A reservoir water level real-time monitoring and early warning system and method based on the Internet of Things

Abstract

The application provides a reservoir water level real-time monitoring and early warning system and method based on Internet of Things, which extracts credible water level time sequence information from water level monitoring data of a target reservoir dam body, determines potential risk intensity of the target reservoir dam body under water level change according to a preset sliding time window and the credible water level time sequence information, inputs the potential risk intensity into a preset water level early warning unit, synchronously accesses a reservoir capacity-pressure distribution map derived in real time by a hydrological model, and determines a safe bearing boundary of the target reservoir dam body structure under the current water level according to the reservoir capacity-pressure distribution map, determines a water level grading early warning value of the target reservoir dam body under the current water level according to the safe bearing boundary and the potential risk intensity, and sends a water level grading early warning signal of the target reservoir dam body to a reservoir management terminal based on the water level grading early warning value. The technical scheme provided by the application can perform water level grading early warning under time-varying risk caused by cumulative damage of a reservoir dam body structure.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water level early warning, and more particularly to a reservoir water level real-time monitoring and early warning system and method based on Internet of Things. BACKGROUND

[0002] Under the background of global climate change, extreme weather events are becoming more frequent, and abnormal changes in water level have become a key factor in causing floods, waterlogging and other disasters. The traditional manual monitoring of water level is inefficient and lacks real-time performance, making it difficult to meet the current demand for precise control of water level changes. In addition, the contradiction between water supply and demand is prominent, and rational allocation of water resources is imminent. In this case, water level early warning emerges as the times require. Water level early warning integrates sensing, communication, data analysis and other technologies, can monitor water level in real time and accurately, and timely issue warnings, providing strong support for flood control and disaster prevention, and scientific management of water resources, greatly reducing disaster losses.

[0003] In existing water level early warning, water level early warning is mainly based on sensors, communication, data analysis and other technologies. Water level sensors, as front-end devices, collect water level data in real time according to different principles. The sensors transmit the collected data to the data processing center through wired or wireless communication. The data center processes the data, compares the real-time water level with the pre-set threshold value such as warning water level, and triggers the early warning mechanism as soon as the water level reaches or exceeds the threshold value. However, in real-time monitoring and early warning of reservoir water level, early warning is mainly dependent on static water level threshold or instantaneous water level value of a single data source, lacking dynamic analysis of the coupling relationship between water level time sequence change characteristics and dam structure resistance decay, making it impossible to effectively identify the time-varying risk caused by cumulative damage of reservoir dam structure under dynamic water level change, and thus leading to a decrease in the accuracy of water level grading early warning. Therefore, how to perform water level grading early warning under the time-varying risk caused by cumulative damage of reservoir dam structure has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a reservoir water level real-time monitoring and early warning system and method based on Internet of Things, which can perform water level grading early warning under the time-varying risk caused by cumulative damage of reservoir dam structure.

[0005] In a first aspect, the present application provides a reservoir water level real-time monitoring and early warning method based on Internet of Things, comprising the following steps:

[0006] Collecting water level monitoring data of the target reservoir dam, and transmitting the water level monitoring data to an edge computing node through an Internet of Things communication network;

[0007] extracting, by the edge computing node, trusted water level time sequence information from the water level monitoring data, and determining potential risk intensity of the target reservoir dam under water level change according to a preset sliding time window in combination with the trusted water level time sequence information;

[0008] inputting the potential risk intensity into a preset water level early warning unit, the water level early warning unit synchronously accessing a reservoir storage capacity-pressure distribution map derived in real time by a hydrological model, and determining a safe bearing boundary of the target reservoir dam structure under a current water level according to the reservoir storage capacity-pressure distribution map;

[0009] performing structural pressure bearing limit analysis on the target reservoir dam according to the safe bearing boundary in combination with the potential risk intensity, to obtain a water level grading early warning value of the target reservoir dam under the current water level;

[0010] based on the water level grading early warning value, sending, by an Internet of Things communication network, a water level grading early warning signal of the target reservoir dam to a reservoir management terminal.

[0011] In some embodiments, extracting, by the edge computing node, trusted water level time sequence information from the water level monitoring data specifically includes:

[0012] the edge computing node receives water level monitoring data transmitted by an Internet of Things communication network, and pre-processes water level monitoring graphs in the water level monitoring data to obtain a pre-processed water level monitoring graph set;

[0013] extracting water level values corresponding to each time node from the pre-processed water level monitoring graph set to form initial water level time sequence data;

[0014] performing completion processing on the initial water level time sequence data by using a time sequence interpolation algorithm to generate a complete water level time sequence;

[0015] performing credibility evaluation on the complete water level time sequence, and screening out time sequence segments that satisfy a preset credibility threshold to form trusted water level time sequence information.

[0016] In some embodiments, determining potential risk intensity of the target reservoir dam under water level change according to a preset sliding time window in combination with the trusted water level time sequence information specifically includes:

[0017] based on a preset sliding time window, slidingly intercepting the trusted water level time sequence information to obtain a plurality of window water level time sequence segments;

[0018] calculating a water level change rate and a water level fluctuation amplitude of each window water level time sequence segment, and further generating a window feature parameter of each window water level time sequence segment;

[0019] inputting the window feature parameter into a preset risk assessment model to obtain a window risk value corresponding to each window water level time sequence segment;

[0020] According to all the window risk values, the potential risk intensity of the target reservoir dam under water level change is determined.

[0021] In some embodiments, the potential risk intensity is input into a preset water level warning unit, and the water level warning unit synchronously accesses a reservoir capacity-pressure distribution map derived in real time by a hydrological model, specifically including:

[0022] The preset water level warning unit receives the potential risk intensity and calls a hydrological model interface to obtain current hydrological parameter data;

[0023] The hydrological model is driven based on the current hydrological parameter data to perform reservoir capacity-pressure field simulation, and a reservoir capacity-pressure distribution map is output;

[0024] The reservoir capacity-pressure distribution map is synchronously accessed into the preset water level warning unit.

[0025] In some embodiments, according to the reservoir capacity-pressure distribution map, the safety bearing boundary of the target reservoir dam structure under the current water level is determined, specifically including:

[0026] Actual pressure values of each structural unit of the target reservoir dam are extracted from the reservoir capacity-pressure distribution map to generate a structural unit pressure data set;

[0027] A unit bearing threshold matrix is established by calling a dam material mechanics parameter library to match the compressive strength threshold of each structural unit;

[0028] The pressure safety margin of each structural unit is determined according to the structural unit pressure data set and the unit bearing threshold matrix;

[0029] The safety bearing boundary of the target reservoir dam structure under the current water level is determined based on the pressure safety margin of each structural unit.

[0030] In some embodiments, the pressure safety margin of each structural unit is determined according to the structural unit pressure data set and the unit bearing threshold matrix, specifically including:

[0031] The structural unit pressure data set and the unit bearing threshold matrix are matched to establish a pressure-threshold correlation pair corresponding to each structural unit;

[0032] The bearing threshold and the actual pressure value of the corresponding structural unit are calculated based on the pressure-threshold correlation pair to obtain the pressure safety margin of each structural unit.

[0033] In some embodiments, a water level monitoring data of the target reservoir dam is collected by a drone provided with a camera.

[0034] In a second aspect, the application provides a reservoir water level real-time monitoring and early warning system based on the Internet of Things, which is used to execute a reservoir water level real-time monitoring and early warning method based on the Internet of Things. The system comprises:

[0035] A collection module is configured to collect water level monitoring data of a target reservoir dam body and transmit the water level monitoring data to an edge computing node through an Internet of Things communication network.

[0036] A processing module is configured to extract credible water level time series information from the water level monitoring data by the edge computing node, and determine potential risk intensity of the target reservoir dam body under water level change according to a preset sliding time window and the credible water level time series information.

[0037] The processing module is further configured to input the potential risk intensity into a preset water level early warning unit, the water level early warning unit is synchronously connected to a reservoir capacity-pressure distribution map derived in real time by a hydrological model, and determines a safe bearing boundary of the target reservoir dam body structure under a current water level according to the reservoir capacity-pressure distribution map.

[0038] The processing module is further configured to perform a structure pressure-bearing limit analysis on the target reservoir dam body according to the safe bearing boundary and the potential risk intensity, and obtain a water level grading early warning value of the target reservoir dam body under the current water level.

[0039] An execution module is configured to send a water level grading early warning signal of the target reservoir dam body to a reservoir management terminal through the Internet of Things communication network based on the water level grading early warning value.

[0040] In a third aspect, the application provides a computer device, which comprises a memory and a processor. The memory stores a code, and the processor is configured to acquire the code and execute the above-mentioned reservoir water level real-time monitoring and early warning method based on the Internet of Things.

[0041] In a fourth aspect, the application provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned reservoir water level real-time monitoring and early warning method based on the Internet of Things is realized.

[0042] The technical scheme provided by the embodiments of the application has the following beneficial effects:

[0043] The application provides a reservoir water level real-time monitoring and early warning system and method based on the Internet of Things, which comprises the following steps: collecting water level monitoring data of a target reservoir dam body, and transmitting the water level monitoring data to an edge computing node through an Internet of Things communication network; extracting credible water level time sequence information from the water level monitoring data by the edge computing node, and determining the potential risk intensity of the target reservoir dam body under water level change according to a preset sliding time window combined with the credible water level time sequence information; further inputting the potential risk intensity into a preset water level early warning unit, synchronously accessing a reservoir capacity-pressure distribution map derived in real time by a hydrological model by the water level early warning unit, and determining the safe bearing boundary of the target reservoir dam body structure under the current water level according to the reservoir capacity-pressure distribution map; then, performing structural pressure limit analysis on the target reservoir dam body according to the safe bearing boundary combined with the potential risk intensity, to obtain a water level grading early warning value of the target reservoir dam body under the current water level; and finally, based on the water level grading early warning value, transmitting a water level grading early warning signal of the target reservoir dam body to a reservoir management terminal through the Internet of Things communication network.

[0044] It can be seen that the application can perform water level grading early warning under the time-varying risk caused by the cumulative damage of the reservoir dam body structure. First, the water level monitoring data is collected and transmitted through the Internet of Things, realizing the real-time monitoring and efficient data transmission, and providing timely and accurate basic data for subsequent analysis. Second, the edge computing node extracts credible water level time sequence information and determines the potential risk intensity combined with the sliding time window, which not only reduces the data transmission amount and network load, but also captures the water level change trend through time sequence analysis, making the risk intensity evaluation more in line with the actual dynamics. Further, the water level early warning unit determines the safe bearing boundary combined with the potential risk intensity and the reservoir capacity-pressure distribution map derived by the hydrological model, associates the abstract risk data with the specific dam body structure stress, realizes the dynamic analysis of the coupling relationship between the water level time sequence change characteristics and the dam body structure resistance attenuation, and further avoids the time-varying risk caused by the cumulative damage of the reservoir dam body structure under the dynamic water level change. Then, the water level grading early warning value is obtained by performing structural pressure limit analysis according to the safe bearing boundary and the potential risk intensity, which closely matches the early warning level with the actual pressure bearing state of the dam body, avoids the limitations of single threshold early warning, and improves the grading early warning accuracy of the reservoir water level. Finally, the grading early warning signal is transmitted to the reservoir management terminal through the Internet of Things, ensuring efficient transmission of early warning information and providing clear decision-making basis for management personnel, improving the timeliness, accuracy and pertinence of reservoir water level monitoring and early warning, and effectively protecting the safety of the reservoir dam body. In summary, the technical scheme provided by the application can perform water level grading early warning under the time-varying risk caused by the cumulative damage of the reservoir dam body structure. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1is an exemplary flow chart of a reservoir water level real-time monitoring and early warning method based on Internet of Things according to some embodiments of the present application;

[0046] Figure 2 is an exemplary flow chart of determining trusted water level time series information according to some embodiments of the present application;

[0047] Figure 3 is an exemplary flow chart of determining a safe bearing boundary according to some embodiments of the present application;

[0048] Figure 4 is a structural schematic diagram of a reservoir water level real-time monitoring and early warning system based on Internet of Things according to some embodiments of the present application;

[0049] Figure 5 is a structural schematic diagram of a computer device for implementing a reservoir water level real-time monitoring and early warning method based on Internet of Things according to some embodiments of the present application. DETAILED DESCRIPTION

[0050] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0051] Reference Figure 1 The figure is an exemplary flow chart of a reservoir water level real-time monitoring and early warning method based on Internet of Things according to some embodiments of the present application, which mainly includes the following steps:

[0052] In step S101, the water level monitoring data of the target reservoir dam body is collected, and the water level monitoring data is transmitted to the edge computing node through the Internet of Things communication network.

[0053] When specifically implemented, the water level monitoring data of the target reservoir dam body can be collected by a drone provided with a camera, and the communication with the edge computing node is established by the Internet of Things communication network to transmit the water level monitoring data to the edge computing node. The water level monitoring data contains water level monitoring graphs at different time nodes, and the water level monitoring graphs contain water level markings and water surface information. Through the determination of the water level monitoring data, data basis can be effectively provided for the water level warning of the target reservoir dam body.

[0054] It should be noted that the edge computing node in the present application refers to a computing node deployed at the edge of the network with data processing, storage and communication capabilities. The edge computing node can process, analyze and filter the raw data collected by the Internet of Things device on site, reduce the amount of data transmission to the cloud, reduce network bandwidth pressure and data transmission delay, and quickly respond to local business needs. It is commonly used in Internet of Things scenarios with high real-time requirements and large data volume.

[0055] In step S102, the edge computing node extracts the trusted water level time series information from the water level monitoring data, and determines the potential risk intensity of the target reservoir dam under water level change according to a preset sliding time window and the trusted water level time series information.

[0056] In some embodiments, with reference to Figure 2 As shown in the figure, which is an exemplary flowchart for determining trusted water level time series information according to some embodiments of the present application, the extraction of the trusted water level time series information by the edge computing node from the water level monitoring data can be implemented by the following steps in the present embodiment:

[0057] In step S1021, the edge computing node receives the water level monitoring data transmitted by the Internet of Things communication network, and pre-processes the water level monitoring graphs in the water level monitoring data to obtain a set of pre-processed water level monitoring graphs;

[0058] In step S1022, the water level values corresponding to each time node are extracted from the set of pre-processed water level monitoring graphs to form initial water level time series data;

[0059] In step S1023, a time series interpolation algorithm is used to complete the initial water level time series data to generate a complete water level time series sequence;

[0060] In step S1024, the complete water level time series sequence is evaluated for trustworthiness, and time series segments that satisfy a preset trustworthiness threshold are selected to form trusted water level time series information.

[0061] In a specific implementation, first, the edge computing node receives water level monitoring data transmitted by an Internet of Things communication network, and filters each water level monitoring graph in the water level monitoring data using a Gaussian filter to obtain a set of preprocessed water level monitoring graphs, the set of preprocessed water level monitoring graphs including a plurality of preprocessed water level monitoring graphs, and the preprocessed water level monitoring graph refers to a water level monitoring graph after filtering processing; second, for each preprocessed water level monitoring graph in the set of preprocessed water level monitoring graphs, the pixel position of a water level line is identified from the preprocessed water level monitoring graph by using an existing edge detection algorithm, and the pixel position is converted into an actual physical height (i.e., a water level value) in combination with image calibration parameters to obtain a water level value of a time node corresponding to the preprocessed water level monitoring graph, and then a water level value of each time node is obtained, all water level values are arranged in chronological order to obtain initial water level time series data, and the initial water level time series data refers to a data sequence formed by arranging water level values corresponding to time nodes in chronological order; then, the initial water level time series data is completed by using a linear interpolation method, that is, for a missing value in the initial water level time series data, a water level value at a missing time is determined by calculating a linear function according to adjacent known water level values and corresponding time intervals, so as to generate a complete water level time series sequence, and the complete water level time series sequence refers to a sequence of water level changes over time after interpolation completion and without missing values; finally, the complete water level time series sequence is evaluated for credibility, the change rate of each data point and an adjacent data point in the complete water level time series sequence is calculated, an effective range of the change rate is set as a credibility judgment standard, time series segments in which change rates of all data points are within the effective range of the change rate are screened out, and credible water level time series information is formed, and the effective range of the change rate can be set according to actual requirements, which is not limited here.

[0062] It should be noted that the credible water level time series information in the present application refers to a time series segment that can reflect the actual water level change, and the credible water level time series information is the core data basis for reservoir water level monitoring and early warning, which can provide accurate and continuous water level change basis for the edge computing node to evaluate the potential risk intensity of the dam body, and ensure that the risk judgment is not biased.

[0063] In some embodiments, the potential risk intensity of a target reservoir dam body under water level change can be determined according to a preset sliding time window and the credible water level time series information by using the following steps:

[0064] The credible water level time series information is intercepted by a preset sliding time window to obtain a plurality of window water level time series segments;

[0065] The water level change rate and the water level fluctuation amplitude of each window water level time series segment are calculated to generate window feature parameters of each window water level time series segment;

[0066] input the window feature parameters into a preset risk assessment model to obtain a window risk value corresponding to each window water level time sequence segment;

[0067] determine the potential risk intensity of the target reservoir dam under water level changes according to all the window risk values.

[0068] In a specific implementation, first, a fixed-length sliding time window is set according to actual requirements, and the sliding time window is moved by a set step in time sequence from the starting time of the credible water level time sequence information, water level data in the time period covered by the window is intercepted after each movement to obtain a plurality of window water level time sequence segments, the window water level time sequence segment refers to a water level data sequence intercepted by the sliding time window; second, the water level change rate and the water level fluctuation amplitude of each window water level time sequence segment are calculated to generate window feature parameters, when the water level change rate is calculated, the difference between the water level values of adjacent time nodes is divided by the corresponding time interval to obtain the local water level change rate of the corresponding time node, and then the average value of all local water level change rates in the corresponding sliding window is taken as the water level change rate of the sliding window, when the water level fluctuation amplitude is calculated, the maximum water level value and the minimum water level value in the sliding window are extracted, and then the difference between the maximum water level value and the minimum water level value is taken as the water level fluctuation amplitude, the water level change rate and the water level fluctuation amplitude jointly constitute the window feature parameters of the corresponding window water level time sequence segment, and then the window feature parameters of each window water level time sequence segment are generated, the window feature parameters refer to quantitative indicators that can reflect the speed of water level change and the size of fluctuation in the window water level time sequence segment; then, the window feature parameters are input into a preset risk assessment model to obtain a window risk value corresponding to each window water level time sequence segment, the risk assessment model can use a multiple linear regression model trained based on historical data, specifically, the water level change rate and the water level fluctuation amplitude in the window feature parameters are taken as input variables of the model, substituted into the regression equation determined by the risk assessment model, and the calculation result of the regression equation is taken as the window risk value of the corresponding window water level time sequence segment, the window risk value refers to a numerical value reflecting the water level risk degree corresponding to a single window water level time sequence segment; finally, the potential risk intensity of the target reservoir dam is determined according to all the window risk values, that is, the weight of the window risk value corresponding to each window water level time sequence segment is given, all the window risk values are calculated by weighted summation, and the calculation result is taken as the potential risk intensity of the target reservoir dam under water level changes, wherein the weight of the window risk value corresponding to each window water level time sequence segment can number the window water level time sequence segments in reverse time order, the most recent window water level time sequence segment is No. 1, and then the time attenuation coefficient between 0 and 1 is set, the weight of No. 1 window is 1 (attenuation coefficient 0 times), the weight of the subsequent window is the attenuation coefficient raised to the power of (window number-1), then all the weights are normalized so that the sum of the weights is 1, and then the weight of the window risk value corresponding to each window water level time sequence segment is obtained.

[0069] It should be noted that the potential risk intensity in the present application refers to a quantitative index for measuring the overall risk degree of the target reservoir dam body in the current water level change process. The prior art calculates the risk by using static data in a fixed time interval, or only considers a single isolated parameter such as water level change rate, which is prone to risk lag due to insufficient data timeliness and single parameter dimension. The present scheme can capture the subtle characteristics of water level changes in different time periods in real time by dynamically intercepting the reliable water level time series information through a preset sliding time window, avoiding the omission of short-term sudden water level fluctuations in a fixed interval, and innovatively combining the water level change rate and fluctuation amplitude to generate window characteristic parameters, which makes up for the defect that a single parameter cannot fully reflect the water level dynamic risk. More importantly, in the weight assignment link, the present scheme discards the extensive methods of equal weight or simple linear weight in the prior art, and adopts dynamic weighting and normalization processing based on time decay coefficient, so that the recent water level data (which can better reflect the current dam body stress state) obtains a higher weight, and the long-term data is reasonably weakened, which avoids the interference of historical data on the current risk assessment and ensures the continuity of risk calculation.

[0070] In step S103, the potential risk intensity is input to a preset water level warning unit, and the water level warning unit synchronously accesses the reservoir capacity-pressure distribution map derived by the hydrological model in real time, and determines the safe bearing boundary of the target reservoir dam structure under the current water level according to the reservoir capacity-pressure distribution map.

[0071] In some embodiments, the potential risk intensity is input to a preset water level warning unit, and the water level warning unit synchronously accesses the reservoir capacity-pressure distribution map derived by the hydrological model in real time, which can be realized by the following steps:

[0072] The preset water level warning unit receives the potential risk intensity and calls the hydrological model interface to obtain the current hydrological parameter data;

[0073] Based on the current hydrological parameter data, the hydrological model is driven to simulate the reservoir capacity-pressure field, and the reservoir capacity-pressure distribution map is output;

[0074] The reservoir capacity-pressure distribution map is synchronously accessed to the preset water level warning unit.

[0075] In a specific implementation, first, the preset water level warning unit receives the potential risk intensity transmitted by the edge computing node, then calls the data source module of the hydrological model through a preset standardized API interface (such as a RESTful interface), and obtains current hydrological parameter data from the data source module. During the acquisition process, the data is integrity checked, and after the abnormal values are removed, a structured parameter data set is formed. The current hydrological parameter data refers to a set of quantitative indicators reflecting the current hydrological state of the reservoir, including but not limited to inflow, outflow, rainfall, evaporation, and dam seepage flow. Then, the hydrological model is driven based on the current hydrological parameter data to simulate the reservoir capacity-pressure field, and the reservoir capacity-pressure distribution map is output. First, the obtained current hydrological parameter data is standardized according to the format required by the hydrological model, and is transmitted to the preprocessing module through the data input interface of the hydrological model. The preprocessing module preprocesses the current hydrological parameter data to form a complete model input data set. Then, the water balance calculation module of the hydrological model calls the built-in water balance equation to calculate the difference between the total inflow and the total outflow in time steps (such as every hour), and obtains the current real-time reservoir capacity value. At the same time, the reservoir capacity value is converted into the corresponding water level height according to the corresponding relationship between the reservoir capacity value and the water level height (determined by the water level-capacity curve of the reservoir, which is fitted by the dam body surveying and hydrological observation data in the early stage). Then, the calculated water level height and dam structure parameters (such as dam length, width, material elastic modulus, and other preset parameters) are input into the structural mechanics analysis submodule of the hydrological model. The structural mechanics analysis submodule uses the finite element analysis method to divide the dam structure into a plurality of unit grids, calculates the water pressure borne by each grid unit based on the principles of fluid statics (the calculation formula is the density of water x gravitational acceleration x the water depth at the unit), and obtains the pressure distribution data of each part of the dam body. After that, the visualization module of the hydrological model reads the reservoir capacity data and pressure distribution data, uses different color gradients to represent the pressure size (such as blue for low pressure and red for high pressure) based on a two-dimensional plan view, superimposes the reservoir contour line and water level line in the graph, and labels the pressure values and corresponding reservoir capacity values of key parts to generate the reservoir capacity-pressure distribution map. The water balance equation is a mathematical formula used to calculate the balance of water quantity of the reservoir, and the finite element analysis method is a numerical calculation method for mechanical analysis by decomposing a complex structure into a finite number of units.

[0076] It should be noted that the reservoir capacity-pressure distribution diagram in the present application refers to a visual graph directly showing the corresponding relationship between the reservoir capacity and the pressure of each part of the dam body. Through determination of the reservoir capacity-pressure distribution diagram, the pressure differences of each region of the dam body under the current reservoir capacity can be directly presented, helping to locate the pressure concentration part. At the same time, the reservoir capacity-pressure distribution diagram can provide core mechanical parameters for the water level warning unit to determine the safe bearing boundary and analyze the structure pressure limit, and can also predict the pressure trend when the reservoir capacity changes. The visual characteristics facilitate managers to quickly grasp the risk points, and provide decision-making reference for formulating preventive measures.

[0077] In some embodiments, with reference to Figure 3 As shown in the figure, the figure is an exemplary flow chart for determining the safe bearing boundary according to some embodiments of the present application. In the present embodiment, the determination of the safe bearing boundary of the target reservoir dam structure under the current water level according to the reservoir capacity-pressure distribution diagram can be realized by the following steps:

[0078] In step S1031, the actual pressure values of each structural unit of the target reservoir dam body are extracted from the reservoir capacity-pressure distribution diagram to generate a structural unit pressure data set;

[0079] In step S1032, the compressive strength threshold of each structural unit is matched by calling the dam body material mechanics parameter library to establish a unit bearing threshold matrix;

[0080] In step S1033, the pressure safety margin of each structural unit is determined according to the structural unit pressure data set and the unit bearing threshold matrix;

[0081] In step S1034, the safe bearing boundary of the target reservoir dam structure under the current water level is determined based on the pressure safety margin of each structural unit.

[0082] In a specific implementation, first, the pressure values corresponding to different color gradients in the reservoir capacity-pressure distribution graph are recognized by a graphic analysis tool OpenCV, and the pressure value of each grid unit is extracted and associated with the corresponding structure unit number in combination with the grid division information of the target reservoir dam structure unit, to form a structure unit pressure data set containing the unit number and the corresponding actual pressure value. The structure unit pressure data set refers to a data set recording the current pressure value borne by each structure unit of the target reservoir dam. The structure unit is the smallest analysis unit formed by pre-dividing the target reservoir dam based on the structure characteristics and stress law of the target reservoir dam. The structure unit can be determined according to actual needs, for example, the structure unit can be set according to the material type of the target reservoir dam structure, which will not be described here. Second, the dam material mechanics parameter library is called, the dam material mechanics parameter library is a database in which the compressive strength design value of the material corresponding to the target reservoir dam is pre-set, and the compressive strength design value of the corresponding material type under the standard working condition is matched from the dam material mechanics parameter library as the compressive strength threshold value according to the material type of each structure unit through a database query statement, and then the compressive strength threshold value of each structure unit is obtained. All the compressive strength threshold values are arranged in the order of spatial distribution of the structure units to form a unit bearing threshold matrix in the form of a two-dimensional matrix. The unit bearing threshold matrix refers to a matrix of the maximum pressure threshold value that can be borne by each structure unit arranged according to the spatial distribution of the dam structure unit. Then, the pressure safety margin of each structure unit is determined according to the structure unit pressure data set and the unit bearing threshold matrix. The pressure safety margin refers to the safety degree value of the structure unit under the action of pressure, which is used to measure the safety reserve of the structure unit. Finally, the safety bearing boundary of the target reservoir dam structure under the current water level is determined based on the pressure safety margin of each structure unit, that is, the pressure safety margins of all structure units are counted, the structure units with the same safety margin are connected to form a safety margin field by using the contour drawing method, and the boundary line in the critical state in the safety margin field is determined according to the preset safety margin critical value (such as zero point), and the area surrounded by the boundary line is taken as the safety bearing boundary of the target reservoir dam structure under the current water level.

[0083] It should be noted that the safety bearing boundary in the present application refers to the limit range boundary of the pressure that the dam body structure can bear under the current water level, which is used to define the safe area and the risk area of the dam body structure. The prior art roughly estimates the safe bearing range based on the overall design of the dam body, without considering the uneven bearing capacity of different structural units due to differences in material, geometric shape and stress environment, which is prone to misjudgment of "overall safety but local overload". Moreover, the boundary is difficult to dynamically adjust with real-time pressure changes. The present scheme innovatively takes "structural unit" as the smallest evaluation unit, extracts the actual pressure value of each unit from the reservoir capacity-pressure distribution diagram, and then obtains the exclusive compressive strength threshold of each unit by matching the dam body material mechanics parameter library, ensuring that the bearing capacity evaluation of each unit is consistent with its real material and working conditions, avoiding the identification deviation of the boundary.

[0084] In some embodiments, determining the pressure safety margin of each structural unit according to the structural unit pressure data set and the unit bearing threshold matrix can be achieved by the following steps:

[0085] Matching the structural unit pressure data set and the unit bearing threshold matrix to establish the corresponding pressure-threshold association pairs of each structural unit;

[0086] Calculating the difference between the bearing threshold and the actual pressure value of the corresponding structural unit based on the pressure-threshold association pairs to obtain the pressure safety margin of each structural unit.

[0087] In specific implementation, first, the actual pressure value and the compressive strength threshold of the same structural unit in the structural unit pressure data set and the unit bearing threshold matrix are associated and bound to form a pressure-threshold association pair indexed by unit number, containing actual pressure value and corresponding bearing threshold. The pressure-threshold association pair refers to the data pair formed by associating the actual pressure value of the same structural unit with its corresponding compressive strength threshold. Second, when calculating the initial pressure safety margin based on the pressure-threshold association pair, the compressive strength threshold in the pressure-threshold association pair is subtracted from the actual pressure value, and the difference obtained is taken as the pressure safety margin of the corresponding structural unit. A positive difference indicates that the unit still has safety reserves, and a negative difference indicates that the unit has exceeded the bearing capacity.

[0088] It should be noted that the pressure safety margin in the present embodiment refers to a quantitative indicator reflecting the actual safety reserves of the structural unit. The pressure safety margin can accurately judge the real-time safety state of a single structural unit, quickly locate the local risk points, and unify the quantitative safety degree of different units, and clearly define the safety imbalance of each area of the dam body.

[0089] In step S104, a structure pressure limit analysis is performed on the target reservoir dam according to the safety bearing boundary and the potential risk intensity, to obtain a water level grading early warning value of the target reservoir dam at the current water level.

[0090] In some embodiments, the structure pressure limit analysis on the target reservoir dam according to the safety bearing boundary and the potential risk intensity, to obtain a water level grading early warning value of the target reservoir dam at the current water level, can be implemented by the following steps:

[0091] A pressure critical interval of the target reservoir dam structure is determined based on the safety bearing boundary;

[0092] The potential risk intensity is mapped to the pressure critical interval to determine an actual pressure position corresponding to the current risk;

[0093] A deviation degree of the actual pressure position from the safety bearing boundary is calculated to generate a structure pressure overrun value of the target reservoir dam;

[0094] According to the structure pressure overrun value and a preset early warning level division rule, a water level grading early warning value of the target reservoir dam at the current water level is determined.

[0095] In a specific implementation, when determining the pressure critical interval of the dam structure based on the safe bearing boundary, the safe region (i.e., a region with a pressure safety margin greater than 0 is regarded as a safe region) and the risk region (i.e., a region with a pressure safety margin less than or equal to 0 is regarded as a risk region) are identified based on the safe bearing boundary, a preset safe buffer range (which can be determined according to the material safety factor in the dam design specification) is extended to the safe region based on the safe bearing boundary, and a preset danger warning range (which can be referred to the risk diffusion distance of the dam after overload in historical accident cases) is extended to the risk region, thereby forming three continuous intervals of the safe region, the buffer region, and the danger region, and further forming the pressure critical interval of the target reservoir dam structure. The pressure critical interval refers to the pressure range interval corresponding to different safety levels divided based on the safe bearing boundary. Second, a corresponding relationship between the potential risk intensity and the pressure value (i.e., a linear fitting can be performed on the corresponding relationship between the potential risk intensity and the equivalent pressure by taking the potential risk intensity as a variable and the equivalent pressure as an independent variable based on the previous test data) is established, the equivalent pressure value corresponding to the current potential risk intensity is calculated according to the corresponding relationship, the equivalent pressure value is substituted into the coordinate system of the pressure critical interval to determine the specific interval position of the equivalent pressure value, and the structural pressure overrun value of the target reservoir dam is obtained. The actual pressure position refers to the specific landing point of the equivalent pressure value corresponding to the current potential risk intensity in the pressure critical interval. Then, the straight-line distance from the actual pressure position to the safe bearing boundary is calculated by using the Euclidean distance, the ratio between the straight-line distance and the total length of the pressure critical interval is calculated, the deviation degree of the actual pressure position from the safe bearing boundary is obtained, and the normalized deviation degree is taken as the structural pressure overrun value of the target reservoir dam. The structural pressure overrun value refers to the quantitative value of the actual pressure position exceeding the safe bearing boundary. Finally, when determining the water level classification warning value according to the structural pressure overrun value and the preset warning level division rule, the structural pressure overrun value is first mapped to a number between 0 and 1 by using the existing normalization, the preset warning level rule (i.e., the water level classification warning value corresponding to the structural pressure overrun value in (0, 0.25] is 1, corresponding to the blue warning, the water level classification warning value corresponding to the structural pressure overrun value in (0.25, 0.5] is 2, corresponding to the yellow warning, the water level classification warning value corresponding to the structural pressure overrun value in (0.5, 0.75] is 3, corresponding to the orange warning, and the water level classification warning value corresponding to the structural pressure overrun value in (0.75, 1) is 4, corresponding to the red warning) is queried, and the corresponding water level classification warning value is determined according to the range of the current structural pressure overrun value between 0 and 1.

[0096] It should be noted that the water level grading early warning value in the present application refers to the specific numerical value of the safety risk level of the reservoir dam body at the current water level. The water level grading early warning value can divide the dam body risk into different levels, accurately match the response measures with the risk, avoid the disadvantages of single threshold early warning, provide a unified standard for multi-department cooperation, clarify the responsibilities of each department, guide the scientific regulation of water level, and balance safety and water resource utilization.

[0097] In step S105, based on the water level grading early warning value, the water level grading early warning signal of the target reservoir dam body is sent to the reservoir management terminal by the Internet of Things communication network.

[0098] In some embodiments, based on the water level grading early warning value, the water level grading early warning signal of the target reservoir dam body can be sent to the reservoir management terminal by the Internet of Things communication network by the following steps:

[0099] The water level grading early warning value is analyzed, and the corresponding water level grading early warning signal is matched;

[0100] The water level grading early warning signal is sent to the reservoir management terminal by the Internet of Things communication network.

[0101] In specific implementation, first, the water level grading early warning value is analyzed, and the corresponding water level grading early warning signal and transmission protocol are matched, the water level grading early warning signal includes blue, yellow, orange, and red early warning signals; then, the water level grading early warning signal is sent to the reservoir management terminal by the Internet of Things communication network.

[0102] It should be noted that the reservoir management terminal in the present application is a special hardware device or a software and hardware integrated system for daily operation monitoring, data receiving and processing, and early warning response operation of the reservoir, which is usually deployed in the core control area of the reservoir management station, the central control room, etc.

[0103] In addition, another aspect of the present application, in some embodiments, the present application provides a real-time monitoring and early warning system for reservoir water level based on Internet of Things, referring to Figure 4 The figure is a structure schematic diagram of the real-time monitoring and early warning system for reservoir water level based on Internet of Things according to some embodiments of the present application, which includes a collection module 201, a processing module 202, and an execution module 203, which are described as follows:

[0104] The collection module 201 is mainly used for collecting the water level monitoring data of the target reservoir dam body, and transmitting the water level monitoring data to the edge computing node through the Internet of Things communication network;

[0105] The processing module 202 is mainly used for extracting trusted water level time sequence information from the water level monitoring data by the edge computing node, and determining potential risk intensity of the target reservoir dam under water level change according to a preset sliding time window and the trusted water level time sequence information.

[0106] The processing module 202 is also used for inputting the potential risk intensity into a preset water level early warning unit, synchronously accessing a reservoir capacity-pressure distribution map derived in real time by a hydrological model, and determining a safe bearing boundary of the target reservoir dam structure under the current water level according to the reservoir capacity-pressure distribution map.

[0107] In addition, the processing module 202 is also used for performing structure pressure limit analysis on the target reservoir dam according to the safe bearing boundary and the potential risk intensity, to obtain a water level grading early warning value of the target reservoir dam under the current water level.

[0108] The execution module 203 is mainly used for sending a water level grading early warning signal of the target reservoir dam to a reservoir management terminal by an Internet of Things communication network based on the water level grading early warning value.

[0109] In addition, the present application also provides a computer device, which comprises a memory and a processor, the memory stores code, and the processor is configured to acquire the code and execute the above-mentioned Internet of Things-based real-time reservoir water level monitoring and early warning method.

[0110] In some embodiments, referring to Figure 5 The figure is a structural schematic diagram of a computer device for implementing the Internet of Things-based real-time reservoir water level monitoring and early warning method according to some embodiments of the present application. The Internet of Things-based real-time reservoir water level monitoring and early warning method in the above-mentioned embodiments can be implemented by the computer device shown in the figure, which comprises at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304. Figure 5

[0111] The processor 301 can be a general central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more circuits for controlling the execution of the Internet of Things-based real-time reservoir water level monitoring and early warning method in the present application.

[0112] The communication bus 302 can be used for transmitting information between the above-mentioned components.

[0113] ​The memory 303 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magneto-optical disk, a magnetic disk or other magnetic storage device, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto. The memory 303 can exist independently of the processor 301 and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301.

[0114] The memory 303 is configured to store program codes for implementing the solutions of the present application, and the processor 301 is configured to control the execution of the program codes stored in the memory 303. The program codes can include one or more software modules. The determination of the reservoir water level real-time monitoring and early warning method based on the Internet of Things in the above embodiments can be implemented by one or more software modules in the program codes of the processor 301 and the memory 303.

[0115] The communication interface 304 is configured to communicate with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc., using any transceiver-like device.

[0116] In specific implementations, as an example, the computer device can include multiple processors, each of which can be a single-CPU processor or a multi-CPU processor. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0117] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0118] In addition, the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize the above-mentioned reservoir water level real-time monitoring and early warning method based on Internet of Things.

[0119] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all the preferred embodiments and all the changes and modifications falling within the scope of the present application.

[0120] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A real-time monitoring and early warning method for reservoir water level based on Internet of Things, characterized in that, The method comprises the following steps: Collecting water level monitoring data of a target reservoir dam body, and transmitting the water level monitoring data to an edge computing node through an Internet of Things communication network; Extracting credible water level time sequence information from the water level monitoring data by the edge computing node, and determining the potential risk intensity of the target reservoir dam body under water level changes according to a preset sliding time window combined with the credible water level time sequence information; Inputting the potential risk intensity into a preset water level warning unit, the water level warning unit synchronously accessing a reservoir capacity-pressure distribution map derived in real time by a hydrological model, and determining the safety bearing boundary of the target reservoir dam body structure under the current water level according to the reservoir capacity-pressure distribution map; Performing structural bearing limit analysis on the target reservoir dam body according to the safety bearing boundary combined with the potential risk intensity, to obtain a water level grading warning value of the target reservoir dam body under the current water level; Based on the water level grading warning value, sending a water level grading warning signal of the target reservoir dam body to a reservoir management terminal through the Internet of Things communication network; Wherein, the structural bearing limit analysis on the target reservoir dam body according to the safety bearing boundary combined with the potential risk intensity to obtain the water level grading warning value of the target reservoir dam body under the current water level is realized by the following steps: Drawing a bearing critical interval of the target reservoir dam body structure with the safety bearing boundary as the benchmark; Mapping the potential risk intensity to the bearing critical interval to determine the actual bearing position corresponding to the current risk; Calculating the deviation degree of the actual bearing position and the safety bearing boundary to generate a structural bearing overrun value of the target reservoir dam body; According to the structural bearing overrun value and a preset warning level division rule, determining the water level grading warning value of the target reservoir dam body under the current water level. 2.The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 1, characterized in that, The edge computing node extracts credible water level time sequence information from the water level monitoring data, which specifically includes: The edge computing node receives water level monitoring data transmitted by the Internet of Things communication network, and pre-processes the water level monitoring graph in the water level monitoring data to obtain a pre-processed water level monitoring graph set; Extracting water level values corresponding to each time node from the pre-processed water level monitoring graph set to form initial water level time sequence data; Completing the initial water level time sequence data by using a time sequence interpolation algorithm to generate a complete water level time sequence; Performing credibility evaluation on the complete water level time sequence, filtering out time sequence segments that meet a preset credibility threshold to form credible water level time sequence information. 3.The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 1, characterized in that, According to the preset sliding time window combined with the credible water level time sequence information, the potential risk intensity of the target reservoir dam body under water level changes is determined, which specifically includes: Based on the preset sliding time window, the credible water level time sequence information is slidingly intercepted to obtain a plurality of window water level time sequence segments; Calculating the water level change rate and water level fluctuation amplitude of each window water level time sequence segment to generate window characteristic parameters of each window water level time sequence segment; Inputting the window characteristic parameters into a preset risk assessment model to obtain a window risk value corresponding to each window water level time sequence segment; According to all window risk values, the potential risk intensity of the target reservoir dam body under water level changes is determined. 4.The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 1, characterized in that, The potential risk intensity is input into a preset water level warning unit, and the water level warning unit synchronously accesses a reservoir storage-capacity-pressure distribution map derived in real time by a hydrological model, and specifically includes: The preset water level warning unit receives the potential risk intensity and calls a hydrological model interface to obtain current hydrological parameter data; The hydrological model is driven based on the current hydrological parameter data to simulate a reservoir storage-capacity-pressure field, and a reservoir storage-capacity-pressure distribution map is output; The reservoir storage-capacity-pressure distribution map is synchronously input into the preset water level warning unit. 5.The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 1, characterized in that, The safety bearing boundary of the target reservoir dam structure under the current water level is determined according to the reservoir storage-capacity-pressure distribution map, and specifically includes: Actual pressure values of each structural unit of the target reservoir dam are extracted from the reservoir storage-capacity-pressure distribution map to generate a structural unit pressure data set; A dam material mechanics parameter library is called to match the compressive strength threshold of each structural unit to establish a unit bearing threshold matrix; The pressure safety margin of each structural unit is determined according to the structural unit pressure data set and the unit bearing threshold matrix; The safety bearing boundary of the target reservoir dam structure under the current water level is determined based on the pressure safety margin of each structural unit. 6.The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 5, characterized in that, The pressure safety margin of each structural unit is determined according to the structural unit pressure data set and the unit bearing threshold matrix, and specifically includes: The structural unit pressure data set and the unit bearing threshold matrix are matched to establish a pressure-threshold correlation pair corresponding to each structural unit; The bearing threshold and the actual pressure value of the corresponding structural unit are calculated based on the pressure-threshold correlation pair to obtain the pressure safety margin of each structural unit.

7. The real-time monitoring and early warning method for reservoir water level based on Internet of Things according to claim 1, characterized in that, An unmanned aerial vehicle provided with a camera collects water level monitoring data of the target reservoir dam.

8. A real-time reservoir water level monitoring and early warning system based on the Internet of Things, used to perform the real-time reservoir water level monitoring and early warning method based on the Internet of Things according to any one of claims 1 to 7, characterized in that, The system includes: A collection module that collects water level monitoring data of the target reservoir dam and transmits the water level monitoring data to an edge computing node through an Internet of Things communication network; A processing module that extracts trusted water level time series information from the water level monitoring data from the edge computing node, and determines the potential risk intensity of the target reservoir dam under water level changes according to a preset sliding time window combined with the trusted water level time series information; The processing module is also configured to input the potential risk intensity into a preset water level warning unit, and the water level warning unit synchronously accesses a reservoir storage-capacity-pressure distribution map derived in real time by a hydrological model, and determines the safety bearing boundary of the target reservoir dam structure under the current water level according to the reservoir storage-capacity-pressure distribution map; The processing module is also configured to perform a structural bearing limit analysis on the target reservoir dam based on the safety bearing boundary combined with the potential risk intensity to obtain a water level grading warning value of the target reservoir dam under the current water level; An execution module that sends a water level grading warning signal of the target reservoir dam to a reservoir management terminal through an Internet of Things communication network based on the water level grading warning value.

9. A computer device, comprising: The computer device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the Internet of Things-based real-time monitoring and warning method for reservoir water level as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by a processor to implement the real-time monitoring and early warning method for water level of a reservoir based on Internet of Things according to any one of claims 1 to 7.

Images