Intelligent optimization method for flood discharge flip bucket body type
By optimizing the shape of the flow-fed nose sill using a BP neural network and the NSGA-II multi-objective algorithm, the problem of cumbersome and resource-intensive design methods in existing technologies is solved, and a fast and accurate flow-fed nose sill design and water tongue control are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-08
- Publication Date
- 2026-05-15
AI Technical Summary
Existing methods for designing a water jet nose sill require repeated trial and error and revision, consuming a lot of manpower and resources, and it is difficult to precisely control the shape and landing point of the water jet.
By combining BP neural network and NSGA-II multi-objective algorithm with orthogonal experimental design, the body shape parameters of the nasal sill are optimized through numerical simulation and physical model experiments. A parameter database is constructed, and the ideal body shape parameters that meet the engineering objectives are obtained through inversion.
It enables rapid and accurate design of the water jet nose, reduces the consumption of physical model experiments, significantly improves design accuracy, and controls the shape and landing point of the water jet.
Smart Images
Figure CN122046469A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of flood discharge sluice gate technology, and specifically relates to a method for intelligent optimization of the shape of a flood discharge sluice gate. Background Technology
[0002] The spillway nose sill is a special structure set at the end of a spillway in hydraulic engineering. Its core function is to control the trajectory of the spillway tongue in order to dissipate energy and reduce scouring of the riverbed.
[0003] How to mitigate the adverse effects of the jet chute on the downstream river channel involves optimizing the shape of the jet chute. The core issue is to understand the impact of the jet chute on the riverbed and reduce the damage to the riverbed and banks.
[0004] The draft nose sill plays a crucial role in controlling the shape and landing point of the draft water jet. The main purpose of optimizing the draft nose sill is to control the shape and landing position of the draft water jet to reduce scouring of the downstream river channel, while also reducing the difficulty and workload of engineering construction. Therefore, research on the optimization of the draft nose sill shape is key to solving the problems of energy dissipation and scouring protection.
[0005] Currently, the design methods for jet sluices mainly rely on experience to initially propose a jet sluice shape, which is then revised and validated based on physical model test results or numerical simulation calculation results. The selection of jet sluice shape parameters often depends on empirical judgment of the water entry position, jet distance, sluice pit depth, and energy dissipation effect, until the design requirements are met. These methods require repeated trial and error and revision, consuming significant human and material resources. Summary of the Invention
[0006] This invention provides an intelligent optimization method for the shape of a flood discharge sluice gate, which solves the technical problem that the design method of the sluice gate in the prior art requires repeated trial and error and correction, which consumes a lot of manpower and material resources.
[0007] This invention is achieved through the following technical solution: A method for intelligent optimization of the shape of a flood discharge embankment includes the following steps: Define the project objectives, and then determine the constraints based on those objectives. The type of nasal cannula is determined based on the constraints, and the range of body shape parameters for the nasal cannula is set. Multiple sets of parameter values are selected as experimental data within the range of body shape parameters. Orthogonal experimental design is used to design experiments on multiple sets of experimental data to obtain experimental body shape parameters for multiple sets of nasal cannsulas with different body shapes. Numerical simulation calculations were performed based on multiple sets of experimental body shape parameters to obtain the morphological parameters of the water jets that the water jets formed by the multiple sets of experimental body shape parameters could generate respectively, and the morphological parameters of the multiple sets of water jets were used as the initial dataset. The initial dataset is expanded using a backpropagation (BP) neural network method to construct a parameter database; Set the target range of the constraints; based on the parameter database, use the NSGA-II multi-objective algorithm to invert and obtain the ideal body shape parameter solution set that falls within the target range; A multi-objective decision-making method is used to select the target body shape parameters of the sluice gate that meet the engineering objectives from the solution set of ideal body shape parameters.
[0008] To better realize the present invention, further optimizations are made to the above structure. When performing numerical simulation calculations based on multiple sets of experimental body size parameters, at least two sets of experimental body size parameters are selected for physical model experiments to verify the results of the numerical simulation calculations.
[0009] To better realize the present invention, further optimizations are made to the above structure. After obtaining the target body shape parameters of the nasal sill that meet the engineering objectives, the target body shape parameters are verified.
[0010] Compared with the prior art, the present invention has the following advantages: The intelligent optimization method for the shape of the spillway sluice gate provided by this invention first clarifies the engineering objective, then obtains the experimental shape parameters of the sluice gate that approximate the engineering objective through reverse thinking, and then performs numerical simulation calculations on the experimental shape parameters to obtain the morphological parameters of the spillway tongue that can be generated by the sluice gate composed of multiple sets of experimental shape parameters. Finally, the target shape parameters of the sluice gate corresponding to the morphological parameters of the spillway tongue that meet the engineering objective are selected. The characteristics of this intelligent optimization method for the shape of the spillway sluice gate are that it is rapid and accurate, and can precisely control the constraints of the engineering objective, significantly improving the design accuracy of the spillway sluice gate while reducing the consumption of manpower and material resources caused by a large number of physical model experiments. Attached Figure Description
[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0012] Figure 1 This is a flowchart illustrating an example of applying the present invention in a specific implementation.
[0013] Figure 2 This is a schematic diagram of the water jet that meets the engineering objectives in the embodiment.
[0014] Figure 3 This is a top view of the water jet that meets the engineering objectives in the embodiment.
[0015] Figure 4 This is a simulation diagram of the water tongue shape generated by body type 1.
[0016] Figure 5 This is a simulation diagram of the water jet shape generated by body type 2.
[0017] Figure 6 This is a simulation diagram of the water jet shape produced by body type 3.
[0018] Figure 7 This is a simulation diagram of the water jet shape produced by body type 4.
[0019] Figure 8 This is a simulation diagram of the water jet shape produced by body type 5.
[0020] Figure 9 This is a simulation diagram of the water jet shape produced by body type 6.
[0021] Figure 10 This is a simulation of the water tongue shape produced by body type 7.
[0022] Figure 11 It is a simulation diagram of the water tongue shape generated by body type 8.
[0023] Figure 12 This is a simulation diagram of the water tongue shape generated by body type 9.
[0024] Figure 13 This is a simulation diagram of the water jet shape in the physical model test of body type 3.
[0025] Figure 14 This is a comparison chart of the predicted and actual mean square error of the single-width flow rate.
[0026] Figure 15 This is a comparison chart of the predicted and actual values of the entry arc length.
[0027] Figure 16 This is a comparison chart of the predicted and actual values of the water tongue deflection angle on the right side.
[0028] Figure 17 This is a comparison chart of the predicted and actual values of the water jet entry angle on the right side.
[0029] Figure 18 This is a comparison chart of the predicted and actual values of the right-hand distance x-coordinate.
[0030] Figure 19 This is a comparison chart of the predicted and actual values of the right-hand y-coordinate distance.
[0031] Figure 20 This is a comparison chart of the predicted and actual values of the water tongue deflection angle.
[0032] Figure 21 This is a comparison chart of the predicted and actual values of the water inlet angle.
[0033] Figure 22 This is a comparison chart of the predicted and actual values of the x-coordinate of the center distance.
[0034] Figure 23 This is a comparison chart of the predicted and actual values of the y-coordinate of the center distance.
[0035] Figure 24 This is a comparison chart of the predicted and actual values of the water tongue deflection angle on the left.
[0036] Figure 25 This is a comparison chart of the predicted and actual values of the water tongue entry angle on the left.
[0037] Figure 26 This is a comparison chart of the predicted and actual values of the left tilt distance x-coordinate.
[0038] Figure 27 This is a comparison chart of the predicted and actual values of the left tilt distance y-coordinate.
[0039] Figure 28 It is the Pareto solution set inverted by the NSGA-II multi-objective algorithm.
[0040] Figure 29 It is a simulation diagram of the shape of the water jet generated by the jet nose sill that meets the engineering objectives.
[0041] Figure 30 This is a unit width flow distribution diagram of the jet flow morphology (before optimization) of the physical model test of body type 3.
[0042] Figure 31 It is a unit width flow distribution diagram of the jet flow tongue shape (after optimization) generated by the jet flow nose sill that meets the engineering objectives. Detailed Implementation
[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0044] In the description of this invention, it should be noted that, unless otherwise stated, "multiple sets" means two or more; the terms "upper," "lower," "left," "right," "inner," "outer," "front end," "rear end," "head," "tail," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0045] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.
[0046] In the embodiments of this application, such as Figure 1 As shown, the intelligent optimization method for the shape of the flood discharge sill includes the following steps: Define the project objectives, and then determine the constraints based on those objectives; among them, The engineering objectives include reducing the impact of the spillway tongue on the riverbed and / or minimizing damage to the riverbed and banks. Constraints include the entry arc length of the spillway tongue and / or the landing point of the spillway tongue, the deflection angle of the spillway tongue, and the unit width flow distribution. In other words, based on the layout of the spillway structures and the topography and geological characteristics of the energy dissipation zone, the ideal distribution form of the spillway tongue is determined to establish the mathematical expression for the optimization objective of the spillway tongue landing point. Based on the optimization objectives, the spillway nose sill to be optimized is selected as the research object. For example, for a sloping spillway nose sill, the shape parameters of the spillway nose sill, including the spillway angle, the radius of the reverse arc, the deflection angle, the radius of the left wall, and the radius of the right wall, need to be determined as control variables to obtain the corresponding spillway characteristic values, such as the spillway distance, the entry arc length, the deflection angle of the spillway tongue, and the unit width flow distribution.
[0047] The type of the nasal cannula is determined according to the constraints, and the range of the nasal cannula's body shape parameters is set. In this embodiment, the type of the nasal cannula and the range of the nasal cannula's body shape parameters are determined by the designers based on their engineering experience and professional knowledge. After determining the type of the nasal cannula and the range of the nasal cannula's body shape parameters, multiple sets of parameter values are selected as experimental data within the range of body shape parameters. Orthogonal experimental design is used to design experiments on multiple sets of experimental data to obtain multiple sets of experimental body shape parameters for nasal cannsulas of different body shapes. It should be noted that the orthogonal experiment method is a mathematical statistics method that uses an orthogonal table to arrange multi-factor and multi-level experiments. It can obtain effective data with fewer experiments. The core lies in its characteristics of uniformity, dispersion, and整齐可比 (comparability in an orderly manner), and it is widely used in fields such as chemical formula optimization, agricultural cultivation experiments, and software testing.
[0048] According to the obtained multiple sets of experimental body shape parameters, perform numerical simulation calculations to obtain the shape parameters (jet flow characteristic values) of the jet flow bucket that can be generated by the jet flow buckets composed of multiple sets of experimental body shape parameters. Take the shape parameters of multiple sets of jet flow buckets as the initial data set. Use the BP neural network method to expand the initial data set to construct a parameter database. It should be noted that the BP neural network method is a multi-layer feedforward neural network trained according to the error backpropagation algorithm. Its core is to adjust the network weights through the gradient descent method to minimize the mean square error between the actual output and the expected output. Using the BP neural network method can expand the discrete and small number of shape parameters of the jet flow buckets in the above initial data set, making the discrete shape parameters of the jet flow buckets in the initial data set become continuous shape parameters of the jet flow buckets to complete the construction of the parameter database.
[0049] Set the target range of the constraint conditions, that is, set the range of data such as the entry arc length of the jet flow bucket and / or the landing position of the jet flow bucket, the deflection angle of the jet flow bucket, and the unit-width flow distribution. Based on the above parameter database, use the NSGA-II multi-objective algorithm to inversely obtain the ideal body shape parameter solution set of the jet flow bucket that falls within the target range. It should be noted that NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a classic multi-objective optimization algorithm. It efficiently solves multi-objective optimization problems through mechanisms such as fast non-dominated sorting, crowding degree calculation, and elitist strategy. In this embodiment, use the NSGA-II multi-objective algorithm to inversely obtain the ideal body shape parameter solution set of the jet flow bucket that falls within the target range of multiple objectives (multiple constraint conditions). Use the multi-objective decision-making method to select the target body shape parameters of the jet flow bucket that meet the engineering objectives from the ideal body shape parameter solution set.
[0050] It should be noted that the multi-objective decision-making method is mainly used to solve complex problems that need to optimize multiple sets of conflicting objectives simultaneously. Its core is to achieve the balance and optimal solution selection between objectives through mathematical methods to select the target body shape parameters of the jet flow bucket that meet the engineering objectives from the ideal body shape parameter solution set.
[0051] In some embodiments, when performing numerical simulation calculations based on multiple sets of experimental body parameters, at least two sets of experimental body parameters are selected for physical model tests to verify the results of the numerical simulation calculations, so as to determine the feasibility of numerical simulation calculations of the hydraulic characteristics of the jet of water generated by the jet nose sill.
[0052] In some embodiments, after obtaining the target shape parameters of the draft nose sill that meet the engineering objectives, the target shape parameters are verified. That is, numerical simulation calculations or physical model tests are performed based on the obtained target shape parameters to determine whether the draft water tongue generated by the draft nose sill formed by the obtained target shape parameters can meet the engineering objectives.
[0053] To better illustrate the operation and feasibility of this intelligent optimization method for the shape of the spillway sill, the following example is used: A certain hydropower project is a Class I large (1) project. The dam height is 239.0m and the total reservoir capacity is 2.467 billion m³. 3 The river valley is narrow and deep. The normal water level of the reservoir is 2702.0m. The flood discharge system consists of two spillway tunnels and one venting tunnel, all located on the right bank. The tunnel axes form an angle of approximately 30° with the downstream river channel. The two spillway tunnels are 1.4km and 1.5km long respectively, both being unpressurized spillway tunnels. The maximum discharge capacity of each spillway tunnel is 4406.38m³. 3 / s.
[0054] The intelligent optimization method for the shape of the spillway nose sill was used to design a spillway nose sill that meets the engineering objectives. The specific method is as follows: Define the project objectives, and then determine the constraints based on those objectives. The project adopts bank-side flood discharge, which is a typical narrow and deep river valley. Under such topographical constraints, in order to achieve a good energy dissipation effect, while minimizing damage to the slopes on both banks, reducing the amount of protective engineering, and saving project investment, the idea is to make the jetting water tongue as close as possible to the slope of the bank (the side where the jetting nose is set) when entering the water, and at the same time, to stretch the jetting water tongue as far as possible along the direction of water flow to reduce the root mean square of the unit width flow distribution of the water inflow. It has been basically determined that the ideal entry shape of the draft jet is a "straight line," and the draft jet should enter the water as close to the bank as possible. The effect of the draft jet is as follows: Figure 2 and Figure 3 As shown.
[0055] Determination of the type of nasal septum for nasal discharge and acquisition of experimental body size parameters: Based on the project objectives, the selected flow-lifting nose sill shape is a slanted diffuser flow-lifting nose sill, and the range of flow-lifting nose sill shape parameters is defined; among them, The height difference between the two sides of the nose sill is 11.15-20m; the turning radius on the left is 100-200m, the turning radius on the right is 400-600m, and the bevel angle of the bottom plate is 110-150°. Multiple sets of parameter values were selected from the range of body shape parameters as experimental data. Nine sets of body shape parameters for the nasal septum were determined based on orthogonal experiments, as shown in Table 1. Table 1: Orthogonal Experiment Table of Body Type Parameters for the Nose Ridge factor Elevation difference between the two sides (m) Left-hand turning radius (m) Right-hand turning radius (m) Bevel angle of the base plate (°) Body type 1 11.15 100 400 110 Body type 2 11.15 150 600 130 Body size 3 11.15 200 500 150 Body size 4 15.00 100 600 150 Body size 5 15.00 150 500 110 Body size 6 15.00 200 400 130 Body size 7 20.00 100 500 130 Body type 8 20.00 150 400 150 Body size 9 20.00 200 600 110 Numerical simulations were performed based on multiple sets of experimental body shape parameters to determine the morphology of the water jets generated by the nine sets of water jet sills, such as... Figures 4 to 12 As shown in the figure, V represents the water flow rate; Based on the numerical simulation results, the morphological parameters of the water tongue corresponding to the water sluice of the above 9 body types were extracted, as shown in Table 2. Table 2: Morphological parameters of the water tongue corresponding to the water ducts of the 9 body types Calculate body shape Leftward tilt distance L1 (m) Water entry angle (°) on the left side Deflection angle of the water tongue on the left (°) Intermediate distance L2 (m) Angle of entry of the middle water tongue into the water (°) The deflection angle of the middle water tongue (°) Rightward tilt distance L3 (m) Water entry angle of the right-side water tongue (°) The angle of deflection of the water tongue on the right side (°) Water entry arc length S (m) Standard deviation of inlet flow rate Body type 1 99.49 45.07 17.40 89.35 41.57 13.42 136.89 44.01 8.76 82.78 22.79 Body type 2 100.86 41.80 12.01 93.75 40.26 14.09 136.67 42.85 6.07 75.28 26.91 Body size 3 103.61 46.37 11.49 98.38 43.95 16.81 140.12 43.38 7.15 67.22 23.11 Body size 4 74.37 39.78 19.45 88.73 35.47 19.05 140.27 43.99 10.80 92.04 16.17 Body size 5 76.66 37.26 12.73 80.02 39.95 15.03 136.44 42.08 11.16 90.69 24.34 Body size 6 75.20 41.11 11.17 79.27 35.65 15.89 134.56 44.41 11.43 89.90 18.74 Body size 7 60.47 36.04 18.63 81.28 30.52 16.33 133.54 38.50 13.94 105.37 14.52 Body type 8 58.52 33.65 15.26 75.97 44.95 17.18 134.43 45.68 14.39 104.72 15.14 Body size 9 54.00 36.57 10.34 83.76 31.89 9.80 130.69 42.22 12.67 105.58 21.71 The results of the numerical simulation can be verified as needed. In this embodiment, body types 3 and 4 were selected for physical model experiments, and the overall shape of the corresponding jetting water tongue was obtained. Taking body type 3 as an example, see [link to example]. Figure 13 The overall morphology and hydraulic characteristics (morphological parameters of the jetting water tongue) of the jetting water tongue were compared, as shown in Table 3. The results show that the experimental and numerical simulation water tongue morphologies are similar, and the errors in the far and near jetting distances are both within 5%, which confirms that it is feasible to use this numerical simulation calculation method to calculate the hydraulic characteristics of the jetting water tongue generated by the jetting nose sill.
[0056] Table 3: Comparison of Numerical Simulation and Experimental Test Results
[0057] 12. According to the calculation results in Table 4, the root mean square error is the smallest and the calculation effect is better when the number of hidden layer neurons is 4.
[0058] Table 4: Ranking of Mean Square Errors Corresponding to the Number of Hidden Layer Nodes in Initial Data Serial Number Number of hidden layer neurons Root mean square error Sort 1 3 <![CDATA[8.7767×10 -2 ]]> 9 2 4 <![CDATA[2.1278×10 -2 ]]> 1 3 5 <![CDATA[8.9176×10 -2 ]]> 10 4 6 <![CDATA[6.9685×10 -2 ]]> 7 5 7 <![CDATA[5.4117×10 -2 ]]> 5 6 8 <![CDATA[2.3393×10 -2 ]]> 2 7 9 <![CDATA[3.9342×10 -2 ]]> 4 8 10 <![CDATA[7.8697×10 -2 ]]> 8 9 11 <![CDATA[6.0430×10 -2 ]]> 6 10 12 <![CDATA[3.0360×10 -2 ]]> 3 Here, we first need to set the sample expansion rules, as shown in Table 5. Based on the morphological parameters of the water jet generated by the 9 body types in Table 2, we use a BP neural network to perform forward simulation to expand the data.
[0059] Table 5: Sample Expansion Rules Body type parameters Minimum change value Maximum change Step size setting Elevation difference between the two sides (m) 11.15 20 2 Left-hand turning radius (m) 100 200 5 Right-hand turning radius (m) 400 600 5 Bevel angle of the base plate (°) 110 150 5 Based on the expansion rules, and using a trained mathematical model, a total of 32,794 sets of expanded data were simulated to determine the shape of the draft sill and the hydraulic characteristics of the draft water tongue generated by each draft sill. The learning results are shown in [link to documentation]. Figures 14 to 27 .
[0060] According to 14 to Figure 27 The results show that the mathematical model has a good training effect.
[0061] Among the various evaluation metrics for machine learning predictions, the mean absolute error (MAE) is 0.02, the mean squared error (MSE) is 0.01, the root mean square error (RMSE) is 0.02, and the mean absolute percentage error (MAPE) is 0.05%. The errors are relatively small, and the mean absolute percentage error (MAPE) is almost 0, indicating that the trained mathematical model is usable.
[0062] 1. NSGA-II multi-objective algorithm inversion: (1) Set the target range of constraints: Based on the constraints of the jet sill determined by the engineering objectives, to achieve the engineering objectives, the jet sill must satisfy the following conditions: the inlet arc length of the jet sill must be maximized and the root mean square of the unit width flow distribution must be minimized. These are described by mathematical expressions as follows: Maximum target for the arc length of the water jet entering the water: (Equation 1) In the formula, the length of the water tongue entering the water corresponding to the nth nasal sill body shape is used as... express.
[0063] Minimum target of root mean square of unit width flow distribution: (Equation 2) In the formula, the root mean square of the unit width flow distribution corresponding to the nth flow nose sill shape is represented by σ. n express.
[0064] (2) Constraints on the landing point of the water tongue: The river valley in the energy dissipation zone of this project is narrow, and the spillway structures are concentrated on the same bank for flood discharge, which has a significant impact on the opposite bank. Therefore, in order to achieve better efficiency, the jet chute is set as close to the local bank as possible for flood discharge. The landing point of the jet chute is constrained as follows: (Equation 3) Where x and y are the horizontal and vertical coordinates of the landing point of the jet of water, respectively. min It is 72m, x max It is 185m; y min For 20m, y max It is 42m.
[0065] (3) Water tongue deflection angle constraint: (Equation 4) Where α is the deflection angle of the jetting water tongue, and the left jetting water tongue α min For 10°, α max 20°; right side water tongue α min It is 6°, α max It is 15°.
[0066] 2. Decision based on inversion results: The inversion yields the Pareto front solution set; see [link / reference]. Figure 28 There are 115 solution sets that meet the optimization conditions. The standard deviation of the unit width flow distribution is between [12,13] and [15,19], and the inlet length is between [92,95] and [100,108] m.
[0067] The target shape parameters of the cantilever nose sill that meet the engineering objectives are selected from the ideal shape parameter solution set and verified. To ensure that the magnitude of the data values does not affect the total score, the data needs to be normalized. For example, when the two objective functions have opposite directions, one may be better the larger it is (e.g., the arc length of the water tongue), while the other may be better the smaller it is (e.g., the root mean square of the unit width flow rate). Therefore, by using the range transformation method, the various indicators can be converted into the same measurement scale, which is beneficial for subsequent weighting processing and application.
[0068] Suppose the objective function for the arc length of the water tongue before normalization of the i-th individual is x. i1 Then, for the normalized objective function y of the water tongue arc length, i1 ,Pick ,have: (Equation 5) Assume the root mean square objective function for the unit width flow rate before normalization of the i-th body type is x. i2 Then, for the normalized objective function y of the water tongue arc length, i2 ,Pick Then we have: (Equation 6) The weights of the inlet arc length and the root mean square of the unit width flow rate are assigned, and the comprehensive value is calculated: (Equation 7) Where ω1 is the weighting coefficient for the inlet arc length of the jet, ω2 is the weighting coefficient for the root mean square of the unit width flow distribution, and u i Let be the comprehensive value of the i-th body type, and finally select the body type with the best comprehensive value as the final body type; In multi-objective inversion decision-making, for the narrow and deep valley of this project, the inflow arc length and unit width flow distribution are equally important. The weights of both inflow arc length and unit width flow distribution are set to 0.5. A combined linear weighting is applied according to the decision-making method based on the inversion results, and the decision results are as follows: The specific decision-making parameters of the NSGA-II algorithm for the sill are as follows: the inlet width is 102.6m, the standard deviation of the unit width flow rate is 15.8, and the corresponding body parameters are: the height difference between the two sides is 19.9m, the left turning radius is 102.9m, the right turning radius is 480.3m, and the bottom plate oblique angle is 137.7°.
[0069] Based on the above decision-making results, the body shape parameters of the draft nose sill were verified. The draft water tongue is basically linearly distributed, and the diffusion effect is good. (See [reference]). Figure 29 The peak flow rate per unit width is distributed between 30 and 40 m. 2 Fluctuations between / s, see Figure 31 Compared with before optimization (see) Figure 30 Compared to the previous method, the distribution is more complete and the distribution effect is better, which meets the engineering objectives.
[0070] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for intelligent optimization of the shape of a flood discharge embankment, characterized in that: Includes the following steps: Define the project objectives, and then determine the constraints based on those objectives. The type of nasal cannula is determined based on the constraints, and the range of body shape parameters for the nasal cannula is set. Multiple sets of parameter values are selected as experimental data within the range of body shape parameters. Orthogonal experimental design is used to design experiments on multiple sets of experimental data to obtain experimental body shape parameters for multiple sets of nasal cannsulas with different body shapes. Numerical simulation calculations were performed based on multiple sets of experimental body shape parameters to obtain the morphological parameters of the water jets that the water jets formed by the multiple sets of experimental body shape parameters could generate respectively, and the morphological parameters of the multiple sets of water jets were used as the initial dataset. The initial dataset is expanded using a backpropagation (BP) neural network method to construct a parameter database; Set the target range of the constraints; based on the parameter database, use the NSGA-II multi-objective algorithm to invert and obtain the ideal body shape parameter solution set that falls within the target range; A multi-objective decision-making method is used to select the target body shape parameters of the sluice gate that meet the engineering objectives from the solution set of ideal body shape parameters.
2. The intelligent optimization method for the shape of the flood discharge and diversion sill as described in claim 1, characterized in that: When performing numerical simulation calculations based on multiple sets of experimental body size parameters, at least two sets of experimental body size parameters are selected for physical model experiments to verify the results of the numerical simulation calculations.
3. The intelligent optimization method for the shape of the flood discharge and diversion sill as described in claim 1, characterized in that: After obtaining the target body shape parameters of the nasal sill that meet the engineering objectives, the target body shape parameters are verified.