Semi-submersible ocean floating platform size optimization design method and device and storage medium

Abstract

The invention discloses a semi-submersible type ocean floating platform size optimization design method and device and a storage medium, and belongs to the technical field of offshore platforms, and the method comprises the steps that according to application scenes and function requirements, a size scheme of a floating platform is obtained through preliminary design; selecting sample points through Latin hypercube sampling, and establishing an agent model through a response surface method; performing optimization design on the external dimension of the platform by using an NSGA-II algorithm based on the proxy model to obtain an optimal solution set; and verifying the optimal solution set to ensure the optimization accuracy, and selecting the optimal size as required. According to the technical scheme, the size of the semi-submersible floating platform is optimized by taking economical efficiency and safety as targets, and the optimization efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of offshore platforms, and in particular relates to a sizing design method and device for a semi-submersible ocean floating platform, and a storage medium. Background Art

[0002] In engineering applications, the construction cost and safety performance of offshore platforms have always been the focus of scholars' research. Compared with land engineering, marine engineering is in a complex environment for a long time and often encounters extreme weather such as typhoons. The marine platforms that have been successfully applied are complex in structure, large in size, expensive in cost, and extremely difficult in the construction process. The civil industry is difficult to support its construction cost and maintenance costs. Therefore, from the perspective of economy and safety, the size optimization of semi-submersible floating platforms is an urgent problem to be solved. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and device for optimizing the design of the size of a semi-submersible ocean floating platform, and a storage medium.

[0004] To achieve the above object, the present invention adopts the following technical solution: A method for optimizing the size of a semi-submersible marine floating platform, comprising: Obtain preliminary floating platform size plan; According to the preliminary floating platform size plan, based on the optimal Latin hypercube sampling, multiple sample points with different geometric design variable values ​​corresponding to different size shapes are generated to form a sample space; According to the sample space, the objective variable and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition are obtained, and the data are divided into a training set and a test set; Based on the training set, a surrogate model is established using the polynomial response surface method, wherein the surrogate model is used to fit the functional relationship between the optimization objective, the constraint variables and the design variables, and the accuracy of the surrogate model is verified using the test set; According to the agent model, different weights are assigned to each optimization objective, and the non-dominated sorting genetic algorithm is used to perform multiple iterations to obtain the Pareto optimal solution set of the design variables. The Pareto optimal solution set of the design variables is compared with the corresponding simulation calculation results to conduct a difference assessment, and the optimal size is selected according to the requirements and error results. At the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

[0005] The present invention also provides a device for optimizing the size of a semi-submersible marine floating platform, comprising: A first processing module is used to obtain a preliminary floating platform size plan; The second processing module is used to generate a plurality of sample points with different geometric design variable values ​​corresponding to different size shapes to form a sample space based on optimal Latin hypercube sampling according to the preliminary floating platform size plan; The third processing module is used to obtain the target variable and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition according to the sample space, and divide the data into a training set and a test set; A fourth processing module is used to establish a proxy model using a polynomial response surface method according to the training set, wherein the proxy model is used to fit the functional relationship between the optimization objective, the constraint variables and the design variables, and the accuracy of the proxy model is verified by using a test set; The fifth processing module is used to assign different weights to each optimization target according to the agent model and then use the non-dominated sorting genetic algorithm to perform multiple iterative calculations to obtain the Pareto optimal solution set of the design variables; The sixth processing module is used to compare the Pareto optimal solution set of the design variables with the corresponding simulation calculation results, conduct difference evaluation, and select the optimal size according to the requirements and error results; at the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

[0006] An embodiment of the present invention further provides a storage medium having a computer program stored thereon, and the computer program executes a method for optimizing the size of a semi-submersible ocean floating platform when the computer program is run.

[0007] According to the application scenarios and functional requirements, the present invention preliminarily designs the size scheme of the floating platform; selects sample points by optimizing Latin hypercube sampling, and establishes a proxy model by using the response surface method; optimizes the appearance size of the platform based on the proxy model using the NSGA-Ⅱ algorithm to obtain the optimal solution set; verifies the optimal solution set to ensure the accuracy of the optimization, and selects the optimal size according to the requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0009] Figure 1 This is a flow chart of a method for optimizing the size of a semi-submersible marine floating platform according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the dimensions of a semi-submersible ocean floating platform according to an embodiment of the present invention; Figure 3 This is a line graph showing the error in the size optimization results of a semi-submersible ocean floating platform according to an embodiment of the present invention. DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0011] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0012] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a method for optimizing the size of a semi-submersible marine floating platform, comprising: S1: Preliminary size plan. According to the application scenario and functional requirements, a preliminary floating platform size plan is designed, a numerical model of the preliminary plan is established, and numerical simulation calculations are performed. The objectives and constraints of the optimization problem are defined, the controlling conditions of the numerical calculation are selected, and the initial value of the floating platform size optimization objective is obtained; S2: Establish mathematical model. According to the geometric data and constraints constituting the floating platform shape, establish a parametric mathematical model to define the required design variables and related parameter ranges; S3: Optimal Latin hypercube sampling. For the initial size plan in step S1, within the geometric design variables and their parameter ranges given in step S2, based on the optimal Latin hypercube sampling method, a certain number of sample points with different geometric design variable values ​​corresponding to different size shapes are sampled to form a sample space; S4: Numerical simulation calculation. Based on the sample space obtained by sampling in step S3, a corresponding numerical model is established, and numerical simulation calculation is performed to output the target variables and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition. Part of the output results and their corresponding input sample points are used as the training set for the subsequent steps, and the other part is used as the test set; S5: Establishing a surrogate model using the response surface method. Use the polynomial response surface method to establish a surrogate model based on the training set in step S4, fit the functional relationship between the optimization objective, constraint variables and design variables, and verify the accuracy of the surrogate model using the data in the test set; S6: NSGA-II performs multi-objective optimization. Using NSGA-II (Non-dominated Sorting Genetic Algorithm II), on the basis of the proxy model described in step S5, different weights are assigned to each optimization objective, and after multiple iterations, the Pareto optimal solution set of the design variables is obtained; S7: Verification of optimization results. According to the size parameters with different weight combinations in S6, the corresponding numerical model is established for simulation calculation to obtain the numerical simulation results, and the difference between them and the solution obtained by the optimization model in S6 is evaluated to verify the accuracy of the optimization results; if the optimization results are accurate, the optimal solution set is returned and the optimal size is selected as needed. At the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

[0013] As an implementation method of an embodiment of the present invention, in step S1, based on economy and safety, the goal of optimizing the size of the floating platform is formulated according to the results of numerical simulation calculations of the initial size scheme.

[0014] As an implementation of the embodiment of the present invention, in step S4, after obtaining the numerical output results of the sample points, a correlation analysis is performed on the input design variables to evaluate the impact of the design variables on the output results.

[0015] As an implementation method of an embodiment of the present invention, in step S5, the fitting process of the proxy model is divided into two stages. In the first stage, the distance relationship between the design variable and the optimal position of the response surface is determined. When the sample point is far away from the optimal position of the response surface, the first-order basis function is used for approximation, as shown in formula (1); in the second stage, the steepest descent method is used to search within the spatial range of the set variable to determine whether a surface appears. If a surface appears, the second-order model is replaced to perform precise approximation near the optimal value, as shown in formula (2).

[0016] (1) (2) in, k is the number of design variables, y represents the predicted response value, , , are the offset term, linear offset, and second-order offset coefficient respectively; is the interaction coefficient, Represents the total error composed of various types of errors.

[0017] By multiple correlation coefficient and corrected multiple correlation coefficient Verify the accuracy of the function. The higher the fitting accuracy of the approximate model, and The closer it is to 1. Use the following formulas (3) to (6) to calculate: (3) (4) (5) (6) in, is the mean of the approximate model, for The theoretical prediction value of n is the number of sample points, k is the number of independent variables.

[0018] As an implementation method of the embodiment of the present invention, in step S6, the convergence of the NSGA-II algorithm is verified through multiple iterations and then the optimization process is performed. If the NSGA-II algorithm does not converge, the process returns to step S3.

[0019] Embodiment 2: like Figure 1 As shown, an embodiment of the present invention also provides a method for optimizing the size of a semi-submersible marine floating platform, comprising the following steps: S1: Preliminary size plan. According to the application scenario and functional requirements, the size plan of the semi-submersible ocean floating platform is preliminarily designed. Its main appearance dimensions are shown in Figure 2 The floating platform structure is divided into a living layer, a mechanical layer, a water tank and a lower heave plate. Its external dimensions include: the side length of the heave plate , Heave Plate Thickness , Water tank height , Water tank side length , Mechanical area height , Living area height and the length of the living area side . Establish a numerical model of the initial proposal and perform numerical simulation calculations using finite element analysis software. Define the optimization goal as minimizing the total mass and heave response , determine the four constraints: stable height , Freeboard , Rolling motion The control condition of numerical calculation is selected as the working condition, and the initial values ​​of the total mass and heave response of the floating platform under this condition are calculated; S2: Establish mathematical model. According to the geometric data and constraints that constitute the floating platform shape, a parametric mathematical model is established to define the required design variables and related parameter ranges. Five independent variables are considered in the design, namely, the water tank height , Water tank side length , Mechanical area height , Living area height and the length of the living area side . The established mathematical model is shown in (7): (7) in, and are the total mass and heave response of the floating platform, and the corresponding weighting coefficients are expressed as and ; Indicates the reference value for each target.

[0020] S3: Optimal Latin hypercube sampling. For the initial size plan in step S1, based on the optimal Latin hypercube sampling method, samples are taken from the range corresponding to each design variable to generate 25 sample points to form a sample space; S4: Numerical simulation calculation. Based on the 25 sample points obtained in step S3, the corresponding numerical model is established using finite element analysis software to perform hydrodynamic analysis, and the stable height of the floating platform corresponding to different sample points under working conditions is output. , Freeboard , roll response value , Heave response value and total mass . 20 groups of output results and their corresponding input sample points constitute the training set for subsequent steps, and the other 5 groups constitute the test set; S5: Establishing a surrogate model using the response surface method. Use the polynomial response surface method to establish a surrogate model based on the training set in step S4, and fit the optimization target ( and ), constraint variables ( , , ) and design variables ( , , , , ) and used the data in the test set to verify the accuracy of the surrogate model. The accuracy evaluation of the response surface model is shown in Table 1. The fitting accuracy of each output parameter meets the requirements.

[0021] Table 1 S6: NSGA-II performs multi-objective optimization. 2000 iterations are performed using NSGA-II based on the proxy model described in step S5, and it is found that NSGA-II has good convergence. and weight Different weight coefficients, 9 combinations with different weight coefficients are selected for optimization to obtain a Pareto optimal solution set that meets the constraint requirements of step S1; S7: Verify the optimization results. Verify the Pareto optimal solution set obtained in step S6.

[0022] According to the 9 combined size data in step S6, the corresponding numerical model is established for simulation calculation, and the numerical simulation results are compared with the optimization results to evaluate the relative error of the optimization model. The error results of the 9 combinations are as follows: Figure 3 As shown in the figure, the errors of all parameters are within the acceptable range, indicating that the optimization results are accurate.

[0023] Based on the 9 combinations in step S6, taking into account the use requirements of the buoy unit for living, the maximum value and characteristic value of the heave motion acceleration of the floating body optimization results under each weight combination are calculated, and the cost, multi-objective optimization results and errors are comprehensively considered to obtain the optimal value. and When the values ​​are 0.4 and 0.6 respectively, the error of each output parameter is relatively small and within a reasonable range. This model is selected as the optimization design model. The comparison of the results before and after optimization is shown in Table 2.

[0024] Table 2 A single-objective global optimization algorithm is used for hierarchical optimization. Based on the optimal design selected above, the heave motion response is used as the optimization constraint without changing other optimization constraints.

[0025] The single-objective optimization mathematical model is shown in (8): (8) in, a is the maximum absolute value of the heave acceleration.

[0026] The results of the global optimization algorithm are in good correspondence with those obtained by NSGA-II. The difference in the optimized weight results is 0.8%, and the differences of the five input parameters are within the acceptable range. The comparison results of different optimization algorithms are shown in Table 3.

[0027] Table 3 Embodiment 3: The embodiment of the present invention further provides a device for optimizing the size of a semi-submersible marine floating platform, comprising: A first processing module is used to obtain a preliminary floating platform size plan; The second processing module is used to generate a plurality of sample points with different geometric design variable values ​​corresponding to different size shapes to form a sample space based on optimal Latin hypercube sampling according to the preliminary floating platform size plan; The third processing module is used to obtain the target variable and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition according to the sample space, and divide the data into a training set and a test set; A fourth processing module is used to establish a proxy model using a polynomial response surface method according to the training set, wherein the proxy model is used to fit the functional relationship between the optimization objective, the constraint variables and the design variables, and the accuracy of the proxy model is verified by using a test set; The fifth processing module is used to assign different weights to each optimization target according to the agent model, and then use the non-dominated sorting genetic algorithm to perform multiple iterations to obtain the Pareto optimal solution set of the design variables; The sixth processing module is used to compare the Pareto optimal solution set of the design variables with the corresponding simulation calculation results, conduct difference evaluation, and select the optimal size according to the requirements and error results; at the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

[0028] Embodiment 4: An embodiment of the present invention further provides a storage medium having a computer program stored thereon, and the computer program executes a method for optimizing the size of a semi-submersible ocean floating platform when the computer program is run.

[0029] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for optimizing the size of a semi-submersible marine floating platform, characterized in that: include: Obtain preliminary floating platform size plan; According to the preliminary floating platform size plan, based on the optimal Latin hypercube sampling, multiple sample points with different geometric design variable values ​​corresponding to different size shapes are generated to form a sample space; According to the sample space, the objective variable and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition are obtained, and the data are divided into a training set and a test set; Based on the training set, a surrogate model is established using the polynomial response surface method, wherein the surrogate model is used to fit the functional relationship between the optimization objective, the constraint variables and the design variables, and the accuracy of the surrogate model is verified using the test set; According to the agent model, different weights are assigned to each optimization objective, and the non-dominated sorting genetic algorithm is used to perform multiple iterations to obtain the Pareto optimal solution set of the design variables. The Pareto optimal solution set of the design variables is compared with the corresponding simulation calculation results to conduct a difference assessment, and the optimal size is selected according to the requirements and error results. At the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

2. A device for optimizing the size of a semi-submersible marine floating platform, characterized in that: include: A first processing module is used to obtain a preliminary floating platform size plan; The second processing module is used to generate a plurality of sample points with different geometric design variable values ​​corresponding to different size shapes to form a sample space based on optimal Latin hypercube sampling according to the preliminary floating platform size plan; The third processing module is used to obtain the target variable and constraint variable values ​​of the floating platform size optimization corresponding to each sample point under the control condition according to the sample space, and divide the data into a training set and a test set; A fourth processing module is used to establish a proxy model using a polynomial response surface method according to the training set, wherein the proxy model is used to fit the functional relationship between the optimization objective, the constraint variables and the design variables, and the accuracy of the proxy model is verified by using a test set; The fifth processing module is used to assign different weights to each optimization target according to the agent model, and use the non-dominated sorting genetic algorithm to perform multiple iterative calculations to obtain the Pareto optimal solution set of the design variables; The sixth processing module is used to compare the Pareto optimal solution set of the design variables with the corresponding simulation calculation results, conduct difference evaluation, and select the optimal size according to the requirements and error results; at the same time, according to the optimal design, one of the optimization objectives of the multi-objective optimization is set as the optimization constraint, and a single-objective global optimization algorithm is used for hierarchical optimization to verify the accuracy and precision of the multi-objective optimization results.

3. A storage medium, characterized in that: The storage medium stores a computer program, which executes the method for optimizing the size of a semi-submersible ocean floating platform as claimed in claim 1 when running.

Images