Building deformation monitoring method and system based on satellite-borne InSAR data

Abstract

The invention relates to the technical field of building monitoring, in particular to a building deformation monitoring method and system based on satellite-borne InSAR data. The method comprises the following steps: periodically collecting satellite-borne InSAR data of a target building; performing time sequence difference processing on the acquired data to obtain a plurality of groups of inclination monitoring data, crack monitoring data and settlement monitoring data of the target building, forming a deformation monitoring data set by a set of all the monitoring data, and coupling each group of data to obtain a building deformation value; a deformation state classification model is constructed by adopting a clustering algorithm, the model is pre-trained based on the building deformation value, and the output of the model is a deformation state classification result; and inputting the building deformation value corresponding to the current period into the pre-trained model, outputting to obtain the current deformation state classification result, and sending a deformation early warning signal, thereby greatly simplifying the deformation monitoring processing flow, and effectively improving the accuracy of structural state evaluation while ensuring the timeliness of building deformation monitoring early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of building monitoring, and in particular to a building deformation monitoring method and system based on spaceborne InSAR data. Background Art

[0002] Spaceborne InSAR, or satellite-borne synthetic aperture radar interferometry, is a radar technology used for geodetic surveying and remote sensing. InSAR uses two or more synthetic aperture radar (SAR) images and the phase differences of the waves returning to the satellite to calculate the topography, landforms, and subtle surface changes in the target area. This technology can potentially measure millimeter-level deformations spanning days to years. Unlike visible or infrared light, radar waves can penetrate most clouds, fog, and smoke to observe surface objects, and are equally effective in darkness. Therefore, due to InSAR's wide-area coverage and its excellent monitoring capabilities even in inclement weather and at night, InSAR has also been widely used in the construction industry.

[0003] For example, Chinese patent CN118330627A provides a slope aperture radar displacement monitoring and early warning system based on a sparrow search algorithm, which enables all-day, all-weather, and large-scale intelligent monitoring and early warning. However, this prior art still has the following technical problems:

[0004] 1. Existing technology uses differential interferometry (D-InSAR) to process SAR image phase differences, but assumes that the atmospheric delay phase and noise phase are equal in the two measurements. However, in actual applications, atmospheric conditions may change over time (such as humidity and temperature fluctuations), and noise may not be completely offset due to environmental interference (such as mining dust and equipment vibration). This can lead to errors in phase difference calculation and affect displacement monitoring accuracy.

[0005] 2. Existing technologies require multiple steps to process SAR images, including image registration, phase unwrapping, and atmospheric phase compensation. They rely particularly on the minimum norm method to unwrap the phase and the least squares method to calculate deformation. Furthermore, the sparrow search algorithm requires complex parameter adjustments, resulting in high computational complexity and a large amount of calculations. This, in turn, causes delayed response times for building deformation monitoring systems, making it difficult to meet the requirements for timely warnings.

[0006] 3. The warning logic of the existing technology is based on whether the stability coefficient output by the sparrow search algorithm exceeds the reference range. However, it only relies on the analysis of a single stability coefficient and a fixed parameter range warning mechanism to judge risks. It will undoubtedly ignore the complex working conditions of other deformation dimensions, resulting in low accuracy of structural status assessment. Summary of the Invention

[0007] In response to the above technical problems, the present invention proposes a building deformation monitoring method and system based on spaceborne InSAR data, aiming to significantly simplify the monitoring and processing process, while ensuring the timeliness of building deformation monitoring and early warning, and effectively improving the accuracy of structural status assessment.

[0008] In a first aspect, the present application provides a building deformation monitoring method based on spaceborne InSAR data, comprising the following steps:

[0009] Periodically collect spaceborne InSAR data of target buildings;

[0010] Perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building.

[0011] Couple each set of tilt monitoring data, crack monitoring data, and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value;

[0012] A clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is the deformation state classification result, and the deformation state categories include qualified, abnormal, and severe;

[0013] Input the building deformation value corresponding to the current period into the pre-trained deformation state classification model, and output the current deformation state classification result;

[0014] A deformation warning signal is issued based on the current deformation classification results.

[0015] In some embodiments, time-series difference processing is performed on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building, including:

[0016] The differences in tilt, crack volume and settlement of spaceborne InSAR data from adjacent periods are calculated, with each period as a group, to obtain several groups of tilt monitoring data, crack monitoring data and settlement monitoring data of the target building.

[0017] In some embodiments, a clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is a deformation state classification result, including:

[0018] Step 201: construct a deformation state classification model and preset three primary cluster centers K1, K2, and K3, representing a qualified deformation state, an abnormal deformation state, and a severe deformation state, respectively;

[0019] Step 202: randomly select three data points from the building deformation values as primary cluster centers K1, K2, and K3 respectively;

[0020] Step 203: Calculate the distance between each data point in the building deformation value and the center of each primary cluster, and assign the data point to the primary cluster closest to it to form three intermediate clusters.

[0021] Step 204, respectively calculating the mean of all data points in each intermediate cluster as the new primary cluster center;

[0022] Step 205 , repeating steps 203 - 204 until a preset convergence condition is reached, thereby obtaining a pre-trained deformation state classification model.

[0023] In some embodiments, in step 204, the mean of all data points in each intermediate cluster is calculated as the new primary cluster center, including:

[0024] When there is no data point in the intermediate cluster during the iteration process, the data point farthest from the current primary cluster center is selected as the new primary cluster center.

[0025] In some embodiments, pre-training a deformation state classification model based on building deformation values includes:

[0026] The building deformation values of the latest Q cycles are stored. When the building deformation values of each R cycle are added, the deformation state classification model is pre-trained based on the latest Q+R building deformation values.

[0027] In some embodiments, issuing a deformation warning signal based on the current deformation classification result further includes:

[0028] Based on the deformation monitoring data set, the building stability value is calculated;

[0029] Based on the current deformation classification results and building stability value, a deformation warning signal is issued.

[0030] In some embodiments, the deformation monitoring data set includes settlement and crack volume of data points, and the building stability value is calculated based on the deformation monitoring data set, including:

[0031] Based on the settlement amount of the data points, the settlement rate is calculated, and the tilt reference value is calculated using the double-point difference method;

[0032] The maximum allowable value constraint method is used to normalize the settlement rate, tilt reference value and crack volume, and then a weighted sum is performed to obtain the building stability value.

[0033] In some embodiments, based on the current deformation classification result and the building stability value, issuing a deformation warning signal includes:

[0034] Preset threshold range of building stability value (E1, E2);

[0035] If the current deformation classification result is qualified and the building stability value is greater than or equal to E2, a good deformation warning signal is issued;

[0036] If the current deformation classification result is qualified and the building stability value is within the threshold range (E1, E2), a relatively stable deformation warning signal is issued;

[0037] If the current deformation classification result is abnormal and the building stability value is within the threshold range (E1, E2), a poor deformation warning signal is issued;

[0038] If the current deformation classification result is abnormal and the building stability value is less than or equal to E1, an unstable deformation warning signal is issued;

[0039] If the current deformation classification result is severe, an extremely poor deformation warning signal will be issued at any building stability value.

[0040] In a second aspect, the present application provides a building deformation monitoring system based on spaceborne InSAR data, comprising:

[0041] Data acquisition module, used to periodically collect spaceborne InSAR data of target buildings;

[0042] The data preprocessing module is used to perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building;

[0043] The deformation value calculation module is used to couple each set of tilt monitoring data, crack monitoring data and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value;

[0044] The deformation state classification module is used to build a deformation state classification model and pre-train the deformation state classification model based on the building deformation value. The output of the model is the deformation state classification result. The deformation state categories include qualified, abnormal, and severe. The building deformation value corresponding to the current cycle is input into the pre-trained deformation state classification model, and the output is the current deformation state classification result.

[0045] The early warning module is used to issue a deformation early warning signal based on the current deformation classification result.

[0046] In some embodiments, the system further comprises:

[0047] The stability value calculation module is used to calculate the building stability value based on the deformation monitoring data set;

[0048] The early warning module is used to issue a deformation early warning signal based on the current deformation classification result and the building stability value.

[0049] The beneficial technical effects of the present invention include at least:

[0050] 1. A building deformation monitoring method and system based on spaceborne InSAR data is adopted. Through the collaborative innovation of "time series difference processing, multidimensional data coupling, and data-driven dynamic clustering and classification," a closed-loop optimization monitoring mechanism is formed. Specifically: First, a dynamic baseline is constructed through a double-difference processing mechanism (spatial phase difference + time series difference). Adopting adjacent period data as a moving reference frame, this avoids the cumulative error of traditional fixed-time reference point monitoring. At the same time, it solves the error problem caused by the assumption of constant atmospheric state in existing technologies. Cleaner deformation monitoring data can be directly obtained without the need for complex atmospheric phase compensation processing. Secondly, by weighted coupling of the three key deformation monitoring data of tilt, cracks, and settlement, the building deformation value is generated, forming a multi-dimensional integrated deformation index. Compared with the single stability coefficient of existing technologies, this can reduce the false alarm rate of early warning to a certain extent. Finally, the dynamic deformation state classification model constructed based on the clustering algorithm avoids the complex computational complexity of the sparrow search algorithm in existing technologies and greatly improves the timeliness of early warning. The three work together to form a technical chain of "error suppression → comprehensive quantification → dynamic classification", achieving a synergistic breakthrough in the building's deformation monitoring accuracy and data processing efficiency, achieving the beneficial effect of "1+1>2".

[0051] 2. The warning logic of the existing technology is based on whether the stability coefficient output by the sparrow search algorithm exceeds the reference range. However, it only relies on the analysis of a single stability coefficient and a fixed parameter range warning mechanism to judge risks. It will undoubtedly ignore the complex working conditions of other deformation dimensions, resulting in low accuracy of structural status assessment. To this end, this application proposes a monitoring and early warning method of "qualitative-quantitative dual-modal collaborative decision-making" to achieve full-chain optimization of building deformation monitoring from data collection to risk decision-making. Specifically: first, the atmospheric delay and noise interference are suppressed through time difference processing to generate high signal-to-noise ratio data. Then, the deformation state classification model constructed by the clustering algorithm is used to provide qualitative judgment of the deformation state ( The system can provide a quantitative assessment of the building stability value (qualified / abnormal / serious), and the two can work together to achieve "qualitative + quantitative" dual verification, and finally trigger a five-level warning signal (good, relatively stable, poor, unstable, and extremely poor). It effectively solves the problems of atmospheric interference, high computational complexity, single warning, and reliance on fixed threshold judgment in existing technologies. It also adapts to different building types and environmental changes through a dynamic threshold adjustment mechanism (adaptively updating the stability value threshold interval based on the cluster mean and standard deviation), effectively improving the accuracy and reliability of the overall building deformation status assessment while ensuring the timeliness of building deformation monitoring and early warning, and effectively reducing the false alarm rate of early warning.

[0052] Other features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The present invention will be further described below with reference to the accompanying drawings:

[0054] Figure 1 This is a flow chart of a building deformation monitoring method based on spaceborne InSAR data according to an embodiment of the present invention.

[0055] Figure 2 This is a flow chart of a building deformation monitoring method based on spaceborne InSAR data according to an embodiment of the present invention.

[0056] Figure 3 The figure is a schematic structural diagram of a building deformation monitoring system based on spaceborne InSAR data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following is an explanation and description of the technical solutions of the embodiments of the present invention in conjunction with the drawings of the embodiments of the present invention. However, the following embodiments are only preferred embodiments of the present invention and are not exhaustive. Based on the embodiments in the implementation manner, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of the present invention.

[0058] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0059] Please see the attached Figure 1 , Figure 1 A flow chart of a building deformation monitoring method based on spaceborne InSAR data provided in one embodiment of this specification is shown.

[0060] like Figure 1 As shown, the building deformation monitoring method based on spaceborne InSAR data may include at least the following steps:

[0061] Step 101: Periodically collect spaceborne InSAR data of the target building.

[0062] Among them, the revisit period of a single SAR satellite is usually 12-24 days (such as 12 days for Sentinel-1), which makes it difficult to capture sudden building deformation. Therefore, by deploying multiple SAR satellites (such as the COSMO-SkyMed constellation), the revisit period can be shortened to provide a data basis for building safety monitoring with hourly to daily response. This is not described in detail in this embodiment.

[0063] Step 102 , performing time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building.

[0064] Specifically, in this embodiment, time-series difference processing is performed on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building, including:

[0065] The differences in tilt, crack volume and settlement of spaceborne InSAR data from adjacent periods are calculated, with each period as a group, to obtain several groups of tilt monitoring data, crack monitoring data and settlement monitoring data of the target building.

[0066] For example, the settlement amount obtained by identifying the target building with the spaceborne InSAR data of the mth period is subtracted from the settlement amount of the target building in the m-1th period to obtain the settlement monitoring data; the inclination obtained by identifying the target building with the spaceborne InSAR data of the mth period is subtracted from the inclination of the target building in the m-1th period to obtain the inclination monitoring data; the crack volume obtained by identifying the target building with the spaceborne InSAR data of the mth period is subtracted from the crack volume of the target building in the m-1th period to obtain the crack monitoring data.

[0067] Among them, the implementation methods of obtaining settlement, inclination and crack volume based on space-borne InSAR data can refer to the existing technology. For example, settlement data is the most direct identification result of space-borne InSAR data. You can refer to the settlement data preprocessing method in Chinese patent CN117723016A "A building settlement monitoring method based on PS-InSAR technology and level measurement". For example, the identification of inclination data can refer to the inclination data preprocessing method in Chinese patent CN106772377A "A building deformation monitoring method based on InSAR", etc. This embodiment will not be repeated here.

[0068] Among them, the deformation monitoring data set of the target building constructed in this embodiment can include both the change monitoring data obtained by time-series difference processing of the space-borne InSAR data and the original monitoring data obtained by identifying the space-borne InSAR data in each period (such as the settlement, inclination, and crack volume obtained by data point identification).

[0069] Existing techniques use differential interferometry (D-InSAR) to process SAR image phase differences, but assume that the atmospheric delay phase and noise phase are equal in both measurements. However, in practical applications, atmospheric conditions may vary over time (such as humidity and temperature fluctuations), and noise may not be fully offset due to environmental interference (such as mining dust and equipment vibration), resulting in errors in phase difference calculation and affecting displacement monitoring accuracy. To address this, this embodiment proposes a "double-difference" processing mechanism that combines traditional InSAR spatial phase difference with time series difference superposition. Spaceborne InSAR data from adjacent periods is used as a dynamic baseline to establish a moving reference frame for building conditions, avoiding the cumulative errors of traditional fixed-time reference point monitoring. At the same time, common errors (such as atmospheric delay and orbital error) are offset through time series difference processing. Furthermore, because atmospheric conditions in adjacent periods are similar, the error problem caused by the existing assumption of constant atmospheric conditions is proactively addressed. This allows for direct acquisition of cleaner deformation monitoring data without the need for complex atmospheric phase compensation processing, improving displacement monitoring accuracy and providing a reliable data foundation for subsequent analysis.

[0070] Step 103: coupling each set of tilt monitoring data, crack monitoring data, and settlement monitoring data in the deformation monitoring data set, and recording the coupling result as the building deformation value;

[0071] Specifically, in this embodiment, the coupling method for each set of tilt monitoring data, crack monitoring data and settlement monitoring data is to perform weighted summation on each set of tilt monitoring data, crack monitoring data and settlement monitoring data, wherein the weight factors of the tilt monitoring data, crack monitoring data and settlement monitoring data can be preset based on experience, or adjusted and optimized according to specific building types, years of use, geological conditions and other factors. As deformation monitoring data continues to accumulate, the weight factors can be further optimized and verified through methods such as data analysis and machine learning. This embodiment does not limit this.

[0072] It can be understood that compared with the existing technology that only relies on the sparrow search algorithm to predict the slope displacement instability to obtain the stability coefficient to judge the risk, the building deformation value in this embodiment considers the three key deformation factors of the building (tilt, cracks, and settlement) to comprehensively quantify the risk, covering a more comprehensive deformation dimension. While significantly reducing the calculation complexity, it can effectively reflect the overall deformation of the target building, avoid misjudgment of a single parameter, and improve the accuracy of subsequent analysis and early warning.

[0073] In step 104, a clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is the deformation state classification result. The deformation state categories include qualified, abnormal, and severe.

[0074] Furthermore, in this embodiment, a clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is the deformation state classification result, including:

[0075] Step 201 : construct a deformation state classification model and preset three primary cluster centers K1 , K2 , and K3 , which respectively represent a qualified deformation state ( K1 ), an abnormal deformation state ( K2 ), and a severe deformation state ( K3 ).

[0076] Step 202: randomly select three data points {u1, u2, u3} from the building deformation values as primary cluster centers K1, K2, and K3 respectively;

[0077] It can be understood that the random selection of the initial cluster center in this embodiment depends on the distribution of the current building deformation value dataset rather than a fixed preset, which helps the model adapt to the data characteristics of different monitoring periods (such as seasonal changes leading to differences in deformation patterns).

[0078] Step 203: Calculate the building deformation value for each data point xi The distance to each primary cluster center {u1, u2, u3}, and the data point x i Assigned to the nearest primary cluster to form three intermediate clusters U1, U2, and U3, thereby achieving the classification of building deformation values.

[0079] In this embodiment, the distance between each data point in the building deformation value and the center of each primary cluster can be calculated by calculating the Euclidean distance or the Mahalanobis distance, etc., which is not limited in this embodiment.

[0080] Step 204 : Calculate the mean of all data points in each intermediate cluster as the new primary cluster center.

[0081] It can be understood that for each intermediate cluster, the mean of all data points therein is calculated as the new primary cluster center.

[0082] On the other hand, in this embodiment, in step 204, the mean of all data points in each intermediate cluster is calculated as the new primary cluster center, and the following steps are also included:

[0083] When there is no data point in the intermediate cluster during the iteration process, the data point farthest from the current primary cluster center is selected as the new primary cluster center.

[0084] It can be understood that this implementation also provides an anomaly absorption mechanism for the deformation state classification model. When an empty cluster appears during a certain iteration, the data point farthest from the current primary cluster center is automatically selected as the new primary cluster center to prevent model failure due to sudden changes in data distribution, thereby effectively improving the stability of the model.

[0085] Step 205 , repeating steps 203 - 204 until a preset convergence condition is reached, thereby obtaining a pre-trained deformation state classification model.

[0086] The preset convergence condition may be a preset number of iterations, or may be that the change in the center of the primary cluster is less than a threshold, which is not limited in this embodiment.

[0087] It can be understood that in each iteration of this embodiment, the primary cluster center is readjusted according to the actual distribution of the current data points. By continuously recalculating the mean of all data points in the intermediate cluster, the deformation state classification model can capture changes in the distribution of building deformation value data, such as the intensification or easing of building deformation trends, and thus dynamically adjust the classification criteria so that the cluster center gradually approaches the actual data distribution to reflect the inherent structure of the building deformation value.

[0088] Furthermore, in this embodiment, pre-training the deformation state classification model based on the building deformation value further includes:

[0089] The building deformation values of the latest Q cycles (Q can be 20-30) are stored. When the building deformation values of each R cycle are added, the deformation state classification model is pre-trained based on the latest Q+R building deformation values.

[0090] It can be understood that in this embodiment, a sliding window mechanism is used to periodically retrain the deformation state classification model with the newly monitored building deformation value data. When new data arrives, the deformation state classification model re-executes the clustering process, thereby achieving dynamic updates to adapt to long-term changes in building deformation (such as the cumulative effect of foundation settlement, etc.) and improve the monitoring sensitivity of the deformation state classification model to gradual deformation.

[0091] This embodiment combines clustering models with time-series difference processing and multi-dimensional data coupling to construct a data-driven dynamic clustering system. It simplifies the complex computational processes of existing technologies, such as sparrow search algorithm modeling and least squares calculation, into a lightweight monitoring chain of "data cleaning → rapid classification". After temporal difference processing suppresses noise and couples multi-dimensional deformation factors to obtain building deformation values, the model automatically divides data categories through unsupervised learning, directly inputs the building deformation value data into the deformation state classification model constructed using the clustering algorithm, and outputs the deformation state classification results. While ensuring data reliability, it significantly shortens the data processing time, greatly improves the timeliness of early warning, and provides real-time guarantee for sudden building deformation monitoring.

[0092] Step 105: Input the building deformation value corresponding to the current period into the pre-trained deformation state classification model, and output the current deformation state classification result.

[0093] Step 106: issuing a deformation warning signal based on the current deformation classification result.

[0094] Among them, the deformation warning signal in this embodiment includes but is not limited to sending a warning text message to the preset responsible person, activating the on-site sound and light alarm device, pushing the red pop-up window and vibration reminder of the mobile monitoring APP, generating an electronic work order containing a deformation parameter QR code and sending it to the maintenance department, etc. This embodiment does not limit this.

[0095] Specifically, the implementation method of issuing deformation warning signals based on the current deformation classification results is as follows:

[0096] If the current deformation classification result is qualified, a good deformation warning signal is issued;

[0097] If the current deformation classification result is abnormal, a poor deformation warning signal is issued;

[0098] If the current deformation classification result is severe, an extremely bad deformation warning signal will be issued.

[0099] In summary, this embodiment forms a closed-loop optimization monitoring mechanism through the collaborative innovation of "time series difference processing-multidimensional data coupling-data-driven dynamic clustering classification". Specifically: First, a dynamic baseline is constructed through a double difference processing mechanism (spatial phase difference + time series difference), and the adjacent period data is used as a moving reference frame to avoid the cumulative error of traditional fixed time reference point monitoring. At the same time, it solves the error problem caused by the assumption that the atmospheric state remains unchanged in the existing technology, and can directly obtain cleaner deformation monitoring data without the need for complex atmospheric phase compensation processing; secondly, by tilting The three key deformation factors of tilt, crack and settlement are weightedly coupled to generate the building deformation value, forming a multi-dimensional integrated deformation index. Compared with the single stability coefficient of the existing technology, it can effectively reduce the false alarm rate of the early warning; finally, the dynamic deformation state classification model constructed based on the clustering algorithm avoids the complex calculation amount of the sparrow search algorithm in the existing technology, greatly improving the timeliness of the early warning. The three work together to form a technical chain of "error suppression → comprehensive quantification → dynamic classification", achieving a synergistic breakthrough in the deformation monitoring accuracy and data processing efficiency of the building, and achieving the beneficial effect of "1+1>2".

[0100] Example 2:

[0101] Please see the attached Figure 2 , Figure 2 A flow chart of a building deformation monitoring method based on spaceborne InSAR data provided in yet another embodiment of this specification is shown.

[0102] like Figure 2 As shown, the building deformation monitoring method based on spaceborne InSAR data includes the following steps:

[0103] Step 301, periodically collecting spaceborne InSAR data of the target building;

[0104] Step 302: Perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The set of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes a deformation monitoring data set of the target building.

[0105] Step 303: Couple each set of tilt monitoring data, crack monitoring data, and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value;

[0106] Step 304: A deformation state classification model is constructed using a clustering algorithm and pre-trained based on the building deformation value. The output of the model is the deformation state classification result. The deformation state categories include acceptable, abnormal, and severe.

[0107] Step 305: Input the building deformation value corresponding to the current period into the pre-trained deformation state classification model, and output the current deformation state classification result;

[0108] Step 306: Calculate the building stability value based on the deformation monitoring data set.

[0109] Specifically, in this embodiment, the deformation monitoring data set includes the settlement amount and crack volume of the data point. Based on the deformation monitoring data set, the building stability value is calculated, including:

[0110] In step 401, the sedimentation rate is calculated based on the sedimentation amount of the data point, and the tilt reference value is calculated using the double-point difference method, which can be specifically expressed as:

[0111]

[0112] Among them, C a represents the sedimentation rate, ΔD represents the difference in sedimentation between two adjacent observations of the same data point, ΔT represents the time interval between two adjacent observations, and B a Indicates the tilt reference value, B b and B c They represent the settlement of two data points in the tilt direction of the target building, L represents B b and B c The horizontal distance between the two corresponding data points.

[0113] Step 402: Use the maximum allowable value constraint method to normalize the settlement rate, tilt reference value, and crack volume, and then perform weighted summation to obtain the building stability value. a It can be expressed as:

[0114]

[0115] Wherein, vmax represents the maximum allowable settlement rate, θmax represents the maximum allowable inclination, A represents the crack volume, and Amax represents the maximum allowable crack volume. The maximum allowable values are set according to building codes. H1, H2, and H3 represent corresponding preset weights. The weight distribution in the calculation process of the building stability value in this embodiment is determined empirically to adapt to the building stability status assessment of different building structure types (for example, H2=0.6 is suitable for high-rise buildings).

[0116] It can be understood that this embodiment first evaluates the settlement dimension through the settlement rate per unit time, reflects the dynamic process of settlement, and helps to identify sudden settlement events. Secondly, the double-point difference method is used to calculate the tilt reference value, and the tilt dimension is evaluated by the ratio of the two-point settlement difference to the horizontal distance, reflecting the rate of change of the tilt angle, which is used to quantify the tilt trend of the building, and helps to avoid the tilt monitoring error caused by the limitations of the radar line of sight (LOS) direction in the existing technology. Then, the three dimensions of tilt, settlement, and crack volume are normalized by the maximum allowable value constraint to achieve comparability of multi-source heterogeneous data. Finally, the weight distribution of empirical coefficients is adapted to different building structure types, and the weighted summation is used to obtain the building stability value to comprehensively evaluate the deformation stability state of the target building.

[0117] Step 307: issuing a deformation warning signal based on the current deformation classification result and the building stability value.

[0118] Specifically, in this embodiment, based on the current deformation classification result and the building stability value, a deformation warning signal is issued, including:

[0119] Preset threshold range of building stability value (E1, E2);

[0120] If the current deformation classification result is qualified and the building stability value is greater than or equal to E2, a good deformation warning signal is issued;

[0121] If the current deformation classification result is qualified and the building stability value is within the threshold range (E1, E2), a relatively stable deformation warning signal is issued;

[0122] If the current deformation classification result is abnormal and the building stability value is within the threshold range (E1, E2), a poor deformation warning signal is issued;

[0123] If the current deformation classification result is abnormal and the building stability value is less than or equal to E1, an unstable deformation warning signal is issued;

[0124] If the current deformation classification result is severe, an extremely poor deformation warning signal will be issued at any building stability value.

[0125] It can be understood that, in the threshold range (E1, E2) of the building stability value, E1 is the critical lower limit of stability, and E2 is the critical upper limit of stability.

[0126] The above steps 301 to 305 may refer to steps 101 to 105 in the first embodiment, and will not be described in detail in this embodiment.

[0127] The warning logic of the existing technology is based on whether the stability coefficient output by the sparrow search algorithm exceeds the reference range. However, it only relies on the analysis of a single stability coefficient and a fixed parameter range warning mechanism to judge risks. It will undoubtedly ignore the complex working conditions of other deformation dimensions, resulting in low accuracy of structural status assessment. To this end, this embodiment proposes a monitoring and early warning method of "qualitative-quantitative dual-modal collaborative decision-making" to achieve full-chain optimization of building deformation monitoring from data collection to risk decision-making. Specifically: first, atmospheric delay and noise interference are suppressed through time difference processing to generate high signal-to-noise ratio data. Then, a deformation state classification model constructed by adopting a clustering algorithm is used to provide a qualitative judgment of the deformation state (qualified / abnormal / serious). At the same time, a quantitative assessment is provided in combination with the building stability value. The two work together to achieve "qualitative + quantitative" dual verification. Finally, a five-level early warning signal is triggered collaboratively (good, relatively stable, poor, unstable, and extremely poor). This effectively solves the rigid problems of atmospheric interference, high computational complexity, single early warning, and reliance on fixed threshold judgment in the existing technology. It also adapts to different building types and environmental changes through a dynamic threshold adjustment mechanism (adaptively updating the stability value threshold interval based on the cluster mean and standard deviation), ensuring the accuracy and reliability of the overall building deformation monitoring and effectively reducing the false alarm rate of the early warning.

[0128] On the other hand, this embodiment also includes a threshold dynamic adjustment mechanism, specifically:

[0129] Using the preset threshold interval of the building stability value as the initial threshold interval;

[0130] When the building deformation value of each R period is added and the deformation state classification model is pre-trained again, the deformation state classification model recalculates the primary cluster center, and the threshold interval is updated based on the data distribution of the primary cluster center. The updated threshold interval can be expressed as:

[0131] E2=μ k2 -1.5σ k2

[0132] E1=μ k3 -1.5σ k3

[0133] Among them, μ k2 and σ k2 They represent the mean and standard deviation of the abnormal deformation state cluster center, μ k3 and σ k3 are the mean and standard deviation of the cluster centers of severe deformation states.

[0134] It can be understood that the threshold dynamic adjustment mechanism proposed in this embodiment realizes the dynamic calibration of the threshold parameters along with the distribution of building deformation value data by binding the threshold interval with the statistical characteristics of the cluster center. Specifically, each new R cycle of data triggers model retraining → cluster center update → threshold interval reconstruction → new threshold to guide the next cycle warning. Compared with the preset fixed threshold, this "model iteration + threshold iteration" dual closed-loop system can keep the threshold parameters synchronized with the latest deformation pattern, so that it can automatically adapt to the data characteristics of different building types and different monitoring stages (such as changes in deformation characteristics during the construction period and the operation period), effectively reducing the false alarm rate of warnings. For example, when the building enters the aging stage and causes the overall shift of the baseline deformation value, the threshold interval will be adjusted synchronously with the drift of the cluster center to avoid the risk of missed reports caused by the preset fixed threshold.

[0135] Example 3:

[0136] Please see the attached Figure 3 , Figure 3 This is a schematic structural diagram of a building deformation monitoring system based on space-borne InSAR data provided in yet another embodiment of this specification.

[0137] like Figure 3 As shown, the building deformation monitoring system based on spaceborne InSAR data may include at least a data acquisition module 1, a data preprocessing module 2, a deformation value calculation module 3, a deformation state classification module 4, and an early warning module 5, wherein:

[0138] Data acquisition module 1, used to periodically collect spaceborne InSAR data of the target building;

[0139] Data preprocessing module 2 is used to perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building;

[0140] The deformation value calculation module 3 is used to couple each set of tilt monitoring data, crack monitoring data and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value;

[0141] The deformation state classification module 4 is used to construct a deformation state classification model and pre-train the deformation state classification model based on the building deformation value. The output of the model is the deformation state classification result. The deformation state categories include qualified, abnormal, and severe. The building deformation value corresponding to the current cycle is input into the pre-trained deformation state classification model, and the output is the current deformation state classification result.

[0142] The early warning module 5 is used to issue a deformation early warning signal based on the current deformation classification result.

[0143] Furthermore, in this embodiment, the building deformation monitoring system based on spaceborne InSAR data may further include:

[0144] The stability value calculation module is used to calculate the building stability value based on the deformation monitoring data set;

[0145] The early warning module is also used to issue a deformation early warning signal based on the current deformation classification result and the building stability value.

[0146] It is understandable that the technical concept of the building deformation monitoring system based on space-borne InSAR data provided in this embodiment is similar to the technical concept of the building deformation monitoring method based on space-borne InSAR data provided in the previous embodiment, and this embodiment will not be repeated here.

[0147] The above description is merely an illustration of the preferred embodiments disclosed in this application and the technical principles employed. Those skilled in the art should understand that the scope of protection provided by this disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0148] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

Claims

1. A building deformation monitoring method based on spaceborne InSAR data, characterized in that: The following steps are involved: Periodically collect spaceborne InSAR data of target buildings; Perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building. Couple each set of tilt monitoring data, crack monitoring data, and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value; A clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is the deformation state classification result, and the deformation state categories include qualified, abnormal, and severe; Input the building deformation value corresponding to the current period into the pre-trained deformation state classification model, and output the current deformation state classification result; A deformation warning signal is issued based on the current deformation classification results.

2. The building deformation monitoring method based on spaceborne InSAR data according to claim 1, characterized in that: By performing time series difference processing on the spaceborne InSAR data, several sets of target building tilt monitoring data, crack monitoring data, and settlement monitoring data are obtained, including: The differences in tilt, crack volume and settlement of spaceborne InSAR data from adjacent periods are calculated, with each period as a group, to obtain several groups of tilt monitoring data, crack monitoring data and settlement monitoring data of the target building.

3. The building deformation monitoring method based on spaceborne InSAR data according to claim 1, characterized in that: A clustering algorithm is used to construct a deformation state classification model, and the deformation state classification model is pre-trained based on the building deformation value. The output of the model is the deformation state classification result, including: Step 201: construct a deformation state classification model and preset three primary cluster centers K1, K2, and K3, representing a qualified deformation state, an abnormal deformation state, and a severe deformation state, respectively; Step 202: randomly select three data points from the building deformation values as primary cluster centers K1, K2, and K3 respectively; Step 203: Calculate the distance between each data point in the building deformation value and the center of each primary cluster, and assign the data point to the primary cluster closest to it to form three intermediate clusters. Step 204, respectively calculating the mean of all data points in each intermediate cluster as the new primary cluster center; Step 205 , repeating steps 203 - 204 until a preset convergence condition is reached, thereby obtaining a pre-trained deformation state classification model.

4. The building deformation monitoring method based on spaceborne InSAR data according to claim 3, characterized in that: In step 204, the mean of all data points in each intermediate cluster is calculated as the new primary cluster center, including: When there is no data point in the intermediate cluster during the iteration process, the data point farthest from the current primary cluster center is selected as the new primary cluster center.

5. The building deformation monitoring method based on spaceborne InSAR data according to claim 1, characterized in that: Pre-training of the deformation state classification model based on building deformation values, including: The building deformation values of the latest Q cycles are stored. When the building deformation values of each R cycle are added, the deformation state classification model is pre-trained based on the latest Q+R building deformation values.

6. The building deformation monitoring method based on spaceborne InSAR data according to claim 1, characterized in that: Based on the current deformation classification results, a deformation warning signal is issued, which also includes: Based on the deformation monitoring data set, the building stability value is calculated; Based on the current deformation classification results and building stability value, a deformation warning signal is issued.

7. The building deformation monitoring method based on spaceborne InSAR data according to claim 6, characterized in that: The deformation monitoring data set includes the settlement amount and crack volume of the data point. Based on the deformation monitoring data set, the building stability value is calculated, including: Based on the settlement amount of the data points, the settlement rate is calculated, and the tilt reference value is calculated using the double-point difference method; The maximum allowable value constraint method is used to normalize the settlement rate, tilt reference value and crack volume, and then a weighted sum is performed to obtain the building stability value.

8. The building deformation monitoring method based on spaceborne InSAR data according to claim 6, characterized in that: Based on the current deformation classification results and building stability value, deformation warning signals are issued, including: Preset threshold range of building stability value (E1, E2); If the current deformation classification result is qualified and the building stability value is greater than or equal to E2, a good deformation warning signal is issued; If the current deformation classification result is qualified and the building stability value is within the threshold range (E1, E2), a relatively stable deformation warning signal is issued; If the current deformation classification result is abnormal and the building stability value is within the threshold range (E1, E2), a poor deformation warning signal is issued; If the current deformation classification result is abnormal and the building stability value is less than or equal to E1, an unstable deformation warning signal is issued; If the current deformation classification result is severe, an extremely poor deformation warning signal will be issued at any building stability value.

9. The building deformation monitoring system based on spaceborne InSAR data is characterized by: include: Data acquisition module, used to periodically collect spaceborne InSAR data of target buildings; The data preprocessing module is used to perform time-series difference processing on the spaceborne InSAR data to obtain several sets of tilt monitoring data, crack monitoring data, and settlement monitoring data of the target building. The collection of all tilt monitoring data, crack monitoring data, and settlement monitoring data constitutes the deformation monitoring data set of the target building; The deformation value calculation module is used to couple each set of tilt monitoring data, crack monitoring data and settlement monitoring data in the deformation monitoring data set, and record the coupling result as the building deformation value; The deformation state classification module is used to build a deformation state classification model and pre-train the deformation state classification model based on the building deformation value. The output of the model is the deformation state classification result. The deformation state categories include qualified, abnormal, and severe. The building deformation value corresponding to the current cycle is input into the pre-trained deformation state classification model, and the output is the current deformation state classification result. The early warning module is used to issue a deformation early warning signal based on the current deformation classification result.

10. The building deformation monitoring system based on spaceborne InSAR data according to claim 9, characterized in that: Also includes: The stability value calculation module is used to calculate the building stability value based on the deformation monitoring data set; The early warning module is used to issue a deformation early warning signal based on the current deformation classification result and the building stability value.

Images