Method for optimizing self-righting structure of inflatable rescue boat based on RSM-GA

Abstract

The invention discloses an inflatable rescue boat self-righting structure optimization method based on RSM-GA, and belongs to the technical field of ship engineering and optimization design, and the method comprises the steps: S1, employing computer aided design software to establish an inflatable rescue boat three-dimensional model, employing simulation software to carry out static stability analysis, and obtaining a three-dimensional model of the inflatable rescue boat; s2, establishing a second-order polynomial regression model of the self-righting capability and design parameters of the inflatable rescue boat by using a response surface method, quantifying interaction of the parameters, and determining an optimization target, and S3, performing multi-target optimization on the second-order polynomial regression model by combining a genetic algorithm, and obtaining optimal design parameters of a self-righting structure when engineering constraint conditions are met at the same time; according to the method for optimizing the self-righting structure of the inflatable rescue boat based on the RSM-GA, the stability and the safety of the rescue boat can be guaranteed, meanwhile, the sailing resistance is effectively reduced, the sailing efficiency is improved, and the self-righting capacity and the sailing performance of the rescue boat are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship engineering and optimization design, and in particular to a self-righting structure optimization method of an inflatable rescue boat based on RSM-GA. Background Art

[0002] Against the backdrop of global climate change, extreme weather events are occurring frequently, and floods pose a serious threat to human life and property. Rescue boats, as core equipment in water rescue missions, directly determine rescue efficiency and safety through their performance. However, traditional rescue boats have numerous shortcomings in complex water environments, particularly in terms of self-righting capability and navigation stability. Once capsized, the rescue boat needs to be able to quickly recover to an upright position to ensure the safety of personnel and continue the rescue mission. However, existing rescue boat designs often struggle to strike a balance between self-righting performance and navigation resistance, especially under variable load and sea conditions.

[0003] Existing research has largely focused on theoretical analysis and preliminary simulations, lacking systematic investigation of multi-objective optimization under actual operating conditions. For example, the optimal design of a self-righting structure requires not only improving the righting arm but also considering increased navigational resistance to ensure the maneuverability and responsiveness of the rescue boat in complex waters. However, traditional methods often struggle to strike a balance between these two considerations, resulting in limitations in the practical application of design results. In recent years, with the advancement of computing technology, advanced optimization techniques such as response surface methodology (RSM) and genetic algorithms (GA) have been widely used in engineering design. Response surface methodology can effectively construct mathematical models between design parameters and performance indicators, quantify the interactions between various parameters, and provide a theoretical basis for the optimization of complex systems. Genetic algorithms, with their powerful global search capabilities and efficient optimization performance, are widely used in multi-objective optimization problems. However, the combined application of these two methods to the optimization design of a rescue boat's self-righting structure has not yet been reported.

[0004] Therefore, the present invention proposes an optimization design method for the self-righting structure of a rescue boat based on response surface methodology and genetic algorithm, aiming to significantly improve the self-righting performance and navigation stability of the rescue boat through multi-objective optimization design, while reducing navigation resistance to meet the needs of rescue missions in complex waters. Summary of the Invention

[0005] The purpose of the present invention is to provide a self-righting structure optimization method for an inflatable rescue boat based on RSM-GA to solve the problems mentioned in the above background technology.

[0006] To achieve the above objectives, the present invention provides an RSM-GA-based self-righting structure optimization method for an inflatable rescue boat, comprising the following steps:

[0007] S1. Use computer-aided design software to build a three-dimensional model of the inflatable rescue boat and use simulation software to perform static stability analysis;

[0008] S2. Using the response surface methodology (RSM), a second-order polynomial regression model of the self-righting ability of the inflatable rescue boat and its design parameters was established to quantify the interaction between the parameters and determine the optimization target.

[0009] S3. Combining a genetic algorithm (GA) to perform multi-objective optimization on the second-order polynomial model while satisfying engineering constraints, and obtaining optimal design parameters of the self-righting structure.

[0010] Preferably, the specific steps of S1 are as follows:

[0011] S11. Select a rescue boat with a rear airbag as the research object, simplify the self-righting structure, define the size parameters of the float and its position parameters relative to the hull, model the float of the self-righting structure using computer-aided software, generate a three-dimensional model file that conforms to a universal format, and establish a three-dimensional model of the inflatable rescue boat and the self-righting structure;

[0012] S12, importing the three-dimensional model into a static stability analysis module of ship simulation software, performing static stability analysis on the rescue boat, and obtaining righting arm data under different tilt angles and different design parameters;

[0013] S13. Output static stability analysis results.

[0014] Preferably, the size parameters in S11 include the airbag width D and the airbag cross-sectional radius R, and the position parameters include the floating body installation height H and the distance L between the floating body and the stern.

[0015] Preferably, the specific steps of S2 are as follows:

[0016] S21. Based on the results of the static stability analysis, a quadratic polynomial regression model is established using the response surface methodology to represent the relationship between the righting arm GZ and the heel angle θ, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L between the float and the stern.

[0017] S22. Draw a response surface diagram of the influence of each design parameter on the righting arm data. Use the response surface diagram combined with variance analysis to evaluate the influence trend of each design variable on the righting arm of the inflatable rescue boat, determine the key optimization variables, and set the optimization target.

[0018] Preferably, the quadratic polynomial regression model in S21 is in the following form:

[0019]

[0020] Among them, β0 is a constant term, β1, β2, β3, β4, β5 are the linear regression coefficients of each single variable, β 11 , β 22 , β 33 , β 44 , β 55 is the quadratic regression coefficient, β 12 , β 13 , β 14 , β 15 , β 23 , β 24 , β 25 , β 34 , β 35 , β 45 is the interaction regression coefficient, X i is the independent variable, X1 is the heel angle, X2 is the width of the airbag, X3 is the cross-sectional radius of the airbag, X4 is the height of the float, X5 is the distance between the float and the stern, ε is the error term, is the variance;

[0021] In order to enhance the fitting ability of the heel angle θ, the sine terms sin(θ) and sin(θ) are additionally introduced into the above regression model. 2 (θ), the regression equation can be expressed as:

[0022]

[0023] Among them, β 21 and β 22 are the regression coefficients of the sine terms, respectively.

[0024] Preferably, the optimization goal set in S22 is to minimize the integral value of the static stability curve in the range of 90° to 180°, and the righting arm is always greater than 0 in the full heel angle range.

[0025] Preferably, the specific steps of S3 are as follows:

[0026] S31. Set genetic parameters, define population size, crossover probability, mutation probability and maximum number of iterations;

[0027] S32. Perform individual coding, discretize the design parameters of the self-righting structure, namely, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L between the float and the stern, and use real number coding to represent the individuals, each of which contains four key design variables;

[0028] S33, setting a fitness function, taking the optimization target of the restoring arm in S22 as the fitness function, and calculating the individual fitness value;

[0029] S34. Perform genetic algorithm operation to optimize the fitness function and determine the optimal design parameters of the self-righting structure.

[0030] Preferably, the fitness function in S33 is to minimize the integral value of the static stability curve in the range of θ=90° to 180°:

[0031]

[0032] Here, θ is the tilt angle.

[0033] Preferably, the specific operation of the genetic algorithm in S34 is:

[0034] S341, initialize the population, generate an initial population that meets the engineering constraints, and calculate the fitness value corresponding to each individual according to the fitness function;

[0035] S342, performing a selection operation based on the fitness value, selecting a parent individual from the current population for reproduction;

[0036] S343, perform a crossover operation on the selected parent individuals to produce new offspring individuals to increase the diversity of the population and speed up the convergence;

[0037] S344, performing mutation operations on offspring individuals according to the set mutation probability to increase the search aperture and avoid local optimality;

[0038] S345, performing iterative update, repeatedly performing selection, crossover, and mutation operations until the maximum number of iterations is reached or the fitness function converges;

[0039] S346. Output the optimal solution to obtain the individual with the best fitness value, and use the self-righting structure design parameters corresponding to the individual as the final optimization result to ensure the improvement of the self-righting capability of the inflatable rescue boat and optimize the route stability.

[0040] Therefore, the present invention adopts the above-mentioned RSM-GA-based inflatable rescue boat self-righting structure optimization method, which has the following beneficial effects:

[0041] (1) By combining the response surface methodology with the genetic algorithm, the self-righting performance of the inflatable rescue boat can be significantly improved under complex conditions of multi-parameter coupling, while effectively reducing navigation resistance and improving rescue efficiency. Moreover, the introduction of the genetic algorithm ensures the global nature of the optimization process and avoids the design limitations caused by local optimal solutions in traditional methods.

[0042] (2) The actual engineering constraints are fully considered, and the optimization results have high engineering application value. They can be directly applied to the design and improvement of rescue boats, and can clearly demonstrate the optimization effect, providing a scientific basis and practical guidance for the design of rescue boats.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a method for optimizing the self-righting structure of an inflatable rescue boat based on RSM-GA of the present invention;

[0045] Figure 2 This is a flow chart of step S1 of a method for optimizing the self-righting structure of an inflatable rescue boat based on RSM-GA of the present invention;

[0046] Figure 3 A side view of a three-dimensional model of an inflatable rescue boat according to an RSM-GA-based self-righting structure optimization method for an inflatable rescue boat of the present invention;

[0047] Figure 4 This is a front view of a three-dimensional model of an inflatable rescue boat according to an RSM-GA-based self-righting structure optimization method for an inflatable rescue boat of the present invention;

[0048] Figure 5 A top view of the three-dimensional model of an inflatable rescue boat based on RSM-GA.

[0049] Figure 6 This is a flow chart of step S2 of a method for optimizing the self-righting structure of an inflatable rescue boat based on RSM-GA of the present invention;

[0050] Figure 7 This is a response surface diagram of the interaction between the ratio of the airbag cross-sectional radius R and the distance L between the float and the stern of an inflatable rescue boat self-righting structure optimization method based on RSM-GA of the present invention;

[0051] Figure 8 This is a flow chart of step S3 of a method for optimizing the self-righting structure of an inflatable rescue boat based on RSM-GA of the present invention. DETAILED DESCRIPTION

[0052] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort shall fall within the scope of protection of the present invention.

[0053] Example

[0054] like Figure 1 As shown, the present invention provides an optimization method for the self-righting structure of an inflatable rescue boat based on RSM-GA, comprising the following steps:

[0055] like Figure 2 As shown in S1, a three-dimensional model of an inflatable rescue boat is established using computer-aided design software, and static stability analysis is performed using simulation software.

[0056] S11. Select the rescue boat with rear airbag as the research object, simplify the self-righting structure, define the size parameters of the float and the position parameters relative to the hull, model the float of the self-righting structure using computer-aided software, generate a three-dimensional model file that conforms to the universal format, and establish a three-dimensional model of the inflatable rescue boat and the self-righting structure. The size parameters include the width D and the cross-sectional radius R of the airbag, and the position parameters include the installation height H of the float and the distance L between the float and the stern. The constructed three-dimensional model is as follows: Figure 3-Figure 5 shown.

[0057] The main design parameters of the inflatable rescue boat in this embodiment are: boat length 4.282 meters, boat width 2.228 meters, and boat depth 0.675 meters. The self-righting structure float is modeled using SolidWorks software, and a three-dimensional model file in .igs format is generated. Subsequently, the .igs file is imported into the MaxsurfModeler module to complete the establishment of the overall model of the inflatable rescue boat.

[0058] S12, importing the three-dimensional model into a static stability analysis module of ship simulation software, performing static stability analysis on the rescue boat, and obtaining righting arm data under different tilt angles and different design parameters;

[0059] S13. Output static stability analysis results.

[0060] like Figure 6 As shown in S2, a second-order polynomial regression model of the self-righting ability of the inflatable rescue boat and the design parameters is established using the response surface methodology (RSM) to quantify the interaction of each parameter and determine the optimization target.

[0061] S21. Based on the results of the static stability analysis, a quadratic polynomial regression model was established using the response surface methodology between the righting lever GZ and the heel angle θ, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L from the float to the stern. The heel angle θ, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L from the float to the stern were used as independent variables, and the righting lever GZ was used as the dependent variable.

[0062] The quadratic polynomial regression model has the following form:

[0063]

[0064] Among them, β0 is a constant term, β1, β2, β3, β4, β5 are the linear regression coefficients of each single variable, β 11 , β 22 , β33 , β 44 , β 55 is the quadratic regression coefficient, β 12 , β 13 , β 14 , β 15 , β 23 , β 24 , β 25 , β 34 , β 35 , β 45 is the interaction regression coefficient, X i is the independent variable, X1 is the heel angle, X2 is the width of the airbag, X3 is the cross-sectional radius of the airbag, X4 is the height of the float, X5 is the distance between the float and the stern, ε is the error term, The experimental data are fitted by the least square method to obtain the regression relationship between the righting arm GZ and each design parameter.

[0065] In order to enhance the fitting ability of the heel angle θ, the sine terms sin(θ) and sin(θ) are additionally introduced into the above regression model. 2 (θ), the regression equation can be expressed as:

[0066]

[0067] Among them, β 21 and β 22 are the regression coefficients of the sine terms, respectively.

[0068] S22. Based on the regression model, draw a response surface diagram of the influence of each design parameter on the righting arm data, and establish an evaluation index for evaluating the performance of the self-righting structure, such as Figure 7 As shown in the figure, the influence trend of each design variable on the righting arm of the inflatable rescue boat was evaluated by response surface plot combined with analysis of variance (ANOVA), the key optimization variables were determined, and the optimization target was set. The optimization target was to minimize the integral value of the static stability curve in the range of 90° to 180°, and ensure that the righting arm was always greater than 0 in the full heel angle range to ensure the self-righting ability of the inflatable rescue boat.

[0069] like Figure 8 As shown in S3, a genetic algorithm (GA) is combined to perform multi-objective optimization on the second-order polynomial model while satisfying engineering constraints to obtain the optimal design parameters of the self-righting structure.

[0070] S31. Set genetic parameters, define population size, crossover probability, mutation probability and maximum number of iterations;

[0071] S32. Perform individual coding, discretize the design parameters of the self-righting structure, namely, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L between the float and the stern, and use real number coding to represent the individuals, each of which contains four key design variables;

[0072] S33, setting a fitness function, taking the optimization target of the restoring arm in S22 as the fitness function, and calculating the individual fitness value;

[0073] The fitness function is to minimize the integral value of the static stability curve in the range of θ = 90° to 180° and ensure that the righting arm is always greater than 0:

[0074]

[0075] Here, θ is the tilt angle.

[0076] S34. Perform genetic algorithm operation to optimize the fitness function and determine the optimal design parameters of the self-righting structure.

[0077] S341. Initialize the population, use the Latin Hypercube Sampling (LHS) method to generate an initial population that meets the engineering constraints, and calculate the fitness value corresponding to each individual according to the fitness function;

[0078] S342, performing a selection operation based on the fitness value, using a roulette wheel selection method to select a parent individual from the current population for reproduction;

[0079] S343, performing a crossover operation on the selected parent individuals, using a simulated binary crossover (SBX) method to produce new offspring individuals to increase the diversity of the population and accelerate the convergence speed;

[0080] S344, performing mutation operations on offspring individuals according to the set mutation probability, using the Gaussian mutation method to increase the search aperture and avoid local optimality;

[0081] S345, performing iterative update, repeatedly performing selection, crossover, and mutation operations until the maximum number of iterations is reached or the fitness function converges;

[0082] S346. Output the optimal solution to obtain the individual with the best fitness value, and use the self-righting structure design parameters corresponding to the individual as the final optimization result to ensure the improvement of the self-righting capability of the inflatable rescue boat and optimize the route stability.

[0083] Therefore, the present invention adopts the above-mentioned RSM-GA-based inflatable rescue boat self-righting structure optimization method, which can effectively reduce navigation resistance, improve navigation efficiency, and significantly improve the self-righting ability and navigation performance of the rescue boat while ensuring the stability and safety of the rescue boat.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A self-righting structure optimization method for an inflatable rescue boat based on RSM-GA, characterized in that: The following steps are involved: S1. Use computer-aided design software to build a three-dimensional model of the inflatable rescue boat and use simulation software to perform static stability analysis; S2. Use response surface methodology to establish a second-order polynomial regression model between the self-righting ability of the inflatable rescue boat and its design parameters, quantify the interaction between the parameters, and determine the optimization target; S3. Combining a genetic algorithm to perform multi-objective optimization on the second-order polynomial model while satisfying engineering constraints, thereby obtaining optimal design parameters of the self-righting structure.

2. The RSM-GA-based self-righting structure optimization method for an inflatable rescue boat according to claim 1, characterized in that: The specific steps of S1 are as follows: S11. Select a rescue boat with a rear airbag as the research object, simplify the self-righting structure, define the size parameters of the float and its position parameters relative to the hull, model the float of the self-righting structure using computer-aided software, generate a three-dimensional model file that conforms to a universal format, and establish a three-dimensional model of the inflatable rescue boat and the self-righting structure; S12, importing the three-dimensional model into a static stability analysis module of ship simulation software, performing static stability analysis on the rescue boat, and obtaining righting arm data under different tilt angles and different design parameters; S13. Output static stability analysis results.

3. The RSM-GA-based self-righting structure optimization method for an inflatable rescue boat according to claim 2, characterized in that: The size parameters in S11 include the airbag width D and the airbag cross-sectional radius R, and the position parameters include the floating body installation height H and the distance L between the floating body and the stern.

4. The RSM-GA-based self-righting structure optimization method for an inflatable rescue boat according to claim 1, characterized in that: The specific steps of S2 are as follows: S21. Based on the results of the static stability analysis, a quadratic polynomial regression model is established using the response surface methodology to represent the relationship between the righting arm GZ and the heel angle θ, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L between the float and the stern. S22. Draw a response surface diagram of the influence of each design parameter on the righting arm data. Use the response surface diagram combined with variance analysis to evaluate the influence trend of each design variable on the righting arm of the inflatable rescue boat, determine the key optimization variables, and set the optimization target.

5. The RSM-GA-based self-righting structure optimization method for an inflatable rescue boat according to claim 4, characterized in that: The quadratic polynomial regression model in S21 is as follows: Among them, β0 is a constant term, β1, β2, β3, β4, β5 are the linear regression coefficients of each single variable, β 11 , β 22 , β 33 , β 44 , β 55 is the quadratic regression coefficient, β 12 , β 13 , β 14 , β 15 , β 23 , β 24 , β 25 , β 34 , β 35 , β 45 is the interaction regression coefficient, X i is the independent variable, X1 is the heel angle, X2 is the width of the airbag, X3 is the cross-sectional radius of the airbag, X4 is the height of the float, X5 is the distance between the float and the stern, ε is the error term, is the variance; In order to enhance the fitting ability of the heel angle θ, the sine terms sin(θ) and sin(θ) are additionally introduced into the above regression model. 2 (θ), the regression equation can be expressed as: Among them, β 21 and β 22 are the regression coefficients of the sine terms, respectively.

6. The RSM-GA-based self-righting structure optimization method for an inflatable rescue boat according to claim 4, characterized in that: The optimization objective set in S22 is to minimize the integral value of the static stability curve in the range of 90° to 180°, and the righting arm is always greater than 0 in the full heel angle range.

7. The RSM-GA based self-righting structure optimization method for an inflatable rescue boat according to claim 1, characterized in that: The specific steps for S3 are as follows: S31. Set genetic parameters, define population size, crossover probability, mutation probability and maximum number of iterations; S32. Perform individual coding, discretize the design parameters of the self-righting structure, namely, the airbag width D, the airbag cross-sectional radius R, the float height H, and the distance L between the float and the stern, and use real number coding to represent the individuals, each of which contains four key design variables; S33, setting a fitness function, taking the optimization target of the restoring arm in S22 as the fitness function, and calculating the individual fitness value; S34. Perform genetic algorithm operation to optimize the fitness function and determine the optimal design parameters of the self-righting structure.

8. The RSM-GA based self-righting structure optimization method for an inflatable rescue boat according to claim 7, characterized in that: The fitness function in S33 is to minimize the integral value of the static stability curve in the range of θ = 90° to 180°: Here, θ is the tilt angle.

9. The RSM-GA based self-righting structure optimization method for an inflatable rescue boat according to claim 7, characterized in that: The specific operations of the genetic algorithm in S34 are: S341, initialize the population, generate an initial population that meets the engineering constraints, and calculate the fitness value corresponding to each individual according to the fitness function; S342, performing a selection operation based on the fitness value, selecting a parent individual from the current population for reproduction; S343, perform a crossover operation on the selected parent individuals to produce new offspring individuals; S344, performing mutation operation on offspring individuals according to the set mutation probability; S345, performing iterative update, repeatedly performing selection, crossover, and mutation operations until the maximum number of iterations is reached or the fitness function converges; S346. Output the optimal solution, obtain the individual with the optimal fitness value, and use the self-righting structure design parameters corresponding to the individual as the final optimization result.

Images