基于GA算法对车家坝河重力坝优化设计

为提高大型水利工程结构计算的精度与速度,将GA算法应用于重力坝结构断面计算,并以车家坝河重力坝为研究对象,基于相关规范提出约束函数对目标函数(断面面积最小)进行求解。计算结果显示,在满足规范要求的前提下,重力坝断面面积减小了27.25%,极大地提高了工程经济性。且计算方法的收敛速度要优于其他传统优化算法。     

一种自动化轨道式龙门起重机作业任务调度多目标优化方法

目前常规的轨道式龙门起重机作业任务调度多目标优化方法主要通过对机械设备的运行路径进行规划模拟,从而生成最优调度方案。针对该方法缺乏对集装箱作业顺序的有效约束、优化效果不佳等问题,提出一种自动化集装箱轨道式龙门起重机作业任务调度多目标优化方法。首先将调度优化问题进行分解,并对不同子问题下的决策变量进行提取;然后以轨道吊作业总延误时间最小作为优化目标,构建多目标优化函数;最后结合双层遗传算法,对目标函数进行求解,从而生成最优调度方案。实验结果表明,新方法具有较为理想的优化效果。     

基于遗传算法的船舶破舱稳性扶正措施优化研究

根据海上舰船的实际破损情况,提出了基于遗传算法（GA）的破损进水舰船的优化扶正措施方案的计算方法;采用符号编码的方式,在GA算法中,通过在进化的不同阶段,设置大小不同的交叉及变异概率,提高进化速度,便于找到全局最优解,并编程实现。通过对实船破舱稳性扶正措施的优化并与传统方法的优化结果对比,证明了用GA优化破损船舶扶正措施的先进性和工程实用性。     

64000吨级散货船舯剖面设计优化目标及经济分析

本文结合64000吨级散货船的船中剖面设计,论述了把纵、横构件的重量和趋向最小,以及把船体强力甲板区域采用高强度钢,顶边舱内甲板纵骨采用大扁钢作为优化目标的理论基础.对建立船中剖面优化设计的目标函数提出了进一步的方案,同时对上述优化目标进行了技术经济分析.     

基于GA和SVM的水火弯板焰道布置优化方法

水火弯板是目前船舶建造中普遍采用的曲型外板加工方法,由于机理复杂,其加工过程参数确定往往依赖于工人的加工经验,难以实现标准化和规范化。文章提出基于遗传算法(GA)和支持向量机(SVM)的水火弯板焰道布置优化方法,以成形曲面和设计曲面之间的形状误差最小为优化目标,将焰道布置优化问题分解成计算最小形状误差和搜寻最佳匹配位置两个问题,并分别运用嵌套GA和SVM来实现这两个问题的求解。实例验证表明该方法能快速高效确定最优的加热线布置方案。     

基于遗传模拟退火算法的舰船分段装载顺序优化设计

以降低舰船分段装载时发生干涉次数和工具更换次数为目的,设计基于遗传模拟退火算法的舰船分段装载顺序优化方法。该方法通过构建分段装载顺序优化数学模型,并设置零件接触关系和零件干涉的装配顺序可行性条件后,利用遗传模拟退火算法经过选取适应度函数、选择分段装载因子、交叉与变异操作和模拟退火处理等步骤,求解分段装载顺序优化数学模型的目标函数,得到舰船分段装载顺序优化结果。实验结果表明,该方法在对舰船分段装载顺序实施优化时的最佳交叉概率和变异概率选取数值分别为0.9和0.1,优化后的舰船分段装载顺序发生累计干涉次数和累计更换工具次数分别降低3次和4次,优化效果显著。     

一种抑制模糊度函数特定区域旁瓣级的波形设计方法

针对发射波形为相位编码,探测低速运动目标时存在的模糊度函数旁瓣峰值过高,容易淹没微弱目标的问题,提出了在特定区域最小化模糊度函数旁瓣级的多相编码波形设计优化算法。该算法利用低速运动目标多普勒频移很小的特点,对模糊度函数进行简化,提出了离散模糊度函数的概念,在此基础上将模糊度函数峰值附近旁瓣级的最小化转化为离散模糊度函数峰值附近旁瓣级的最小化问题,并利用循环算法进行相位编码的设计。计算机仿真结果表明,所提出的波形设计方法能够有效抑制离散模糊度函数原点附近的旁瓣级,提高探测系统对微弱低速运动目标的检测能力。     

基于多目标混沌云粒子群算法的泊位-岸桥分配研究

为了提高集装箱港口泊位-岸桥分配效果和优化效率,以集卡运距和船舶在港时间最小为优化目标,建立了多目标离散泊位-岸桥分配模型,利用混沌云粒子群算法对泊位-岸桥分配模型进行求解,开发了粒子可行-整数化处理模块,内嵌于混沌云粒子群算法进化中,制定了粒子编码规则,设计了多目标函数的粒子历史极值和全局极值的计算方法,提出了基于混沌云粒子群优化算法求解多目标离散泊位-岸桥分配模型的新方法,数值算例结果证明了该模型和算法的可行性和实用性。     

基于二次流能量法的最小阻力船型研究

船体尾部流场速度场的横向和垂向分量是导致粘性阻力增加的根本原因,为了获得最小总阻力船型,以船体尾部区域为优化设计对象,以YZ方向的二次流能量最小为目标函数,以样条函数的参数为设计变量,在保证排水量为基本约束条件下,根据实际情况附加其它约束条件来控制尾部形状的变化,采用非线性规划法进行优化设计。通过集装箱船的优化算例,证实了采用该方法进行船型阻力优化的可靠性。     

基于区间分析方法的船舶不确定稳健设计优化

实际船舶优化设计中,大量不确定因素的存在可能会导致船舶性能达不到预定的设计目标。因此为了保证船型方案的可行性,本文将区间分析方法应用到不确定稳健设计优化中,以一条散货船的概念设计为例,针对单个不确定变量存在和多个不确定变量共同存在的情况,分别进行研究,以单位运输成本的中值和半径最小为目标,采用双层嵌套优化体系,内层采用多岛遗传算法求解目标函数的区间,外层采用NSGA-II算法来优化目标函数,从而保证船舶的稳健性。     

Least-weight topology and size optimization of high speed vehicle-passenger catamaran structure by genetic algorithm

Selection of the “best” or “optimum” engineering design has always been a major concern of designers. Reduction of hull weight is the most important aim in the structural design of many ship types. But the ability of designers to produce optimal designs of ship structures is severely limited by the calculation techniques available for this task. Complete definition of the optimal structural design requires formulation of size–topology–shape–material optimization task unifying optimization problems from four areas and effective solution of the problem. So far a significant progress towards solution of this problem has not been achieved. In other hand in recent years attempts have been made to apply genetic algorithm (GA) optimization techniques to design of ship structures. An objective of the paper was to create a computer code and investigate a possibility of simultaneous optimization of both topology and scantlings of structural elements of large spatial sections of ships using GA. In the paper GA is applied to solve the problem of weight minimization of a high speed vehicle-passenger catamaran structure with several design variables as dimensions of the plate thickness, longitudinal stiffeners and transverse frames and spacing between longitudinals and transversal members. Results of numerical experiments obtained using the code are presented. They show that GA can be an efficient optimization tool for simultaneous design of topology and sizing high speed craft structures.     

基因演算法於船体加强板架之最佳化设计应用

船体结构之最佳化设计是一个复杂非线性的混和离散问题,并且要搜寻到全域的最佳值并不容易。在复杂的设计环境下基因演算法（Genetic Algorithm;GA）却可以搜寻到近似的全域最佳值。本文主要是应用基因演算法对T加强板架（Tee stiffened panel）、平板加强板架（flat-bat stiffened Panel）等常用且最具代表性之船体结构件进行最佳化设计,使结构在满足终极破坡限制（ultimate failure constraints）与耐用破坏限制（serviceability failure constraints）等所有限制条件下,求得最佳目标函数值中各设计变之最佳组合。在过程中并考量不同族群大小、变换机率、突变机率因素对最佳化结果的影响。文中是以制造成本为目标函数,其中同时考量材料成本及劳工成本,且所得之结果与连续性线性规则（Sequential Linear Programming;SLP）最佳化结果作了比较。计算的结果显示基因演算法可以有效地与快速地获得最小重量和最低成本的目标。     

基于粒子群算法的起重船扒杆结构优化设计

基于Isight优化软件和通用有限元软件,以扒杆重量为目标函数,采用粒子群算法（PSO）和遗传算法对某起重船扒杆结构进行了优化设计,并讨论了PSO算法的稳定性。通过对两种算法优化结果的比较分析表明,PSO算法优化效果好,收敛速度快,且计算稳定性高,验证了PSO算法在工程船舶结构优化设计中的有效性。     

集装箱船主尺度全局最优化的混沌算法

提出了应用混沌优化方法（Chaos Optimization Algorithm,COA)进行集装箱船船型主尺度要素全局优化的新策略。混沌优化方法利用混沌变量的随机性、规律性、遍历性寻优，能够克服经典优化方法如直接法、梯度法、Hessian法等方法容易陷入局部极小点的不足，方法简单、快速、易于掌握，其效率比一些目前广泛应用的随机优化方法如模拟退火法（SAA）、遗传算法（GA）等高得多。实际算例的结果证实了混沌优化方法用于集装箱船船型优化的有效性。     

基于遗传算法的最小阻力船型优化设计

遗传算法是一种全局最优化算法,它能够克服传统优化方法的缺点和不足,从而获得全局最优解。因此,为了获得阻力性能更好的优良船型,将遗传算法进行适当改进并用于船型优化中,进行最小阻力船型优化设计,以非线性兴波阻力理论(Rankine源法)为基础,利用遗传算法并结合CAD技术进行船型优化设计。在优化过程中,把总阻力作为目标函数,设计变量取船型修改函数的参数,确保排水量为基本约束条件下,对船体前半体型线进行优化研究。选取某高速巡逻艇作为初始船型进行优化计算,获得的最优船型总阻力降低了13.1%,兴波阻力降低了21.7%,表明遗传算法用于船体线型优化设计是行之有效的。     

Application of a genetic algorithm to the optimal structural design of a ship's engine room taking dynamic constraints into consideration

The genetic algorithm, known as GA, is used to optimize engine room structure, not only under static constraints, but also under dynamic constraints. A penalty function method is used to handle the complicated constraint conditions based on the numerical results of dynamic and static analyses. There are several ways to take the dynamic effect into account in the optimum design of ship structure. First, the inequality constraint condition is applied to separate the natural frequency and the exciting frequency. Second, generalized design variables are introduced in order to transfer not only the dynamic but also the static equilibrium equations into the equality constraints, resulting in the optimal structural design without the need to solve these equilibrium equations. Third, the magnitudes of the acceleration and displacement are constrained instead of applying the natural frequency constraint condition. In order to achieve better convergency in the optimization with least resources, several operators and methods are considered and then introduced into the structural design of the engine room. The new operator, called either objective elitism or fitness elitism, is introduced to improve the efficiency of the method. The effect of boundary mutation and nonuniform mutation on the performance of the GA is examined. Not only binary representation but also floating-point representation are used to express the design gene in the GA. Fuzzy theory is applied in the GA to handle the uncertainty of the constraint conditions. Two ways of solving fuzzy optimization are investigated in order to obtain a fuzzy solution and a crisp solution. Received: October 2, 2000 / Accepted: November 30, 2000     

UUV操纵性能综合优化模型研究

操纵性能是无人潜器（UUV）航行的重要性能之一,其优劣直接影响到UUV的航行安全和稳定性,UUV操纵性能评判和优化是UUV优化设计的重要组成部分.基于AUTOSUB型无人潜器的设计模型,在充分分析艇体操纵性能的基础上,重点研究UUV水平运动和垂直运动性能,提出了较为完备的UUV操纵性能优化数学模型.采用模糊评判方法构造操纵性系统总目标函数,利用专家咨询法确定了各子系统的权重;通过大量艇体操纵性能数据对各个性能指标进行统计分析,选择模糊数学中对应的隶属度函数进行拟合,确定相应隶属度函数参数;利用禁忌搜索算法对遗传算法的改进而得到的遗传禁忌搜索算法（GA-TS）,由并行和分层策略改进遗传算法得到的并行遗传算法（PGA）以及遗传二次载波算法（LGA）,将数学模型与这3种算法集成,利用C＋＋语言编写了UUV操纵性能优化软件.通过对总系统优化得到的遗传禁忌搜索算法寻优能力最强,利用该算法研究水平面运动和垂直面运动2个子系统,得到各个性能指标权重对系统目标函数影响程度的排序,同时分别得到-组最佳性能的权重分配.     

基于遗传算法的舰船舱段可靠性优化设计

遗传算法在引入动态自适应策略和"免疫算子"之后,其收敛效率有了较大的提高。对于以可靠性作为约束的随机结构系统优化问题,以罚函数法为基础,构造了有效的约束与目标函数向适应值函数的映射公式。建立合理的安全余量,采用随机有限元法处理结构分析中所涉及的有关参量的随机性,计算结构响应和敏度分析,并进行系统的可靠性计算。通过两种算法的结合,利用自适应免疫遗传算法、随机有限元法及可靠性的基本理论,建立了一套完整的基于遗传算法与随机有限元的结构系统可靠性优化设计方法。对舰船舱段结构梁系截面的优化计算结果表明,算法对多随机因素结构系统的可靠性优化具有良好的收敛效果。     

支持向量机和遗传算法组合策略的VLCC船中结构优化设计(英文)

In this paper a hybrid process of modeling and optimization,which integrates a support vector machine(SVM) and genetic algorithm(GA),was introduced to reduce the high time cost in structural optimization of ships.SVM,which is rooted in statistical learning theory and an approximate implementation of the method of structural risk minimization,can provide a good generalization performance in metamodeling the input-output relationship of real problems and consequently cuts down on high time cost in the analysis of real problems,such as FEM analysis.The GA,as a powerful optimization technique,possesses remarkable advantages for the problems that can hardly be optimized with common gradient-based optimization methods,which makes it suitable for optimizing models built by SVM.Based on the SVM-GA strategy,optimization of structural scantlings in the midship of a very large crude carrier(VLCC) ship was carried out according to the direct strength assessment method in common structural rules(CSR),which eventually demonstrates the high efficiency of SVM-GA in optimizing the ship structural scantlings under heavy computational complexity.The time cost of this optimization with SVM-GA has been sharply reduced,many more loops have been processed within a small amount of time and the design has been improved remarkably.     

应用GA,PSO,ACO算法进行水下自主运载器路径规划(英文)

In this paper,an underwater vehicle was modeled with six dimensional nonlinear equations of motion,controlled by DC motors in all degrees of freedom.Near-optimal trajectories in an energetic environment for underwater vehicles were computed using a numerical solution of a nonlinear optimal control problem(NOCP).An energy performance index as a cost function,which should be minimized,was defined.The resulting problem was a two-point boundary value problem(TPBVP).A genetic algorithm(GA),particle swarm optimization(PSO),and ant colony optimization(ACO) algorithms were applied to solve the resulting TPBVP.Applying an Euler-Lagrange equation to the NOCP,a conjugate gradient penalty method was also adopted to solve the TPBVP.The problem of energetic environments,involving some energy sources,was discussed.Some near-optimal paths were found using a GA,PSO,and ACO algorithms.Finally,the problem of collision avoidance in an energetic environment was also taken into account.