基于分阶段粒子群优化算法的船舶横向运动水动力参数辨识

提出了一种基于分阶段粒子群优化算法的船舶横向运动参数辨识问题。针对船舶横向水动力参数多、参数之间耦合度高的特点,提出了一种计算参数敏感性系数的方法,并依据敏感性系数对参数进行了分类,采用分阶段粒子群优化算法对参数进行辨识。对船舶横向运动参数辨识问题的求解结果表明,该算法能够快速地辨识出满足精度要求的船舶横向运动参数,验证了算法的有效性。     

基于粒子群优化的飞行器地磁相关匹配新算法仿真

鉴于飞行器地磁相关匹配算法高精度、高可靠性和高实时性要求,本文将影响地磁相关匹配算法的相似性度量函数、地磁特征参量和搜索策略综合考虑.相似度度量函数采用归一化积相关函数、地磁特征参量选用归一化的地磁场总强度,将粒子群优化算法引入匹配区搜索.基于海洋实测地磁场数据进行了实验室仿真验证.实验结果表明,在匹配概率、匹配精度与...     

高速公路挖方边坡优化设计智能方法与应用

文章针对高速公路挖方边坡设计的特点和要求,结合依托工程实例,阐述了基于支持向量机和粒子群算法的智能方法在高速公路挖方边坡优化设计中的具体应用,为高速公路挖方边坡优化设计提供参考。     

Monte Carlo Simulation of Electron Swarms Parameters in c-C4F8/CF4 Gas Mixtures

The swarm parametes for c-C4F8/CF4 mixtures, including the density-normalized effective ionization coefficient, drift velocity and mean energy were calculated using Monte-Carlo method with the null collision technique. The overall density-reduced electric field strength could be varied between 150 and 500 Td,while the c-C4F8 content in gas mixtures is varied in the range of 0-100%. The value of the density-normalize deffective ionization coefficient shows a strong dependence on the c-C4F8 content, becoming more electronegative as the content of c-C4F8 is increased. The drift velocity of c-C4F4/CF4 mixtures is more affected by CF4. The calculated limiting field strength for c-C4F8/CF4 mixtures is higher than that of SF6/CF4.     

基于多目标粒子群优化算法的某轻型商用车操纵稳定性优化研究

针对某轻型商用车稳态回转时侧倾度偏大的问题对其悬架进行优化改进。基于ADAMS/car搭建整车多体动力学模型,通过前悬架反向平行轮跳试验、后悬架理论计算验证了悬架仿真模型的准确性。进行整车稳态回转工况和转向盘中间位置转向工况仿真分析,结果表明,车身侧倾度偏高。为实现操纵稳定性优化分析的流程自动化,提出了基于modeFRONTIER的联合仿真方法。以悬架设计参数为优化变量,以汽车的侧倾度与横摆角速度响应滞后时间为优化目标,采用拉丁超立方试验设计方法拟合得到混合代理模型,并结合多目标粒子群优化算法对悬架系统进行多目标优化,获得了悬架系统优化方案。优化结果显示,在不影响平顺性的前提下,汽车车身侧倾度降低了13.93%,横摆角速度响应滞后时间降低了2.75%,整车操纵稳定性得到了提升。     

典型工况下的燃料电池船舶复合储能系统设计

针对燃料电池船的电能质量品质不高、蓄电池使用寿命短等问题,设计了由超级电容、磷酸铁锂电池组成的复合储能系统,并提出了基于功率分流式的能量管理策略。在MATLAB/Simulink环境下建立系统仿真模型,并采用自适应粒子群算法调用仿真模型,对复合储能系统的容量配置与能量管理策略的参数进行联合优化。仿真结果表明：优化后的复合储能系统可以满足船舶典型工况需求,并且能够缓冲负载波动对燃料电池与磷酸铁锂电池的冲击,使燃料电池工作在高效率区间,机动工况下船舶能量效率提高了3.17%;磷酸铁锂电池的充放电过程得到优化,能延长其使用寿命;母线电压波动减小,提高了电能质量。     

基于SAPSO-BP网络模型的港口潮汐实时预报

为了提高港口码头潮汐预报的精度,提出一种自适应变异的粒子群优化算法SAPSO,将SAPSO优化算法与BP神经网络结合,用以潮汐水位的实时预报。SAPSO-BP网络模型运用自适应变异的PSO算法优化BP神经网络的网络参数,克服了传统BP神经网络所具有的对初始权值阈值敏感、容易陷入局部极小值的缺点,最后选用Isabel港口的实测潮汐值数据进行潮汐水位的实时预报仿真试验,用以验证SAPSO-BP预测模型的实用性和可靠性。     

船队规划数学模型及一种新的规划方法的研究

从船运公司船队规划的概念及意义人手．建立了船队规划的数学模型。并分析了传统船队规划方法的优缺点，采用改进的离散粒子群算法进行大规模的船队规划计算研究。该方法既避免了线性规划算法出现的购买船艘数不为整数的问题．又避免了动态规划方法在进行大规模船队规划时出现的”维数灾”问题。通过实例表明提出的算法适用于多阶段船队规划数学模型。     

Time-dependent fuzzy random location-scheduling programming for hazardous materials transportation

The tremendous use of hazardous materials has promoted the economic development, which also brings about a growing risk causing a widespread concern. In this work, we consider a location-scheduling problem on hazardous materials transportation under the assumption that transportation risks are time-dependent fuzzy random variables. First, we formulate a scheduling optimization model and design a fuzzy random simulation based genetic algorithm to optimize the departure time and dwell times for each depot–customer pair. Then we establish an expected value model and design a modified particle swarm optimization algorithm to minimize the en route risks and site risks. Finally, numerical examples are given to illustrate the effectiveness of the proposed models and algorithms.     

Soft Radial Basis Cellular Neural Network (SRB-CNN) based robust low-cost truck detection using a single presence detection sensor

This paper does present a comprehensive concept for a robust and reliable truck detection involving solely one single presence sensor (e.g. an inductive loop, but also any other presence sensor) at a signalized traffic junction. Hereby, two operations modes are distinguished: (a) during green traffic light phases, and (b) a much challenging case, during red traffic light phases. First, it is shown how difficult the underlying classification task is, this mainly due to strongly overlapped classes, which cannot be easily separated by simple hyper-planes. Then, a novel soft radial basis cellular neural/nonlinear network (SRB-CNN) based concept is developed, validated and extensively benchmarked with a selection of the best representatives of the current related state-of-the-art classification concepts (namely the following: support vector machines with radial basis function, artificial neural network, naive Bayes, and decision trees). For benchmarking purposes, all selected competing classifiers do use the same features and the superiority of the novel CNN based classifier is thereby underscored, as it strongly outperforms the other ones. This novel SRB-CNN based concept does satisfactorily fulfill the hard industrial requirements regarding robustness, low-cost, high processing speed, low memory consumption, and the capability to be deployed in low cost embedded systems.