle changes in risk, making the model more flexible and sensitive to deformation changes. Through this combination, the early warning assessment model can not only process a large range of structural deformation data, but also respond to subtle risk changes, ensuring the stability and sensitivity of the model.

[0115] This implementation comprehensively considers node density, deformation values, and their weighted influence, providing a more accurate risk assessment. While some existing methods may overlook the mutual influence between nodes or their varying contributions to risk, this step, through the use of comprehensive weighting and exponential functions, more accurately reflects the building's actual risk status, improving the accuracy and timeliness of early warnings.

[0116] This embodiment constructs an indicator for evaluating the deformation risk of a building by integrating multiple factors, namely the deformation risk index Fx. The specific logic is to comprehensively consider the density of abnormal assessment nodes, the relative deformation values ​​of nodes of different levels, and their respective risk weights to assess the overall deformation risk of the building.

[0117] Fx represents the deformation risk index of the building being assessed. It comprehensively considers the density of assessment nodes and the deformation of risk nodes, and is a quantitative indicator of the building's overall deformation risk. A larger Fx indicates a higher deformation risk. As the proportion of abnormal nodes and the deformation value of risk nodes increase, the risk index Fx increases. This relationship is monotonically increasing, as an increase in each independent variable increases the deformation risk, thereby increasing Fx. An increased proportion of abnormal nodes means more areas are in an abnormal state. Larger deformation values, combined with a higher risk weight, indicate that the area may pose a greater threat to the overall structural safety, and therefore need to be reflected in the risk index.

[0118] use In order to deal with the abnormal node ratio, the formula is sensitive to this ratio and numerically stable. The exponential function The impact of risk nodes on the entire building is magnified, making the model more sensitive to variance. Density and deformation values ​​are weighted and indexed to form a holistic risk assessment. This design ensures the model's sensitivity and stability within a range of variations, effectively assessing and reflecting building deformation risks.

[0119] Setting a deformation risk threshold requires comprehensive consideration of multiple factors, including the building's structural characteristics, functional use, historical monitoring data, and relevant industry standards. Initially, long-term monitoring data from the building and similar structures can be analyzed to identify a reasonable range for the building's deformation risk index under normal operating conditions. Then, based on experience and statistical analysis, a preliminary threshold range can be established. The specific usage environment and importance of the building should also be considered when setting the threshold. For example, for some important public buildings or high-risk buildings, the threshold may need to be set lower to ensure a greater safety margin. Furthermore, the building's geographical environment should be considered; for example, buildings in earthquake-prone areas may require stricter threshold standards. Through a comprehensive assessment of these factors, appropriate deformation risk thresholds can be customized for different types of buildings.

[0120] This embodiment systematically integrates building design data with real-time monitoring data, using a GIS platform to construct an accurate 3D visualization model and assign precise 3D location coordinates to each monitoring node. This process ensures accurate spatial mapping of monitoring data and addresses the issues of inaccurate data integration and spatial positioning in traditional methods. By creating a regular grid within the 3D model and employing inverse distance weighted interpolation technology to accurately estimate the deformation values ​​of evaluation nodes, the spatial analysis capabilities of deformation data are effectively enhanced, enabling a more comprehensive reflection of the overall and local deformation characteristics of the building.

[0121] This embodiment normalizes the deformation values ​​of assessment nodes, calculates relative deformation values, and uses a density distribution index to assign risk levels to abnormal assessment points. This enables a multi-dimensional assessment of building deformation risk. This not only improves the accuracy and detail of risk identification, but also enhances the responsiveness and reliability of the early warning system. The early warning assessment model, based on the distribution density, relative deformation values, and risk weights of abnormal assessment points, dynamically generates a building deformation risk index, accurately determining whether a warning signal is necessary. This enables efficient and accurate monitoring and risk assessment of building deformation, providing timely warnings of potential structural issues.

[0122] See also Figure 2 The present invention further provides an early warning system for urban building deformation, wherein the early warning system is used to execute the above-mentioned early warning method for urban building deformation, comprising:

[0123] The model building module is used to obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, build a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node in the 3D visualization model;

[0124] The deformation monitoring module is used to simultaneously obtain the deformation value of each monitoring node, map the deformation value of each monitoring node to the 3D position coordinates of the monitoring node, create a regular grid within the 3D visualization model, use each grid intersection as an evaluation node, obtain the 3D position coordinates of the evaluation node, and number them;

[0125] A node screening module is used to interpolate the deformation value of each evaluation node using inverse distance weighted interpolation, obtain an estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation values ​​of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation values ​​of the evaluation nodes;

[0126] The neighborhood analysis module is used to set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes in the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the abnormal assessment point with a risk level according to the density distribution index, and set the risk weight;

[0127] The early warning analysis module is used to build an early warning assessment model based on the distribution density of all marked abnormal assessment points in the three-dimensional visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, to generate the deformation risk index of the building to be assessed, and determine whether to issue an early warning based on the deformation risk index.

[0128] The present invention further provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned early warning method for urban building deformation can be implemented.

[0129] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0130] 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 in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0131] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0132] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for early warning of urban building deformation, characterized in that: The specific steps include: Obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, construct a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node within the 3D visualization model; At the same time, the deformation value of each monitoring node is obtained, and the deformation value of each monitoring node is mapped to the three-dimensional position coordinates of the monitoring node. A regular grid is created in the three-dimensional visualization model, and each grid intersection is used as an evaluation node. The three-dimensional position coordinates of the evaluation node are obtained and numbered. Use inverse distance weighted interpolation to interpolate the deformation value of each evaluation node, obtain the estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation value of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation value of the evaluation node; Set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes in the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the abnormal assessment point with a risk level according to the density distribution index, and set the risk weight; Based on the distribution density of all marked abnormal assessment points in the 3D visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, an early warning assessment model is constructed to generate a deformation risk index for the building to be assessed. The deformation risk index is then used to determine whether to issue an early warning. The deformation value of each monitoring node is the stress value of the monitoring node. The size and range of the grid are set. A regular grid is generated according to the analysis requirements to cover the building to be evaluated. The grid intersection is extracted as the evaluation node and its three-dimensional position coordinates are recorded. The grid is a three-dimensional grid. The deformation value of each evaluation node is interpolated using inverse distance weighted interpolation. The formula for obtaining the estimated value of the deformation value of each evaluation node is as follows: Among them, Z j represents the estimated value of the deformation value of the j-th evaluation node, Y i represents the deformation value of the i-th monitoring node, I represents the total number of monitoring nodes, d ij represents the distance between the jth evaluation node and the ith monitoring node, i is the number of the monitoring node, j is the number of the evaluation node, (x i ,y i , z i ) represent the three-dimensional position coordinates of the i-th monitoring node, (x j ,y j , z j ) represent the three-dimensional position coordinates of the j-th evaluation node.

2. The method for early warning of urban building deformation according to claim 1, characterized in that: The method of constructing a 3D visualization model is: Architectural design data is obtained through building information models or computer-aided design drawings. The architectural design data is converted into a software format that conforms to 3D modeling using Autodesk Revit or AutoCAD software, unifying the coordinate system of geographic spatial data; Select ArcGIS Pro or QGIS as the GIS platform, import the processed building model and geographic data into the GIS platform, mark the location of key monitoring nodes, and obtain the 3D position coordinates of each monitoring node; The key structural nodes serving as the monitoring nodes include the junction of columns and beams, the midpoint of the contact portion between floor slabs and beams, and the intersection of shear walls and frame structures. When allocating three-dimensional position coordinates, the lowest point located on the easternmost and southernmost sides of the building to be evaluated is used as the origin, and a Cartesian coordinate system is constructed with the east-west direction as the x-axis, the north-south direction as the y-axis, and the direction perpendicular to the ground as the z-axis.

3. The method for early warning of urban building deformation according to claim 1, characterized in that: The method for normalizing the estimated deformation values ​​of all evaluation nodes is: Get the estimated values ​​of the deformation values ​​of all evaluation nodes, and calculate the maximum and minimum values ​​of the estimated values ​​of the deformation values ​​of all evaluation nodes, specifically: WITH max =max[Z1、Z2、…、Z j ,…,WITH n ] WITH min =min[Z1、Z2、…、Z j ,…,WITH n ] Among them, Z max and Z min They represent the maximum and minimum values ​​of the estimated deformation values ​​of all evaluation nodes, Z j represents the estimated value of the deformation value of the j-th evaluation node before normalization, j represents the number of the evaluation node, and n represents the total number of evaluation nodes; The estimated values ​​of the deformation values ​​of all evaluation nodes are scaled to the range of [0, 1], specifically: Zg j Represents the estimated value of the normalized deformation value of the j-th evaluation node.

4. The method for early warning of urban building deformation according to claim 3, characterized in that: The formula for calculating the relative deformation value of each evaluation node is: Among them, Xd j Represents the relative deformation value of the jth evaluation node. When identifying abnormal evaluation points, if Xd j ≥By, then the corresponding evaluation node is determined to be an abnormal evaluation node, and By is the relative deformation threshold; When calculating the density distribution index of each abnormal evaluation point, the neighborhood range is set to Where x represents the side length of the constructed three-dimensional grid, and the calculation is centered on the abnormal evaluation node. The relative deformation values ​​of all evaluation nodes in the spherical area of ​​radius are calculated, and the average is calibrated as the density distribution index of the corresponding abnormal evaluation node; When marking the risk level of abnormal assessment points according to the density distribution index, if Md j ≥0.8By, the abnormal assessment node is marked as the first risk node. If 0.8By>Md j >0.4By, then the abnormal assessment node is marked as the second risk node. If 0.4By≥Md j , then the abnormal assessment node is marked as the third risk node, Md j represents the density distribution index of the j-th evaluation node; When setting risk weights, the risk weight of the first risk node is set to α, the risk weight of the second risk node is set to β, and the risk weight of the third risk node is set to γ, α>β>γ>0, and α+β+γ=1.

5. The method for early warning of urban building deformation according to claim 4, characterized in that: The formula for constructing the early warning assessment model is: Among them, Fx represents the deformation risk index of the building to be evaluated, m represents the number of abnormal evaluation nodes, M represents the number of evaluation nodes, Xd1 p and P represent the relative deformation value of the pth first risk node and the total number of first risk nodes, respectively. q and Q represent the relative deformation value of the qth second risk node and the number of second risk nodes, respectively. w and W represent the relative deformation value of the wth third risk node and the number of third risk nodes, respectively. When Fx ≥ Fxy, a building deformation warning is issued, and Fxy represents the deformation risk threshold.

6. An early warning system for urban building deformation, characterized by: The early warning system is used to execute the early warning method for urban building deformation according to any one of claims 1 to 5, comprising: The model building module is used to obtain the architectural design data of the building to be evaluated, model the architectural design data using the GIS platform, build a 3D visualization model, use the key structural nodes inside the building as monitoring nodes, and assign 3D position coordinates to each monitoring node in the 3D visualization model; The deformation monitoring module is used to simultaneously obtain the deformation value of each monitoring node, map the deformation value of each monitoring node to the 3D position coordinates of the monitoring node, create a regular grid within the 3D visualization model, use each grid intersection as an evaluation node, obtain the 3D position coordinates of the evaluation node, and number them; A node screening module is used to interpolate the deformation value of each evaluation node using inverse distance weighted interpolation, obtain an estimated value of the deformation value of each evaluation node, normalize the estimated values ​​of the deformation values ​​of all evaluation nodes, calculate the relative deformation value of each evaluation node, and identify abnormal evaluation points based on the relative deformation values ​​of the evaluation nodes; The neighborhood analysis module is used to set the neighborhood range with the abnormal assessment point as the center, obtain the relative deformation values ​​of all assessment nodes in the neighborhood range of the abnormal assessment point, calculate the density distribution index of each abnormal assessment point, mark the abnormal assessment point with a risk level according to the density distribution index, and set the risk weight; The early warning analysis module is used to build an early warning assessment model based on the distribution density of all marked abnormal assessment points in the three-dimensional visualization model, as well as the relative deformation value and risk weight of each marked abnormal assessment point, to generate the deformation risk index of the building to be assessed, and determine whether to issue an early warning based on the deformation risk index.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, can implement the early warning method for urban building deformation according to any one of claims 1 to 5.

Images