Overwater floating monitoring working platform for light wave water environment and hydrological monitoring method

Abstract

The invention relates to the technical field of hydrological monitoring, in particular to an overwater floating monitoring working platform for a light-wave water environment, which comprises a water pipe, a first end of the water pipe is provided with a water suction head, and a water suction end of the water suction head is provided with a filter screen; the input end of the water pump is connected with the second end of the water pipe; the water pipe releasing equipment is provided with slow-moving rotating storage equipment, and a main body of the water pipe is wound and stored on the slow-moving rotating storage equipment; the monitoring end of the flow velocity sensor is installed on the water pipe. The flow velocity sensor is used for detecting the flow velocity of water in the water pipe. The sensor is installed on the water pipe, and the distance from the sensor to the water suction head is the preset height from the sensor to underwater sludge. The overwater floating monitoring working platform for the light wave water environment can solve the problem that the underwater distance from a sensor to sludge is difficult to accurately control. In addition, the invention provides a hydrological monitoring method which uses the water floating monitoring working platform for the light wave water environment.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrological monitoring, and particularly to a floating monitoring working platform for a light-wave water environment and a hydrological monitoring method. Background Art

[0002] In the existing hydrological monitoring systems, they are generally suspended on the water surface. An important topic in hydrological monitoring is the monitoring of the deposition direction of underwater silt. General monitoring devices have certain limitations. The sensors for monitoring silt need to be arranged at a specific height, usually at a certain height distance from the silt. General underwater devices are difficult to accurately detect the depth of the silt. Especially for the floating platforms used in rivers and lakes, the distances from the underwater silt to the water surface at different positions are different. If the height of the placement detection area is insufficient, it is easy to have a huge impact on the entire data acquisition of underwater monitoring, especially on the accuracy and integrity.

[0003] During the hydrological monitoring process, the distribution characteristics of sedimentation directly affect the layout scheme of sensors, and the rationality of the layout scheme in turn determines the accuracy and integrity of the monitoring data. The sedimentation areas usually show non-uniform spatial distribution characteristics. The sedimentation rate is relatively fast in some areas, while relatively stable in some other areas. Since the change of sedimentation thickness is closely related to factors such as water velocity, sediment content, and terrain characteristics, the sensor layout needs to fully consider these factors to ensure that the monitoring points can reflect the true state of sedimentation. However, the technical contradiction faced in the actual layout is that although a too dense sensor layout can improve the data accuracy, it will significantly increase the equipment cost and maintenance difficulty; while a sparse layout may lead to the locality of the monitoring data and cannot comprehensively capture the dynamic changes of sedimentation. In addition, the matching between the measurement range of the sensor and the sedimentation depth is also a key issue. A too small measurement range may lead to data missing, and a too large one may reduce the fineness of the data. These problems need to be comprehensively considered in the layout scheme. Summary of the Invention

[0004] To solve the above problems, the present invention proposes a floating monitoring working platform for a light-wave water environment, which can solve the problem that it is difficult to accurately control the height of the sensor arranged underwater from the silt. In addition, the present invention proposes a hydrological monitoring method using the above floating monitoring working platform for a light-wave water environment.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] In the first technical solution, a floating monitoring working platform for a light-wave water environment includes:

[0007] A water pipe, the first end of the water pipe is installed with a water suction head, and the water suction end of the water suction head has a filter screen;

[0008] A water pump, the input end of the water pump is connected to the second end of a water pipe, and is used for pumping water through the water pump;

[0009] A water pipe releasing device, the water pipe releasing device has a slow-moving rotating storage device, and the main body of the water pipe is coiled and stored on the slow-moving rotating storage device;

[0010] A flow velocity sensor, the monitoring end of the flow velocity sensor is installed on the water pipe, and the flow velocity sensor is used for detecting the flow velocity of the water body in the water pipe;

[0011] A sensor, the sensor is installed on the water pipe and the distance from the water suction head is the preset height of the sensor from the underwater silt.

[0012] In the first technical solution, preferably, the water pipe and the input end of the water pump are connected through a sealed bearing.

[0013] In the first technical solution, preferably, the water pipe releasing device includes:

[0014] A rotating power device;

[0015] An output shaft, the output shaft is connected to the output end of the rotating power device, and the output shaft is vertically arranged;

[0016] A support plate, the upper end of the output shaft is connected to the rotation center of the support plate;

[0017] A limit plate, the limit plate is installed above the support plate, and a hole for the water pipe to pass through is opened on the limit plate;

[0018] The water pump is installed above the limit plate.

[0019] In the first technical solution, preferably, a set of water pipe alignment rollers for guiding the vertical downward movement of the water pipe is further arranged outside the water pipe releasing device.

[0020] In the first technical solution, preferably, the water suction head includes a water suction disc and a plurality of branch pipes, the water suction disc is provided with at least 2 water suction holes, a filter screen is arranged inside each water suction hole, and the first ends of the plurality of branch pipes are respectively connected to the water suction holes, and the second ends of the branch pipes are gathered and communicated with the water pipe.

[0021] In the first technical solution, preferably, the usage method of the floating monitoring work platform on the light wave water environment is as follows:

[0022] Install the water suction head on the water pipe, connect the second end of the water pipe to the input end of the water pump, install the sensor on the water pipe and keep a predetermined distance from the water suction head, place the water suction head underwater, and complete the preparation work;

[0023] Rotate the water pipe release device to release the water pipe slowly. At the same time, turn on the water pump and the flow velocity sensor. When the flow velocity sensor detects that the water body flow velocity in the water pipe is less than the threshold value, control the water pipe release device to stop releasing the water pipe. At this time, the suction head contacts the silt, the silt seals the suction holes, the water body flow velocity in the water pipe decreases, and the sensor is at a predetermined distance from the bottom silt.

[0024] In the second technical solution, a hydrological monitoring method uses the floating monitoring work platform in the light wave water environment described in the first technical solution. The method includes:

[0025] Obtain the historical siltation data of the target water area, analyze the spatial characteristics of the siltation distribution and the temporal variation trend of the siltation rate, and determine the high-siltation areas and the key points of rate change;

[0026] According to the siltation distribution characteristics and the rate change trend, preset the initial positions and quantities of the sensor layout to ensure coverage of the high-siltation areas and key points;

[0027] Adopt the sensor measurement range and accuracy parameters, calculate the monitoring coverage range and error range of each preset position, and adjust the layout positions and quantities to optimize the coverage effect of the monitoring network;

[0028] By simulating the siltation rate change trend, predict the possible changes in the future siltation distribution, and judge whether it is necessary to increase or adjust the sensor layout positions and quantities;

[0029] Adopt the clustering analysis method in the machine learning algorithm to cluster the historical siltation data, identify the main patterns and change rules of the siltation distribution, and assist in optimizing the sensor layout plan;

[0030] By using the regression analysis method in the machine learning algorithm, establish a relationship model between the siltation rate and time, predict the future change trend of the siltation rate, and provide a basis for dynamic adjustment of the sensor layout.

[0031] In the second technical solution, preferably, the obtaining of the historical siltation data of the target water area, analyzing the spatial characteristics of the siltation distribution and the temporal variation trend of the siltation rate, and determining the high-siltation areas and the key points of rate change includes:

[0032] Obtain the historical siltation data of the target water area and define the dataset boundary based on the water area range;

[0033] Adopt the spatial analysis method to calculate the spatial characteristics of the siltation distribution and generate a spatial distribution map;

[0034] Through the time analysis method, calculate the temporal variation trend of the siltation rate and generate a time trend map;

[0035] Combined with the spatial distribution map, judge the boundaries and positions of the high-siltation areas;

[0036] Determine the key time points of the change in the sedimentation rate according to the time trend graph;

[0037] Integrate the high-incidence areas and key time points to generate a time-series distribution map of the high-incidence areas of sedimentation;

[0038] Based on the time-series distribution map, establish a prediction model for the high-incidence areas of sedimentation;

[0039] According to the sedimentation distribution characteristics and the rate change trend, preset the initial positions and quantities of the sensor layout to ensure coverage of the high-incidence areas and key points, including:

[0040] Obtain the historical sedimentation data of the target area and extract the spatial characteristics of the sedimentation distribution;

[0041] Analyze the time-series data to determine the change trend pattern of the sedimentation rate;

[0042] Combine the spatial characteristics and change trend to draw a spatial distribution map of the high-incidence areas of sedimentation;

[0043] According to the distribution characteristics of the high-incidence areas, determine the preset sensor layout points;

[0044] If the change in the sedimentation rate is drastic, increase the preset quantity of the sensor layout;

[0045] Adopt the spatial density calculation method to optimize the sensor layout plan to ensure coverage of the key points;

[0046] Implement data collection through the preset plan to establish a sedimentation monitoring and analysis model.

[0047] In the second technical solution, preferably, the monitoring coverage range and error range of each preset position are calculated by using the measurement range and accuracy parameters of the sensor, and the layout position and quantity are adjusted to optimize the coverage effect of the monitoring network, including:

[0048] Obtain the measurement range and accuracy parameters of the sensor, and for each preset position, calculate the monitoring coverage range by using the spatial coverage algorithm;

[0049] According to the accuracy parameters, calculate the error range of each preset position by using the error propagation model;

[0050] Judge whether the monitoring coverage range meets the preset threshold. If not, adjust the layout position and quantity;

[0051] Adopt the network optimization algorithm to recalculate the monitoring coverage range and error range for the adjusted layout position and quantity;

[0052] According to the recalculated results, use the comprehensive evaluation model to judge the coverage effect of the monitoring network;

[0053] If the coverage effect does not reach the optimal, return to the step of adjusting the layout position and quantity;

[0054] Determine the final layout plan and output the optimized monitoring network coverage effect;

[0055] In the second technical solution, preferably, the clustering analysis method in the machine learning algorithm is used to cluster the historical siltation data, identify the main patterns and variation laws of the siltation distribution, and assist in optimizing the sensor layout plan, including:

[0056] Obtain the original data set from the historical siltation data, and perform preprocessing operations on the data set to remove noise and standardize the data scale;

[0057] Use the K-means clustering algorithm to perform clustering analysis on the processed data, and select the Euclidean distance as the distance metric standard;

[0058] Determine the number of clustering centers according to the data characteristics, and generate the siltation distribution map and the change rate statistical result;

[0059] If the clustering result shows significant regional differences in the data distribution, adjust the sensor layout position;

[0060] By optimizing the layout points, improve the monitoring coverage range of the sensor for the siltation data;

[0061] Generate the sensor distribution map according to the final layout plan to achieve efficient monitoring;

[0062] The relationship model between the siltation rate and time is established by using the regression analysis method in the machine learning algorithm to predict the change trend of the future siltation rate and provide a basis for dynamic adjustment of the sensor layout, including:

[0063] Obtain the rate values on the historical time axis, and use the linear regression method to establish the relationship formula between the rate values and the time axis;

[0064] Calculate the predicted values according to the relationship formula, and determine the change amount of the rate values;

[0065] Obtain the position information of the sensor layout points, and calculate the adjustment amount in combination with the predicted values;

[0066] Judge the relationship between the change amount and the preset threshold. If the change amount exceeds the threshold, update the position information of the layout points;

[0067] Recalculate the adjustment amount according to the updated layout point information, and determine the new sensor layout plan;

[0068] Use the decision tree algorithm to classify the adjustment amount and judge the dynamic index;

[0069] Optimize the model quantity according to the dynamic index and output the final sensor layout scheme.

[0070] The beneficial effects of this solution are described in detail below through embodiments. Brief Description of the Drawings

[0071] Figure 1 It is an overall schematic diagram of the floating monitoring work platform for the light wave water environment of the present invention.

[0072] Figure 2 For Figure 1 It is a schematic diagram of the functional equipment components in

[0073] Figure 3 For Figure 2 It is a side view of the water pipe deviation correction roller in

[0074] Figure 4 It is a schematic diagram of the water suction head.

[0075] Figure 5 It is a schematic diagram of the water suction disc.

[0076] Figure 6 It is a flowchart of the hydrological monitoring method.

[0077] The reference numerals include:

[0078] 10 - floating body, 20 - functional equipment components, 30 - equipment box, 40 - photovoltaic system, 50 - camera, 60 - communication system;

[0079] 21 - rotating power device, 22 - output shaft, 23 - support plate, 24 - limiting plate, 25 - water pipe, 26 - water pump, 27 - sealing bearing, 28 - flow velocity sensor, 29 - support platform, 210 - water pipe deviation correction roller, 211 - water suction head, 2111 - water suction disc, 2112 - branch pipe, 212 - sensor. Detailed Embodiments

[0080] To make the purpose, technical solution and advantages of this technical solution clearer, the following further details this technical solution in combination with specific embodiments. It should be understood that these descriptions are exemplary and not intended to limit the scope of this technical solution.

[0081] Embodiment 1

[0082] To solve the problem that it is difficult to control the layout distance between the sensor 212 and the silt surface in the prior art, as Figures 1 - 5 shown, this embodiment proposes a floating monitoring work platform for the light wave water environment.

[0083] As Figure 1As shown, the floating monitoring work platform for the light wave water environment includes a float 10, a solid as the main buoyancy providing component of the equipment platform, and the upper part of the float 10 is the working platform. Specifically, the top surface of the float 10 is the working platform, and a guardrail is arranged at the periphery of the working platform. A photovoltaic system 40 including two photovoltaic panels is arranged on the equipment platform. The photovoltaic system 40 has a built-in battery to store electrical energy and supply power to other electronic equipment and power equipment on the equipment platform. A functional equipment component 20 is also installed on the equipment platform, which is used to control the height of the sensor 212, that is, the lower sensor 212 makes the sensor 212 reach a specified distance from the underwater mud.

[0084] A support pole is erected on the work platform, and an equipment box 30 is installed on the support pole. The equipment box 30 stores necessary tools to facilitate the maintenance of the floating monitoring work platform on the water. A camera 50 and a communication system 60 are also installed on the support pole, wherein the camera 50 is used for monitoring, and the communication device is used to communicate with external devices and transmit data signals and control signals in real time. The above-mentioned functional equipment components 20, camera 50 and communication system 60 are all electrically connected to the photovoltaic system 40.

[0085] like Figure 2 As shown, in this embodiment, the functional device assembly 20 includes a rotating power device 21, and the rotating power device 21 includes a motor and a reducer, wherein the output end of the motor is connected to the input end of the reducer, and the output end of the reducer is connected to an output shaft 22. In this embodiment, the output shaft 22 is vertically arranged. The output shaft 22 is connected to the rotation center of the lower end surface of the circular support plate 23. A limit plate 24 is installed above the support plate 23, and the limit plate 24 is connected to the support plate 23 through a small support rod. The limit plate 24 is a circular plate, and the center position of the limit plate 24 has a hollow through hole, and a water pump 26 is installed above the limit plate 24.

[0086] The above structure is the basic structure of the functional equipment assembly 20. The water pipe 25 is coiled and placed between the support plate 23 and the limit plate 24. The first end of the water pipe 25 is connected to the water suction head 211, and the second end of the water pipe 25 passes through the through hole on the limit plate 24 and is connected to the input end of the water pump 26. Preferably, when the rotating power device 21 drags the water pipe 25 to rotate around the axis of the output shaft 22, in order to prevent the water pipe 25 from twisting and deforming, the water pipe 25 is connected to the input end of the water pump 26 through a sealed bearing 27.

[0087] In addition, in this embodiment, the role of setting the limiting plate 24 is to prevent the water pipe 25 from being squeezed into a flat shape, which would cause the problem of difficulty in absorbing water. Due to the combination of the supporting plate 23 and the limiting plate 24, even if the water pipe 25 receives radial pressure, its cross-sectional shape shrinks from a circle to a square, and the water flow effect can still be maintained. When the water pump 26 absorbs water, the water inside it can also have a certain effect of resisting the water pipe 25 from being flattened.

[0088] In a feasible embodiment, when the pallet 23 and the limit plate 24 rotate to release the water pipe 25, the water pipe 25 is guided by two water pipe alignment rollers 210 provided on the support platform 29, so that the water pipe 25 can only move downward in the vertical direction. The structure of the water pipe alignment roller 210 is as Figure 3 shown, its wheel surface is a concave curved structure, and the curvature of the curved surface matches the outer diameter of the water pipe 25.

[0089] As Figure 4 and Figure 5 shown, in this embodiment, the water suction head 211 includes a water suction disc 2111 and a plurality of branch pipes 2112. Three water suction holes are provided on the water suction disc 2111, and a filter screen is arranged inside each water suction hole. The first ends of the branch pipes 2112 are respectively connected to the water suction holes, and the second ends of the branch pipes 2112 are gathered and communicated with the water pipe 25. The function of arranging a plurality of water suction holes on the water suction disc 2111 is to prevent sundries in the water from blocking in one water suction hole, resulting in the triggering of the flow rate sensor and the incorrect measurement of the silt depth.

[0090] Combined with the above technical solutions, the usage method of the floating monitoring work platform on the water surface in a light wave water environment proposed in this embodiment is as follows:

[0091] Install the water suction head 211 on the water pipe 25, connect the second end of the water pipe 25 to the input end of the water pump 26, install the sensor 212 on the water pipe 25 and keep a predetermined distance from the water suction head 211, and place the water suction head 211 underwater to complete the preparation work;

[0092] Rotate and release the water pipe 25 release device, and at the same time turn on the water pump 26 and activate the flow rate sensor 212. Slowly release the water pipe 25. When the flow rate sensor 212 detects that the water flow rate in the water pipe 25 is less than the threshold value, at this time, the sealing net with side water suction holes is blocked by the silt. At this time, control the water pipe 25 release device to stop releasing the water pipe 25. At this time, the water suction head 211 contacts the silt, the silt seals the water suction holes, the water flow rate in the water pipe 25 decreases, and the sensor 212 reaches a predetermined distance from the bottom silt.

[0093] Embodiment 2

[0094] This embodiment proposes a hydrological monitoring method, which uses the floating monitoring work platform on the water surface in a light wave water environment in Embodiment 1. Since the floating monitoring work platform on the water surface in a light wave water environment can more accurately control the distance between the sensor 212 and the silt, therefore, through the combination of this method and the floating monitoring work platform on the water surface in a light wave water environment in Embodiment 1, the expected detection effect can be more accurately achieved. As Figure 6 shown, specifically, the hydrological monitoring method may specifically include:

[0095] Step S101: Obtain the historical sedimentation data of the target water area, analyze the spatial characteristics of sedimentation distribution and the temporal variation trend of sedimentation rate, and determine the high-sedimentation regions and the key points of rate change.

[0096] Obtain the historical sedimentation data of the target water area and define the dataset boundary based on the water area scope. Adopt spatial analysis methods to calculate the spatial characteristics of sedimentation distribution and generate a spatial distribution map. Through temporal analysis methods, calculate the temporal variation trend of sedimentation rate and generate a temporal trend map. Combine the spatial distribution map to judge the boundaries and locations of high-sedimentation regions. According to the temporal trend map, determine the key time points of sedimentation rate change. Integrate the high-sedimentation regions and the key time points to generate a time series distribution map of high-sedimentation regions. Based on the time series distribution map, establish a prediction model for high-sedimentation regions.

[0097] Specifically, to obtain the historical siltation data of the target water area, relevant information can be retrieved from hydrological yearbooks, historical navigational charts, historical bathymetric survey reports, etc., and key information can be digitally extracted. For example, the dredging volume data of each cross-section can be extracted from the maintenance dredging project reports of a certain deep-water channel from 1980 to 2020. Combining the cross-section spacing (assuming the spacing between cross-section A and cross-section B is 5000 meters) and the channel width (assuming it is 500 meters), the annual average siltation thickness of each cross-section can be calculated. (For example, if the dredging volume of cross-section A in 1985 was 5 million cubic meters, then the annual average siltation thickness in that year was 5 million cubic meters / (5000 meters * 500 meters) = 2 meters). Then, using the Kriging interpolation algorithm, based on the existing siltation thickness data of each cross-section, a siltation thickness distribution map of the entire target water area (assuming a range of 100 square kilometers) can be generated, with the spatial resolution set to 100 meters × 100 meters, and the inverse distance weighting method (IDW) can be used for supplementary interpolation to improve the accuracy of the spatial distribution. To analyze the spatial characteristics of the siltation distribution, the spatial coefficient of variation of the siltation thickness can be calculated. (For example, if the calculated coefficient of variation of the siltation thickness for the entire area is 6, it indicates that there are significant spatial differences in siltation). The area where the siltation thickness is greater than 3 meters can be delineated as the high-siltation area. (For example, it is found that the annual siltation thickness in a certain area south of the main channel exceeds 3 meters). At the same time, the historical navigational chart can be digitized, and using GIS technology, the offset of the channel centerline in different years can be calculated, and the correlation between the offset and the siltation thickness can be analyzed. (For example, it is found that the southward offset of the channel centerline is positively correlated with the siltation thickness on the south side, and the correlation coefficient is 8), further corroborating the high-siltation area. To analyze the temporal variation trend of the siltation rate, time series analysis can be performed on the annual average siltation thickness data of each cross-section (such as cross-section A). The moving average method (such as a 5-year moving average) can be used to smooth the data, eliminate short-term fluctuations, and observe the long-term trend. Further, the Mann-Kendall trend test method can be used to determine whether there is a significant change trend in the siltation rate. (For example, the siltation rate of cross-section A shows a significant downward trend after 1995, with a significance level p < 0.05), and combined with the wavelet analysis method, the periodic characteristics of the change in the siltation rate can be identified. (For example, it is found that there is a periodic fluctuation of about 10 years in the siltation rate of cross-section A), and 1998 and 2010 are the key years for the change in the siltation rate.

[0098] Step S102, according to the siltation distribution characteristics and the rate change trend, preset the initial positions and quantities of the sensors 212 to ensure coverage of the high-siltation areas and key points.

[0099] Obtain the historical siltation data of the target area and extract the spatial characteristics of the siltation distribution. Analyze the time series data to determine the changing trend pattern of the siltation rate. Combine the spatial characteristics and the changing trend to draw the spatial distribution map of the high-siltation areas. Determine the layout points of the preset sensor 212 according to the distribution characteristics of the high-siltation areas. If the change of the siltation rate is drastic, increase the number of preset sensors 212. Use the spatial density calculation method to optimize the layout scheme of the sensor 212 to ensure the coverage of key points. Implement data collection through the preset scheme and establish a siltation monitoring and analysis model.

[0100] Specifically, first, utilize the historical siltation data, such as the annual siltation volume and siltation range of a certain reservoir in the past 10 years, to draw the siltation distribution isogram and the rate change trend graph through geographic information system software such as ArcGIS. Suppose the analysis result shows that the average annual siltation rate in area A upstream of the reservoir is 5 m / year, the average annual siltation rate in area B downstream is 1 m / year, and in the middle area C, due to the influence of the terrain, there is a local high-value area with a siltation rate of 8 m / year. Based on this, adopt the stratified sampling combined with the Kriging interpolation method to preliminarily determine the layout scheme of the sensor 212: Since the change of the siltation rate in area A is relatively uniform, 1 sensor 212 is arranged per 2 square kilometers; the siltation rate in area B is low and the change is gentle, 1 sensor 212 is arranged per 5 square kilometers; area C is a high-siltation area, 1 sensor 212 is arranged per 5 square kilometers, and additional sensors 212 are added at the position with the largest change gradient of the siltation rate (determined by calculating the rate change rate, for example, the position where the change rate exceeds 2 m / year / km²). At the same time, combined with the numerical simulation of water flow, use software such as HEC-RAS to simulate the water flow velocity and direction under different incoming water conditions, predict the sediment transport path, and add sensors 212 at the predicted main sediment channels, such as point D (coordinates X = 123456, Y = 789012) at a bend of a certain river channel, to capture the siltation situation at key points. In this way, through data and model analysis, it is preliminarily determined to arrange 30 sensors 212, including 5 in area A, 4 in area B, 18 in area C, and 3 at point D and the sediment channels. Through the time series analysis of the siltation rate, for example, use the ARIMA model to predict the change of the siltation rate in the next 5 years, and combine the wavelet analysis to identify the periodic fluctuation of the siltation rate, and dynamically adjust the layout density of the sensor 212 according to the prediction result and the periodic fluctuation characteristics. Automatically execute and analyze using software.

[0101] In step S103, use the measurement range and accuracy parameters of the sensor 212 to calculate the monitoring coverage range and error range of each preset position, adjust the layout position and quantity, and optimize the coverage effect of the monitoring network.

[0102] Obtain the measurement range and accuracy parameters of the sensor 212. For each preset position, use the spatial coverage algorithm to calculate the monitoring coverage range. According to the accuracy parameters, use the error propagation model to calculate the error range of each preset position. Determine whether the monitoring coverage range meets the preset threshold. If not, adjust the layout position and quantity. Use the network optimization algorithm to recalculate the monitoring coverage range and error range for the adjusted layout position and quantity. According to the recalculated results, use the comprehensive evaluation model to judge the monitoring network coverage effect. If the coverage effect does not reach the optimal, return to the step of adjusting the layout position and quantity. Determine the final layout plan and output the optimized monitoring network coverage effect.

[0103] Specifically, obtaining the measurement range and accuracy parameters of sensor 212 is the crucial first step in optimizing the layout plan. Taking a certain type of acoustic Doppler current profiler (ADCP) as an example, its measurement range can reach 100 meters and the accuracy is ±1%. For each preset position, a spatial coverage algorithm is used to calculate the monitoring coverage range. For example, using the Voronoi diagram algorithm, the reservoir area is divided into multiple polygons, and each polygon represents the coverage range of a sensor 212. According to the accuracy parameters, an error propagation model is used to calculate the error range of each preset position. For example, if the measured water depth at a certain position is 50 meters, considering the ±1% accuracy of the ADCP, the error range at this position can be obtained as ±0.5 meters. This step helps to evaluate the data reliability and provides a basis for subsequent decisions. Determine whether the monitoring coverage range meets the preset threshold. If not, adjust the layout positions and quantities. Suppose the preset threshold is 90% coverage rate. Through calculation, it is found that the initial layout plan only reaches 85% coverage rate and needs to be adjusted. It can be considered to add sensors 212 in areas with low coverage rate, or move the positions of existing sensors 212 to expand the coverage range. Using a network optimization algorithm, recalculate the monitoring coverage range and error range for the adjusted layout positions and quantities. For example, use a genetic algorithm to optimize the layout of sensor 212. Through multiple iterations, find the optimal layout plan. Each iteration will evaluate the coverage rate and error range, and gradually optimize until the preset goal is reached. According to the recalculated results, use a comprehensive evaluation model to judge the coverage effect of the monitoring network. A multi-objective evaluation function including factors such as coverage rate, error range, and cost can be constructed. For example, set the weight of the coverage rate to 0.5, the weight of the error range to 0.3, and the weight of the cost to 0.2, and calculate the comprehensive score. If the score does not reach the preset threshold, return to the step of adjusting the layout positions and quantities. This iterative optimization process can not only improve the coverage effect of the monitoring network, but also balance the cost and benefit. For example, through optimization, it may be found that adding a small number of high-precision sensors 212 in some areas is more effective than adding a large number of low-precision sensors 212. This method can maximize the resource utilization efficiency while ensuring the monitoring quality. After determining the final layout plan, output the optimized coverage effect of the monitoring network. This may include the coverage rate being increased to 95%, the average error range being reduced to ±0.3 meters, and at the same time saving 20% of the cost compared to the initial plan. This optimization not only improves the monitoring accuracy, but also enhances the reliability and representativeness of the data, providing a more solid foundation for reservoir sedimentation monitoring and management decisions. Through this series of steps, an efficient and accurate reservoir sedimentation monitoring network can be established. This method not only considers the spatial coverage, but also pays attention to the data quality and cost-benefit, providing reliable technical support for water resources management. The optimized monitoring network can better capture the dynamic changes of sedimentation, provide timely and accurate data support for reservoir operation and sediment management, and thus improve the long-term operation efficiency and safety of the reservoir.

[0104] Step S104: Predict the possible changes in future siltation distribution by simulating the changing trend of siltation rate, and determine whether it is necessary to increase or adjust the layout position and quantity of sensors 212.

[0105] Obtain the change amount in historical siltation data and analyze the trend characteristics therein. Process the trend characteristics using time series analysis methods to obtain simulation values. Match the simulation values with a preset siltation model to calculate predicted values. Generate a siltation distribution map based on the predicted values and identify the characteristic values in the distribution map. Determine the position points and quantity values of the layout points of sensors 212 according to the characteristic values. If the characteristic value exceeds the preset threshold, calculate the required adjustment amount. Combine the adjustment amount with the positional relationship of the existing layout points to evaluate the required value for the layout of sensors 212.

[0106] Specifically, assuming that the historical sedimentation data of a reservoir shows that in the past 10 years, the average sedimentation rate of area A is 15 meters per year, area B is 1 meter per year, and area C is 0.5 meters per year. Now, in this embodiment, the ARIMA model (autoregressive integrated moving average model) in the time series analysis method is used to simulate the sedimentation rate of each region. First, the sedimentation rate data of area A (assuming 14, 16, 15, 17, 14, 15, 16, 18, 15, 14) are analyzed, and the model parameters are determined by calculating the autocorrelation function (ACF) and the partial autocorrelation function (PACF). It is assumed that it is determined to be an ARIMA (1, 0, 1) model, that is, a first-order autoregressive and first-order moving average model. The model parameters are estimated using the least squares method or the maximum likelihood estimation method, and the model equation is obtained: sedimentation rate (t) = 6 * sedimentation rate (t-1) + 2 * error (t-1) + error (t) + 15. Similarly, a model is established for the data of areas B and C. Next, the established ARIMA model is used to predict the sedimentation rate in the next five years. It is assumed that the predicted values ​​of area A in the next five years are: 16 meters, 17 meters, 18 meters, 17 meters, and 16 meters. Corresponding predictions are also made for areas B and C. The predicted sedimentation rate data is input into a two-dimensional water and sediment transport mathematical model based on finite elements or finite differences. The model takes into account factors such as water flow, sediment transport, and riverbed deformation, and simulates the sediment transport and deposition process in the reservoir through numerical calculations. It is assumed that the model calculation results show that the sedimentation thickness in area A will increase significantly due to the increase in the sedimentation rate in the future. Then, the cumulative sedimentation amount in each area in the next five years is calculated, and a sedimentation thickness distribution map is generated. Compared with the current sensor 212 distribution map (assuming that there are 2 sensors 212 in area A, 3 in area B, and 2 in area C), it is found that the number of sensors 212 in area A is relatively small relative to its predicted sedimentation amount, and the distribution may not cover the area with severe sedimentation. Therefore, the system automatically generates a report, adds one sensor 212 in area A, and adjusts the position of one of the sensors 212 from the original coordinates (x1, y1) to (x2, y2) to more accurately monitor the siltation changes. At the same time, the system synchronizes the sensor 212 adjustment information to the database and updates the sensor 212 distribution map on the visualization interface.

[0107] Step S105, using the cluster analysis method in the machine learning algorithm to cluster the historical siltation data, identify the main patterns and changing laws of siltation distribution, and assist in optimizing the sensor 212 deployment plan.

[0108] Obtain the original dataset from the historical sedimentation data, perform preprocessing operations on the dataset, remove noise and standardize the data scale. Use the K-means clustering algorithm to perform clustering analysis on the processed data, and select the Euclidean distance as the distance metric standard. Determine the number of clustering centers according to the data characteristics, and generate the sedimentation distribution map and the change rate statistical results. If the clustering results show significant regional differences in the data distribution, adjust the layout position of sensor 212. By optimizing the layout points, improve the monitoring coverage of sensor 212 for sedimentation data. Generate the distribution map of sensor 212 according to the final layout plan to achieve efficient monitoring.

[0109] Specifically, it is assumed that there is a set of historical sedimentation data in this embodiment, which records the monthly sedimentation thickness (unit: cm) of 10 different locations in a reservoir in the past 5 years. The data is stored in a CSV file named "sediment.csv", and the file contains four columns: "location ID", "year", "month", and "sedimentation thickness". In order to identify the sedimentation distribution pattern and optimize the layout of sensor 212, the K-means clustering algorithm is used in this embodiment. First, the data is read using Python's Pandas library, and the data is preprocessed. The "year" and "month" are merged into timestamps to form a new feature "year and month". Then, a pivot table is constructed with "location ID" as the row, "year and month" as the column, and "sedimentation thickness" as the value, and missing values ​​are filled with 0. Next, the KMeans class in the Scikit-learn library is used for cluster analysis. Considering that there may be 3-5 main types of reservoir sedimentation patterns, the number of clusters n_clusters is set to 3, 4, and 5 in this embodiment for trial, and the silhouette coefficient under different numbers of clusters is calculated. For example, when n_clusters=4, the calculated silhouette coefficient is 65, which is higher than the results when n_clusters=3 (52) and n_clusters=5 (48), indicating that the best effect is achieved when the number of clusters is 4. Through cluster analysis, in this embodiment, 10 positions are divided into 4 groups: Group 1 includes positions 1, 5, and 8, Group 2 includes positions 2 and 6, Group 3 includes positions 3, 7, and 9, and Group 4 includes positions 4 and 10. By observing the curve of the siltation thickness of the positions in each group over time, it is found that the average siltation thickness of Group 1 is the largest and shows obvious seasonal fluctuations, the siltation thickness of Group 2 is low and changes slowly, and the siltation thickness and change trend of Group 3 and Group 4 are between the two. Based on the clustering results, in order to more effectively monitor the siltation of the reservoir, in this embodiment, a representative position is selected in each group to deploy the sensor 212: Group 1 selects position 5 (the most representative change in siltation thickness), Group 2 selects position 2, Group 3 selects position 9, and Group 4 selects position 4. In this way, the main siltation patterns can be covered by four sensors 212, and the siltation of the entire reservoir can be effectively monitored. Compared with the original deployment of sensors 212 at 10 locations, resources are saved and monitoring efficiency is improved. At the same time, the groupby function of Pandas is used to calculate the average and standard deviation of the siltation thickness of each group, and these statistical results are associated with the deployment location of the sensor 212, and written into a new file "sensor_location.csv", which contains four columns: "Group ID", "Representative location ID", "Average siltation thickness", and "Standard deviation of siltation thickness", which is convenient for subsequent analysis and decision-making.

[0110] Step S106: Establish a relationship model between the siltation rate and time through the regression analysis method in the machine learning algorithm, predict the change trend of the future siltation rate, and provide a basis for dynamically adjusting the layout of sensor 212.

[0111] Obtain the rate values on the historical time axis, and establish a relational expression between the rate values and the time axis using the linear regression method. Calculate the predicted values according to the relational expression to determine the change amount of the rate values. Obtain the position information of the layout points of sensor 212, and calculate the adjustment amount in combination with the predicted values. Judge the relationship between the change amount and the preset threshold. If the change amount exceeds the threshold, update the position information of the layout points. Recalculate the adjustment amount according to the updated layout point information to determine a new layout plan for sensor 212. Classify the adjustment amount using the decision tree algorithm to judge the dynamic index. Optimize the model quantity according to the dynamic index and output the final layout plan for sensor 212.

[0112] Specifically, assume that the sedimentation rate data for the past 10 years have been obtained through some means, measured once a year, and the data (unit: cm / year) are: 0, 2, 5, 9, 2, 4, 7, 0, 2, 4. To establish a relationship model between the sedimentation rate and time and predict future trends, a linear regression analysis method can be used. First, number the years. For example, 2014 is 1, 2015 is 2, and so on, and 2023 is 10. Then, take the year as the independent variable (x) and the sedimentation rate as the dependent variable (y), and use the Scikit-learn library in Python to construct a linear regression model. The specific implementation is as follows: import `LinearRegression` from `sklearn.linear_model`, create a model instance `model = LinearRegression()`, and use `model.fit(X, y)` for model training, where X is a two-dimensional array composed of years `[[1], [2], [3], [4], [5], [6], [7], [8], [9],

[10] ]`, and y is a one-dimensional array composed of sedimentation rates `[0, 2, 5, 9, 2, 4, 7, 0, 2, 4]`. After training, obtain the slope through `model.coef_` and the intercept through `model.intercept_`. Assume that the obtained slope is 25 and the intercept is 75, then the linear regression equation is y = 25x + 75. To predict the sedimentation rate for the next 3 years, substitute the years 11, 12, and 13 into the equation respectively, and the predicted values are 5 cm / year, 75 cm / year, and 0 cm / year respectively. According to the prediction results and combined with historical data analysis, the sedimentation rate shows an increasing trend year by year, and the growth rate remains basically stable. Therefore, in the layout of sensor 212, these predicted values can be used as a reference. For example, if sensor 212 needs to be maintained or replaced when the sedimentation rate reaches 0 cm / year, then it can be estimated that the corresponding operation will be carried out around the 13th year. At the same time, to ensure the accuracy of the model, new sedimentation rate data need to be obtained regularly (such as every six months or one year), the model needs to be retrained, the model parameters need to be updated, and the layout strategy of sensor 212 needs to be dynamically adjusted according to the new prediction results, such as adjusting the position or replacement cycle of sensor 212.

[0113] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art in the relevant technical field can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

[0114] It should be noted that in the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more; the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. At the same time, in the description of the present invention, unless otherwise clearly specified and defined, the terms "connected" and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0115] The above content is only the preferred embodiment of the present invention. For those of ordinary skill in the art, according to the idea of the present technical content, many changes can be made in the specific implementation manner and application scope. As long as these changes do not depart from the concept of the present invention, they all fall within the protection scope of this patent.

Claims

1. A floating monitoring work platform for light wave water environment, characterized by: include: A water pipe, wherein a water suction head is installed at the first end of the water pipe, and a water suction end of the water suction head has a filter screen; a water pump, wherein an input end of the water pump is connected to the second end of the water pipe and is used to pump water through the water pump; A water pipe release device, the water pipe release device having a slow-motion rotating storage device, the main body of the water pipe being coiled and stored on the slow-motion rotating storage device; A flow velocity sensor, the monitoring end of which is installed on the water pipe, and the flow velocity sensor is used to detect the flow velocity of water in the water pipe; The sensor is installed on the water pipe and the distance from the water suction head is the preset height of the sensor from the underwater silt.

2. The floating monitoring work platform for light wave water environment according to claim 1 is characterized by: The water pipe is connected to the water pump input end via a sealing bearing.

3. The floating monitoring work platform for light wave water environment according to claim 2 is characterized by: The water pipe release device comprises: Rotating power unit; An output shaft, the output shaft is connected to the output end of the rotary power device, and the output shaft is vertically arranged; A support plate, wherein the upper end of the output shaft is connected to the rotation center of the support plate; A limit plate, the limit plate is installed above the supporting plate, and a hole is provided on the limit plate for the water pipe to pass through; The water pump is installed above the limiting plate.

4. The floating monitoring work platform for light wave water environment according to claim 1 is characterized by: A group of water pipe deviation correcting rollers for guiding the water pipe to move vertically downward are also arranged on the outer side of the water pipe releasing device.

5. The floating monitoring work platform for light wave water environment according to claim 1 is characterized by: The water suction head includes a water suction tray and several branch pipes. The water suction tray is provided with no less than 2 water suction holes. A filter screen is provided inside each water suction hole. The first ends of several branch pipes are respectively connected to the water suction holes, and the second ends of the branch pipes are connected to the water pipe after being collected.

6. The floating monitoring work platform for light wave water environment according to any one of claims 1 to 5, characterized in that: The method of using the floating monitoring work platform for light wave water environment is as follows: Install the water suction head on the water pipe, connect the second end of the water pipe to the input end of the water pump, install the sensor on the water pipe and space it from the water suction head by a predetermined distance, place the water suction head under water, and complete the preparation work; Turn the water pipe release device to slowly release the water pipe, turn on the water pump and the flow rate sensor at the same time. When the flow rate sensor detects that the water flow rate in the water pipe is less than the threshold, control the water pipe release device to stop releasing the water pipe. At this time, the suction head contacts the silt, the silt blocks the water suction hole, the water flow rate in the water pipe decreases, and the sensor reaches a predetermined distance from the bottom of the water.

7. A hydrological monitoring method, using the floating monitoring work platform for light wave water environment as claimed in any one of claims 1 to 5, characterized in that: The method comprises: Obtain historical sedimentation data of the target waters, analyze the spatial characteristics of sedimentation distribution and the temporal variation trend of sedimentation rate, and determine the high-incidence areas of sedimentation and the key points of rate change; According to the distribution characteristics of siltation and the trend of rate change, the initial location and number of sensors are preset to ensure coverage of high-incidence areas and key points; Using the sensor measurement range and accuracy parameters, calculate the monitoring coverage and error range of each preset location, adjust the deployment location and quantity, and optimize the coverage effect of the monitoring network; By simulating the trend of sedimentation rate changes, the possible changes in sedimentation distribution in the future can be predicted to determine whether it is necessary to increase or adjust the location and number of sensors; The cluster analysis method in the machine learning algorithm is used to cluster the historical sedimentation data, identify the main patterns and change laws of sedimentation distribution, and assist in optimizing the sensor deployment plan; Through the regression analysis method in the machine learning algorithm, a relationship model between the sedimentation rate and time is established to predict the changing trend of the sedimentation rate in the future, providing a dynamic adjustment basis for the deployment of sensors.

8. The hydrological monitoring method according to claim 7, characterized in that: The above-mentioned acquisition of historical sedimentation data of the target waters, analysis of the spatial characteristics of sedimentation distribution and the temporal variation trend of sedimentation rate, and determination of high-incidence areas of sedimentation and key points of rate variation include: Obtain historical sedimentation data of the target water area and define the dataset boundary based on the water area; Using spatial analysis methods, the spatial characteristics of siltation distribution are calculated and spatial distribution maps are generated; By using the time analysis method, the time variation trend of the sedimentation rate is calculated and a time trend graph is generated; Combined with the spatial distribution map, the boundaries and locations of high-incidence areas of siltation can be determined; According to the time trend chart, determine the key time points of sedimentation rate change; Integrate high-incidence areas and key time points to generate a time series distribution map of high-incidence areas of siltation; Based on the time series distribution map, a prediction model for high-incidence areas of siltation is established; According to the distribution characteristics of siltation and the rate change trend, the initial position and number of sensors are preset to ensure coverage of high-incidence areas and key points, including: Obtain historical sedimentation data of the target area and extract the spatial characteristics of sedimentation distribution; Analyze time series data to determine trend patterns in sedimentation rates; Combine spatial characteristics and changing trends to draw a spatial distribution map of high-incidence areas of siltation; Determine the preset sensor deployment points based on the distribution characteristics of high-incidence areas; If the sedimentation rate changes dramatically, increase the number of preset sensors; Use spatial density calculation methods to optimize sensor deployment plans and ensure coverage of key points; Data collection is implemented through preset plans, and a sedimentation monitoring and analysis model is established.

9. The hydrological monitoring method according to claim 7, characterized in that: The sensor measurement range and accuracy parameters are used to calculate the monitoring coverage and error range of each preset location, adjust the deployment location and quantity, and optimize the coverage effect of the monitoring network, including: Obtain the measurement range and accuracy parameters of the sensor, and use the spatial coverage algorithm to calculate the monitoring coverage for each preset location; According to the accuracy parameter, the error propagation model is used to calculate the error range of each preset position; Determine whether the monitoring coverage meets the preset threshold. If not, adjust the deployment location and quantity; Adopt network optimization algorithm to recalculate monitoring coverage and error range based on adjusted deployment locations and quantities; Based on the recalculated results, a comprehensive evaluation model is used to judge the coverage effect of the monitoring network; If the coverage effect is not optimal, return to the step of adjusting the layout position and quantity; Determine the final deployment plan and output the optimized monitoring network coverage effect.

10. The hydrological monitoring method according to claim 7, characterized in that: The cluster analysis method in the machine learning algorithm is used to cluster the historical sedimentation data, identify the main patterns and change rules of sedimentation distribution, and assist in optimizing the sensor deployment plan, including: Obtain the original data set from the historical sedimentation data, perform preprocessing operations on the data set, remove noise and standardize the data scale; The K-means clustering algorithm was used to perform cluster analysis on the processed data, and the Euclidean distance was selected as the distance metric; Determine the number of cluster centers based on data characteristics, generate silt distribution diagrams and change rate statistics; If the clustering results show that there are significant regional differences in data distribution, adjust the sensor layout; Improve the coverage of sensors for siltation data monitoring by optimizing the deployment points; Generate a sensor distribution map based on the final deployment plan to achieve efficient monitoring; The regression analysis method in the machine learning algorithm is used to establish a relationship model between the sedimentation rate and time, predict the change trend of the sedimentation rate in the future, and provide a dynamic adjustment basis for the sensor deployment, including: Obtain the rate value on the historical time axis, and use the linear regression method to establish the relationship between the rate value and the time axis; Calculate the predicted value based on the relationship and determine the change in the rate value; Obtain the location information of the sensor deployment point and calculate the adjustment amount based on the predicted value; Determine the relationship between the change amount and a preset threshold value, and if the change amount exceeds the threshold value, update the location information of the deployment point; Recalculate the adjustment amount according to the updated layout point information and determine a new sensor layout plan; The decision tree algorithm is used to classify the adjustment amount and determine the dynamic index; Optimize the model quantity according to the dynamic indicators and output the final sensor layout plan.

Images