Generation platform of zero-code flood control dispatching system

Abstract

The invention discloses a zero-code flood control scheduling system generation platform, and the platform comprises a marking module which is used for marking a water conservancy project, a lake and a flood control section on a river reach of a target watershed, and the water conservancy project, the lake and the flood control section are connected through the river reach to generate a topological relation; the configuration module is used for configuring data information for the water conservancy project and / or the section; the generation module is used for generating a flood control dispatching system after application information verification; zero code editing operation is realized at the client, water conservancy professionals can also perform flood control dispatching application management, the project implementation efficiency can be improved, and the implementation cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of flood control dispatching management systems, and in particular to a zero-code generation platform for flood control dispatching systems. Background Art

[0002] The zero-code platform is a rapid development tool designed to help users quickly build and deploy applications without writing complex code. It provides an intuitive graphical user interface, where users can quickly build applications for various business systems by dragging and dropping various components or modules in the interface, greatly reducing development time and costs.

[0003] At present, there is a lack of applications that use zero-code automatic page generation systems in river basin / reservoir flood control scheduling and management systems. In addition, actual flood control management systems often involve some complex data processing and calculations. Therefore, how to provide a data extraction and operation method based on a zero-code platform that can meet the various complex water level prediction data processing and calculations in flood control scheduling and management systems is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide a zero-code flood control dispatching system generation platform to solve the technical problem in the prior art of lacking an application of a zero-code automatic page generation system in a flood control dispatching management system.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A zero-code flood control dispatch system generation platform, including:

[0007] A marking module is used to mark water conservancy projects, lakes and flood control sections on the river sections of the target basin, and the water conservancy projects, lakes and flood control sections are connected through the river sections to generate topological relationships;

[0008] A configuration module, configuring data information for the water conservancy project and / or section;

[0009] The generation module generates the flood control dispatching system after applying information verification.

[0010] Furthermore, the water conservancy projects are specifically reservoirs, flood storage areas and weirs.

[0011] Furthermore, the configuration module includes:

[0012] A watershed network topology drawing module is used to select reservoir symbols and runoff symbols in a visual editing interface to form a distributed runoff map of upstream and downstream reservoirs, and input the name of each reservoir in the visual editing interface;

[0013] A parameter acquisition module, used for acquiring reservoir elements in the distributed runoff map, wherein the reservoir elements include the name of each reservoir and the runoff direction of each reservoir;

[0014] A data acquisition and analysis module, used to obtain the historical water and rainfall data of the reservoir and the basic reservoir parameters and weather environment parameters of the reservoir from the database according to the name of the reservoir, analyze the historical water and rainfall data of each reservoir by using a deep learning algorithm, and screen out the influencing factors of the water level of each reservoir and the influence coefficient of each influencing factor from the reservoir parameters and weather environment parameters;

[0015] A prediction module, which obtains the influencing factors affecting the water level of each reservoir and the influencing coefficient of each influencing factor based on the data acquisition and analysis module, and dynamically follows the current state of each reservoir to predict the future water level of the reservoir;

[0016] The scheduling model management module marks the corresponding relationship between the different scheduling modes of each reservoir at each flood discharge and the water level drop rate of each reservoir based on the data acquisition and analysis module, determines the water level rise rate of each reservoir according to the prediction module, and selects the corresponding scheduling mode in combination with the water level rise rate of each reservoir and the relationship between the future water level of each reservoir and the warning water level.

[0017] Further, a historical water level change trend diagram of each of the reservoirs is formed based on the data acquisition and analysis module;

[0018] Based on the prediction module, a predicted water level change trend graph of each reservoir is formed, and the predicted water level change trend graph and the real-time monitoring water level change trend graph of the same reservoir are integrated into the same trend graph;

[0019] Based on the scheduling model management model, the scheduling model that meets the warning water level is automatically screened out from all scheduling modes for the user.

[0020] Furthermore, the data acquisition and analysis module uses a deep learning algorithm to analyze the historical water and rainfall data of each reservoir in the following steps:

[0021] Obtain the historical water level monitoring data of each reservoir, smooth the historical water level monitoring data, and form a historical water level change trend chart;

[0022] Extracting a water level rise segment from the historical water level change trend graph, and obtaining the daily rainfall and daily water level increase corresponding to the water level rise segment;

[0023] The daily water level increase corresponding to the same daily rainfall is extracted from the water level rising section, and the basic parameters of the reservoir when the daily rainfall is the same are obtained. Based on the differentiation of the daily water level increase, a deep learning algorithm is used to determine the relationship between the reservoir water level change and the rainfall duration and the basic parameters of the reservoir. The influencing factors affecting the reservoir water level and the influence coefficient of each of the influencing factors are screened out from the rainfall duration and the basic parameters of the reservoir.

[0024] Furthermore, the basic parameters of the reservoir include the reservoir surface area, water evaporation, reservoir depth and underground seepage;

[0025] The weather environment parameters include temperature, humidity and rainfall intensity;

[0026] Among them, firstly, the correlation model between the weather environment parameters and the basic parameters of the reservoir and the internal relationship between the basic parameters of the reservoir is established, and then the influencing factors related to the reservoir water level and the influencing coefficient of each influencing factor are screened out from the basic parameters of the reservoir, and the influencing factors are specifically water evaporation and underground seepage;

[0027] Determine the specific value of the water evaporation and the specific value of the underground seepage by using the association model, and determine the influence trend of the current influencing factors on the reservoir water level based on the influence of each unit of water evaporation and underground seepage on the reservoir water level by using the association model;

[0028] The calculation method of the future water level FW of the reservoir is:

[0029] FW=∑ t {NW(t)+J(t)-[(A(t)*α+B(t)*β]};

[0030] Among them, NW(t)=NW(t-1)+J(t-1)-[(A(t-1)*α+B(t-1)*β];

[0031] FW is the future water level of the reservoir; NW(t) is the water level at the current moment, J(t) is the rainfall at the current moment, A(t) is the specific value of influencing factor A, α is the influence coefficient of influencing factor A; B(t) is the specific value of influencing factor B, β is the influence coefficient of influencing factor B.

[0032] Furthermore, the historical water and rainfall data are divided into a training set and a test set, the training set is tested using a deep learning algorithm to generate a water level prediction model, and the test set is used to adjust the model parameters of the water level prediction model. The specific implementation method is:

[0033] The historical water level monitoring data of each reservoir in the test set is used to form a historical water level change trend graph;

[0034] Based on the initial water level value of the water level rise section in the historical water level change trend diagram, and the basic reservoir parameters and weather environment parameters during the water level rise section;

[0035] The basic parameters of the reservoir, weather environment parameters and initial water level values ​​are imported into the water level prediction model to form a predicted water level rise curve. The water level prediction model is adjusted based on the degree of fit between the predicted water level rise curve and the water level rise segment. The above operation is repeated until the degree of fit between the predicted water level rise curve and the water level rise segment meets expectations.

[0036] Furthermore, the prediction module combines the current state of each reservoir to dynamically follow the prediction of the future water level of the reservoir in the following manner:

[0037] Real-time monitoring of the current water level of the reservoir, as well as the current total rainfall in the reservoir;

[0038] Based on the current weather environment parameters of the reservoir, the specific value of the water evaporation amount and the specific value of the underground seepage amount of the current reservoir are updated in real time using the association model;

[0039] Based on the specific value of the water evaporation amount and the specific value of the underground seepage amount of the current reservoir updated in real time, combined with the calculation formula of the future water level of the reservoir, the latest water level of the reservoir is calculated in real time.

[0040] Further, the scheduling model management model includes a flood discharge level prediction unit and a scheduling mode selection unit;

[0041] The flood discharge level prediction unit is used to establish a relationship between each scheduling mode and the water level reduction speed according to the deep learning results of the data acquisition and analysis module;

[0042] The dispatching mode selection unit predicts the future water level of the reservoir based on the prediction module, and determines the reservoir water level after flood discharge under each dispatching mode in combination with the flood discharge water level of each dispatching mode in the future flood discharge period, and selects the dispatching mode based on the standard that the reservoir water level after flood discharge does not exceed the warning water level;

[0043] When the water level of the reservoir after flood discharge is less than the warning water level, the dispatching mode selection unit is used to select the corresponding dispatching mode. The specific implementation method is as follows:

[0044] When the current water level is at the warning water level, the prediction module is used to predict the future water level of the reservoir within a set time in the future;

[0045] Through simulation operation, the reservoir's flood discharge drop level under each dispatching mode within the future set time is calculated, and the future reservoir water level and flood discharge drop level are superimposed;

[0046] If the difference between the future water level of the reservoir and the flood discharge drop water level is less than the warning water level, the dispatching mode is retained;

[0047] If the difference between the future water level of the reservoir and the flood discharge drop water level is greater than the warning water level, the scheduling mode is screened out.

[0048] Furthermore, the flood discharge level prediction unit is used to establish the relationship between each scheduling mode and the water level reduction speed according to the deep learning result of the data acquisition analysis module in the following manner:

[0049] Obtain the flood discharge working section in the historical water level change trend diagram of each reservoir;

[0050] Eliminate the influence of flood discharge inflow, rainfall and level drop of influencing factors from the reservoir water level in the flood discharge working section to obtain the rated water level of each reservoir, and form a flood discharge water level change diagram of the flood discharge working section;

[0051] Based on the water level drop speed of the flood discharge level change diagram, the relationship between each scheduling mode and the water level drop speed is determined.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention can add reservoirs and runoff directions by dragging the page in the flood control scheduling management system generation platform, and can also automatically add the historical water and rainfall data of each reservoir to form a historical water level change trend chart, and use the water level prediction model to form a predicted water level change trend chart of the current reservoir, and integrate multiple scheduling modes, based on the predicted water level change trend chart and the flood discharge water level drop speed of each scheduling mode, to automatically recommend a suitable scheduling mode to the user.

[0054] Therefore, zero-code editing and operation can be achieved on the client side, and water conservancy professionals can also carry out flood control scheduling application management, which can improve the efficiency of project implementation and reduce the implementation cost. The specific flood control scheduling system can use the deep learning neural network algorithm to generate a water level prediction model. Therefore, through the analysis of historical data, the relationship between the reservoir water level and the weather environment and the basic parameters of the reservoir is determined, and the reservoir water level can be accurately predicted to achieve accurate deployment and control in advance. Therefore, the flood control scheduling management system created by the modeling platform of this implementation system can not only dynamically and intuitively observe the water level changes of each reservoir, but also accurately control the water level, which plays a certain role in flood control and waterlogging prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0056] Figure 1 A structural block diagram of a platform for generating an embodiment of the present invention;

[0057] Figure 2 is a structural block diagram of a configuration module according to an embodiment of the present invention;

[0058] The numbers in the figure represent the following:

[0059] Reservoir runoff map drawing module 1, parameter acquisition module 3, data acquisition and analysis module 4, prediction module 5, scheduling model management model 6. DETAILED DESCRIPTION

[0060] 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.

[0061] The present invention provides a zero-code flood control dispatching system generation platform, which can realize zero-code editing and operation on the client of the parent system, and can be flexibly configured according to actual needs, so that water conservancy professionals can also generate corresponding subsystems according to actual needs to achieve the purpose of flood control dispatching management. For example, in the present invention, it can generate corresponding flood control management subsystems according to different needs, so as to manage regional water conservancy projects and river sections in a targeted manner, improve implementation efficiency and reduce implementation costs.

[0062] like Figure 1 As shown, the generation platform includes:

[0063] A marking module is used to mark water conservancy projects and / or flood control sections on the river section of the parent system (in this embodiment, the water conservancy projects are specifically reservoirs, flood storage areas and weirs), mark connection routes on the river section, and generate topological relationships through connection nodes on the river section, wherein certain designated connection nodes are marked as scheduling nodes;

[0064] A configuration module, configuring data information for the water conservancy project and / or flood control section;

[0065] Generate the module and generate the subsystem after applying information verification.

[0066] In the above, the flood control section refers to a marking point at a designated location where monitoring, forecasting, and scheduling are required. Its specific use is determined according to actual management needs.

[0067] In the present invention, the specific topological relationship refers to the connectivity relationship between different water conservancy projects and river sections, as well as the water flow direction, which is mainly used to guide the subsequent water flow direction and the logical relationship between different water conservancy projects (such as drainage of the upper-level reservoir and storage of water in the lower-level reservoir).

[0068] Among them, in this embodiment, the focus is on configuring data information for the water conservancy project and / or flood control section, such as Figure 2 As shown, its configuration modules specifically include a reservoir runoff map drawing module 1, a parameter acquisition module 3, a data acquisition and analysis module 4, a prediction module 5 and a scheduling model management model 6.

[0069] This embodiment can add reservoirs, flood control sections, and runoff directions by dragging the page in the management system generation platform. At the same time, it can also automatically add the historical water and rainfall data of each reservoir to form a historical water level change trend chart, and use the prediction module 5 to form a predicted water level change trend chart of the current reservoir, and integrate multiple scheduling modes. Based on the predicted water level change trend chart and the flood discharge water level drop speed of each scheduling mode, it automatically recommends a suitable scheduling mode to the user.

[0070] Therefore, zero-code editing and operation is realized on the client side, and water conservancy professionals can also manage flood control scheduling applications. They only need to drag and drop the page in the reservoir runoff map drawing module 1, which can improve the efficiency of project implementation and reduce the implementation cost.

[0071] In addition, it needs to be further emphasized that in this specific implementation, when generating a subsystem, it only needs to be configured by clicking or dragging. In the following specific implementation of the present invention, the specific working principle of its configuration module will be focused on, and this is the fundamental reason why the specific technical solution in the present invention can realize subsystem configuration by clicking or dragging.

[0072] Specifically, the reservoir runoff map drawing module 1 is used to select reservoir symbols and runoff symbols in the visual editing interface to form a distributed runoff map of upstream and downstream reservoirs, and input the name of each reservoir in the visual editing interface.

[0073] Select the reservoir to be edited, double-click, and you can edit the information on the page that pops up. The edited information includes basic information, basic curve, gate opening curve, frequency curve, common data, etc.

[0074] The basic information includes: reservoir name, code, longitude and latitude, flood control section, reservoir type and other content that needs to be filled in or selected. Users need to fill in according to actual conditions and save after completion.

[0075] At the same time, the editing interface can be used to modify basic curves such as the historical water level change trend chart and the predicted water level change trend chart, including modifying the name and unit of the curve xy axis, and modifying the data through editing.

[0076] The relevant equipment data can be imported into the gate opening curve, and the data can be modified by editing.

[0077] Commonly used data include characteristic water level, alarm threshold, output coefficient, single-machine capacity, number of units, single-machine overflow, etc. Users can download the data template, fill in the template, and then import the data.

[0078] The parameter acquisition module 3 is used to acquire the reservoir elements in the distributed network topology map, and the reservoir elements include the name of each reservoir and the runoff direction of each reservoir.

[0079] The data acquisition and analysis module 4 is used to obtain the historical water and rainfall data of the reservoir, as well as the basic reservoir parameters and weather environment parameters of the reservoir from the database according to the reservoir name, use the deep learning algorithm to analyze the historical water and rainfall data of each reservoir, and screen out the influencing factors of the water level of each reservoir and the influence coefficient of each influencing factor from the reservoir parameters and weather environment parameters.

[0080] The prediction module 5 obtains the influencing factors affecting the water level of each reservoir and the influence coefficient of each influencing factor based on the data acquisition and analysis module 4, and dynamically follows the current state of each reservoir to predict the future water level of the reservoir.

[0081] The scheduling model management model 6 marks the corresponding relationship between different scheduling modes and the water level drop rate of each reservoir at each flood discharge based on the data acquisition and analysis module 4, and uses the prediction module 5 to determine the water level rise rate of each reservoir. The corresponding scheduling mode is selected according to the water level rise rate of each reservoir and the relationship between the future water level of each reservoir and the warning water level.

[0082] Therefore, a historical water level change trend chart of each reservoir is formed based on the data acquisition and analysis module 4, a predicted water level change trend chart of each reservoir is formed based on the prediction module 5, and the predicted water level change trend chart and the real-time monitoring water level change trend chart of the same reservoir are integrated into the same trend chart. Based on the scheduling model management model 6, the user can automatically filter out the scheduling mode that meets the warning water level from all scheduling modes.

[0083] Therefore, in this embodiment, there are at least 4 pages in total. The first page is the reservoir runoff map page, and the reservoir scheduling flow direction of a certain river section is formed by dragging and editing the drawing elements; the second page is the historical water level change trend chart of each reservoir in the reservoir runoff map. The year object of the historical water level change trend chart can be one or more. The water change trend charts of each reservoir in multiple years are integrated into the same diagram, which can realize one-click code generation.

[0084] The third page is a predicted water level change trend chart for each reservoir. The predicted water level change trend chart is specifically established based on the water level prediction model created by the data acquisition and analysis module 4. It can also be generated with one click. At the same time, the real-time monitoring water level change trend chart of the reservoir can also be integrated into the predicted water level change trend chart.

[0085] The fourth page is the scheduling mode selection page. According to the current water level and future water level of each reservoir, as well as the flood discharge speed corresponding to each scheduling mode, the scheduling mode that can maintain the future water level below the warning water level is automatically determined, thereby realizing automated scheduling mode screening and zero-code operation.

[0086] The data acquisition and analysis module 4 uses a deep learning algorithm to analyze the historical water and rainfall data of each reservoir in the following steps:

[0087] The historical water level monitoring data of each reservoir is obtained, and the historical water level monitoring data is smoothed to form a historical water level change trend chart.

[0088] The water level rise segment is extracted from the historical water level change trend chart, and the daily rainfall and daily water level increase corresponding to the water level rise segment are obtained.

[0089] The daily water level increase corresponding to the same daily rainfall is extracted from the water level rising section, and the basic parameters of the reservoir when the daily rainfall is the same are obtained. Based on the differentiation of the daily water level increase, the deep learning algorithm is used to determine the relationship between the reservoir water level change and the rainfall duration and the basic parameters of the reservoir. The influencing factors affecting the reservoir water level and the influence coefficient of each influencing factor are screened out from the rainfall duration and the basic parameters of the reservoir.

[0090] The basic parameters of a reservoir include reservoir surface area, water evaporation, reservoir depth and underground seepage.

[0091] Weather environment parameters include temperature, humidity and rainfall intensity.

[0092] Among them, the correlation model between weather environment parameters and basic reservoir parameters as well as the internal basic parameters of the reservoir is first established, and then the influencing factors related to the reservoir water level and the influence coefficient of each influencing factor are screened out from the basic reservoir parameters. The influencing factors are specifically water evaporation and groundwater seepage.

[0093] The association model is used to determine the specific values ​​of water evaporation and groundwater seepage. Based on the impact of each unit of water evaporation and groundwater seepage on the reservoir water level, the association model is used to determine the impact trend of current influencing factors on the reservoir water level.

[0094] Specifically, water evaporation is affected by the surface area of ​​the reservoir, temperature, and humidity. The larger the surface area of ​​the reservoir, the higher the temperature and the lower the humidity, the greater the water evaporation. Conversely, the smaller the surface area of ​​the reservoir, the lower the temperature and the higher the humidity, the smaller the water evaporation.

[0095] The groundwater seepage rate is affected by the reservoir depth and rainfall intensity. The greater the reservoir depth and the smaller the rainfall intensity, the greater the groundwater seepage rate and groundwater seepage intensity. The smaller the reservoir depth and the greater the rainfall intensity, the lower the groundwater seepage rate and groundwater seepage intensity.

[0096] Therefore, the calculation method of the future water level FW of the reservoir is:

[0097] FW=∑ t {NW(t)+J(t)-[(A(t)*α+B(t)*β]};

[0098] Among them, NW(t)=NW(t-1)+J(t-1)-[(A(t-1)*α+B(t-1)*β];

[0099] FW is the future water level of the reservoir; NW(t) is the water level at the current moment, J(t) is the rainfall at the current moment, A(t) is the specific value of the influencing factor A, α is the influence coefficient of the influencing factor A; B(t) is the specific value of the influencing factor B, β is the influence coefficient of the influencing factor B, the specific influencing factor A is the water evaporation, and the influencing factor B is the groundwater seepage.

[0100] The data acquisition and analysis module 4 uses a deep learning neural network algorithm to first determine the impact of the weather environment parameters of the reservoir on the basic parameters of the reservoir and the mutual influence of the parameters within the basic parameters of the reservoir, such as the impact of temperature, humidity, and reservoir surface area on water evaporation, and the impact of rainfall intensity and reservoir depth on underground seepage;

[0101] The influence of water evaporation and groundwater seepage on the reservoir water level was further determined. Since water evaporation and groundwater seepage are particularly important for the dynamic balance of the reservoir, the water level in the reservoir can achieve self-dynamic balance without opening the gates to release floodwaters.

[0102] Therefore, this embodiment studies the impact of water evaporation and underground seepage on reservoir water levels, so as to more comprehensively predict the water level changes of each reservoir and thus more accurately manage flood discharge.

[0103] A water level prediction model is generated using a deep learning neural network algorithm. Therefore, through the analysis of historical data, the relationship between the reservoir water level and the weather environment and the basic parameters of the reservoir is determined. The reservoir water level can be accurately predicted and accurate control can be deployed in advance. Therefore, the management system created by the management system generation platform of this implementation system can not only dynamically and intuitively observe the water level changes of each reservoir, but also accurately control the water level, playing a certain role in flood control and waterlogging prevention.

[0104] In addition, in order to ensure the accuracy of the water level prediction model, this implementation method divides the historical water and rainfall data into a training set and a test set, uses a deep learning algorithm to test the training set, generates a water level prediction model, and uses the test set to adjust the model parameters of the water level prediction model. The specific implementation method is as follows:

[0105] The historical water level monitoring data of each reservoir in the test set is used to form a historical water level change trend graph.

[0106] Based on the initial water level value of the water level rise section in the historical water level change trend chart, as well as the basic reservoir parameters and weather environment parameters during the water level rise period.

[0107] The basic parameters of the reservoir, weather and environmental parameters, and initial water level values ​​are imported into the water level prediction model to form a predicted water level rise curve. The water level prediction model is adjusted based on the degree of fit between the predicted water level rise curve and the water level rise segment. The above operation is repeated until the degree of fit between the predicted water level rise curve and the water level rise segment meets expectations.

[0108] This implementation method divides the historical water and rainfall data into a training set and a test set, and uses the test set to continuously adjust the model parameters of the water level prediction model to repeatedly determine the influence coefficient of each influencing factor (i.e., water evaporation and underground seepage) until the accuracy of the water level prediction model reaches the highest.

[0109] Specifically, the prediction module 5 is used to truly predict the future water level of each reservoir, and the implementation method of dynamically following the current state of each reservoir to predict the future water level of the reservoir is as follows:

[0110] Real-time monitoring of the current water level of the reservoir, as well as the current total rainfall in the reservoir;

[0111] Based on the current weather and environmental parameters of the reservoir, the association model is used to update the specific values ​​of the current reservoir's water evaporation and underground seepage in real time;

[0112] Based on the real-time updated specific values ​​of the current reservoir's water evaporation and the specific values ​​of the underground seepage, combined with the calculation formula for the reservoir's future water level, the latest reservoir water level is calculated in real time.

[0113] It should be noted that in this embodiment, since the weather environment parameters are constantly changing during the rainfall process, the specific data of the factors affecting the reservoir water level (i.e., water evaporation and underground seepage) are also constantly changing. In other words, each influencing factor (i.e., water evaporation and underground seepage) is not constant in the process of predicting the future water level of the reservoir. Therefore, the future water level of the reservoir predicted during the rainfall process is not a linear relationship. Therefore, it is necessary to use the prediction module 5 to dynamically follow the water level prediction model to predict the future water level of the reservoir.

[0114] The scheduling model management model 6 includes a flood discharge level prediction unit and a scheduling mode selection unit, wherein the flood discharge level prediction unit is used to establish the relationship between each scheduling mode and the water level reduction speed according to the deep learning results of the data acquisition analysis module 4.

[0115] The dispatching mode selection unit predicts the future water level of the reservoir based on the prediction module 5, and determines the reservoir water level after flood discharge under each dispatching mode in combination with the flood discharge level of each dispatching mode in the future flood discharge period, and selects the dispatching mode based on the standard that the reservoir water level after flood discharge does not exceed the warning water level.

[0116] Specifically, the flood discharge level prediction unit is used to establish the relationship between each scheduling mode and the water level reduction speed according to the deep learning results of the data acquisition analysis module 4 in the following manner:

[0117] Obtain the flood discharge working section in the historical water level change trend diagram of each reservoir;

[0118] Eliminate the influence of flood discharge inflow, rainfall and drop in influencing factors from the reservoir water level in the flood discharge working section to obtain the rated water level of each reservoir and form a flood discharge water level change diagram of the flood discharge working section;

[0119] Based on the water level drop rate of the flood discharge level change diagram, the relationship between each scheduling mode and the water level drop rate is determined.

[0120] Specifically, the dispatching mode selection unit is used to select the corresponding dispatching mode based on the benchmark that the reservoir water level after flood discharge is less than the warning water level. The specific implementation method is as follows:

[0121] When the current water level is at the warning water level, the prediction module 5 is used to predict the future water level of the reservoir within a set time in the future;

[0122] Through simulation operation, the reservoir's flood discharge drop level under each dispatching mode within the future set time is calculated, and the future reservoir water level and flood discharge drop level are superimposed;

[0123] If the difference between the future water level of the reservoir and the flood discharge drop level is less than the warning water level, the dispatching mode will be retained;

[0124] If the difference between the future water level of the reservoir and the flood discharge drop level is greater than the warning water level, the scheduling mode will be screened out.

[0125] This embodiment can add reservoirs and runoff directions by dragging the page in the management system generation platform, and can also automatically add the historical water and rainfall data of each reservoir to form a historical water level change trend chart, and use the prediction module 5 to form a predicted water level change trend chart of the current reservoir, and integrate multiple scheduling modes. Based on the predicted water level change trend chart and the flood discharge water level drop speed of each scheduling mode, it automatically recommends a suitable scheduling mode to the user.

[0126] Therefore, zero-code editing and operation can be achieved on the client side, and water conservancy professionals can also carry out flood control scheduling application management, which can improve the efficiency of project implementation and reduce the implementation cost. The specific generated management system can use the deep learning neural network algorithm to generate a water level prediction model. Therefore, through the analysis of historical data, the relationship between the reservoir water level and the weather environment and the basic parameters of the reservoir is determined, and the reservoir water level can be accurately predicted to achieve accurate deployment and control in advance. Therefore, the management system created by the management system generation platform of this implementation system can not only dynamically and intuitively observe the water level changes of each reservoir, but also accurately control the water level, which plays a certain role in flood control and waterlogging prevention.

[0127] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A zero-code flood control dispatch system generation platform, characterized in that: include: A marking module is used to mark water conservancy projects, lakes and flood control sections on the river sections of the target basin, and the water conservancy projects, lakes and flood control sections are connected through the river sections to generate topological relationships; A configuration module, configuring data information for the water conservancy project and / or section; The generation module generates the flood control dispatching system after applying information verification.

2. A zero-code flood control dispatch system generation platform according to claim 1, characterized in that: The water conservancy projects specifically include reservoirs, flood storage areas and weirs.

3. A zero-code flood control dispatch system generation platform according to claim 2, characterized in that: The configuration module includes: A watershed network topology drawing module (1) is used to select reservoir symbols and runoff symbols in a visual editing interface to form a distributed runoff map of upstream and downstream reservoirs, and input the name of each reservoir in the visual editing interface; A parameter acquisition module (3) is used to acquire reservoir elements in the distributed runoff map, wherein the reservoir elements include the name of each reservoir and the runoff direction of each reservoir; A data acquisition and analysis module (4) is used to obtain the historical water and rainfall data of the reservoir and the basic reservoir parameters and weather environment parameters of the reservoir from the database according to the name of the reservoir, analyze the historical water and rainfall data of each reservoir using a deep learning algorithm, and screen out the influencing factors of the water level of each reservoir and the influence coefficient of each influencing factor from the reservoir parameters and weather environment parameters; A prediction module (5) is used to obtain the influencing factors affecting the water level of each reservoir and the influencing coefficient of each influencing factor based on the data acquisition and analysis module (4), and to dynamically follow up and predict the future water level of the reservoir in combination with the current state of each reservoir; The dispatching model management module (6) marks the corresponding relationship between the different dispatching modes of each reservoir at each flood discharge and the water level drop speed of each reservoir based on the data acquisition and analysis module (4), determines the water level rise speed of each reservoir according to the prediction module (5), and selects the corresponding dispatching mode in combination with the water level rise speed of each reservoir and the relationship between the future water level of each reservoir and the warning water level.

4. A zero-code flood control dispatch system generation platform according to claim 3, characterized in that: Based on the data acquisition and analysis module (4), a historical water level change trend graph of each reservoir is formed; Based on the prediction module (5), a predicted water level change trend graph of each reservoir is formed, and the predicted water level change trend graph and the real-time monitoring water level change trend graph of the same reservoir are integrated into the same trend graph; Based on the scheduling model management model (6), the user can automatically select a scheduling mode that meets the warning water level from all scheduling modes.

5. A zero-code flood control dispatch system generation platform according to claim 3, characterized in that: The data acquisition and analysis module (4) uses a deep learning algorithm to analyze the historical water and rainfall data of each reservoir in the following steps: Obtain the historical water level monitoring data of each reservoir, smooth the historical water level monitoring data, and form a historical water level change trend chart; Extracting a water level rise segment from the historical water level change trend graph, and obtaining the daily rainfall and daily water level increase corresponding to the water level rise segment; The daily water level increase corresponding to the same daily rainfall is extracted from the water level rising section, and the basic parameters of the reservoir when the daily rainfall is the same are obtained. Based on the differentiation of the daily water level increase, a deep learning algorithm is used to determine the relationship between the reservoir water level change and the rainfall duration and the basic parameters of the reservoir. The influencing factors affecting the reservoir water level and the influence coefficient of each of the influencing factors are screened out from the rainfall duration and the basic parameters of the reservoir.

6. A zero-code flood control dispatch system generation platform according to claim 5, characterized in that: The basic parameters of the reservoir include reservoir surface area, water evaporation, reservoir depth and underground seepage; The weather environment parameters include temperature, humidity and rainfall intensity; Among them, firstly, the correlation model between the weather environment parameters and the basic parameters of the reservoir and the internal relationship between the basic parameters of the reservoir is established, and then the influencing factors related to the reservoir water level and the influencing coefficient of each influencing factor are screened out from the basic parameters of the reservoir, and the influencing factors are specifically water evaporation and underground seepage; Determine the specific value of the water evaporation and the specific value of the underground seepage by using the association model, and determine the influence trend of the current influencing factors on the reservoir water level based on the influence of each unit of water evaporation and underground seepage on the reservoir water level by using the association model; The calculation method of the future water level FW of the reservoir is: FW=∑ t {NW(t)+J(t)-[(A(t)*α+B(t)*β]}; Among them, NW(t)=NW(t-1)+J(t-1)-[(A(t-1)*α+B(t-1)*β]; FW is the future water level of the reservoir; NW(t) is the water level at the current moment, J(t) is the rainfall at the current moment, A(t) is the specific value of influencing factor A, α is the influence coefficient of influencing factor A; B(t) is the specific value of influencing factor B, β is the influence coefficient of influencing factor B.

7. A zero-code flood control dispatch system generation platform according to claim 6, characterized in that: The historical water and rainfall data are divided into a training set and a test set, the training set is tested using a deep learning algorithm to generate a water level prediction model, and the test set is used to adjust the model parameters of the water level prediction model. The specific implementation method is: The historical water level monitoring data of each reservoir in the test set is used to form a historical water level change trend graph; Based on the initial water level value of the water level rise section in the historical water level change trend diagram, and the basic reservoir parameters and weather environment parameters during the water level rise section; The basic parameters of the reservoir, weather environment parameters and initial water level values ​​are imported into the water level prediction model to form a predicted water level rise curve. The water level prediction model is adjusted based on the degree of fit between the predicted water level rise curve and the water level rise segment. The above operation is repeated until the degree of fit between the predicted water level rise curve and the water level rise segment meets expectations.

8. A zero-code flood control dispatch system generation platform according to claim 6, characterized in that: The prediction module (5) combines the current state of each reservoir to dynamically follow the prediction of the future water level of the reservoir in the following way: Real-time monitoring of the current water level of the reservoir, as well as the current total rainfall in the reservoir; Based on the current weather environment parameters of the reservoir, the specific value of the water evaporation amount and the specific value of the underground seepage amount of the current reservoir are updated in real time using the association model; Based on the specific value of the water evaporation amount and the specific value of the underground seepage amount of the current reservoir updated in real time, combined with the calculation formula of the future water level of the reservoir, the latest water level of the reservoir is calculated in real time.

9. A zero-code flood control dispatch system generation platform according to claim 8, characterized in that: The dispatch model management model (6) includes a flood discharge level prediction unit and a dispatch mode selection unit; The flood discharge level prediction unit is used to establish a relationship between each scheduling mode and the water level reduction speed according to the deep learning result of the data acquisition and analysis module (4); The dispatching mode selection unit predicts the future water level of the reservoir based on the prediction module (5), and determines the reservoir water level after flood discharge under each dispatching mode in combination with the flood discharge water level of each dispatching mode in the future flood discharge period, and selects the dispatching mode based on the standard that the reservoir water level after flood discharge does not exceed the warning water level; When the water level of the reservoir after flood discharge is less than the warning water level, the dispatching mode selection unit is used to select the corresponding dispatching mode. The specific implementation method is as follows: When the current water level is at the warning water level, the prediction module (5) is used to predict the future water level of the reservoir within a set time in the future; Through simulation operation, the reservoir's flood discharge drop level under each dispatching mode within the future set time is calculated, and the future reservoir water level and flood discharge drop level are superimposed; If the difference between the future water level of the reservoir and the flood discharge drop water level is less than the warning water level, the dispatching mode is retained; If the difference between the future water level of the reservoir and the flood discharge drop water level is greater than the warning water level, the scheduling mode is screened out.

10. A zero-code flood control dispatch system generation platform according to claim 9, characterized in that: The flood discharge level prediction unit is used to establish the relationship between each scheduling mode and the water level reduction speed according to the deep learning result of the data acquisition analysis module (4) in the following manner: Obtain the flood discharge working section in the historical water level change trend diagram of each reservoir; Eliminate the influence of flood discharge inflow, rainfall and level drop of influencing factors from the reservoir water level in the flood discharge working section to obtain the rated water level of each reservoir, and form a flood discharge water level change diagram of the flood discharge working section; Based on the water level drop speed of the flood discharge level change diagram, the relationship between each scheduling mode and the water level drop speed is determined.

Images