Hydrodynamic environment data detection method

Abstract

The invention relates to the technical field of environment simulation, in particular to a hydrodynamic environment data detection method, which comprises the following steps of: constructing a hydrodynamic model based on an MIKE 21 model; determining parameters of the hydrodynamic model and carrying out sensitivity analysis on the parameters of the hydrodynamic model to obtain the sensitivity degree of each parameter; according to the method, the parameters of the hydrodynamic model are automatically calibrated based on the neural network model to obtain the automatic calibrated parameters, and then the parameters of the hydrodynamic model are manually calibrated based on the automatic calibrated parameters and the sensitivity degrees of the parameters, so that the accuracy of the hydrodynamic model is improved; the hydrodynamic model after manual calibration is verified, verification results are generated, and the verification results include that the hydrodynamic model meets the requirement and that the hydrodynamic model does not meet the requirement; and under the condition that the hydrodynamic model meets the requirements, multi-working-condition simulation of reservoir environment change is realized through the hydrodynamic model, so that a certain reference value is provided for environment optimization.

Description

Technical Field

[0001] The invention relates to the technical field of environmental simulation, and in particular to a method for detecting hydrodynamic environmental data. Background Art

[0002] At present, the demand for marine reservoirs in my country is very common, but the land resources are limited. Therefore, there is a great demand for building reservoirs in estuaries and bays, especially in the economically developed eastern coastal areas. At the same time, the terrain in the eastern coastal areas of my country is low, and it is feasible to build reservoirs by collecting water in principle, but there is little research on the environmental problems that come with it. Therefore, it is necessary to study the impact of reservoir construction on the hydrodynamic environment of estuaries and bays.

[0003] The coastal zone is the part where the ocean and the land are connected, with frequent exchanges of materials and information. It is the frontier area for human contact and development of the ocean and one of the most productive areas. Under normal circumstances, the impact of human activities such as reservoir construction on the environment is smaller than that of natural processes. For minor environmental changes caused by human activities, the coastal zone can recover quickly without applying additional pressure. With the rapid increase in population in the coastal zone, the development of industry and agriculture, and the improvement of living standards, the coastal zone has been continuously developed and utilized, and the natural conditions have been gradually destroyed. The environment is facing long-term, multi-type, and varying degrees of additional pressure, and the environmental quality has declined significantly. Problems such as shore siltation and erosion, abnormal changes in hydrodynamics, water quality deterioration, eutrophication of water bodies, and imbalance of biodiversity are becoming increasingly serious, and the adverse effects on human activities and economic and social development are gradually emerging.

[0004] The hydrodynamic environment generated by the construction of Changhuikou Reservoir directly affects the surrounding environmental quality and has an indirect impact on social and economic activities. How to achieve multi-condition simulation of environmental changes is one of the problems that urgently need to be solved. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method for detecting hydrodynamic environment data, which is helpful to realize the simulation of multiple working conditions caused by environmental changes.

[0006] In order to implement the above technical solution, in a first aspect, the present invention provides a method for detecting hydrodynamic environment data, comprising: Step 1: Construct a hydrodynamic model based on the MIKE 21 model; Step 2: Determine the parameters of the hydrodynamic model and perform sensitivity analysis on the parameters of the hydrodynamic model to obtain the sensitivity of each parameter; Step 3: Automatically calibrate the parameters of the hydrodynamic model based on the neural network model to obtain automatic calibration parameters; Step 4: Based on the automatically calibrated parameters and the sensitivity of each parameter, the parameters of the hydrodynamic model are manually calibrated; Step 5: Verify the manually calibrated hydrodynamic model and generate verification results, where the verification results include whether the hydrodynamic model meets the requirements and whether the hydrodynamic model does not meet the requirements; Step 6: When the hydrodynamic model meets the requirements, perform multi-condition simulation of reservoir environmental changes through the hydrodynamic model.

[0007] Furthermore, the step 1 comprises: Collecting reservoir boundary area information, and drawing a reservoir including the reservoir boundary information by using AutoCAD software according to the collected boundary area information, so as to obtain a first reservoir boundary information file; Obtaining hydrometeorological data, topographic data and water quality data of the reservoir as a second information file; According to the obtained first reservoir boundary information file and the second information file, the reservoir is meshed by an unstructured mesh generator based on MIKE ZERO to generate an unstructured triangular mesh of the reservoir; The unstructured triangular mesh process of the generated reservoir is interpolated.

[0008] Furthermore, the step 2 comprises: Matlab software was used to perform Latin hypercube sampling on the parameters of the hydrodynamic model to extract the parameters; Obtain the indicators, influencing factors and levels of each parameter; Calculate the range of the sum of the indicators corresponding to each parameter at a certain level, where the range calculation formula is as follows: ; Among them, i is the influencing factor, j is the level, is the extreme value; It is the maximum value of the sum of all indicators when the influencing factor i is at level j; It is the minimum value of the sum of various indicators when the influencing factor i is at level j; Based on the calculated range values, the sensitivity of each parameter of the hydrodynamic model is determined.

[0009] Furthermore, the step three comprises: Establish a parameter calibration model based on feedback artificial neural network; Training the established parameter calibration model based on feedback artificial neural network; Verify the trained parameter calibration model based on the feedback artificial neural network, and adjust the parameter calibration model based on the verification result; The parameters of the hydrodynamic model are automatically calibrated by using the adjusted parameter calibration model to generate automatic calibration parameters.

[0010] Furthermore, the step 4 includes: Based on the automatic calibration parameters and the sensitivity of each parameter, the hydrodynamic model parameters are manually calibrated by trial and error.

[0011] Furthermore, the step five comprises: After manual calibration, the simulated data output by the hydrodynamic model is obtained and the measured data is selected according to the actual situation; Based on the simulation data and measured data, the Nash coefficient and the average relative error are calculated. If the Nash coefficient value is greater than the preset Nash coefficient threshold and the average relative error is less than the preset average relative error threshold, it means that the model meets the requirements. If not, it means that the hydrodynamic model does not meet the requirements.

[0012] Furthermore, the calculation formula of the Nash coefficient is as follows:

[0013] in, is the simulated data; is the measured data; is the measured mean; n is the number of data; The calculation formula of relative mean error (RMAE) is as follows: .

[0014] In a second aspect, the present invention provides a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for detecting hydrodynamic environment data.

[0015] The beneficial effects of the present invention are: The present invention helps to improve the accuracy of the hydrodynamic model by analyzing the sensitivity of various parameters of the hydrodynamic model, automatically calibrating the parameters of the hydrodynamic model based on a neural network model, and then manually calibrating based on the automatically calibrated parameters and the sensitivity of each parameter; then the hydrodynamic model after manual calibration is verified, and when the hydrodynamic model meets the requirements, multi-condition simulation of reservoir environmental changes is achieved, thereby providing a certain reference value for optimizing the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0017] Figure 1 The present invention is a flow chart of a method for detecting hydrodynamic environment data. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0019] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present invention. Unless otherwise specified, each technical and scientific term used in this embodiment has the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0020] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0021] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0022] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. Relevant scientific research or technical personnel in this field can determine the specific meanings of the above terms in the present invention according to specific circumstances, and they should not be understood as limiting the present invention. Embodiment 1: like Figure 1 As shown, this embodiment provides a method for detecting hydrodynamic environment data, comprising the following steps: S1: Construct a hydrodynamic model based on the MIKE 21 model.

[0023] The construction of the hydrodynamic model includes: S1-1: Collecting reservoir boundary area information, and drawing a reservoir including the reservoir boundary information by using AutoCAD software according to the collected boundary area information, so as to obtain a first reservoir boundary information file; S1-2: Obtain the hydrological and meteorological data, topographic data and water quality data of the reservoir as the second information file.

[0024] Among them, hydrological and meteorological data include hydrodynamic characteristics such as the direction, speed and depth of water flow at a specific location at a certain time.

[0025] S1-3: According to the obtained first reservoir boundary information file and the second information file, the reservoir is meshed by using an unstructured mesh generator (Mesh Generator) based on MIKE ZERO to obtain a mesh file in ASCII format including an unstructured triangular mesh of the reservoir.

[0026] The specific steps include: S1-3-1: Extract reservoir information from the reservoir drawn by AutoCAD software, summarize the reservoir information and organize it into a .xyz format document; S1-3-2: The unstructured grid generator based on MIKE ZERO uses triangular grids to divide the reservoir map, constructs an unstructured triangular grid of the reservoir, and stores the constructed unstructured triangular grid of the reservoir in an ASCII grid file.

[0027] Specifically, the steps include: A: Based on the reservoir information in the .xyz format file, the boundary vertices in the reservoir channel are redistributed and the boundaries are smoothed to determine the maximum area threshold and minimum angle threshold of the grid; By determining the maximum area threshold and minimum angle threshold of the mesh, it helps to avoid the occurrence of unqualified area triangle networks; B: Smooth the triangular mesh and optimize the local elements to make the mesh as close to an equilateral triangle as possible.

[0028] C: Locally optimize and refine the mesh to obtain an unstructured triangular mesh of the reservoir, and store the obtained unstructured triangular mesh of the reservoir in an ASCII mesh file.

[0029] S1-4: Based on the .xyz format file, interpolate the nodes of the unstructured triangular mesh stored in the ASCII format mesh file.

[0030] S2: Determine the parameters of the hydrodynamic model and perform sensitivity analysis on the parameters of the hydrodynamic model to obtain the sensitivity of each parameter.

[0031] Specifically, the sensitivity of the hydrodynamic model parameters is analyzed by the nonlinear mutual information method. Among them, the sensitivity analysis of the parameters of the hydrodynamic model can quantitatively understand the sensitivity of each parameter and provide a basis for the automatic calibration of the model; S2-1: Latin hypercube sampling of the parameters of the hydrodynamic model was performed using Matlab software to extract the parameters.

[0032] S2-2: Obtain the indicators, influencing factors and levels of each parameter; S2-3: Calculate the range of the sum of various indicators corresponding to each parameter at a certain level; Specifically, the calculation formula is as follows: ; Among them, i is the influencing factor, j is the level, is the extreme value; It is the maximum value of the sum of all indicators when the influencing factor i is at level j; It is the minimum value of the sum of various indicators when the influencing factor i is at level j.

[0033] S2-4: Based on the calculated range values, determine the sensitivity of each parameter of the hydrodynamic model.

[0034] S3: Automatically calibrate the parameters of the hydrodynamic model based on the neural network model to obtain automatic calibration parameters.

[0035] The specific steps include: S3-1: Establish a parameter calibration model based on feedback artificial neural network.

[0036] The specific steps include: S3-1-1: Determine the input variables and output target variables of the parameter calibration model; S3-1-2: Cross-validate the parameter calibration model based on the feedback artificial neural network based on the determined input variables and output target variables to determine the proportion of training data, verification data and test data.

[0037] S3-1-3: Adjust the structure of the parameter calibration model based on the feedback artificial neural network based on the determined ratio, including the number of hidden neurons and delay values.

[0038] Specifically, the error rate of the parameter calibration model is reduced by changing the ratio and adjusting the weights of each neuron connection in the network among the training data, validation data and test data.

[0039] S3-2: Train the established parameter calibration model based on feedback artificial neural network.

[0040] S3-3: Verify the trained parameter calibration model based on the feedback artificial neural network, and adjust the parameter calibration model based on the verification result; S3-4: Automatically calibrate the parameters of the hydrodynamic model by using the adjusted parameter calibration model to generate automatic calibration parameters; S4: Based on the automatically calibrated parameters and the sensitivity of each parameter, the hydrodynamic model parameters are manually calibrated.

[0041] Specifically, based on the automatic calibration parameters and the sensitivity of each parameter, the hydrodynamic model parameters are manually calibrated by a trial and error method.

[0042] S5: Verify the manually calibrated hydrodynamic model and generate verification results, where the verification results include whether the hydrodynamic model meets the requirements or not.

[0043] After manual calibration, S5-1 obtains the simulated data output by the hydrodynamic model and selects the measured data according to the actual situation (such as the actual flow data collected at a fixed position upstream and the corresponding water depth data collected at a fixed position downstream).

[0044] S5-2: Based on the simulated data and measured data, the simulation effect of the hydrodynamic model is evaluated by the Nash coefficient (Ens) and the mean relative error (RMAE).

[0045] Specifically, (1) The calculation formula of the Nash coefficient (Ens) is as follows:

[0046] in, is the simulated data; is the measured data; is the measured mean; n is the number of data; (2) The calculation formula of relative mean error (RMAE) is as follows:

[0047] If the Nash coefficient value is greater than the preset Nash coefficient threshold and the average relative error is less than the preset average relative error threshold, it means that the model meets the requirements. If not, it means that the hydrodynamic model does not meet the requirements.

[0048] S6: When the hydrodynamic model meets the requirements, multiple operating condition simulations of reservoir environmental changes are performed through the hydrodynamic model.

[0049] By simulating the reservoir environment, we can intuitively understand the reservoir environment.

[0050] It should be noted that the control equation of the hydrodynamic model is as follows: (1) Mass conservation equation:

[0051] (2) Momentum equation:

[0052]

[0053] Where: is the water level; h is the still water depth; H is the total water depth, H=h+ ; u and v are the vertical average flow velocities in the x and y directions respectively; g is the gravitational acceleration; f is the Coriolis force parameter ( , is the geographical latitude of the sea area); CZ is the Xie Cai coefficient, , n is the Manning coefficient; is the horizontal eddy viscosity coefficient in the x and y directions.

[0054] The initial conditions of the hydrodynamic model are: .

[0055] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0056] In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can It can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0057] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] In addition, it should be noted that the flowchart in the accompanying drawings shows the method of the embodiment of the present disclosure. In the corresponding description in the flowchart or block diagram in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be performed substantially in parallel, or sometimes in the opposite order, which may depend on the functions involved. Each block in the block diagram and / or flow chart, and the combination of blocks in the block diagram and / or flow chart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting hydrodynamic environment data, characterized in that: include: Step 1: Construct a hydrodynamic model based on the MIKE 21 model; Step 2: Determine the parameters of the hydrodynamic model and perform sensitivity analysis on the parameters of the hydrodynamic model to obtain the sensitivity of each parameter; Step 3: Automatically calibrate the parameters of the hydrodynamic model based on the neural network model to obtain automatic calibration parameters; Step 4: Based on the automatically calibrated parameters and the sensitivity of each parameter, the parameters of the hydrodynamic model are manually calibrated; Step 5: Verify the manually calibrated hydrodynamic model and generate verification results, where the verification results include whether the hydrodynamic model meets the requirements and whether the hydrodynamic model does not meet the requirements; Step 6: When the hydrodynamic model meets the requirements, perform multi-condition simulation of reservoir environmental changes through the hydrodynamic model.

2. The method for detecting hydrodynamic environment data according to claim 1, characterized in that: The step one comprises: Collecting reservoir boundary area information, and drawing a reservoir including the reservoir boundary information by using AutoCAD software according to the collected boundary area information, so as to obtain a first reservoir boundary information file; Obtaining hydrometeorological data, topographic data and water quality data of the reservoir as a second information file; According to the obtained first reservoir boundary information file and the second information file, the reservoir is meshed by an unstructured mesh generator based on MIKE ZERO to generate an unstructured triangular mesh of the reservoir; The unstructured triangular mesh process of the generated reservoir is interpolated.

3. The method for detecting hydrodynamic environment data according to claim 1, characterized in that: The second step comprises: Matlab software was used to perform Latin hypercube sampling on the parameters of the hydrodynamic model to extract the parameters; Obtain the indicators, influencing factors and levels of each parameter; Calculate the range of the sum of the indicators corresponding to each parameter at a certain level, where the range calculation formula is as follows: ； Among them, i is the influencing factor, j is the level, is the extreme value; It is the maximum value of the sum of all indicators when the influencing factor i is at level j; It is the minimum value of the sum of various indicators when the influencing factor i is at level j; Based on the calculated range values, the sensitivity of each parameter of the hydrodynamic model is determined.

4. The method for detecting hydrodynamic environment data according to claim 1, characterized in that: The step three comprises: Establish a parameter calibration model based on feedback artificial neural network; Training the established parameter calibration model based on feedback artificial neural network; Verify the trained parameter calibration model based on the feedback artificial neural network, and adjust the parameter calibration model based on the verification result; The parameters of the hydrodynamic model are automatically calibrated by using the adjusted parameter calibration model to generate automatic calibration parameters.

5. The method for detecting hydrodynamic environment data according to claim 1, characterized in that: The fourth step comprises: Based on the automatic calibration parameters and the sensitivity of each parameter, the hydrodynamic model parameters are manually calibrated by trial and error.

6. The method for detecting hydrodynamic environment data according to claim 1, characterized in that: The step five comprises: After manual calibration, the simulated data output by the hydrodynamic model is obtained and the measured data is selected according to the actual situation; Based on the simulation data and measured data, the Nash coefficient and the average relative error are calculated. If the Nash coefficient value is greater than the preset Nash coefficient threshold and the average relative error is less than the preset average relative error threshold, it means that the model meets the requirements. If not, it means that the hydrodynamic model does not meet the requirements.

7. The method for detecting hydrodynamic environment data according to claim 6, characterized in that: The calculation formula of the Nash coefficient is as follows: in, is the simulated data; is the measured data; is the measured mean; n is the number of data; The calculation formula of relative mean error (RMAE) is as follows: 。 8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the hydrodynamic environment data detection method described in claim 7.

Images