Underwater submerged dike design and optimization method based on weighted K-means method

Abstract

The invention discloses an underwater submerged dike design and optimization method based on a weighted K-means method, and the method comprises the following steps: carrying out a test according to a test combination obtained through a D-optimal design method, and collecting test data; the collected test data are preprocessed, a transmission coefficient is calculated, and factors influencing the wave absorption performance of the submerged dike are determined; and clustering the transmission coefficients by using a weighted K-means clustering method, analyzing an obtained clustering result, and determining a parameter selection range capable of maximizing the submerged dike wave absorption performance. According to the underwater submerged dike design and optimization method based on the weighted K-means method, marine environment data can be more accurately analyzed, the submerged dike design precision is improved, the engineering cost is effectively reduced, the submerged dike stability and durability are improved, high universality is achieved, the method is suitable for design and optimization of different types of underwater submerged dikes, and the method is suitable for popularization and application. The calculation amount and complexity are greatly reduced, and a conclusion can be obtained in a short time.

Description

Technical Field

[0001] The present invention relates to the technical fields of ocean engineering, coastal protection and ecological restoration, and particularly relates to a design and optimization method for underwater submerged breakwaters based on the weighted K-means method. Background Art

[0002] Oyster reefs, as part of so-called ecosystem engineering, are widely distributed in temperate and subtropical estuaries and shallow sea areas. These coral reefs make significant contributions to water purification, enhancement of fish resources, mitigation of coastline erosion, carbon sequestration, enhancement of biodiversity and overall ecosystem stability. They play a crucial role in stabilizing intertidal sediments and influencing hydrodynamic patterns in the coastal environment.

[0003] Although traditional rigid protection structures (such as concrete dams) can effectively resist wave erosion, they have a negative impact on the ecological environment. In recent years, nature-based protection structures (such as oyster reefs, coral reefs, etc.) have gradually attracted attention because they can not only dissipate wave energy, but also promote biodiversity, improve water quality and restore the ecosystem.

[0004] In practical applications, natural underwater submerged breakwaters should meet the following conditions: (1) having good wave dissipation performance; (2) not causing too much negative impact on the local ecological environment; (3) the cost and construction difficulty should be controlled within a reasonable range; (4) being able to ensure the long-term stability of the structure without damage. In order to meet the above conditions, the design and optimization of underwater submerged breakwaters are very important. When sufficient data is collected, it is crucial to quickly identify which factors have a greater impact on the wave dissipation performance of the submerged breakwater, which factors have a smaller impact, and their interaction.

[0005] Traditional methods rely on empirical formulas and numerical simulations. Empirical formulas are usually based on experimental data or historical engineering cases under specific conditions, and their applicable range is limited. When the marine environmental conditions change, the prediction accuracy of empirical formulas will decrease significantly. Although numerical simulation technology can simulate complex marine environments, its calculation accuracy highly depends on the selection of model parameters and the setting of boundary conditions. Moreover, the computational amount of numerical simulation is large, especially when dealing with large-scale and multi-scale marine environmental data, the computational efficiency is low.

[0006] In the prior art, clustering analysis is an unsupervised learning method that can automatically discover potential patterns and structures from a large amount of data. In ocean engineering, clustering analysis can be used to identify the key features of the ocean environment, providing a scientific basis for the design of submerged breakwaters. Although the traditional K-means clustering method is simple and effective, it has certain limitations when dealing with complex data, such as being sensitive to noise and difficult to handle non-uniform data distributions. The weighted K-means method can better reflect the importance or influence of data by assigning weights to data points, thereby improving the accuracy of clustering. In the design of submerged breakwaters, the weighted K-means method can assign weights according to the influence degree of different environmental parameters on the design, so as to more accurately identify key design parameters and optimize the design scheme.

[0007] Therefore, based on physical model tests, the present invention adopts the weighted K-means clustering method and proposes a method for designing and optimizing underwater submerged breakwaters based on the weighted K-means method to achieve the design and optimization of ecological submerged breakwaters. Summary of the Invention

[0008] The object of the present invention is to provide a method for designing and optimizing underwater submerged breakwaters based on the weighted K-means method. By introducing the weighted K-means clustering method, it can more accurately analyze ocean environment data and improve the accuracy of submerged breakwater design; by optimizing design parameters, it can effectively reduce engineering costs and improve the stability and durability of submerged breakwaters; it can greatly reduce the amount of calculation and complexity, and draw conclusions in a short time, and can be applied to the design and optimization of different types of underwater submerged breakwaters.

[0009] To achieve the above object, the present invention provides a method for designing and optimizing underwater submerged breakwaters based on the weighted K-means method, including the following steps:

[0010] Step S1: Conduct experiments according to the experimental combinations obtained by the D-optimal design method, and collect experimental data;

[0011] Step S2: Preprocess the collected experimental data, calculate the transmission coefficient under each working condition, and determine the main factors affecting the wave dissipation performance of the submerged breakwater;

[0012] Step S3: Use the weighted K-means clustering method to cluster the preprocessed data according to the transmission coefficient, analyze the obtained clustering results, and determine the parameter selection range that can maximize the wave dissipation performance of the submerged breakwater.

[0013] Preferably, in step S1, give the experimental combinations according to the D-optimal design method, simulate different ocean environments through adjusting the parameters of the wave maker, and simultaneously collect and record the data of the wave height meter for subsequent analysis;

[0014] Among them, the collected test data specifically include: the transmitted wave height H t and the relationships with seven independent variable parameters, namely the relative water depth kh, the wave steepness kH / 2, the relative submergence depth d / h of the oyster reef, the relative length kL / (2π) of the oyster reef, the relative distance kL s / (2π) between oyster reefs, the riverbed slope s, and the number N of oyster reefs.

[0015] Preferably, in step S2, the collected test data is preprocessed, and the transmission coefficient K t is calculated to determine the main factors affecting the wave dissipation performance of the submerged breakwater. The specific process is as follows:

[0016] Step S21: Preprocess the collected test data;

[0017] The collected data contains incident wave signals and reflected wave signals, so the data is separated as follows:

[0018]

[0019] η1 = A1 cosωt + B1 sinωt;

[0020] η2 = A2 cosωt + B2 sinωt;

[0021] where a i is the incident wave amplitude, a r is the reflected wave amplitude, k is the wave number, and Δl is the distance between wave gauges No. 1 and No. 2; η1 and η2 are the measured data of wave gauges No. 1 and No. 2 respectively, and the values of parameters A1, B1, A2, and B2 are obtained from this;

[0022] Step S22: Calculate the transmission coefficient K t ;

[0023] After separating the incident wave and the reflected wave, the transmitted wave height is obtained, and the transmission coefficient K t is calculated as follows:

[0024]

[0025] where K t is the transmission coefficient; H t is the transmitted wave height measured in the test; H i is the incident wave height; a t is the transmitted wave amplitude;

[0026] Step S23: Determine the main factors affecting the wave dissipation performance;

[0027] According to the transmission coefficient obtained in step S22, the Box-plot method is used to analyze the influence of a single factor on the transmission coefficient K t The influence effect is obtained by judging the change of the median with the change of the parameter value, and the influence degree of the parameter on the wave dissipation performance is obtained;

[0028] Step S24: Perform t-sne dimensionality reduction and visualization processing on the independent variable parameters;

[0029] According to the basic principle of t-sne, the relative water depth kh, wave steepness kH / 2, relative immersion depth d / h of oyster reefs, relative length kL / (2π) of oyster reefs, relative distance kL s / (2π) between oyster reefs, riverbed slope s, and the number N of oyster reefs, seven independent variable parameters and the transmission coefficient K t are dimensionally reduced to a two-dimensional space for subsequent clustering operations.

[0030] Preferably, in step S3, the weighted K-means clustering method is used to cluster the preprocessed data according to the transmission coefficient K t The clustering results are analyzed to determine the parameter selection range that can maximize the wave dissipation performance of the submerged breakwater. The specific process is as follows:

[0031] Step S31: Determine the number of cluster centers;

[0032] According to the basic principle of K-means clustering, the goal of clustering is to minimize the sum of squared errors of each sample point to the nearest cluster center. Then the sum of squared errors SSE of the data set is as follows:

[0033]

[0034] where the size of SSE represents the quality of the clustering result; x is the data object; C i is the i-th cluster center; K is the number of cluster centers;

[0035] where the maximum value of K does not exceed the square root of the sample size N, as follows:

[0036]

[0037] Step S32: Introduce the weight vector w, assign weights according to the influence degree of different environmental parameters on the design, and thus identify the key design parameters and optimize the design scheme;

[0038] After considering the influence of each independent variable parameter, the selected weight assignment is as follows:

[0039] w = [0.04, 0.04, 0.04, 0.04, 0.04, 0.04, 0.04, 0.72];

[0040] Step S33. The weighted K-means optimizes the cluster centers and the assignment of data points through iteration until convergence, thereby realizing the clustering operation.

[0041] Preferably, in step S33, the clustering process is as follows:

[0042] Step S331. Assign data points to the nearest cluster center;

[0043] For each data point x i , calculate its weighted distance from each cluster center C j as follows:

[0044] d ij = w i ·||x i - C j ||;

[0045] where d ij is the weighted distance between the data point x i and the cluster center C j ; w i is the weight of the data point x i ; ||x i - C j || is the Euclidean distance between the data point x i and the cluster center C j ;

[0046] Step S332. Update the cluster centers;

[0047] For each cluster j, recalculate its cluster center C' j through the weighted average of all current data points, as follows:

[0048]

[0049] where x i ∈ Cluster j represents all data points x i that currently belong to the j-th cluster;

[0050] Step S333. Check for convergence;

[0051] Calculate the change amount between the current cluster center and the cluster center of the previous iteration. If the change amount is less than a preset threshold, the algorithm converges and stops iterating; otherwise, return to step S331 to continue iterating.

[0052] Preferably, in step S4, according to the clustering analysis results, the geometric shape, material selection, and structural layout of the submerged breakwater are optimized. The specific process is as follows:

[0053] Analyze the obtained clustering results, combine the Box-plot method to obtain the parameters with greater influence, and under the condition of reducing the transmitted wave height, obtain the value range of the corresponding independent variable parameters by plotting; the weighted K-means method clusters with K t as the main factor, comprehensively consider the interaction effects between independent variable parameters to obtain the value range of parameters with the best wave dissipation performance; optimize the structure, material, and layout of the underwater submerged breakwater according to the obtained conclusions to achieve the best wave dissipation performance.

[0054] Therefore, the present invention adopts the above-mentioned underwater submerged breakwater design and optimization method based on the weighted K-means method, and the beneficial effects are as follows:

[0055] (1) Accuracy: By introducing the weighted K-means clustering method, the present invention can analyze marine environmental data more accurately and improve the accuracy of submerged breakwater design;

[0056] (2) Economy: By optimizing the design parameters, the present invention can effectively reduce the project cost and improve the stability and durability of the submerged breakwater;

[0057] (3) Universality: The method of the present invention has strong versatility and can be applied to the design and optimization of different types of underwater submerged breakwaters;

[0058] (4) Rapidness: Compared with the traditional optimization method, the present invention can greatly reduce the calculation amount and complexity and can draw conclusions in a short time.

[0059] Next, through the drawings and embodiments, the technical solutions of the present invention will be further described in detail. Brief Description of the Drawings

[0060] Figure 1 is the simplified test model diagram corresponding to the present invention;

[0061] Figure 2 is the sample point distribution diagram of tests with different d / h;

[0062] Figure 3 is the schematic principle diagram of the Box-plot method;

[0063] Figure 4 is the result of applying the Box-plot method to the seven independent variable parameters in the present invention; where, a is the relative water depth kh; b is the wave steepness kH / 2; c is the relative immersion depth d / h of the oyster reef; d is the relative length kL / (2π) of the oyster reef; e is the relative distance kL between oyster reefss / (2π); f is the riverbed slope s; g is the number of oyster reefs N;

[0064] Figure 5 It is the clustering visualization effect diagram after applying the t-sne technique;

[0065] Figure 6 It is the sum of squared errors (SSE) of clustering in the present invention;

[0066] Figure 7 It is the feature map of each class after clustering is completed;

[0067] Figure 8 It is the distribution of the clustering results under seven independent variable parameters; among them, a is the relative water depth kh; b is the wave steepness kH / 2; c is the relative immersion depth of the oyster reef d / h; d is the relative length of the oyster reef kL / (2π); e is the relative distance between oyster reefs kL s / (2π); f is the riverbed slope s; g is the number of oyster reefs N;

[0068] Figure 9 It is the value range of three main parameters; among them, a is the relative immersion depth of the oyster reef d / h; b is the relative length of the oyster reef kL / (2π); c is the number of oyster reefs N. Specific implementation manner

[0069] The technical solution of the present invention will be further described below through the drawings and embodiments.

[0070] A method for designing and optimizing an underwater submerged breakwater based on the weighted K-means method in the present invention includes the following steps:

[0071] Step S1: Conduct experiments according to the experimental combinations obtained by the D-optimal design method, and collect experimental data.

[0072] Step S2: Preprocess the collected experimental data, calculate the transmission coefficient K t , determine the main factors affecting the wave dissipation performance of the submerged breakwater, and perform normalization processing on the independent variable parameters for subsequent clustering operations.

[0073] Step S3: Use the weighted K-means clustering method to cluster the preprocessed data according to the transmission coefficient K t Perform analysis on the obtained clustering results to determine the parameter selection range that can maximize the wave dissipation performance of the submerged breakwater.

[0074] Step S4: Optimize the geometric shape, material selection, and structural layout of the submerged breakwater according to the clustering analysis results.

[0075] Embodiment

[0076] Step S1: Conduct experiments according to the experimental combinations obtained by the D-optimal design method, and collect experimental data.

[0077] Taking oyster reefs as the research object, in the laboratory, according to the experimental combinations given by the D-optimal design method, by adjusting the parameters of the wave generator, different marine environments are simulated for experiments, and at the same time, the data of four wave gauges are collected and recorded for subsequent analysis.

[0078] Among them, the collected experimental data specifically includes: the transmitted wave height H t and the relationships with seven independent variable parameters, namely the relative water depth (kh), wave steepness (kH / 2), relative submergence depth of the oyster reef (d / h), relative length of the oyster reef (kL / (2π)), relative distance between oyster reefs (kL s / (2π)), riverbed slope (s), and the number of oyster reefs (N).

[0079] Using the D-optimal design method in the present invention can ensure that the experimental combinations are as comprehensive as possible, while reducing the number of design groups, which is reduced to five ten-thousandths of the original in the present invention, greatly reducing the time of physical model experiments and numerical simulation calculations.

[0080] Step S2: Preprocess the collected experimental data, calculate the transmission coefficient K t under each working condition, determine the main factors affecting the wave dissipation performance of the submerged breakwater, and perform normalization processing on the independent variable parameters for subsequent clustering operations.

[0081] Step S21: Preprocess the collected experimental data.

[0082] As Figure 1 shown, for the data of the water surface height measured by the four wave gauges collected, due to the certain reflection effect of the submerged breakwater on the waves, the data collected by wave gauges No. 1 and No. 2 not only contain the incident wave signal but also the reflected wave signal. Therefore, separation processing is required as follows:

[0083]

[0084] η1 = A1 cosωt + B1 sinωt;

[0085] η2 = A2 cosωt + B2 sinωt;

[0086] where, a i is the incident wave amplitude, a r is the reflected wave amplitude, k is the wave number, and Δl is the distance between wave gauges No. 1 and No. 2; η1 and η2 are the measured data of wave gauges No. 1 and No. 2 respectively, from which the values of parameters A1, B1 and A2, B2 are obtained.

[0087] Step S22: Calculate the transmission coefficient K under each working condition t .

[0088] After separating the incident wave and the reflected wave, the transmitted wave height is obtained, and the transmission coefficient K is calculated t , as follows:

[0089]

[0090] where K t is the transmission coefficient; H t is the transmitted wave height measured in the experiment; H i is the incident wave height; a t is the transmitted wave amplitude.

[0091] Step S23: Determine the main factors affecting the wave dissipation performance

[0092] Based on the transmission coefficient obtained in Step S22, it is possible to know the quality of the wave dissipation performance under different working conditions, but it is impossible to obtain the influence degree of a single factor on the wave dissipation performance of the submerged breakwater. Therefore, in order to determine the main factors affecting the wave dissipation performance, the Box-plot method can be used to quickly analyze the influence effect of a single factor on the transmission coefficient K t , so as to eliminate the independent variable factors that have little influence on the test results, achieve the purpose of quickly reducing the number of test independent variables, thereby reducing the subsequent workload and saving test time.

[0093] As Figure 2 shown, the transmission coefficient K corresponding to different values of a single parameter is plotted in a graph. The specific operation process of the Box-plot method is as t shown. According to the plotted sample points, information such as the upper bound, lower bound, median, upper and lower quartiles, and outliers of the sample can be displayed. By judging the change of the median of K Figure 3 with the change of the parameter value, the influence degree of the parameter on the wave dissipation performance can be determined. t As

[0094] shown, the relative water depth (kh), wave steepness (kH / 2), relative immersion depth of oyster reef (d / h), relative length of oyster reef (kL / (2π)), relative distance between oyster reefs (kL Figure 4 / (2π)), riverbed slope (s), and number of oyster reefs (N), seven independent variable parameters are respectively shown. The change curves of the transmission coefficient with their own changes are plotted, and the median of the transmission coefficient corresponding to all working conditions with the change of a single factor is obtained. s / (2π)), riverbed slope (s), number of oyster reefs (N), seven independent variable parameters, and the change curves of the transmission coefficient with their own changes are plotted, and the median of the transmission coefficient corresponding to all working conditions with the change of a single factor is obtained.

[0095] By judging the change of the median as the parameter value changes, the influence degree of the parameter on the wave-dissipating performance is obtained. Select several parameters with significant median changes as the main influencing factors as the parameter value changes, and mainly consider their influences to reduce the independent variables and simplify the model.

[0096] Therefore, it is analyzed that among the seven independent variable parameters, the three independent variable parameters of the relative submergence depth of the oyster reef (d / h), the relative length of the oyster reef (kL / (2π)), and the number of oyster reefs (N) have the greatest influence on the result of the transmission coefficient, while the influence of the remaining independent variable parameters on the wave-dissipating performance of the submerged breakwater is not significant. Therefore, focus on the above three independent variable factors.

[0097] Step S24: Perform t-sne dimensionality reduction and visualization processing on the independent variable parameters.

[0098] According to the basic principle of t-sne, it is a non-linear dimensionality reduction technique mainly used to reduce high-dimensional data to two-dimensional or three-dimensional space for better observing and visualizing the structure and characteristics of the data.

[0099] Therefore, use the t-sne dimensionality reduction technique to reduce the seven independent variable parameters of the relative water depth (kh), wave steepness (kH / 2), relative submergence depth of the oyster reef (d / h), relative length of the oyster reef (kL / (2π)), relative distance between oyster reefs (kL s / (2π)), riverbed slope (s), and the number of oyster reefs (N) and the transmission coefficient K t to two-dimensional space as Figure 5 shown for subsequent clustering operations.

[0100] Step S3: Use the weighted K-means clustering method to cluster the preprocessed data according to the transmission coefficient K t and analyze the obtained clustering results to determine the parameter selection range that can maximize the wave-dissipating performance of the submerged breakwater.

[0101] Step S31: Determine the number of cluster centers.

[0102] According to the basic principle of K-means clustering, the goal of clustering is to minimize the sum of squared errors of each sample point to the nearest cluster center, that is, the cost function SSE of clustering. Therefore, the sum of squared errors SSE of the entire data set is as follows:

[0103]

[0104] where the size of SSE represents the quality of the clustering result; x is the data object; C i is the i-th cluster center; and K is the number of cluster centers.

[0105] Theoretically, as K increases, the SSE will monotonically decrease because the increase in the number of cluster centers means that there will always be some sample points that will save a certain distance due to belonging to new cluster centers until K = N, at which point each sample will form its own class and the SSE value will drop to 0. However, to ensure that the SSE is as small as possible while minimizing the number of cluster centers, generally ensure that the maximum value of K does not exceed the square root of the sample size N, as follows:

[0106]

[0107] As Figure 6 shown, it can be clearly seen that when K = 6, the descent rate of the SSE image decreases rapidly, so it is preferred to choose K = 6 as the number of cluster centers.

[0108] Step S32: Introduce the weight vector w and assign weights according to the influence degree of different environmental parameters on the design, so as to more accurately identify the key design parameters and optimize the design scheme.

[0109] In order to better reflect the importance or influence of data and improve the accuracy of clustering, adding the weight w on the basis of K-means clustering can assign weights according to the influence degree of different environmental parameters on the design, so as to more accurately identify the key design parameters and optimize the design scheme. After fully considering the influence of each independent variable parameter, the selected weight assignment is as follows:

[0110] w = [0.04, 0.04, 0.04, 0.04, 0.04, 0.04, 0.04, 0.72].

[0111] Step S33: Weighted K-means optimizes the allocation of cluster centers and data points through iteration until convergence, and then realizes the clustering operation.

[0112] The clustering process can be iteratively operated by a computer, and the specific process is as follows:

[0113] Step S331: Allocate data points to the nearest cluster center.

[0114] For each data point x i , calculate its weighted distance from each cluster center C j , as follows:

[0115] d ij = w i · ||x i - C j ||;

[0116] Among them, d ij is the distance between the data point x i and the cluster center Cj Weighted distance; w i is the data point x i 's weight; ||x i - C j || is the Euclidean distance between the data point x i and the cluster center C j , and its calculation formula is:

[0117]

[0118] Step S332, update the cluster center.

[0119] For each cluster, recalculate its cluster center C’ by the weighted average of all current data points j , as follows:

[0120]

[0121] where, x i ∈ Cluster j represents all data points x that currently belong to the j-th cluster i .

[0122] Step S333, check convergence.

[0123] Calculate the change amount between the current cluster center and the cluster center of the previous iteration. If the change amount is less than the preset threshold, the algorithm converges and stops iterating; otherwise, return to step S331 to continue iterating.

[0124] Step S4, according to the clustering analysis results, optimize the geometric shape, material selection and structural layout of the submerged breakwater.

[0125] Analyze the obtained clustering results, focusing on the class with the smallest transmission coefficient K t The weighted K-means method clusters with K t as the main factor, and comprehensively considers the interaction effects between independent variable parameters to obtain the parameter value range with the best wave dissipation performance.

[0126] According to the obtained conclusions, the structure, materials and layout of the underwater submerged breakwater can be optimized to achieve the best wave dissipation performance.

[0127] As Figure 7 shown, all samples are divided into six categories according to K = 6. As shown in Table 1, the first category has the smallest transmission coefficient, so the value range of the parameters in the first category is focused on.

[0128] Table 1 Range of values of each parameter for each category after clustering

[0129] Clustering <![CDATA[K t <!-- 7 -->]]> Cluster 1 [0.19，0.52) Cluster 2 [0.52，0.70) Cluster 3 [0.70，0.82) Cluster 4 [0.82，0.90) Cluster 5 [0.90，0.95) Cluster 6 [0.95，1.00]

[0130] As Figure 8 shown, through data analysis, it can be seen that: when the independent variables of concern are the three independent variable parameters of the relative immersion depth of the oyster reef (d / h), the relative length of the oyster reef (kL / (2π)), and the number of oyster reefs (N), the distribution of the first category is significantly limited within a certain range of values, while the six clustering results of the remaining independent variable parameters are generally evenly distributed. This also confirms to a certain extent that the three independent variable parameters of the relative immersion depth of the oyster reef (d / h), the relative length of the oyster reef (kL / (2π)), and the number of oyster reefs (N) have the greatest impact on the wave-dissipating performance, while the influence of the remaining independent variables can be ignored. Through analysis, when the wave-dissipating performance is optimal, as Figure 9 shown, the range of values of the above three main independent variable parameters is as follows:

[0131] Relative immersion depth of oyster reef (d / h) ∈ [0.55, 0.70];

[0132] Relative length of oyster reef (kL / (2π)) ∈ [0.22, 0.30];

[0133] Number of oyster reefs N = 3 or 4;

[0134] According to the conclusions obtained, the structure, materials, and layout of the underwater submerged breakwater can be optimized to achieve the best wave-dissipating performance, which has great significance in practical engineering applications.

[0135] Therefore, the present invention adopts the above-mentioned method for designing and optimizing an underwater submerged breakwater based on the weighted K-means method. By introducing the weighted K-means clustering method, it can analyze marine environmental data more accurately and improve the accuracy of submerged breakwater design; by optimizing design parameters, it can effectively reduce engineering costs and improve the stability and durability of the submerged breakwater; the method proposed by the present invention has strong versatility and can be applied to the design and optimization of different types of underwater submerged breakwaters; compared with traditional optimization methods, it can greatly reduce the amount of calculation and complexity and can draw conclusions in a short time.

[0136] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for designing and optimizing underwater submerged dikes based on weighted K-means method, characterized in that: The following steps are involved: Step S1, conducting tests according to the test combination obtained by the D-optimal design method and collecting test data; Step S2, pre-processing the collected test data, calculating the transmission coefficient under each working condition, and determining the main factors affecting the wave dissipation performance of the submerged dike; Step S3: cluster the preprocessed data according to the transmission coefficient using the weighted K-means clustering method, analyze the obtained clustering results, and determine the parameter selection range that can maximize the submerged dike wave absorption performance.

2. The underwater submerged dike design and optimization method based on the weighted K-means method according to claim 1, characterized in that: In step S1, a test combination is given according to the D-optimal design method, and the wave machine parameters are adjusted to simulate different ocean environments for testing, while the data of the wave height meter are collected and recorded for subsequent analysis; The collected test data specifically include: transmission wave height H t Relative water depth kh, wave steepness kH / 2, relative immersion depth of oyster reef d / h, relative length of oyster reef kL / (2π), relative distance between oyster reefs kL s / (2π), riverbed slope s and the number of oyster reefs N.

3. The underwater submerged dike design and optimization method based on the weighted K-means method according to claim 1, characterized in that: In step S2, the collected test data is preprocessed to calculate the transmission coefficient K under each working condition. t , determine the main factors affecting the wave-breaking performance of the submerged dike. The specific process is as follows: Step S21, preprocessing the collected test data; The collected data contains incident wave signals and reflected wave signals, so the data is separated and processed as shown below: η1=A1 cosωt+B1 sinωt; η2=A2 cosωt+B2 sinωt; Among them, a i is the incident wave amplitude, a r is the reflected wave amplitude, k is the wave number, Δl is the distance between wave height meters 1 and 2; η1 and η2 are the measured data of wave height meters 1 and 2, respectively, from which the values ​​of parameters A1, B1 and A2, B2 are obtained; Step S22: Calculate the transmission coefficient K under each working condition t ; After separating the incident wave and the reflected wave, the transmission wave height is obtained and the transmission coefficient K is calculated. t , as shown below: Among them, K t is the transmission coefficient; H t H is the transmission wave height measured in the experiment; i is the incident wave height; a t is the transmission amplitude; Step S23, determining the main factors affecting the wave absorbing performance; According to the transmission coefficient obtained in step S22, the Box-plot method is used to analyze the effect of a single factor on the transmission coefficient K t By judging the change of the median with the change of parameter value, the influence degree of the parameter on the wave-breaking performance can be obtained; Step S24, performing t-SNE dimension reduction and visualization processing on the independent variable parameters; According to the basic principle of t-sne, the relative water depth kh, wave steepness kH / 2, relative immersion depth of oyster reef d / h, relative length of oyster reef kL / (2π), relative distance between oyster reefs kL s / (2π), riverbed slope s, number of oyster reefs N and transmission coefficient K t Reduce the dimension to two-dimensional space for subsequent clustering operations.

4. The underwater submerged dike design and optimization method based on the weighted K-means method according to claim 1, characterized in that: In step S3, the weighted K-means clustering method is used to cluster the preprocessed data according to the transmission coefficient K t Clustering is performed, and the obtained clustering results are analyzed to determine the parameter selection range that can maximize the wave absorption performance of the submerged dike. The specific process is as follows: Step S31, determining the number of cluster centers; According to the basic principle of K-means clustering, the goal of clustering is to make the total square error of each sample point to the nearest cluster center, then the square error SSE of the data set is as follows: Among them, the size of SSE indicates the quality of clustering results; x is the data object; C i is the i-th cluster center; K is the number of cluster centers; Among them, the maximum value of K does not exceed the square root of the sample size N, as shown below: Step S32: introducing a weight vector w, assigning weights according to the degree of influence of different environmental parameters on the design, thereby identifying key design parameters and optimizing the design scheme; After considering the influence of each independent variable parameter, the weight distribution is selected as follows: w＝[0.04,0.04,0.04,0.04,0.04,0.0.4,0.04,0.72]； Step S33: Weighted K-means optimizes the distribution of cluster centers and data points by iteration until convergence, thereby achieving clustering operation.

5. The underwater submerged dike design and optimization method based on the weighted K-means method according to claim 1, characterized in that: In step S33, the clustering process is as follows: Step S331, assigning data points to the nearest cluster center; For each data point x i , calculate its relationship with each cluster center C j The weighted distance is as follows: d ij =w i ·||x i -C j ||; Among them, d ij is the data point x i With cluster center C j The weighted distance of i is the data point x i The weight of ||x i -C j || is the data point x i With cluster center C j The Euclidean distance between Step S332, updating the cluster center; For each cluster, recalculate its cluster center C' by taking the weighted average of all current data points j , as shown below: Among them, x i ∈Cluster j Represents all data points x that currently belong to the jth cluster i ; Step S333, checking convergence; The change between the current cluster center and the cluster center of the previous iteration is calculated. If the change is less than a preset threshold, the algorithm converges and the iteration stops; otherwise, return to step S331 to continue the iteration.

6. The underwater submerged dike design and optimization method based on the weighted K-means method according to claim 1, characterized in that: In step S4, the geometry, material selection and structural layout of the submerged dike are optimized according to the cluster analysis results. The specific process is as follows: The clustering results were analyzed and the Box-plot method was used to obtain the parameters with greater influence. Under the condition of reducing the transmission wave height, the value range of the corresponding independent variable parameters was obtained by drawing. The weighted K-means method was based on K t The main factors are clustered and the interaction effects between the independent variable parameters are comprehensively considered to obtain the parameter value range with the best wave-breaking performance; based on the conclusions, the structure, material and layout of the underwater submerged dike are optimized to achieve the best wave-breaking performance.

Images