求解多峰性函数全局最优解的进化算法及其应用研究

本又针对简单遗传算法（SGA）在解决多峰性函数最优化问题存在的不足，提出了一种分配区间型进化算法，能够求出多峰性函数所有全局最优解及多个局部最优解。通过十几个多峰性函数与工程实例的数值实验，验证了算法的正确性。对简易海洋平台进行了疲劳可靠性优化设计为算例，取得了满意的结果。     

基于稳性实时计算技术的船舶破损智能扶正系统研究

基于船舶稳性实时计算技术研究船舶实时状态三维模型数字化算法用于快速计算船舶的大倾角稳性、破舱稳性和平衡浮态。参考遗传算法研究船舶破损智能扶正方案生成算法来实现智能生成扶正方案功能。然后运用上述两种核心算法设计船舶破损智能扶正系统软件,为船舶在突发破损事故时提供一套包含压载水调拨措施与步骤建议的智能扶正方案,提高船舶破损事故的处理能力。     

基于无线传感器网络的运动目标检测动态聚类图

有效的目标跟踪需要积极的传感器节点对运动目标群实行跟踪。与单目标跟踪相比,聚类在效能上有显著提高。本文提出准确的相干和非相干运动模式下目标的聚类,采用隐式动态时间框架来评估在创建连接组件加权图的目标关系史。该算法采用目标跟踪中定位算法的关键特征,即估计当前和预测的位置来确定移动目标的方向和距离的关系。模拟结果显示,通过动态调整历史窗口大小和预测目标之间的关系,可以显著提高聚类的准确性并减少运算时间。     

一种免疫算法的改进

针对一种免疫算法在求解多模态函数优化问题的不足,利用基于相似结构的小生境技术和近优淘汰算子对免疫算法加以改进.通过仿真实验,本文分析了交叉算子、变异算子及近优淘汰算子对算法的影响.仿真结果表明改进后的算法的性能有明显的提高.     

Transit network design with allocation of green vehicles: A genetic algorithm approach

The use of fossil fuels in transportation generates harmful emissions that accounts for nearly half of the total pollutants in urban areas. Dealing with this issue, local authorities are dedicating specific efforts to seize the opportunity offered by new fuels and technological innovations in achieving a cleaner urban mobility. In fact, authorities are improving environmental performances of their public transport fleet by procuring cleaner vehicles, usually called low and zero emission vehicles (LEV and ZEV, respectively). Nevertheless there seems to be a lack of methodologies for supporting stakeholders in decisions related to the introduction of green vehicles, whose allocation should be performed since the network design process in order to optimize their available green capacity.In this paper, the problem of clean vehicle allocation in an existing public fleet is faced by introducing a method for solving the transit network design problem in a multimodal, demand elastic urban context dealing with the impacts deriving from transportation emissions.The solving procedure consists of a set of heuristics which includes a routine for route generation and a genetic algorithm for finding a sub-optimal set of routes with the associated frequencies.     

可变编组动车组运维一体化帕累托前沿分析

动车组运用和检修是铁路运输生产的重要过程,占据很大的成本比例. 为与客流需求相匹配,在未来实现跨线动车组列车在某些枢纽站组合和分解存在可能,充分考虑组合动车组类型一致性,动车组在不同运行线进行重联与分解的接续条件,动车组进行一二级修的里程和时间标准等,以动车组的正常接续和空走接续时间里程费用、一二级维修作业费用、动车组运用费用和动车组接续时间费用之和最小及动车组空走费用占比最小为双目标,构建基于可变编组条件下的动车组运用和维修一体化模型方法.应用改进的非支配排序遗传算法求解,将目标值进行帕累托前沿分析,发现两者很难同时达到最优.模型的计算结果体现了动车组担当长编组运行线任务前后的组合和分解过程,同时也进一步分析了在动车组类型归一化或者动车组维修地点不受限情况下动车组运用数量的变化,反应了相关运行参数对结论的影响.     

基于神经网络和遗传算法的系泊线长度参数优化

摘 要: 针对多成分系泊线三段长度如何取值的问题,采用一种基于神经网络和遗传算法对深海多成分锚泊系统长度进行优化。应用AQWA软件计算多点系泊FPSO,其时域结果直接用于训练BP神经网络。从而利用神经网络的非线性映射功能构建替代锚泊时域计算网络,大大缩短了优化所需的时间。以FPSO最小平面运动值为目标函数,锚链破断强度作为约束条件,采用遗传算法优化系泊长度。计算结果表明,与传统设计的锚泊长度相比,优化后FPSO在各个浪向下纵荡横荡值均能减少20%以上。 关键词:系泊;神经网络;遗传算法;优化     

基于HMM-SVR的船舶动力设备故障模式识别与状态预测研究

船舶动力设备因故障监测信号样本少、变化缓慢且数据特征呈非线性,使得设备故障模式的准确识别和状态预测比较难。鉴于此,文章研究了基于隐马尔科夫模型的故障模式识别方法,利用该模型将微弱变化的信号特征转换为变化较大的对数似然概率对故障模式实现有效识别。在此基础上进一步提出基于HMM-SVR的设备状态预测模型,将遗传算法用于支持向量回归模型参数寻优,并结合隐马尔科夫模型,实现对设备状态的预测。对船用柴油机进行仿真,结果表明上述模型具有较高的识别率,能准确预测船舶动力设备的当前状态。     

钢筋混凝土梁遗传算法优化设计

遗传算法是建立在自然遗传学机理基础上的参数搜索方法。通过介绍遗传算法在钢筋混凝土梁结构参数求解中的应用,利用遗传算法对钢筋混凝土梁进行优化,建立钢筋混凝土矩形截面梁的满足约束、造价最低优化模型及相应的适应度函数,采用二进制编码,通过执行遗传算法的选择、交叉和变异算子,实现对结构的优化设计,并分析了算例,成功求解了钢筋混凝土梁结构非线性优化设计模型。实例结果表明:该法可以节省时间,优化结果准确并可以降低造价。     

Global cutting-path optimization considering the minimum heat effect with microgenetic algorithms

This article considers microgenetic algorithms (GAs), which explore in a small population with a few genetic operators, for cutting-path optimization problems. The major difference between GAs and simple genetic algorithms (SGAs) is how to make a reproductive plan for an improved searching technique because of population choice. It is shown that GAs implementation reaches the near-optimal region much earlier than the SGAs approach, and the GAs give a better solution than simulated annealing (SA). The main objective was to determine what temperature distribution can be obtained from the solution of a travelling distributed heat source. The solution of the travelling heat source on nested raw plate provides information about the vertices of each nested part of the raw plate. From the fact that the initial temperature at a piercing point strongly depends on the heat flow which stems from the previous cutting contour, the temperature of all piercing points must be lower than the critical temperature after each cutting of the components of a part. The critical temperature is identified as the mechanical melting temperature of steels. A heuristic back-tracking method is introduced to find the near-optimum cutting path considering the minimum heat effect on deformation. The heuristic back-tracking method is incorporated with the GAs.