偏最小二乘回归在舰船维修费用预测中的应用

考虑到偏最小二乘回归方法在处理小样本多元数据方面具有独特的优势,分析了影响舰船维修费用的因素,结合变量投影重要性分析方法对影响因素进行筛选,提出用偏最小二乘回归方法建立舰船维修费用预测模型。通过实例进行计算,用历史数据预测舰船维修费用,在数据样本量小的情况下,预测结果较多元回归方法精度高。     

全寿命费用的DEA优化逐步回归分析法及其应用

在全寿命费用估算建模领域,逐步回归能对多因素进行筛选,克服了建模因素之间的多重相关性对最小二乘估计的干扰。逐步回归分析法本质上是对数据平均趋势的估算,无法避免“由失真数据得到无效模型”的根本问题。为此,提出用数据包络分析（DEA）优化逐步回归的建模方法,用DEA方法对数据进行评价,剔除无效数据,将有效的数据用来逐步回归建模。该方法能有效克服干扰数据对提取成分的影响,弥补逐步回归方法的不足。通过实例计算并与逐步回归、多元线性回归比较分析,DEA优化逐步回归建模精度为2．64％,高于逐步回归的3．39％和多元线性回归的3．49％,具有实用价值。     

港口集疏运网络流量预测模型

通过对集疏运网络流量的经济相关性、分布非均质性、动态性等特征的分析.指出港口集疏运网络流量既受腹地货源量、港口竞争等经济因素的影响,又受通道费用、网络容量等物流因素的影响.建立了港口集疏运网络流量的双因素两阶段预测模型:第一阶段考虑宏观经济发展趋势、腹地GDP、外贸进出口总额、港口建设投资额等经济因素,利用统计回归方法建立腹地货源量与港口吞吐量的预测模型;第二阶段考虑通道费用、网络流量等物流因素,在给定货源量与港口吞吐量的基础上,建立基于用户流量——费用均衡的网络流量分配模型.     

基于Matlab软件算法的引信储存寿命预测

文章分析了引信长期储存失效的影响因素,运用Matlab软件分别得到不同地区引信储存寿命与仓库温湿度关系的拟合曲线,建立了线性、交叉回归、纯二次三种回归模型,并通过rstool命令求取了相关系数,最后进行了对残差检验。结果表明：纯二次模型残差最小,拟合效果最好。     

基于主成分和支持向量机的设备寿命周期费用建模方法

提出运用主成分分析法和支持向量机技术相结合的分析法来减少影响设备寿命周期费用因素的数量,降低建模的难度。利用主成分分析法来约简影响因素,采用支持向量机技术来建模,减少非线性数据带来的不确定性。采用Matlab中的支持向量机工具箱,建立回归估算模型,并以实例分析验证本方法的可行性。     

基于径向基网络的船舶临修费用预测研究

临修对维持装备完好率具有重要意义，准确掌握船舶临修费用对于科学筹划其维修保障具有重要作用。由于船舶临修费用的影响因素较多，相互关系复杂，准确预测临修费用难度较大。文章应用基于径向基网络的预测模型对单船年度临修费用进行了研究，结果表明，该方法对大样本情况的预测较为理想。     

基于Bellman-Ford算法的配电网节能控制研究

为解决大量分布基于改进最小费用路算法的电源并网场景下的主动配电网节能控制优化问题,通过建立与配电网相应的图论模型,将潮流管理问题转化为寻求图论模型最小费用流的问题。鉴于传统最小费用路算法具有结构复杂、计算繁琐等缺点,论文提出了一种基于Bellman-Ford算法改进的最小费用流计算,该算法采用容量修改方式取代传统算法中的流量修改方式,大大简化了寻找图论模型中最小费用流的计算。应用Matlab建立仿真模型并进行仿真,仿真结果表明,改进的最小费用流Bellman-Ford算法应用于主动配电网潮流管理能够实现潮流优化,可以有效解决分布式电源(DG)并网造成的潮流阻塞问题,最终达到配电网节能控制的目的。     

舰船批量建造费用的组合预测应用研究

研究了舰船批量建造费用的组合预测问题.首先依据舰船批量建造费用的变化特点,采用生长曲线法、数据平滑法、灰色分析法对费用进行预测,然后运用支持向量机的回归算法对3种预测方法的预测值进行有机组合,建立了舰船批量建造费用的组合预测模型,最后利用样本数据分析了一个参数变化对预测性能的影响,给出了支持向量机参数选择的依据.仿真结果表明,该模型能明显提高系统预测的精度和稳定性,可用于舰船批量建造费用的预测和估算,具有较大的实用价值.     

二阶波浪漂移力的回归分析

二阶波浪载荷的预报对动力定位能力评估具有重要意义。对二阶波浪载荷的预报,通常可采用模型试验和数值模拟的方法。模型试验费用昂贵,数值模拟时面元划分的合理性对计算结果的影响很大,且模型试验和数值模拟周期都相对较长。采用压力直接积分法进行系列船型的二阶波浪漂移力计算,在此基础上,采用模长界限控制的正交化方法的多元多项式回归分析,给出二阶波浪漂移力的回归公式,并进行了验证分析。验证分析表明回归公式置信区间为0.95。     

船东节省与控制港口使费策略

本文结合港口使费的结构,分析影响港口使费的因素,提出船东节省与控制港口使费成本的策略。船舶、船舶载运的货物在港发生的各种费用通常统称为港口使费。港口使费通常分为两大类:港口费用和货物费用。影响港口使费的因素很多,使得港口使费具有很强的变动性,这就为船东在节省和控制港口使费方面提供了广阔空间。     

Exploring vessel-price dynamics: the case of the dry bulk market

We investigate second-hand vessel price heterogeneity. Based on a sample of 5,591 purchase and sale transactions in the dry bulk sector over the period 1998–2016, we deploy a nonparametric regression technique to assess the determinants of vessel price and vessel price variability. Next, we use quantile regression to estimate the effect of regressors (sources of heterogeneity) at different parts of the vessel price distribution. We find evidence that main sources of vessel price heterogeneity are the age of the ship (the older the vessel the higher its maintenance cost), the 3-month LIBOR (reflecting the cost of financing) and the annual charter rate (revenues from operation). Their influence is stronger at all higher quantiles (periods of expansion) and the median of the vessel price distribution.     

Price formation of dry bulk carriers in the Chinese shipbuilding industry

In this paper, we present, for the first time, the price formation of Chinese dry bulk carriers based on the historical shipbuilding contract prices. Price determinants include generic market factors as well as Chinese elements. Principal component regression analysis is employed as the solution for the multicollinearity problem among explanatory variables. The result indicates that the time charter rate has the most significant positive impact on shipbuilding price; increases in three other factors, namely the cost of shipbuilding, the price-cost margin and the shipbuilding capacity utilisation, have positive influences in the descending order. Unlike the traditional perception of newbuilding price that shipbuilding cost has the most significant effect, we assert that the most important role the time charter rate plays is attributed mainly to the ‘China Factor’ in the bulk carrier sector. In addition, simulations are performed to investigate what would happen to the Chinese dry bulk carrier prices under changes in the time charter rate and shipbuilding cost. The findings are useful for Chinese shipyards, shipowners and emerging shipbuilders.     

Measuring the Cost of Beach Retreat

We estimate the cost over the next 50 years of allowing Delaware's ocean beaches to retreat inland. Since most of the costs are expected to be land and capital loss, especially in housing, we focus our attention on measuring that value. We use a hedonic price regression to estimate the value of land and structures in the region using a data set on recent housing sales. Then, using historical rates of erosion along the coast and an inventory of all housing and commercial structures in the threatened coastal area, we predict the value of the land and capital loss assuming that beaches migrate inland at these historic rates. We purge the losses of any amenity values due to proximity to the coast, because these are merely transferred to properties further inland. If erosion rates remain at historic levels, our estimate of the cost of retreat over the next 50 years in present value terms is about $291 million (2000$). The number rises if we assume higher rates of erosion. We compare these estimates to the current costs of nourishing beaches and conclude that nourishment make economic sense, at least over this time period.     

Supply and demand of new oil tankers

This paper examines the world-wide supply and demand for new oil tankers. A simultaneous supply and demand model is developed and estimated using two-stage least squares techniques and empirical data from 1972 to 1983. The relationships between tanker newbuilding orders and prices, and other relevant market factors are analysed. Major factors affecting the tanker new building market are identified. The results indicate that: oil price and second-hand tanker price are predominant factors influencing future newbuilding demand; a moderate decrease in laid-up tonnage would not induce a significant increase in newbuilding orders; shipbuilding capacity is a more influential factor for the short-run supply of new tankers than shipbuilding cost. Technological change has also played an important role in the market.     

Is the West doomed to lose its maritime-related industries?

The continuous decline of maritime-related industries, i.e. shipping, shipbuilding and metallurgy in Europe has been accomplished in the same period as their growth in Asia, especially in the newly industrialized countries (NICS). European public policies have been impaired by feelings of a fateful trend in the new international division of labour, based upon economic theory. At least two of those theories, viz. the theory of difference between absolute cost and the theory of comparative advantage are not confirmed by statistical analysis. Sociological factors are more relevant in explaining this trend. Present public policies may therefore be questioned.     

燃气热泵的经济性分析

利用热经济学的研究方法对燃气热泵和其它几种常规空调方式的经济性进行了研究比较,并就能源价格变化对经济性的影响进行了研究,获得了适宜燃气热泵推广应用的能源价格范围。结果表明,燃气热泵的年度总成本最低,具有经济性优势。     

沿海干散货船的船价影响因素及概率统计分析

由于船舶的投资额很大,所以航运企业在做投资决策之前对船价的影响因素做系统的分析,并对其进行准确的估计,对航运企业来说是至关重要的。本文分析了近几年沿海干散货船舶市场的影响因素,并运用概率统计的方法给出了近期船价的概率分布模型。     

Short-term liner shipping bunker procurement with swap contracts

The bunker price fluctuations in recent years have severely threatened the stability of liner shipping companies’ operations. As an efficient countermeasure, the swap contract is widely adopted throughout the liner shipping industry to hedge the procurement risk resulting from the bunker price fluctuation. This paper looks at the short-term liner shipping bunker procurement problem with swap contracts (BPPSC), aiming to optimally plan the amount of bunker purchased from the spot market and the amount hedged by the swap contract for several months ahead. This BPPSC is first formulated as a bunker procurement cost mean-variance minimization (MVM) model, and is subsequently solved using a tangible two-step approach developed in this study. In the first step, the movements of the swap contract price and the spot market price of the bunker are described using a calibrated multivariate generalized autoregressive conditional heteroskedasticity (mGARCH) time series model. In the second step, the MVM model is approximated and solved by a price scenario tree constructed from the mGARCH time series model. A numerical example shows that the risk hedging strategy obtained can simultaneously control the bunker procurement cost as well as the procurement risk from price fluctuations. This article is a revised and expanded version of the abridged eight-page paper entitled ‘Optimal hedging for liner bunker procurement’ presented at ‘2015 International Conference on Logistics and Maritime Systems (LOGMS 2015)’, Hong Kong, 27–29 August 2015.     

Port pricing: a cost axiomatic approach

The earlier port pricing literature argued that port prices should be based uponk marginal cost pricing. However, recent literature suggests that a conflicts would arise between marginal cost pricing and full cost recovery at ports. Further, problems arise in determining or estimating marginal costs. A price structure that addresses the problems of port marginal cost pricing is cost axiomatic pricing, given the goals, objectives and constraints of ports. Fairness and cost efficiency cost axioms for ports are considered. A methodology for determining cost axiomatic prices for a marine container terminal is presented.