Dam settlement monitoring method, device, equipment, medium and program product

Abstract

The application provides a dam settlement monitoring method, device, equipment, medium and program product, relates to the technical field of artificial intelligence, and is used for improving the accuracy of dam settlement monitoring. The specific technical scheme is as follows: acquiring satellite collected dam ground surface image data and ground surface sensor collected dam state data; performing feature extraction on the dam ground surface image data to obtain dam structure feature information; performing settlement anomaly identification based on the dam state data to obtain dam settlement anomaly area information; inputting the dam structure feature information and the dam settlement anomaly area information into a dam settlement prediction model for prediction to obtain settlement trend information of the dam in a future time period; and the application is applied to a dam settlement early warning scene.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, medium, and program product for monitoring dam settlement. Background Technology

[0002] Currently, dams are key infrastructure in water conservancy projects, and their structural safety is directly related to flood control, power generation, and the safety of downstream areas. Under the influence of long-term water pressure, geological changes, and environmental factors, the dam body may experience settlement and deformation. If this is not detected and addressed in a timely manner, there is a significant risk of structural instability or even dam failure.

[0003] In related technologies, dam settlement monitoring is mainly carried out through traditional monitoring methods, such as leveling and GPS measurement. Specifically, leveling determines the dam's settlement by measuring the elevation differences between different monitoring points on the dam; GPS measurement captures satellite signals by deploying receivers at different monitoring points on the dam to obtain information on changes in the surface cover around the dam, such as the expansion of dam cracks or areas of water seepage.

[0004] However, the aforementioned traditional monitoring methods generally suffer from problems such as low efficiency, limited coverage, and inability to achieve continuous all-weather observation, making it difficult to conduct high-precision, full-coverage, and real-time dynamic safety monitoring of dams, resulting in the inability to detect and warn of potential safety hazards in a timely manner. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and program product for monitoring dam settlement, which can improve the accuracy of dam settlement monitoring.

[0006] In a first aspect, embodiments of this application provide a method for monitoring dam settlement. The method includes: acquiring satellite-collected dam surface image data and dam state data collected by surface sensors. The dam state data includes at least: dam displacement data, dam stress data, dam seepage data, and dam environmental data; extracting features from the dam surface image data to obtain dam structural feature information; identifying settlement anomalies based on the dam state data to obtain information on dam settlement anomaly areas; inputting the dam structural feature information and dam settlement anomaly area information into a dam settlement prediction model for prediction to obtain dam settlement trend information over a future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model is used to derive the relationship between dam structure and dam settlement, and the second sub-prediction model is used to derive the relationship between dam environmental data and dam settlement.

[0007] The technical solution provided in this application brings at least the following beneficial effects: the relationship between dam structure and dam settlement is derived through the first sub-prediction model, and the relationship between dam environmental data and dam settlement is derived by combining the second sub-prediction model. Thus, the dam settlement prediction model can achieve seamless integration of satellite data and surface sensor data through multi-source heterogeneous data, make up for the limitations of a single data source, and improve monitoring accuracy and reliability.

[0008] One possible implementation involves inputting dam structural feature information and dam settlement anomaly area information into a dam settlement prediction model to predict the dam's settlement trend information over a future period. This includes: inputting dam structural feature information, dam state data, and dam settlement anomaly area information into the dam settlement prediction model; using a first sub-prediction model, performing settlement inference based on dam structural feature information, dam displacement data, dam stress data, dam seepage data, and dam settlement anomaly area to obtain the theoretical settlement value of key dam points; and using a second sub-prediction model, performing correlation inference based on the theoretical settlement value of key dam points and dam environmental data to obtain the settlement trend information over a future period.

[0009] Another possible implementation, after inputting the dam structural characteristics information and the information on abnormal dam settlement areas into the dam settlement prediction model to obtain the dam settlement trend information in the future time period, the method further includes: calculating the mean and standard deviation of the historical settlement amount in each unit time period based on the historical settlement data under normal dam operation conditions in the historical time period; constructing a normal distribution model of settlement amount based on the mean and standard deviation of the historical settlement amount in each unit time period based on the mean and standard deviation of the historical settlement amount in each unit time period based on the normal distribution model of settlement amount; generating a settlement baseline curve based on the mean and standard deviation of the historical settlement amount in each unit time period based on the normal distribution model of settlement amount; and obtaining dam settlement early warning information based on dam status data, settlement trend information, and settlement baseline curve, which is used to indicate the severity of dam settlement.

[0010] Another possible implementation method is to obtain the dam settlement early warning level based on the dam status data, settlement trend information and settlement baseline curve, including: outputting dam settlement early warning information when the first settlement amount is greater than the first settlement range; wherein, the first settlement amount is the difference between the second settlement amount calculated based on the dam status data and the third settlement amount obtained based on the settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

[0011] Another possible implementation method, before acquiring the satellite-collected dam surface image data and the dam state data collected by surface sensors, includes: based on the dam's physical structural parameters, simulating the stress distribution of the dam under various uniform stresses, deriving the correlation between the dam structure's stress and settlement, and generating a first sub-prediction model; based on the dam's corresponding historical settlement data and the corresponding environmental data, deriving the correlation between the historical settlement data and the environmental data, and generating a second sub-prediction model; and based on the first and second sub-prediction models, constructing a dam settlement prediction model.

[0012] Secondly, embodiments of this application provide a dam settlement monitoring device, comprising: an acquisition module, an extraction module, an identification module, and a processing module. The acquisition module acquires dam surface image data collected by satellite and dam state data collected by surface sensors. The dam state data includes at least: dam displacement data, dam stress data, dam seepage data, and dam environmental data. The extraction module extracts features from the dam surface image data to obtain dam structural feature information. The identification module identifies settlement anomalies based on the dam state data to obtain information on dam settlement anomaly areas. The processing module inputs the dam structural feature information and dam settlement anomaly area information into a dam settlement prediction model for prediction, obtaining dam settlement trend information over a future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model derives the relationship between dam structure and dam settlement, and the second sub-prediction model derives the relationship between dam environmental data and dam settlement.

[0013] One possible implementation is that the aforementioned processing module is specifically used to input dam structural feature information, dam state data, and dam settlement anomaly area information into the dam settlement prediction model; and through the first sub-prediction model, to perform settlement inference based on dam structural feature information, dam displacement data, dam stress data, dam seepage data, and dam settlement anomaly area to obtain the theoretical settlement value of key dam points; and through the second sub-prediction model, to perform correlation inference based on the theoretical settlement value of key dam points and dam environmental data to obtain settlement trend information in the future time period.

[0014] In another possible implementation, the aforementioned processing module is also used to input dam structural characteristic information and dam settlement anomaly area information into the dam settlement prediction model for prediction. After obtaining the dam's settlement trend information in the future time period, based on historical settlement data under normal dam operation conditions in the historical time period, the mean and standard deviation of historical settlement in each unit time period are calculated. Based on the mean and standard deviation of historical settlement in each unit time period, a normal distribution model of settlement is constructed. Through the normal distribution model of settlement, based on the mean and standard deviation of historical settlement in each unit time period, a settlement baseline curve is generated. Based on the dam status data, settlement trend information, and settlement baseline curve, dam settlement early warning information is obtained, which is used to indicate the severity of dam settlement.

[0015] Another possible implementation is that the above processing module is specifically used to output dam settlement early warning information when the first settlement amount is greater than the first settlement range; wherein, the first settlement amount is the difference between the second settlement amount calculated based on the dam status data and the third settlement amount obtained based on the settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

[0016] In another possible implementation, the aforementioned processing module is further used to, before acquiring satellite-collected dam surface image data and dam state data collected by surface sensors, simulate the stress distribution of the dam under various uniform stresses based on the dam's physical structural parameters, deduce the correlation between dam structural stress and settlement, and generate a first sub-prediction model; and based on the historical settlement data corresponding to the dam and the corresponding environmental data, deduce the correlation between historical settlement data and environmental data, and generate a second sub-prediction model; and based on the first and second sub-prediction models, construct a dam settlement prediction model.

[0017] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory stores a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the method of the first aspect described above.

[0018] Fourthly, this application provides a readable storage medium on which a program or instructions are stored, which, when executed by a computer, implement the method of the first aspect described above.

[0019] Fifthly, this application provides a computer program product stored in a storage medium, which, when executed by a computer, implements the method described in the first aspect.

[0020] In a sixth aspect, embodiments of this application provide a chip including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0021] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0022] Figure 1 A schematic diagram of the network architecture for a dam settlement monitoring method provided in this application embodiment;

[0023] Figure 2 A flowchart illustrating a dam settlement monitoring method provided in this application embodiment;

[0024] Figure 3 A flowchart illustrating another dam settlement monitoring method provided in this application embodiment;

[0025] Figure 4 A flowchart illustrating yet another dam settlement monitoring method provided in this application embodiment;

[0026] Figure 5 A flowchart illustrating yet another dam settlement monitoring method provided in this application embodiment;

[0027] Figure 6 A flowchart illustrating yet another dam settlement monitoring method provided in this application embodiment;

[0028] Figure 7 This is a schematic diagram of the structure of a dam settlement monitoring system provided in an embodiment of this application;

[0029] Figure 8 This is a schematic diagram of the structure of a dam settlement monitoring device provided in an embodiment of this application;

[0030] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] The following is a detailed description of the dam settlement monitoring method, apparatus, equipment, media, and program products provided in this application, with reference to the accompanying drawings.

[0032] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0033] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application 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.

[0034] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0035] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0036] The embodiments of this application provide a dam settlement monitoring method, device, equipment, medium, and program product that can be applied to dam settlement detection and early warning scenarios.

[0037] Currently, dams, as key infrastructure in water conservancy projects, play a vital role in flood control, power generation, irrigation, and water supply. However, due to the long-term influence of various factors such as water pressure, geological conditions, and climate change, dams may experience safety issues such as settlement and deformation. If these problems are not detected and addressed in a timely manner, they may lead to structural damage to the dam, or even dam failure, threatening the lives and property of people downstream and the ecological environment. Traditional methods for monitoring dam settlement mainly include leveling and Global Positioning System (GPS) measurements. Leveling establishes a horizontal line of sight using a level instrument and measures the elevation difference between different measuring points to calculate settlement. As the most basic settlement monitoring method, it is widely used for vertical displacement monitoring during dam construction and operation. However, manual operation is time-consuming and labor-intensive, cannot achieve real-time dynamic monitoring, and is greatly affected by terrain and weather, making it difficult to cover large areas. GPS acquires the three-dimensional coordinates of measuring points through satellite signals, while total stations use the polar coordinate method to measure horizontal displacement and settlement. GPS is widely used in dam surface deformation monitoring, while total stations are often used to measure dam cracks and structural displacement. However, GPS is affected by obstruction and atmospheric interference, total stations rely on manual operation, and the density of measuring points is limited.

[0038] To address the aforementioned technical problems, this application provides a method, device, equipment, medium, and program product for monitoring dam settlement. It derives the relationship between dam structure and dam settlement through a first sub-prediction model, and combines this with a second sub-prediction model to derive the relationship between dam environmental data and dam settlement. Thus, the dam settlement prediction model can achieve seamless integration of satellite data and surface sensor data through multi-source heterogeneous data, overcoming the limitations of a single data source and improving monitoring accuracy and reliability.

[0039] Furthermore, with the continuous development of remote sensing satellite technology, remote sensing satellites have demonstrated powerful advantages in acquiring geographic information. Remote sensing satellites are characterized by wide coverage, high observation frequency, and independence from terrain and climate conditions, enabling them to rapidly acquire information about large areas of the Earth's surface. This application applies remote sensing satellite technology to dam settlement monitoring, which can compensate for the shortcomings of traditional monitoring methods. By comprehensively utilizing remote sensing satellites, image processing, model building, and communication technologies, real-time monitoring, accurate early warning, and timely handling of dam settlement are achieved, providing a more reliable guarantee for the safe operation of dams.

[0040] Moreover, this application breaks through the limitations of "point monitoring" and achieves full coverage. A single transit of a remote sensing satellite can cover hundreds of square kilometers, and a single image can acquire the surface deformation field of the entire dam and several kilometers upstream and downstream. This achieves a leap from "point monitoring" to "area monitoring", which can accurately identify the subsidence relationship between the dam body and the surrounding strata and avoid safety hazards caused by local monitoring blind spots.

[0041] Furthermore, multi-dimensional information fusion analysis is achieved through dam settlement prediction models. Specifically, the dam settlement prediction model integrates satellite-acquired dam surface image data with dam status data acquired by surface sensors in a spatiotemporal manner to construct a "settlement-load-environment" multi-factor correlation model, accurately identifying the inducing factors of abnormal settlement.

[0042] Finally, automated real-time monitoring is achieved, with satellites automatically acquiring surface image data of the dam at fixed intervals, enabling full automation of the "data acquisition-processing-early warning" process and increasing the monitoring frequency to sub-weekly levels.

[0043] The following description, in conjunction with the accompanying drawings, details the dam settlement monitoring method, apparatus, equipment, medium, and program products provided in the embodiments of this application.

[0044] Figure 1 The network architecture of a dam settlement monitoring method provided in an embodiment of this application is illustrated. Figure 1 As shown, the network architecture includes a dam settlement monitoring device 101 and a satellite device 102. The dam settlement monitoring device 101 and the satellite device 102 are interconnected.

[0045] In some embodiments, the dam settlement monitoring device 101 described above may be a server, a computer, or a processor or processing unit within a server or computer. The server may be a single server or a server cluster consisting of multiple servers. It should be noted that the embodiments of this application do not limit the specific device form of the dam settlement monitoring device 101. Figure 1 The example shown is a single server, namely the dam settlement monitoring device 101.

[0046] In some embodiments, the satellite device 102 may be a Gaofen-3 satellite, a Sentinel-1 satellite, etc., and the embodiments of this application do not specifically limit it.

[0047] In some embodiments, satellite equipment 102 sends collected dam surface image data to dam settlement monitoring device 101. Dam settlement monitoring device 101 receives the dam surface image data sent by satellite equipment 102 and acquires dam status data collected by surface sensors. Then, it extracts features from the dam surface image data to obtain dam structural feature information. Next, it identifies settlement anomalies based on the dam status data to obtain dam settlement anomaly area information. Finally, it inputs the dam structural feature information and the dam settlement anomaly area information into a dam settlement prediction model for prediction to obtain dam settlement trend information in the future time period.

[0048] It should be noted that the network architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As network architectures evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0049] See Figure 2 This is a flowchart illustrating a dam settlement monitoring method provided in an embodiment of this application. Figure 2 As shown, the dam settlement monitoring method provided in this application embodiment can be implemented by the dam settlement monitoring device described above, specifically including the following steps 201 to 204.

[0050] Step 201: The dam settlement monitoring device acquires satellite-collected dam surface image data and dam status data collected by surface sensors.

[0051] In some embodiments, the dam status data mentioned above includes at least: dam displacement data, dam stress data, dam seepage data, and dam environmental data.

[0052] In some embodiments, the aforementioned satellites may be one or more.

[0053] For example, the aforementioned satellites may include high-resolution optical satellites and synthetic aperture radar (SAR) satellites.

[0054] For example, the aforementioned high-resolution optical satellites can acquire details of surface textures, such as cracks and vegetation anomalies, while SAR satellites can monitor millimeter-level deformation through all-weather microwave imaging.

[0055] In some embodiments, the above-mentioned dam surface image data may include dam surface images taken by satellite at preset time thresholds at intervals.

[0056] In some embodiments, the above-mentioned dam surface image data may include at least one of the following: extracting vegetation cover changes from optical images (indirectly reflecting seepage), retrieving surface humidity from SAR images (monitoring seepage paths), and analyzing topographic slope changes (early warning of landslide risks).

[0057] In some embodiments, the preset time threshold can be one week, two weeks, or three weeks, etc. The specific time threshold can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0058] In some embodiments, the aforementioned surface sensors may include at least one of the following: a Global Navigation Satellite System Monitoring Station (GNSS), an inclinometer, and a piezometer.

[0059] In some embodiments, the aforementioned dam environmental data may include at least one of the following: water level, rainfall, and temperature. The specific data can be determined based on actual usage requirements, and this application does not impose any limitations.

[0060] In some embodiments, the dam settlement monitoring device can receive dam surface image data acquired by satellite and dam status data acquired by surface sensors via wireless connection.

[0061] Step 202: The dam settlement monitoring device extracts features from the dam surface image data to obtain dam structural feature information.

[0062] In some embodiments, the above-mentioned dam structural feature information may include at least one of the following: dam outline, spatial location and geometric parameters of key structures (e.g., cutoff wall, drainage hole), elastic modulus, Poisson's ratio, self-weight, water pressure, and temperature.

[0063] For example, the geometric parameters of the drainage holes may include at least one of the following: hole diameter, drainage hole shape, and number of drainage holes. The specific parameters can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0064] In some embodiments, the dam settlement monitoring device can vectorize the dam surface image data to obtain vectorized dam surface image data, and then extract features from the vectorized dam surface image data to obtain dam structural feature information.

[0065] For example, the dam settlement monitoring device uses a deep learning algorithm to extract features from the vectorized dam surface image data to obtain dam structural feature information.

[0066] For example, the deep learning algorithm described above can be any of the following: the U-Net algorithm or a mask region-based convolutional neural network (Mask R-CNN) algorithm. The specific algorithm can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0067] In some embodiments, the dam settlement monitoring device can train the initial algorithm based on the labeled dam image data training set to obtain the aforementioned deep learning algorithm.

[0068] For example, the aforementioned dam image data training set includes at least one of the following categories: dam body, spillway, gate, vegetation cover area, etc. The specific category can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0069] Step 203: The dam settlement monitoring device identifies settlement anomalies based on dam status data to obtain information on dam settlement anomaly areas.

[0070] In some embodiments, the dam settlement monitoring device can employ feature point matching combined with the Random Sample Consensus (RANSAC) algorithm to achieve sub-pixel-level registration of images from different times, identify changes in land cover around the dam using the interpolation method, and extract abnormal areas using threshold segmentation. It outputs a vector map of the settlement anomaly areas, a deformation gradient heat map, and labels the specific locations where settlement exceeds limits.

[0071] For example, the above difference method can be the difference of the Normalized Difference Vegetation Index (NDVI) or the difference of the Modified Normalized Difference Water Index (MNDWI).

[0072] For example, the aforementioned changes in land cover around the dam could be areas of crack expansion or water seepage.

[0073] For example, the specific locations mentioned above can be key parts such as the dam foundation and dam shoulders.

[0074] Step 204: The dam settlement monitoring device inputs the dam structural characteristic information and the dam settlement anomaly area information into the dam settlement prediction model to make predictions and obtain the dam settlement trend information in the future time period.

[0075] In some embodiments, the above-mentioned dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model is used to derive the relationship between the dam structure and dam settlement, and the second sub-prediction model is used to derive the relationship between dam environmental data and dam settlement.

[0076] In some embodiments, the aforementioned future time period can be user-defined or preset by the dam settlement monitoring device. The specific time period can be determined based on actual usage requirements, and this application embodiment does not impose any limitations.

[0077] For example, the aforementioned future time period could be a week, a month, or a year.

[0078] It should be noted that the specific implementation process of step 204 above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0079] In some embodiments, combined with Figure 2 ,like Figure 3 As shown, step 204 can be implemented through steps 204a to 204c as described below.

[0080] Step 204a: The dam settlement monitoring device inputs the dam structural characteristics information, dam status data, and dam settlement anomaly area information into the dam settlement prediction model.

[0081] In some embodiments, the dam settlement monitoring device can input dam structural characteristic information, dam state data, and dam settlement anomaly area information into the dam settlement prediction model through the input interface in the dam settlement prediction model.

[0082] Step 204b: The dam settlement monitoring device uses the first sub-prediction model to perform settlement inference based on dam structural feature information, dam displacement data, dam stress data, dam seepage data, and dam settlement anomaly areas, and obtains the theoretical settlement value of key dam points.

[0083] For example, the first sub-prediction model can construct a three-dimensional solid model of the dam based on the Analysis Systems (ANSYS) system, and simulate the mechanical mechanism of structural stress and settlement based on the elastic modulus, Poisson's ratio, self-weight, water pressure, and temperature, and output the theoretical settlement values ​​of key points.

[0084] Step 204c: The dam settlement monitoring device uses the second sub-prediction model to perform correlation reasoning based on the theoretical settlement values ​​of key dam locations and dam environmental data to obtain settlement trend information for the future time period.

[0085] For example, the second sub-prediction model uses a neural network to learn the correlation between historical settlement data and dam environmental data to predict future settlement trends.

[0086] Thus, the first sub-prediction model provides the theoretical boundary of structural safety, while the second sub-prediction model captures the complex patterns in actual operation. After fusion, the prediction error is reduced by 30% compared to a single model. By combining the first and second sub-prediction models, the mechanical characteristics of the dam structure are considered, and potential patterns are mined from historical data, thereby achieving accurate prediction and dynamic early warning of settlement trends.

[0087] The dam settlement monitoring method provided in this application acquires dam surface image data collected by satellite and dam state data collected by surface sensors. The dam state data includes at least: dam displacement data, dam stress data, dam seepage data, and dam environmental data. Feature extraction is performed on the dam surface image data to obtain dam structural feature information. Settlement anomaly identification is performed based on the dam state data to obtain dam settlement anomaly area information. The dam structural feature information and dam settlement anomaly area information are input into a dam settlement prediction model for prediction to obtain dam settlement trend information in the future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model is used to derive the relationship between dam structure and dam settlement, and the second sub-prediction model is used to derive the relationship between dam environmental data and dam settlement. In this scheme, the relationship between dam structure and dam settlement is derived through the first sub-prediction model, and the relationship between dam environmental data and dam settlement is derived by combining the second sub-prediction model. Thus, the dam settlement prediction model can achieve seamless integration of satellite data and surface sensor data through multi-source heterogeneous data, making up for the limitations of a single data source and improving monitoring accuracy and reliability.

[0088] In some embodiments, combined with Figure 2 ,like Figure 4 As shown, after step 204 above, the dam settlement monitoring method provided in this application embodiment further includes steps 301 to 304 as described below.

[0089] Step 301: The dam settlement monitoring device calculates the mean and standard deviation of the historical settlement amount per unit time within the historical time period based on the historical settlement data under normal dam operation conditions during the historical time period.

[0090] For example, the dam settlement monitoring device can select historical settlement data (at least 3 years of data) under normal dam operating conditions, and remove fluctuation data caused by abnormal events such as heavy rainfall and earthquakes. The mean and standard deviation of daily or weekly settlement are calculated.

[0091] Step 302: The dam settlement monitoring device constructs a normal distribution model of settlement based on the mean and standard deviation of historical settlement in each unit time period within the historical time period.

[0092] In some embodiments, the dam settlement monitoring device can calculate the normal distribution data corresponding to each unit time based on the mean and standard deviation of the historical settlement amount within each unit time, and then plot the normal distribution curve based on the normal distribution data corresponding to each unit time to obtain the normal distribution model of the settlement amount.

[0093] Step 303: The dam settlement monitoring device generates a settlement baseline curve based on the mean and standard deviation of the historical settlement in each unit time using a normal distribution model of settlement.

[0094] For example, the dam settlement monitoring device can use the mean as the center, set ±2 standard deviations as the normal fluctuation range, and ±3 standard deviations as the warning threshold boundary to draw a dynamic settlement baseline curve.

[0095] Step 304: The dam settlement monitoring device obtains dam settlement early warning information based on dam status data, settlement trend information and settlement baseline curve.

[0096] In some embodiments, the aforementioned dam settlement early warning information is used to indicate the severity of dam settlement.

[0097] In some embodiments, after receiving dam settlement early warning information, the dam settlement monitoring device can send dam settlement early warning information to the operation and maintenance personnel to prompt them to carry out maintenance.

[0098] It should be noted that the specific implementation process of step 304 above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0099] In some embodiments, combined with Figure 4 ,like Figure 5 As shown, step 304 above can be implemented through step 304a below.

[0100] Step 304a: When the first settlement amount is greater than the first settlement range, the dam settlement monitoring device outputs dam settlement early warning information.

[0101] In some embodiments, the first settlement is the difference between the second settlement calculated based on dam status data and the third settlement obtained based on settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

[0102] For example, the dam settlement monitoring device can synchronously input minute-level settlement data collected by surface sensors and model prediction values ​​into the comparison module in the dam settlement prediction model. When the real-time settlement exceeds the ±3 standard deviation threshold, or exceeds the ±2 standard deviation range for three consecutive monitoring cycles, it is determined to be an abnormal fluctuation and triggers a preliminary warning. Combined with the model prediction trend, if the predicted value continues to deviate from the baseline and approaches the warning threshold, the warning level is upgraded and manual review is prompted.

[0103] In some embodiments, the dam settlement monitoring device can establish a graded early warning system based on dam design specifications, historical settlement data, and expert experience. This includes a yellow warning indicating a slight anomaly, suggesting that the dam may be experiencing initial anomalies and that monitoring frequency should be increased; an orange warning indicating a moderate anomaly, suggesting that technical personnel should be immediately organized to conduct on-site investigations and that emergency plans should be prepared; and a red warning indicating a severe anomaly, with a rapid increase in settlement exceeding the maximum allowable settlement range or signs of structural damage (such as rapid crack propagation), in which case emergency evacuation measures should be taken immediately, surrounding personnel should be evacuated, and rescue work should be carried out.

[0104] In some embodiments, the dam settlement monitoring device can recalculate and calibrate the early warning threshold quarterly based on the dam's operating status, seasonal changes (e.g., differences between flood and dry seasons), and newly accumulated monitoring data to ensure the accuracy and applicability of the threshold. Furthermore, by incorporating machine learning algorithms, it analyzes settlement response patterns under different operating conditions, enabling the early warning threshold to be automatically optimized in response to factors such as dam aging and environmental changes, thereby improving the sensitivity and reliability of the early warning system.

[0105] In some embodiments, the dam settlement monitoring device can instantly alert on-duty personnel through pop-ups, vibrations, and voice broadcasts, while displaying detailed warning information, including the location, extent, predicted trend, and recommended handling measures of the settlement anomaly. It integrates with devices such as smart bracelets and smartwatches, receiving warning information via Bluetooth or the network. For staff who are on the move or unable to check their phones promptly, warnings can be quickly obtained via bracelet vibration and SMS push notifications, ensuring timely information delivery. As a supplementary channel, warning SMS messages and emails can be sent to relevant management personnel and emergency response department heads.

[0106] In some embodiments, combined with Figure 2 ,like Figure 6 As shown, prior to step 201 above, the dam settlement monitoring method provided in this application embodiment further includes steps 401 to 403 as described below.

[0107] Step 401: Based on the physical structural parameters of the dam, the dam settlement monitoring device simulates the stress distribution of the dam under various uniform stresses, derives the correlation between the dam structure stress and settlement, and generates the first sub-prediction model.

[0108] For example, the above physical structural parameters include at least one of the following: elastic modulus, Poisson's ratio, self-weight, water pressure, and temperature.

[0109] For example, the first sub-prediction model mentioned above can be a three-dimensional solid model of the dam.

[0110] Step 402: Based on the historical settlement data corresponding to the dam and the dam environmental data corresponding to the historical settlement data, the dam settlement monitoring device derives the correlation between the historical settlement data and the environmental data, and generates the second sub-prediction model.

[0111] For example, the second sub-prediction model described above can be a neural network model.

[0112] Step 403: The dam settlement monitoring device constructs a dam settlement prediction model based on the first sub-prediction model and the second sub-prediction model.

[0113] In some embodiments, the dam settlement monitoring device can use the output of the first sub-prediction model as the input of the second sub-prediction model to construct a dam settlement prediction model.

[0114] In this way, the dam settlement monitoring device provides the theoretical boundary of structural safety through the physical model and captures the complex laws in actual operation through the data-driven model. After fusion, the prediction error is reduced by 30% compared with the single model. By combining the physical model and the data-driven model, it not only considers the mechanical characteristics of the dam structure, but also uses historical data to mine potential laws, so as to achieve accurate prediction and dynamic early warning of settlement trend.

[0115] The following specific embodiments illustrate the dam settlement monitoring method of this application.

[0116] The implementation process of the dam settlement monitoring method provided in this application includes the following steps S1 to S4:

[0117] S1, the dam settlement monitoring device collects data.

[0118] (i) Satellite data acquisition: Select satellites with high-resolution optical imaging (such as 0.5-meter resolution) and SAR interferometry capabilities (such as Gaofen-3 and Sentinel-1) to periodically acquire multi-band images and DEM (digital elevation model) data of the dam area, covering visible light, near infrared and microwave frequency bands.

[0119] (ii) Auxiliary data collection: Deploy GNSS monitoring stations, inclinometers, piezometers and other sensors to collect dam displacement, stress and seepage data in real time, which complements satellite data.

[0120] S2, the dam settlement monitoring device processes the data.

[0121] (a) Image preprocessing, which eliminates imaging errors through radiometric calibration, geometric fine correction, atmospheric correction, etc.

[0122] (ii) Feature extraction: Deep learning algorithms are used to identify dam outlines, cracks, and water boundary changes. Semantic segmentation networks such as U-Net and Mask R-CNN are used for training on labeled dam image datasets (including categories such as dam body, spillway, gate, and vegetation cover) to automatically extract the spatial location and geometric parameters of dam outlines and key structures (such as anti-seepage walls and drainage holes).

[0123] (III) Settlement analysis: SIFT / SURF feature point matching combined with the RANSAC algorithm is used to achieve sub-pixel-level registration of images from different time phases. Difference methods (such as NDVI vegetation index difference and MNDWI water index difference) are used to identify changes in land cover around the dam (e.g., crack propagation and water seepage areas). Threshold segmentation is then used to extract anomalous areas. Vector maps of anomalous settlement areas and deformation gradient heat maps are output, marking the specific locations where settlement exceeds limits (e.g., key parts such as the dam foundation and abutments).

[0124] S3. Model analysis of the dam settlement monitoring device.

[0125] (I) Settlement Model Construction: Physical Model: The dam structure is discretized into a finite number of elements. The mechanical equilibrium equations are solved using ANSYS software to simulate the stress and strain distribution of the dam under the action of multiple factors such as self-weight, water pressure, temperature load, and foundation reaction force, thereby deriving the relationship between structural deformation and settlement. For example, the gravity dam model needs to consider the elastic modulus and Poisson's ratio of the dam material, as well as the mechanical parameters of the foundation soil and rock.

[0126] Data-driven model: Uses LSTM neural networks to learn the correlation between historical settlement data and environmental factors (water level, rainfall, temperature) to predict future settlement trends.

[0127] By employing a dual-path modeling approach combining physical mechanisms and data-driven methods, and integrating dynamic baseline comparison, we can achieve accurate prediction of dam settlement and intelligent risk identification, providing a scientific basis for safety early warning.

[0128] (II) Baseline Comparison and Anomaly Monitoring: Historical settlement data (at least 3 years) under normal dam operation conditions are selected, excluding fluctuations caused by abnormal events such as heavy rainfall and earthquakes. The mean (μ) and standard deviation (σ) of daily or weekly settlement are calculated to construct a normal distribution model of settlement. With the mean as the center, ±2σ is set as the normal fluctuation range, and ±3σ is set as the warning threshold boundary to generate a dynamic settlement baseline curve. The minute-level settlement data collected by sensors and the model prediction values ​​are synchronously input into the comparison module. When the real-time settlement exceeds the ±3σ threshold, or exceeds the ±2σ range for 3 consecutive monitoring cycles, it is judged as an abnormal fluctuation, triggering a preliminary warning. Combined with the trend prediction of the LSTM model, if the predicted value continues to deviate from the baseline and approaches the warning threshold, the warning level is upgraded, and manual review is prompted.

[0129] S4. The dam settlement monitoring device provides early warning feedback.

[0130] (i) Setting early warning thresholds: Based on dam design specifications, historical settlement data and expert experience, a graded early warning system is established, including a yellow warning indicating a slight anomaly, which may indicate an initial anomaly in the dam and requires increased monitoring frequency; an orange warning indicating a moderate anomaly, which indicates that technical personnel should be organized to conduct on-site investigation immediately and emergency plans should be activated; and a red warning indicating a severe anomaly, where the settlement increases sharply, exceeds the maximum allowable settlement range, or there are signs of structural damage (such as rapid expansion of cracks), in which case emergency evacuation measures should be taken immediately, surrounding personnel should be evacuated, and rescue work should be carried out.

[0131] (ii) Dynamic adjustment of thresholds: The early warning thresholds are recalculated and calibrated quarterly based on the dam's operating status, seasonal changes (such as differences between flood and dry seasons), and newly accumulated monitoring data to ensure the accuracy and applicability of the thresholds. Combined with machine learning algorithms, settlement response patterns under different operating conditions are analyzed, enabling the early warning thresholds to be automatically optimized in response to factors such as dam aging and environmental changes, thereby improving the sensitivity and reliability of early warnings.

[0132] (III) Communication Feedback: Develop a dedicated dam safety monitoring application that supports iOS and Android systems. When an alert is triggered, the application will immediately notify on-duty personnel via pop-ups, vibration, and voice broadcasts, while displaying detailed alert information, including the location, extent, predicted trend, and recommended handling measures for abnormal settlement. It will integrate with devices such as smart bracelets and smartwatches to receive alert information via Bluetooth or the network. For staff who are on the move or unable to check their phones promptly, alerts can be quickly obtained via bracelet vibration and SMS push notifications, ensuring timely information delivery. As a supplementary channel, alert SMS messages and emails will be sent to relevant management personnel and emergency response department heads.

[0133] Thus, the dam settlement monitoring device integrates high-resolution optical satellites (such as Gaofen-2, 0.8m resolution) and SAR satellites (such as Sentinel-1) to construct an airborne monitoring system. The former acquires details of surface texture (cracks, vegetation anomalies, etc.), while the latter achieves millimeter-level deformation monitoring through all-weather microwave imaging (unaffected by clouds, rain, day and night). At the same time, GNSS receivers, piezometers and other ground sensors are deployed at key parts of the dam to collect displacement and seepage data in real time, achieving seamless integration of satellite remote sensing data and ground sensor data, making up for the limitations of a single data source and improving monitoring accuracy and reliability.

[0134] This paper proposes a dual-model fusion technology for settlement prediction and anomaly detection: The physical model, based on ANSYS finite element analysis, constructs a three-dimensional solid model of the dam, inputting material parameters (elastic modulus, Poisson's ratio) and load conditions (self-weight, water pressure, temperature) to simulate the mechanical mechanism of structural stress and settlement, and outputs the theoretical settlement values ​​at key points. The data-driven model uses an LSTM neural network to learn the correlation between historical settlement data and environmental factors (water level, rainfall, temperature) to predict future settlement trends. The physical model provides the theoretical boundary for structural safety, while the data-driven model captures the complex patterns in actual operation. After fusion, the prediction error is reduced by 30% compared to a single model. Combining the physical model and the data-driven model considers both the mechanical characteristics of the dam structure and utilizes historical data to mine potential patterns, achieving accurate prediction and dynamic early warning of settlement trends.

[0135] It should be noted that the descriptions of each step S1 to S4 in this embodiment can be found in the descriptions in the above embodiments, and will not be repeated here.

[0136] It should be noted that the above-described method embodiments, or the various possible implementations of the method embodiments, can be executed individually, or, provided there is no conflict, they can be combined with each other. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0137] Figure 7 This is a schematic diagram of a dam settlement monitoring system provided in an embodiment of this application. Figure 7 As shown, the dam settlement monitoring system 800 may include: a remote sensing data acquisition module 801, a data processing module 802, a dam settlement monitoring module 803, a user interface and reporting module 804, and a communication and feedback module 805.

[0138] Among them, the remote sensing data acquisition module 801 is used to acquire surface images and deformation data flexibly by using high-resolution optical satellites and SAR satellites according to the dam monitoring needs and weather conditions; and is applied to the above steps 201 and related schemes.

[0139] The data processing module 802 is used to preprocess and perform in-depth analysis on the collected raw data, and eliminate errors caused by sensor and environmental factors through radiometric correction and geometric correction; it is applied to the above-mentioned S2, steps 202 and 203 and related schemes of S2, steps 202 and 203.

[0140] The dam settlement monitoring module 803 is used for the construction and comparative analysis of dam settlement prediction models; it is applied to step 204 and related schemes mentioned above.

[0141] The user interface and reporting module 804 is used to automatically generate monitoring reports containing data statistics, anomaly analysis, etc., according to time periods; it is applied to the above S4 and related solutions.

[0142] The communication and feedback module 805 is used for two-way interaction, supporting on-duty personnel to confirm warnings and provide feedback on the on-site situation online; it is applied to the above-mentioned S4 and related S4 solutions.

[0143] It should be noted that for a detailed explanation of the steps performed by each module and their beneficial effects, please refer to the description in the above embodiments, which will not be repeated here.

[0144] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0145] This application embodiment can divide the dam settlement monitoring device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0146] In some embodiments, this application also provides a dam settlement monitoring device. The dam settlement monitoring device may include one or more functional modules for implementing the dam settlement monitoring method described in the above embodiments.

[0147] For example, Figure 8 This is a structural schematic diagram of a dam settlement monitoring device provided in an embodiment of this application. Figure 8 As shown, the dam settlement monitoring device 900 includes: an acquisition module 901, an extraction module 902, an identification module 903, and a processing module 904.

[0148] The system comprises the following modules: Acquisition module 901 acquires satellite-generated surface image data of the dam and surface sensor-collected dam status data, including at least dam displacement data, dam stress data, dam seepage data, and dam environmental data. Extraction module 902 extracts features from the dam surface image data to obtain dam structural feature information. Identification module 903 identifies settlement anomalies based on the dam status data to obtain information on dam settlement anomaly areas. Processing module 904 inputs the dam structural feature information and dam settlement anomaly area information into a dam settlement prediction model for prediction, obtaining dam settlement trend information over a future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model derives the relationship between dam structure and dam settlement, while the second sub-prediction model derives the relationship between dam environmental data and dam settlement.

[0149] In the dam settlement monitoring device provided in this application, the relationship between dam structure and dam settlement is derived through a first sub-prediction model, and the relationship between dam environmental data and dam settlement is derived by combining a second sub-prediction model. Thus, the dam settlement prediction model can achieve seamless integration of satellite data and surface sensor data through multi-source heterogeneous data, making up for the limitations of a single data source and improving monitoring accuracy and reliability.

[0150] In some embodiments, the processing module 904 is specifically used to input dam structural feature information, dam state data, and dam settlement anomaly area information into the dam settlement prediction model; and through the first sub-prediction model, perform settlement inference based on dam structural feature information, dam displacement data, dam stress data, dam seepage data, and dam settlement anomaly area to obtain the theoretical settlement value of key dam points; and through the second sub-prediction model, perform correlation inference based on the theoretical settlement value of key dam points and dam environmental data to obtain settlement trend information in the future time period.

[0151] In other embodiments, the processing module 904 is further configured to input the dam structural feature information and the dam settlement anomaly area information into the dam settlement prediction model for prediction. After obtaining the dam settlement trend information in the future time period, it calculates the mean and standard deviation of the historical settlement amount in each unit time period based on the historical settlement data under normal dam operation conditions in the historical time period. Based on the mean and standard deviation of the historical settlement amount in each unit time period, it constructs a settlement amount normal distribution model. Through the settlement amount normal distribution model, based on the mean and standard deviation of the historical settlement amount in each unit time period, it generates a settlement baseline curve. Based on the dam status data, settlement trend information, and settlement baseline curve, it obtains dam settlement early warning information, which is used to indicate the severity of dam settlement.

[0152] In some other embodiments, the processing module 904 is specifically used to output dam settlement early warning information when the first settlement amount is greater than the first settlement range; wherein the first settlement amount is the difference between the second settlement amount calculated based on dam status data and the third settlement amount obtained based on settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

[0153] In some other embodiments, the processing module 904 is further configured to, before acquiring satellite-collected dam surface image data and dam state data collected by surface sensors, simulate the stress distribution of the dam under various uniform stresses based on the dam's physical structural parameters, deduce the correlation between dam structural stress and settlement, and generate a first sub-prediction model; and based on the historical settlement data corresponding to the dam and the corresponding environmental data, deduce the correlation between historical settlement data and dam environmental data, and generate a second sub-prediction model; and based on the first and second sub-prediction models, construct a dam settlement prediction model.

[0154] It should be noted that the dam settlement monitoring device can realize all the processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0155] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 9 As shown, the electronic device 90 includes: a processor 92, a communication interface 93, and a bus 94. Optionally, the electronic device 90 may also include a memory 91.

[0156] Processor 92 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0157] Communication interface 93 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0158] The memory 91 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0159] As one possible implementation, the memory 91 can exist independently of the processor 92. The memory 91 can be connected to the processor 92 via a bus 94 and is used to store instructions or program code. When the processor 92 calls and executes the instructions or program code stored in the memory 91, it can implement the dam settlement monitoring method provided in this application embodiment.

[0160] In another possible implementation, memory 91 can also be integrated with processor 92.

[0161] Bus 94 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 94 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0162] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0163] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described dam settlement monitoring method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0164] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0165] This application also provides a readable storage medium storing a program or instructions that, when executed by a computer, implement the dam settlement monitoring method provided in the above embodiments. It is understood that all or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware; the readable storage medium can be any of the foregoing embodiments or memory; the readable storage medium can also be an external storage device of the service invocation device, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the readable storage medium can include both internal storage units of the service invocation device and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0166] This application also provides a computer program product, which is stored in a storage medium and, when executed by a computer, implements the dam settlement monitoring method provided in the above embodiments.

[0167] 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. Without further limitations, 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. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application 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. Additionally, features described with reference to certain examples may be combined in other examples.

[0168] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0169] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application 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 this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for monitoring dam settlement, characterized in that, include: The system acquires satellite-collected surface image data of the dam and surface sensor-collected dam status data, which includes at least: dam displacement data, dam stress data, dam seepage data, and dam environmental data. Feature extraction is performed on the surface image data of the dam to obtain structural feature information of the dam; Based on the dam status data, settlement anomaly identification is performed to obtain information on the dam settlement anomaly area; The dam structural feature information and the dam settlement anomaly area information are input into the dam settlement prediction model for prediction to obtain the dam settlement trend information in the future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model is used to derive the relationship between the dam structure and the dam settlement, and the second sub-prediction model is used to derive the relationship between the dam environmental data and the dam settlement.

2. The dam settlement monitoring method according to claim 1, characterized in that, The step of inputting the dam structural feature information and the dam settlement anomaly area information into the dam settlement prediction model for prediction, and obtaining the dam settlement trend information in the future time period, includes: The dam structural feature information, the dam state data, and the dam settlement anomaly area information are input into the dam settlement prediction model; Using the first sub-prediction model, settlement inference is performed based on the dam structural feature information, dam displacement data, dam stress data, dam seepage data, and the dam settlement anomaly area to obtain the theoretical settlement value of key dam points; By using the second sub-prediction model, based on the theoretical settlement values ​​of the key points of the dam and the dam environmental data, the settlement trend information for the future time period is obtained through correlation reasoning.

3. The dam settlement monitoring method according to claim 1 or 2, characterized in that, After inputting the dam structural feature information and the dam settlement anomaly area information into the dam settlement prediction model for prediction to obtain the dam settlement trend information in the future time period, the method further includes: Based on historical settlement data under normal dam operation conditions within a historical period, the mean and standard deviation of historical settlement in each unit time within the historical period are calculated. Based on the mean and standard deviation of the historical settlement amount in each unit time period within the historical time period, a normal distribution model of settlement amount is constructed. Using the normal distribution model of settlement, a settlement baseline curve is generated based on the mean and standard deviation of the historical settlement within each unit time. Based on the dam status data, the settlement trend information, and the settlement baseline curve, dam settlement early warning information is obtained, which is used to indicate the severity of dam settlement.

4. The dam settlement monitoring method according to claim 3, characterized in that, The process of obtaining dam settlement early warning information based on the dam status data, the settlement trend information, and the settlement baseline curve includes: If the first settlement amount exceeds the first settlement range, the dam settlement early warning information will be output. Wherein, the first settlement is the difference between the second settlement calculated based on the dam status data and the third settlement obtained based on the settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

5. The dam settlement monitoring method according to claim 1, characterized in that, Before acquiring satellite-collected surface image data of the dam and surface sensor-collected dam status data, the method further includes: Based on the physical structural parameters of the dam, the stress distribution of the dam under various uniform stresses is simulated, the correlation between the stress on the dam structure and settlement is derived, and the first sub-prediction model is generated. Based on the historical settlement data corresponding to the dam and the environmental data corresponding to the historical settlement data, the correlation between the historical settlement data and the dam environmental data is derived, and the second sub-prediction model is generated. Based on the first sub-prediction model and the second sub-prediction model, the dam settlement prediction model is constructed.

6. A dam settlement monitoring device, characterized in that, include: Acquisition module, extraction module, recognition module, and processing module; The acquisition module is used to acquire dam surface image data collected by satellite and dam status data collected by surface sensors. The dam status data includes at least: dam displacement data, dam stress data, dam seepage data and dam environmental data. The extraction module is used to extract features from the dam surface image data to obtain dam structural feature information; The identification module is used to identify settlement anomalies based on the dam status data and obtain information on the dam settlement anomaly area. The processing module is used to input the dam structural feature information and the dam settlement anomaly area information into the dam settlement prediction model for prediction, and obtain the dam settlement trend information in the future time period. The dam settlement prediction model includes a first sub-prediction model and a second sub-prediction model. The first sub-prediction model is used to derive the relationship between the dam structure and the dam settlement, and the second sub-prediction model is used to derive the relationship between the dam environmental data and the dam settlement.

7. The dam settlement monitoring device according to claim 6, characterized in that, The processing module is specifically used to input the dam structural feature information, the dam state data, and the dam settlement anomaly area information into the dam settlement prediction model; And through the first sub-prediction model, settlement inference is performed based on the dam structural feature information, the dam displacement data, the dam stress data, the dam seepage data, and the dam settlement anomaly area to obtain the theoretical settlement value of the key points of the dam; Furthermore, by using the second sub-prediction model, based on the theoretical settlement values ​​of the key points of the dam and the environmental data of the dam, the settlement trend information for the future time period is obtained through correlation reasoning.

8. The dam settlement monitoring device according to claim 6 or 7, characterized in that, The processing module is further configured to input the dam structural feature information and the dam settlement anomaly area information into the dam settlement prediction model for prediction, and after obtaining the dam settlement trend information in the future time period, calculate the mean and standard deviation of the historical settlement amount in each unit time period based on the historical settlement data under the normal operating conditions of the dam in the historical time period. Based on the mean and standard deviation of the historical settlement amount in each unit time period within the historical time period, a normal distribution model of settlement amount is constructed. Using the normal distribution model of settlement, a settlement baseline curve is generated based on the mean and standard deviation of the historical settlement within each unit time. Based on the dam status data, the settlement trend information, and the settlement baseline curve, dam settlement early warning information is obtained, which is used to indicate the severity of dam settlement.

9. The dam settlement monitoring device according to claim 8, characterized in that, The processing module is specifically used to output the dam settlement early warning information when the first settlement amount is greater than the first settlement range; Wherein, the first settlement is the difference between the second settlement calculated based on the dam status data and the third settlement obtained based on the settlement trend information, and the first settlement range is determined based on the settlement baseline curve.

10. The dam settlement monitoring device according to claim 6, characterized in that, The processing module is also used to simulate the stress distribution of the dam under various uniform stresses based on the physical structural parameters of the dam before acquiring the dam surface image data collected by satellite and the dam state data collected by surface sensors, deduce the correlation between the dam structure stress and settlement, and generate the first sub-prediction model. Based on the historical settlement data corresponding to the dam and the environmental data corresponding to the historical settlement data, the correlation between the historical settlement data and the dam environmental data is derived, and the second sub-prediction model is generated. And based on the first sub-prediction model and the second sub-prediction model, the dam settlement prediction model is constructed.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the dam settlement monitoring method as described in any one of claims 1-5.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a computer, implement the dam settlement monitoring method as described in any one of claims 1-5.

13. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by a computer, the computer program product implements the dam settlement monitoring method as described in any one of claims 1-5.

Images