动态模糊神经网络在船舶航向控制器上的应用

当船舶在海湾、海峡等狭窄海域行驶时,对于船舶航向控制器的可靠性和灵活性均有较高的要求,由于船舶模型的参数受到航速和载重量的影响,因而无法保证航向控制的精确性。本文提出一种船舶模型控制与动态神经网络相结合的方法,提高船舶航向控制器的控制精度和可靠性。设计一种零稳态误差控制器对船舶航向进行控制,同时利用模糊神经网络确定闭环控制系统的极点,并用仿真证明本文提出的方法具有较高的精确性和可靠性。     

立体影像法船舱容量测量技术研究

目前国内外大容量计量应用最为广泛的是全站仪测量。其特点是单点测量精度较高,但对于较复杂或存在大曲面船舱壁的舱室而言,明显存在着采样点密度不足、人为影响因素较大、自动化程度不高等缺点。数字摄影测量的飞速发展为解决不规则复杂舱室的容量计量难题提供了新的方法。提出了一种基于结构光和近景摄影测量技术获取物体点云的便携式船舱容量测量技术,首先利用结构光为船舱内壁提供纹理信息,然后基于近景摄影测量技术获取点云,最后利用NURBS曲面拟合船舱内壁并计算体积。试验证明,该技术具有可行性和可靠性。     

PERT网络图回路的判断方法

根据PERT网络图的特点,简化了通过处理PERT图紧前紧后关联矩阵来判断网络回路的算法,并给出了相应的计算机算法和关联矩阵的存储方法.该算法对开发PERT网络图的计算机绘制软件具有一定的实际可行的应用参考价值.     

汽车电路图的识读方法

针对维修电工在从事汽车电子电器维修过程中对汽车电路图识读存在的问题,以帕萨特1．8GSI（2005年款）汽车电路为例,介绍了汽车电路图的组成,通过回路原则将电路简化,让维修电工充分熟悉整车电路图,并能迅速准确地根据汽车电路图找出故障并排除。     

一种移动式港口起重机绞车松绳压绳器

多功能移动式港口起重机为处理集装箱、重装大件和散杂货物,通常在吊钩的基础上配备集装箱吊具、抓斗或其他起重设备,因此起升绞车的防乱绳装置尤为重要.针对钢丝绳在卷筒上出现松绳后发生乱绳和跳槽问题,通过计算分析,设计一种新型绞车松绳压绳器,可防止出现乱绳现象.     

深水AUV安全系统的设计与实现

  目的  为保障高速自主式水下机器人（AUV）的航行安全,研制一套智能应急自救系统。  方法  首先,介绍应急自救系统的组成与功能,对其进行可靠性分析与设计;其次,重点研究多信道信息采集融合机制、主动应急机制、故障优先级整定机制和应急处理决策机制;再次,设计应急专家决策模型,提出一种基于离散规则应急操舵的应急处理方法;最后,基于VxWorks实时操作系统编制应急系统控制软件,并搭建半实物仿真平台进行系统联调仿真试验。  结果  试验结果验证了该应急自救机制与策略的可靠性和可行性。  结论  该应急系统弥补了传统应急手段的不足,对AUV的应急自救具有重要的借鉴作用。     

某型船主机遥控系统典型故障分析

某船航行过程中,遥控工况下主机偶发性出现转速波动,转速测量板上的转速值与机旁仪表上的转速值偏差较大,影响船舶航行安全。文章通过梳理遥控系统转速控制指令的信号走向,对主机闭环调速系统进行分析检查、排除故障,形成了典型故障的诊断方法,为后续同类系统的检修和故障排除提供参考。     

基于迭代均值组合近似模型和序贯优化与可靠性评估法的船舶结构优化设计

  目的  针对传统船舶结构可靠性优化设计中难以同时保证全局近似精度与计算效率的问题,提出一种基于少数类合成的过采样算法（SMOTE）和动态代理模型的可靠性优化策略。  方法  首先,通过最优拉丁超立方试验设计,在设计空间中选择初始样本点,构造BP神经网络模型;然后,利用全局优化算法−模拟退火法（ASA）和可靠性优化设计的单循环法（SLA）,找到当前全局最优解;最后,通过SMOTE算法增加最优解周围的样本点,更新代理模型以提高其在全局最优解附近的精度,直至优化迭代收敛。  结果  结果显示,SMOTE算法可以合成位于失效面附近的样本点,从而使BP神经网络模型更高效地拟合极限状态函数;SLA法将可靠性优化问题解耦成确定性优化问题,在保持计算精度的同时提高了计算效率。  结论  优化结果表明,采用所提方法在获得分析模型全局最优解的同时还能有效减少计算成本。     

Forecasting road traffic conditions using a context-based random forest algorithm

With the ability to accurately forecast road traffic conditions several hours, days and even months ahead of time, both travellers and network managers can take pro-active measures to minimise congestion, saving time, money and emissions. This study evaluates a previously developed random forest algorithm, RoadCast, which was designed to achieve this task. RoadCast incorporates contexts using machine learning to forecast more accurately contexts such as public holidays, sporting events and school term dates. This paper evaluates the potential of RoadCast as a traffic forecasting algorithm for use in Intelligent Transport System applications. Tests are undertaken using a number of different forecast horizons and varying amounts of training data, and an implementation procedure is recommended.     

Long distance truck tracking from advanced point detectors using a selective weighted Bayesian model

Truck flow patterns are known to vary by season and time-of-day, and to have important implications for freight modeling, highway infrastructure design and operation, and energy and environmental impacts. However, such variations cannot be captured by current truck data sources such as surveys or point detectors. To facilitate development of detailed truck flow pattern data, this paper describes a new truck tracking algorithm that was developed to estimate path flows of trucks by adopting a linear data fusion method utilizing weigh-in-motion (WIM) and inductive loop point detectors. A Selective Weighted Bayesian Model (SWBM) was developed to match individual vehicles between two detector locations using truck physical attributes and inductive waveform signatures. Key feature variables were identified and weighted via Bayesian modeling to improve vehicle matching performance. Data for model development were collected from two WIM sites spanning 26 miles in California where only 11 percent of trucks observed at the downstream site traversed the whole corridor. The tracking model showed 81 percent of correct matching rate to the trucks declared as through trucks from the algorithm. This high accuracy showed that the tracking model is capable of not only correctly matching through vehicles but also successfully filtering out non-through vehicles on this relatively long distance corridor. In addition, the results showed that a Bayesian approach with full integration of two complementary detector data types could successfully track trucks over long distances by minimizing the impacts of measurement variations or errors from the detection systems employed in the tracking process. In a separate case study, the algorithm was implemented over an even longer 65-mile freeway section and demonstrated that the proposed algorithm is capable of providing valuable insights into truck travel patterns and industrial affiliation to yield a comprehensive truck activity data source.