Regularization method and immune genetic algorithm for inverse problems of ship maneuvering

Ship maneuverability, in the field of ship engineering, is often predicted by maneuvering motion group MMG) mathematical model. Then it is necessary to determine hydrodynamic coefficients and interaction force coefficients of the model. Based on the data of free running model test, the problem for obtaining these coefficients is called inverse one. For the inverse problem, ill-oposedness is inherent, nonlinearity and great computation happen,and the computation is also insensitive, unstable and time-consuming. In the paper, a regnlarization method is introduced to solve ill-posed problem and genetic algorithm is used for nonlinear motion of ship maneuvering. In addition, the immunity is applied to solve the prematurity, to promote the global searching ability and to increase the converging speed. The combination of regnlarization method and immune genetic algorithm(RIGA) applied in MMG mathematical model, showed rapid converging speed and good stability.     

内河船舶避碰路径优化研究

内河船舶碰撞事故导致重大生命及财产损失，已经引起人们的高度关注．提出一种内河船舶自动避碰路径优化的研究方法，建立了内河船舶操纵运动数学模型，将遗传算法运用到内河船舶避碰路径选优中，提出内河船舶避碰路径优化准则，并构建一种考虑内河航道中运动船舶及障碍物的适应度函数．优化结果表明了本方法的可行性。     

基于图像信息检测的船-桥智能避碰系统研究

将避碰决策系统分为船舶运动检测、视觉几何模型和船舶运动态势计算、碰撞预报及预控3部分.针对图像质量问题采取图像预处理增强、中值滤波、直方图均衡处理方法.采用相位相关算法基于背景模态模式静态空间信息记录图像信息,补偿图像抖动.基于视觉几何模型计算船舶运动态势计算船舶目标空间坐标位置、船舶型尺度、船速、船首向等.基于实时运动状态信息和桥区船舶运动态势预报碰撞危险以及避碰决策模式.引入避碰等级术语通过计算桥区船舶操纵避碰相关参数,进行避碰早期预警并得出避碰操纵决策方案.形成合理化的船-桥避碰决策系统,以达到船-桥避碰预警预控的智能效果.     

Minimum resistance ship hull uncertainty optimization design based on simulation-based design method

In the ship hull optimization design based on simulation-based design (SBD) technology, low precision of the approximate model leads to an uncertainty form of optimization model. In order to enable the approximate model with finite precision to maximize the effectiveness, uncertainty optimization method is introduced here. Wave resistance coefficient approximation model, built by back propagation (BP) neural network, is represented as a form of interval. Afterwards, a minimum resistance optimization model is established with the design space constituted by principal dimensions and ship form coefficients. Double-level nested optimization architecture is proposed: for outer layer, improved particle swarm optimization (IPSO) algorithm with learning factor improvement strategy is used to generate design variables, and for inner layer, modified very fast simulated annealing (MVFSA) algorithm is used to solve the objective function interval with uncertainty region. Cases calculation proves the effectiveness and superiority of uncertainty optimization method for ship hull SBD optimization design, thus providing a good way for finding optimal designs.     

船舶静止受外力作用运动规律探析

本文在假定理想条件下,探讨船舶受外力作用时的运动状态改变规律,通过力学原理进行计算推导,结合船舶操纵实践,分析不同受力情况下的船舶运动,并给出操作建议。     

开阔水域多物标动态自适应智能航行方法

考虑船舶操纵特性、《1972年国际海上避碰规则》和良好船艺要求,提出了动态自适应目标船不协调避碰行动的开阔水域智能航行方法;将物标分类、建模并构建数字孪生交通环境,结合航向控制方法、操纵运动和复航模型构建了自动航行模型,推演了船舶非线性操纵运动;基于自动航行模型量化解析了《规则》要求,探究动态避碰机理,建立了可行航向求取方法;在多目标环境中,提出了目标船机动判别方法,研究了《规则》约束下构成自主航行方案的改向时机、幅度和复航时机等要素求取方法。仿真结果表明:依靠信息秒级更新的滚动计算,提出的智能航行方法可自适应剩余误差和目标船随机运动;提出的智能航行方法能将可行航向区间和改向幅度精确到1°;将程序运行和复航时机计算步长设置为1、10 s,设置多类静态物标和6艘保向保速目标船,在640、1 053、2 561和3 489 s,本船进行右转9°、复航、保向保速和复航等操纵可让请所有目标并自主航行至终点;设置目标船在300 s采取不协调转向避让行动,本船在980、2 790、3 622、5 470 s时进行右转9°、左转12°、右转17°和复航等操纵可让请所有目标并自主航行至终点。可见,任意初始状态下的船舶均可沿计划航线自动航行至终点,提出的方法能满足多个、多类动静态物标共存的真实开阔水域环境中的智能航行需要。      

Investigation on maneuverability of a twin-screw ship driven by one screw

It is possible for a twin-screw ship that one screw failure occurs during navigation, and the maneuverability in this case should be noticed by ship designers and operators. It is of great significance to evaluate the related risk. Firstly, a mathematical model for the twin-screw ship maneuvering motion with one failed screw is developed based on the maneuvering model group (MMG) equations, and verified by the model test results. Secondly, the maneuvering motions of a twin-screw liquefied natural gas (LNG) ship with one free rotating failure screw or with one locked failure screw are simulated and compared by using the mathematical model. It is shown that the numerical modeling results are in agreement with the model test results. Compared with those of normal navigation, the port turning ability of the ship with one failed port screw is better, but the starboard turning ability and yaw checking ability become worse. The maneuverability of the ship with locked failure screw is better than that with free failure screw, although the ship speed drops obviously.     

考虑航艏向与数据变化差异的船舶轨迹预测

船舶自动识别系统(Automatic Identify System,AIS)数据可以实时体现船舶当前时刻的具体动态,采用传统BP(Back Propagation)神经网络模型的船舶轨迹分析预测方法,在计算中直接将航艏向数据纳入模型,没有考虑船舶航艏向在零度附近变动时带来的实际方向变动幅度与数据变化幅度存在较大偏差问题。为解决该问题,在BP神经网络基础上,引入双三角函数变换,同时将正弦值与余弦值纳入模型,将两者相结合,从两维度体现航艏向情况;在拟合预测后进行反三角函数变换和平均处理,构建一种基于改进神经网络算法的船舶AIS轨迹预测模型。选取实例数据进行模型验证,实例结果表明,该模型预测结果比不考虑差异方法的误差均方差更小,大幅降低误差幅度,可更精确地预测船舶轨迹。     

基于线性矩阵不等式的船舶动力定位滑模控制

为了解决具有非线性和环境干扰的船舶动力定位系统的控制问题, 提出了一种基于线性矩阵不等式的滑模控制算法; 将跟踪误差设计为滑模函数, 设计线性矩阵不等式, 求解状态反馈增益; 基于二次型Lyapunov函数证明了闭环系统的稳定性; 设计切换函数, 使系统对不确定性和外加干扰具有较强的鲁棒性, 避免出现抖振现象; 对基于线性矩阵不等式的滑模控制器进行仿真, 计算出动力定位船舶在无扰动的匀速运动和有外界环境扰动的变速运动2种不同情况下的前进速度、横荡速度、艏向角速度、前进加速度、横荡加速度、艏向角加速度、前进控制力、横荡控制力和艏向控制力矩等; 分析了状态反馈增益线性矩阵、边界层、切换项增益等参数对控制性能的影响。研究结果表明: 采用基本滑模控制使前进速度达到期望值所需的上升时间为29s, 而新算法为15s, 节约了48.28%;采用基本滑模控制使横荡速度达到期望值所需的上升时间为24s, 而新算法为14s, 节约了41.67%;采用基本滑模控制使艏向角速度达到期望值所需的上升时间为13s, 而新算法为10s, 节约了23.08%。可见, 设计的控制器对有非线性和环境干扰的船舶动力定位系统都具有较强的鲁棒性, 具有控制输入连续、控制抖振小、不存在过高增益等特点。      

集装箱船舶贝内配载和堆场装船顺序协调优化

针对集装箱船舶贝内配载和堆场装船顺序协调优化问题，以堆场贝位和船舶贝位翻箱次数之和最小为优化目标，考虑堆场装船要求和船舶适航性等多种约束条件，建立数学模型. 鉴于问题的NP特性，提出混合演化策略算法(HES)求解模型，设计二维实数编码，提出基于力矩平衡和逐列装载的解码方法. 基于三点交叉互换的重组算子，单点突变的变异算子和互换的局部搜索策略对算法进行改进. 通过计算证明，对不同规模算例，HES算法均能求解出较优的贝内配载方案和堆场装船顺序.HES 算法与传统演化策略算法(ES)、粒子群算法 (PSO)、基于规则的启发式算法(HA-MBSCC)进行对比，进一步验证了算法的优越性.     

集装箱船舶贝内配载和堆场装船顺序协调优化

针对集装箱船舶贝内配载和堆场装船顺序协调优化问题，以堆场贝位和船舶贝位翻箱次数之和最小为优化目标，考虑堆场装船要求和船舶适航性等多种约束条件，建立数学模型. 鉴于问题的NP特性，提出混合演化策略算法(HES)求解模型，设计二维实数编码，提出基于力矩平衡和逐列装载的解码方法. 基于三点交叉互换的重组算子，单点突变的变异算子和互换的局部搜索策略对算法进行改进. 通过计算证明，对不同规模算例，HES算法均能求解出较优的贝内配载方案和堆场装船顺序.HES 算法与传统演化策略算法(ES)、粒子群算法 (PSO)、基于规则的启发式算法(HA-MBSCC)进行对比，进一步验证了算法的优越性.     

Ship appearance optimal design on RCS reduction using response surface method and genetic algorithms

Radar cross section (RCS) reduction technologies are very important in survivability of the militarynaval vessels. Ship appearance shaping as an effective countermeasure of RCS reduction redirects the scatteredenergy from one angular region of interest in space to another region of little interest. To decrease the scatteringelectromagnetic signals from ship scientifically, optimization methods should be introduced in shaping design.Based on the assumption of the characteristic section design method, mathematical formulations for optimalshaping design were established. Because of the computation-intensive analysis and singularity in shapingoptimization, the response surface method (RSM) combined genetic algorithm (GA) was proposed. The poly-nomial response surface method was adopted in model approximation. Then genetic algorithms were employedto solve the surrogate optimization problem. By comparison RCS of the conventional and the optimal design,the superiority and effectiveness of proposed design methodology were verified.Ky words: radar cross section (RCS); characteristic section design method; response surface method; genetic algorithm (GA) was proposed. The polynomial response surface method was adopted in model approximation. Then genetic algorithms were employed to solve the surrogate optimization problem. By comparison RCS of the conventional and the optimal design, the superiority and effectiveness of proposed design methodology were verified.     

基于单参数自调节RM-GO-LSVR的船舶操纵灰箱辨识建模

为实现舵角小、试验数据少条件下船舶操纵辨识建模, 提出了一种船舶操纵运动灰箱模型; 搜集水动力系数已知的船舶运动数学模型作为备选参考模型(RM), 计算被辨识船舶与备选RM的相关系数, 并以此筛选合适的RM; 运用相似准则将观测数据映射到RM的输入值域, 建立被辨识船舶与RM的运动关联, 获得了RM的加速度项, 并使用线性支持向量回归(LSVR)机补偿被辨识船舶和RM加速度项间的误差; 分析了机理模型, 设计了合适的LSVR输入项, 使用全局优化(GO)算法自动调节了LSVR的不敏感边界参数; 基于自航模试验数据训练了灰箱模型, 并与约束模试验(CMT)结果和计算流体力学结果比较, 验证了灰箱模型的泛化能力和预报精度。研究结果表明: 在20°船艏向、20°舵角Z形试验预报中, 灰箱模型所得第一超越角精度至少比CMT、虚拟约束模试验(VCMT)和RM方法所得结果高1°, 灰箱模型所得第二超越角精度至少比CMT和VCMT所得结果高0.4°; 在35°舵角旋回试验预报中, 灰箱模型所得进距精度至少比CMT、VCMT、数值循环水槽试验(NCWCT)和RM方法所得结果高1%, 灰箱模型所得战术直径精度比CMT所得结果低4%, 比NCWCT所得结果高10%;RM方法有助于灰箱辨识建模, GO算法能够优化LSVR的不敏感边界参数, 建立的单参数自调节灰箱辩识建模方法能够实现小舵角、少数试验条件下的船舶操纵辨识建模。      

基于遗传算法求解转移流量的多目标规划方法

以十字交叉口为例,在分析交叉口进、出口流量与转移流量之间关系的基础上,以进口交通流量观测值与来自各个出口并进入该进口的估计转移流量之差的绝对值和出口交通流量观测值与该出口到达各个进口的估计转移流量之差的绝对值之和最小为目标函数,转移流量的实际取值范围作为约束条件,建立了求解转移流量的多目标规划模型.利用遗传算法并行运算的特性,提出了基于遗传算法求解转移流量的多目标规划方法.最后通过一个算例给出了应用该方法求解转移流量的多目标规划模型的求解效果.     

基于遗传算法求解转移流量的多目标规划方法

以十字交叉口为例,在分析交叉口进、出口流量与转移流量之间关系的基础上,以进口交通流量观测值与来自各个出口并进入该进口的估计转移流量之差的绝对值和出口交通流量观测值与该出口到达各个进口的估计转移流量之差的绝对值之和最小为目标函数,转移流量的实际取值范围作为约束条件,建立了求解转移流量的多目标规划模型.利用遗传算法并行运算的特性,提出了基于遗传算法求解转移流量的多目标规划方法.最后通过一个算例给出了应用该方法求解转移流量的多目标规划模型的求解效果.     

考虑换船作业的长江干线集装箱船舶调度

考虑换船作业情况，建立以总运输成本最小为目标的非线性规划模型，提出包括船舶选择、挂靠港选择和运输任务指派三方面内容的不定期集装箱船舶调度优化方法；针对模型特点，考虑基因融合及基因修复，设计改进遗传算法对问题进行求解，应用案例获得集装箱船舶调度优化方案；采用多算例方法将考虑换船作业与不考虑换船作业的调度方案进行对比分析. 结果表明，考虑换船作业可以降低运输总成本，减少船公司的投入运力，有效提高投入运力的综合利用率，增强船公司的竞争力，为船公司制定船舶调度方案提供决策参考.     

集装箱船舶支线运输航线优化算法

以枢纽港船舶限制时间和支线船舶容量为基础,分析了轴-辐式网络运输模式。以船舶最小总航行时间为目标函数,建立了混合整数规划支线集装箱运输模型。通过设计巡回路线方法实现杂交和变异,更新了解的构成,运用遗传算法求解模型。计算结果表明:当船舶容量为150 TEU时,在160次迭代后,总航行时间为708.6 h,航线数量为8条;当船舶容量分别为100、150 TEU时,在150次迭代后,总航行时间为714.6 h,航线数量为9条;对枢纽港船舶限制时间和支线船舶容量进行方差分析,F检验统计量的概率值均明显小于0.05;对支线船舶容量和运营成本进行敏感性分析,增大船舶容量能够减小航线数量和运行时间,但增大了运营成本,增大枢纽港船舶限制时间能够减小航线数量;考虑航行时间和运营成本,当船舶容量为150 TEU时最合理。     

考虑船舶封存与压港的电煤船舶调度优化模型

针对中国电煤水运系统的实际特点, 综合考虑了船舶封存与港口拥堵(压港)因素, 建立了混合整数规划优化模型, 对电煤船舶调度方案进行优化; 基于运输需求的硬时间窗、卸货港船舶排队等待时间与水路-铁路运输协同三因素之间的互动关系, 以运输系统总成本最小为目标, 协同优化水、铁电煤运输的货运分担率、水路运输任务指派和相应的船舶调度与封存/启用方案; 基于改进列生成算法, 提出了一种可精确求解实际规模电煤船舶调度问题的列生成算法, 利用Gurobi求解列生成的主模型, 使用动态规划标号法求解列生成的子模型; 利用中国南部某火力发电集团的实际数据, 对提出的算法进行了算例分析。计算结果表明: 在中等规模的算例中, 使用提出的改进算法获得最优解仅需73.61 s, 相比于使用基于运输任务运量排序的启发式求解方法(PHA), 求解效率提高了18.1%;在较大规模的算例中, 使用提出算法的计算时间仅为222.02 s, 同比PHA, 计算效率提高了19.1%;通过求解一个实际的调度问题可以发现, 利用提出的优化模型和算法能有效缩短船舶在卸货港的等待时长与船舶处于启用状态的时长, 使运输总成本下降17.13%, 实现了电煤稳定运输, 提升了企业运营效率, 降低了运营成本。      

Research on a Task Planning Method for Multi-Ship Cooperative Driving

A new method for a cooperative multi-task allocation problem(CMTAP) is proposed in this paper,taking into account the multi-ship, multi-target, multi-task and multi-constraint characteristics in a multi-ship cooperative driving(MCD) system. On the basis of the general CMTAP model, an MCD task assignment model is established. Furthermore, a genetic ant colony hybrid algorithm(GACHA) is proposed for this model using constraints, including timing constraints, multi-ship collaboration constraints and ship capacity constraints. This algorithm uses a genetic algorithm(GA) based on a task sequence, while the crossover and mutation operators are based on similar tasks. In order to reduce the dependence of the GA on the initial population, an ant colony algorithm(ACA) is used to produce the initial population. In order to meet the environmental constraints of ship navigation, the results of the task allocation and path planning are combined to generate an MCD task planning scheme. The results of a simulated experiment using simulated data show that the proposed method can make the assignment more optimized on the basis of satisfying the task assignment constraints and the ship navigation environment constraints. Moreover, the experimental results using real data also indicate that the proposed method can find the optimal solution rapidly, and thus improve the task allocation efficiency.     

分布式MAS 在飞行冲突解脱中的应用研究

在自由飞行的环境下,为解决飞行冲突探测与解脱（conflict detection and resolution,CDR）问题,提出一种基于高度层、航向和速度调配的综合解脱方法,并将多 agent 系统(multi-agent system, MAS) 的分布式技术与启发式算法相结合,进行问题求解. 首先设计了分布式MAS框架结构,然后建立了飞行冲突探测模型,高度层调配模型及航向、速度调配模型,最后,综合运用了基于合同网协议的分布式算法和自适应遗传算法进行问题求解.仿真实验表明,所设计的MAS框架是可行的,同时分布式算法和自适应遗传算法的综合应用能很快找到基于高度层、航向和速度分配的近似最优解,为CDR问题提供了新的解决思路.