基于并行聚类算法的无监督异常检测研究

为满足高效聚类大规模数据集的要求,该文提出一种基于k均值算法的并行聚类算法,该并行算法能使聚类时间随节点主机数目的增多,呈近似线性递减。为了更好地平衡检测率与误报率,文章又提出了基于平方误差最小的重定位算法,相比于李娜等人提出的算法,该重定位算法使检测率提升了5%,误报率降低了1.1%。实验结果表明,该文算法不但能够提高聚类效率,而且能够更加有效地检测出已知和未知攻击。     

面向多约束的船舶组立构件建造作业调度方法研究

为了提高船舶中小组立等中间产品建造作业调度能力，提升船舶建造效率，提出面向多约束的船舶组立建造作业调度方法。首先，分析船舶组立建造的工艺流程和作业调度方法，综合考虑机器小组、工艺和交货期等多种约束条件，以建造周期最短为调度目标，建立船舶组立建造作业调度数学模型；其次，综合运用算法分解策略及调度规则，设计改进的最短作业优先调度算法实现模型求解；最后，以某船厂建造车间一定生产周期（17天）的中小组立先行中日程计划为对象，验证该方法的有效性和实用性。研究结果表明，所提出的面向多约束的船舶组立建造作业调度方法相较于当前的调度方法，排产周期压缩22小时，即缩短了原有周期的16.18%，有效提高了生产计划排产和作业调度效率。     

基于变权值令牌环模型的UUV推进系统网络研究

本文针对UUV(无人水下航行器)推进系统搭建了Modbus通信网络,实现对航行器电力推进系统的网络控制。由于标准的Modbus通信协议具有实时性较低的问题,提出了一种具有优先级的令牌环模型,通过令牌传递的方式协调各从站并行处理数据,从而大大减少了网络通信的延时。在此基础上扩展出了变权值令牌环模型,可满足应对不同工况及时修改各从站延时的需求,并能以牺牲一定的传输实时性为代价避免处理大量数据时低优先级从站数据彻底丢包的现象出现。仿真实验验证了所提出的Modbus改进模型的有效性。     

基于改进Apriori算法的船用柴油机装配工艺文件关联规则挖掘研究

柴油机作为船舶关键部件之一,其装配工艺设计的合理与否与船舶的整体性能直接相关。针对企业历史装配工艺文件不能充分为新机型装配任务发布时装配工艺设计提供支撑的问题,提出一个基于关联规则挖掘的柴油机装配工艺规则挖掘系统,该系统充分利用已有装配工艺文件,结合数据挖掘技术,对文件进行挖掘分析,建立装配规则库,为后续装配工艺智能设计提供数据支持。本文提出一种改进的Apriori算法,建立了关联规则挖掘的数学模型和基于自定义词典装配工艺文件分词算法,将分词处理过后的文件可以作为数据挖掘算法的输入,并在传统Apriori算法的基础上提出一种改进的Apriori算法,该算法核心思想是在对候选频繁事务集剪枝时,降低算法的时间复杂度,从而提高挖掘效率直到获得柴油机装配工艺文件中的关联规则。最后以某船厂的历史机型柴油机气缸盖装配工艺文件为例,验证了改进Apriori算法在挖掘柴油装配工艺文件关联规则时的可行性和有效性。     

Path optimization for marine vehicles in ocean currents using reinforcement learning

This study proposes a path planning algorithm for marine vehicles based on machine learning. The algorithm considers the dynamic characteristics of the vehicle and disturbance effects in ocean environments. The movements of marine vehicles are influenced by various physical disturbances in ocean environments, such as wind, waves, and currents. In the present study, the effects of ocean currents are the primary consideration. A kinematic model is used to incorporate the nonholonomic motion characteristics of a marine vehicle, and the reinforcement learning algorithm is used for path optimization to generate a feasible path that can be tracked by the vehicle. The proposed approach determines a near-optimal path that connects the start and goal points with a reasonable computational cost when the map and current field data are provided. To verify the optimality and validity of the proposed algorithm, a set of simulations were performed in simulated and actual ocean current conditions, and their results are presented.     

A combined tramp ship routing,fleet deployment,and network design problem

In this paper, a tramp ship routing model of fleet deployment in a hub-and-spoke network is presented. This model simultaneously determines the selection of hubs, the assignment of spokes to hubs, the deployment of feeder-containerships as well as containership routing between spokes and spokes, hubs and spokes, and hubs and hubs. Even though some parts have been studied, this complex combination of shipping problems has never been addressed. Because the problem is NP-hard, a genetic algorithm (GA) with local search is proposed. In the algorithm, a cut-off procedure is applied to fleet deployment in a sub-route strategy. A number of randomly generated problem instances are solved by both a mathematical program and the GA with local search. A simple but realistic heuristic algorithm is also developed. Both the GA with local search and the heuristic algorithm are used to solve a number of real case instances. A comparison of the results shows the efficiency of the GA with local search. The developed model can be used as a route-decision support tool for shipping companies that provide long-haul shipping services in a hub-and-spoke network.     

An integrated programming model for storage management and vehicle scheduling at container terminals

In this paper, we study the optimization of yard operations, which are critical for the terminal efficiency. A linear mixed integer programming (MIP) model is proposed for scheduling different types of equipment and planning the storage strategy in an integrated way. We also investigate a nonlinear mixed integer programming (NLMIP) model to reduce the number of constraints and the computational time. A set of numerical results are carried out for the comparison between the linear model and the nonlinear model. Finally, we propose a genetic algorithm for the MIP model to illustrate how large scale problems can be solved and to show the effect of different factors on the performances of the optimization model.     

A two-phase tabu search approach to scheduling optimization in container terminals

An optimization model for scheduling of quay cranes （QCs） and yard trailers was proposed to improve the overall efficiency of container terminals. To implement this model, a two-phase tabu search algorithm was designed. In the QCs scheduling phase of the algorithm, a search was performed to determine a good QC unloading operation order. For each QC unloading operation order generated during the QC＇s scheduling phase, another search was run to obtain a good yard trailer routing for the given QC＇s unloading order. Using this information, the time required for the operation was estimated, then the time of return to availability of the units was fed back to the QC scheduler. Numerical tests show that the two-phase Tabu Search algorithm searches the solution space efficiently, decreases the empty distance yard trailers must travel, decreases the number of trailers needed, and thereby reduces time and costs and improves the integration and reliability of container terminal operation systems.     

Path-planning algorithm for ships in close-range encounters

Efficient maritime navigation through obstructions at close range is still one of the many problems faced by mariners. The increasing traffic densities and average cruise speed of ships also impede the collision avoidance process by reducing the time available for decision making. This study develops a path-planning algorithm that determines an optimal navigation path for ships in close-range encounters, using known and predicted data about the traffic and environment. An improved ship dynamic model has also been developed to better approximate the ship movement under external influences, and the algorithm was evaluated with a set of test cases simulating various traffic scenarios typically encountered at close range. Since the method is based on evolutionary algorithm, the algorithm behaviours were evaluated statistically, where properties such as consistency and practicality of the algorithm outputs are discussed.     

A genetic algorithm for the hub-and-spoke problem applied to containerized cargo transport

A genetic algorithm for the hub-and-spoke problem (GAHP) is proposed in this work. The GAHP configures a hub-and-spoke network with shuttle services for containerized cargo transport. For a fixed number of hubs, it determines the best network configuration of hub locations and spoke allocations that minimizes the total costs of the system. The GAHP has a simple individual structure with integer number representation, where spokes, their allocations, and hub locations are easily recognized. Due to the characteristics of the problem, which has fixed number of hubs, rearrangements should be performed after every process. The GAHP rearrangement process includes improvements of individual structures, resulting in an improved population. Before applying the GAHP to the container transport network problem, the algorithm is validated using the Civil Aeronautics Board data set, which is extensively used in the literature to benchmark heuristics of hub location problems. To illustrate an example of a hub-and-spoke network with shuttle services, a study case with 18 ports is analyzed.     

基于自适应变异 PSO-BP算法的船舶横摇运动预测

为了准确高效预测船舶在海上的航行状态,以保证人员、货物和船舶的安全,提出一种自适应变异的粒子群优化算法（self-adapting particle swarm optimization algorithm,SAPSO）,将该算法与误差反传（back propaga-tion,BP）神经网络结合。SAPSO-BP预测模型使用SAPSO算法优化BP网络的网络参数。克服传统BP神经网络对初始权值阈值敏感,容易陷入局部极小值的缺点,同时也克服了传统PSO算法早熟收敛、搜索准确度低及迭代效率低等缺点。运用该模型对科研教学船“育鲲”轮在海上航行的横摇情况进行实时预测实验,验证该方法的可行性与有效性具有较高的预测精度。     

基于自主平台的NMEA2000协议改进和优化

[目的]为了拓展NMEA2000通信协议标准的应用范围,优化、提升网络传输效率,研制基于自主可控平台的NMEA2000数据采集传输系统。该系统可将非认证设备接入NMEA2000网络并提升其传输效率。[方法]以GD32F207芯片为微控制器并在与RT-Thread嵌入式实时操作系统结合的自主可控平台上,根据各厂商原有设备协议和NMEA2000协议标准,采用数据映射的方式,完成协议格式转换。利用NMEA2000数据帧未使用的标识符域和优先级动态调整,提升NMEA2000网络传输效率。[结果]基于自主可控平台的NMEA2000板卡实现了非认证设备的接入,优化后网络传输效率随着传输字节数的不同有着不同程度的提升,网络实时性与可靠性也有所提升。[结论]所提数据采集传输系统具有多种接口,能够完成非认证设备的接入,网络数据传输效率、实时性和可靠性能够满足船载设备间数据传输的需要。     

远程UUV指挥控制流程分层Petri网建模及延时分析

对于控制节点多、流程复杂的远程UUV指挥控制流程建模及延时分析问题,传统建模方法往往难于对其进行详细描述和分析.文中建立远程UUV指挥控制流程分层延时Petri网模型,采用基于Petri网的层次化建模方法提升模型对复杂流程的表达能力,将变迁引入时间参数,使模型具备对时间的描述和分析能力,并给出不同结构的延时计算方法.仿真结果表明所建模型可用于对远程UUV指挥控制流程进行分析和计算,分析方法正确、适用性好,可为远程UUV指挥控制系统评价及完善提供参考和技术支持.     

Analysis of solution findings in the conceptual design of function structures

In the conceptual stage the function design process is realized by the computer aided application. After surveying on the function specification methods and the function modeling, a computer aided function design environment is analyzed. Subsequently based on a module library and principle catalogue, a solution finding process as a part of conceptual design is proposed for a creative design. In addition, a search algorithm to find the solution of adaptable function structure is also discussed. The concepts proposed in this paper can support the subsequent design stages, especially simulation for checking the function structure defects.     

基于高级遗传算法的船舶模型参数辨识

提出一种以二阶K-T方程为基础，并基于高级遗传算法的船舶参数辨识算法，能有效地保证了算法的收敛性和全局优化能力，避免陷入局部最优解。并引入噪声参数，再用基于多局部种群的遗传算法进行迭代计算，将残差白噪声化。最终将该方法与传统的广义最小二乘算法相比较，得到了较为理想的船舶参数。通过对采集的仿真数据和实际自动舵数据的辨识结果验证了该方法在实际工程应用中的可行性和有效性。     

多Agent的船舶电力系统网络重构技术

Reconfigurability of the electrical network in a shipboard power system (SPS) after its failure is central to the restoration of power supply and improves survivability of an SPS. The navigational process creates a sequence of different operating conditions. The priority of some loads differs in changing operating conditions. After analyzing characteristics of typical SPS, a model was developed used a grade III switchboard and an environmental prioritizing agent (EPA) algorithm. This algorithm was chosen as it is logically and physically decentralized as well as multi-agent oriented. The EPA algorithm was used to decide on the dynamic load priority, then it selected the means to best meet the maximum power supply load. The simulation results showed that higher priority loads were the first to be restored. The system satisfied all necessary constraints, demonstrating the effectiveness and validity of the proposed method.     

从CATIA到TRIBON的板架结构数据转换方法

船舶行业不同CAD软件间的数据交换是个倍受关注的问题,从CATIA到TRIBON的数据转换是其中一个重要的环节。通过对船舶CAD软件CATIA与TRIBON之间模型数据结构的分析研究,开发了从CATIA到TRIBON的船体板架结构的数据转换方法。该方法首先分析研究CATIA结构树,然后通过对CATIA系统的二次开发提取板架结构几何与属性信息,其中可以通过控制提取数据的精度来提高数据转换过程的精度;利用外挂软件将数据信息合并到一个文档,按照数据映射关系将其转换为能够在TRIBON中进行建模的格式文件;开发TRIBON系统建模模块,最终迅速有效地完成数据的转换。几个板架结构的转换实例说明该方法能为两个不同CAD软件间的数据交换提供一种有效的工具。     

基于AODEsr分类的负载优先级评估

负载管理是舰船电力系统最重要的技术之一。要对负载合理分配电能,以实现能量最优调度的目标,首要的问题是对负载的优先级做出合理的评估,分析了利用层次分析法进行负载优先级评估的不足,提出了一种基于AODEsr分类的属性权重评估算法,有效地将专家经验与客观数据本身的特性结合在一起。实验结果表明：舰船电力系统负载优先级主要受需求紧迫性和易损性两种属性的影响,各种算法的结果均与上述结论基本保持一致,证明了算法的正确性。     

一种基于控制图的燃气轮机压气机性能评价方法

介绍了对象燃气轮机的结构、状态临测系统,并存MATLAB软件仿真平台上开发了基于喻测参数的燃机性能计算程序,发现随着机组工作时间的累积,燃气轮机压气机效率有着明显的降级。为了科学有效地评价降级,将工程管理中的控制图法运用剑压气机性能的评价工作中,分析了机组某次停机水洗前后的性能变化。以压气机效率为控制图特征值,发现水洗前压气机效率处于“失控状态”,水洗后爪气机效率重新回到“受控状态”。结果表明：控制图法可以反映燃气轮机运行过程中的性能变化情况,依据控制图法判断机组工作过程是否异常,可为燃气轮机的维护工作提供帮助。     

Power efficient formation configuration for centralized leader–follower AUVs control

Autonomous underwater vehicles (AUVs) have rapidly developed in the last few decades due to their autonomous properties in the investigation of an underwater environment. The goal of this paper is to develop a power efficient formation control for the cooperative motion of AUVs with a support vessel as a leader. In this paper, a kinematic algorithm for the joint motion of an AUV with a support vessel was developed and that algorithm was expanded for the formation of AUVs. The AUV yaw, surge and sway control loops were designed for that purpose. The complexing navigation system structure for the AUV was also developed. Simulation results demonstrated efficiency of the proposed kinematic algorithm for the joint motion of AUVs. Also, influence of lateral ocean current was considered. After development of the centralized leader?Cfollower formation control for the group of AUVs with a support vessel as a leader, we optimized a formation configuration in terms of power efficiency. Drag forces caused by AUV motion in the water can significantly influence power consumption. We investigated the relationship between the AUV's formation configuration, underwater coverage efficiency, communication quality and power consumption. As a result of research, we proposed a power efficient formation configuration for typical underwater operations. As a result, the effect of the AUV formation configuration on the power consumption was investigated and a trade-off solution for the optimal AUV positions in formation with minimal energy consumption, high coverage efficiency and small communication power consumption was derived.