Intelligent flood control monitoring device and method for water conservancy projects

Abstract

This invention discloses an intelligent flood control monitoring device and method for water conservancy projects, comprising four steps: monitoring flood control information of water conservancy projects, constructing a flood prediction model, evaluating the accuracy of the model's prediction, and optimizing the flood prediction model. By monitoring and acquiring flood control information of water conservancy projects, a flood prediction model is constructed. A preliminary analysis and assessment of the immediate risk level of the water conservancy project and the risk impact of the flood are conducted. A comprehensive analysis and assessment of the predicted risk level of the flood disaster is then performed, providing early warning of flood disasters for professionals to refer to for targeted disaster control and management at appropriate levels. Finally, by comparing the actual flood occurrence with the actual flood situation, the prediction accuracy of the flood prediction model is evaluated, and a model management signal feedback optimization model is generated to establish an accurate and reliable flood prediction model, providing scientific basis and support for flood control work and emergency decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy engineering, and in particular to an intelligent flood control monitoring device and method for water conservancy engineering. Background Art

[0002] Water conservancy project facilities include sluices, dams, reservoirs, rivers and other facilities, which are used to regulate water resources. Water conservancy project management mainly serves flood control, drainage, irrigation, power generation, water transportation, aquatic products, industrial water, domestic water and environmental improvement, and serves social and economic development and people's lives.

[0003] The existing flood control monitoring devices for water conservancy projects have incomplete data monitoring and lack of pertinence, making it difficult to assess the current basic risks of water conservancy projects, as well as the risk impact of meteorological and environmental conditions on water conservancy projects. This leads to poor prediction effects and insufficient accuracy of prediction models for floods, resulting in defects in flood control monitoring of water conservancy projects, making it difficult to provide a scientific basis and support for flood control work and emergency decision-making.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the defects of incomplete and insufficient pertinence of data monitoring and analysis in existing flood control monitoring devices for water conservancy projects, as well as the poor flood prediction accuracy caused by the above defects, which cause flood control monitoring defects of water conservancy projects. The present invention obtains flood control information of hydraulic projects through monitoring, and then constructs a flood prediction model. The immediate risk level of hydraulic projects and the risk impact level of floods are preliminarily analyzed and evaluated, and then the predicted risk level of floods is comprehensively analyzed and evaluated, so as to provide risk warning for flood disasters for reference by professionals to carry out targeted disaster regulation and management at the corresponding level. The prediction accuracy of the flood prediction model is evaluated by comparing the actual flood occurrence of floods, and a model management signal feedback optimization model is generated to establish an accurate and reliable flood prediction model to provide a scientific basis and support for flood control work and emergency decision-making.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An intelligent flood control monitoring method for a water conservancy project comprises the following steps:

[0008] Step 1: Monitor and obtain flood control information of hydraulic engineering: Flood control information includes meteorological data, hydrological data and environmental data. Set the information collection period Tc to monitor flood control information regularly.

[0009] Step 2: Build a flood prediction model. The specific process is as follows:

[0010] First, through preliminary analysis of hydrological data, the basic risk coefficient of hydraulic engineering is obtained to assess the immediate risk level of hydraulic engineering;

[0011] Then, by combining meteorological data with environmental data, we can obtain the flood risk impact coefficient and assess the degree of flood risk impact;

[0012] Then, by combining the basic risk coefficient of hydraulic engineering with the risk impact coefficient of flood, the predicted risk level of flood disaster is evaluated, the flood prediction index is obtained and the corresponding risk warning signal is generated, so as to provide risk warning for flood disaster for reference by professionals;

[0013] Step 3: Evaluate the prediction accuracy of the model: collect the actual flood occurrence corresponding to the prediction time node and evaluate the actual risk level of the flood disaster, compare the actual risk level of the flood disaster with the predicted risk level, obtain the model deviation index of the flood prediction model, evaluate the prediction accuracy of the flood prediction model, and generate corresponding model management signals;

[0014] Step 4: Optimize the flood prediction model: Feed the model management signal back to the flood prediction model to continuously optimize and improve the flood prediction model.

[0015] Furthermore, the specific process of collecting flood control information is as follows:

[0016] Meteorological data include rainfall, wind speed and direction; hydrological data include water level, flow and velocity; environmental data include soil moisture content, temperature and humidity;

[0017] A hydraulic engineering stereo model is constructed by three-dimensional modeling technology, the hydraulic engineering stereo model is divided into N0 characteristic regions, any characteristic region is marked as A, N1 characteristic points are extracted from the characteristic region A, and any characteristic point is marked as B;

[0018] The water level at feature point B is marked as SWb, the flow rate is marked as LLb, and the flow velocity is marked as LSb;

[0019] The soil water content of feature point B is marked as HSb, the temperature is marked as WDb, and the humidity is marked as SDb;

[0020] The rainfall at feature point B is marked as JYb, the wind speed is marked as FSb, and the wind direction is marked as FXb;

[0021] Among them, the numerical value of wind direction FXb refers to the angular difference between the current wind direction and the water flow direction. Taking the water flow direction as the reference line, the wind direction FXb is numerically marked: if the current wind direction is the same as the water flow direction, the mark FXb=0; if the current wind direction is opposite to the water flow direction, the mark FXb=π.

[0022] Furthermore, the specific process of obtaining the basic risk coefficient of hydraulic engineering is as follows:

[0023] Hydrological data include water level, flow rate and flow velocity. First, the water level SWb, flow rate LLb and flow velocity LSb of feature point B are combined to obtain the water regime assessment coefficient Xsp of feature point B.

[0024] Then, the water status coefficient Xsz of the characteristic area A is obtained through the water status evaluation coefficient Xsp of the N1 characteristic points;

[0025] Then, the basic risk coefficient Xjf of hydraulic engineering is obtained through the water state coefficient Xsz of N0 characteristic areas;

[0026] The standard interval of the basic risk factor Xjf is set, and the immediate risk level of the hydraulic project is evaluated by interval comparison.

[0027] Furthermore, the specific process of obtaining the flood risk impact coefficient is as follows:

[0028] Meteorological data include rainfall, wind speed and direction, and environmental data include soil moisture content, temperature and humidity;

[0029] First, the meteorological influence coefficient Xqy of feature point B is obtained by combining the rainfall JYb, wind speed FSb and wind direction FXb of feature point B;

[0030] Obtain the meteorological state coefficient Xqz of the characteristic area A through the meteorological influence coefficient Xqy of N1 characteristic points;

[0031] Then, the environmental impact coefficient Xhy of feature point B is obtained by combining the soil moisture content HSb, temperature WDb and humidity SDb of feature point B;

[0032] Obtain the environmental state coefficient Xhz of the feature area A through the environmental impact coefficient Xhy of N1 feature points;

[0033] Then, the risk assessment coefficient Xfp of the characteristic area A is obtained by combining the meteorological state coefficient Xqz and the environmental state coefficient Xhz of the characteristic area A;

[0034] Then, the risk impact coefficient Xfy of the flood is obtained through the risk assessment coefficient Xfp of N0 characteristic areas;

[0035] Set the standard interval of the risk impact coefficient Xfy and evaluate the risk impact of the flood through interval comparison.

[0036] Furthermore, the specific process of obtaining the flood prediction index is as follows:

[0037] The flood prediction index Zyc is obtained by combining the basic risk coefficient Xjf of hydraulic engineering and the risk impact coefficient Xfy of flood;

[0038] The standard interval of the flood prediction index Zyc is set, and the predicted risk level of flood disasters is evaluated through interval comparison, and corresponding risk warning signals are generated, so as to provide risk warnings for flood disasters for reference by professionals to carry out targeted disaster regulation and management at the corresponding level.

[0039] Furthermore, the specific process of obtaining the model deviation index is as follows:

[0040] Set the forecast time node as T0, and mark the actual risk level of flood at the forecast time node T0 as level w, where the actual risk level w is evaluated and marked by professional technicians;

[0041] Then, by comparing the differences between the actual risk level w and the predicted risk level v for n0 times, the model deviation index PC is obtained;

[0042] Set the standard interval of the model deviation index PC, evaluate the prediction accuracy of the flood prediction model through interval comparison, and generate corresponding model management signals;

[0043] When a y-level model management signal is generated, the adjustment degree of the weight factor coefficient in the preset model is φy%, thereby continuously optimizing and improving the prediction model.

[0044] An intelligent flood control monitoring device for water conservancy projects uses the intelligent flood control monitoring method for water conservancy projects.

[0045] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0046] The present invention obtains flood control information of hydraulic engineering through monitoring, and then constructs a flood prediction model, preliminarily analyzes and evaluates the immediate risk level of hydraulic engineering and the risk impact level of flood, and then comprehensively analyzes and evaluates the predicted risk level of flood disaster, so as to provide risk warning for flood disaster, and provide reference for professionals to carry out targeted disaster regulation and management at the corresponding level, and then evaluates the prediction accuracy of the flood prediction model by comparing the actual flood occurrence situation of the flood disaster, and generates a model management signal feedback optimization model, so as to establish an accurate and reliable flood prediction model, and provide a scientific basis and support for flood control work and emergency decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The overall working process schematic diagram of the present invention is shown;

[0048] Figure 2 A schematic flow chart of the flood prediction model of the present invention is shown. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Embodiment 1:

[0051] like Figure 1-2 As shown, an intelligent flood control monitoring device for water conservancy projects, using the intelligent flood control monitoring method for water conservancy projects described below, includes the following steps:

[0052] Step 1: Monitor and obtain flood control information of hydraulic engineering: Flood control information includes meteorological data, hydrological data and environmental data. Set the information collection period Tc to monitor flood control information regularly.

[0053] The specific process of collecting flood control information is as follows:

[0054] Meteorological data include rainfall, wind speed and direction; hydrological data include water level, flow and velocity; environmental data include soil moisture content, temperature and humidity;

[0055] The hydraulic engineering 3D model is constructed by 3D modeling technology. Since the hydraulic engineering includes structures such as reservoirs, sluice gates and river channels, the hydraulic engineering 3D model is divided into N0 feature areas, and any feature area is marked as A. N1 feature points are extracted from feature area A, and any feature point is marked as B.

[0056] Feature area A includes three situations: water, land, and air. Information collection is performed for each of the three situations:

[0057] If the feature point B is located in the air, the meteorological data of the feature point B is collected; if the feature point B is located on the water surface, the hydrological data of the feature point B is collected; if the feature point B is located on land, the environmental data of the feature point B is collected;

[0058] The water level at feature point B is marked as SWb, the flow rate is marked as LLb, and the flow velocity is marked as LSb;

[0059] The soil water content of feature point B is marked as HSb, the temperature is marked as WDb, and the humidity is marked as SDb;

[0060] The rainfall at feature point B is marked as JYb, the wind speed is marked as FSb, and the wind direction is marked as FXb;

[0061] The value of wind direction FXb refers to the angle difference between the current wind direction and the water flow direction. The wind direction FXb is numerically marked with the water flow direction as the reference line: if the current wind direction is the same as the water flow direction, then FXb=0; if the current wind direction is opposite to the water flow direction, then FXb=π;

[0062] Step 2: Construct a flood prediction model: First, obtain the basic risk coefficient of hydraulic engineering through preliminary analysis of hydrological data, and evaluate the immediate risk level of hydraulic engineering; then, obtain the risk impact coefficient of floods through combining meteorological data with environmental data, and evaluate the risk impact level of floods; then, evaluate the predicted risk level of floods through combining the basic risk coefficient of hydraulic engineering with the risk impact coefficient of floods, obtain the flood prediction index and generate corresponding risk warning signals, so as to provide risk warning for flood disasters, which can be used as a reference for professionals to carry out targeted disaster regulation and management at the corresponding level;

[0063] S2-1: The specific process of obtaining the basic risk factor of hydraulic engineering is as follows:

[0064] The hydrological data include water level, flow rate and flow velocity. The water level of feature point B is marked as SWb, the flow rate is marked as LLb, and the flow velocity is marked as LSb;

[0065] First, the water level SWb, flow rate LLb and flow velocity LSb of the characteristic point B are combined to obtain the water situation assessment coefficient Xsp of the characteristic point B: Xsp = α1*SWb+α2*LLb+α3*LSb;

[0066] Among them, α1, α2 and α3 are weight factor coefficients of water level SWb, flow rate LLb and flow velocity LSb respectively, and α1, α2 and α3 are all greater than 0; the weight factor coefficients are obtained by a large number of experimental measurements and preset. When the water level SWb, flow rate LLb and flow velocity LSb of the feature point b are higher, the water situation assessment coefficient Xsp is higher, indicating that the water situation of the feature point B is more serious and the basic risk of flood is higher;

[0067] Then, the water status coefficient Xsz of the characteristic area A is obtained through the water status evaluation coefficient Xsp of the N1 characteristic points:

[0068] When the mean value of the water regime assessment coefficient Xsp of the N1 characteristic points is higher, it means that the overall water regime of the characteristic area A is more serious and the basic risk level of flood disaster is higher;

[0069] Then, the basic risk coefficient Xjf of hydraulic engineering is obtained through the water state coefficient Xsz of N0 characteristic areas:

[0070] When the mean value of the water regime state coefficients Xsz of N0 characteristic points is higher and the variance is larger, it indicates that the overall basic risk level of the water conservancy project is high and the regional fluctuation difference is larger. Furthermore, it shows that the overall water regime state is more serious and the basic risk degree of flood occurrence is higher.

[0071] Set the standard interval of the basic risk coefficient Xjf, and evaluate the immediate risk degree of the hydraulic project through interval comparison: It is preset that there are R standard intervals, and any one standard interval is marked as Hr, where r is the serial number of the standard interval, 0 < r ≤ R. When the basic risk coefficient Xjf is within the standard interval Hr, the immediate risk degree of the hydraulic project is evaluated as level r.

[0072] S2-2: The specific process of obtaining the risk impact coefficient of the flood is as follows:

[0073] The meteorological data includes rainfall, wind speed and wind direction. Mark the rainfall of characteristic point B as JYb, the wind speed as FSb, and the wind direction as FXb.

[0074] The environmental data includes soil moisture content, temperature and humidity. Mark the soil moisture content of characteristic point B as HSb, the temperature as WDb, and the humidity as SDb.

[0075] First, combine the rainfall JYb, wind speed FSb and wind direction FXb of characteristic point B to obtain the meteorological impact coefficient Xqy of characteristic point B:

[0076] Among them, β1 and β2 are the weight factor coefficients of rainfall JYb and wind speed FSb respectively, and both β1 and β2 are greater than 0. When the rainfall JYb is higher, the wind speed FSb is larger, and the wind direction FXb is closer to the water flow direction, the meteorological impact coefficient Xqy is larger, indicating that the meteorological conditions of characteristic point B have a more serious impact on the flood.

[0077] Through the meteorological impact coefficients Xqy of N1 characteristic points, obtain the meteorological state coefficient Xqz of characteristic area A:

[0078]

[0079] When the mean value of the meteorological impact coefficients Xqy of N1 characteristic points is higher, it indicates that the overall meteorological state of characteristic area A is more serious and the impact degree on the flood is higher.

[0080] Then, combine the soil moisture content HSb, temperature WDb and humidity SDb of characteristic point B to obtain the environmental impact coefficient Xhy of characteristic point B: Xhy = λ1 * HSb + λ2 * WDb + λ3 * SDb;

[0081] Among them, λ1, λ2 and λ3 are weight factor coefficients of soil moisture content HSb, temperature WDb and humidity SDb respectively, and λ1, λ2 and λ3 are all greater than 0; when the soil moisture content HSb, temperature WDb and humidity SDb of feature point B are higher, the environmental impact coefficient Xhy is higher, indicating that the environmental conditions of feature point B have a more serious impact on floods;

[0082] High temperatures may cause changes in rainfall patterns and accelerate the melting of ice and snow, which in turn increases the formation and scale of floods. In addition, high temperatures may also cause soil drying and increase the amount of surface runoff, thereby exacerbating the extent and scope of floods; high humidity is usually associated with increased water vapor content in the atmosphere, increasing the likelihood of precipitation in the atmosphere. Under high humidity conditions, the water vapor content in the atmosphere is greater, and precipitation events may be more frequent and more intense, thereby increasing the risk of floods;

[0083] The environmental state coefficient Xhz of the feature area A is obtained through the environmental impact coefficient Xhy of N1 feature points:

[0084]

[0085] When the mean value of the environmental impact coefficient Xhy of the N1 feature points is higher, it means that the overall environmental state of the feature area A is more serious and the impact of the flood is higher;

[0086] Then, by combining the meteorological state coefficient Xqz and the environmental state coefficient Xhz of the characteristic area A, the risk assessment coefficient Xfp of the characteristic area A is obtained: Xfp = Xqz ω1 +Xhz ω2 ;

[0087] Among them, ω1 and ω2 are the weight coefficients of the meteorological state coefficient Xqz and the environmental state coefficient Xhz, respectively, and both ω1 and ω2 are greater than 0; when the meteorological state coefficient Xqz and the environmental state coefficient Xhz are higher, the risk assessment coefficient Xfp is higher, indicating that the comprehensive impact of meteorological state and environmental state on flood disasters is deeper;

[0088] Then, the risk impact coefficient Xfy of the flood is obtained through the risk assessment coefficient Xfp of N0 characteristic areas:

[0089]

[0090] When the mean of the risk assessment coefficient Xfp of the N0 characteristic regions is higher and the variance is larger, it means that the overall level of the impact risk of floods in water conservancy projects is high and the fluctuation difference between regions is large, the water flow of water conservancy projects is unstable, and the risk impact of floods is deeper;

[0091] Set the standard interval of the risk impact coefficient Xfy, and evaluate the risk impact degree of the flood through interval comparison: Presuppose U standard intervals, and mark any one of the standard intervals as Hu, where u is the serial number of the standard interval, 0 < u ≤ U. When the risk impact coefficient Xfy is within the standard interval Hu, the risk impact degree of the flood is evaluated as level u;

[0092] S2-3: The specific process of obtaining the flood prediction index is as follows:

[0093] Combine the basic risk coefficient Xjf of the hydraulic project and the risk impact coefficient Xfy of the flood to obtain the flood prediction index Zyc: Zyc = ε1 * Xjf + ε2 * Xfy;

[0094] Where ε1 and ε2 are the weight factor coefficients of the basic risk coefficient Xjf and the risk impact coefficient Xfy respectively. When the basic risk coefficient Xjf of the hydraulic project and the risk impact coefficient Xfy of the flood are higher, the flood prediction index Zyc is higher;

[0095] Set the standard interval of the flood prediction index Zyc, evaluate the prediction risk degree of the flood disaster through interval comparison, and generate corresponding risk warning signals:

[0096] Presuppose V standard intervals, and mark any one of the standard intervals as Hv, where v is the serial number of the standard interval, 0 < v ≤ V. When the flood prediction index Zyc is within the standard interval Hv, the prediction risk degree of the flood disaster is evaluated as level v and a level v risk warning signal is generated, so as to conduct risk early warning for the flood disaster, for professional personnel to refer to for targeted disaster control management at the corresponding level;

[0097] Step three, evaluate the prediction accuracy of the model: Collect the actual flood occurrence situation corresponding to the prediction time node and evaluate the actual risk degree of the flood disaster. Compare the actual risk degree of the flood disaster with the predicted risk degree to obtain the model deviation index of the flood prediction model, evaluate the prediction accuracy of the flood prediction model, and generate corresponding model management signals;

[0098] The specific process of obtaining the model deviation index is as follows:

[0099] Set the prediction time node as T0, and mark the actual risk degree of the flood at the prediction time node T0 as level w, where the actual risk degree level w is evaluated and marked by professional technical personnel;

[0100] Then, by comparing the difference between the actual risk degree level w n0 times and the predicted risk degree level v, obtain the model deviation index PC:

[0101] Among them, μ is the conversion coefficient and μ > 0. The conversion coefficient μ refers to the constant that combines the actual risk level w and the predicted risk level v and then converts them into the model deviation index PC. The higher the difference between the actual risk level w and the predicted risk level v, the larger the model deviation index PC, and the lower the prediction accuracy of the flood prediction model.

[0102] Set the standard interval of the model deviation index PC, evaluate the prediction accuracy of the flood prediction model through interval comparison, and generate corresponding model management signals:

[0103] There are Y preset standard intervals, and any one of the standard intervals is marked as Hy, where y is the serial number of the standard interval, 0 < y ≤ Y. When the model deviation index PC is within the standard interval Hy, the prediction accuracy of the flood prediction model is evaluated as level y and a level y model management signal is generated, and the weight factor coefficients in the model are adjusted to different degrees;

[0104] Step four, optimize the flood prediction model: Feed the model management signal back into the flood prediction model, continuously optimize and improve the prediction model to establish an accurate and reliable flood prediction model, providing a scientific basis and support for flood control work and emergency decision-making;

[0105] When generating a level y model management signal, the preset adjustment degree of the weight factor coefficients in the model is φy%. For example, for the weight factor coefficients ε1 and ε2:

[0106] The adjusted ε1 is marked as ε10: ε10 = ε1 * (1 ± φy%);

[0107] The adjusted ε2 is marked as ε20: ε20 = ε2 * (1 ± φy%);

[0108] Thus, continuously optimize and improve the prediction model to establish an accurate and reliable flood prediction model, providing a scientific basis and support for flood control work and emergency decision-making.

[0109] In summary, the present invention obtains the flood control information of hydraulic engineering through monitoring, then constructs a flood prediction model, preliminarily analyzes and evaluates the immediate risk level of the hydraulic engineering and the risk impact level of the flood, and then comprehensively analyzes and evaluates the predicted risk level of the flood disaster, so as to conduct risk early warning of the flood disaster for professional personnel to refer to for targeted disaster regulation management at corresponding levels. Then, by comparing the actual flood occurrence situation of the flood disaster, the prediction accuracy of the flood prediction model is evaluated, and a model management signal is generated to feedback and optimize the model, so as to establish an accurate and reliable flood prediction model, providing a scientific basis and support for flood control work and emergency decision-making.

[0110] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0112] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent flood control monitoring method for water conservancy projects, characterized in that: The following steps are involved: Step 1: Monitor and obtain flood control information of hydraulic engineering: Flood control information includes meteorological data, hydrological data and environmental data. Set the information collection period Tc to monitor flood control information regularly. Step 2: Build a flood prediction model. The specific process is as follows: First, through preliminary analysis of hydrological data, the basic risk coefficient of hydraulic engineering is obtained to assess the immediate risk level of hydraulic engineering; Then, by combining meteorological data with environmental data, we can obtain the flood risk impact coefficient and assess the degree of flood risk impact; Then, by combining the basic risk coefficient of hydraulic engineering with the risk impact coefficient of flood, the predicted risk level of flood disaster is evaluated, the flood prediction index is obtained and the corresponding risk warning signal is generated, so as to provide risk warning for flood disaster for reference by professionals; Step 3: Evaluate the prediction accuracy of the model: collect the actual flood occurrence corresponding to the prediction time node and evaluate the actual risk level of the flood disaster, compare the actual risk level of the flood disaster with the predicted risk level, obtain the model deviation index of the flood prediction model, evaluate the prediction accuracy of the flood prediction model, and generate corresponding model management signals; Step 4: Optimize the flood prediction model: Feed the model management signal back to the flood prediction model to continuously optimize and improve the flood prediction model; The specific process of collecting flood control information is as follows: Meteorological data include rainfall, wind speed and direction; hydrological data include water level, flow and velocity; environmental data include soil moisture content, temperature and humidity; A hydraulic engineering stereo model is constructed by three-dimensional modeling technology, the hydraulic engineering stereo model is divided into N0 characteristic regions, any characteristic region is marked as A, N1 characteristic points are extracted from the characteristic region A, and any characteristic point is marked as B; The water level at feature point B is marked as SWb, the flow rate is marked as LLb, and the flow velocity is marked as LSb; The soil water content of feature point B is marked as HSb, the temperature is marked as WDb, and the humidity is marked as SDb; The rainfall at feature point B is marked as JYb, the wind speed is marked as FSb, and the wind direction is marked as FXb; The wind direction value FXb refers to the angle difference between the current wind direction and the water flow direction. The wind direction FXb is numerically marked with the water flow direction as the reference line: if the current wind direction is the same as the water flow direction, then FXb=0; if the current wind direction is opposite to the water flow direction, then FXb=π; The specific process of obtaining the basic risk coefficient of hydraulic engineering is as follows: Hydrological data include water level, flow rate and flow velocity. First, the water level SWb, flow rate LLb and flow velocity LSb of feature point B are combined to obtain the water regime assessment coefficient Xsp of feature point B. Then, the water status coefficient Xsz of the characteristic area A is obtained through the water status evaluation coefficient Xsp of the N1 characteristic points; Then, the basic risk coefficient Xjf of hydraulic engineering is obtained through the water state coefficient Xsz of N0 characteristic areas; The standard interval of the basic risk factor Xjf is set, and the immediate risk level of the hydraulic project is evaluated by interval comparison.

2. The intelligent flood control monitoring method for water conservancy projects according to claim 1 is characterized in that: The specific process of obtaining the flood risk impact coefficient is as follows: Meteorological data include rainfall, wind speed and direction, and environmental data include soil moisture content, temperature and humidity; First, the meteorological influence coefficient Xqy of feature point B is obtained by combining the rainfall JYb, wind speed FSb and wind direction FXb of feature point B; Obtain the meteorological state coefficient Xqz of the characteristic area A through the meteorological influence coefficient Xqy of N1 characteristic points; Then, the environmental impact coefficient Xhy of feature point B is obtained by combining the soil moisture content HSb, temperature WDb and humidity SDb of feature point B; Obtain the environmental state coefficient Xhz of the feature area A through the environmental impact coefficient Xhy of N1 feature points; Then, the risk assessment coefficient Xfp of the characteristic area A is obtained by combining the meteorological state coefficient Xqz and the environmental state coefficient Xhz of the characteristic area A; Then, the risk impact coefficient Xfy of the flood is obtained through the risk assessment coefficient Xfp of N0 characteristic areas; Set the standard interval of the risk impact coefficient Xfy and evaluate the risk impact of the flood through interval comparison.

3. The intelligent flood control monitoring method for water conservancy projects according to claim 2 is characterized in that: The specific process of obtaining the flood prediction index is as follows: The flood prediction index Zyc is obtained by combining the basic risk coefficient Xjf of hydraulic engineering and the risk impact coefficient Xfy of flood; The standard interval of the flood prediction index Zyc is set, and the predicted risk level of flood disasters is evaluated through interval comparison, and corresponding risk warning signals are generated, so as to provide risk warnings for flood disasters for reference by professionals to carry out targeted disaster regulation and management at the corresponding level.

4. The intelligent flood control monitoring method for water conservancy projects according to claim 3 is characterized in that: The specific process of obtaining the model deviation index is: Set the forecast time node as T0, and mark the actual risk level of flood at the forecast time node T0 as level w, where the actual risk level w is evaluated and marked by professional technicians; Then, by comparing the differences between the actual risk level w and the predicted risk level v for n0 times, the model deviation index PC is obtained; Set the standard interval of the model deviation index PC, evaluate the prediction accuracy of the flood prediction model through interval comparison, and generate corresponding model management signals; When a y-level model management signal is generated, the adjustment degree of the weight factor coefficient in the preset model is φy%, thereby continuously optimizing and improving the prediction model.

5. An intelligent flood control monitoring device for water conservancy projects, characterized in that: The intelligent flood control monitoring device for water conservancy projects applies the intelligent flood control monitoring method for water conservancy projects described in any one of claims 1 to 4 above.

Images