Offshore wind power jacket structure optimization method based on collider optimization algorithm
By grouping and optimizing the components of the offshore jacket structure using a collision body optimization algorithm, the problems of excessive weight and insufficient material utilization of the jacket structure in deep-sea environments were solved, achieving lightweighting and improved economy of the jacket structure.
Patent Information
- Application Number
- CN202511586030.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-31
- Publication Date
- 2026-02-10
AI Technical Summary
Existing offshore jacket structure designs suffer from insufficient material utilization and excessive structural weight in complex deep-sea environments, making it difficult to balance safety and economy. Traditional methods lack global search capabilities and are prone to getting trapped in local optima.
A collision-based optimization algorithm is used to group the jacket structure members. The overall weight is minimized as the optimization objective. Iterative updates are performed by combining an external penalty function, individual collision updates, elite memory retention, and random dimension regeneration mechanism to optimize the outer diameter and wall thickness of the members in order to achieve global search and local convergence.
The design achieves lightweighting of the jacket structure, reducing the total weight by 8.5%, while meeting the requirements for member strength, stability, and displacement constraints, thus improving material utilization efficiency and design economy.
Smart Images
Figure CN121502939A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of offshore jacket structure optimization technology, and in particular to an offshore wind power jacket structure optimization method based on a collision body optimization algorithm. Background Technology
[0002] With the continuous advancement of deep-sea resource development and offshore engineering construction, the safety and economy of jacket structures, as a widely used type of offshore foundation structure, are receiving increasing attention. In complex sea conditions, jacket structures not only need to withstand multiple environmental loads such as wind, waves, and currents, but also must meet requirements for strength, stability, and durability during long-term service. Traditional jacket structure design typically relies on empirical formulas and iterative scheme selection. While this can meet basic design requirements, it falls short in terms of material utilization and overall lightweighting, often leading to structural redundancy and increased construction costs.
[0003] In the complex environment of deep-sea areas, the optimized design of jacket foundations not only needs to ensure structural safety and compliance with regulations, but also needs to strike a balance between material usage, construction economy, and service life. By introducing intelligent optimization algorithms, the grouped dimensions of jacket members can be systematically optimized under multiple constraints such as strength, buckling, nodal bearing capacity, and overall deformation. This significantly reduces structural weight, improves material utilization efficiency, and enhances the overall design's economy and sustainability. Currently, optimization research on offshore jacket structures still largely focuses on traditional algorithms or empirical methods, lacking systematic research combining novel intelligent optimization methods for deep-sea environments.
[0004] Therefore, this invention proposes a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, aiming to improve the current situation where existing jacket structure designs suffer from excessive structural weight and insufficient material utilization, making it difficult to meet safety requirements in complex deep-sea environments. Summary of the Invention
[0005] In view of this, the present invention proposes an optimization method for offshore wind power jacket structures based on a collision body optimization algorithm, which involves grouping different types of rods, minimizing the total weight of the jacket as the optimization objective, configuring constraints, generating an initial population of a certain size based on the upper and lower limits of the design variables, and updating the population to obtain the optimal jacket structure that meets the requirements of engineering performance and economy.
[0006] On the one hand, the present invention provides a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, comprising the following steps: S1: Group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables; S2: With minimizing the overall weight of the offshore wind turbine jacket as the optimization objective, constraints are introduced for the members; S3: Generate an initial population within the given design variable range, calculate the fitness value of each individual based on the external penalty function, and sort the individuals according to their fitness. S4: Using the collision body optimization algorithm, the initial population is iteratively updated by employing an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient, so as to achieve global search and local convergence of the solution space until the termination condition is met. S5: Output the optimal design scheme for offshore wind turbine jacket structure that meets the requirements.
[0007] Based on the above technical solutions, preferably, step S1 involves inputting the basic design data of the jacket structure and dividing the members into sections according to their structural characteristics. n Group, No. i The outer diameter of the rods in each group D i and wall thickness t i As a design variable, i =1, 2, ..., n Then, the design variables are digitally encoded to form the design vectors of individual populations. X , X =[ D 1, t 1, D 2, t 2, ..., D n , t n ].
[0008] Preferably, step S2 involves setting the optimization objective as minimizing the overall weight of the offshore wind turbine jacket: setting the following constraints: member strength and stability constraints; local buckling and slenderness ratio constraints; node bearing capacity constraints; and overall displacement constraints.
[0009] Further preferably, step S3, which involves generating an initial population within a given range of design variables and calculating the fitness value for each individual based on the external penalty function method, serves as the population initialization mechanism, given the population size. N Maximum number of iterations iter max The number of constraints is m , j =1, 2, ..., m Given a coefficient of recovery, the first iter Individual representation , s =1, 2, ...,N ; d The fitness function is calculated based on the overall weight of the offshore wind turbine jacket, the weighting coefficient of the constraint category, the normalized violation amount of the constraint, and the penalty index of the constraint category.
[0010] Further preferably, the individual collision update mechanism described in step S4 includes the following: according to the... iter The historical optimal solution, combined with the first iter Substitute the individual and the perturbation factor, and iteratively obtain the first... iter+ Individuals of the first generation.
[0011] Furthermore, the elite memory retention mechanism described in step S4 includes the following: using an elite memory mechanism to save historical optimal solutions and constructing an elite set. E According to the iter The set of historical optimal solutions, the first iter The front in the elite solution set k The individual obtains the first iter+ An elite collection of individuals from the first generation.
[0012] Further preferably, the random dimension regeneration mechanism described in step S4 includes the following: To avoid getting trapped in local optima, some dimensions of some individuals are randomly selected for regeneration during the iteration process. The regenerated individuals include global regeneration and targeted regeneration. Global regeneration adds a random offset to the minimum value of the search space, thereby randomly generating a new individual; targeted regeneration projects the guiding value onto a specified set according to the mapping operator. .
[0013] A further preferred embodiment of the decay strategy for the recovery coefficient in step S4 includes the following: configuring a segmented iteration threshold for the recovery coefficient, and dynamically adjusting the recovery coefficient based on the relationship between the current iteration number and the segmented iteration threshold.
[0014] On the other hand, the present invention provides an offshore wind turbine jacket structure optimization system based on a collision body optimization algorithm, used to implement the method, comprising: The member grouping unit is used to group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables to form a population of individuals; The target generation unit is optimized based on minimizing the overall weight of the offshore wind turbine jacket, and constraints on the members are introduced. The population generation and historical best solution selection unit is used to generate an initial population within the range of design variables, calculate the fitness value of each individual in the initial population, sort the individuals in the population according to their fitness values, and select the individual with the highest fitness value as the historical best solution. The population iterative update unit uses a collision body optimization algorithm and employs an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient to iteratively update the initial population, achieving global search and local convergence of the solution space until the termination condition is met; it outputs an optimal design scheme for the offshore wind turbine jacket structure that meets the requirements.
[0015] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer program, wherein when the calculator program stored on the storage medium is executed by a processor, it implements the above-described method.
[0016] The present invention provides a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, which has the following advantages compared with the prior art: (1) This method takes minimizing the overall weight of the jacket as the objective and fully considers the key engineering constraints of the offshore wind turbine jacket, including member strength / stability, local buckling / slenderness ratio, node bearing capacity and overall displacement, to ensure that the optimization results are feasible and safe in engineering. The optimal structural scheme of the jacket that meets the requirements of strength, stability and displacement can be obtained through the iteration of the collision body optimization algorithm. (2) When calculating fitness, the enhanced external penalty function method is adopted to unify the scale of constraint violations of different physical dimensions and different orders of magnitude, so that the calculation of penalty terms is more reasonable; different types of constraint conditions are assigned different initial penalty weights, and the penalty weight of constraint violations will increase with the increase of the number of iterations. (3) The initial population is iteratively updated by adopting an individual collision update mechanism, an elite memory retention mechanism, a random dimension rebirth mechanism, and a decay strategy of the recovery coefficient. The rebirth probability of the random dimension rebirth mechanism is based on the comprehensive contribution of the design variables. The elite memory retention mechanism can prevent the loss of high-quality historical solutions and can continuously affect the update direction of the subsequent population. The decay strategy of the recovery coefficient makes the recovery coefficient gradually decrease according to the iteration progress. The larger recovery coefficient in the early stage of iteration gives the algorithm a stronger global search capability. In the later stage of iteration, the recovery coefficient gradually decreases, making the search process more focused on local convergence, thereby achieving a balance between global and local. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1This is a flowchart of a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, according to the present invention. Figure 2 This is a schematic diagram of the structure of an offshore wind turbine jacket structure according to the present invention, which is a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm. Figure 3 This is a schematic diagram of the iterative results of an optimization method for offshore wind turbine jacket structures based on a collision body optimization algorithm according to the present invention. Detailed Implementation
[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0020] Optimization research on offshore jacket structures still largely focuses on traditional algorithms or empirical methods, lacking systematic research combining novel intelligent optimization methods for deep-sea environments. Traditional methods lack global search capabilities and often easily lead to getting trapped in local optima. Therefore, on the one hand, such as... Figure 1 As shown, this invention provides a method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, comprising the following steps: S1: Group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables.
[0021] Step S1 involves inputting the basic design data of the jacket structure and dividing the members into sections according to their structural characteristics. n Group, No. i The outer diameter of the rods in each group D i and wall thickness t i As a design variable, i =1, 2, ..., n Then, the design variables are digitally encoded to form the design vectors of individual populations. X , X =[ D 1, t 1, D 2, t 2, ..., D n , t n ].
[0022] like Figure 2As shown, in one embodiment, it is assumed that the members of the offshore wind turbine jacket are divided into 6 groups, with the first group being the main legs and the remaining groups being the diagonal braces and the top small members. i The outer diameter of the rods in each group D i and wall thickness t i The range of values for are respectively , formula 1; D i 0 and t i 0 represents the initial design outer diameter and initial design wall thickness, respectively. The input environmental loads include time-history curves of wave force, current force, and wind load under a 50-year return period design wind, wave, and current condition. Material parameters include the elastic modulus of steel. E =2.06×10 5 MPa, yield strength F y =355 MPa.
[0023] S2: With minimizing the overall weight of the offshore wind turbine jacket as the optimization objective, constraints are introduced for the members.
[0024] Let the optimization objective be: , formula 2; W This refers to the overall weight of the offshore wind turbine jacket. r For the density of steel, A i For the first i The cross-sectional area of the members in each group, L i For the first i The total length of the members in each group is calculated, and min() is used to calculate the minimum value. Based on the input environmental loads and in accordance with the API RP 2A standard recommended by the American Petroleum Institute, the design constraints are determined as follows: 1) Strength and stability constraints of members: , formula 3; P This is the design value for axial force. P a This is the design value for the axial bearing capacity of the member. M This is the design value for bending moment. M a This refers to the design value of the bending moment bearing capacity of the member; 2) Local buckling and slenderness ratio constraints: , formula 4; K To calculate the length coefficient, L For any member length, r Radius of gyration E The elastic modulus of steel, F y Yield strength; 3) Node Bearing Capacity Constraints: The intersection of a member with an adjacent offshore wind turbine jacket component is considered a node, including welded nodes and bolted connections. Regardless of whether the connection is rigid or hinged, all nodes must meet the bearing capacity requirements specified in the code. The stress on each node must not exceed its ultimate bearing capacity. , Formula 5; Q Design values for nodal shear or punching shear force. Q allow The ultimate bearing capacity of the node; 4) Overall displacement constraint: , Formula 6; This refers to the horizontal displacement of the top of the offshore wind turbine jacket. H This refers to the total height of the offshore wind turbine jacket.
[0025] S3: Generate an initial population within the given design variable range, calculate the fitness value of each individual based on the external penalty function, and sort the individuals according to their fitness.
[0026] The initial population is generated within the given design variables. The fitness value of each individual is calculated based on the external penalty function method. This is the population initialization mechanism, given the population size. N Maximum number of iterations iter max The number of constraints is m , j =1, 2, ..., m Given a coefficient of recovery , No. iter Individual representation , s =1, 2, ..., N , d To determine the number of design variables, D ∈ d .
[0027] fitness function The expression is: Formula 7; , formula 8; Formula 9; where g j For the first j The actual value of each constraint condition For the first j The allowable value of each constraint condition. s j For the first j The normalization scale for each constraint condition is selected in this embodiment. As a normalization metric; P cat(j) For the first jThe penalty index for the category to which each constraint belongs takes a value of 2; For the first j The weighted coefficients for the categories to which each constraint belongs. v j For the first j The normalized violation quantity of each constraint. βcat ( j ) is the first j The rate at which the penalty weight of each constraint category increases over time. For the first j The penalty weight of each constraint category relative to the initial value of the category weighting coefficient. The maximum growth multiple; The coefficient of recovery.
[0028] To simultaneously consider both the optimization objective and constraints during the optimization process, this scheme adopts the external penalty function method, with the fitness function employing hierarchical normalized adaptive penalty, linked to the recovery coefficient to dynamically adjust the constraint convergence strength; at the same time, a dual-criteria individual ranking rule prioritizing feasibility is introduced to improve the convergence efficiency of constraint satisfaction.
[0029] The fitness of each individual is calculated separately, and the individuals are ranked according to the results of the fitness function calculation. Specifically, finite element analysis and fitness evaluation are performed on each candidate individual. Each individual is input into the finite element model, and a shell-bar hybrid modeling method is used to calculate the stress, displacement, and buckling eigenvalues of each member. The calculation results are then substituted into the fitness function to obtain the corresponding fitness value, and the individuals are ranked.
[0030] S4: Using the collision body optimization algorithm, an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient are employed to iteratively update the initial population, achieving global search and local convergence of the solution space until the termination condition is met.
[0031] To enhance the optimization's global search and local convergence capabilities, this invention introduces an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient during the optimization iteration process.
[0032] 1) Individual collision update mechanism, including the following: Let the first... iter The formula for updating an individual in a generation is: , formula 10; For the first iter The historical optimal solution is the individual with the highest fitness in the population. The opponent is a randomly selected individual. As a disturbance factor, For the first iter+ Individuals of the first generation, rand ( ) is the function for generating random numbers; the individual collision update mechanism makes inferior solutions move closer to the historical best solution, and retains a certain amount of perturbation to avoid premature convergence of the population.
[0033] 2) Elite memory retention mechanism, including the following: using an elite memory mechanism to save historical optimal solutions and constructing an elite set. E , No. iter+ The elite collection of individuals from the first generation for , Formula 11; For the first iter The set of historically optimal solutions. Indicates the first iter The front in the elite solution set k For each individual, ∪ represents the union operation; the elite memory retention mechanism ensures that past high-quality solutions are not forgotten and can influence subsequent searches. In this embodiment, k The value is 10.
[0034] 3) Random dimension regeneration mechanism, including the following: To avoid getting trapped in local optima, during the iteration process, some dimensions of some individuals are randomly selected for regeneration, based on the comprehensive contribution of each design variable. C D Calculate the rebirth probability P s : , Formula 12; No. D The combined contribution of each design variable is , For the first D Finite-difference sensitivity of design variables to constraint violation degree For the first D The utilization increment of constraints directly related to each design variable. The weighting factor is used for the reborn individuals. , Formula 13; and These represent the maximum and minimum values of the search space, respectively. Global regeneration adds a random offset to the minimum value of the search space, thereby randomly generating a new individual; directed regeneration is based on the mapping operator. , will guide value Projection to set .
[0035] 4) The decay strategy for the coefficient of recovery, including the following: coefficient of recovery The dynamic adjustment formula is: Formula 14; where The initial value of the coefficient of restitution. This represents the minimum value of the coefficient of restitution. This is the starting value for the segment. and The first and second piecewise iteration thresholds for the recovery coefficients are both no more than the maximum number of iterations. iter max ; To trigger the rebound value when the system is stationary, and These are the first attenuation rate coefficient and the second attenuation rate coefficient.
[0036] In this embodiment, a maximum number of iterations is given. iter max The population size is 200. N =50, the initial value of the coefficient of restitution. The minimum value of the coefficient of restitution is 0. The initial value for the segment is 0.01. It is 0.3 First decay rate coefficient Second decay rate coefficient The values are 2 and 0.05, respectively.
[0037] The termination condition refers to reaching the maximum number of iterations. iter max Or it satisfies the fitness convergence criterion, i.e. or ,in The convergence threshold, and These represent the optimal fitness function value of the previous iteration and the optimal fitness function value of the current iteration, respectively.
[0038] S5: Output the optimal design scheme for offshore wind turbine jacket structure that meets the requirements.
[0039] Figure 3 The iterative process of the optimal design of the offshore wind turbine jacket structure is shown. The vertical axis represents the overall weight of the offshore wind turbine jacket in kN, and the horizontal axis represents the number of iterations. The optimized design of the offshore wind turbine jacket structure is shown in Table 1. Compared with the original design, the total self-weight of the jacket is reduced by about 8.5%, the strength and stability of the members meet the specifications, and the top displacement constraint is also satisfied.
[0040] Table 1 Comparison of main design parameters before and after optimization of offshore wind turbine jacket structure
[0041] On the other hand, the present invention also provides an optimization system for offshore wind turbine jacket structures based on a collision body optimization algorithm, comprising: The digital modeling and coding module is used to group and model the structural parameters of the jacket platform, digitally code the outer diameter and wall thickness of each group of members as design variables, and set optimization objectives and constraints to limit the range of design variables. The structural analysis and fitness calculation module is used to call the finite element analysis program to perform stress and displacement calculations on candidate design schemes, obtain the actual values of constraints such as member stress, overall stability, node bearing capacity and platform displacement, and calculate the fitness value based on the external penalty function method to reflect the degree to which the design scheme meets the optimization objectives and constraints. The collision body optimization algorithm iterative optimization module generates an initial population, ensuring that each individual represents a different jacket structure scheme. During the optimization iteration process, the population is updated based on the collision body optimization algorithm. This involves a collision update mechanism to move inferior solutions closer to superior solutions, an elite memory mechanism to retain historical best solutions, a random dimension regeneration mechanism to prevent the population from getting trapped in local optima, and a dynamic recovery coefficient to gradually transition from global exploration to local convergence until the set termination conditions are met. Ultimately, a lightweight jacket structure scheme that meets the requirements for strength, stability, and displacement is obtained.
[0042] The collision optimization algorithm's iterative optimization module employs a dynamic adjustment strategy during individual updates: in the early stages of iteration, the recovery coefficient is larger to enhance global search capabilities; in the later stages of iteration, the recovery coefficient gradually decreases to improve local convergence accuracy. Simultaneously, combined with a random dimension regeneration mechanism, some dimensions of some individuals are reassigned with a set probability in each iteration to increase population diversity and prevent premature convergence.
[0043] On the other hand, the present invention provides an offshore wind turbine jacket structure optimization system based on a collision body optimization algorithm, used to implement an offshore wind turbine jacket structure optimization method based on a collision body optimization algorithm, comprising: The member grouping unit is used to group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables to form a population of individuals; The target generation unit is optimized based on minimizing the overall weight of the offshore wind turbine jacket, and constraints on the members are introduced. The population generation and historical best solution selection unit is used to generate an initial population within the range of design variables, calculate the fitness value of each individual in the initial population, sort the individuals in the population according to their fitness values, and select the individual with the highest fitness value as the historical best solution. The population iterative update unit uses a collision body optimization algorithm and employs an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient to iteratively update the initial population, achieving global search and local convergence of the solution space until the termination condition is met; it outputs an optimal design scheme for the offshore wind turbine jacket structure that meets the requirements.
[0044] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer program, wherein when the computer program stored on the storage medium is executed by a processor, it implements the above-mentioned method for optimizing the offshore wind turbine jacket structure based on the collision body optimization algorithm.
[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm, characterized in that, Includes the following steps: S1: Group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables; S2: With minimizing the overall weight of the offshore wind turbine jacket as the optimization objective, constraints are introduced for the members; S3: Generate an initial population within the given design variable range, calculate the fitness value of each individual based on the external penalty function, and sort the individuals according to their fitness. S4: Using the collision body optimization algorithm, the initial population is iteratively updated by employing an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient, so as to achieve global search and local convergence of the solution space until the termination condition is met. S5: Output the optimal design scheme for offshore wind turbine jacket structure that meets the requirements.
2. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 1, characterized in that, Step S1 involves inputting the basic design data of the jacket structure and dividing the members into sections according to their structural characteristics. n Group, No. i The outer diameter of the rods in each group D i and wall thickness t i As a design variable, i =1, 2, ..., n ; Then, the design variables are digitally encoded to form design vectors for individual populations. X , X =[ D 1, t 1, D 2, t 2, ..., D n , t n ].
3. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 2, characterized in that, Step S2 involves setting the optimization objective as minimizing the overall weight of the offshore wind turbine jacket: the following constraints are set: member strength and stability constraints; local buckling and slenderness ratio constraints; nodal bearing capacity constraints; and overall displacement constraints.
4. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 3, characterized in that, Step S3, which involves generating an initial population within the given design variable range and calculating the fitness value of each individual based on the external penalty function method, is the population initialization mechanism, given the population size. N Maximum number of iterations iter max The number of constraints is m , j =1, 2, ..., m ; Given the coefficient of recovery, the first iter Individual representation , s =1, 2, ..., N ; d The fitness function is calculated based on the overall weight of the offshore wind turbine jacket, the weighting coefficient of the constraint category, the normalized violation amount of the constraint, and the penalty index of the constraint category.
5. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 4, characterized in that, The individual collision update mechanism described in step S4 includes the following: according to the... iter The historical optimal solution, combined with the first iter Substitute the individual and the perturbation factor, and iteratively obtain the first... iter+ Individuals of the first generation.
6. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 5, characterized in that, The elite memory retention mechanism described in step S4 includes the following: using an elite memory mechanism to save historical optimal solutions and constructing an elite set. E According to the iter The set of historical optimal solutions, the first iter The front in the elite solution set k The individual obtains the first iter+ An elite collection of individuals from the first generation.
7. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 4, characterized in that, The random dimension regeneration mechanism described in step S4 includes the following: In order to avoid getting trapped in local optima, some dimensions of some individuals are randomly selected for regeneration during the iteration process. The regenerated individuals include global regeneration and targeted regeneration. Global regeneration adds a random offset to the minimum value of the search space, thereby randomly generating a new individual. Targeted regeneration projects guided values onto a specified set based on mapping operators. .
8. The method for optimizing offshore wind turbine jacket structures based on a collision body optimization algorithm according to claim 4, characterized in that, The decay strategy for the recovery coefficient described in step S4 includes the following: configuring a segmented iteration threshold for the recovery coefficient, and dynamically adjusting the recovery coefficient based on the relationship between the current iteration number and the segmented iteration threshold.
9. A structural optimization system for offshore wind turbine jackets based on a collision body optimization algorithm, used to implement the method described in any one of claims 1-8, characterized in that, include: The member grouping unit is used to group the members of the offshore wind turbine jacket, and digitally encode the outer diameter and wall thickness of each grouped member as design variables to form a population of individuals; The target generation unit is optimized based on minimizing the overall weight of the offshore wind turbine jacket, and constraints on the members are introduced. The population generation and historical best solution selection unit is used to generate an initial population within the range of design variables, calculate the fitness value of each individual in the initial population, sort the individuals in the population according to their fitness values, and select the individual with the highest fitness value as the historical best solution. The population iterative update unit uses a collision body optimization algorithm and employs an individual collision update mechanism, an elite memory retention mechanism, a random dimension regeneration mechanism, and a decay strategy for the recovery coefficient to iteratively update the initial population, achieving global search and local convergence of the solution space until the termination condition is met; it outputs an optimal design scheme for the offshore wind turbine jacket structure that meets the requirements.
10. A computer-readable storage medium for storing a computer program, characterized in that, When the calculator program stored on the storage medium is executed by the processor, it implements the method as described in any one of claims 1-8.