Water conservancy water level monitoring device and method

Abstract

The invention belongs to the technical field of water conservancy monitoring, and discloses a water conservancy water level monitoring device and method, and the method comprises the steps: a monitoring point arrangement module of a monitoring mechanism reasonably arranges the number and positions of monitoring points; the flow velocity monitoring module monitors the water velocity; the meteorological data acquisition module acquires meteorological data; the echo sounder emits sound waves, and the water depth is calculated according to the sound wave propagation time and the sound velocity in water; the pressure water level gauge, the laser water level gauge and the radar water level gauge monitor the water level of water conservancy. The echo data analysis module analyzes the echo data; the comprehensive analysis module comprehensively analyzes the water level; the predictive analysis module predicts a water level trend and potential risks. The water level of water conservancy is monitored through various water level gauges, cross validation and high precision are achieved, and the sediment deposition thickness is accurately calculated by analyzing echo data; the comprehensive analysis module comprehensively evaluates the water level; the prediction analysis module integrates various monitoring equipment data and meteorological data, and predicts the water level trend and potential risks.

Description

Technical Field

[0001] The present application relates to the field of water conservancy monitoring technology, and more specifically, to a water conservancy water level monitoring device and method. Background Art

[0002] Water level is a direct indicator of the water's condition. Its fluctuations are primarily caused by changes in the volume of water. When the water level rises above a certain threshold, disasters such as flooding and dam breaches can occur. This threshold serves as a safety line for the surface of rivers, lakes, oceans, reservoirs, and other bodies of water, often referred to as the water level warning line. Because the water level warning lines vary across rivers, lakes, oceans, and reservoirs, accurate and systematic water level monitoring is crucial for mitigating potential risks and taking effective measures to regulate water levels and ensure the safety of people living and working downstream.

[0003] The prior art document CN212567593U provides a water level monitoring device, comprising a measuring tube equipped with a float, a measuring unit for indicating the position of the float, a solar panel for powering the measuring unit, and an adjustment unit. The adjustment unit is configured to rotate the solar panel about its first hinged end. The adjustment unit is located on the side of the measuring tube and has a fixing member connected to the measuring tube. The fixing member is provided with a lifting member, the top of which is connected to the second hinged end of the solar panel. The utility model has a simple structure and is easy to use. It can easily adjust the tilt angle of the solar panel, maximizing the absorption of solar energy and converting it into electrical energy to ensure the normal operation of the device. Secondly, the float is mounted on a vertical track with a ball bearing, and an infrared ranging sensor is used for position measurement. This avoids measurement errors caused by the float getting stuck, greatly improves measurement accuracy, and provides accurate and effective real-time data for timely response to water level changes.

[0004] Although the above-mentioned existing technical solutions can achieve the relevant beneficial effects through the existing technical structure, they still have the following defects: 1. The sensors used in the existing water level monitoring devices have limited accuracy, making it difficult to accurately measure tiny water level changes. This cannot meet the needs of high-precision monitoring. 2. After long-term operation in harsh outdoor environments, the electronic components of the water level monitoring devices are prone to aging, resulting in inaccurate monitoring data. 3. Most existing devices simply collect and transmit data, with limited data analysis and processing capabilities. They cannot conduct accurate trend analysis and early warning based on water level changes in a timely manner, and cannot provide effective decision-making support for the safe operation of water conservancy projects.

[0005] In view of this, we propose a water level monitoring device and method. Summary of the Invention

[0006] 1. Technical problems to be solved

[0007] The purpose of this application is to provide a water conservancy water level monitoring device and method, which solves the technical problems raised in the above background technology, realizes water conservancy water level monitoring through multiple water level gauges, realizes cross-validation and high precision, and the pressure water level gauge, laser water level gauge and radar water level gauge monitor the water level from different principles respectively. Multiple devices can realize data cross-validation in parallel; ensure the continuity and accuracy of water level monitoring. The combination of multiple devices can adapt to the complex and changeable environmental conditions of water conservancy waters, and ensure that water level data can be accurately obtained under various circumstances; accurately monitor sediment deposition through the echo data analysis module, accurately calculate the sediment deposition thickness through the analysis of echo data, and timely grasp the evolution of the riverbed; comprehensively evaluate the water level through the comprehensive analysis module, and comprehensively analyze the monitoring results of multiple water level gauges, so as to more comprehensively and accurately evaluate the water level status; the prediction analysis module integrates data from multiple monitoring equipment and meteorological data to establish a water level prediction model, which can predict water level trends and potential risks.

[0008] 2. Technical solution

[0009] The technical solution of this application provides a water level monitoring device, comprising:

[0010] Poles: Multiple poles are deployed in the water conservancy area; the poles are made of high-strength stainless steel. A positioning plate is fixed at the lower end of the pole, and several anchor rods are detachably fixed to the positioning plate. The anchor rods and positioning plate secure the poles together.

[0011] Photovoltaic panels: A photovoltaic panel is fixed to the top of the pole; a photovoltaic energy storage system is installed beneath the panel. This system converts solar energy into electricity, using lithium batteries as the energy storage device. The photovoltaic energy storage system is equipped with an intelligent charge controller that monitors the panel's output power and the lithium battery's charge level in real time, automatically adjusting the charging process to avoid overcharging and over-discharging, ensuring stable system operation. The energy storage system also features a backup power supply port, allowing it to be connected to an external power source in exceptional circumstances, such as continuous rainy weather.

[0012] Pressure water level gauge: A pressure water level gauge is installed around the bottom of the photovoltaic panel; the protection level of the pressure water level gauge reaches IP68 and can work stably in an underwater environment for a long time.

[0013] Laser water level meter: A laser water level meter is fixed under the photovoltaic panel; it uses the principle of laser ranging to determine the water level by emitting a laser beam and measuring the time it takes for the laser to reflect back.

[0014] Radar water level meter: A radar water level meter is fixedly installed under the photovoltaic panel.

[0015] Echo sounder: An echo sounder is installed beneath the photovoltaic panels. It emits sound waves, which are reflected by the water bottom. The water depth is calculated based on the sound wave propagation time and the speed of sound in the water. Regularly measuring the water depth at the same location can reveal the thickness of sediment deposits.

[0016] A monitoring mechanism is fixed on the pole to monitor and analyze the water level and detect abnormal situations in a timely manner.

[0017] Furthermore, monitoring agencies include:

[0018] Data Collection Module: This module collects geological and hydraulic data on water resources. Geographic data includes topography, riverbed slope, and water area. Hydraulic data includes water level, flow rate, temperature, and quality. The collected data undergoes preliminary processing, including data cleaning, format conversion, and unit unification, to ensure accuracy and consistency.

[0019] Monitoring Point Layout Module: Rationally arranges the number and location of monitoring points based on the geological data of the water area and monitoring needs. Utilizing Geographic Information System (GIS) technology and data analysis algorithms, the layout of monitoring points is optimized, taking into account the water area's topography, flow characteristics, and monitoring objectives. Dynamically adjusts the layout of monitoring points based on actual monitoring conditions and data analysis results.

[0020] Flow rate monitoring module: includes a flow meter to monitor water flow rate.

[0021] Meteorological data acquisition module: A meteorological data acquisition module is set on one or several poles; meteorological data is acquired in real time; the meteorological instrument can acquire meteorological data in real time, including temperature, air pressure, wind speed, wind direction, rainfall, etc.

[0022] Echo Data Analysis Module: This module analyzes echo data. Sound waves are reflected from the water's bottom interface and the water depth is calculated based on the sound wave's propagation time and the speed of sound in the water. Regularly measuring water depth changes at the same location can determine sediment deposition thickness.

[0023] Comprehensive Analysis Module: This module combines the monitoring results of pressure, laser, and radar water level gauges to comprehensively analyze water levels. Using methods such as multivariate statistical analysis and time series analysis, this integrated data is deeply analyzed to uncover the inherent relationships and patterns of change within the data. Based on the analysis results, the current water level is assessed to determine whether it is within the normal range or whether there are any abnormal fluctuations.

[0024] Prediction and analysis module: Combines the monitoring results of pressure water level gauges, flow meters, laser water level gauges, echo sounders and radar water level gauges with meteorological data to establish a water level prediction model to predict water level trends and potential risks.

[0025] Alarm module: This includes an alarm that issues a prompt alert when an abnormality or potential risk is detected. Alarm thresholds for parameters such as water level and silt accumulation are set based on the characteristics and management requirements of the water conservancy area. Alarms are triggered when monitored data exceeds or falls below the set thresholds. The alarm module includes an audible and visual alarm and a text message alarm. When an abnormality or potential risk is detected, the audible and visual alarm emits a loud siren and flashes lights, alerting on-site personnel to take immediate action. The text message alarm sends the alarm information to the mobile phones of relevant managers, ensuring they are informed of the situation and can make decisions promptly.

[0026] Control center: network connected with data collection module, monitoring point layout module, meteorological data acquisition module, echo data analysis module, prediction analysis module and alarm module.

[0027] Furthermore, the echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the speed of sound in the water. The water depth changes at the same location are regularly measured to calculate the sediment deposition thickness. This includes the following steps:

[0028] 1. Data Measurement: Select an appropriate echo sounder model based on the depth range and accuracy requirements of the waters to be monitored. Power on the echo sounder and begin measuring. The instrument automatically calculates and displays the water depth at your current location based on the propagation time of the sound waves and the speed of sound in water. Record the measured water depth data in real time using a data acquisition system connected to the echo sounder (such as a computer or data logger). Also, record the measurement time, date, and corresponding geographic coordinates. This ensures the integrity and accuracy of the recorded data and prevents data loss or errors.

[0029] 2. Regular Measurement: Develop a detailed regular measurement plan based on monitoring needs. Determine the measurement cycle. During each regular measurement, repeat the water depth measurement at the same location according to the initial measurement steps. Ensure that the measurement parameters are consistent with the initial measurement to ensure data comparability.

[0030] 3. Data Comparison and Analysis: Compare the water depth data obtained from each regular measurement with the initial measurement data and the data from previous measurements. Calculate the difference in water depth between different periods. If the water depth becomes shallower, the difference is the thickness of sediment deposited during that period.

[0031] 4. Data processing: All measured water depth data and corresponding sediment thickness data are sorted, arranged in chronological order, and a data table is created. The data are numbered to facilitate subsequent query and analysis.

[0032] 5. Trend Analysis: Analyze the trend of sediment accumulation by plotting the changes in water depth and sediment thickness over time. Determine whether sediment accumulation is gradually increasing, stable, or showing other changes.

[0033] 6. Spatial Analysis: Perform spatial analysis on data from different measurement points. By drawing iso-deposition thickness maps, we can understand the distribution differences of sediment accumulation in different regions and identify areas with more severe and less severe sedimentation.

[0034] 7. Report Generation: Based on the data analysis results, a monitoring report is prepared. The report includes the monitoring objectives, an overview of the monitoring area, the instruments and measurement methods used, a summary of the measurement data, an analysis of sediment accumulation trends, spatial distribution characteristics, and relevant conclusions and recommendations. Based on the sediment accumulation situation, staff will arrange for desilting operations on the underwater sediment.

[0035] Furthermore, the comprehensive analysis module combines the water level monitoring results of the pressure water level gauge and the laser water level gauge with the monitoring results of the radar water level gauge to comprehensively analyze the water level; the module includes the following steps:

[0036] 1. Data Collection: Obtain water level monitoring data from the pressure water level gauge, record the water level value corresponding to each measurement moment, and collect relevant information such as the measurement time and location. Obtain water level measurement results from the laser water level gauge, also recording the measurement time and water level value. Collect monitoring data from the radar water level gauge.

[0037] 2. Data preprocessing: Preprocess the collected data, including data cleaning and data normalization.

[0038] 3. Data fusion: Align the data of pressure water level gauges, laser water level gauges, and radar water level gauges according to time to ensure that relevant data from different devices are available at each time point.

[0039] 4. Data analysis.

[0040] 4.1 Multivariate Statistical Analysis: Multivariate statistical analysis methods, such as principal component analysis (PCA), factor analysis, and cluster analysis, are used to reduce the dimensionality of the fused data and extract features, thereby exploring the inherent relationships and underlying structures within the data. Principal component analysis can identify the main factors influencing water level fluctuations, while cluster analysis can group similar water level data to better understand water level variation patterns.

[0041] 4.2. Time Series Analysis: Time series analysis methods, such as the Autoregressive Integrated Moving Average (ARIMA) model, seasonal decomposition, and wavelet analysis, are used to model and forecast water level data. Through time series analysis, long-term trends, seasonal changes, and cyclical fluctuations in water levels can be identified, and future changes in water levels can be predicted.

[0042] 5. Water Level Assessment: Based on historical water level data and relevant water conservancy standards, a normal range for water levels is set. This range can include upper and lower limits for the water level, as well as normal fluctuations over different time periods. To determine the water level status, compare the current water level data with the set normal range to determine whether the water level is within the normal range.

[0043] 6. Result output and early warning: The results of the comprehensive analysis are compiled into a report, including the current status of the water level, change trends, abnormal situation analysis, etc. If abnormal fluctuations in the water level are detected, the early warning mechanism will be triggered in a timely manner.

[0044] 7. Continuous Monitoring and Optimization: Continuously collect monitoring data from pressure water level gauges, laser water level gauges, and radar water level gauges, update the data warehouse, and provide richer information for subsequent analysis. Optimize and adjust the data analysis model based on actual conditions and new data.

[0045] Furthermore, the forecasting and analysis module combines the monitoring results of pressure water level gauges, flow meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to establish a water level forecasting model to predict water level trends and potential risks. The module includes the following steps:

[0046] 1. Data Collection and Integration: Continuously collect data from pressure water level gauges, flow meters, laser water level gauges, radar water level gauges, and echo sounders, recording key information such as the time of each measurement, water level height, and water flow velocity. Obtain local meteorological data, including rainfall, temperature, wind speed, and humidity, as these data significantly influence water level fluctuations. Align data from different sources chronologically to ensure a one-to-one correspondence between monitoring data and meteorological data at each point in time.

[0047] 2. Data preprocessing: Preprocess the collected data, including data cleaning and data normalization.

[0048] 3. Feature Engineering: Analyze the correlation between various monitoring and meteorological data and water level changes, and select features that have a significant impact on water level prediction. Statistical methods such as correlation analysis and variance analysis can be used to determine feature importance. Based on existing features, new features can be constructed to improve the model's predictive ability.

[0049] 4. Model Construction: A water level prediction model is constructed using neural network machine learning algorithms (such as multi-layer perceptrons and long short-term memory (LSTM) networks). Neural networks have powerful nonlinear fitting capabilities and are suitable for processing complex water level fluctuations. The preprocessed historical data is divided into training, validation, and test sets. The selected model is trained using the training set, and by continuously adjusting the model's parameters, the model learns the patterns and regularities in the data. During the training process, the validation set is used to evaluate the model's performance to avoid overfitting.

[0050] 5. Model Evaluation and Optimization: Use the test set to evaluate the trained model. Common evaluation metrics include mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Analyze the model's prediction accuracy at different time scales and water levels to identify any deficiencies. Based on the evaluation results, optimize the model. Model parameters can be adjusted, training data can be added, and feature engineering can be improved to improve the model's predictive performance.

[0051] 6. Water Level Trend Forecast: Using a trained and optimized model, current monitoring data and meteorological data are input to predict water level trends over the next period of time. Predictions include the magnitude of water level rise or fall, peak time, and more. You can set different forecast timeframes based on your needs, such as the next week.

[0052] 7. Potential Risk Assessment: Identify potential risk types, such as floods and droughts, and develop appropriate risk assessment criteria. Based on projected water level trends, combined with historical data and relevant water conservancy standards, assess the likelihood and impact of potential risks. Probabilistic analysis and scenario analysis can be used to conduct risk assessments.

[0053] 8. Response Measures: Develop appropriate response measures based on the risk assessment results. Develop a detailed emergency response plan that clearly defines the emergency response process and division of responsibilities for different risk levels. The emergency plan should include information on the emergency command structure, emergency rescue teams, and emergency material reserves.

[0054] 9. Output: Develop a detailed report containing water level forecasts, potential risk assessments, and recommended response measures. Present the report in charts, tables, and other formats to visually demonstrate the analysis. Submit the report to the water management department to support decision-making.

[0055] Furthermore, the monitoring point layout module reasonably arranges the number and location of monitoring points according to the geological data of the water area and monitoring needs; the module includes the following steps:

[0056] 1. Data Collection: Gather detailed geographic information for the target waters, including high-precision topographic data (e.g., Digital Elevation Model (DEM)). Obtain water flow characteristics such as velocity, flow rate, and direction through historical records from hydrological stations and past water flow monitoring research. Clarify the core objectives of monitoring.

[0057] 2. Initial monitoring point planning: Use professional geographic information system software (such as ArcGIS, QGIS, etc.) to build a work platform, import the acquired geographic data and water flow characteristic data into the system, and generate a visual water area map, including elements such as terrain, water system, and surrounding environment, to provide an intuitive basis for subsequent monitoring point planning. First, a preliminary uniform distribution of points is carried out throughout the water area according to a certain grid or distance interval, which serves as the basic framework for subsequent optimization. Prioritize the location of monitoring points in key locations in the water area. These areas have complex water flow conditions and often more drastic water level fluctuations, making them key monitoring areas. Based on clear monitoring objectives, points are distributed in relevant key areas. The initial distribution plan is generated on the GIS platform, and the locations of the initial monitoring points are generated by manual annotation or using the software's spatial analysis tools. Each monitoring point is numbered and its geographic coordinate information is recorded. Based on different monitoring needs, the type of equipment installed at each monitoring point is preliminarily planned.

[0058] 3. Optimized layout of monitoring points:

[0059] 3.1 Water Flow Simulation and Analysis: Utilizing hydrodynamic models and combining existing geographic and water flow data, numerical simulations are conducted on the water flow conditions in the target water area. The flow velocity and direction distribution under different water levels and flow conditions are simulated to identify areas with complex water flows and areas with significant water level fluctuations.

[0060] 3.2 Data Analysis: Spatial autocorrelation analysis, kriging interpolation, and other data analysis algorithms are used to analyze water flow simulation results and historical monitoring data. Spatial autocorrelation analysis can help determine the spatial correlation between monitoring points and understand which areas have similar or different monitoring data. Kriging interpolation can be used to predict water flow and water level characteristics in unmonitored areas, providing a basis for optimizing monitoring point placement.

[0061] 3.3、Optimization strategy formulation:

[0062] 3.3.1. Density adjustment: Based on simulation and analysis results, the density of monitoring points is increased in areas with complex water flows and large water level fluctuations.

[0063] 3.3.2. Point movement: For some monitoring points whose initial locations are unreasonable, they will be moved appropriately according to the water flow and terrain characteristics.

[0064] 3.3.3. Equipment Optimization: Based on the monitoring needs and characteristics of different areas, further optimize the equipment configuration of monitoring points. In areas where flow velocity fluctuates dramatically and high accuracy flow velocity data is required, high-precision acoustic Doppler flowmeters should be deployed. In areas where water levels fluctuate frequently and high accuracy is required, more accurate pressure water level gauges or laser water level gauges should be used.

[0065] 3.3.4. Determine the optimized monitoring point layout plan: On the GIS platform, adjust the initial monitoring points according to the optimization strategy to generate an optimized monitoring point layout plan. Detailed information such as the new location, geographic coordinates, and monitoring equipment of each monitoring point should be recorded. A detailed layout diagram and explanatory documentation should be prepared.

[0066] 4. Dynamic Adjustment of Monitoring Point Layout: Establish a real-time monitoring data transmission system, regularly analyze collected monitoring data, and utilize statistical analysis methods and time series analysis to assess the rationality of monitoring point layout. Set trigger conditions for dynamic adjustment. Once the dynamic adjustment mechanism is triggered, conduct on-site surveys of the relevant areas to verify the data and understand actual water flow, topographic changes, and factors that may affect monitoring. Develop specific adjustment plans based on the results of the on-site survey and data analysis.

[0067] The present invention provides a water level monitoring method, comprising the following steps:

[0068] S1. The monitoring point layout module of the monitoring agency shall reasonably layout the number and location of monitoring points (including current meters, pressure water level gauges, laser water level gauges, radar water level gauges and echo sounders) according to the geological data of the water area and monitoring needs.

[0069] S2. The flow rate monitoring module monitors the water flow rate; the meteorological data acquisition module obtains meteorological data in real time; the weather data includes temperature, air pressure, wind speed, wind direction, rainfall, etc.; the echo sounder uses the echo sounder to emit sound waves, which are reflected back when they encounter the bottom interface, and the water depth is calculated based on the sound wave propagation time and the sound speed in the water.

[0070] S3, pressure water level gauge, laser water level gauge and radar water level gauge monitor the water level of the water conservancy respectively.

[0071] S4. The echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the speed of sound in water. The water depth changes at the same location are regularly measured to calculate the sediment deposition thickness.

[0072] S5. The comprehensive analysis module combines the monitoring results of the pressure water level gauge, laser water level gauge and radar water level gauge to comprehensively analyze the water level.

[0073] S6. The prediction and analysis module combines the monitoring results of pressure water level gauges, flow meters, laser water level gauges, echo sounders and radar water level gauges with meteorological data to establish a water level prediction model to predict water level trends and potential risks.

[0074] S7. When abnormal conditions or potential risks are detected, the alarm module issues a prompt alert. Alarm thresholds for parameters such as water level and sediment accumulation are set based on the characteristics and management requirements of the water conservancy area. When monitoring data exceeds or falls below the set threshold, the alarm mechanism is triggered.

[0075] 3. Beneficial effects

[0076] One or more technical solutions provided in the technical solution of this application have at least the following technical effects or advantages:

[0077] 1. By continuously measuring water depth with an echo sounder, the dynamic changes in the bottom topography of the water area can be tracked, and changes in water depth that may be caused by water scouring and silt accumulation can be detected in a timely manner, providing real-time information for the safe operation of water conservancy facilities and waterway maintenance.

[0078] 2. Water level monitoring at the conservancy project is achieved through cross-validation and high precision using a variety of water level gauges. Pressure, laser, and radar level gauges each monitor water levels using different principles. The parallel operation of multiple devices enables data cross-validation, ensuring the continuity and accuracy of water level monitoring. This diverse combination of devices can adapt to the complex and changing environmental conditions of conservancy waters, ensuring accurate water level data acquisition in all situations.

[0079] 3. Accurately monitor sediment deposition through the echo data analysis module. By analyzing the echo data, the thickness of sediment deposition can be accurately calculated, and the evolution of the riverbed can be grasped in a timely manner.

[0080] 4. Comprehensive water level assessments are performed through the comprehensive analysis module, integrating monitoring results from multiple water level gauges for a more comprehensive and accurate assessment of water level conditions. Different water level gauges may experience deviations during measurement due to various factors. Comprehensive analysis can eliminate some of these errors and produce results closer to the actual water level. Furthermore, combining data from water level gauges at different locations allows analysis of the spatial distribution of water levels within the water area, understanding flow patterns and surface fluctuations, and providing comprehensive and accurate water level information for water conservancy operations, flood control, and early warning.

[0081] 5. The forecasting and analysis module integrates data from various monitoring devices and meteorological data to establish a water level forecasting model, which can predict water level trends and potential risks (such as floods and droughts). Predicting water level trends in advance allows water management departments sufficient time to take countermeasures. By assessing potential risks, it provides a scientific basis for decision-making in water management. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1This is a flow chart of a water level monitoring method disclosed in a preferred embodiment of the present application.

[0083] Figure 2 This is a structural diagram of a water conservancy water level monitoring device disclosed in a preferred embodiment of the present application.

[0084] Figure numerals: 1. vertical pole; 2. photovoltaic panel; 3. laser water level meter; 4. radar water level meter 4; 5. positioning plate; 6. anchor rod. DETAILED DESCRIPTION

[0085] The present application is further described in detail below with reference to the accompanying drawings.

[0086] Reference Figure 1 and Figure 2 , an embodiment of the present application provides a water conservancy water level monitoring device, comprising:

[0087] Pole 1: Multiple poles 1 are laid out in the water conservancy waters. The poles are made of high-strength stainless steel with good corrosion resistance and wind resistance to adapt to long-term use in different water conservancy environments. The height of the pole is customized according to the characteristics of the water area and monitoring needs to ensure that each monitoring device can be in a suitable monitoring position. The bottom of the pole is reinforced and fixed to the bottom of the water or the shore by concrete pouring or piling to ensure its stability. A positioning plate 5 is fixed at the lower end of the pole 1, and a number of anchor rods 6 are detachably fixed on the positioning plate 5. The pole 1 is fixed by the anchor rods 6 and the positioning plate 5.

[0088] Photovoltaic Panel 2: A photovoltaic panel 2 is fixed to the top of pole 1. A photovoltaic energy storage system is installed beneath the panel, converting solar energy into electricity. The system utilizes lithium batteries as energy storage devices, which offer advantages such as high energy density, efficient charging and discharging, and a long service life. The photovoltaic energy storage system is equipped with an intelligent charge controller that monitors the panel's output power and the lithium battery's charge level in real time, automatically adjusting the charging process to avoid overcharging and over-discharging, ensuring stable system operation. The energy storage system also features a backup power supply port, allowing it to be connected to an external power source in exceptional circumstances, such as continuous rainy weather.

[0089] Pressure water level gauges are installed around the perimeter of the photovoltaic panels. These gauges utilize high-precision pressure sensors to accurately measure changes in water pressure and calculate the water level based on the relationship between pressure and water level. These pressure water level gauges are waterproof, moisture-proof, and corrosion-resistant, with an IP68 rating, ensuring long-term, stable operation in underwater environments. They also feature temperature compensation, eliminating the effects of water temperature fluctuations on measurement results and improving accuracy.

[0090] Laser water level meter 3: A laser water level meter 3 is fixed beneath the photovoltaic panel 2. It uses the principle of laser ranging to determine the water level by emitting a laser beam and measuring the time it takes for the laser's reflection echo to return. Laser water level meters offer high measurement accuracy, fast response, and are unaffected by water quality and currents. Measurement accuracy can reach millimeter levels. To ensure proper operation, a protective cover is installed to prevent interference from dust, moisture, and debris.

[0091] Radar water level gauge 4: A radar water level gauge 4 is fixedly installed below the photovoltaic panel 2.

[0092] Echo sounder: An echo sounder is fixed beneath the photovoltaic panels. It transmits sound waves, which are reflected by the water's bottom interface. The water depth is calculated based on the wave's propagation time and the speed of sound in the water. Regularly measuring water depth changes at the same location reveals sediment accumulation thickness. This method offers high accuracy, is relatively simple to operate, and is applicable to a wide range of waters.

[0093] A monitoring mechanism is fixed on the pole to monitor and analyze the water level and detect abnormal situations in a timely manner.

[0094] Furthermore, monitoring agencies include:

[0095] Data Collection Module: This module collects geological and hydraulic data on water resources. Geographic data includes topography, riverbed slope, and water area. Hydraulic data includes water level, flow rate, temperature, and quality. The collected data undergoes preliminary processing, including data cleaning, format conversion, and unit unification, to ensure accuracy and consistency.

[0096] Monitoring Point Layout Module: Based on the geological data of the water area and monitoring needs, the number and location of monitoring points (including current meters, pressure water level gauges, laser water level gauges, radar water level gauges, and echo sounders) are rationally arranged. Using Geographic Information System (GIS) technology and data analysis algorithms, the layout of monitoring points is optimized based on the water area's topography, flow characteristics, and monitoring objectives. For example, the density of monitoring points is increased in areas with complex water flows and large water level fluctuations to improve monitoring accuracy and reliability. The layout of monitoring points is dynamically adjusted based on actual monitoring conditions and data analysis results to ensure that monitoring points consistently cover key areas.

[0097] Flow rate monitoring module: includes a flow meter to monitor water flow rate.

[0098] Meteorological data acquisition module: A meteorological data acquisition module is set on one or several poles; for example, a meteorological instrument, which acquires meteorological data in real time; the meteorological instrument can acquire meteorological data in real time, including temperature, air pressure, wind speed, wind direction, rainfall, etc.

[0099] Echo Data Analysis Module: This module analyzes echo data. Sound waves are reflected from the water's bottom interface and the water depth is calculated based on the sound wave's propagation time and the speed of sound in the water. Regularly measuring water depth changes at the same location can determine sediment deposition thickness.

[0100] Comprehensive Analysis Module: This module combines the monitoring results of pressure, laser, and radar water level gauges to comprehensively analyze water levels. Using methods such as multivariate statistical analysis and time series analysis, this integrated data is deeply analyzed to uncover the inherent relationships and patterns of change within the data. Based on the analysis results, the current water level is assessed to determine whether it is within the normal range or whether there are any abnormal fluctuations.

[0101] The Prediction and Analysis Module combines monitoring results from pressure water level gauges, flow meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to predict water level trends and potential risks. A water level prediction model is then established. This model uses machine learning algorithms such as neural networks and support vector machines to learn and train historical data to improve prediction accuracy. Using this established prediction model, water level trends over the next period of time are predicted, including the magnitude of water level rise or fall and the time of peak value. Based on the prediction results, potential risks are assessed, such as the likelihood and impact of disasters such as floods and droughts. Response measures and emergency plans are also developed to provide decision-making support to water management departments.

[0102] Alarm module: This module includes an alarm that issues a prompt alert when abnormal conditions or potential risks are detected. Alarm thresholds for parameters such as water level and sediment accumulation are set based on the characteristics and management requirements of the water conservancy area. Alarms are triggered when monitored data exceeds or falls below the set thresholds.

[0103] Alarm method: The alarm module includes an audible and visual alarm and a text message alarm. When an abnormal situation or potential risk is detected, the audible and visual alarm will emit a loud alarm and flashing lights to remind on-site personnel to take timely measures. At the same time, the text message alarm will send the alarm information to the mobile phone of the relevant management personnel, ensuring that the management personnel can understand the situation and make decisions in a timely manner.

[0104] Control center: network connected with data collection module, monitoring point layout module, meteorological data acquisition module, echo data analysis module, prediction analysis module and alarm module.

[0105] Furthermore, the echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the speed of sound in the water. The water depth changes at the same location are regularly measured to calculate the sediment deposition thickness. This includes the following steps:

[0106] 1. Data Measurement: Select an appropriate echo sounder model based on factors such as the depth range and accuracy requirements of the waters to be monitored. Start the echo sounder and begin measuring. The instrument transmits sound waves, which propagate through the water and are reflected back upon encountering the bottom interface and received by the instrument. The instrument automatically calculates and displays the water depth at the current location based on the propagation time and the speed of sound in the water. A data acquisition system connected to the echo sounder (such as a computer or data logger) records the measured water depth data in real time. The measurement time, date, and corresponding geographic coordinates are also recorded. This ensures the integrity and accuracy of the recorded data and prevents data loss or errors.

[0107] 2. Regular Measurement: Develop a detailed regular measurement plan based on monitoring needs. Determine the measurement frequency, such as weekly, monthly, or quarterly. During each regular measurement, repeat the water depth measurement at the same location, following the initial measurement steps. Ensure that the measurement parameters are consistent with the initial measurement to ensure data comparability.

[0108] 3. Data Comparison and Analysis: Compare the water depth data obtained from each regular measurement with the initial measurement data and the data from previous measurements. Calculate the difference in water depth between different periods. If the water depth becomes shallower, the difference is the thickness of sediment deposited during that period.

[0109] 4. Data processing: All measured water depth data and corresponding sediment thickness data are sorted, arranged in chronological order, and a data table is created. The data are numbered to facilitate subsequent query and analysis.

[0110] 5. Trend analysis: Analyze the trend of sediment accumulation by plotting the change of water depth and sediment thickness over time. Determine whether sediment accumulation is gradually increasing, stable, or showing other changing trends. For example, if the curve shows an upward trend, it means that the sediment thickness is increasing; if the curve is relatively flat, it means that the sediment accumulation is relatively stable. The trend analysis model is:

[0111] Where H is the actual sedimentation thickness; △H t is the initial calculated apparent sediment thickness; a1 is the compensation weight for the change of sound velocity with water temperature, which is calibrated in real time by the sound velocity profiler with a dynamic range of 0.002-0.005 / ℃ (related to water salinity); T 水 is the water temperature; v represents the speed of sound waves in water (unit: m / s); C is the turbidity influencing factor, the attenuation coefficient of suspended particulate matter on sound wave scattering (dimensionless), generated by the LSTM dynamic prediction model, and the input includes: laser backscattering data; historical sedimentation sample library; Tur is the water turbidity (unit: NTU), which reflects the concentration of suspended matter; measured by a multispectral sensor.

[0112] 6. Spatial Analysis: Perform spatial analysis on data from different measurement points. By drawing iso-deposition thickness maps, we can understand the distribution differences of sediment accumulation in different regions and identify areas with more severe and less severe sedimentation.

[0113] 7. Report Generation: Based on the data analysis results, a monitoring report is prepared. The report content includes the monitoring objectives, an overview of the monitoring area, the instruments and equipment used and the measurement methods, a summary of the measurement data, an analysis of sedimentation trends, spatial distribution characteristics, and relevant conclusions and recommendations. Based on the sedimentation situation, desilting operations are carried out.

[0114] Furthermore, the comprehensive analysis module combines the water level monitoring results of the pressure water level gauge and the laser water level gauge with the monitoring results of the radar water level gauge to comprehensively analyze the water level; the module includes the following steps:

[0115] 1. Data Collection: Obtain water level monitoring data from the pressure water level gauge, record the water level value corresponding to each measurement moment, and collect relevant information such as the measurement time and location. Obtain water level measurement results from the laser water level gauge, also recording the measurement time and water level value. Collect monitoring data from the radar water level gauge.

[0116] 2. Data preprocessing: Preprocess the collected data, including data cleaning and data normalization.

[0117] Data cleaning: Check the collected data and remove obvious errors, outliers, and missing values. Missing data can be supplemented using interpolation methods (such as linear interpolation and spline interpolation); outliers can be identified and corrected based on the statistical characteristics of the data (such as mean and standard deviation).

[0118] Data normalization: Since data from different monitoring devices may have different dimensions and ranges, data normalization is necessary to facilitate subsequent analysis and integration. Common normalization methods include min-max normalization and Z-score normalization.

[0119] 3. Data fusion: Align the data from the pressure water level gauge, laser water level gauge, and radar water level gauge according to time to ensure that relevant data from different devices are available at each time point. Based on the characteristics of the data and analysis requirements, choose the weighted average method, assign different weights to different devices based on their reliability and accuracy, and take a weighted average of the water level monitoring results of each device. More complex fusion algorithms such as Kalman filtering and neural networks can also be used. Perform data fusion according to the following formula:

[0120] Y = w1y1 + w2y2 + w3y3; w1 + w2 + w3 = 1; where Y is the fused water level value. It is calculated by comprehensively considering the monitoring results of three monitoring devices: the pressure water level gauge, the laser water level gauge, and the radar water level gauge, to more accurately reflect the actual water level. y1 is the water level monitoring result of the pressure water level gauge. The pressure water level gauge typically measures water height based on the pressure principle. y2 is the water level monitoring result of the laser water level gauge. Y3 is the water level monitoring result of the radar water level gauge. w1 is the weight of the pressure water level gauge monitoring result in the fusion calculation. W2 is the weight of the laser water level gauge monitoring result in the fusion calculation. W3 is the weight of the radar water level gauge monitoring result in the fusion calculation.

[0121] 4. Data Analysis

[0122] 4.1 Multivariate Statistical Analysis: Multivariate statistical analysis methods, such as principal component analysis (PCA), factor analysis, and cluster analysis, are used to reduce the dimensionality of the fused data and extract features, thereby exploring the inherent relationships and underlying structures within the data. Principal component analysis can identify the main factors influencing water level fluctuations, while cluster analysis can group similar water level data to better understand water level variation patterns.

[0123] 4.2. Time Series Analysis: Time series analysis methods, such as the Autoregressive Integrated Moving Average (ARIMA) model, seasonal decomposition, and wavelet analysis, are used to model and forecast water level data. Through time series analysis, long-term trends, seasonal changes, and cyclical fluctuations in water levels can be identified, and future changes in water levels can be predicted.

[0124] 5. Water Level Assessment: Based on historical water level data and relevant water conservancy standards, a normal range for water levels is established. This range can include upper and lower limits for the water level, as well as normal fluctuations over different time periods. To assess the water level status, the current water level data is compared with the established normal range to determine whether the water level is within the normal range. If the water level exceeds the normal range, it is considered an abnormal fluctuation. If the water level is within the normal range but shows a clear abnormal trend (such as a rapid rise or fall), further attention is also required.

[0125] 6. Result Output and Early Warning: The comprehensive analysis results are compiled into a report, including the current status of the water level, changing trends, and analysis of abnormalities. The report can be presented in charts, tables, and other formats to intuitively present the analysis results. If abnormal water level fluctuations are detected, an early warning mechanism is triggered immediately. This warning can be notified to relevant personnel via text message, email, or audio and visual alarms, prompting them to take appropriate measures, such as strengthening monitoring and adjusting the operation of water conservancy facilities.

[0126] 7. Continuous Monitoring and Optimization: Continuously collect monitoring data from pressure level gauges, laser level gauges, and radar level gauges, update the data warehouse, and provide richer information for subsequent analysis. Optimize and adjust the data analysis model based on actual conditions and new data. If certain analysis methods or models are found to be ineffective, try alternative methods or improve existing models to improve the accuracy and reliability of the analysis.

[0127] Furthermore, the forecasting and analysis module combines the monitoring results of pressure water level gauges, flow meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to establish a water level forecasting model to predict water level trends and potential risks. The module includes the following steps:

[0128] 1. Data collection and integration: Continuously collect data from pressure water level gauges, flow meters, laser water level gauges, radar water level gauges, and echo sounders, recording key information such as the time of each measurement, water level height, and water flow velocity. Obtain local meteorological data, including rainfall, temperature, wind speed, humidity, etc., as these data have a significant impact on water level changes. Collect the above-mentioned data types over the past years as the basis for model training. Align data from different sources in chronological order to ensure that the monitoring data and meteorological data at each time point correspond one-to-one. Establish a unified data storage system, such as a database, to store the integrated data for easy subsequent access and processing.

[0129] 2. Data preprocessing: Preprocess the collected data, including data cleaning and data normalization.

[0130] Data cleaning: Check the data for missing values, outliers, and erroneous data. Missing values can be supplemented using interpolation methods (such as linear interpolation and spline interpolation). Outliers can be identified and corrected based on the statistical characteristics of the data (such as mean and standard deviation). Duplicate data records should be removed to ensure data uniqueness.

[0131] Data normalization: Since data from different monitoring devices and meteorological data may have different dimensions and ranges, data normalization is necessary to facilitate subsequent analysis and model training. Common normalization methods include min-max normalization and Z-scor normalization.

[0132] 3. Feature Engineering: Analyze the correlation between various monitoring and meteorological data and water level changes, and select features that have a significant impact on water level prediction. For example, rainfall and water flow velocity are often closely related to water level changes. Statistical methods such as correlation analysis and variance analysis can be used to determine the importance of features. Based on existing features, new features can be constructed to improve the model's predictive ability. For example, average rainfall and cumulative rainfall over a period of time can be calculated.

[0133] 4. Model Construction: Use neural network (such as a multi-layer perceptron or long short-term memory (LSTM)) machine learning algorithms to build a water level prediction model. Neural networks have powerful nonlinear fitting capabilities and are suitable for handling complex water level fluctuations. Divide the preprocessed historical data into training, validation, and test sets. Use the training set to train the selected model, continuously adjusting the model parameters to enable the model to learn the patterns and regularities in the data. During the training process, use the validation set to evaluate the model's performance to avoid overfitting.

[0134] 5. Model Evaluation and Optimization: Use the test set to evaluate the trained model. Common evaluation metrics include mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Analyze the model's prediction accuracy at different time scales and water levels to identify any deficiencies. Based on the evaluation results, optimize the model. Model parameters can be adjusted, training data can be added, and feature engineering can be improved to improve the model's predictive performance.

[0135] 6. Water level trend prediction: Using a trained and optimized model, input current monitoring data and meteorological data to predict water level trends over the next period of time. The prediction content includes the rise or fall of the water level, the time to reach the peak, etc. You can set different prediction time ranges according to actual needs, such as the next week. The water level prediction model is:

[0136] S t =Σ T i＝1 [Attn i ·(a i P t-i +β i L t-i )]+tanh[Σ 6 k＝1 (w k R t-k )]+ε.

[0137] Г(Q t )=tanh[Σ 6 k＝1 (w k R t-k )]; Attn i =softmax(W a [h t-i ,x t-i ]); where S t is the predicted water level value at time t (unit: meter); T is the length of the historical time window (default value: 24 hours); Attn iis the dynamic weight, the attention weight of the i-th historical moment (range [0,1]); a i and β i is the time-varying calibration coefficient of the pressure / laser sensor, which is obtained by the hidden state h of the LSTM. t-i Dynamic adjustment to solve the problem of sensor aging drift; P t-i is the pressure water level gauge measurement value at time ti (unit: kPa); L t-i is the measurement value of the laser water level meter at time ti (unit: mm); w k is the rainfall hysteresis coefficient (k = 1 to 6 corresponds to 1 to 6 hours ago); calibrated by basin hydrological experiments; R t-k is the rainfall intensity at time tk; Tanh(·) is the hyperbolic tangent function. ε is the error correction term, which is a constant. i =softmax(W a [h t-i ,x t-i ]); W a is the attention weight matrix; [h t-i ,x t-i ] is the concatenated vector, LSTM hidden state h t-i With input feature x t-i splicing (dimension d h +d x );h t-i is the encoding history information, x t-i Contains sensor data (such as water level, flow rate). Softmax is a normalization function that converts the raw scores into a probability distribution.

[0138] 7. Potential Risk Assessment: Identify potential risk types, such as floods and droughts, and develop corresponding risk assessment criteria. For example, when the water level exceeds a certain threshold, a flood disaster is considered likely; when the water level falls below a certain threshold, a drought disaster is considered likely.

[0139] Based on the predicted water level trends, combined with historical data and relevant water conservancy standards, the likelihood and impact of potential risks can be assessed. Probabilistic analysis, scenario analysis, and other methods can be used to conduct risk assessments.

[0140] 8. Response Measures: Develop appropriate response measures based on the risk assessment results. For example, if a flood is predicted, measures can be taken to reinforce levees and evacuate residents from low-lying areas. If a drought is predicted, water conservation measures and water resource redeployment can be implemented. Develop a detailed emergency response plan that clearly defines the emergency response process and responsibilities for different risk levels. The plan should include information on the emergency command structure, emergency rescue teams, and emergency material reserves.

[0141] 9. Result output: The water level forecast results, potential risk assessment report and response measures are organized into a detailed report and displayed in the form of charts, tables, etc. to intuitively present the analysis results.

[0142] The report is submitted to the water conservancy management department to provide decision-making support. The water conservancy management department can take appropriate measures in a timely manner based on the content of the report to ensure the safe operation of water conservancy facilities and the safety of people's lives and property.

[0143] Furthermore, the monitoring point layout module reasonably arranges the number and location of monitoring points (including current meters, pressure water level gauges, laser water level gauges, radar water level gauges and echo sounders) according to the geological data of the water area and monitoring needs; the module includes the following steps:

[0144] 1. Data collection: Collect detailed geographic information data of the target water area, including high-precision topographic data (such as digital elevation models (DEMs), which can be obtained from surveying and mapping departments and professional geographic data providers. These data can intuitively display the terrain undulations, riverbed morphology and other information of the water area, which is crucial for understanding water flow paths and potential complex areas. Through the historical records of hydrological stations and past water flow monitoring research data, water flow characteristic data such as water flow velocity, flow rate, and flow direction are obtained. Clarify the core objectives of monitoring. For example, if the purpose is to monitor the impact of water level changes on surrounding residential areas during floods, the monitoring focus will be on waters close to residential areas and possible flood channels.

[0145] 2. Initial Monitoring Point Planning: Utilize professional geographic information system software (such as ArcGIS or QGIS) to build a work platform. Import acquired geographic data and flow characteristic data into the system to generate a visual map of the watershed, including topography, water systems, and surrounding environment. This provides a visual basis for subsequent monitoring point planning. Initially, evenly distribute monitoring points across the entire watershed using a grid or spacing interval. This serves as a framework for subsequent optimization. For example, for large lakes with relatively stable water flow, a certain number of monitoring points per square kilometer can be established. Prioritize monitoring point locations in key locations within the watershed, such as river confluences, river narrowings, and upstream and downstream of sluices or dams. These areas feature complex flow conditions and often drastic water level fluctuations, making them key monitoring areas. Based on clear monitoring objectives, monitoring points are deployed in relevant key areas. For example, for flood control monitoring in residential areas, monitoring points are located on the riverbank near the residential area and in low-lying areas that may be flooded. To generate the initial monitoring point plan, manually mark the locations of the initial monitoring points on the GIS platform or use spatial analysis tools in the software. Each monitoring point is numbered and its geographic coordinates recorded. Based on different monitoring needs, a preliminary plan is made on the type of equipment to be installed at each monitoring point, such as installing echo sounders in areas where water depth changes greatly, and installing flow meters in areas where water flow velocity changes are sensitive.

[0146] 3. Optimized layout of monitoring points:

[0147] 3.1 Water Flow Simulation and Analysis: Utilizing hydrodynamic models (such as the MIKE series and EFDC models), combined with existing geographic and flow data, numerical simulations are performed on the water flow conditions in the target water area. The velocity and direction of the flow are simulated under different water levels and flow conditions, and areas with complex flow (such as eddies and areas with sudden velocity changes) and areas with significant water level fluctuations are identified.

[0148] 3.2 Data Analysis: Spatial autocorrelation analysis, kriging interpolation, and other data analysis algorithms are used to analyze water flow simulation results and historical monitoring data. Spatial autocorrelation analysis can help determine the spatial correlation between monitoring points and understand which areas have similar or different monitoring data. Kriging interpolation can be used to predict water flow and water level characteristics in unmonitored areas, providing a basis for optimizing monitoring point placement.

[0149] 3.3、Optimization strategy formulation:

[0150] 3.3.1 Density Adjustment: Based on simulation and analysis results, the density of monitoring points will be increased in areas with complex water flows and large water level fluctuations. For example, in areas of turbulence caused by sharp river bends or confluences, the spacing between monitoring points will be reduced from hundreds of meters to tens of meters to more accurately capture changes in water flow and water level.

[0151] 3.3.2. Point Movement: For some monitoring points whose initial locations are unreasonable, appropriate relocations will be made based on water flow and terrain characteristics. For example, a monitoring point located in deep water with stable water flow but of little significance to the overall monitoring can be moved closer to the shore or to an area with significant water flow changes to improve the validity of the monitoring data.

[0152] 3.3.3. Equipment Optimization: Based on the monitoring needs and characteristics of different areas, further optimize the equipment configuration of monitoring points. In areas where flow velocity fluctuates dramatically and high accuracy flow velocity data is required, high-precision acoustic Doppler flowmeters should be deployed. In areas where water levels fluctuate frequently and high accuracy is required, more accurate pressure water level gauges or laser water level gauges should be used.

[0153] 3.3.4. Determine the optimized monitoring point layout plan: On the GIS platform, adjust the initial monitoring points according to the optimization strategy to generate an optimized monitoring point layout plan. Detailed information such as the new location, geographic coordinates, and monitoring equipment of each monitoring point should be recorded. A detailed layout diagram and explanatory documentation should be prepared.

[0154] 4. Dynamic Adjustment of Monitoring Point Layout: Establish a real-time monitoring data transmission system to transmit data collected by devices such as flowmeters, pressure level gauges, laser level gauges, radar level gauges, and echo sounders to a data center in real time via wireless transmission (e.g., GPRS, 4G / 5G networks) or wired transmission. Ensure data accuracy, completeness, and timeliness to support dynamic adjustments. Analyze collected monitoring data regularly (e.g., daily or weekly), using statistical analysis methods and time series analysis to assess the rationality of the monitoring point layout. Set trigger conditions for dynamic adjustments. Once the dynamic adjustment mechanism is triggered, conduct on-site surveys of the relevant areas to verify the data and understand actual water flow, topographic changes, and factors that may affect monitoring. Based on the results of the on-site survey and data analysis, develop a specific adjustment plan. This may include adding new monitoring points, removing or relocating some existing monitoring points, and adjusting the type or parameters of monitoring equipment. Simulate the effects of the adjustment plan on a GIS platform to evaluate the improvement in monitoring accuracy and reliability. Then, implement the adjustment according to the plan and promptly update relevant records and documentation of the monitoring point layout.

[0155] The present invention provides a water level monitoring method, comprising the following steps:

[0156] S1. The monitoring point layout module of the monitoring agency shall reasonably layout the number and location of monitoring points (including current meters, pressure water level gauges, laser water level gauges, radar water level gauges and echo sounders) according to the geological data of the water area and monitoring needs.

[0157] S2. The flow rate monitoring module monitors the water flow rate; the meteorological data acquisition module obtains meteorological data in real time; the weather data includes temperature, air pressure, wind speed, wind direction, rainfall, etc.; the echo sounder uses the echo sounder to emit sound waves, which are reflected back when they encounter the bottom interface, and the water depth is calculated based on the sound wave propagation time and the sound speed in the water.

[0158] S3, pressure water level gauge, laser water level gauge and radar water level gauge monitor the water level of the water conservancy respectively.

[0159] S4. The echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the speed of sound in water. The water depth changes at the same location are regularly measured to calculate the sediment deposition thickness.

[0160] S5. The comprehensive analysis module combines the monitoring results of the pressure water level gauge, laser water level gauge and radar water level gauge to comprehensively analyze the water level.

[0161] S6. The prediction and analysis module combines the monitoring results of pressure water level gauges, flow meters, laser water level gauges, echo sounders and radar water level gauges with meteorological data to establish a water level prediction model to predict water level trends and potential risks.

[0162] S7. When abnormal conditions or potential risks are detected, the alarm module issues a prompt alert. Alarm thresholds for parameters such as water level and sediment accumulation are set based on the characteristics and management requirements of the water conservancy area. When monitoring data exceeds or falls below the set threshold, the alarm mechanism is triggered.

[0163] The operating principle of the water level monitoring device of the present invention is as follows: the monitoring point layout module of the monitoring mechanism rationally arranges the number and location of monitoring points based on the geological data of the water area and monitoring needs; the flow rate monitoring module monitors the water flow velocity; the meteorological data acquisition module obtains meteorological data in real time; the echo sounder uses the echo sounder to emit sound waves, which are reflected back from the water bottom interface, and the water depth is calculated based on the sound wave propagation time and the sound speed in the water. The pressure water level gauge, laser water level gauge, and radar water level gauge respectively monitor the water level of the water conservancy; the echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the sound speed in the water. The water depth changes at the same location are regularly measured to calculate the thickness of the sediment accumulation. The comprehensive analysis module combines monitoring data from pressure water level gauges, laser water level gauges, and radar water level gauges to comprehensively analyze water levels. The predictive analysis module combines monitoring data from pressure water level gauges, flow meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to develop a water level prediction model to predict water level trends and potential risks. The alarm module issues a prompt alert when abnormal conditions or potential risks are detected. Alarm thresholds for parameters such as water level and sediment accumulation are set based on the characteristics and management requirements of the water conservancy area. Alarms are triggered when monitoring data exceeds or falls below the set thresholds.

[0164] This invention uses a monitoring point layout module to rationally determine the number and location of monitoring points, ensuring comprehensive coverage of waters with diverse topography, flow conditions, and functional areas. This ensures representative monitoring data, avoids blind spots, and comprehensively reflects the overall condition of the water area. Continuously measuring water depth with an echo sounder tracks dynamic changes in the bottom topography of the water area, promptly detecting changes in water depth that may be caused by scour or silt accumulation, and providing real-time information for the safe operation of water conservancy facilities and waterway maintenance. Water level monitoring using multiple water level gauges achieves cross-validation and high accuracy. Pressure, laser, and radar water level gauges each monitor water level using different principles, and operating multiple devices in parallel allows for data cross-validation. If a device malfunctions or data anomalies occur, data from other devices can be used as supplementary reference to ensure the continuity and accuracy of water level monitoring. Different devices have their own advantages in terms of accuracy and applicable environments. Their combined use can improve overall water level monitoring accuracy and meet the high-precision water level data requirements of water conservancy management. This diverse combination of devices can adapt to the complex and changing environmental conditions of water conservancy waters, ensuring accurate water level data acquisition in all situations. The echo data analysis module enables precise sedimentation monitoring. By analyzing echo data, the thickness of sediment accumulation can be accurately calculated, providing timely insights into riverbed evolution. This is crucial for the safety of water conservancy projects. For example, excessive sediment accumulation in riverbeds around reservoirs and dams can affect the stability of engineering structures. Sedimentation in waterways affects navigation capacity. Timely monitoring of sedimentation thickness allows for proactive planning of maintenance work, such as dredging, to ensure the normal operation of water conservancy facilities and the smooth flow of waterways. Regularly measuring water depth changes at the same location to calculate sedimentation thickness accumulates long-term data series for analyzing long-term sedimentation trends. Understanding whether sedimentation is increasing, remaining stable, or improving year by year provides a scientific basis for developing long-term water conservancy plans and ecological protection strategies, such as predicting future river channel changes and planning flood control embankment construction or adjusting water intake locations. The comprehensive analysis module provides comprehensive water level assessments, integrating monitoring data from multiple water level gauges for a more comprehensive and accurate assessment of water level conditions. Different water level gauges may experience deviations during measurement due to various factors. Comprehensive analysis can eliminate some of these errors, resulting in results that are closer to the actual water level. Furthermore, by combining data from water level gauges at different locations, the spatial distribution of water levels within the water area can be analyzed, understanding flow patterns and surface fluctuations. This provides comprehensive and accurate water level information for water conservancy operations and flood prevention warnings. The predictive analysis module integrates data from various monitoring devices and meteorological data to create a water level forecast model, which can predict water level trends and potential risks (such as floods and droughts). Predicting water level trends in advance allows water management departments sufficient time to implement countermeasures. This assessment of potential risks provides a scientific basis for decision-making in water management.

[0165] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A water level monitoring method, characterized in that: The following steps are involved: S1. The monitoring point layout module of the monitoring agency reasonably arranges the number and location of monitoring points based on the geological data of the water area and monitoring needs; S2, the flow rate monitoring module monitors the water flow rate; the meteorological data acquisition module obtains meteorological data in real time; the echo sounder transmits sound waves and calculates the water depth based on the sound wave propagation time and the sound speed in the water; the photovoltaic panels and photovoltaic energy storage system provide auxiliary power supply; S3, pressure water level gauge, laser water level gauge and radar water level gauge monitor the water level of the water conservancy respectively; S4, the echo data analysis module analyzes the echo data and calculates the water depth based on the sound wave propagation time and the speed of sound in water; regularly measures the water depth changes at the same location and calculates the sediment deposition thickness; S5, comprehensive analysis module combines the monitoring results of pressure water level gauge, laser water level gauge and radar water level gauge to comprehensively analyze the water level; S6, the prediction and analysis module combines the monitoring results of pressure water level gauges, current meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to establish a water level prediction model to predict water level trends and potential risks; S7. When abnormal conditions or potential risks are detected, the alarm module will issue an alarm in time.

2. The water level monitoring method according to claim 1, characterized in that: Step S1 includes the following steps: S11. Data collection: Collect detailed geographic information data of the target water area, obtain water flow velocity, flow rate and flow direction characteristics data, and clarify the core objectives of monitoring; S12. Initial monitoring point planning: Initially distribute monitoring points evenly throughout the water area at regular intervals, prioritizing the locations of monitoring points at key locations within the water area. Based on clear monitoring objectives, distribute monitoring points in relevant key areas. On a GIS platform, utilize the software's spatial analysis tools to generate the locations of initial monitoring points, number each monitoring point, and record its geographic coordinate information. S13, optimization layout of monitoring points; S14. Dynamic adjustment of monitoring point layout: Establish a real-time transmission system for monitoring data, regularly analyze the collected monitoring data, and use statistical analysis methods to evaluate the rationality of the monitoring point layout; set the trigger conditions for dynamic adjustment. When the dynamic adjustment mechanism is triggered, conduct on-site inspections of the relevant areas, and formulate specific adjustment plans based on the results of the on-site inspections and data analysis.

3. The water level monitoring method according to claim 2, characterized in that: Step S13 includes the following steps: S13.1 Water Flow Simulation and Analysis: Utilize hydrodynamic models, combined with existing geographic and water flow data, to numerically simulate water flow conditions in target waters. Simulate the velocity and direction of water flow under varying water levels and flow rates, and identify areas with complex water flows and significant water level fluctuations. S13.

2. Data analysis: Use spatial autocorrelation analysis algorithm to analyze water flow simulation results and historical monitoring data; S13.3, Optimization Strategy Development: S13.3.

1. Density Adjustment: Based on simulation and analysis results, increase the density of monitoring points in areas with complex water flows and large water level fluctuations; S13.3.

2. Point movement: For some monitoring points whose initial locations are unreasonable, they should be moved appropriately according to the water flow and terrain characteristics; S13.3.

3. Equipment Optimization: Based on the monitoring needs and characteristics of different areas, further optimize the equipment configuration of monitoring points; S13.3.

4. Determination of optimized monitoring point layout plan: On the GIS platform, the initial monitoring points are adjusted according to the optimization strategy to generate an optimized monitoring point layout plan.

4. The water level monitoring method according to claim 1, characterized in that: Step S4 includes the following steps: S41, data measurement: Start the echo sounder and start measurement; automatically calculate the water depth data of the current position based on the sound wave propagation time and the sound speed in the water; S42. Regular measurement: regularly measure the water depth at the same location; S43. Data comparison and analysis: Compare the water depth data obtained from each regular measurement with the initial measurement data and the data from previous measurements; calculate the difference in water depth at different times. If the water depth becomes shallower, the difference is the thickness of the sediment accumulated during that time period; S44, data processing: sort out all measured water depth data and corresponding sediment thickness data, arrange them in chronological order, create a data table; number the data; S45. Trend analysis: Analyze the trend of sediment deposition by plotting the curves of water depth and sediment thickness over time. The trend analysis model is: Where H is the actual sedimentation thickness; △H t is the initial calculated apparent sediment thickness; a1 is the compensation weight for the change of sound velocity with water temperature, which is calibrated in real time by the sound velocity profiler; T 水 is the water temperature; v represents the propagation speed of sound waves in water; C is the turbidity influencing factor, generated by the LSTM dynamic prediction model; Tur is the water turbidity, which reflects the concentration of suspended matter and is measured by a multispectral sensor; S46. Spatial Analysis: Perform spatial analysis on data from different measurement points to understand the distribution differences of sediment accumulation in different regions and identify areas with more severe and less severe sediment accumulation. S47. Generate report: Write a monitoring report based on the data analysis results.

5. The water level monitoring method according to claim 1, characterized in that: Step S5 includes the following steps: S51. Data collection: Obtain water level monitoring data from the pressure water level gauge; obtain water level measurement results from the laser water level gauge; collect monitoring data from the radar water level gauge; S52, data preprocessing: preprocess the data, including data cleaning and data normalization; S53, data fusion: align the data of the pressure water level gauge, laser water level gauge, and radar water level gauge according to time and fuse the data; perform data fusion according to the following formula: Y=w1y1+w2y2+w3y3; w1+w2+w3=1; where Y is the fused water level value; y1 is the water level monitoring result of the pressure water level gauge; y2 is the water level monitoring result of the laser water level gauge; Y3 is the water level monitoring result of the radar water level gauge; w1 is the weight of the pressure water level gauge monitoring result in the fusion calculation; W2 is the weight of the laser water level gauge monitoring result in the fusion calculation; W3 is the weight of the radar water level gauge monitoring result in the fusion calculation; S54, data analysis; S55, water level assessment: set the normal range of water level based on historical water level data and relevant water conservancy standards; judge the water level status, compare the current water level data with the set normal range, and determine whether the water level is within the normal range; S56. Result output and early warning: The results of the comprehensive analysis are compiled into a report, including the current status of the water level, change trends, and abnormal situation analysis. If abnormal fluctuations in the water level are detected, the early warning mechanism is triggered in a timely manner. S57. Continuous monitoring and optimization: Continuously collect monitoring data from pressure water level gauges, laser water level gauges, and radar water level gauges, and optimize and adjust the data analysis model based on actual conditions and new data.

6. The water level monitoring method according to claim 5, characterized in that: Step S54 includes the following steps: S54.

1. Multivariate statistical analysis: Use principal component analysis (PCA) to reduce the dimensionality and extract features from the fused data, exploring the inherent relationships and potential structures between the data. Use principal component analysis to identify the main factors affecting water level changes. Use cluster analysis to group similar water level data. S54.

2. Time series analysis: The autoregressive integrated moving average (ARIMA) model is used to model and predict water level data. Through time series analysis, the long-term trend, seasonal changes, and cyclical fluctuations of water levels are discovered, and future changes in water levels are predicted.

7. The water level monitoring method according to claim 1, characterized in that: Step S6 includes the following steps: S61. Data Collection and Integration: Continuously collect data from pressure gauges, current meters, laser water level gauges, radar water level gauges, and echo sounders; obtain local meteorological data; and align data from different sources in chronological order. S62. Data preprocessing: preprocess the data, including data cleaning and data normalization; S63. Feature Engineering: Analyze the correlation between various monitoring data and meteorological data and water level changes, and select features that have a significant impact on water level prediction; based on existing features, construct new features to improve the model's predictive ability; S64. Model Construction: Use the Long Short-Term Memory (LSTM) machine learning algorithm to build a water level prediction model. Divide the preprocessed historical data into a training set, a validation set, and a test set. Use the training set to train the selected model, continuously adjusting the model parameters to enable the model to learn the patterns and rules in the data. Use the validation set to evaluate the model's performance. S65, Model evaluation and optimization: Use the test set to evaluate the trained model; optimize the model based on the evaluation results; S66, Water Level Trend Forecast: Use the trained and optimized model, input current monitoring data and meteorological data, and predict the water level trend in the future; S67. Potential risk assessment: Identify potential risk types and develop corresponding risk assessment standards; assess the likelihood and impact of potential risks based on predicted water level trends, combined with historical data and relevant water conservancy standards; S68. Response measures: Develop corresponding response measures based on the risk assessment results; S69. Result output: Organize the water level forecast results, potential risk assessment report and response measures into a detailed report and display it.

8. The water level monitoring method according to claim 7, characterized in that: In step S66, the water level prediction model is: S t =S T i＝1 [Attn. i ·(a i P t-i +b i L t-i )]+tanh[Σ 6 k＝1 (w k R t-k )]+e; Г(Q t )=tanh[Σ 6 k＝1 (w k R t-k )]; Attn i =softmax(W a [h t-i ,x t-i ]); where S t is the predicted water level value at time t; T is the length of the historical time window; Attn i is the dynamic weight, the attention weight of the i-th historical moment; a i and β i is the time-varying calibration coefficient of the pressure / laser sensor, which is obtained by the hidden state h of the LSTM. t-i Dynamic adjustment; P t-i is the measured value of the pressure water level gauge at time ti; L t-i is the measurement value of the laser water level meter at time ti; w k is the rainfall hysteresis coefficient; R t-k is the rainfall intensity at time tk; Tanh(·) is the hyperbolic tangent function; ε is the error correction term; W a is the attention weight matrix; [h t-i ,x t-i ] is the concatenated vector, LSTM hidden state h t-i With input feature x t-i splicing; h t-i is the encoding history information, x t-i Contains sensor data; softmax is the normalization function.

9. The water level monitoring method according to claim 1, characterized in that: The monitoring agencies include: Data collection module: collects geological data and water conservancy data of water conservancy areas; performs preliminary processing on the collected data, including data cleaning, format conversion and unit unification; Monitoring point layout module: reasonably layout the number and location of monitoring points based on the geological data of the water area and monitoring needs; Flow rate monitoring module: including a flow meter to monitor water flow rate; Meteorological data acquisition module: a meteorological data acquisition module is set on one or several poles to obtain meteorological data in real time; Echo data analysis module: Analyzes echo data and calculates water depth based on sound wave propagation time and sound speed in water; regularly measures water depth changes at the same location to obtain sediment deposition thickness; Comprehensive analysis module: combines the monitoring results of pressure water level gauge, laser water level gauge and radar water level gauge to comprehensively analyze the water level; Prediction and Analysis Module: This module combines the monitoring results of pressure water level gauges, current meters, laser water level gauges, echo sounders, and radar water level gauges with meteorological data to establish a water level prediction model to predict water level trends and potential risks. Alarm module: including alarm, which will issue an alarm in time when abnormal conditions or potential risks are detected; Control center: network connected with data collection module, monitoring point layout module, meteorological data acquisition module, echo data analysis module, prediction analysis module and alarm module.

10. A water level monitoring device, comprising: Pole, photovoltaic panel, pressure water level gauge, laser water level gauge, radar water level gauge and echo sounder; its characteristics are: Poles: Multiple poles are laid out in the water conservancy waters; a positioning plate is fixedly provided at the lower end of the pole, and a number of anchor rods are detachably fixed on the positioning plate; Photovoltaic panels: A photovoltaic panel is fixed on the top of the pole; a photovoltaic energy storage system is installed under the photovoltaic panel to convert solar energy into electrical energy; Pressure water level gauge: A pressure water level gauge is installed around the bottom of the photovoltaic panel; Laser water level meter: A laser water level meter is fixedly installed under the photovoltaic panel; Radar water level meter: A radar water level meter is fixedly installed under the photovoltaic panel; Echo sounder: An echo sounder is fixed under the photovoltaic panel; A monitoring mechanism is fixed on the pole to monitor and analyze the water level and detect abnormal situations in a timely manner.

Images