A reservoir dam deformation monitoring system

Abstract

This invention discloses a reservoir dam deformation monitoring system, belonging to the field of water conservancy engineering safety monitoring technology. To address the problems of limited data acquisition dimensions, difficulty in comprehensively presenting the true state of the dam under complex working conditions, lack of in-depth detection capabilities of the dam's internal structure, and difficulty in accurately predicting dam deformation trends, this invention comprehensively considers the interaction of displacement, stress, temperature, and hydraulic fields to accurately assess the dam's mechanical state and deformation trends. It utilizes elastic wave tomography technology to quickly and accurately detect internal defects in the dam, providing crucial evidence for dam maintenance and reinforcement, improving the system's defect identification capabilities. Employing dynamic risk assessment technology, it updates the dam deformation state transition probability by combining historical and real-time data, identifying potential safety hazards in advance, and constructing a complete closed-loop monitoring system to achieve all-weather intelligent protection. This significantly improves the accuracy, timeliness, and reliability of monitoring, effectively ensuring the safe operation of the reservoir.

Description

Technical Field

[0001] This invention relates to the field of water conservancy project safety monitoring technology, and in particular to a reservoir dam deformation monitoring system. Background Technology

[0002] Traditional reservoir dam monitoring methods have many limitations, often relying on single-parameter monitoring and lacking multi-dimensional data fusion and intelligent analysis. Patent application CN106895788A discloses an automatic monitoring method and system for reservoir dam deformation. The method includes the following steps: setting up detection points and a centralized monitoring device for the reservoir dam; acquiring reference image information of the detection points; and detecting reservoir dam deformation. The system includes a centralized monitoring device for the reservoir dam and several monitoring devices at equally spaced intervals arranged on the dam body along a straight line. The centralized monitoring device is located at one end of the detection points and can monitor all detection points to acquire image information from the monitoring devices at those points. This patent application selects N detection points on the dam body to generate light sources one by one, uses a progressive magnification positioning and shooting method to acquire the light source images of each detection point, and then extracts the deformation feature values ​​of each detection point to automatically monitor the settlement and horizontal displacement of the reservoir dam.

[0003] While the aforementioned patents have enabled automatic monitoring of reservoir dam settlement and horizontal displacement, improving monitoring efficiency to some extent, the following problems still exist:

[0004] 1. Existing technologies cannot integrate multi-dimensional monitoring data, nor can they obtain key data such as internal strain of the dam body, temperature gradient, and reservoir water level, making it difficult to fully reflect the true state of the dam body under complex working conditions.

[0005] 2. It can only extract deformation feature values ​​of the current detection point. When encountering complex internal structures of the dam, the signal is easily scattered and attenuated, making it difficult to effectively detect deep and large areas. The prediction of the future deformation trend of the dam is inaccurate, and it is difficult to take targeted preventive measures in advance. Summary of the Invention

[0006] The purpose of this invention is to provide a reservoir dam deformation monitoring system that integrates multi-dimensional monitoring data to achieve multi-physics field coupling analysis, accurately detects internal defects in the dam body, and scientifically predicts deformation trends. This allows for a comprehensive and accurate assessment of dam safety risks, ensuring the safe operation of the reservoir and solving the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A reservoir dam deformation monitoring system, comprising:

[0009] The data acquisition module is configured to collect displacement data of the dam body in real time based on a sensor network, and at the same time, acquire environmental parameters of the dam body's location and package them to generate basic data of the dam body.

[0010] The modeling and analysis module is configured to create a three-dimensional model of the dam body, and input the real-time acquired basic data and environmental parameters into the three-dimensional model of the dam body for mechanical analysis and deformation prediction.

[0011] The data fusion and evaluation module is configured to construct a multi-dimensional feature matrix based on the mechanical analysis results and the reservoir water level data in the basic data of the dam body, and to comprehensively evaluate the safety risk level of the dam body based on the deformation prediction results.

[0012] The early warning feedback module is configured to trigger an early warning mechanism based on the results of a security risk assessment, match and send the corresponding early warning information to the remote monitoring terminal, and adjust the monitoring strategy according to the feedback instructions from the remote monitoring terminal.

[0013] Furthermore, the data acquisition module includes:

[0014] The displacement strain acquisition unit is configured to install array-type displacement sensors at key locations on the dam body to acquire surface displacement data of the dam body in real time, and to deploy internal strain sensors inside the dam body to monitor the internal strain and temperature changes of the dam body in real time, thereby acquiring key data on dam body deformation in real time.

[0015] The environmental parameter acquisition unit is configured to continuously measure the temperature changes at different depths of the dam body based on the deployed temperature chain, and at the same time monitor the water level in the reservoir area using a pressure-type water level gauge.

[0016] The data transmission unit is configured to align the data collected by the displacement strain acquisition unit and the environmental parameter acquisition unit based on the time series, and package them to generate the basic data of the dam body.

[0017] Furthermore, the modeling and analysis module includes:

[0018] The 3D modeling unit is configured to obtain dam material parameters based on BIM parameters and geological exploration reports, determine the layered structure and bedrock constraint conditions in conjunction with dam design drawings, and construct a 3D model of the dam.

[0019] The finite element analysis unit is configured to preprocess the real-time monitoring data, and input the preprocessed data as boundary conditions into the dam's three-dimensional model for mechanical analysis, generating a stress-strain spatiotemporal distribution cloud map.

[0020] The finite element analysis unit also includes acquiring historical monitoring data of the dam body, analyzing and modeling the historical monitoring data and the currently input basic data based on time series analysis algorithms, and predicting the future deformation trend of the dam body.

[0021] Furthermore, the 3D modeling unit also includes:

[0022] When constructing the three-dimensional model of the dam, historical basic data is extracted from historical monitoring data to identify effective data related to the mechanical properties and deformation of the dam.

[0023] Based on the identification results, the attribute information of valid data is determined, and a valid dataset is generated by packaging it.

[0024] Cluster analysis is performed on the attribute information of each sub-data in the effective dataset to divide the sub-data into at least one data set;

[0025] Multiple storage nodes are set up in the effective storage area. Key storage nodes are extracted from the storage nodes based on the election mechanism. The connection relationship with other storage nodes is determined based on the performance parameters of each storage node, and a communication tree is generated.

[0026] Based on the characteristics of the data set, combined with the network topology of the communication tree and the performance indicators of the storage nodes, the target storage node of the communication tree is determined.

[0027] A DMA control block is constructed to describe the data transfer information for storing the data set to each target storage node. Based on the key storage nodes, the data transfer information is verified to generate a verification information list and perform data anomaly detection. If an anomaly is found, an alarm is issued; otherwise, a storage completion message is generated.

[0028] Furthermore, the data fusion evaluation module includes:

[0029] The multi-source data fusion unit is configured to match the mechanical analysis results with the reservoir water level data and the corresponding time period data in the effective data in the dam body basic data in terms of time and space based on the spatiotemporal correlation algorithm, and construct a multi-dimensional feature matrix.

[0030] The dynamic evaluation unit is configured to obtain the real-time operating status and historical evolution trend of the dam body based on the simulation results of the dam body three-dimensional model, dynamically evaluate the dam body status, identify the development trend of potential defects and safety hazards, and dynamically evaluate the dam body safety risk level.

[0031] Furthermore, the dynamic evaluation unit also includes:

[0032] The dynamic Bayesian network sub-unit is configured to use a hidden Markov model combined with historical data in the historical monitoring database, and uses a multi-dimensional feature matrix to update the dam deformation state transition probability in real time, and outputs the dam abnormal deformation probability value.

[0033] The elastic wave tomography subunit is configured to use an array-type piezoelectric excitation device to emit elastic wave signals, reconstruct the three-dimensional velocity field of the dam body based on the received reflected waveform, determine the distribution of abnormal areas in the three-dimensional velocity field of the dam body, identify the location, size and development of structural defects inside the dam body, and adjust the elastic wave emission frequency, emission angle and emission time interval according to the structural characteristics of the dam body and the previous monitoring results.

[0034] The risk assessment subunit is configured as a dynamic stability evaluation model based on the Mohr-Coulomb criterion and incorporating fuzzy logic. It calculates the local safety factor of the dam body based on the probability value of abnormal deformation of the dam body and the distribution of abnormal areas in the three-dimensional velocity field of the dam body. At the same time, it comprehensively analyzes the safety factor of each local area and the overall mechanical response of the dam body to calculate the overall stability factor of the dam body. Based on the overall stability factor and the local safety factor of the dam body, it assesses the safety risk level of the dam body.

[0035] Furthermore, the early warning feedback module includes:

[0036] The early warning triggering unit is configured to compare the assessed dam safety risk level with a preset risk early warning threshold. When the safety risk level reaches the corresponding threshold range, the early warning mechanism is triggered to determine the level of early warning information to be sent.

[0037] The information sending unit is configured to match the corresponding early warning information content from a predefined early warning information database according to the early warning level determined by the early warning triggering unit, and send the early warning information content to the remote monitoring terminal via an encrypted LoRa network;

[0038] The strategy adjustment unit is configured to receive feedback instructions sent by the remote monitoring terminal, parse the instruction content, and adjust the monitoring strategy according to the instruction requirements.

[0039] Furthermore, the early warning mechanism includes a three-level response mechanism: a yellow warning is triggered when the local safety factor is less than 1.5 or the overall stability factor is less than 2.0; an orange warning is triggered when the local safety factor is less than 1.2 or the overall stability factor is less than 1.5; and a red warning is activated when the local safety factor is less than 1.0 or the overall stability factor is less than 1.2.

[0040] Furthermore, it also includes: a display module, used to dynamically display the 3D model of the dam body based on the deformation prediction results, specifically including:

[0041] The mapping unit constructs the display interface, and at the same time, obtains the edge point position information of the dam body 3D model, performs association mapping on the display interface based on the edge point position information, and displays the dam body 3D model based on the association mapping result;

[0042] The unit division is used to obtain the key structural points of the dam body 3D model, and to divide the dam body 3D model according to the key structural points to obtain multiple sub-dam body 3D models, where each sub-dam body 3D model contains one key structural point;

[0043] Analysis unit, used for:

[0044] The initial stress value of each key structural point is obtained, and the predicted stress value of each key structural point is determined based on the deformation prediction results.

[0045] Compare the initial stress values ​​of key structural points with the corresponding predicted stress values ​​within their set ranges;

[0046] When the initial stress value of a critical structural point is within the set range of the corresponding predicted stress value, the current critical structural point is determined to be stable.

[0047] Otherwise, the current critical structural point is determined to be unstable. At the same time, the corresponding sub-dam body 3D model is marked according to the current critical structural point to obtain the marked area.

[0048] The region index determination unit is used to obtain the location information of the current key structural point and generate the region index of the labeled area based on the location information of the current key structural point.

[0049] The dynamic analog video generation unit is used for:

[0050] Obtain the time interval between the initial stress value and the predicted stress value, and determine the stress change within a preset unit time based on the time interval between the initial stress value and the predicted stress value.

[0051] Based on the stress change within a preset unit time, the stress change of key structural points in the marked area is simulated, and dynamic change frames are generated based on the simulation results. Based on the dynamic change frames, dynamic simulation videos of the marked area are generated.

[0052] The display unit is used to encapsulate the dynamic simulation video according to the region index, and simultaneously display the 3D model of the dam body based on the display interface. At the same time, the region index of the marked area is displayed in the 3D model of the dam body for the second time. The dynamic simulation video is retrieved based on the region index and displayed in the third time according to the display interface.

[0053] Furthermore, the modeling and analysis module, which predicts deformation of the dam's 3D model, also includes:

[0054] The data retrieval unit is used to retrieve historical dam deformation prediction data and the corresponding actual data.

[0055] The first computing unit is used for:

[0056] Based on historical dam deformation prediction data and corresponding actual data, determine the number of times the dam deformation prediction was accurate and the number of times the dam deformation prediction was inaccurate.

[0057] The accuracy of deformation prediction for the 3D model of the dam is calculated based on the number of times the dam deformation prediction is accurate and the number of times the dam deformation prediction is inaccurate.

[0058]

[0059] Where δ represents the accuracy of deformation prediction for the 3D model of the dam; n represents the total number of historical dam deformation predictions; n1 represents the number of times the dam deformation prediction was accurate; and n0 represents the number of times the dam deformation prediction was inaccurate.

[0060] The comparison unit is used to obtain a preset accuracy threshold and compare the accuracy of deformation prediction of the dam body 3D model with the preset accuracy threshold.

[0061] The second calculation unit is used to calculate the average error of the dam deformation prediction when the accuracy of the deformation prediction of the dam body three-dimensional model is less than the preset accuracy threshold.

[0062]

[0063] Where Δs represents the mean error of the dam deformation prediction; i represents the sequence number of the historical dam deformation predictions; s i This represents the actual data at the i-th historical dam deformation prediction; This represents the predicted data for the i-th historical dam deformation prediction.

[0064] Correction unit, used for:

[0065] Read the real-time predicted value of the current dam deformation prediction, and correct the real-time predicted value based on the average error of the dam deformation prediction.

[0066]

[0067] Where S represents the correction value applied to the real-time forecast; s 实时 This represents the real-time predicted value for the current dam deformation prediction.

[0068] Update the real-time prediction value of the current dam deformation prediction based on the correction results.

[0069] Compared with the prior art, the beneficial effects of the present invention are:

[0070] By comprehensively considering the interaction of displacement, stress, temperature, and hydraulic fields, the mechanical state and deformation trend of the dam body are accurately assessed, enabling multi-physics field coupling analysis. Elastic wave tomography technology is used to quickly and accurately detect internal defects in the dam body, providing crucial information for dam maintenance and reinforcement, and improving the system's defect identification capabilities. Dynamic risk assessment technology is employed, combining historical and real-time data to update the probability of dam deformation state transitions, allowing for the early detection of potential safety hazards. A complete closed-loop monitoring system is constructed to achieve all-weather intelligent protection, significantly improving the accuracy, timeliness, and reliability of monitoring, effectively ensuring the safe operation of the reservoir, reducing the risk of safety accidents, and safeguarding the lives and property of people downstream.

[0071] By identifying key structural points in the dam's 3D model, the model is divided based on these points. Simultaneously, the initial stress value and the predicted stress value under deformation prediction are determined for each key structural point. The stability of the dam's 3D model is then assessed based on the relative magnitudes of the initial and predicted stress values. In cases of instability, the corresponding sub-dam 3D models are annotated, generating corresponding region indexes. Furthermore, dynamic simulation videos of the annotated regions are generated based on the initial and predicted stress values. Finally, the dam's 3D model, the region indexes of the annotated areas, and the dynamic simulation videos are displayed accordingly. This facilitates timely and effective viewing and understanding of the dam's 3D model, improving the accuracy and reliability of reservoir dam deformation monitoring and providing convenience for reservoir dam deformation monitoring.

[0072] By calculating the accuracy of deformation prediction of the dam's three-dimensional model, the prediction effect can be effectively measured. When the accuracy is less than the preset threshold, the real-time prediction value can be effectively corrected by calculating the mean error, thus ensuring the accuracy and effectiveness of the final prediction value. Attached Figure Description

[0073] Figure 1 This is a module diagram of the reservoir dam deformation monitoring system of the present invention. Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] To address the technical problems in existing technologies, such as the limited data acquisition dimensions, inability to comprehensively represent the true state of the dam body under complex operating conditions, lack of in-depth detection capabilities of the dam body's internal structure, and difficulty in accurately predicting dam deformation trends, please refer to [the relevant documentation / reference]. Figure 1 This embodiment provides the following technical solution:

[0076] A reservoir dam deformation monitoring system, comprising:

[0077] The data acquisition module is configured based on a sensor network, integrating multiple sensors such as displacement sensors, strain sensors, tilt sensors, and fiber optic temperature sensors. It collects real-time displacement data of the dam body and simultaneously acquires environmental parameters at the dam's location, packaging them to generate basic dam data, including surface displacement, internal strain, temperature gradient, and reservoir water level data.

[0078] The displacement strain acquisition unit is configured to install array-type displacement sensors (surface displacement gauges) at key locations on the dam body to acquire surface displacement data of the dam body in real time, and to deploy internal strain sensors inside the dam body to monitor the internal strain and temperature changes of the dam body in real time, thereby acquiring key data on dam body deformation in real time.

[0079] The environmental parameter acquisition unit is configured to continuously measure the temperature changes at different depths of the dam body based on a deployed temperature chain, i.e., distributed fiber optic temperature sensors, while monitoring the reservoir water level using pressure level gauges.

[0080] The data transmission unit is configured to align the data collected by the displacement strain acquisition unit and the environmental parameter acquisition unit based on the time series, and package them to generate the basic data of the dam body;

[0081] The modeling and analysis module is configured to create a three-dimensional model of the dam body that includes material constitutive relations, layered structure and bedrock constraints, and input real-time acquired basic data and environmental parameters into the three-dimensional model of the dam body for mechanical analysis and deformation prediction.

[0082] The data fusion and evaluation module is configured to construct a multi-dimensional feature matrix based on the mechanical analysis results and the reservoir water level data in the basic data of the dam body, and to comprehensively evaluate the safety risk level of the dam body based on the deformation prediction results.

[0083] The early warning feedback module is configured to trigger an early warning mechanism based on the results of a security risk assessment, match and send the corresponding early warning information to the remote monitoring terminal, and adjust the monitoring strategy according to the feedback instructions from the remote monitoring terminal.

[0084] In this embodiment, multiple sensors in the data acquisition module collect basic data such as dam displacement, strain, temperature, and water level in real time. The modeling and analysis module constructs a three-dimensional model and performs mechanical analysis and deformation prediction. Then, the data fusion and evaluation module combines the results of mechanical analysis and deformation prediction with reservoir water level data to construct a multi-dimensional feature matrix to assess the dam's safety risk level. Finally, the early warning feedback module triggers an early warning based on the risk level and adjusts the monitoring strategy according to the feedback instructions. This achieves multi-dimensional, real-time, and intelligent monitoring of the reservoir dam's operating status, enabling timely detection of potential safety hazards, early warning, and dynamic optimization of monitoring strategies. This effectively ensures the safe and stable operation of the reservoir, reduces the risk of safety accidents, and protects the lives and property of people downstream.

[0085] In this embodiment, the modeling and analysis module includes:

[0086] The 3D modeling unit is configured to obtain dam material parameters, such as elastic modulus and Poisson's ratio, based on BIM parameters and geological exploration reports, and determine the layered structure and bedrock constraints in conjunction with dam design drawings, thereby constructing a 3D model of the dam that includes material constitutive relations, layered structure, and bedrock constraints.

[0087] The finite element analysis unit is configured to preprocess the real-time monitoring data, including format conversion, removal of outliers and noise interference, and input the preprocessed data as boundary conditions into the dam body three-dimensional model for mechanical analysis, generating a stress-strain spatiotemporal distribution cloud map.

[0088] The finite element analysis unit also includes acquiring historical monitoring data of the dam body, analyzing and modeling the historical monitoring data and the currently input basic data based on time series analysis algorithms, and predicting the deformation trend of the dam body in the next 72 hours.

[0089] In this embodiment, the 3D modeling unit further includes:

[0090] When constructing the 3D model of the dam, historical basic data is extracted from historical monitoring data, and effective data related to the mechanical properties and deformation of the dam are identified. For the determination of dam material parameters, monitoring data related to elastic modulus and Poisson's ratio are extracted. For the simulation of layered structure and bedrock constraint conditions, data such as displacement, strain and environmental parameters near the bedrock in different layers are extracted.

[0091] Based on the identification results, determine the attribute information of the valid data, such as the data collection time, collection location, data type, etc., and package them to generate a valid dataset;

[0092] Cluster analysis is performed based on the attribute information of each sub-data in the effective dataset to divide the sub-data into at least one data set. For example, data related to the material properties of the dam body are grouped into one category, and data related to the impact of environmental factors are grouped into another category.

[0093] Multiple storage nodes are set up in the effective storage area. Key storage nodes are extracted from the storage nodes based on the election mechanism. The connection relationship with other storage nodes is determined based on the performance parameters of each storage node, such as location information, storage capacity, and transmission rate, and a communication tree is generated.

[0094] Based on the characteristics of the data set, combined with the network topology of the communication tree and the performance indicators of the storage nodes, the target storage node of the communication tree is determined.

[0095] A DMA control block is constructed to describe the data transfer information for storing the data set to each target storage node. Based on the key storage nodes, the data transfer information is verified to generate a verification information list and perform data anomaly detection. If an anomaly is found, an alarm is issued; otherwise, a storage completion message is generated.

[0096] In this embodiment, a 3D model of the dam is constructed by combining BIM parameters and geological exploration reports with a 3D modeling unit. Valid data is extracted from historical monitoring data to improve the model foundation. After cluster analysis, the data is rationally planned and stored in the target nodes of the communication tree. The finite element analysis unit preprocesses the real-time basic data and inputs it into the 3D model of the dam for mechanical analysis, generating a stress-strain spatiotemporal distribution cloud map. Combined with historical monitoring data, the deformation trend of the dam in the next 72 hours is predicted, constructing a high-precision 3D model of the dam. This achieves the effect of visual analysis of the mechanical state of the dam and accurate prediction of deformation trends, providing a reliable digital foundation and analytical basis for subsequent data fusion assessment and risk level determination, effectively improving the scientificity and accuracy of reservoir dam deformation monitoring.

[0097] In this embodiment, the data fusion evaluation module includes:

[0098] The multi-source data fusion unit is configured to match the mechanical analysis results with the reservoir water level data and the corresponding time period data in the effective data in the dam body basic data in time and space based on the spatiotemporal correlation algorithm, and construct a multi-dimensional feature matrix covering displacement, stress, temperature and hydraulic multi-field coupling characteristics.

[0099] The dynamic evaluation unit is configured to acquire the real-time operating status and historical evolution trend of the dam body based on a multi-dimensional feature matrix and the simulation results of the dam body's three-dimensional model, dynamically evaluate the dam body's condition, identify the development trend of potential defects and safety hazards, and dynamically evaluate the dam body's safety risk level. It also includes:

[0100] The dynamic Bayesian network sub-unit is configured to use a hidden Markov model combined with historical data in a historical monitoring database to update the dam deformation state transition probability in real time using a multi-dimensional feature matrix. The hidden Markov model automatically adjusts the weights for calculating the state transition probability based on the actual operation of the dam and outputs the probability value of abnormal deformation of the dam.

[0101] The elastic wave tomography subunit is configured to emit elastic wave signals using an array-type piezoelectric excitation device. Based on the received reflected waveform, an optimized full waveform inversion algorithm is used to reconstruct the three-dimensional velocity field of the dam body in real time, determine the distribution of abnormal areas in the three-dimensional velocity field of the dam body, identify the location, size, and development of structural defects inside the dam body, and adjust the elastic wave emission frequency (0.5-5kHz), emission angle, and emission time interval according to the structural characteristics of the dam body and the previous monitoring results.

[0102] The risk assessment subunit is configured as a dynamic stability evaluation model based on the Mohr-Coulomb criterion and incorporating fuzzy logic. It calculates the local safety factor of the dam body based on the probability value of abnormal deformation of the dam body and the distribution of abnormal areas in the three-dimensional velocity field of the dam body. At the same time, it comprehensively analyzes the safety factor of each local area and the overall mechanical response of the dam body to calculate the overall stability factor of the dam body. Based on the overall stability factor and the local safety factor of the dam body, it assesses the safety risk level of the dam body.

[0103] In this embodiment, the multi-source data fusion unit employs a spatiotemporal correlation algorithm to perform spatiotemporal matching of mechanical analysis results, reservoir water level data, and historical valid data to construct a multi-dimensional feature matrix. This comprehensively integrates multi-field coupling information of the dam body, utilizes a hidden Markov model to accurately update the deformation state transition probability, and provides predictions of abnormal deformation probabilities. The array-type piezoelectric vibration device reconstructs the three-dimensional velocity field of the dam body in real time, identifies internal defects, and dynamically adjusts detection parameters. This enables real-time monitoring and dynamic evaluation of the dam body's operating status, accurately predicts the probability of abnormal deformation of the dam body, provides important basis for risk assessment, provides intuitive internal structural information for dam body safety assessment, and calculates the local safety factor and overall stability factor of the dam body. This allows for a more comprehensive assessment of the dam body's safety risk level and improves the intelligence level and early warning accuracy of reservoir dam body safety monitoring.

[0104] In this embodiment, the early warning feedback module includes:

[0105] The early warning triggering unit is configured to compare the assessed dam safety risk level with a preset risk early warning threshold. When the safety risk level reaches the corresponding threshold range, the early warning mechanism is triggered to determine the level of early warning information to be sent.

[0106] In this embodiment, the early warning mechanism includes a three-level response mechanism: a yellow warning is triggered when the local safety factor is less than 1.5 or the overall stability factor is less than 2.0; an orange warning is triggered when the local safety factor is less than 1.2 or the overall stability factor is less than 1.5; and a red warning is activated when the local safety factor is less than 1.0 or the overall stability factor is less than 1.2.

[0107] The information sending unit is configured to match the corresponding early warning information content from a predefined early warning information database, including text descriptions, risk warnings, and suggested measures, based on the early warning level determined by the early warning triggering unit, and send the early warning information content to the remote monitoring terminal via an encrypted LoRa network through a wireless communication network to ensure timely information transmission.

[0108] The strategy adjustment unit is configured to receive feedback instructions sent by the remote monitoring terminal, parse the instruction content, and adjust the monitoring strategy according to the instruction requirements. For example, it can adjust the acquisition frequency of certain sensors in the data acquisition module, or change the analysis parameters and prediction cycle of the modeling and analysis module to adapt to different monitoring needs and realize the dynamic optimization of the monitoring system.

[0109] In this embodiment, a three-level response mechanism is used to accurately trigger early warnings at different levels, enabling managers to quickly understand the risk level of the dam. The encrypted LoRa network promptly transmits the matching early warning information to the remote monitoring terminal, ensuring information security and zero delay. This achieves timely perception, effective communication, and precise response to dam safety risks, greatly improving the timeliness and effectiveness of reservoir dam safety monitoring, reducing the possibility of safety accidents, ensuring the stable operation of the reservoir and the safety of people's lives and property downstream. The encrypted LoRa network also enables dynamic optimization of the monitoring system, allowing it to better adapt to complex and ever-changing monitoring scenarios.

[0110] In one embodiment, a reservoir dam deformation monitoring system further includes: a display module for dynamically displaying a three-dimensional model of the dam body based on deformation prediction results, specifically including:

[0111] The mapping unit constructs the display interface, and at the same time, obtains the edge point position information of the dam body 3D model, performs association mapping on the display interface based on the edge point position information, and displays the dam body 3D model based on the association mapping result;

[0112] The unit division is used to obtain the key structural points of the dam body 3D model, and to divide the dam body 3D model according to the key structural points to obtain multiple sub-dam body 3D models, where each sub-dam body 3D model contains one key structural point;

[0113] Analysis unit, used for:

[0114] The initial stress value of each key structural point is obtained, and the predicted stress value of each key structural point is determined based on the deformation prediction results.

[0115] Compare the initial stress values ​​of key structural points with the corresponding predicted stress values ​​within their set ranges;

[0116] When the initial stress value of a critical structural point is within the set range of the corresponding predicted stress value, the current critical structural point is determined to be stable.

[0117] Otherwise, the current critical structural point is determined to be unstable. At the same time, the corresponding sub-dam body 3D model is marked according to the current critical structural point to obtain the marked area.

[0118] The region index determination unit is used to obtain the location information of the current key structural point and generate the region index of the labeled area based on the location information of the current key structural point.

[0119] The dynamic analog video generation unit is used for:

[0120] Obtain the time interval between the initial stress value and the predicted stress value, and determine the stress change within a preset unit time based on the time interval between the initial stress value and the predicted stress value.

[0121] Based on the stress change within a preset unit time, the stress change of key structural points in the marked area is simulated, and dynamic change frames are generated based on the simulation results. Based on the dynamic change frames, dynamic simulation videos of the marked area are generated.

[0122] The display unit is used to encapsulate the dynamic simulation video according to the region index, and simultaneously display the 3D model of the dam body based on the display interface. At the same time, the region index of the marked area is displayed in the 3D model of the dam body for the second time. The dynamic simulation video is retrieved based on the region index and displayed in the third time according to the display interface.

[0123] In this embodiment, edge points refer to the contour points of the dam's three-dimensional model.

[0124] In this embodiment, key structural points refer to structures in the 3D model of the dam that can characterize the dam's structural condition, such as load-bearing points.

[0125] In this embodiment, the sub-dam 3D model refers to the result obtained by dividing the dam 3D model according to key structural points, and is a part of the original dam 3D model.

[0126] In this embodiment, the stress prediction value refers to the stress value of each key structural point after deformation, determined based on the deformation prediction results.

[0127] In this embodiment, the region index is generated based on the location information of key structural points and is used to provide retrieval guidance when searching the labeled region.

[0128] In this embodiment, the preset unit time is set in advance, such as one hour or one day.

[0129] In this embodiment, the dynamic change frame is used to characterize the degree of change in specific stress at different key structural points at each moment, including the magnitude of the change.

[0130] In this embodiment, the first display refers to displaying the three-dimensional model of the dam body.

[0131] In this embodiment, the second display refers to displaying the region index of the labeled area.

[0132] In this embodiment, the third display refers to the display of dynamic simulated video within the marked area.

[0133] The working principle and beneficial effects of the above technical solution are as follows: By identifying key structural points in the 3D model of the dam, the 3D model of the dam is divided according to these key structural points. Simultaneously, the initial stress value and the predicted stress value under deformation prediction results are determined for each key structural point. The stability of the 3D model of the dam is then judged based on the relative magnitude of the initial stress value and the predicted stress value. Furthermore, when unstable, the corresponding sub-dam 3D models are labeled, and corresponding regional indexes are generated based on the labeling results. Simultaneously, dynamic simulation videos of the labeled regions are generated based on the initial stress value and the predicted stress value. Finally, the 3D model of the dam, the regional indexes of the labeled regions, and the dynamic simulation videos are displayed accordingly, facilitating timely and effective viewing and understanding of the specific situation of the 3D model of the dam. This improves the accuracy and reliability of reservoir dam deformation monitoring and provides convenience for reservoir dam deformation monitoring.

[0134] In one embodiment, a reservoir dam deformation monitoring system is provided, in which the modeling and analysis module predicts the deformation of the dam's three-dimensional model, and further includes:

[0135] The data retrieval unit is used to retrieve historical dam deformation prediction data and the corresponding actual data.

[0136] The first computing unit is used for:

[0137] Based on historical dam deformation prediction data and corresponding actual data, determine the number of times the dam deformation prediction was accurate and the number of times the dam deformation prediction was inaccurate.

[0138] The accuracy of deformation prediction for the 3D model of the dam is calculated based on the number of times the dam deformation prediction is accurate and the number of times the dam deformation prediction is inaccurate.

[0139]

[0140] Where δ represents the accuracy of deformation prediction for the 3D model of the dam; n represents the total number of historical dam deformation predictions; n1 represents the number of times the dam deformation prediction was accurate; and n0 represents the number of times the dam deformation prediction was inaccurate.

[0141] The comparison unit is used to obtain a preset accuracy threshold and compare the accuracy of deformation prediction of the dam body 3D model with the preset accuracy threshold.

[0142] The second calculation unit is used to calculate the average error of the dam deformation prediction when the accuracy of the deformation prediction of the dam body three-dimensional model is less than the preset accuracy threshold.

[0143]

[0144] Where Δs represents the mean error of the dam deformation prediction; i represents the sequence number of the historical dam deformation predictions; s i This represents the actual data at the i-th historical dam deformation prediction; This represents the predicted data for the i-th historical dam deformation prediction.

[0145] Correction unit, used for:

[0146] Read the real-time predicted value of the current dam deformation prediction, and correct the real-time predicted value based on the average error of the dam deformation prediction.

[0147]

[0148] Where S represents the correction value applied to the real-time forecast; s 实时 This represents the real-time predicted value for the current dam deformation prediction.

[0149] Update the real-time prediction value of the current dam deformation prediction based on the correction results.

[0150] In this embodiment, the preset accuracy threshold is set in advance and is used as a standard to measure whether the mean error needs to be calculated. When the accuracy of deformation prediction of the dam body three-dimensional model is equal to or greater than the preset accuracy threshold, the mean error does not need to be calculated.

[0151] In this embodiment, This is to ensure that the corrected results are more accurate.

[0152] The working principle and beneficial effects of the above technical solution are as follows: by calculating the accuracy of deformation prediction of the three-dimensional model of the dam, the prediction effect can be effectively measured. Furthermore, when the accuracy is less than the preset accuracy threshold, the real-time prediction value can be effectively corrected by calculating the mean error, thus ensuring the accuracy and effectiveness of the final prediction value.

[0153] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A reservoir dam deformation monitoring system, characterized in that, include: The data acquisition module is configured to collect displacement data of the dam body in real time based on a sensor network, and at the same time, acquire environmental parameters of the dam body's location and package them to generate basic data of the dam body. The modeling and analysis module is configured to create a three-dimensional model of the dam body, input real-time acquired basic data and environmental parameters into the three-dimensional model of the dam body for mechanical analysis and deformation prediction, and correct the prediction results based on the deformation prediction accuracy. The data fusion and evaluation module is configured to construct a multi-dimensional feature matrix based on the mechanical analysis results and the reservoir water level data in the basic data of the dam body, and to comprehensively evaluate the safety risk level of the dam body based on the deformation prediction results. The early warning feedback module is configured to trigger an early warning mechanism based on the results of the security risk assessment, match and send the corresponding early warning information to the remote monitoring terminal, and adjust the monitoring strategy according to the feedback instructions from the remote monitoring terminal. The display module is used to dynamically display the 3D model of the dam body based on the deformation prediction results; The modeling and analysis module includes: The 3D modeling unit is configured to obtain dam material parameters based on BIM parameters and geological exploration reports, determine the layered structure and bedrock constraint conditions in conjunction with dam design drawings, and construct a 3D model of the dam. The finite element analysis unit is configured to preprocess the real-time monitoring data, and input the preprocessed data as boundary conditions into the dam's three-dimensional model for mechanical analysis, generating a stress-strain spatiotemporal distribution cloud map. The finite element analysis unit also includes acquiring historical monitoring data of the dam body, analyzing and modeling the historical monitoring data and the currently input basic data based on time series analysis algorithms, and predicting the future deformation trend of the dam body. The 3D modeling unit also includes: When constructing the three-dimensional model of the dam, historical basic data is extracted from historical monitoring data to identify effective data related to the mechanical properties and deformation of the dam. Based on the identification results, the attribute information of valid data is determined, and a valid dataset is generated by packaging it. Cluster analysis is performed on the attribute information of each sub-data in the effective dataset to divide the sub-data into at least one data set; Multiple storage nodes are set up in the effective storage area. Key storage nodes are extracted from the storage nodes based on the election mechanism. The connection relationship with other storage nodes is determined based on the performance parameters of each storage node, and a communication tree is generated. Based on the characteristics of the data set, combined with the network topology of the communication tree and the performance indicators of the storage nodes, the target storage node of the communication tree is determined. A DMA control block is constructed to describe the data transfer information for storing the data set to each target storage node. Based on the key storage nodes, the data transfer information is verified to generate a verification information list and perform data anomaly detection. If an anomaly is found, an alarm is issued; otherwise, a storage completion message is generated.

2. The reservoir dam deformation monitoring system as described in claim 1, characterized in that, The data acquisition module includes: The displacement strain acquisition unit is configured to install array-type displacement sensors at key locations on the dam body to acquire surface displacement data of the dam body in real time, and to deploy internal strain sensors inside the dam body to monitor the internal strain and temperature changes of the dam body in real time, thereby acquiring key data on dam body deformation in real time. The environmental parameter acquisition unit is configured to continuously measure the temperature changes at different depths of the dam body based on the deployed temperature chain, and at the same time monitor the water level in the reservoir area using a pressure-type water level gauge. The data transmission unit is configured to align the data collected by the displacement strain acquisition unit and the environmental parameter acquisition unit based on the time series, and package them to generate the basic data of the dam body.

3. The reservoir dam deformation monitoring system as described in claim 2, characterized in that, The data fusion evaluation module includes: The multi-source data fusion unit is configured to match the mechanical analysis results with the reservoir water level data and the corresponding time period data in the effective data in the dam body basic data in terms of time and space based on the spatiotemporal correlation algorithm, and construct a multi-dimensional feature matrix. The dynamic evaluation unit is configured to obtain the real-time operating status and historical evolution trend of the dam body based on the simulation results of the dam body three-dimensional model, dynamically evaluate the dam body status, identify the development trend of potential defects and safety hazards, and dynamically evaluate the dam body safety risk level.

4. The reservoir dam deformation monitoring system as described in claim 3, characterized in that, The dynamic evaluation unit also includes: The dynamic Bayesian network sub-unit is configured to use a hidden Markov model combined with historical monitoring data to update the dam deformation state transition probability in real time using a multi-dimensional feature matrix and output the dam abnormal deformation probability value. The elastic wave tomography subunit is configured to use an array-type piezoelectric excitation device to emit elastic wave signals, reconstruct the three-dimensional velocity field of the dam body based on the received reflected waveform, determine the distribution of abnormal regions in the three-dimensional velocity field of the dam body, identify the location, size and development of structural defects inside the dam body, and adjust the elastic wave emission frequency, emission angle and emission time interval based on the parameters of the three-dimensional model of the dam body and historical monitoring data. The risk assessment subunit is configured to calculate the local safety factor of the dam body based on the probability value of abnormal deformation of the dam body and the distribution of abnormal areas in the three-dimensional velocity field of the dam body. At the same time, it comprehensively analyzes the safety factor of each local area and the overall mechanical response of the dam body to calculate the overall stability factor of the dam body. Based on the overall stability factor and the local safety factor of the dam body, it assesses the safety risk level of the dam body.

5. The reservoir dam deformation monitoring system as described in claim 1, characterized in that, The early warning feedback module includes: The early warning triggering unit is configured to compare the assessed dam safety risk level with a preset risk early warning threshold. When the safety risk level reaches the corresponding threshold range, the early warning mechanism is triggered to determine the level of early warning information to be sent. The information sending unit is configured to match the corresponding early warning information content from a predefined early warning information database according to the early warning level determined by the early warning triggering unit, and send the early warning information content to the remote monitoring terminal via an encrypted LoRa network; The strategy adjustment unit is configured to receive feedback instructions sent by the remote monitoring terminal, parse the instruction content, and adjust the monitoring strategy according to the instruction requirements.

6. The reservoir dam deformation monitoring system as described in claim 5, characterized in that, The early warning mechanism includes a three-level response mechanism: a yellow warning is triggered when the local safety factor is less than 1.5 or the overall stability factor is less than 2.0; an orange warning is triggered when the local safety factor is less than 1.2 or the overall stability factor is less than 1.5; and a red warning is activated when the local safety factor is less than 1.0 or the overall stability factor is less than 1.

2.

7. The reservoir dam deformation monitoring system as described in claim 1, characterized in that, The display module specifically includes: The mapping unit constructs the display interface, and at the same time, obtains the edge point position information of the dam body 3D model, performs association mapping on the display interface based on the edge point position information, and displays the dam body 3D model based on the association mapping result; The unit division is used to obtain the key structural points of the dam body 3D model, and to divide the dam body 3D model according to the key structural points to obtain multiple sub-dam body 3D models, where each sub-dam body 3D model contains one key structural point; Analysis unit, used for: The initial stress value of each key structural point is obtained, and the predicted stress value of each key structural point is determined based on the deformation prediction results. Compare the initial stress values ​​of key structural points with the corresponding predicted stress values ​​within their set ranges; When the initial stress value of a critical structural point is within the set range of the corresponding predicted stress value, the current critical structural point is determined to be stable. Otherwise, the current critical structural point is determined to be unstable. At the same time, the corresponding sub-dam body 3D model is marked according to the current critical structural point to obtain the marked area. The region index determination unit is used to obtain the location information of the current key structural point and generate the region index of the labeled area based on the location information of the current key structural point. The dynamic analog video generation unit is used for: Obtain the time interval between the initial stress value and the predicted stress value, and determine the stress change within a preset unit time based on the time interval between the initial stress value and the predicted stress value. Based on the stress change within a preset unit time, the stress change of key structural points in the marked area is simulated, and dynamic change frames are generated based on the simulation results. Based on the dynamic change frames, dynamic simulation videos of the marked area are generated. The display unit is used to encapsulate the dynamic simulation video according to the region index, and simultaneously display the 3D model of the dam body based on the display interface. At the same time, the region index of the marked area is displayed in the 3D model of the dam body for the second time. The dynamic simulation video is retrieved based on the region index and displayed in the third time according to the display interface.

8. The reservoir dam deformation monitoring system as described in claim 1, characterized in that, The modeling and analysis module includes deformation prediction of the dam's 3D model, and also includes: The data retrieval unit is used to retrieve historical dam deformation prediction data and the corresponding actual data. The first computing unit is used for: Based on historical dam deformation prediction data and corresponding actual data, determine the number of times the dam deformation prediction was accurate and the number of times the dam deformation prediction was inaccurate. The accuracy of deformation prediction for the 3D model of the dam is calculated based on the number of times the dam deformation prediction is accurate and the number of times the dam deformation prediction is inaccurate. ； in, This indicates the accuracy of deformation prediction based on the 3D model of the dam body; This represents the total number of historical dam deformation predictions. Indicates the number of times the dam deformation prediction was accurate; This indicates the number of times the dam deformation prediction was inaccurate. The comparison unit is used to obtain a preset accuracy threshold and compare the accuracy of deformation prediction of the dam body 3D model with the preset accuracy threshold. The second calculation unit is used to calculate the average error of the dam deformation prediction when the accuracy of the deformation prediction of the dam body three-dimensional model is less than the preset accuracy threshold. ； in, This represents the mean error in the prediction of dam deformation. The index value represents the number of predictions for historical dam deformation. Indicates the first Actual data from the prediction of historical dam deformation; Indicates the first Predicted data from the prediction of the deformation of the dam body in the previous historical period; Correction unit, used for: Read the real-time predicted value of the current dam deformation prediction, and correct the real-time predicted value based on the average error of the dam deformation prediction. ； in, This indicates the correction value used to adjust the real-time forecast. This represents the real-time predicted value for the current dam deformation prediction. Update the real-time prediction value of the current dam deformation prediction based on the correction results.

Images