A method and device for optimizing sediment model parameters and simulating sediment transport process

Abstract

The present invention provides a method and device for optimizing sediment model parameters and simulating sediment transport processes, wherein the sediment model parameter optimization method includes: establishing an optimization objective function in combination with a first initial neural network model, a second initial neural network model, and a water-sand model, wherein the restoration saturation coefficient and roughness in the water-sand model are determined by the second initial neural network model; solving the optimization objective function, optimizing the first network model parameters and the second network model parameters, and obtaining the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function; determining the second initial neural network model including the second network model optimization parameters as a restoration saturation coefficient and roughness dual-parameter optimization model. The restoration saturation coefficient and roughness determined by the restoration saturation coefficient and roughness dual-parameter optimization model optimized by the method provided in the embodiment of the present invention are more consistent with the actual physical process.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering simulation and numerical simulation, and in particular to a method and device for optimizing sediment model parameters and simulating sediment transport process. Background Art

[0002] The simulation and forecast of reservoir sediment is generally based on the methods of hydraulics and river dynamics. By analyzing the complex river network information in the reservoir area, a reservoir sediment forecasting model is established, and the sediment transport process under different water and sediment conditions is analyzed in real time. The recovery saturation coefficient is an important parameter for the calculation of the sediment mathematical model. It is a comprehensive coefficient that requires inverse calculation based on measured data. However, there are many influencing factors, which are related to both water flow conditions and sediment conditions, and they change anytime and anywhere. At the same time, the roughness parameter is an important parameter of the hydrodynamic module in the model, and it also has the characteristics of time-varying. Different water and sediment conditions will affect its value.

[0003] The recovery saturation coefficient and roughness parameters of the traditional sediment model have time-varying characteristics. In application, there is a large adjustment range, and the calibration and optimization are highly dependent on the personal experience of the debugger. The parameters of the general neural network fitting are mainly based on mathematical statistical methods to select the optimal solution, lack strong constraints on the physical process, and have no physical meaning. There are often situations where the solution is not unique and overfitting does not conform to the actual physical process. At the same time, the fitting process requires continuous solution of the control equation, which has a large amount of calculation, limiting the further development and application of the model. Summary of the invention

[0004] Therefore, the technical problem to be solved by the present invention is to overcome the defects in the prior art that the parameters fitted by the neural network have no physical meaning, and the output results of the optimized neural network model do not conform to the actual physical process, thereby providing a method and device for optimizing sediment model parameters and simulating sediment transport process.

[0005] The invention provides a method for optimizing sediment model parameters, comprising the following steps: establishing an optimization objective function by combining a first initial neural network model, a second initial neural network model, and a water-sand model, wherein the water-sand parameters in the water-sand model are determined by the first initial neural network model, the recovery saturation coefficient and the roughness in the water-sand model are determined by the second initial neural network model, and the optimization objective function is determined according to the sum of simulation residuals of each water-sand model; solving the optimization objective function, optimizing the first network model parameters and the second network model parameters, obtaining the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function, wherein the first network model is the parameters in the first initial network model, and the second network model parameters are the parameters in the second initial network model; and determining the second initial neural network model containing the second network model optimization parameters as a dual-parameter optimization model of recovery saturation coefficient and roughness.

[0006] Optionally, in the sediment model parameter optimization method provided by the present invention, the simulation residuals of the water-sediment model include the residuals of the water flow continuity equation, the residuals of the water flow motion equation, the residuals of the sediment continuity equation, and the residuals of the riverbed deformation equation.

[0007] Optionally, in the sediment model parameter optimization method provided by the present invention, the water and sediment parameters determined by the first initial neural network model include flow and water level, and the optimization objective function also includes the approximation error of the flow output by the first initial neural network model to the actual flow, and the approximation error of the water level output by the first initial neural network model to the actual water level.

[0008] Optionally, in the sediment model parameter optimization method provided by the present invention, the simulation residual of the water-sediment model includes:

[0009]

[0010] Among them, e1 represents the residual of the water flow continuity equation, e2 represents the residual of the water flow motion equation, e3 represents the residual of the sediment continuity equation, e4 represents the residual of the riverbed deformation equation, B represents the water surface width, Z s Indicates water level, Q s represents flow, t represents time, x represents space, q L represents the lateral inflow per unit river length, A represents the water cross-sectional area, g represents the gravitational acceleration, and n js represents the roughness, R represents the hydraulic radius, S s represents the sand content of the section, α js represents the recovery saturation coefficient, ω represents the sediment settling velocity, S L Indicates the sediment content of the lateral inflow, S * represents the sediment-carrying force of water flow, ρ s ' represents the dry density of sediment on the riverbed surface, Z bs Indicates the bed elevation, G b represents the bed load transport rate, where Z s =Z s (x,t;θ u ), Q s =Q s (x,t;θ u ), n js =n js (x;θ p ), S s =S s (x,t;θ u ), Z bs =Z bs (x,t;θ u ), α js =α js(x;θ p ), θ u represents the first network model parameter, θ p Represents the second network model parameters.

[0011] The second aspect of the present invention provides a method for simulating a sediment transport process, comprising: dividing a target river channel into multiple river sections, and obtaining water and sediment data of each river section; determining the recovery saturation coefficient and roughness of each river section based on a dual-parameter optimization model of recovery saturation coefficient and roughness corresponding to each river section, wherein the dual-parameter optimization model of recovery saturation coefficient and roughness is determined according to the sediment model parameter optimization method provided by the first aspect of the present invention; inputting the water and sediment data of each river channel and the recovery saturation coefficient and roughness into the water and sediment model respectively, and obtaining the sediment transport process of the target river channel.

[0012] Optionally, in the sediment transport process simulation method provided by the present invention, the water-sediment model input data of the river section at the current moment also includes the water-sediment model output data of the adjacent upstream river section at the previous moment.

[0013] The third aspect of the present invention provides a sediment model parameter optimization device, including: an optimization objective function establishment module, which is used to establish an optimization objective function in combination with a first initial neural network model, a second initial neural network model, and a water-sand model, the water-sand parameters in the water-sand model are determined by the first initial neural network model, the recovery saturation coefficient and the roughness in the water-sand model are determined by the second initial neural network model, and the optimization objective function is determined according to the sum of the simulation residuals of each water-sand model; a network parameter optimization module, which is used to solve the optimization objective function, optimize the first network model parameters and the second network model parameters, and obtain the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function, the first network model is the parameters in the first initial network model, and the second network model parameters are the parameters in the second initial network model; an optimization model determination module, which is used to determine the second initial neural network model containing the second network model optimization parameters as a dual-parameter optimization model of recovery saturation coefficient and roughness.

[0014] The fourth aspect of the present invention provides a device for simulating a sediment transport process, comprising: a data acquisition module for dividing a target river channel into multiple river sections and obtaining water and sediment data of each river section; a parameter determination module for determining the recovery saturation coefficient and roughness of each river section based on a dual-parameter optimization model of recovery saturation coefficient and roughness corresponding to each river section, wherein the dual-parameter optimization model of recovery saturation coefficient and roughness is determined according to the sediment model parameter optimization method provided by the first aspect of the present invention; a simulation module for inputting the water and sediment data of each river channel and the recovery saturation coefficient and roughness into a water-sediment model respectively to obtain the sediment transport process of the target river channel.

[0015] The fifth aspect of the present invention provides a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to execute the sediment model parameter optimization method provided in the first aspect of the present invention, or the sediment transport process simulation method provided in the second aspect of the present invention.

[0016] The sixth aspect of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the sediment model parameter optimization method provided by the first aspect of the present invention, or the sediment transport process simulation method provided by the second aspect of the present invention.

[0017] The technical solution of the present invention has the following advantages:

[0018] 1. The method for optimizing sediment model parameters provided by the present invention, since the optimization objective function is determined according to the sum of the simulated residuals of the water-sand model, wherein the restoration saturation coefficient and roughness in the water-sand model are determined by the second initial neural network model, the second network model optimization parameters of the second neural network model determined in the process of solving the optimization objective function can minimize the sum of the simulated residuals of the water-sand model. It can be seen that the method provided by the embodiment of the present invention optimizes the second initial neural network model on the basis of the strong constraints of the physical process, and the restoration saturation coefficient and roughness determined by the dual-parameter optimization model of the restoration saturation coefficient and roughness obtained by the method provided by the embodiment of the present invention are more in line with the actual physical process. In addition, the method provided by the embodiment of the present invention can directly optimize the objective function by using the gradient optimization algorithm by putting the control equation of the water-sand model into the optimized objective function, without iterating the equation. At the same time, the physical driving term is introduced in the objective function, so that the optimization algorithm requires less observation data. The method can obtain the optimal solution of the restoration saturation coefficient and roughness parameter with physical significance without solving the control equation, which can effectively improve the simulation efficiency and accuracy of the river sediment transport process.

[0019] 2. The sediment transport process simulation method provided by the present invention divides the target river channel into multiple river sections, determines the recovery saturation coefficient and roughness of each river section according to the dual-parameter optimization model of recovery saturation coefficient and roughness corresponding to each river section, and inputs the water and sediment data of each river channel and the recovery saturation coefficient and roughness into the water and sediment model respectively to obtain the sediment transport process of the target river channel. Since the dual-parameter optimization model of recovery saturation coefficient and roughness used in the embodiment of the present invention is optimized by realizing the second initial neural network model on the basis of strong constraints of the physical process, the embodiment of the present invention can obtain a combination of recovery saturation coefficient and roughness parameters suitable for the sediment transport process of the river channel, and finally realize the accurate simulation of the sediment transport process of the river channel. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flowchart of a specific example of a sediment model parameter optimization method according to an embodiment of the present invention;

[0022] Figure 2 A flowchart of a specific example of a method for simulating sediment transport process in an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of the topological structure of a Bushi river section in an embodiment of the present invention;

[0024] Figure 4 It is a principle block diagram of a specific example of a sediment model parameter optimization device in an embodiment of the present invention;

[0025] Figure 5 It is a principle block diagram of a specific example of a device for simulating sediment transport process in an embodiment of the present invention;

[0026] Figure 6 It is a principle block diagram of a specific example of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0028] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0029] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0031] The embodiment of the present invention provides a method for optimizing sediment model parameters. Figure 1 As shown, the following steps are included:

[0032] Step S11: Establish an optimization objective function by combining the first initial neural network model, the second initial neural network model, and the water-sand model. The water-sand parameters in the water-sand model are determined by the first initial neural network model, and the recovery saturation coefficient and roughness in the water-sand model are determined by the second initial neural network model. The optimization objective function is determined based on the sum of the simulation residuals of each water-sand model.

[0033] In an optional embodiment, the water-sand model used to establish the optimization objective function is a one-dimensional water-sand model, and the output of the first initial neural network model includes Z s =Z s (x,t;θ u ), Q s =Q s (x,t;θ u ), S s =S s (x,t;θ u ), Z bs =Z bs (x,t;θ u ), etc., wherein Z s Indicates water level, Q s Indicates flow rate, S s Indicates the sand content of the section, Z bs represents the bed elevation, x represents space, t represents time, θ u Represents the first network model parameter. When solving the optimization objective function, the first network model parameter needs to be optimized. The space represented by x refers to the distance along the river direction in the one-dimensional coordinate system established by the model.

[0034] In an optional embodiment, the output of the second initial neural network model includes njs =n js (x;θ p ) and α js =α js (x;θ p ), where n js represents the roughness of the j-th river section, α js represents the recovery saturation coefficient of the jth river section, θ p It represents the second network model parameter. When solving the optimization objective function, the second network model parameter needs to be optimized.

[0035] Step S12: Solve the optimization objective function, optimize the first network model parameters and the second network model parameters, and obtain the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function, the first network model is the parameters in the first initial network model, and the second network model parameters are the parameters in the second initial network model.

[0036] In an optional embodiment, a classical simulated annealing method for finding the global optimum may be used to solve the optimization objective function, thereby obtaining the first network model optimization parameters and the second network model optimization parameters.

[0037] Step S13: Determine the second initial neural network model including the second network model optimization parameters as a restoration saturation coefficient and roughness dual-parameter optimization model.

[0038] In the sediment model parameter optimization method provided by the embodiment of the invention, since the optimization objective function is determined according to the sum of the simulated residuals of the water-sand model, the restoration saturation coefficient and roughness in the water-sand model are determined by the second initial neural network model, and the second network model optimization parameters of the second neural network model determined in the process of solving the optimization objective function can minimize the sum of the simulated residuals of the water-sand model. It can be seen that the method provided by the embodiment of the invention optimizes the second initial neural network model on the basis of the strong constraints of the physical process, and the restoration saturation coefficient and roughness determined by the dual-parameter optimization model of the restoration saturation coefficient and roughness obtained by the method provided by the embodiment of the invention are more in line with the actual physical process. In addition, the method provided by the embodiment of the invention can directly optimize the objective function using a gradient optimization algorithm by placing the control equation of the water-sand model into the optimized objective function without iterating the equation. At the same time, a physical driving term (i.e., the simulated residual of each water-sand model) is introduced into the objective function, so that the optimization algorithm requires less observation data. This method can obtain the optimal solution of the restoration saturation coefficient and roughness parameter with physical significance without solving the control equation, which can effectively improve the simulation efficiency and accuracy of the river sediment transport process.

[0039] In an optional implementation embodiment, the simulation residuals of the water-sediment model used in constructing the optimization objective function include the residuals of the water flow continuity equation, the residuals of the water flow motion equation, the residuals of the sediment continuity equation, and the residuals of the riverbed deformation equation, that is, the optimization objective function is established based on the sum of the residuals of the water flow continuity equation, the residuals of the water flow motion equation, the residuals of the sediment continuity equation, and the residuals of the riverbed deformation equation.

[0040] In an optional embodiment, the simulation residual of the water-sediment model when establishing the optimization objective function includes:

[0041]

[0042] Among them, e1 represents the residual of the water flow continuity equation, e2 represents the residual of the water flow motion equation, e3 represents the residual of the sediment continuity equation, e4 represents the residual of the riverbed deformation equation, B represents the water surface width, Z s Indicates water level, Q s represents flow, t represents time, x represents space, q L represents the lateral inflow per unit river length, A represents the water cross-sectional area, g represents the gravitational acceleration, and n js represents the roughness, R represents the hydraulic radius, S s represents the sand content of the section, α js represents the recovery saturation coefficient, ω represents the sediment settling velocity, SL represents the sediment content of the lateral inflow, S* represents the sediment entrainment force of the water flow, ρ s ' represents the dry density of sediment on the riverbed surface, Z bs Indicates the bed elevation, G b represents the bed load transport rate, where Z s =Z s (x,t;θ u ), Q s =Q s (x,t;θ u ), n js =n js (x;θ p ), S s =S s (x,t;θ u ), Z bs =Z bs (x,t;θ u ), α js =α js (x;θ p ), θ u represents the first network model parameter, θ p Represents the second network model parameters.

[0043] In an optional embodiment, the optimization objective function also includes the approximation error e5=Q of the flow output by the first initial neural network model to the actual flow s -Q * , and the approximation error of the water level output by the first initial neural network model to the actual water level is e6 = Z s -Z * , where Q s represents the flow rate output by the first initial neural network model, Q * Indicates the actual flow rate, Z s represents the water level output by the first initial neural network model, Z * Indicates the actual water level, actual flow and actual water level are obtained through observation.

[0044] In an optional embodiment, the optimization objective function is:

[0045] In an embodiment of the present invention, the optimization objective function is solved until the first network model optimization parameters and the second network model optimization parameters are obtained, so that the outputs of the two neural network models satisfy the control equations as much as possible and are as close to the observed data as possible.

[0046] In an optional embodiment, since the water levels and cross-sectional conditions in different sections of the same river channel are different, the roughness and recovery saturation coefficient are naturally different. Therefore, even for the same river channel, it is necessary to divide the river channel into multiple sections. For each section, the method provided in the above embodiment is executed respectively to obtain the dual-parameter optimization model of recovery saturation coefficient and roughness corresponding to each section.

[0047] The embodiment of the present invention provides a method for simulating sediment transport process, such as Figure 2 As shown, including:

[0048] Step S21: Divide the target river into multiple river sections, and obtain the water and sediment data of each river section.

[0049] In an optional embodiment, the incoming water and sediment data include the sediment content of the water body.

[0050] In an optional embodiment, the water and sediment data are obtained based on monitoring stations established on the main and tributary rivers.

[0051] In an optional embodiment, based on the historical cross-sectional data of the main and tributary rivers along the target river channel, the changes in cross-sectional morphology caused by sediment deposition are analyzed, and the target river channel is divided into multiple river sections based on the analysis results.

[0052] In an optional embodiment, the target river channel can be divided according to the cross-sectional width of each cross section of the target river channel, and the cross-sectional widths similar to each other are divided into the same river section. The topological structure diagram of the distributed river section is shown in FIG. Figure 3 .

[0053] Step S22: Determine the restoration saturation coefficient and roughness of each river section based on the restoration saturation coefficient and roughness dual parameter optimization model corresponding to each river section. The restoration saturation coefficient and roughness dual parameter optimization model is determined according to the sediment model parameter optimization method provided in the above embodiment.

[0054] In the embodiment of the present invention, since the cross-section of each river section is similar, an approximate restoration saturation coefficient and roughness can be selected in the same river section.

[0055] Step S23: inputting the water and sediment data of each river channel, the recovery saturation coefficient and the roughness into the water-sediment model respectively to obtain the sediment transport process of the target river channel.

[0056] In an embodiment of the present invention, the water and sediment data of the river section at the previous moment are input into the water-sediment model corresponding to the river section, so as to obtain the water level flow and sediment content of the river section at the current moment; the water level flow and sediment content of the river section at the current moment are input into the water-sediment model corresponding to the adjacent downstream river section, so as to predict the water level flow and sediment content of the adjacent downstream river section at the next moment; and so on, the sediment transport process of the target river channel can be predicted.

[0057] The water-sand model used in the embodiment of the present invention is the same as the water-sand model used in the above step S11.

[0058] The sediment transport process simulation method provided by the embodiment of the present invention divides the target river channel into multiple river sections, determines the restoration saturation coefficient and roughness of each river section according to the restoration saturation coefficient and roughness dual-parameter optimization model corresponding to each river section, and inputs the water and sediment data of each river channel and the restoration saturation coefficient and roughness into the water and sediment model respectively to obtain the sediment transport process of the target river channel. Since the restoration saturation coefficient and roughness dual-parameter optimization model used in the embodiment of the present invention is optimized by implementing the second initial neural network model on the basis of strong constraints on the physical process, the restoration saturation coefficient and roughness parameter combination suitable for the sediment transport process of the river channel can be obtained in the embodiment of the present invention, and finally the accurate simulation of the sediment transport process of the river channel is realized.

[0059] In an optional embodiment, a finite difference method is used to solve the water-sediment model to obtain the sediment transport process of the target river channel.

[0060] In an optional embodiment, since the calculation of each river section is relatively independent, the calculation result of the upstream river section at the previous moment is the input condition for the numerical calculation of the adjacent river section at the current moment. By simulating the long-term history of water and sediment processes in multiple river sections, the water level flow and sediment transport process of the entire river channel can be obtained.

[0061] The embodiment of the present invention provides a device for optimizing sediment model parameters, such as Figure 4 As shown, including:

[0062] The optimization objective function establishment module 11 is used to establish the optimization objective function in combination with the first initial neural network model, the second initial neural network model, and the water-sand model. The water-sand parameters in the water-sand model are determined by the first initial neural network model, and the recovery saturation coefficient and roughness in the water-sand model are determined by the second initial neural network model. The optimization objective function is determined based on the sum of the simulation residuals of each water-sand model. For details, please refer to the description of step S11 in the above embodiment and will not be repeated here.

[0063] The network parameter optimization module 12 is used to solve the optimization objective function, optimize the first network model parameters and the second network model parameters, and obtain the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function. The first network model is the parameter in the first initial network model, and the second network model parameter is the parameter in the second initial network model. For details, please refer to the description of step S12 in the above embodiment and will not be repeated here.

[0064] The optimization model determination module 13 is used to determine the second initial neural network model including the second network model optimization parameters as a dual-parameter optimization model of restoration saturation coefficient and roughness. For details, please refer to the description of step S13 in the above embodiment and will not be repeated here.

[0065] The embodiment of the present invention provides a device for simulating sediment transport process, such as Figure 5 As shown, including:

[0066] The data acquisition module 21 is used to divide the target river into multiple river sections and obtain the water and sediment data of each river section. The details are described in the description of step S21 in the above embodiment and will not be repeated here.

[0067] The parameter determination module 22 is used to determine the restoration saturation coefficient and roughness of each river section based on the dual-parameter optimization model of restoration saturation coefficient and roughness corresponding to each river section. The dual-parameter optimization model of restoration saturation coefficient and roughness is determined according to the sediment model parameter optimization method provided in the above embodiment. For details, please refer to the description of step S22 in the above embodiment and will not be repeated here.

[0068] The simulation module 23 is used to input the water and sediment data of each river channel and the recovery saturation coefficient and roughness into the water and sediment model to obtain the sediment transport process of the target river channel. The details are described in the description of step S23 in the above embodiment and will not be repeated here.

[0069] An embodiment of the present invention provides a computer device, such as Figure 6As shown, the computer device mainly includes one or more processors 31 and a memory 32. Figure 6 A processor 31 is taken as an example.

[0070] The computer device may further include: an input device 33 and an output device 34 .

[0071] The processor 31, the memory 32, the input device 33 and the output device 34 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0072] The processor 31 may be a central processing unit (CPU). The processor 31 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or a combination of the above chips. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The memory 32 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of a sediment model parameter optimization device, or a sediment transport process simulation device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory 32 may optionally include a memory remotely arranged relative to the processor 31, and these remote memories may be connected to the sediment model parameter optimization device, or the sediment transport process simulation device through a network. The input device 33 can receive the calculation request (or other digital or character information) input by the user, and generate key signal input related to the sediment model parameter optimization device, or the sediment transport process simulation device. The output device 34 can include a display device such as a display screen to output the calculation results.

[0073] The embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer storage medium stores computer executable instructions, which can execute the sediment model parameter optimization method in any of the above method embodiments, or the sediment transport process simulation method. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0074] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A sediment model parameter optimization method, characterized in that: The steps include: An optimization objective function is established by combining the first initial neural network model, the second initial neural network model, and the water-sand model, wherein the water-sand parameters in the water-sand model are determined by the first initial neural network model, the recovery saturation coefficient and the roughness in the water-sand model are determined by the second initial neural network model, and the optimization objective function is determined according to the sum of the simulation residuals of each water-sand model; Solving the optimization objective function, optimizing the first network model parameters and the second network model parameters, and obtaining the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function, wherein the first network model parameters are parameters in the first initial neural network model, and the second network model parameters are parameters in the second initial neural network model; Determine the second initial neural network model including the second network model optimization parameters as a restoration saturation coefficient and roughness dual parameter optimization model; The simulation residuals of the water-sediment model include: Among them, e1 represents the residual of the water flow continuity equation, e2 represents the residual of the water flow motion equation, e3 represents the residual of the sediment continuity equation, e4 represents the residual of the riverbed deformation equation, B represents the water surface width, Z s Indicates water level, Q s represents flow, t represents time, x represents space, q L represents the lateral inflow per unit river length, A represents the water cross-sectional area, g represents the gravitational acceleration, and n js represents the roughness, R represents the hydraulic radius, S s represents the sediment content of the section, α js represents the recovery saturation coefficient, ω represents the sediment settling velocity, S L Indicates the sediment content of the lateral inflow, S * represents the sediment-carrying force of water flow, ρ s ' represents the dry density of sediment on the riverbed surface, Z bs Indicates the bed elevation, G b represents the bed load transport rate, where Z s =Z s (x,t;θ u ), Q s =Q s (x,t;θ u ), n js =n js (x;θ p ), S s =S s (x,t;θ u ), Z bs =Z bs (x,t;θ u ), α js =α js (x;θ p ), θ u represents the first network model parameter, θ p represents the second network model parameter; The optimization objective function also includes the approximation error e5=Q of the flow output by the first initial neural network model to the actual flow s -Q * , and the approximation error of the water level output by the first initial neural network model to the actual water level is e6 = Z s -Z * , where Q s represents the flow rate output by the first initial neural network model, Q * Indicates the actual flow rate, Z s represents the water level output by the first initial neural network model, Z * Indicates the actual water level, actual flow and actual water level are obtained through observation.

2. The sediment model parameter optimization method according to claim 1, characterized in that: The water and sediment parameters determined by the first initial neural network model include flow and water level.

3. A method for simulating sediment transport process, characterized in that: include: Divide the target river into multiple river sections and obtain the water and sediment data of each river section; Based on the restoration saturation coefficient and roughness dual parameter optimization model corresponding to each river section, the restoration saturation coefficient and roughness of each river section are determined, wherein the restoration saturation coefficient and roughness dual parameter optimization model is determined according to the sediment model parameter optimization method according to claim 1 or 2; The water and sediment data of each river channel and the recovery saturation coefficient and roughness are respectively input into the water-sediment model to obtain the sediment transport process of the target river channel.

4. The method for simulating sediment transport process according to claim 3, characterized in that: The water-sediment model input data of the river section at the current moment also includes the water-sediment model output data of the adjacent upstream river section at the previous moment.

5. A sediment model parameter optimization device, characterized in that: include: An optimization objective function establishment module is used to establish an optimization objective function by combining the first initial neural network model, the second initial neural network model, and the water-sand model, wherein the water-sand parameters in the water-sand model are determined by the first initial neural network model, the restoration saturation coefficient and the roughness in the water-sand model are determined by the second initial neural network model, and the optimization objective function is determined according to the sum of the simulation residuals of each water-sand model; A network parameter optimization module, used to solve the optimization objective function, optimize the first network model parameters and the second network model parameters, and obtain the first network model optimization parameters and the second network model optimization parameters that minimize the value of the optimization objective function, wherein the first network model parameters are the parameters in the first initial neural network model, and the second network model parameters are the parameters in the second initial neural network model; An optimization model determination module, used for determining the second initial neural network model including the second network model optimization parameters as the restoration saturation coefficient and roughness dual-parameter optimization model; The simulation residuals of the water-sediment model include: Among them, e1 represents the residual of the water flow continuity equation, e2 represents the residual of the water flow motion equation, e3 represents the residual of the sediment continuity equation, e4 represents the residual of the riverbed deformation equation, B represents the water surface width, Z s Indicates water level, Q s represents flow, t represents time, x represents space, q L represents the lateral inflow per unit river length, A represents the water cross-sectional area, g represents the gravitational acceleration, and n js represents the roughness, R represents the hydraulic radius, S s represents the sediment content of the section, α js represents the recovery saturation coefficient, ω represents the sediment settling velocity, S L Indicates the sediment content of the lateral inflow, S * represents the sediment-carrying force of water flow, ρ s ' represents the dry density of sediment on the riverbed surface, Z bs Indicates the bed elevation, G b represents the bed load transport rate, where Z s =Z s (x,t;θ u ), Q s =Q s (x,t;θ u ), n js =n js (x;θ p ), S s =S s (x,t;θ u ), Z bs =Z bs (x,t;θ u ), α js =α js (x;θ p ), θ u represents the first network model parameter, θ p represents the second network model parameter; The optimization objective function also includes the approximation error e5=Q of the flow output by the first initial neural network model to the actual flow s -Q * , and the approximation error of the water level output by the first initial neural network model to the actual water level is e6 = Z s -Z * , where Q s represents the flow rate output by the first initial neural network model, Q * Indicates the actual flow rate, Z s represents the water level output by the first initial neural network model, Z * Indicates the actual water level, actual flow and actual water level are obtained through observation.

6. A device for simulating sediment transport process, characterized in that: include: The data acquisition module is used to divide the target river into multiple river sections and obtain the water and sediment data of each river section; A parameter determination module, for determining the restoration saturation coefficient and roughness of each river section based on a dual-parameter optimization model of restoration saturation coefficient and roughness corresponding to each river section, wherein the dual-parameter optimization model of restoration saturation coefficient and roughness is determined according to the sediment model parameter optimization method according to claim 1 or 2; The simulation module is used to input the water and sediment data of each river channel and the recovery saturation coefficient and roughness into the water-sediment model respectively to obtain the sediment transport process of the target river channel.

7. A computer device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to execute the sediment model parameter optimization method as described in claim 1 or 2, or the sediment transport process simulation method as described in claim 3 or 4.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the sediment model parameter optimization method as described in claim 1 or 2, or the sediment transport process simulation method as described in claim 3 or 4.

Images