A high-rise building group health monitoring method and system based on time-series InSAR

Abstract

The application discloses a kind of high-rise building group health monitoring method and system based on timing InSAR, belong to building health monitoring technical field.The method includes: obtaining multi-temporal SAR image, extracting scattering point deformation time series;Identify high-rise building group and group according to spatial position;To single building vertically divided height layer;Calculate the average deformation sequence of each height layer, the seasonal deformation parameters of the same height layer of the same building are counted, and a group deformation reference model is constructed;Abnormal height layer is identified based on dynamic threshold and statistical significance test;Map the anomaly to the corresponding building, and if there are multiple abnormal height layers in the same building, the structure abnormal risk is determined.The method does not require external temperature data, can effectively distinguish seasonal deformation and structural anomaly, and improve monitoring accuracy and automation level.

Description

Technical Field

[0001] This invention belongs to the field of building health monitoring technology, specifically relating to a method and system for health monitoring of high-rise building clusters based on temporal InSAR. Background Technology

[0002] With the acceleration of urbanization and the surge in the number of high-rise buildings, structural health monitoring faces significant challenges. Traditional manual inspections and localized sensor monitoring methods suffer from low efficiency, limited coverage, and difficulty in long-term sustainability. In recent years, temporal interferometric synthetic aperture radar (InSAR) technology has become an effective tool for building deformation monitoring due to its advantages of wide coverage, high precision, and non-contact operation. However, existing technologies still have the following significant drawbacks in practical applications:

[0003] Confusing seasonal deformation with structural anomalies: High-rise buildings experience periodic thermal expansion and contraction due to temperature changes, a phenomenon highly similar in deformation characteristics to abnormal deformations such as structural damage. Traditional InSAR methods struggle to distinguish between the two, easily leading to misjudgments.

[0004] Strong dependence on external data: Existing methods rely on accurate external temperature field data to establish thermal deformation correction models, but the cost of acquiring temperature field data in urban areas is high and the spatiotemporal resolution is insufficient, which seriously restricts the universality of the technology.

[0005] Limitations of individual building monitoring: Current technologies mostly focus on analyzing individual buildings, lacking the ability to explore the coordinated deformation patterns of building groups. High-rise buildings with similar structures within the same area have comparable thermodynamic response characteristics, and this group characteristic has not been effectively used to improve the reliability of anomaly detection.

[0006] Rigid threshold setting: Anomaly detection often uses fixed thresholds, which are difficult to adapt to the deformation fluctuation characteristics of different building groups and different seasons, and are prone to missed detections or false alarms.

[0007] Therefore, there is an urgent need to develop a monitoring method for high-rise building clusters that does not require external temperature data, can utilize group collaboration characteristics, and adaptively distinguish between seasonal deformation and structural anomalies, in order to improve the automation level and accuracy of large-scale urban building health assessment. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for health monitoring of high-rise building clusters based on time-series InSAR. With group collaborative analysis as its core, it solves key problems in the health monitoring of high-rise buildings, such as temperature dependence, high misjudgment rate, and difficulty in scaling, through algorithm innovation (dynamic threshold, time-weighted index) and engineering design (modular system). It has significant technological breakthroughs and industrialization potential, and can solve at least one of the technical problems involved in the background art.

[0009] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0010] This invention provides a method for health monitoring of high-rise building clusters based on time-series InSAR, comprising the following steps:

[0011] Step S1: Acquire multi-temporal high-resolution SAR images covering the target area;

[0012] Step S2: Process the SAR image using time-series InSAR technology to extract the deformation time series of stable scattering points within the region;

[0013] Step S3: Identify high-rise building clusters within the image range and divide the buildings into at least one group according to their spatial location;

[0014] Step S4: For a single building, divide it into multiple height layers along the vertical direction based on the elevation of the scattering point;

[0015] Step S5: Calculate the average deformation time series of each height layer, statistically analyze the seasonal deformation parameters of the same height layer of the same type of building within the building group, and construct a group deformation benchmark model; wherein the seasonal deformation parameters include amplitude, phase and period, and the benchmark model includes the mean, median and standard deviation of the deformation parameters of each height layer;

[0016] Step S6: Identify abnormal height layers that deviate significantly from the group deformation benchmark model by using dynamic thresholds and statistical significance tests.

[0017] Step S7: Map the abnormal height layers to the corresponding buildings. If the same building has ≥3 abnormal height layers or two or more consecutive abnormal height layers, then the building is determined to have structural abnormality risk.

[0018] Step S8: Mark the risky building as a monitoring target and start continuous monitoring.

[0019] Optionally, in step S2, the time-series InSAR technique is permanent scatterer interferometry (PSI) or small baseline set (SBAS) technique.

[0020] Optionally, in step S4, the height layer division is achieved by using a fixed number of layers or a fixed height interval.

[0021] Optionally, in step S6, the dynamic threshold and statistical significance test include:

[0022] Step S61, calculate the height layer In time t Actual deformation value Compared with the baseline model mean Deviation amount:

[0023] ;

[0024] Step S62, calculate the standardized deviation. ,in Standard deviation of the baseline model:

[0025] ;

[0026] Step S63, based on the time window length n and weight function Calculate the anomaly index :

[0027] ;

[0028] in The parameter α controls the time decay weight; n The length of the continuous observation time window; j Indicates the current time of the investigation t Previous continuum n At a specific moment within a set of observation time points

[0029] S64. When When it is judged as abnormal, the threshold is... ,in , , respectively, are the mean and standard deviation of the regional anomaly index, and k is a preset multiple.

[0030] Optionally, in step S64, the determination of an anomaly point requires that it meet any of the following conditions:

[0031] (a) Anomalies at three consecutive time points of the permanent scatterer (PS) point;

[0032] (b) The number of anomalous time points exceeds 50% of the total observation time points.

[0033] Optionally, in step S7, the determination of structural anomaly risk must meet the following conditions: the abnormal height layer continues to appear for ≥n consecutive time points, and n≥3.

[0034] Optionally, in step S8, the continuous monitoring includes:

[0035] Step S81: Calculate the overall tilt or settlement of the structure based on the deformation difference between the building top and the scattering point on the facade;

[0036] Step S82: Use a machine learning model to predict deformation trends and generate risk warnings.

[0037] The present invention also provides a time-series InSAR-based health monitoring system for high-rise building complexes for implementing the method described above, comprising:

[0038] The data acquisition module is used to acquire multi-temporal SAR images;

[0039] The InSAR processing module is used to extract the time series of scattering point deformation using permanent scatterer interferometry (PSI) or small baseline set (SBAS) techniques.

[0040] The building processing module is used to perform building grouping and height layer division.

[0041] The baseline modeling module is used to construct a baseline model for group deformation.

[0042] An anomaly detection module is used to identify abnormal buildings based on dynamic thresholds and statistical significance tests;

[0043] The output module is used to output the coordinates of risky buildings and monitoring recommendations.

[0044] Compared with the prior art, the advantages of this invention are as follows:

[0045] 1. This invention constructs a group deformation benchmark model for similar building complexes, which can distinguish between seasonal thermal expansion and contraction (normal deformation) and abnormal structural deformation without the need for external temperature field data, significantly improving the universality and engineering applicability of the method.

[0046] 2. This invention pioneers a collaborative reference analysis mechanism, which uses the deformation patterns of structurally similar buildings within a region to establish a benchmark, thereby enhancing the sensitivity and reliability of anomaly detection and overcoming the isolation defects of traditional single-unit monitoring.

[0047] 3. This invention employs a time-weighted anomaly index algorithm (combining Z-score standardization, Gaussian weighted window, and adaptive threshold) to dynamically adapt to the fluctuation characteristics of different building groups and time windows, thereby improving the scientific nature and accuracy of anomaly identification.

[0048] 4. The method provided by this invention is compatible with the wide coverage characteristics of time-series InSAR (PSI / SBAS) and, combined with automated processing procedures (such as building grouping and height layer division), achieves efficient batch processing to meet the monitoring needs of smart city-level building clusters.

[0049] 5. The modular system design of this invention covers the entire chain of data acquisition, processing, analysis, and output, making it easy to embed into existing remote sensing platforms and providing standardized tools for government supervision and engineering operation and maintenance.

[0050] In summary, this invention, with group collaborative analysis as its core, solves key problems in health monitoring of high-rise buildings, such as temperature dependence, high misjudgment rate, and difficulty in scaling up, through algorithmic innovation (dynamic threshold, time-weighted index) and engineering design (modular system). It has significant technological breakthroughs and industrialization potential. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0052] Figure 1 A flowchart illustrating a health monitoring method for high-rise building clusters based on temporal InSAR provided in an embodiment of the present invention;

[0053] Figure 2 A diagram of a health monitoring system for high-rise building complexes based on time-series InSAR provided in an embodiment of the present invention;

[0054] Figure 3 This is a PS-InSAR calculation result diagram of a high-rise building complex in a certain city, provided as an embodiment of the present invention.

[0055] Figure 4 This is a schematic diagram illustrating the comparison between the identified abnormal PS points and the baseline value provided in an embodiment of the present invention.

[0056] Figure 5 This is a schematic diagram illustrating the abnormal distribution of high-rise building clusters provided in an embodiment of the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0059] Please see Figure 1 As shown, this embodiment of the invention provides a method for health monitoring of high-rise building clusters based on time-series InSAR, including the following steps:

[0060] Step S1: Acquire multi-temporal high-resolution SAR images covering the target area;

[0061] Step S2: Process the SAR image using time-series InSAR technology to extract the deformation time series of stable scattering points within the region;

[0062] Step S3: Identify high-rise building clusters within the image range and divide the buildings into at least one group according to their spatial location;

[0063] Step S4: For a single building, divide it into multiple height layers along the vertical direction based on the elevation of the scattering point;

[0064] Step S5: Calculate the average deformation time series of each height layer, statistically analyze the seasonal deformation parameters of the same height layer of the same type of building within the building group, and construct a group deformation benchmark model; wherein the seasonal deformation parameters include amplitude, phase and period, and the benchmark model includes the mean, median and standard deviation of the deformation parameters of each height layer;

[0065] Step S6: Identify abnormal height layers that deviate significantly from the group deformation benchmark model by using dynamic thresholds and statistical significance tests.

[0066] Step S7: Map the abnormal height layers to the corresponding buildings. If the same building has ≥3 abnormal height layers or two or more consecutive abnormal height layers, then the building is determined to have structural abnormality risk.

[0067] Step S8: Mark the risky building as a monitoring target and start continuous monitoring.

[0068] In step S2, the time-series InSAR technique is permanent scatterer interferometry or small baseline set technique.

[0069] In step S4, the height layer division is achieved by using a fixed number of layers or a fixed height interval.

[0070] In step S6, the dynamic threshold and statistical significance test include:

[0071] Step S61, calculate the height layer The actual deformation value at time t Compared with the baseline model mean Deviation amount:

[0072] ;

[0073] Step S62, calculate the standardized deviation. ,in Standard deviation of the baseline model:

[0074] ;

[0075] Step S63, based on the time window length n and weight function Calculate the anomaly index :

[0076] ;

[0077] in The parameter α controls the time decay weight; n The length of the continuous observation time window; j Indicates the current time of the investigation t Previous continuum n At a specific moment within a set of observation time points

[0078] S64. When When it is judged as abnormal, the threshold is... ,in , , respectively, are the mean and standard deviation of the regional anomaly index, and k is a preset multiple.

[0079] In step S64, an outlier must meet any of the following conditions to be determined:

[0080] (a) The permanent scatterer point shows anomalies at three consecutive time points;

[0081] (b) The number of anomalous time points exceeds 50% of the total observation time points.

[0082] In step S7, the structural anomaly risk must be determined if the following conditions are met: the abnormal height layer appears continuously for ≥n consecutive time points, and n≥3.

[0083] In step S8, the continuous monitoring includes:

[0084] Step S81: Calculate the overall tilt or settlement of the structure based on the deformation difference between the building top and the scattering point on the facade;

[0085] Step S82: Use a machine learning model to predict deformation trends and generate risk warnings.

[0086] Combined Figure 2 As shown, the present invention also provides a health monitoring system for high-rise building clusters based on time-series InSAR for implementing the method, including a data acquisition module, an InSAR processing module, a building processing module, a baseline modeling module, an anomaly detection module, and an output module.

[0087] The data acquisition module is used to collect multi-temporal high-resolution SAR images of the study area.

[0088] The InSAR processing module is used to extract the time series of scattering point deformation through permanent scatterer interferometry or small baseline set technology.

[0089] The building processing module is used to perform building grouping and height layer division.

[0090] The benchmark modeling module is used to calculate the average deformation time series of each height layer, extract seasonal deformation parameters, and construct a group deformation benchmark model within the group.

[0091] The anomaly detection module is used to identify abnormal buildings based on dynamic thresholds and statistical significance tests.

[0092] The output module is used to output the coordinates of the risky building and monitoring recommendations.

[0093] The following specific embodiment 1 verifies the health monitoring method for high-rise building clusters based on temporal InSAR provided by the present invention.

[0094] Example 1

[0095] Example 1 provides a method for health monitoring of high-rise building clusters based on time-series InSAR, including the following steps:

[0096] Step S1: Acquire 16 SAR images of a residential community in a certain city, with a time range from June 26, 2023 to November 24, 2024;

[0097] Step S2: Process the SAR image using time-series InSAR technology to extract the deformation time series of stable scattering points within the region;

[0098] Step S3: Identify high-rise building clusters within the image range and divide the buildings into at least one group based on their spatial location (e.g., Figure 3 As shown, a total of 9 buildings are divided within the area.

[0099] Step S4: For a single building, divide it into multiple height layers along the vertical direction based on the elevation of the scattering point. Specifically, divide it into multiple height layers along the vertical direction in units of 5 meters, for a total of 63 height layers (0-155m).

[0100] Step S5: Calculate the average deformation time series of each height layer, statistically analyze the seasonal deformation parameters of the same height layer of the same type of building within the building group, and construct a group deformation benchmark model; wherein the seasonal deformation parameters include amplitude, phase and period, and the benchmark model includes the mean, median and standard deviation of the deformation parameters of each height layer;

[0101] Step S6: Identify abnormal height layers that significantly deviate from the group deformation baseline model through dynamic thresholding and statistical significance testing. The preset multiplier k is 2.5, the time window length is 5, and the time decay weight parameter α is 1.5. The identification results are as follows: Figure 4 As shown, a total of 978 abnormal time points were identified, and these abnormal points were filtered according to the following two criteria:

[0102] (a) The permanent scatterer point shows anomalies at three consecutive time points;

[0103] (b) The number of anomalous time points exceeds 50% of the total observation time points.

[0104] A total of 28 abnormal PS points were identified.

[0105] Step S7: Map the abnormal height layers to the corresponding buildings. If the same building has ≥3 abnormal height layers or two or more consecutive abnormal height layers, then the building is determined to have a structural anomaly risk. Figure 5 Analysis shows that the currently identified abnormal PS points are distributed relatively discretely, and no concentrated anomalies have been found so far.

[0106] Step S8: Mark the risky building as a monitoring target and start continuous monitoring.

[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0108] Furthermore, it should be noted that the scope of the methods and systems in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0109] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A high-rise building group health monitoring method based on time-series InSAR, characterized in that, The method comprises the following steps: Step S1, acquiring multi-temporal high-resolution SAR images covering a target area; Step S2, processing the SAR images using time-series InSAR technology to extract deformation time series of stable scatterers in the area; Step S3, identifying high-rise building groups in the image range and dividing the buildings into at least one group according to spatial positions; Step S4, for a single building, dividing it into multiple height layers along the vertical direction according to the elevations of the scatterers; Step S5, calculating the average deformation time series of each height layer, and statistically calculating the seasonal deformation parameters of the same height layer of similar buildings in the building group to construct a group deformation reference model; wherein the seasonal deformation parameters include amplitude, phase and period, and the reference model includes the mean, median and standard deviation of the deformation parameters of each height layer; Step S6, identifying abnormal height layers that have significant deviations from the group deformation reference model through dynamic threshold and statistical significance test; Step S7, mapping the abnormal height layers to the corresponding buildings, and if there are ≥3 abnormal height layers in the same building or abnormalities occur in two or more consecutive height layers, it is determined that the building has a structural abnormality risk; Step S8, marking the risk building as a monitoring target and starting continuous monitoring.

2. The method of claim 1, wherein, In step S2, the time-series InSAR technology is permanent scatterer interferometry or small baseline set technology.

3. The method of claim 1, wherein, In step S4, the height layer division is implemented by fixed number of layers or fixed height interval.

4. The method of claim 1, wherein, In step S6, the dynamic threshold and statistical significance test include: Step S61, calculate height layer Actual deformation value at time t Deviation amount from reference model mean value: ； Step S62, calculating the standardized deviation amount wherein is the reference model standard deviation: ； Step S63, based on the time window length n and the weight function , calculate the anomaly index : ； wherein the parameter a controls the time decay weight; n is the length of the time window of the continuous observation; j denotes the time instant currently under consideration t the preceding continuous n observation time points; S64, when an abnormality is determined, threshold wherein , are the mean and standard deviation of the regional anomaly index, respectively, and k is a preset multiple.

5. The method of claim 4, wherein, In step S64, the abnormal point needs to meet any one of the following conditions: (a) the permanent scatterer point is abnormal for three consecutive time points; (b) the number of abnormal time points exceeds 50% of the total observation time points.

6. The method of claim 1, wherein, In step S7, the determination of structural abnormality risk needs to meet: the abnormal height layer continuously appears at subsequent ≥n consecutive time points, and n≥3.

7. The method of claim 1, wherein, In step S8, the continuous monitoring includes: Step S81, calculating the overall tilt or settlement of the structure according to the deformation difference between the top and facade scatterers of the building; Step S82, using a machine learning model to predict the deformation trend and generate a risk warning.

8. A time-series InSAR based high-rise building cluster health monitoring system for implementing the method according to any one of claims 1 to 7, characterized in that, It comprises: a data acquisition module for collecting multi-temporal SAR images; an InSAR processing module for extracting scatterer deformation time series by permanent scatterer interferometry or small baseline set technology; a building processing module for performing building grouping and height layer division; a reference modeling module for constructing a group deformation reference model; an anomaly detection module for identifying abnormal buildings based on dynamic threshold and statistical significance test; an output module for outputting risk building coordinates and monitoring suggestions.

Images