基于BP人工神经网络的滑坡预测分析

文章以汶川地震引发的滑坡为研究对象,以震中距、地震烈度、坡度、前缘高程、坡高和岩性等影响坡体稳定性的因素为切入点,利用BP人工神经网络对实际坡体的稳定性进行了预测分析。结果表明,BP人工神经网络方法能有效预测坡体的稳定情况。     

机械复合管在海底管道中的应用

原油、湿气含有CO2或H2S是造成海底管道内腐蚀失效的主要原因之一。机械复合管作为一种新型管材,可以有效解决CO2或H2S造成的内腐蚀问题,在国际上得到了广泛应用,但其在国内油气田开发海底管道中,尚无应用先例。文中介绍了机械复合管的制造原理、设计制造规范、用作海底管道的技术要求、海上安装技术特点以及应用前景。文中研究了机械复合管在海底管道中应用对设计制造和安装技术的要求,以推动其在国内油气田开发海底管道中的应用。     

The effectiveness of a European speed limit versus an international bunker-levy to reduce CO2 emissions from container shipping

In the fight to reduce CO₂ emissions from international shipping, a bunker-levy is currently under consideration at the International Maritime Organization (IMO). Faced with the inability of the IMO to reach an agreement in the short term, the European Commission is now contemplating a unilateral measure of a speed limit for all ships entering European Union (EU) ports. This paper argues that this measure is counterproductive for two reasons. Firstly, because it may ultimately generate more emissions and incur a cost per ton of CO₂ which is more than society is willing to pay. Secondly, because it is sub-optimal compared to results obtained if an international bunker-levy was to be implemented. These elements are illustrated using two direct transatlantic services operated in 2010.     

The value of options for time charterparty extension: an artificial neural networks (ANN) approach

The most frequently associated options in the physical shipping market are options to extend the charter period on time charters and additional shipment options on contracts of affreightment. The value of freight options, in practice, is estimated mostly by referring to forward curves. An option on freight has different properties from its financial counterparts, and the straightforward adoption of theoretical models does not produce promising results. In this paper, extension options, which have the property of options on futures, were transformed into regular European options before the application of the Black-Scholes model (BSM). The efficient market hypothesis, which justifies the parity of the performance of a long-term charter to that of repetitive short-term charters, worked as the basis for the transformation. The option values determined by the BSM were compared with actual realized values. Additionally, the artificial neural networks (ANN) was employed to derive the option values. This study is meaningful as the first-time application of both the closed-form solution and the ANN to the valuation of physical freight options. The research results can contribute to the quality of chartering decisions. The results could also be used in quantifying credit risk, as extension options tend to be granted to charterers with more creditability.     

固态胺纤维制备及在密闭舱内吸附CO2性能研究

以聚丙烯腈纤维(PAN)为基体,通过水解、酰氯化及与聚乙烯亚胺(PEI)接枝反应制备得到多胺基型固态胺纤维.应用红外光谱仪、热重分析仪及扫描电子显微镜表征了纤维的官能团结构、热稳定性及表面微观形貌.在温度25.0℃、相对湿度80%、初始CO2浓度1.0%的条件下,测得纤维在30 min内对CO2的吸附量可达154.4 g/kg;105℃ 水蒸气再生10 min,循环吸附再生50次,纤维的再生效率为98.3%.     

基于正交设计的船用柴油机燃烧系统参数匹配及优化

为研究柴油机燃烧系统参数匹配对柴油机动力和排放性能的影响,首先分别利用AVL_BOOST和AVL_FIRE仿真软件建立4190ZLC-2型船用柴油机整机模型和缸内燃烧高压循环模型,然后基于已建模型应用正交试验设计方法安排柴油机进气系统、喷油系统和燃烧室结构尺寸参数匹配仿真计算。研究结果表明,通过极差分析可以得出燃烧系统参数对4190ZLC-2型柴油机性能的影响主次顺序。以柴油机指示功率为评价指标时,参数组合0.26 mm-28°CA-160°-0.9-145 mm-2.6 mm-22 mm(喷孔直径-喷油提前角-油束夹角-涡流比-喉口直径-凸台高度-凹坑半径)对应的指示功率为63.40 k W,比原机仿真值高15%;以NOX排放为评价指标时,参数组合0.30 mm-24°CA-140°-0.4-135 mm-6.6 mm-14 mm(喷孔直径-喷油提前角-油束夹角-涡流比-喉口直径-凸台高度-凹坑半径)对应的NOX排放质量分数为0.015 7%,比原机仿真值低30.2%。     

基于PSO-BP神经网络的油船中部结构优化

以舱段质量为目标函数,以相关规范要求的板厚及应力为约束条件,通过灵敏度分析确定设计变量,对油船中部结构优化。构建基于粒子群优化的BP神经网络模型,并代替有限元分析确定应力与设计变量之间关系,从而对舱段进行结构优化。优化后舱段质量降低了4.2%,优化后的有限元分析结果表明满足规范要求,PSOBP神经网络模型在船舶结构优化设计中具有可行性。     

基于神经网络对电控柴油机运行特性影响因素仿真研究

基于AVL-BOOST软件仿真平台建立某船用四缸柴油机仿真模型,标定后的模型进行柴油机全工况仿真计算.仿真出来的3 200组数据作为人工神经网络输入数据,采用贝叶斯统计方法对网络进行训练建立2层的反馈神经网络仿真模型.并分别通过实验、AVL-BOOST和神经网络数据曲线的对比分析,验证人工神经网络预测的准确性.利用验证好的人工神经网络模型预测进排气压力对柴油机转矩的影响,以及预测压缩比和供油定时对柴油机排放性能和动力性能的影响,最后利用扰动法分析不同工况下柴油机各个参数对柴油机性能的影响程度.     

接触网检测车振动补偿研究

针对接触检测车实际工况,分析了检测车车体振动的动力学特性,建立了基于运动规律的数学模型,论述了训练样本得出检测车拉出值振动补偿函数的原理和方法。     

用人工神经网络预测沥青路面材料的回弹模量

将人工神经网络应用于沥青路面材料的回弹模量的预测 ,提出了一种有效的预测方法 ,并构造了预测回弹模量的神经网络模型 .预测结果表明 ,该模型具有较高的预测精度 ,为预测路面材料的回弹模量等力学指标提供了一种新的方法