一种多学科设计优化近似模型构建方法

通过采用单个参数控制样本的误差界限、采用Laplace损失函数和改变置信区间项,给出了一种基于单参数的Lagrangian支持向量回归算法。以实际数值函数为例,通过采用三组不同样本集进行拟合训练,构建了基于支持向量机的近似模型;以石油平台支援船总阻力估算为例,通过与模型试验及其他典型方法的对比,检验了算法用于近似模型构建的准确性和适用性。研究结果表明,采用支持向量机方法构建近似模型在小样本条件下比神经网络等传统方法具有更好的泛化性和推广能力,能够有效提高计算精度与优化效率,在复杂系统多学科优化设计中具有很大的应用价值。     

回转体艇型阻力近似计算方法与试验研究

研究了试验设计和近似模型技术,确定了回转体艇型曲线的6个控制参数,根据系列回转体阻力数值计算结果,建立了水下航行器阻力近似计算的响应面模型及径向基神经网络模型。通过系列模型试验验证了多种近似模型的拟合精度,与工程估算方法以及CFD方法进行了比较。结果表明,4阶响应面模型及径向基神经网络模型精度远高于工程经验公式,能够正确反映艇型参数对阻力结果的影响,为后续艇型优化设计带来一定的参考价值。     

基于近似模型的海上发射船船型优化

基于耐径向基函数神经网络模型(RBF),以火箭承受弯矩为单目标优化函数,对双体发射船船型参数进行优化研究。选定对船型参数CB和L/B作为优化变量,利用Lackenby方法,对船型参数化建模,应用最优拉丁超立方方法(LHD)选取样本点,采用二次插值方法扩充样本点数据,建立双体船运动响应及阻力近似模型,利用多岛遗传算法(MIGA)搜索最优船型。结果表明优化后船型的火箭弯矩减小3.86%,从而为双体火箭发射船的设计及相关船型研究提供参考。     

组合近似模型在小水线面双体船应力预测中的应用

小水线面双体船受海浪冲击时结构应力的准确预测对保证航行安全具有重要意义。采用有限元软件进行应力的数值仿真需要花费巨大的时间成本,构建近似模型成为解决这一问题的有效途径。由于样本点有限,当选择不适当的近似模型时难以保证近似模型精度,组合近似模型(EMs)技术能避免选择单一近似模型的不足和缺陷。本文采用组合近似建模技术预测小水线面双体船在受海浪冲击时的最大结构应力,并与单一近似模型预测精度进行比较,结果表明,组合近似模型的精度更高,能够有效预测最大结构应力,具有较大的工程实用价值。     

半潜平台浮托安装水动力响应特性数值模拟与模型试验研究

半潜式平台（Semi-Submersible Platform, SEMI）是海洋石油天然气开发中钻井和生产中常见的浮式平台,随着海洋资源的不断开发,浮托安装作为一种省时省力的新型模块安装法逐渐成为主流。本文以半潜平台上部组块浮托安装过程为研究对象,以数值模拟和模型试验为研究手段,针对不同海况条件,探究半潜平台在浮托安装船进船过程中的水动力响应特性,并对平台是否会发生触底进行评估。结果表明,Newman近似法得到的垂荡运动结果与全QTF法误差较大,后者与模型试验吻合更好;本文平台不会发生触底现象,可以安全进行浮托安装作业,研究结果为实际工程安装提供数据支持与有力支撑。     

组合近似模型在小水线面双体船应力预测中的应用

小水线面双体船受海浪冲击时结构应力的准确预测对保证航行安全具有重要意义.采用有限元软件进行应力的数值仿真需要花费巨大的时间成本,构建近似模型成为解决这一问题的有效途径.由于样本点有限,当选择不适当的近似模型时难以保证近似模型精度,组合近似模型(EMs)技术能避免选择单一近似模型的不足和缺陷.本文采用组合近似建模技术预测小水线面双体船在受海浪冲击时的最大结构应力,并与单一近似模型预测精度进行比较,结果表明,组合近似模型的精度更高,能够有效预测最大结构应力,具有较大的工程实用价值.     

基于支持向量机的船舶结构优化方法

针对船舶等大型结构在优化过程中耗时长的问题,提出了支持向量机与遗传算法组合优化方法。基于支持向量机建立结构的近似模型,代替耗时长的有限元分析并应用遗传算法进行结构优化,形成一套省时、精度高、适应性强的优化方法。以某舱段结构优化为例,建立支持向量机近似模型,模拟结构设计尺寸与结构响应的映射关系,并选用二阶响应面模型做精度对比。分别使用支持向量机与遗传算法组合优化方法(SVM-GA)、传统的有限元法与遗传算法组合优化方法(FEM-GA)进行优化分析,计算结果表明,SVM-GA法相对于传统的FEM-GA法,不仅显著降低计算时间成本,而且具有良好的精度。     

基于CFD数值模拟和模型试验的三体船片体位置优化

论文采用低精度CFD数值计算和高精度模型试验相结合的方法，以总阻力为目标，对Fr=0.27速度工况下的某型三体船的片体位置进行优化。利用拖曳水池对不同片体位置的三体船进行模型试验，获得三体船在不同片体位置下的总阻力性能。使用自主开发的CFD黏流数值求解器naoe-FOAM-SJTU对一定范围内的其他片体位置进行水动力数值计算。根据模型试验和数值计算结果，使用自主开发的船型优化软件OPTShip-SJTU对三体船的片体位置进行优化。通过模型试验与数值方法相结合的方式构建Co-Kriging近似模型，并使所构建的模型融合模型试验的信息，以保证优化结果的可靠性。结果显示，沿船长方向不同的片体位置对三体船总阻力的影响有着明显的变化规律。     

大型船舶艏侧推槽道布置参数优化

为减小侧推槽道带来的船体阻力增值，以某集装箱船为研究对象，开展槽道布置参数优化研究。以设计工况下的总阻力最小为优化目标，以侧推槽道的纵向位置和垂向位置为设计变量，在设计空间内采用全因子法采样，并进行数值仿真，得到样本响应值构成样本空间；采用响应面法构建代理模型，并采用模拟退火算法对该模型进行寻优。结果表明，优化船的阻力性能相比原始船有明显改善，设计工况下的总阻力减小1.7%。     

风电安装船运动响应分析及模型试验研究

为了分析风电安装船在实际海况下的运动响应及阻力性能,基于三维势流理论,本文对风电安装船进行频域和时域运动响应数值分析,并开展风电安装船模型试验,对航行阻力、幅频响应函数和在位运动响应进行试验研究。通过试验得到风电安装船在航速13 kn时阻力为899 k N,RAO响应曲线和不规则波中的运动幅值验证了数值计算的准确性。研究结果表明风电安装船在十年一遇的北大西洋海况中运动幅值较大,不宜进行安装作业。     

FPSO单点系泊系统动力截断优化设计

浮体系泊系统在海洋工程水池进行模型试验时，由于水池尺度有限，首先对系泊线进行等效截断设计，是被动式混合模型试验的重要一步。截断设计时，基于细长杆理论，模拟系泊线的非线性动力特性，将计算所得时域内的系泊力转换到频域响应，选择有代表性的频率及响应建立目标函数，结合NSGA II优化算法，确定最优截断系泊参数，计算快速准确。针对一作业水深420m的FPSO单点系泊系统，进行水平截断设计。截断前后系泊系统和单根系泊线的静力特性吻合很好。截断系泊系统在不同环境载荷作用下的总体响应和系泊动力，都与截断前一致。证明了截断设计的合理性和准确性，为后续的模型试验工作打下了基础。     

基于序贯Kriging模型的潜器型线优化设计

潜器型线优化设计是一个多目标优化问题,在型线设计过程中,阻力性能与包络体积的要求是相互冲突的。为了解决计算流体力学软件如Fluent在进行潜器的外形优化设计时效率低下问题,采用Kriging模型代替仿真模型进行潜器外形设计的策略,其基本思想是：选取设计变量和样本点,利用ICEM软件建立参数化的水动力分析模型,用Fluent软件计算得到样本点的阻力响应值,建立反映设计变量与响应之间关系的Kriging模型,将阻力和体积作为潜器外形优化的两个目标,利用多目标遗传算法求出Pareto最优解。由于采样策略对Kriging模型精度影响很大,本文提出了一种新的序贯采样方法命名为加权累积误差方法,来选取样本点以提高Kriging模型精度。结果表明提出的序贯Kriging建模技术能极大提高潜器型线优化设计效率,同时保证设计精度。     

Efficient optimization design method of jacket structures for offshore wind turbines

With the gradual implementation of offshore wind energy production, the future tendency is to expand into the deeper water. The jacket foundations will take the place of the present monopile foundations when the water depth increases. The foundations account for the majority of the construction cost for offshore wind farms, and the structural optimization of jackets will bring lucrative economic benefits. Structural optimization is a complex iterative process that requires huge computing costs. Therefore, this paper proposes a structural optimization method based on surrogate models to solve this problem effectively and swiftly obtain optimized design schemes of lightweight jackets for offshore wind turbines. The structural responses of jacket wind turbine systems under the equivalent static extreme loads with a recurrence period of 50 years are mainly considered in structural optimization design, and the key optimization variables of jackets are determined by parameter sensitivity analysis. The finite element models of jackets are transformed into surrogate models, and the genetic algorithm is employed to optimize the surrogate models directly. The optimized jackets are additionally verified through coupled dynamic analysis, besides, buckling strength and fatigue life are also checked. And local refined optimizations are carried out for the failure members. According to the optimized design schemes of lightweight jackets for 30 m, 50 m and 70 m water depths, it is demonstrated that the structural optimization design method is adequate and efficient for jackets of wind turbines. Parameter sensitivity analysis can cut the number of optimization variables in half to improve the optimization efficiency. Furthermore, the application of surrogate models can significantly speed up the optimization process by saving about 98.61% of the original time consumed. The optimization design method of the jackets for offshore wind turbines proposed in this paper is suitable for practical engineering, with high precision and efficiency.     

Design of the lines of underwater vehicles based on collaborative optimization

A generalized collaborative optimization (CO) framework is proposed to the optimization design of the lines of an underwater vehicle. The resistance and maneuvering performances are concerned about and taken as the optimization objectives in the optimization framework. The resistance, lateral force and yaw moment are calculated by RANS method. To improve the optimization efficiency, an automatic integration optimization platform is constructed in which a surrogate model is adopted. A SUBOFF model is taken as the verification model. The optimal results demonstrate the validity of the optimization strategy proposed.     

三体槽道船船型设计及阻力性能研究

基于原三体风电维护船船型,结合M型船主要特征要素设计改造出三体槽道风电维护船。利用数值仿真技术模拟出M型风电维护船在中高航速下船底槽道的水气两相流变化,并在此基础上进一步探索船体槽道高度、长度的变化位置对船体总阻力的影响,最终确定阻力性能较优的船型方案,从而为海上三体槽道风电维护船船型设计提供参考。     

A decomposition method for surrogate models of large scale structures

Analysis is computationally the most expensive part of optimization. Surrogate models, which are approximate but faster statistical models, can be used in place of more precise but more computer-intensive methods like finite element method to improve efficiency. Unfortunately, the surrogate models are limited by the number of model parameters. So large-scale problems cannot be fully defined by a single surrogate model. Furthermore, current domain decomposition methods cannot be used with black-box models. This study presents a novel approach to design thin-walled structures using surrogate models that overcome the curse of dimensionality by a special decomposition method. A parametric panel structure is defined as a building block. An interface is developed to maintain compatibility across the blocks. Finally, an iterative algorithm finds the displaced state using only local information. Three test structures are used to show the convergence of the algorithm for static analysis. In these sample cases, number of steps required for convergence of the error did not change with the number of panels. This approach offers many benefits including automatic design creation and optimization, effective usage of stream processors and model reuse.     

代理模型在水下航行体空泡压力预示的应用研究

文章基于径向基神经网络(Radial Basis Function,RBF)和Kriging代理模型方法分别对水下垂直发射航行体表面附着空泡闭合区压力预示模型进行了研究,首先分析了影响空泡闭合区压力变化的物理因素,通过代理模型方法建立了影响因素与空泡闭合区压力最大值和压力空间分布波形之间的数学模型,形成了空泡闭合区压力分布预示方法,而后针对典型工况开展预示结果与试验数据比对,表明RBF方法和Kriging方法均能较为准确地获取空泡闭合区压力特征,在有限子样条件下Kriging代理模型对空泡闭合区压力峰值预示精度更高。     

风机运输甲板驳结构强度评估

风机运输甲板驳是用于海上风机运输的海洋工程辅助船,近年来随着海上风力发电的兴起而迅速发展。本文采用全船有限元直接计算和 CCS规范计算2种方法对某风机运输甲板驳的结构强度进行评估,计算表明该船结构强度满足设计要求。本文的研究成果和结论对同类型风电安装船舶的结构设计具有参考意义。     

Broaching prediction of a wave-piercing tumblehome vessel with twin screws and twin rudders

The new intact stability criteria which are under development at the International Maritime Organization (IMO) are required to cover a broaching phenomenon, well known as a great threat to high-speed vessels which can lead to capsizing. Some reports exist which demonstrate that their numerical models can predict a highly nonlinear phenomenon of broaching. However, additional validation studies are needed for unconventional vessels, in addition to conventional ones, to develop direct stability assessment methods for the new intact stability criteria. In this research, we selected as the subject ship a wave-piercing tumblehome vessel with twin screws and twin rudders, a design expected to be one of a new generation of high-speed monohull ships. Firstly, a series of captive model tests were conducted to measure the resistance, the manoeuvring forces, the wave-exciting forces, the heel-induced hydrodynamic forces, and the roll restoring variation for the unconventional tumblehome vessel. Secondly, the existing mathematical model which had been developed for broaching prediction of conventional vessels with a single propeller and a single rudder was extended to unconventional vessels with twin propellers and twin rudders. Finally, comparisons between numerical simulations and the existing free running model experiments were conducted. As a result, it was demonstrated that fair quantitative prediction of broaching is realised when the rudder force variation, the roll restoring variation and the heel-induced hydrodynamic force for large heel angles are taken into account.