面向编队协同防空决策的多智能体规划方法

高技术条件下的现代海战,协同防空已成为编队防空作战的一种主要模式。针对编队协同防空决策过程中各舰艇成员之间如何协同的关键问题,将编队舰艇成员抽象为决策智能体,基于智能规划理论,提出一种面向编队协同防空决策的多智能体规划方法,能够有效的实现各舰艇决策智能体之间的协作与协调。     

复杂电磁环境下炮兵火力打击目标价值分析

为提高对复杂电磁环境下炮兵预处理目标实施火力分配的量化决策水平,运用主成分分析法对炮兵目标复杂电磁环境下价值排序的多项指标进行了聚集,利用理想点理论建立了综合优化决策模型,并进行实例分析,所得结果合理且符合客观实际,从而为作战指挥员提供了一种合理的决策依据和决策方法。     

紧迫危险下的船舶智能避碰决策研究

随着船舶的大型化、高速化以及通航水域船舶密度增加和会遇率的增大,船舶的碰撞事故时有发生,这就对避碰问题的研究提出了更高的要求.通过对紧迫危险及紧迫危险区域的深入研究,提出了紧迫危险距离的量化模型及紧迫危险下的避碰决策,并通过几何作图分析和模拟操纵仿真试验加以验证.     

HTS磁体的失超判别

高温超导磁体的失超过程比较缓慢,失超判别很困难。本文提出定性的失超判别方法：在电流恒定的前提下,若磁体电压持续上升,则认为磁体失超。对试验数据进行线性拟合,提出失超判别的数学表示形式：磁体电压的变化率dV／dt〉0。     

基于粗糙集的铁路工程项目投标决策方法研究

铁建企业项目具有规模大、周期长、技术性强等特征,使工程投标项目评估更复杂、决策难度更大.本文将盈利与竞争力提升作为铁路建筑企业项目投标决策的直接影响因素,提出了基于波士顿矩阵原理的项目分类策略,从项目因素、环境因素、自身因素和业主因素等4个方面出发构建了项目类别判定的粗糙集模型,并利用SVM(支持向量机)对已建立的粗糙集模型进行改进,证明改进模型的计算结果更加准确.根据模型分析结果对项目投标提出了若干有意义的建议,为铁路建筑企业项目投标决策提供参考.     

Terminal investment timing decisions in a competitive setting with uncertainty using a real option approach

This paper uses a real option approach to analyze terminal investment timing decisions for situations in which a port faces competition from its rivals in an uncertain market. We propose a network model to describe carriers’ cargo routing decisions and competition among rival ports. We then transform this model into a multicommodity flow problem and use the column generation algorithm to solve it. After obtaining a port’s possible future annual revenues and the potential net present value (NPV) for its terminal construction project through the network model, we adopt the expanded NPV rule and transform the investment timing decision into an optimal stopping problem. A least squares Monte Carlo simulation algorithm is proposed to find the investing probabilities for future years. The proposed models are applied to a steel cargo terminal investment case in the Port of Bengbu in Anhui province of China. The impacts on the investing probability and the expanded NPV of changes in the demand volatility, the initial investment and the port discharging rate are analyzed to provide managerial insights for port managers.     

Competitiveness prioritisation of container ports in Asia under the background of China’s Belt and Road initiative

ABSTRACT

The understanding of the competitiveness of different ports under the background of China’s “Belt and Road Initiative” (BRI) is critical for drafting appropriate plans and taking suitable actions to select the best port in the logistics supply chains. A novel Multi-Attribute Decision Analysis (MADA) was proposed for the evaluation of port competitiveness. In the developed MADA method, the interval Analytic Hierarchy Process and the projection method was combined for the evaluation of port competitiveness. Three container ports in Asia including Shanghai, Hong Kong, and Singapore were studied under the background of China’s BRI. The results demonstrate that the port of Singapore is the most competitive at the initial stage of China’s BRI, followed by Hong Kong and Shanghai in the descending order. The results were validated by sum weighted method and Technique for Order Preference by Similarity to an Ideal Solution method, and sensitivity analysis was also carried out. The competitiveness of the three ports in the next ten years were also studied with the consideration of the influences of China’s BRI, and the results reveal that Shanghai port can even exceed Hong Kong port and Singapore port if it can effectively take the advantage s of China’s BRI.     

基于VLCC的液货智能管理系统设计技术

基于超大型油船(VLCC),针对液货相关系统展开分析,完成以液货智能管理系统框架设计、液货和货舱监测报警系统集成设计、液货保护系统监测报警系统集成设计、辅助决策设计为四大关键技术的液货智能管理系统的设计研究。在智能船舶1.0的研究背景下,依托招商局能源公司VLCC实船安装的液货智能管理系统,通过对关键数据进行采集和监测分析,实现液货系统的预报警和报警功能,同时为船员提供对应辅助决策。该系统突破了常规油船液货控制及监测系统独立显示和报警的模式,实现了对液货系统状态的集成监测报警、智能管理及辅助决策功能,很大程度地提高了液货系统操作的安全性和便利性。     

Decision tree method for modeling travel mode switching in a dynamic behavioral process

As road congestion is exacerbated in most metropolitan areas, many transportation policies and planning strategies try to nudge travelers to switch to other more sustainable modes of transportation. In order to better analyze these strategies, there is a need to accurately model travelers’ mode-switching behavior. In this paper, a popular artificial intelligence approach, the decision tree (DT), is used to explore the underlying rules of travelers’ switching decisions between two modes under a proposed framework of dynamic mode searching and switching. An effective and practical method for a mode-switching DT induction is proposed. A loss matrix is introduced to handle class imbalance issues. Important factors and their relative importance are analyzed through information gains and feature selections. Household Travel Survey data are used to implement and validate the proposed DT induction method. Through comparison with logit models, the improved prediction ability of the DT models is demonstrated.     

改进可辨识矩阵的启发式知识约简及规则算法

首先提出了改进可辨识矩阵,然后对属性重要性进行了重新定义,并且将模糊聚类应用于属性重要性划分,从而在此基础上提出了一种启发式知识约简及决策规则提取算法.给出了新的不相容率的概念,用于描述知识数据库中数据不相容特征和修正提取的决策规则的决策错误率.经过实验,该算法具有优良的性能.