River channel bed forming flow range calculation method and device, electronic equipment and storage medium

By obtaining the inlet flow sequence and hydrological prediction model of the river channel, establishing a functional relationship between water level and sand content, and calculating the flow range of the riverbed, solving the problem of insufficient calculation accuracy of bed flow in the existing technology, and realizing the riverbed construction Accurate evaluation of bed flow range.

CN118917226AActive Publication Date: 2024-11-08THREE GORGES GROUP IND DEVELOPMENT (BEIJING) CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411415914.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-11-08
Estimated Expiration
2044-10-11

AI Technical Summary

Technical Problem

The calculation accuracy of riverbed flow in the prior art is insufficient, especially when there is no observation channel and the complex mechanism of river evolution cannot be fully reflected.

Method used

By obtaining the inlet flow sequence, flat water level and sand loading force of the river to be tested, input it into the pre-trained hydrological prediction model, establish a functional relationship between water level and sand content, determine the evaluation parameter value of the bed construction degree, and then calculate the river bed construction Flow range.

Benefits of technology

It improves the calculation accuracy of the riverbed flow range, can be promoted and applied in observable river channels, and provides a more scientific basis for design and operation of water conservancy engineering.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917226A_ABST
    Figure CN118917226A_ABST
Patent Text Reader

Abstract

The invention discloses a method and device for calculating the flow range of river channel bed making, electronic equipment and a storage medium, and belongs to the field of hydrological data processing. The method comprises the following steps: inputting flow corresponding to each flow level in an inlet flow sequence into a pre-trained hydrological prediction model to obtain a section water level prediction value, a section flow prediction range and a section sand content prediction range associated with each flow level; determining a section sand content upper limit and a section sand content lower limit associated with each water level level according to the section water level predicted value of each water level level and the first function relationship; determining a bed building degree evaluation parameter value according to the section water level predicted value, the flat beach water level and the sand carrying capacity of each water level level, and the section sand content upper limit and the section sand content lower limit associated with each water level level; determining a target section water level value according to the target water level associated with the minimum evaluation parameter value; according to the target section water level value and the second function relation, the river channel bed forming flow range of the section is determined.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of hydrological data processing, and specifically relates to a method, device, electronic equipment and storage medium for calculating the flow range of river bed formation. Background Art

[0002] Bed-forming flow is the characteristic flow that characterizes river channel evolution, representing the flow value that dominates the shaping of river channel cross-sectional morphology. Determining bed-forming flow is often difficult because excessive flow is rare and therefore ineffective in shaping riverbed morphology. Excessively low flow, however, is insufficient and similarly ineffective in influencing riverbed morphology. Traditional methods for calculating bed-forming flow include using the flow through the section when the water level is flush with the bank as the bed-forming flow, or using the Makaveev method.

[0003] Current technical solutions, on the one hand, rely on measured data and can only determine bed-forming discharges for sections with observations, making them inapplicable to rivers without such data. On the other hand, empirical formulas such as the Makaveev equation, which assumes the water level is level with the bank, fail to fully reflect the complex mechanisms of river channel evolution. Accurately determining bed-forming discharges is crucial for river management planning and design, requiring the adoption of more scientific and comprehensive calculation and analysis methods.

[0004] Therefore, the current calculation accuracy of the flow range for river bed formation is insufficient. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for calculating the flow range of river bed formation, which can solve the current problem of insufficient calculation accuracy of the flow range of river bed formation.

[0006] In a first aspect, an embodiment of the present application provides a method for calculating a flow range for riverbed formation, the method comprising: Obtain the inlet flow sequence, flat water level, and sediment entrainment of the river to be measured. The inlet flow sequence includes the flow during the rising and falling water processes. The starting and ending flows of the inlet flow sequence are equal to the lower limit of the flow study range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow study range. The flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to obtain the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment concentration prediction range associated with each flow level; According to the predicted value of the cross-section water level and the predicted range of the cross-section sediment content, the first functional relationship is established; According to the predicted value of the cross-section water level and the predicted range of the cross-section flow, a second functional relationship is established; Determine the upper limit and lower limit of cross-section sediment content associated with each water level according to the cross-section water level prediction value of each water level and the first functional relationship; The bed formation degree evaluation parameter values ​​are determined based on the cross-section water level prediction values ​​at each water level level, the flat beach water level, the sediment entrainment capacity, and the upper and lower limits of the cross-section sediment content associated with each water level level. The values ​​of the bed formation degree evaluation parameter values ​​are inversely proportional to the bed formation effect. Determining a target section water level value according to a target water level level associated with a minimum evaluation parameter value; wherein the minimum evaluation parameter value is a minimum value among a plurality of bed formation degree evaluation parameter values; According to the relationship between the target section water level value and the second function, the flow range of the river bed formation in the section is determined.

[0007] In a second aspect, an embodiment of the present application provides a device for calculating a flow range for river bed formation, the device comprising: The acquisition module is used to obtain the inlet flow sequence, flat water level and sediment entrainment of the river channel to be measured. The inlet flow sequence includes the flow during the rising and falling water processes. The starting flow and ending flow of the inlet flow sequence are equal to the lower limit of the flow study range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow study range. An input module is used to input the flow corresponding to each flow level in the inlet flow sequence into a pre-trained hydrological prediction model, run the hydrological prediction model several times, and obtain the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment content prediction range associated with each flow level; A first establishing module is used to establish a first functional relationship according to the cross-section water level prediction value and the cross-section sediment content prediction range; The second establishing module is used to establish a second functional relationship according to the cross-section water level prediction value and the cross-section flow prediction range; A first determining module is used to determine the upper limit and the lower limit of the cross-section sediment content associated with each water level according to the cross-section water level prediction value of each water level and the first functional relationship; The second determination module is used to determine the bed formation degree evaluation parameter value based on the cross-section water level prediction value of each water level level, the flat beach water level, the sediment entrainment capacity, and the cross-section sediment concentration upper limit and cross-section sediment concentration lower limit associated with each water level level; the value of the bed formation degree evaluation parameter value is inversely proportional to the bed formation effect; A third determining module is configured to determine a target section water level value based on a target water level associated with a minimum evaluation parameter value, wherein the minimum evaluation parameter value is a minimum value among a plurality of bed formation degree evaluation parameter values; The fourth determination module is used to determine the riverbed formation flow range of the section according to the target section water level value and the second function relationship.

[0008] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0011] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0012] In the embodiment of the present application, by obtaining the inlet flow sequence, flat water level and sediment entrainment of the river to be measured, the inlet flow sequence includes the flow during the process of rising and falling water, the starting flow and the ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range; the flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to quickly obtain the cross-section water level prediction value, cross-section flow prediction range and cross-section sediment content prediction range associated with each flow level; according to the cross-section water level prediction value and the cross-section sediment content prediction range, a cross-section water level prediction model is established. The first functional relationship; the second functional relationship is established according to the section water level prediction value and the section flow prediction range; through the first functional relationship, the corresponding section sediment content upper limit and section sediment content lower limit can be calculated according to the section water level prediction value of different water level levels, and the bed formation degree evaluation parameter value is determined according to the section water level prediction value of each water level level, the flat beach water level, the sediment entrainment capacity, and the section sediment content upper limit and section sediment content lower limit associated with each water level level. Here, by integrating multi-factor analysis, the water level, sediment content characteristics and sediment entrainment capacity are comprehensively considered to calculate the bed formation degree evaluation parameter value corresponding to each water level level, which can improve the scientific nature of decision-making through quantitative evaluation parameter values. Since the numerical value of the bed-forming degree evaluation parameter is inversely proportional to the bed-forming effect, the target water level associated with the minimum evaluation parameter value is the water level with the strongest bed-forming effect. The target section water level value is determined based on the target water level associated with the minimum evaluation parameter value; based on the target section water level value and the second function relationship, the river bed-forming flow range of the section can be accurately determined, which provides a more scientific basis for the subsequent design and operation of water conservancy projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flow chart of a method for calculating the flow range of river bed formation provided in an embodiment of the present application; Figure 2 This is a schematic diagram of an import flow sequence provided in an embodiment of the present application; Figure 3 is a schematic diagram of a first functional relationship provided in an embodiment of the present application; Figure 4 is a schematic diagram of a second functional relationship provided in an embodiment of the present application; Figure 5 This is a structural diagram of a device for calculating the flow range of a river bed formation provided in an embodiment of the present application; Figure 6 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will be combined with the accompanying drawings of the embodiments of the present application to clearly describe the technical solutions of the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0015] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0016] The method for calculating the flow range of river bed formation provided in the embodiment of the present application can be applied to at least the following application scenarios, which are described below.

[0017] Bed-forming flow refers to the flow that has the greatest impact on the riverbed during a specific time period (usually a hydrological year), compared to other flows during the same period. This flow is not equal to the maximum flood flow, but rather refers to the flow whose bed-forming effect is equal to the combined bed-forming effect of multi-year flow processes.

[0018] In practical applications, the bed-forming flow rate is often used as the design flow rate for reclaimed water treatment, also known as the treatment flow rate. It serves as the basis for designing treatment lines and structures. Numerous methods exist for calculating the bed-forming flow rate, which requires a comparative evaluation process. In practice, the flatland flow rate is often used as the treatment flow rate. While floodwaters have a strong bed-forming effect, the duration is short, making it ineffective in controlling bed formation. Dry seasons, while long, have a less pronounced effect due to the low flow rate.

[0019] The main functions of bed flow prediction are as follows: Understanding river channel evolution trends and predicting bed-forming flows allows us to analyze changes in river channel morphology under different flow conditions and understand long-term river channel evolution trends. This is crucial for river management planning and decision-making.

[0020] Guiding engineering design, bed flow prediction can provide a basis for river engineering design, such as the design of embankments, revetments, riverbed stabilization measures, etc., to ensure the effectiveness and safety of the project.

[0021] Guiding scouring and sedimentation control and mastering the prediction results of bed-forming flow can provide a reference for scouring and sedimentation control in river channels, such as rationally scheduling sediment discharge and dredging river channels. This helps maintain the flood-carrying capacity of the river channel and the ecological environment.

[0022] Supporting disaster prevention and reduction, bed-making flow prediction helps predict river deformation during floods, provides a scientific basis for flood prevention and disaster reduction warnings, and reduces disaster risks.

[0023] Optimize water resource allocation, and the bed flow prediction results can provide information support for the rational allocation of water resources, such as reservoir scheduling, water supply planning, etc.

[0024] Therefore, bed-forming flow prediction provides an important scientific basis for river management and planning, and is of great significance for promoting the sustainable utilization of river resources.

[0025] In response to the problems arising in the related art, the embodiments of the present application provide a method and device for calculating the flow range of river bed construction, which can solve the problem of insufficient calculation accuracy of the flow range of river bed construction in the related art.

[0026] The method for calculating the flow range of river bed formation provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0027] Figure 1 A flow chart of a method for calculating the flow range of river bed formation provided in an embodiment of the present application.

[0028] like Figure 1As shown, the method for calculating the flow range of a river bed formation may include steps 110 to 180. The method is applied to a device for calculating the flow range of a river bed formation, and is specifically as follows: Step 110: Obtain the inlet flow sequence, flat water level, and sediment entrainment of the river channel to be measured. The inlet flow sequence includes the flow during the rising and falling water levels. The starting and ending flow rates of the inlet flow sequence are equal to the lower limit of the flow study range, and the peak flow rate of the inlet flow sequence is equal to the upper limit of the flow study range. Step 120: Input the flow rate corresponding to each flow level in the inlet flow sequence into a pre-trained hydrological prediction model, run the hydrological prediction model several times, and obtain the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment concentration prediction range associated with each flow level; Step 130, establishing a first functional relationship based on the cross-section water level prediction value and the cross-section sediment content prediction range; Step 140: establishing a second functional relationship based on the cross-sectional water level prediction value and the cross-sectional flow prediction range; Step 150, determining the upper limit and lower limit of the cross-section sediment concentration associated with each water level according to the cross-section water level prediction value of each water level and the first functional relationship; Step 160: Determine a bed formation degree evaluation parameter value based on the cross-sectional water level prediction value for each water level, the flat beach water level, the sediment entrainment capacity, and the upper and lower limits of the cross-sectional sediment concentration associated with each water level. The value of the bed formation degree evaluation parameter value is inversely proportional to the bed formation effect. Step 170, determining a target cross-section water level value based on a target water level associated with a minimum evaluation parameter value; the minimum evaluation parameter value is the minimum value among a plurality of bed formation degree evaluation parameter values; Step 180: Determine the flow range of the riverbed formation at the section based on the target section water level value and the second function relationship.

[0029] In the embodiment of the present application, by obtaining the inlet flow sequence, flat water level and sediment entrainment of the river to be measured, the inlet flow sequence includes the flow during the process of rising and falling water, the starting flow and the ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range; the flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to quickly obtain the cross-section water level prediction value, cross-section flow prediction range and cross-section sediment content prediction range associated with each flow level; according to the cross-section water level prediction value and the cross-section sediment content prediction range, a cross-section water level prediction model is established. The first functional relationship; the second functional relationship is established according to the section water level prediction value and the section flow prediction range; through the first functional relationship, the corresponding section sediment content upper limit and section sediment content lower limit can be calculated according to the section water level prediction value of different water level levels, and the bed formation degree evaluation parameter value is determined according to the section water level prediction value of each water level level, the flat beach water level, the sediment entrainment capacity, and the section sediment content upper limit and section sediment content lower limit associated with each water level level. Here, by integrating multi-factor analysis, the water level, sediment content characteristics and sediment entrainment capacity are comprehensively considered to calculate the bed formation degree evaluation parameter value corresponding to each water level level, which can improve the scientific nature of decision-making through quantitative evaluation parameter values. Since the numerical value of the bed-forming degree evaluation parameter is inversely proportional to the bed-forming effect, the target water level associated with the minimum evaluation parameter value is the water level with the strongest bed-forming effect. The target section water level value is determined based on the target water level associated with the minimum evaluation parameter value; based on the target section water level value and the second function relationship, the river bed-forming flow range of the section can be accurately determined, which provides a more scientific basis for the subsequent design and operation of water conservancy projects.

[0030] Steps 110 to 180 are described below: Step 110: Obtain the inlet flow sequence, flat water level, and sediment entrainment of the river channel to be measured. The inlet flow sequence includes the flow during the rising and falling water levels. The starting and ending flow rates of the inlet flow sequence are equal to the lower limit of the flow study range, and the peak flow rate of the inlet flow sequence is equal to the upper limit of the flow study range. We need to obtain the entire flow time series data at the inlet of the river, including flow values ​​at various moments during the flooding and falling processes. Flat water level refers to the water level under normal conditions without flooding, and sediment carrying capacity refers to the amount of sediment that the river can carry and transport. These data are essential for subsequent analysis. The following describes each of these: The flat water level refers to the water level when the cross-section of the river reaches a balanced state under a certain flow rate. It reflects the sediment holding capacity of the river and is an important indicator for measuring the river's passing capacity. The higher the flat water level, the stronger the sediment holding capacity of the river and the faster the siltation rate.

[0031] Sediment-carrying capacity, also known as sand-carrying capacity or pushing capacity, refers to the ability of a river to carry or push sand of a certain particle size at a certain section. The sediment-carrying capacity is determined by factors such as flow velocity, flow rate, and water depth. The greater the sediment-carrying capacity, the easier it is to scour the river channel and the slower the siltation rate.

[0032] The flat water level and sediment-carrying capacity reflect the movement characteristics of the river channel and are important physical factors in the river development process. They are interrelated and have important significance for river channel regulation and water environment management.

[0033] like Figure 2 As shown, with time on the horizontal axis and flow rate on the vertical axis, an "isosceles triangle" inlet flow sequence is established to simulate the process of rising and falling water. The flow sequence uses Ra as the valley value at the start and end of the sequence, and the starting and ending flow rates of the inlet flow sequence are equal to the lower limit of the flow study range. Using Rb as the peak value, the flow sequence is divided into flow levels, that is, the peak flow rate of the inlet flow sequence is equal to the upper limit of the flow study range.

[0034] Step 120: Input the flow rate corresponding to each flow level in the inlet flow sequence into a pre-trained hydrological prediction model, run the hydrological prediction model several times, and obtain the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment concentration prediction range associated with each flow level; The previously collected inlet flow series data was fed into a pre-established hydrological forecasting model. The model was run multiple times to produce the model's output, which included predicted values ​​and ranges for future water levels, flow rates, and sediment concentrations for the river section.

[0035] In a possible embodiment, before step 120, the following steps may be further included: Obtain flow research range and bed-making flow accuracy; The flow research range is divided into multiple flow levels according to the bed-making flow accuracy.

[0036] Determine the flow range to be covered by the study based on the river's characteristics and management objectives. This typically includes daily baseflow, typical flood flows, and extreme flood flows. Collect flow observation data for as long as possible to fully capture flow variability. For rivers without observational data, flow simulations can be performed using methods such as hydrological models.

[0037] Specifically, the flow study range [Ra, Rb] is determined based on the hydrological frequency, ranging from 10-year (Ra) to 100-year (Rb). Once the range is determined, the flow levels are further divided according to the required accuracy. For example, if the bed formation flow accuracy is required to be 50 m³ / s, the flow levels can be set to 50 m³ / s.

[0038] For example, the flow research range is determined as [2000, 8000] according to the hydrological frequency from 10-year (Ra) to 100-year (Rb). After the range is determined, the flow level is further divided according to the accuracy requirements. Since the level accuracy of the bed flow is required to be 50m 3 / s, so the flow rate is set to every 50m 3 / s is a flow level, which divides the flow range.

[0039] Therefore, by reasonably dividing the flow research scope and accuracy level, targeted analysis methods can be adopted according to actual needs to improve the scientificity and effectiveness of river management.

[0040] In a possible embodiment, before step 120, the following steps may be further included: Step 210: Obtain the river section inlet flow and labeled hydrological data, where the labeled hydrological data includes: section water level label data, section flow label data, and section sediment content label data; Step 220, inputting the river section inlet flow into a preset LSTM to obtain predicted hydrological data; Step 230 : training a preset LSTM according to the predicted hydrological data and the labeled hydrological data until the preset LSTM meets the preset training conditions, thereby obtaining a hydrological prediction model.

[0041] Involving step 210, obtaining the river section inlet flow and label hydrological data, obtaining the river section inlet flow data from relevant data sources, and at the same time obtaining the section water level label data, section flow label data and section sediment content label data of the river section through the water and sediment mathematical model.

[0042] In a possible embodiment, step 210 includes: Obtain measured cross-section topographic data, river section inlet flow and river section sediment concentration process data; The measured cross-section topographic data, river section inlet flow and river section sediment content process data are input into the pre-established water and sediment mathematical model to obtain the labeled hydrological data, flat water level and sediment carrying capacity of each river section.

[0043] For example, the river channel to be measured is 150 km long. In order to obtain the approximate range of bed-forming flow at a certain section A in this river channel, a water-sediment mathematical model can be established.

[0044] Specifically, a one-dimensional water-sediment mathematical model was established, and the topographic scatter data of the river section measured in 2012 were input. The sections were spaced an average of 1 to 1.5 km apart, with a total of 80 sections, each consisting of a series of xz elevation scatter points. The model was fed with the temporal changes in the river inlet flow Qin (t) and sediment content Sin (t) in the flood year of 2012, the dry year of 2013, and the normal year of 2015. The model was then simulated to calculate the temporal changes in the water level Z(t), flow Q(t), and sediment content S(t) of section A in the river, as well as the flat water level Z*=15.5m and sediment carrying capacity S*=0.64kg / m 3 ,The time interval of data input and output is interpolated to 30 s, so the mapping relationships between the inlet flow and the water level, flow and sediment content of section A are obtained, which are 3,156,480 sets of data.

[0045] In step 220, a preset LSTM (Long Short-Term Memory) model is selected or built, and the acquired river section inlet flow data is input into the LSTM model. The LSTM model predicts the corresponding water level, flow and sediment content data based on the input flow data.

[0046] Involving step 230, the hydrological data predicted by the LSTM model in step 220 is compared with the labeled hydrological data obtained in step 210. The difference between the predicted data and the labeled data is used to continuously optimize the weight parameters of the LSTM model through the back propagation algorithm. The training process is repeated until the LSTM model meets the preset training conditions, such as the prediction error is less than the preset error threshold, and finally a trained hydrological prediction model is obtained.

[0047] Therefore, the LSTM model can be used to predict and simulate river hydrological processes. A well-trained hydrological prediction model can handle large-scale inflow flow sequences, improving prediction efficiency.

[0048] In a possible embodiment, the preset LSTM includes: a first LSTM, a second LSTM, and a third LSTM. Step 230 includes: Input the river section inlet flow into the first LSTM, the second LSTM and the third LSTM respectively to obtain the cross-section water level prediction data, the cross-section flow prediction data and the cross-section sediment concentration prediction data; Training the first LSTM based on the section water level prediction data and the section water level label data; and Training the second LSTM based on the section flow prediction data and the section flow label data; and Train the third LSTM based on the cross-section sediment content prediction data and cross-section sediment content label data; Until the first LSTM, the second LSTM and the third LSTM meet the preset training conditions, a hydrological prediction model is obtained.

[0049] The pre-set LSTMs include a first LSTM, a second LSTM, and a third LSTM, totaling three deep learning LSTMs. The inlet flow process Qin (t) from the water-sediment mathematical model in step 210 is used as input. The water level, flow rate, and sediment concentration at section A calculated by the model serve as prediction targets for the three LSTM models. The training data volume is 3,156,480 sets. After completing training and testing of the three LSTM models, it was determined that the LSTM predictions at each step based on the past seven flow values ​​were the most accurate.

[0050] The flow rate corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times. That is, the flow sequence is input into three LSTM models in batches according to n flow levels each time, and the LSTM model is run several times to obtain the section water level prediction value, section flow prediction range and section sediment content prediction range associated with each flow level.

[0051] Based on the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment concentration prediction range associated with each flow level, the first functional relationship and the second functional relationship are established. They are explained below: Step 130, establishing a first functional relationship based on the cross-section water level prediction value and the cross-section sediment content prediction range; Taking the predicted value of the section water level as the independent variable and the predicted range of the section sediment content as the dependent variable, a functional relationship between the section water level and the section sediment content is established through curve fitting or other mathematical modeling methods.

[0052] For example, the flow sequence will be 2000m 3 / s as the valley value of the sequence start and end positions, and 8000m 3 / s is used as the peak value, and the flow sequence is divided into 241 flow levels. The flow sequence is fed into three LSTM models in batches of seven flow levels, determined in the above steps. The LSTM models are run several times to predict the water level and sediment concentration ranges at each section of the river. This prediction establishes a relationship between the cross-section water level and sediment concentration range.

[0053]

[0054] In formula (1), z is the predicted value of the cross-section water level, S range It is the predicted range of cross-section sediment content.

[0055] The first functional relationship between the predicted value of the cross-section water level and the predicted range of the cross-section sediment concentration is as follows: Figure 3As shown, the horizontal axis is water level, the vertical axis on the left is sediment concentration, and the vertical axis on the right is the bed formation evaluation parameter value. The two solid lines represent the sediment concentration range of the section, and the dotted lines represent the bed formation evaluation parameter values ​​at different water levels and sediment concentrations.

[0056] Step 140: establishing a second functional relationship based on the cross-sectional water level prediction value and the cross-sectional flow prediction range;

[0057] In formula (2), z is the predicted value of the cross-section water level, Q range is the cross-section flow prediction range.

[0058] Taking the predicted value of the section water level as the independent variable and the predicted range of the section flow as the dependent variable, the functional relationship between the section water level and the section flow is established through curve fitting or mathematical modeling methods.

[0059] The second functional relationship between the section water level prediction value and the section flow prediction range is as follows: Figure 4 As shown, the horizontal axis is the water level and the vertical axis is the flow rate.

[0060] Therefore, based on the water level prediction value, the corresponding sediment content prediction range and flow prediction range can be obtained, and two important functional relationships can be established.

[0061] Step 150, determining the upper limit and lower limit of the cross-section sediment concentration associated with each water level according to the cross-section water level prediction value of each water level and the first functional relationship; By substituting the water level prediction values ​​of different water level levels into the first functional relationship (the functional relationship between the cross-section water level and the cross-section sediment content), the upper and lower limits of the sediment content corresponding to each water level level can be determined.

[0062] Assuming that every 0.2m is one water level level, the water level Z is substituted into the first functional relationship to obtain the upper and lower limits of sediment content at each water level.

[0063] Step 160: Determine a bed formation degree evaluation parameter value based on the cross-sectional water level prediction value for each water level, the flat beach water level, the sediment entrainment capacity, and the upper and lower limits of the cross-sectional sediment concentration associated with each water level. The value of the bed formation degree evaluation parameter value is inversely proportional to the bed formation effect. In a possible embodiment, step 160 may specifically include the following steps: For any water level, the water level evaluation parameter value is determined based on the cross-section water level prediction value and the flat beach water level; Determine the average sediment content based on the upper limit of the sediment content range of the section and the lower limit of the sediment content range of the section; Determine the sediment content evaluation parameter value based on the average sediment content and sediment carrying capacity; The bed formation degree evaluation parameter value is determined based on the water level evaluation parameter value and the sediment content evaluation parameter value.

[0064] The evaluation parameter values ​​of bed formation degree under each water level and sediment content, such as Figure 3 As shown, the horizontal axis is water level, the vertical axis on the left is sediment concentration, and the vertical axis on the right is the bed formation evaluation parameter value. The two solid lines represent the sediment concentration range of the section, and the dotted lines represent the bed formation evaluation parameter values ​​at different water levels and sediment concentrations.

[0065] For any water level, the water level evaluation parameter value is determined based on the section water level prediction value and the flat beach water level.

[0066] Water level evaluation parameter value = (cross-section water level prediction value - flat beach water level) / maximum water level difference; The water level evaluation parameter value indicates the degree of difference between the current water level and the flat beach water level, reflecting the impact of the water level on the bed formation process.

[0067] Average sediment content = (upper sediment content + lower sediment content) / 2; The average sediment content is used to represent the sediment content characteristics of the section corresponding to the water level.

[0068] Sediment content evaluation parameter value = (average sediment content - sediment holding capacity) / maximum sediment content difference The sediment content evaluation parameter value reflects the influence of the current water level and cross-section sediment content characteristics on the bed formation process.

[0069] Bed formation degree evaluation parameter value = water level evaluation parameter value + sediment content evaluation parameter value.

[0070] The bed formation degree evaluation parameter values ​​reflect the influence of water level and sediment content on the bed formation process.

[0071] From this, we can calculate the bed-building evaluation parameter value corresponding to each water level. The smaller the parameter value, the stronger the bed-building effect. This information can provide a basis for subsequently determining the target water level and flow range.

[0072] In a possible embodiment, determining a water level evaluation parameter value based on a section water level prediction value and a flat beach water level includes: Determine the maximum water level difference based on the predicted cross-section water level and the flat beach water level; Determine the water level evaluation parameter value based on the section water level prediction value, the maximum water level difference and the flat beach water level; Determining the sediment content evaluation parameter value based on the average sediment content and the sediment holding capacity of the section includes: Determine the maximum sediment content difference based on the average sediment content and sediment carrying capacity; The sediment content evaluation parameter values ​​are determined based on the average sediment content, maximum sediment content difference and sediment carrying capacity.

[0073]

[0074] The smaller it is, the closer the water level is to the flat beach water level, and the closer the cross-section sediment content is to the sediment-carrying capacity, the more obvious the bed-forming effect is.

[0075] Z represents the cross-section water level value predicted by LSTM, Z* represents the flat water level of the cross-section; △Z max Represents the maximum difference between the water level prediction value of the current section and the flat water level; S represents the cross-section sediment content value predicted by LSTM, S* represents the cross-section sediment holding capacity, △S max Represents the maximum difference between the predicted sediment content of the current section and the sediment carrying capacity.

[0076] Step 170, determining a target cross-section water level value based on a target water level associated with a minimum evaluation parameter value; the minimum evaluation parameter value is the minimum value among a plurality of bed formation degree evaluation parameter values; Among the previously calculated values ​​for the bed formation evaluation parameter for each water level, find the water level corresponding to the minimum value. This is the target water level. After calculating the bed formation evaluation parameter values ​​for all water levels and corresponding sediment concentrations, take the target section water level value for which the bed formation evaluation parameter value is the minimum.

[0077] For example, Figure 4 As shown in the figure, the minimum value among the multiple bed formation evaluation parameter values ​​corresponds to a target section water level value of 15.89m.

[0078] Step 180: Determine the flow range of the riverbed formation at the section based on the target section water level value and the second function relationship.

[0079] The flow range [Qa, Qb] corresponding to the target section water level value is calculated through the second functional relationship. This range is the river bed formation flow range of the current section.

[0080] For example, the flow range [Qa, Qb] corresponding to the water level calculated by providing the second functional relationship is approximately [5350, 5650], which is the approximate range value of the bed-forming flow rate of the current section.

[0081] Substituting the determined target water level value into the second functional relationship, the corresponding river bed formation flow range can be obtained.

[0082] Thus, the embodiments of this application can calculate the approximate range of bed-forming flow rates for any section of a river, enriching and supplementing traditional bed-forming flow rates. This solves the problem that current methods, which rely on measured data, can only obtain bed-forming flow rates for sections with observations and cannot be generalized and applied to rivers without observations.

[0083] In the embodiment of the present application, by obtaining the inlet flow sequence, flat water level and sediment entrainment of the river to be measured, the inlet flow sequence includes the flow during the process of rising and falling water, the starting flow and the ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range; the flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to quickly obtain the cross-section water level prediction value, cross-section flow prediction range and cross-section sediment content prediction range associated with each flow level; according to the cross-section water level prediction value and the cross-section sediment content prediction range, a cross-section water level prediction model is established. The first functional relationship; the second functional relationship is established according to the section water level prediction value and the section flow prediction range; through the first functional relationship, the corresponding section sediment content upper limit and section sediment content lower limit can be calculated according to the section water level prediction value of different water level levels, and the bed formation degree evaluation parameter value is determined according to the section water level prediction value of each water level level, the flat beach water level, the sediment entrainment capacity, and the section sediment content upper limit and section sediment content lower limit associated with each water level level. Here, by integrating multi-factor analysis, the water level, sediment content characteristics and sediment entrainment capacity are comprehensively considered to calculate the bed formation degree evaluation parameter value corresponding to each water level level, which can improve the scientific nature of decision-making through quantitative evaluation parameter values. Since the numerical value of the bed-forming degree evaluation parameter is inversely proportional to the bed-forming effect, the target water level associated with the minimum evaluation parameter value is the water level with the strongest bed-forming effect. The target section water level value is determined based on the target water level associated with the minimum evaluation parameter value; based on the target section water level value and the second function relationship, the river bed-forming flow range of the section can be accurately determined, which provides a more scientific basis for the subsequent design and operation of water conservancy projects.

[0084] The method for calculating the flow range of a river bed formation provided in the embodiment of the present application can be executed by a device for calculating the flow range of a river bed formation. In the embodiment of the present application, the device for calculating the flow range of a river bed formation is used as an example to illustrate the method for calculating the flow range of a river bed formation.

[0085] Figure 5 : is a block diagram of a device for calculating a flow range for river bed formation provided in an embodiment of the present application. The device 500 includes: Acquisition module 510 is used to obtain the inlet flow sequence, flat water level, and sediment entrainment of the river channel to be measured. The inlet flow sequence includes the flow during the rising and falling water processes. The starting flow and ending flow of the inlet flow sequence are equal to the lower limit of the flow study range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow study range. Input module 520 is used to input the flow corresponding to each flow level in the inlet flow sequence into a pre-trained hydrological prediction model, run the hydrological prediction model several times, and obtain the cross-section water level prediction value, cross-section flow prediction range, and cross-section sediment concentration prediction range associated with each flow level; A first establishing module 530 is used to establish a first functional relationship based on the cross-section water level prediction value and the cross-section sediment content prediction range; The second establishing module 540 is used to establish a second functional relationship according to the cross-section water level prediction value and the cross-section flow prediction range; A first determining module 550 is configured to determine an upper limit and a lower limit of cross-sectional sediment concentration associated with each water level according to the cross-sectional water level prediction value of each water level and the first functional relationship; The second determination module 560 is used to determine a bed formation degree evaluation parameter value based on the cross-sectional water level prediction value at each water level level, the flat beach water level, the sediment entrainment capacity, and the upper and lower limits of the cross-sectional sediment concentration associated with each water level level. The value of the bed formation degree evaluation parameter value is inversely proportional to the bed formation effect. The third determining module 570 is configured to determine a target cross-section water level value based on a target water level associated with a minimum evaluation parameter value, wherein the minimum evaluation parameter value is the minimum value among multiple bed formation degree evaluation parameter values; The fourth determination module 580 is used to determine the riverbed formation flow range of the section according to the target section water level value and the second functional relationship.

[0086] In a possible embodiment, the second determining module 560 is specifically configured to: For any water level, the water level evaluation parameter value is determined based on the cross-section water level prediction value and the flat beach water level; Determine the average sediment content based on the upper limit of the sediment content range of the section and the lower limit of the sediment content range of the section; Determine the sediment content evaluation parameter value based on the average sediment content and sediment carrying capacity; The bed formation degree evaluation parameter value is determined based on the water level evaluation parameter value and the sediment content evaluation parameter value.

[0087] In a possible embodiment, the second determining module 560 is specifically configured to: Determine the maximum water level difference based on the predicted cross-section water level and the flat beach water level; Determine the water level evaluation parameter value based on the section water level prediction value, the maximum water level difference and the flat beach water level; Determining the sediment content evaluation parameter value based on the average sediment content and the sediment holding capacity of the section includes: Determine the maximum sediment content difference based on the average sediment content and sediment carrying capacity; The sediment content evaluation parameter values ​​are determined based on the average sediment content, maximum sediment content difference and sediment carrying capacity.

[0088] In a possible embodiment, the acquisition module 510 is further used to obtain the flow research range and bed-making flow accuracy; The apparatus 500 may further include: The division module is used to divide the flow research range into multiple flow levels according to the bed-making flow accuracy.

[0089] In a possible embodiment, the acquisition module 510 is further configured to acquire the river section inlet flow and labeled hydrological data, where the labeled hydrological data includes: section water level label data, section flow label data, and section sediment content label data; The input module 520 is further used to input the river section inlet flow into the preset LSTM to obtain predicted hydrological data; The apparatus 500 may further include: The training module is used to train the preset LSTM according to the predicted hydrological data and the labeled hydrological data until the preset LSTM meets the preset training conditions to obtain a hydrological prediction model.

[0090] In a possible embodiment, the preset LSTM includes: a first LSTM, a second LSTM, and a third LSTM, and a training module, specifically configured to: Input the river section inlet flow into the first LSTM, the second LSTM and the third LSTM respectively to obtain the cross-section water level prediction data, the cross-section flow prediction data and the cross-section sediment concentration prediction data; Training the first LSTM based on the section water level prediction data and the section water level label data; and Training the second LSTM based on the section flow prediction data and the section flow label data; and Train the third LSTM based on the cross-section sediment content prediction data and cross-section sediment content label data; Until the first LSTM, the second LSTM and the third LSTM meet the preset training conditions, a hydrological prediction model is obtained.

[0091] In a possible embodiment, the acquisition module 510 is specifically configured to: Obtain measured cross-section topographic data, river section inlet flow and river section sediment concentration process data; The measured cross-section topographic data, river section inlet flow and river section sediment content process data are input into the pre-established water and sediment mathematical model to obtain the labeled hydrological data, flat water level and sediment carrying capacity of each river section.

[0092] In the embodiment of the present application, by obtaining the inlet flow sequence, flat water level and sediment entrainment of the river to be measured, the inlet flow sequence includes the flow during the process of rising and falling water, the starting flow and the ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range; the flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to quickly obtain the cross-section water level prediction value, cross-section flow prediction range and cross-section sediment content prediction range associated with each flow level; according to the cross-section water level prediction value and the cross-section sediment content prediction range, a cross-section water level prediction model is established. The first functional relationship; the second functional relationship is established according to the section water level prediction value and the section flow prediction range; through the first functional relationship, the corresponding section sediment content upper limit and section sediment content lower limit can be calculated according to the section water level prediction value of different water level levels, and the bed formation degree evaluation parameter value is determined according to the section water level prediction value of each water level level, the flat beach water level, the sediment entrainment capacity, and the section sediment content upper limit and section sediment content lower limit associated with each water level level. Here, by integrating multi-factor analysis, the water level, sediment content characteristics and sediment entrainment capacity are comprehensively considered to calculate the bed formation degree evaluation parameter value corresponding to each water level level, which can improve the scientific nature of decision-making through quantitative evaluation parameter values. Since the numerical value of the bed-forming degree evaluation parameter is inversely proportional to the bed-forming effect, the target water level associated with the minimum evaluation parameter value is the water level with the strongest bed-forming effect. The target section water level value is determined based on the target water level associated with the minimum evaluation parameter value; based on the target section water level value and the second function relationship, the river bed-forming flow range of the section can be accurately determined, which provides a more scientific basis for the subsequent design and operation of water conservancy projects.

[0093] The river bed formation flow range calculation device provided in the embodiment of the present application can implement each process implemented in the above method embodiment. To avoid repetition, it will not be described here.

[0094] Optionally, Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0095] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0096] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0097] Memory 402 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway disaster recovery device. In certain embodiments, memory 402 is non-volatile solid-state memory. In certain embodiments, memory 402 includes read-only memory (ROM). Where appropriate, the ROM may be mask-programmable ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0098] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any one of the river bed formation flow range calculation methods in the embodiments shown in the figure.

[0099] In one example, the electronic device may further include a communication interface 404 and a bus 410. Figure 6 As shown, the processor 401 , the memory 402 , and the communication interface 404 are connected via a bus 410 and communicate with each other.

[0100] The communication interface 404 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0101] Bus 410 includes hardware, software, or both that couples components of an electronic device to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0102] The electronic device can execute the riverbed flow range calculation method in the embodiment of the present application, thereby realizing the combination of Figure 1-Figure 4 Described is a method for calculating the flow range for channel formation.

[0103] In addition, in combination with the flow range calculation method for river channel bed formation in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the Figure 1 Calculation method for the flow range of river bed formation.

[0104] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0105] The functional blocks shown in the block diagrams described above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they may be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments may be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or communication link. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memory, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. Code segments may be downloaded via a computer network such as the Internet or an intranet.

[0106] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0107] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for calculating the flow range of river bed construction, characterized in that: The method comprises: Obtain the inlet flow sequence, flat water level and sediment entrainment of the river to be tested. The inlet flow sequence includes the flow during the process of rising and falling water. The starting flow and ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range. The flow corresponding to each flow level in the inlet flow sequence is input into the pre-trained hydrological prediction model, and the hydrological prediction model is run several times to obtain the cross-section water level prediction value, cross-section flow prediction range and cross-section sediment content prediction range associated with each flow level; According to the predicted value of the cross-section water level and the predicted range of the cross-section sediment content, the first functional relationship is established; A second functional relationship is established according to the predicted value of the cross-section water level and the predicted range of the cross-section flow; According to the cross-sectional water level prediction value of each water level level and the first functional relationship, the upper limit of the cross-sectional sediment content and the lower limit of the cross-sectional sediment content associated with each water level level are determined; According to the predicted values ​​of the cross-section water level at each water level level, the flat water level, the sediment entraining force, the upper and lower limits of the cross-section sediment content associated with each water level level, the values ​​of the bed-forming degree evaluation parameters are determined; the values ​​of the bed-forming degree evaluation parameters are inversely proportional to the bed-forming effect; Determining a target section water level value according to a target water level level associated with a minimum evaluation parameter value; the minimum evaluation parameter value is the minimum value among a plurality of bed formation degree evaluation parameter values; According to the water level value of the target section and the second function relationship, the river bed formation flow range of the section is determined.

2. The method according to claim 1, characterized in that The bed formation degree evaluation parameter values ​​are determined according to the predicted values ​​of the cross-section water level at each water level level, the flat beach water level, the sediment entrainment capacity, the upper limit of the cross-section sediment content and the lower limit of the cross-section sediment content associated with each water level level, including: For any water level, the water level evaluation parameter value is determined based on the cross-section water level prediction value and the flat beach water level; Determine the average sediment content based on the upper limit of the sediment content range of the cross section and the lower limit of the sediment content range of the cross section; Determine the sediment content evaluation parameter value based on the average sediment content and sediment carrying capacity; The bed formation degree evaluation parameter values ​​are determined based on the water level evaluation parameter values ​​and the sediment content evaluation parameter values.

3. The method according to claim 2, characterized in that Determining the water level evaluation parameter value according to the cross-section water level prediction value and the flat beach water level includes: Determine the maximum water level difference based on the predicted cross-section water level and the flat beach water level; Determine the water level evaluation parameter value based on the cross-section water level prediction value, the maximum water level difference value and the flat beach water level; Determining the sediment content evaluation parameter value according to the average sediment content and the sediment holding capacity of the cross section includes: According to the average sediment content and sediment-carrying capacity, the maximum sediment content difference is determined; The sediment content evaluation parameter values ​​are determined based on the average sediment content, the maximum sediment content difference and the sediment carrying capacity.

4. The method according to claim 1, characterized in that: Before inputting the flow corresponding to each flow level in the inlet flow sequence into the pre-trained hydrological prediction model, the method further includes: Obtain flow research range and bed-making flow accuracy; The flow research range is divided into multiple flow levels according to the bed-making flow accuracy.

5. The method according to claim 1, characterized in that Before inputting the flow corresponding to each flow level in the inlet flow sequence into the pre-trained hydrological prediction model, the method further includes: Obtain the river section inlet flow and labeled hydrological data. The labeled hydrological data include: section water level label data, section flow label data and section sediment content label data; Input the inlet flow of the river section into the preset LSTM to obtain the predicted hydrological data; According to the predicted hydrological data and the labeled hydrological data, the preset LSTM is trained until the preset LSTM meets the preset training conditions to obtain a hydrological prediction model.

6. The method according to claim 5, characterized in that The preset LSTM includes: a first LSTM, a second LSTM and a third LSTM. The preset LSTM is trained according to the predicted hydrological data and the labeled hydrological data until the preset LSTM meets the preset training conditions to obtain a hydrological prediction model, including: Input the inlet flow of the river section into the first LSTM, the second LSTM and the third LSTM respectively, and obtain the cross-section water level prediction data, the cross-section flow prediction data and the cross-section sediment content prediction data respectively; Training the first LSTM according to the section water level prediction data and the section water level label data; and, Training the second LSTM according to the cross-sectional flow prediction data and the cross-sectional flow label data; and, The third LSTM is trained based on the cross-section sediment content prediction data and cross-section sediment content label data; Until the first LSTM, the second LSTM and the third LSTM meet the preset training conditions, a hydrological prediction model is obtained.

7. The method according to claim 5, characterized in that The method of obtaining the river section inlet flow and label hydrological data includes: Obtain measured cross-section topographic data, river section inlet flow and river section sediment content process data; The measured cross-section topographic data, river section inlet flow and river section sediment content process data are input into the pre-established water-sediment mathematical model to obtain the labeled hydrological data, flat water level and sediment-carrying capacity of each section of the river.

8. A device for calculating the flow range of a river bed formation, characterized in that: The device comprises: The acquisition module is used to obtain the inlet flow sequence, flat water level and sediment entrainment of the river to be tested. The inlet flow sequence includes the flow during the process of rising and falling water. The starting flow and ending flow of the inlet flow sequence are equal to the lower limit of the flow research range, and the peak flow of the inlet flow sequence is equal to the upper limit of the flow research range. An input module is used to input the flow corresponding to each flow level in the inlet flow sequence into a pre-trained hydrological prediction model, run the hydrological prediction model several times, and obtain the cross-sectional water level prediction value, cross-sectional flow prediction range, and cross-sectional sediment content prediction range associated with each flow level; A first establishing module is used to establish a first functional relationship according to a predicted value of a cross-section water level and a predicted range of a cross-section sediment content; A second establishing module is used to establish a second functional relationship according to the cross-section water level prediction value and the cross-section flow prediction range; A first determination module is used to determine the upper limit and lower limit of the cross-section sediment content associated with each water level level according to the cross-section water level prediction value of each water level level and the first functional relationship; The second determination module is used to determine the bed formation degree evaluation parameter value according to the cross-section water level prediction value of each water level level, the flat beach water level, the sediment entrainment force, the cross-section sediment content upper limit and the cross-section sediment content lower limit associated with each water level level; the value of the bed formation degree evaluation parameter value is inversely proportional to the bed formation effect; A third determination module is used to determine the target section water level value according to the target water level level associated with the minimum evaluation parameter value; the minimum evaluation parameter value is the minimum value among the multiple bed formation degree evaluation parameter values; The fourth determination module is used to determine the riverbed-forming flow range of the section according to the target section water level value and the second functional relationship.

9. The device according to claim 8, characterized in that The second determination module is specifically used for: For any water level, the water level evaluation parameter value is determined based on the cross-section water level prediction value and the flat beach water level; Determine the average sediment content based on the upper limit of the sediment content range of the cross section and the lower limit of the sediment content range of the cross section; Determine the sediment content evaluation parameter value based on the average sediment content and sediment carrying capacity; The bed formation degree evaluation parameter values ​​are determined based on the water level evaluation parameter values ​​and the sediment content evaluation parameter values.

10. The device according to claim 9, characterized in that The second determination module is specifically used for: Determine the maximum water level difference based on the predicted cross-section water level and the flat beach water level; Determine the water level evaluation parameter value based on the cross-section water level prediction value, the maximum water level difference value and the flat beach water level; Determining the sediment content evaluation parameter value according to the average sediment content and the sediment holding capacity of the cross section includes: According to the average sediment content and sediment-carrying capacity, the maximum sediment content difference is determined; The sediment content evaluation parameter values ​​are determined based on the average sediment content, the maximum sediment content difference and the sediment carrying capacity.

11. The device according to claim 8, characterized in that The acquisition module is also used to obtain the flow research range and bed-making flow accuracy; The device for calculating the flow range of river bed construction also includes: The division module is used to divide the flow research range into multiple flow levels according to the bed-making flow accuracy.

12. The device according to claim 8, characterized in that The acquisition module is also used to obtain the river section inlet flow and label hydrological data, the label hydrological data includes: section water level label data, section flow label data and section sediment content label data; The input module is also used to input the river section inlet flow into the preset LSTM to obtain the predicted hydrological data; The device for calculating the flow range of river bed construction also includes: The training module is used to train the preset LSTM according to the predicted hydrological data and the labeled hydrological data until the preset LSTM meets the preset training conditions to obtain the hydrological prediction model.

13. The device according to claim 12, characterized in that Get the module, specifically for: Obtain measured cross-section topographic data, river section inlet flow and river section sediment content process data; The measured cross-section topographic data, river section inlet flow and river section sediment content process data are input into the pre-established water-sediment mathematical model to obtain the labeled hydrological data, flat water level and sediment-carrying capacity of each section of the river.

14. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for calculating the flow range of river bed formation as claimed in any one of claims 1-7 is implemented.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the method for calculating the flow range of river bed formation as described in any one of claims 1-7.

Citation Information

Patent Citations

  • Method for jointly determining bed-building flow and flat beach water level of tidal river reach

    CN110555248A

  • Bed flow calculation method based on sand carrying capacity of water flow

    CN112989565A

  • Creating and using multiple packet traffic profiling models to profile packet flows

    US20120281590A1