Dam risk monitoring system

Abstract

The invention discloses a dam risk monitoring system, and the system comprises an external strength monitoring device which is disposed on the surface of a dam, and carries out the monitoring of the structural strength of the dam through a vibration monitoring mechanism; the internal monitoring device is arranged in the dam and is used for monitoring the internal structure of the dam; the water and soil safety monitoring device is arranged in a water and soil structure at the joint of the dam, and judges the water and soil loss state around the dam through water quality monitoring, water wave impact strength, wave sound strength and the like; the data fusion processing unit is used for fusing monitoring data of the external strength monitoring device, the internal monitoring device and the water and soil safety monitoring device for comprehensive judgment; and the monitoring and early warning unit is used for monitoring the comprehensive judgment result of the data fusion processing unit. According to the dam risk monitoring system provided by the invention, the external strength monitoring device, the internal monitoring device and the water and soil safety monitoring device are integrated, so that the omnibearing monitoring of the dam risk is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of safety monitoring and early warning of water conservancy projects, and particularly relates to a dam risk monitoring system. Background Art

[0002] As an important water conservancy infrastructure, dams play a key role in flood control, power generation, irrigation, etc. However, the safe operation of dams faces many challenges, such as natural disasters, structural aging caused by long-term operation, and soil and water loss. Traditional monitoring methods mainly rely on manual inspections and a small number of automated monitoring devices, and these methods have the following limitations:

[0003] Single monitoring means: Traditional monitoring mainly focuses on the external structure or internal stress state of the dam, lacking a comprehensive assessment of the overall risk of the dam. For example, only through external vibration monitoring or internal stress monitoring, the safety state of the dam in a complex environment cannot be fully reflected.

[0004] Insufficient data fusion: In existing monitoring systems, data from different monitoring devices are often processed independently, lacking an effective data fusion mechanism. This decentralized processing method is difficult to achieve a dynamic assessment of the overall risk of the dam.

[0005] Lack of dynamic adjustment ability: In actual operation, the risk state of the dam changes dynamically with time and environment, but existing systems are difficult to dynamically adjust monitoring and early warning strategies according to real-time data.

[0006] Therefore, developing a system that can comprehensively monitor the risk of dams, dynamically fuse multi-source data, and adjust monitoring and early warning strategies according to real-time data is of great significance for ensuring the safe operation of dams. Summary of the Invention

[0007] The present invention provides a dam risk monitoring system to solve the above-mentioned technical problems, and specifically adopts the following technical solutions:

[0008] A dam risk monitoring system includes: an external strength monitoring device, an internal monitoring device, a water and soil safety monitoring device, a data fusion processing unit, and a monitoring and early warning unit;

[0009] The external strength monitoring device is arranged on the surface of the dam, and monitors the structural strength of the dam through a vibration monitoring mechanism;

[0010] The internal monitoring device is arranged inside the dam to monitor the internal structure of the dam;

[0011] The water and soil safety monitoring device is arranged in the water and soil structure at the connection of the dam, and judges the state of soil and water loss around the dam through water quality monitoring, water wave impact intensity, wave sound intensity, etc.;

[0012] The data fusion processing unit is used to fuse the monitoring data of the external intensity monitoring device, the internal monitoring device and the water and soil safety monitoring device for comprehensive judgment;

[0013] The monitoring and early warning unit executes a complete monitoring and early warning process according to the comprehensive judgment result of the data fusion processing unit. The monitoring and early warning process includes real-time monitoring of dam risks, risk level assessment, hierarchical sending of early warning signals, and activation of emergency response measures.

[0014] Further, the external intensity monitoring device includes a plurality of vibration sensors, which are evenly distributed on the outer surface of the dam and are used to monitor the vibration signals outside the dam in real time. The vibration signals include vibration frequency, vibration amplitude and vibration duration. By analyzing the vibration signals, the strength state of the external structure of the dam is evaluated;

[0015] The internal monitoring device includes a stress sensor and a strain sensor, which are respectively arranged at key stress-bearing parts inside the dam and are used to monitor the stress and strain conditions inside the dam in real time. The stress and strain data are used to evaluate the stability of the internal structure of the dam;

[0016] The water and soil safety monitoring device includes a water quality sensor, a water wave sensor and a wave sound sensor. The water quality sensor is used to monitor the water quality parameters of the water body around the dam, including pH value, sediment content, dissolved oxygen, etc.; the water wave sensor is used to monitor the impact intensity and frequency of water waves; the wave sound sensor is used to monitor the wave sound intensity of water waves. By comprehensively analyzing the water quality parameters, water wave impact intensity and wave sound intensity, the water and soil loss situation around the dam and the erosion degree of the water body on the dam are judged.

[0017] Further, the data fusion processing unit uses the following formula to fuse the monitoring data:

[0018] F = w1 × F 外 + w2 × F 内 + w3 × F 水土

[0019] where F is the comprehensive risk assessment value, F 外 is the risk assessment value of the external intensity monitoring device, F 内 is the risk assessment value of the internal monitoring device, F 水土 is the risk assessment value of the water and soil safety monitoring device, and w1, w2, and w3 are the weight coefficients of the external intensity monitoring device, the internal monitoring device and the water and soil safety monitoring device respectively. The weight coefficients are set according to the influence degree of each monitoring device on the dam risk.

[0020] Further, the risk assessment value F外 , F 内 , F 水土 are calculated respectively by the following formulas:

[0021] F 外 = a1×f 频率 + a2×f 幅度 + a3×f 时间

[0022] F 内 = b1×s 应力 + b2×s 应变

[0023] F 水土 = c1×q 水质 + c2×q 水波 + c3×q 波声

[0024] where f 频率 , f 幅度 , f 时间 are the evaluation factors of the external strength monitoring device; s 应力 , s 应变 are the evaluation factors of the internal monitoring device; q 水质 , q 水波 , q 波声 are the evaluation factors of the soil and water safety monitoring device; the calculation formulas of the evaluation factors are:

[0025]

[0026]

[0027] where k 频率 , k 幅度 , k 时间 , k 应力 , k 应变 , k 水质 , k 水波 , k 波声 are dynamic adjustment factors, which are used to dynamically adjust the weights of each evaluation factor according to historical data and real-time monitoring data to more accurately reflect the actual risk status of the dam.

[0028] Furthermore, the dynamic adjustment factor k 动态 is calculated according to the following formula:

[0029] k 动态 = α×k 历史 + β×k 实时

[0030] where k 历史 is the risk factor based on historical data, k 实时It is a risk factor based on real-time monitoring data, where α and β are adjustment coefficients satisfying α + β = 1 and 0 ≤ α, β ≤ 1; the historical data includes the monitoring data and risk assessment results over a past period of time, and the real-time monitoring data includes the monitoring data within the current monitoring period.

[0031] Furthermore, the system also includes a data storage unit and a data transmission unit. The data storage unit is used to store the monitoring data and the comprehensive risk assessment value, and the data transmission unit is used to transmit the monitoring data and the comprehensive risk assessment value to the monitoring and warning unit. The data transmission unit combines wireless communication and wired communication to ensure the stability and reliability of data transmission; the data storage unit is also used to store the historical monitoring data and risk assessment results, and the data fusion processing unit dynamically adjusts the risk assessment factors of each monitoring device according to the historical data and real-time monitoring data.

[0032] Furthermore, the data storage unit also includes a data analysis module. The data analysis module is used to analyze the stored historical monitoring data, extract characteristic parameters for dynamically adjusting the risk assessment factors; the data analysis module uses machine learning algorithms to train the historical data to generate a risk prediction model, and the risk prediction model is used to predict the dam risk status in the future for a period of time.

[0033] Furthermore, the weight coefficients w1, w2, w3 can be dynamically adjusted according to the real-time monitoring data and historical data, and the dynamic adjustment formula is as follows:

[0034]

[0035] where, w i (t) is the weight coefficient of the i-th monitoring device at time t, w i (t - 1) is the weight coefficient at the previous moment, γ is the adjustment factor, ΔF i (t) is the change amount of the risk assessment value of the i-th monitoring device at time t, and F i (t) is the risk assessment value of the i-th monitoring device at time t.

[0036] Furthermore, the dynamic adjustment mechanism optimizes the weight adjustment strategy by introducing uncertainty estimation, and the specific formula is:

[0037]

[0038] where, σ i (t) is the uncertainty estimation value of the i-th monitoring device at time t, which is used to reflect the quality and reliability of the data.

[0039] Furthermore, the monitoring and warning process of the monitoring and warning unit includes the following steps:

[0040] Receive the comprehensive risk assessment value F of the real-time data fusion processing unit in real time;

[0041] Judge the comprehensive risk assessment value F according to the preset risk thresholds. If F is greater than or equal to the first-level risk threshold, initiate the first-level early warning. If F is greater than or equal to the second-level risk threshold, initiate the second-level early warning. If F is greater than or equal to the third-level risk threshold, initiate the third-level early warning;

[0042] Send early warning signals to relevant personnel through different communication methods according to the early warning levels. The first-level early warning is sent via text message and email. The second-level early warning is sent via text message, email, and voice call. The third-level early warning is sent via text message, email, voice call, and emergency broadcast;

[0043] Initiate corresponding emergency response measures according to the early warning levels. During the first-level early warning, conduct on-site inspections and encrypted monitoring of monitoring equipment. During the second-level early warning, prepare for on-site emergency rescue and personnel evacuation. During the third-level early warning, initiate the emergency plan and organize personnel evacuation and emergency rescue.

[0044] The beneficial effect of the present invention lies in the provided dam risk monitoring system. By integrating external strength monitoring devices, internal monitoring devices, and water and soil safety monitoring devices, it realizes the all-round monitoring of dam risks. At the same time, the system comprehensively analyzes multi-source monitoring data through the data fusion processing unit, and introduces a dynamic adjustment mechanism and uncertainty estimation, significantly improving the accuracy and reliability of dam risk assessment.

[0045] The beneficial effect of the present invention also lies in the provided dam risk monitoring system. By dynamically adjusting the weight coefficients, the system can optimize the risk assessment model in real time according to the changes in real-time monitoring data and historical data. This dynamic adjustment mechanism enables the system to more flexibly adapt to the changes in the dam operation state and improve the accuracy and reliability of risk assessment.

[0046] The beneficial effect of the present invention also lies in the provided dam risk monitoring system. By introducing uncertainty estimation, the system can quantify the uncertainty and reliability of monitoring data. In this way, the system can better handle data noise and outliers during the risk assessment process, reduce misjudgments, and further improve the scientificity and reliability of risk assessment. Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 It is a schematic diagram of a dam risk monitoring system of the present invention. Specific implementation manner

[0049] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation of the present application.

[0050] As Figure 1 shown, a dam risk monitoring system of the present application includes: an external strength monitoring device, an internal monitoring device, a water and soil safety monitoring device, a data fusion processing unit, and a monitoring and warning unit.

[0051] The external strength monitoring device monitors the strength of the dam structure through a vibration monitoring mechanism arranged outside the dam. Specifically, the device includes a plurality of vibration sensors, which are evenly distributed on the outer surface of the dam and can monitor the vibration signals outside the dam in real time. The vibration signals mainly include vibration frequency, vibration amplitude, and vibration duration. By analyzing these vibration signals, the strength state of the external structure of the dam can be evaluated. For example, when the vibration frequency is too high, the vibration amplitude is too large, or the vibration duration is too long, it may indicate that the external structure of the dam is subjected to a large impact and there are potential safety hazards. In order to more accurately evaluate the external structure strength, the system uses a specific algorithm to process the vibration signals. First, the collected vibration signals are filtered to remove noise interference, and then the time-domain signals are converted into frequency-domain signals through Fourier transform for more intuitive analysis of the vibration frequency components. Next, according to the magnitudes of the vibration frequency, vibration amplitude, and vibration duration, the corresponding evaluation factors are calculated respectively. The calculation formula of the evaluation factor is as follows:

[0052]

[0053] where f 实测 , A 实测 , T 实测 are the measured vibration frequency, vibration amplitude, and vibration duration respectively, and f 阈值 , A 阈值 , T 阈值 are the thresholds of the preset vibration frequency, vibration amplitude, and vibration duration respectively. When the measured value exceeds the threshold, the evaluation factor is greater than 1, indicating that there may be risks in the structural strength corresponding to this parameter; on the contrary, when the evaluation factor is less than 1, it indicates that the structural strength is relatively safe. k 频率 , k 幅度 , k 时间is the corresponding dynamic adjustment factor, which is used to dynamically adjust the weights of each evaluation factor according to historical data and real-time monitoring data, so as to more accurately reflect the actual risk status of the dam.

[0054] Finally, according to the magnitudes of the evaluation factors, calculate the risk assessment value F of the external strength monitoring device 外 , and the calculation formula is as follows:

[0055] F 外 = a1×f 频率 + a2×f 幅度 + a3×f 时间

[0056] Among them, a1, a2, and a3 are the weight coefficients of the vibration frequency, vibration amplitude, and vibration duration respectively. The setting of the weight coefficients is based on the influence degree of each parameter on the external structure strength of the dam. For example, the influence of the vibration amplitude on the structure strength may be greater than that of the vibration frequency, so a larger weight coefficient can be assigned to the vibration amplitude. Through the above algorithm, the strength state of the dam's external structure can be scientifically and reasonably evaluated, providing an important basis for subsequent comprehensive risk judgment.

[0057] The internal monitoring device is also crucial for the safe operation of the dam. This device is set inside the dam and includes stress sensors and strain sensors. The stress sensors and strain sensors are respectively installed at the key stress-bearing parts inside the dam to monitor the stress and strain conditions inside the dam in real time. Stress and strain are important indicators to measure the internal structure stability of the dam. When the stress is too large or the strain is abnormal, it may cause problems such as cracks and deformations in the internal structure of the dam, thereby affecting the overall stability of the dam. In order to accurately evaluate the internal structure strength of the dam body, this system uses a specific algorithm to process the collected stress and strain data. First, perform filtering processing on the stress and strain data to remove noise interference, and then calculate the corresponding evaluation factors according to the magnitudes of the stress and strain. The calculation formula of the evaluation factor is as follows:

[0058]

[0059] Among them, σ 实测 , ε 实测 are the measured stress and strain respectively, and σ 阈值 , ε 阈值 are the preset thresholds of stress and strain respectively. When the measured value exceeds the threshold, the evaluation factor is greater than 1, indicating that there may be risks in the internal structure strength of the dam body; on the contrary, when the evaluation factor is less than 1, it indicates that the structure strength is relatively safe. k 应力 , k 应变 are the corresponding dynamic adjustment factors. Finally, according to the magnitudes of the evaluation factors, calculate the risk assessment value F 内 , and the calculation formula is as follows:

[0060] F 内 = b1 × s 应力 + b2 × s 应变

[0061] Wherein, b1 and b2 are the weight coefficients of stress and strain respectively. The setting of the weight coefficients is based on the influence degree of stress and strain on the strength of the internal structure of the dam. For example, the influence of stress on the structural strength may be greater than that of strain, so a larger weight coefficient can be assigned to stress. Through the above algorithm, the strength state of the internal structure of the dam can be scientifically and reasonably evaluated, providing an important basis for subsequent comprehensive risk judgment.

[0062] The water and soil safety monitoring device is mainly used to monitor the water and soil environment around the dam to judge the situation of soil erosion and the erosion degree of the water body on the dam. The device is arranged in the water and soil structure at the connection between the dam and the soil foundation, and includes a water quality sensor, a water wave sensor and a wave sound sensor. The water quality sensor is used to monitor the water quality parameters of the water body around the dam, such as pH value, sediment content, dissolved oxygen, etc. The water wave sensor is used to monitor the impact intensity and frequency of water waves, and the wave sound sensor is used to monitor the wave sound intensity of water waves. These parameters can reflect the erosion effect of the water body on the dam and the situation of soil erosion. For example, when the water quality parameters are abnormal, the water wave impact intensity is too large or the wave sound intensity is abnormal, it may indicate that the erosion effect of the water body on the dam is enhanced or the soil erosion is aggravated, thus affecting the safe operation of the dam. In order to accurately evaluate the water and soil safety state, the system uses a specific algorithm to process the collected water quality parameter, water wave impact intensity and wave sound intensity data. First, filter the parameter data to remove noise interference, and then calculate the corresponding evaluation factors according to the magnitudes of the parameters. The calculation formula of the evaluation factor is as follows:

[0063]

[0064] Wherein, Q 实测 、W 实测 、S 实测 are the measured water quality parameter, water wave impact intensity and wave sound intensity respectively, and Q 阈值 、W 阈值 、S 阈值 are the thresholds of the preset water quality parameter, water wave impact intensity and wave sound intensity respectively. When the measured value exceeds the threshold, the evaluation factor is greater than 1, indicating that there may be risks in the water and soil safety state; on the contrary, when the evaluation factor is less than 1, it indicates that the water and soil safety state is relatively safe. k 水质 、k 水波 、k 波声 are the corresponding dynamic adjustment factors. Finally, according to the magnitude of the evaluation factor, calculate the risk assessment value F_water and soil of the water and soil safety monitoring device. The calculation formula is as follows:

[0065] F 水土 = c1×q 水质 + c2×q 水波 + c3×q 波声

[0066] Among them, c1, c2, and c3 are the weight coefficients of water quality parameters, water wave impact intensity, and wave sound intensity respectively. The setting of the weight coefficients is based on the influence degree of each parameter on the water and soil safety state. For example, the influence of the water wave impact intensity on the water and soil safety state may be greater than that of the water quality parameters, so a larger weight coefficient can be assigned to the water wave impact intensity. Through the above algorithm, the water and soil safety state can be scientifically and reasonably evaluated, providing an important basis for subsequent comprehensive risk judgment.

[0067] It can be seen that in the implementation manner of this application, in order to further improve the accuracy of risk assessment, this system introduces a dynamic adjustment factor k_dynamic, which is used to dynamically adjust the weights of each evaluation factor according to historical data and real-time monitoring data. The calculation formula of the dynamic adjustment factor k_dynamic is as follows:

[0068] k 动态 = α×k 历史 + β×k 实时

[0069] Among them, k 历史 is the risk factor based on historical data, k 实时 is the risk factor based on real-time monitoring data, α and β are adjustment coefficients, satisfying α + β = 1, and 0 ≤ α, β ≤ 1. Historical data includes monitoring data and risk assessment results in the past period of time, and real-time monitoring data includes monitoring data in the current monitoring cycle. Through the dynamic adjustment factor, the weights of risk assessment factors can be adjusted in real time according to the actual operation state of the dam and the changes in historical data, so as to more accurately reflect the actual risk state of the dam. Here, k 动态 specifically refers to the aforementioned k 频率 , k 幅度 , k 时间 , k 应力 , k 应变 , k 水质 , k 水波 , k 波声 .

[0070] The data fusion processing unit is the core part of this system, and its function is to fuse the monitoring data of the external intensity monitoring device, internal monitoring device, and water and soil safety monitoring device to achieve a comprehensive judgment of the dam risk. The data fusion processing unit uses the following formula to fuse the monitoring data:

[0071] F = w1×F 外 + w2×F 内 + w3×F水土

[0072] Among them, F is the comprehensive risk assessment value, F 外 、F 内 、F 水土 are the risk assessment values of the external strength monitoring device, the internal monitoring device, and the water and soil safety monitoring device respectively, and w1, w2, and w3 are the weight coefficients of the external strength monitoring device, the internal monitoring device, and the water and soil safety monitoring device respectively. The setting of the weight coefficients is based on the influence degree of each monitoring device on the dam risk. For example, the influence of the internal monitoring device on the dam risk may be greater than that of the external strength monitoring device, so a larger weight coefficient can be assigned to the internal monitoring device. Through the above formula, the risk assessment values of the three monitoring devices are weighted and summed to obtain the comprehensive risk assessment value F. The comprehensive risk assessment value F can comprehensively reflect the overall risk status of the dam and provide an accurate judgment basis for the monitoring and early warning unit.

[0073] As a preferred implementation manner, in the dam risk monitoring system, the data fusion processing unit optimizes the accuracy of risk assessment by dynamically adjusting the weight coefficients. Specifically, the weight coefficients w1, w2, and w3 correspond to the external strength monitoring device, the internal monitoring device, and the water and soil safety monitoring device respectively. These weight coefficients can be dynamically adjusted according to the real-time monitoring data and historical data to reflect the contribution degree of each monitoring device to the dam risk at different time points.

[0074] The dynamic adjustment formula is as follows:

[0075]

[0076] Among them, w i (t) is the weight coefficient of the i-th monitoring device at time t, w i (t - 1) is the weight coefficient at the previous moment, γ is the adjustment factor, ΔF i (t) is the change amount of the risk assessment value of the i-th monitoring device at time t, and F i (t) is the risk assessment value of the i-th monitoring device at time t.

[0077] Specifically, at the start of the system, the initial weight coefficients w1, w2, and w3 are assigned according to the initial importance of each monitoring device. For example, assume that the initial weight coefficients are w1 = 0.3, w2 = 0.4, and w3 = 0.3, indicating that the internal monitoring device has the greatest contribution to risk assessment in the initial state.

[0078] In each monitoring cycle, calculate the risk assessment value F i (t) of each monitoring device, and calculate its change amount ΔF i(t). For example, if the risk assessment value of the external intensity monitoring device in the current period is F 外 (t) = 0.7 and that in the previous period is F 外 (t - 1) = 0.6, then ΔF 外 (t) = 0.1.

[0079] According to the above formula, combined with the adjustment factor γ (for example, γ = 0.1), the weight coefficient is dynamically adjusted. For example, for the external intensity monitoring device: w 外 (t) = w 外 (t - 1) × (1 + 0.1 × 0.7^0.1) ≈ 0.3 × 1.014 ≈ 0.304.

[0080] To ensure that the sum of the weight coefficients is 1, the adjusted weight coefficients are normalized:

[0081]

[0082] Through the above dynamic adjustment mechanism, the system can optimize the weight allocation in real time according to the changes in the monitoring data, so as to more accurately reflect the contribution of each monitoring device to the dam risk.

[0083] To further optimize the weight adjustment strategy, the system introduces uncertainty estimation. Uncertainty estimation is used to measure the reliability and data quality of the risk assessment value of each monitoring device. By introducing uncertainty estimation, the system can adjust the weight coefficient more flexibly and reduce misjudgments caused by data noise or outliers.

[0084] The formula for uncertainty estimation is as follows:

[0085]

[0086] Among them, σ i (t) is the uncertainty estimation value of the i-th monitoring device at time t, which is used to reflect the data quality and reliability.

[0087] The uncertainty estimation σ i (t) can be calculated by various methods, such as uncertainty interval estimation based on time series. For example, the EnbPI (Ensemble Bootstrap Prediction Interval) method is used to estimate the uncertainty of the risk assessment value of each monitoring device. This method calculates the confidence interval of the risk assessment value by simulating the data distribution, so as to obtain the uncertainty estimation value.

[0088] Combined with the uncertainty estimation value, the weight coefficient is dynamically adjusted. For example, if the uncertainty estimation value of the external intensity monitoring device is σ 外 (t) = 0.2, then its weight coefficient is adjusted to:

[0089]

[0090] Similarly, to ensure that the sum of the weight coefficients is 1, the adjusted weight coefficients are normalized.

[0091] By introducing uncertainty estimation, the system can more accurately evaluate the risk contribution of each monitoring device while reducing misjudgments caused by data noise or outliers.

[0092] The core of uncertainty estimation is to quantify the uncertainty and reliability of data. In the dam risk monitoring system, uncertainty may stem from various factors, such as measurement errors of sensors, noise in data transmission, and the impact of environmental changes on monitoring data. By introducing uncertainty estimation, the system can more flexibly adjust the weight coefficients, thereby improving the accuracy and reliability of risk assessment.

[0093] The calculation methods of uncertainty estimation usually rely on statistical and machine learning techniques. For example, the EnbPI method calculates the confidence interval of the risk assessment value by simulating the data distribution. The core idea of this method is to estimate the distribution characteristics of the data through multiple resamplings and model fittings, so as to obtain the uncertainty estimation value. Specifically, the EnbPI method includes the following steps:

[0094] Data decomposition: Use the Seasonal-Trend Decomposition (STL) method to decompose the monitoring data into trend terms, seasonal terms, and residual terms.

[0095] Outlier detection: Use the Isolation Forest (iForest) algorithm to detect outliers in the residual terms.

[0096] The monitoring and warning unit executes a complete monitoring and warning process based on the comprehensive risk assessment value F of the data fusion processing unit. This process includes real-time monitoring of the dam risk, risk level assessment, hierarchical sending of warning signals, and initiation of emergency response measures. The specific steps are as follows:

[0097] (1) Receive the comprehensive risk assessment value F of the data fusion processing unit in real time. The monitoring and warning unit is connected to the data fusion processing unit through the data transmission unit and can obtain the comprehensive risk assessment value F in real time to promptly grasp the risk status of the dam.

[0098] (2) Judge the comprehensive risk assessment value F according to the preset risk thresholds. The preset risk thresholds are divided into the first-level risk threshold, the second-level risk threshold, and the third-level risk threshold. When the comprehensive risk assessment value F is greater than or equal to the first-level risk threshold, initiate a first-level early warning; when the comprehensive risk assessment value F is greater than or equal to the second-level risk threshold, initiate a second-level early warning; when the comprehensive risk assessment value F is greater than or equal to the third-level risk threshold, initiate a third-level early warning. The first-level early warning indicates that there is a slight risk to the dam, the second-level early warning indicates that there is a medium risk to the dam, and the third-level early warning indicates that there is a serious risk to the dam, which may endanger the safety of the dam.

[0099] (3) Send early warning signals to relevant personnel through different communication methods according to the early warning level. The first-level early warning is sent via text message and email, notifying relevant personnel to pay attention to the dam status and conduct a preliminary inspection; the second-level early warning is sent via text message, email, and voice call, notifying relevant personnel to immediately take measures, such as increasing the monitoring frequency and preparing emergency supplies; the third-level early warning is sent via text message, email, voice call, and emergency broadcast, notifying relevant personnel to immediately initiate the emergency plan and organize personnel evacuation and emergency rescue.

[0100] (4) Initiate corresponding emergency response measures according to the early warning level. During the first-level early warning, conduct on-site inspections and encrypted monitoring of monitoring equipment to promptly detect potential problems and take measures; during the second-level early warning, prepare for on-site emergency rescue and personnel evacuation to ensure a rapid response in case of increased risk; during the third-level early warning, initiate the emergency plan, organize personnel evacuation and emergency rescue to minimize losses to the greatest extent.

[0101] The dam risk monitoring system of this application also includes a data storage unit and a data transmission unit. The data storage unit is used to store monitoring data and the comprehensive risk assessment value. The data transmission unit is used to transmit the monitoring data and the comprehensive risk assessment value to the monitoring and early warning unit. The data transmission unit combines wireless communication and wired communication to ensure the stability and reliability of data transmission; the data storage unit is also used to store historical monitoring data and risk assessment results. The data fusion processing unit dynamically adjusts the risk assessment factors of each monitoring device according to historical data and real-time monitoring data. The data storage unit also includes a data analysis module. The data analysis module is used to analyze the stored historical monitoring data, extract characteristic parameters, and be used to dynamically adjust the risk assessment factors; the data analysis module uses machine learning algorithms to train the historical data to generate a risk prediction model. The risk prediction model is used to predict the dam risk status in a future period of time.

[0102] Specifically, the data storage unit and the data transmission unit ensure the integrity of the monitoring data and the reliability of the transmission. The data storage unit not only stores real-time monitoring data and comprehensive risk assessment values, but also stores historical monitoring data and risk assessment results, providing data support for dynamically adjusting risk assessment factors. The data storage unit adopts a distributed storage architecture, combining local storage and cloud storage to ensure data security and scalability. The data transmission unit uses a combination of wireless communication and wired communication to ensure the stability and reliability of data transmission. Wireless communication is applicable to data transmission between on-site devices and the monitoring center, using low-power wide-area network (LPWAN) technologies such as LoRa or NB-IoT to meet the characteristics of wide distribution and complex environment of dam monitoring devices. Wired communication is used for data transmission between the monitoring center and the superior management department, using fiber optic communication technology to ensure high-speed and stable data transmission. In addition, the data transmission unit also supports data encryption and authentication mechanisms to prevent data leakage and unauthorized access.

[0103] The implementation of the dynamic adjustment mechanism relies on the historical data and real-time monitoring data in the data storage unit. The system analyzes the historical data through the data analysis module to extract characteristic parameters for calculating k_history. At the same time, the system calculates k_real based on the data within the current monitoring period. The data analysis module uses machine learning algorithms to train the historical data to generate a risk prediction model, which can predict the dam risk status in the future for a period of time based on the current data. Through the dynamic adjustment mechanism, the system can dynamically adjust the weights of risk assessment factors according to the actual operation status of the dam and the changes in historical data, so as to more accurately reflect the actual risk status of the dam.

[0104] To improve the operability and management efficiency of the system, the dam risk monitoring system is also equipped with a remote monitoring module. The remote monitoring module is connected to the monitoring and warning unit through the Internet and supports the access of multiple terminal devices, including mobile devices, desktop computers, and display terminals in the monitoring center. Users can view the monitoring data, risk assessment results, and warning information of the dam in real time through the remote monitoring module, and can also remotely control the operating status of the monitoring devices, such as adjusting the monitoring frequency, starting or stopping the devices, etc.

[0105] The remote monitoring module has a user permission management function, providing different operation interfaces and function permissions according to the user's permission level. For example, ordinary users may only be able to view monitoring data and warning information, while administrator users can perform device configuration and system management operations. In addition, the remote monitoring module ensures the security of data transmission through an encrypted communication protocol to prevent data leakage and unauthorized access. Through the remote monitoring module, users can grasp the safety status of the dam at any time, respond to risk warnings in a timely manner, and improve the efficiency and reliability of dam safety management.

[0106] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the above embodiments do not limit the present invention in any form. Any technical solutions obtained by means of equivalent replacement or equivalent transformation fall within the protection scope of the present invention.

Claims

1. A dam risk monitoring system, characterized in that: include: External strength monitoring device, internal monitoring device, soil and water safety monitoring device, data fusion processing unit and monitoring and early warning unit; The external strength monitoring device is arranged on the surface of the dam and monitors the structural strength of the dam through a vibration monitoring mechanism; The internal monitoring device is arranged inside the dam to monitor the internal structure of the dam; The water and soil safety monitoring device is installed in the water and soil structure at the connection of the dam, and determines the state of water and soil loss around the dam by monitoring water quality, water wave impact intensity, wave sound intensity, etc.; The data fusion processing unit is used to fuse the monitoring data of the external strength monitoring device, the internal monitoring device and the soil and water safety monitoring device for comprehensive judgment; The monitoring and early warning unit executes a complete monitoring and early warning process according to the comprehensive judgment result of the data fusion processing unit. The monitoring and early warning process includes real-time monitoring of dam risks, risk level assessment, graded sending of early warning signals and initiation of emergency response measures.

2. The dam risk monitoring system according to claim 1, characterized in that: The external strength monitoring device includes a plurality of vibration sensors, which are evenly distributed on the external surface of the dam and are used to monitor the vibration signals of the external dam in real time. The vibration signals include vibration frequency, vibration amplitude and vibration duration. By analyzing the vibration signals, the strength state of the external structure of the dam is evaluated. The internal monitoring device includes a stress sensor and a strain sensor, which are respectively arranged at key stress-bearing positions inside the dam to monitor the stress and strain conditions inside the dam in real time. The stress and strain data are used to evaluate the stability of the internal structure of the dam; The soil and water safety monitoring device includes a water quality sensor, a water wave sensor and a wave-acoustic sensor. The water quality sensor is used to monitor the water quality parameters of the water body around the dam, including pH, sand content, dissolved oxygen, etc.; the water wave sensor is used to monitor the impact intensity and frequency of water waves; the wave-acoustic sensor is used to monitor the wave-acoustic intensity of water waves. Through a comprehensive analysis of the water quality parameters, water wave impact intensity and wave-acoustic intensity, the soil and water loss situation around the dam and the degree of erosion of the dam by the water body can be judged.

3. The dam risk monitoring system according to claim 2, characterized in that: The data fusion processing unit uses the following formula to perform fusion processing on the monitoring data: F=w1×F 外 +w2×F 内 +w3×F 水土 Among them, F is the comprehensive risk assessment value, F 外 is the risk assessment value of the external strength monitoring device, F 内 is the risk assessment value of the internal monitoring device, F 水土 is the risk assessment value of the soil and water safety monitoring device, w1, w2, and w3 are the weight coefficients of the external strength monitoring device, the internal monitoring device, and the soil and water safety monitoring device, respectively. The weight coefficients are set according to the degree of influence of each monitoring device on the dam risk.

4. The dam risk monitoring system according to claim 3, characterized in that: The risk assessment value F 外 、F 内 、F 水土 Calculated by the following formulas: F 外 =a1×f 频率 +a2×f 幅度 +a3×f 时间 F 内 =b1×s 应力 +b2×s 应变 F 水土 =c1×q 水质 +c2×q 水波 +c3×q 波声 Among them, f 频率 、f 幅度 、f 时间 is the evaluation factor of the external strength monitoring device; 应力 、s 应变 is the evaluation factor of the internal monitoring device; q 水质 ,q 水波 ,q 波声 is the evaluation factor of the soil and water safety monitoring device; the calculation formula of the evaluation factor is: Among them, k 频率 , k 幅度 , k 时间 , k 应力 , k 应变 , k 水质 , k 水波 , k 波声 It is a dynamic adjustment factor, which is used to dynamically adjust the weight of each assessment factor according to historical data and real-time monitoring data to more accurately reflect the actual risk status of the dam.

5. The dam risk monitoring system according to claim 4, characterized in that: The dynamic adjustment factor k 动态 Calculated according to the following formula: k 动态 =α×k 历史 +β×k 实时 Among them, k 历史 is the risk factor based on historical data, k 实时 is a risk factor based on real-time monitoring data, α and β are adjustment coefficients, satisfying α+β=1, and 0≤α, β≤1; the historical data includes monitoring data and risk assessment results in the past period of time, and the real-time monitoring data includes monitoring data in the current monitoring cycle.

6. The dam risk monitoring system according to claim 5, characterized in that: The system also includes a data storage unit and a data transmission unit. The data storage unit is used to store monitoring data and comprehensive risk assessment values. The data transmission unit is used to transmit the monitoring data and comprehensive risk assessment values ​​to the monitoring and early warning unit. The data transmission unit adopts a combination of wireless communication and wired communication to ensure the stability and reliability of data transmission. The data storage unit is also used to store historical monitoring data and risk assessment results. The data fusion processing unit dynamically adjusts the risk assessment factors of each monitoring device according to historical data and real-time monitoring data.

7. The dam risk monitoring system according to claim 6, characterized in that: The data storage unit also includes a data analysis module, which is used to analyze the stored historical monitoring data and extract characteristic parameters for dynamically adjusting the risk assessment factor; the data analysis module uses a machine learning algorithm to train the historical data to generate a risk prediction model, and the risk prediction model is used to predict the dam risk status in the future.

8. The dam risk monitoring system according to claim 3, characterized in that: The weight coefficients w1, w2, w3 can be dynamically adjusted according to real-time monitoring data and historical data, and the dynamic adjustment formula is as follows: Among them, w i (t) is the weight coefficient of the i-th monitoring device at time t, w i (t-1) is the weight coefficient of the previous moment, γ is the adjustment factor, ΔF i (t) is the change in the risk assessment value of the ith monitoring device at time t, F i (t) is the risk assessment value of the ith monitoring device at time t.

9. The dam risk monitoring system according to claim 8, characterized in that: The dynamic adjustment mechanism optimizes the weight adjustment strategy by introducing uncertainty estimation. The specific formula is: Among them, σ i (t) is the uncertainty estimate of the ith monitoring device at time t, which is used to reflect the quality and reliability of the data.

10. The dam risk monitoring system according to claim 3, characterized in that: The monitoring and early warning process of the monitoring and early warning unit includes the following steps: Receive the comprehensive risk assessment value F of the data fusion processing unit in real time; The comprehensive risk assessment value F is judged according to the preset risk threshold. If F is greater than or equal to the first-level risk threshold, the first-level warning is activated; if F is greater than or equal to the second-level risk threshold, the second-level warning is activated; if F is greater than or equal to the third-level risk threshold, the third-level warning is activated; According to the warning level, warning signals are sent to relevant personnel through different communication methods. Level 1 warnings are sent through SMS and emails, Level 2 warnings are sent through SMS, emails and voice calls, and Level 3 warnings are sent through SMS, emails, voice calls and emergency broadcasts. Initiate corresponding emergency response measures according to the warning level. During the first-level warning, conduct on-site inspections and encrypt monitoring with monitoring equipment. During the second-level warning, make on-site rescue preparations and personnel evacuation preparations. During the third-level warning, activate the emergency plan and organize personnel evacuation and emergency rescue.

Images