基于RBFNN的铁路混凝土桥梁构件状态评估

介绍了RBF神经网络模型的结构和训练算法,提出了既有铁路桥梁构件的综合状态评估模型,根据RBF神经网络的自适应性和学习能力,成功的将RBF神经网络应用于既有铁路桥梁构件综合状态评估中去,并给出了便于获取,且能全面准确反映桥梁实际工作状态的输入参数.以某铁路线的若干组实测数据对RBF神经网络进行训练和测试,系统输出与期望输出吻合较好,证明了RBF神经网络评估既有桥梁构件综合状态的准确性、有效性和稳定性.     

基于BP神经网络和遗传算法的桥梁损伤识别方法研究

以钟祥汉江大桥的损伤识别为例，对基于BP神经网络和遗传算法的桥梁结构损伤诊断方法进行的实例应用研究，结果表明该方法兼有神经网络广泛的映射能力和遗传算法快速的全局收敛性能。     

生命周期评价及其在汽车排放领域的应用

介绍了生命周期评价(LCA)的定义、评估对象、范围、评价思路、步骤及其体系框架,说明了汽车排放分析中存在的两种循环(燃料循环和车辆循环)。通过分析汽车生命周期排放模型及其在CATCH(Clean A ccessible Transport for Community Health)研究中的一个实际应用案例,进一步阐明了生命周期评价在对各种燃料进行排放分析过程中的实际应用价值,最后介绍了生命周期评价在国外汽车企业中的研究发展情况、实际产品以及应用前景。     

Measuring the sustainability of marine fuels: A fuzzy group multi-criteria decision making approach

The use of alternative energy sources instead of HFO has been recognized as a promising way for reducing emissions from shipping and promoting the development of green shipping. However, it is usually difficult for the decision-making to select the best choice among multiple alternative marine fuels. In order to address this, a complete criteria system for sustainability assessment of alternative marine fuels was firstly established, and a fuzzy group multi-criteria decision making method has been developed to rank the alternative marine fuels by combining fuzzy logarithmic least squares and fuzzy TOPSIS (Technique for Order Performance by Similarity to Ideal Solution). Fuzzy logarithmic least squares method has been employed to determine the weights of the criteria for sustainability assessment, and fuzzy TOPSIS was employed to determine the sustainability order of the alternatives. An illustrative case with three alternative marine fuels including methanol, LNG and hydrogen has been studied by the proposed method, and hydrogen has been recognized as the most sustainable scenario, follows by LNG, and methanol in the descending order. The results show that the proposed method is feasible for prioritizing the alternative marine fuels; it also has the ability to help the decision-makers to select the most sustainable option among multiple marine fuels.     

A Value-at-Risk (VAR) approach to routing rail hazmat shipments

Hazardous materials (hazmat) accidents are rare though the consequences could be disastrous. Given the possibility of low probability – high consequence event, a risk-averse routing hazmat shipment is necessary. We propose a value-at-risk (VaR) approach to route rail hazmat shipments, using the best train configuration, over a given railroad network with limited number of train services such that the transport risk as measured by VaR is minimized. Freight train derailment reports of the Federal Railroad Administration were analyzed to develop expressions that would incorporate characteristics of railroad accidents, and then to estimate the different inputs. The proposed methodology was used to study several problem instances generated using the realistic network of a railroad operator, and to demonstrate that it is possible to develop different routes for shipments depending on the risk preference of the decision maker.     

The effect of railway local irregularities on ground vibration

The environmental effects of ground-borne vibrations generated due to localised railway defects is a growing concern in urban areas. Frequency domain modelling approaches are well suited for predicting vibration levels on standard railway lines due to track periodicity. However, when considering individual, non-periodic, localised defects (e.g. a rail joint), frequency domain modelling becomes challenging. Therefore in this study, a previously validated, time domain, three-dimensional ground vibration prediction model is modified to analyse such defects. A range of different local (discontinuous) rail and wheel irregularity are mathematically modelled, including: rail joints, switches, crossings and wheel flats. Each is investigated using a sensitivity analysis, where defect size and vehicle speed is varied. To quantify the effect on railroad ground-borne vibration levels, a variety of exposure–response relationships are analysed, including: peak particle velocity, maximum weighted time-averaged velocity and weighted decibel velocity. It is shown that local irregularities cause a significant increase in vibration in comparison to a smooth track, and that the vibrations can propagate to greater distances from the line. Furthermore, the results show that step-down joints generate the highest levels of vibration, whereas wheel flats generate much lower levels. It is also found that defect size influences vibration levels, and larger defects cause greater vibration. Lastly, it is shown that for different defect types, train speed effects are complex, and may cause either an increase or decrease in vibration levels.     

Life cycle assessment of bituminous pavements produced at various temperatures in the Belgium context

Bituminous mixture is the premier material for road construction in Belgium. Innovative technologies to improve energy efficiency of pavement constructions are necessary. Warm mix asphalt may provide significant energy savings to the asphalt industry, but the environmental impact of the total life cycle has to be investigated. The use of additives may counteract the reduced environmental impact due to energy savings. This paper presents the results of an environmental impact assessment of four wearing course test sections. Using life cycle assessment, hot mix asphalt is compared to a cold asphalt mix with emulsion and warm mix asphalt with two types of additives: a synthetic zeolite and an organic Fischer–Tropsch wax. Neither hot nor warm mix asphalt could be preferred based on the results of this study, because the additive has a major influence on the environmental results. It was seen that the production of bitumen, the transport and energy in order to generate heat mainly contribute to the total environmental impact. The results from the sensitivity analyses show that the total environmental impact of the life of the pavement can vary significantly based on the choice of the specific data source and service life.     

Assessing the impact of tactical airport surface operations on airline schedule block time setting

With the growth of air traffic, airport surfaces are congested and air traffic operations are disrupted by the formation of bottlenecks on the surface. Hence, improving the efficiency and predictability of airport surface operations is not only a key goal of NASA’s initiatives in Integrated Arrival/Departure/Surface (IADS) operations, but also has been recognized as a critical aspect of the FAA NextGEN implementation plan. While a number of tactical initiatives have been shown to be effective in improving airport surface operations from a service provider’s perspective, their impacts on airlines’ scheduled block time (SBT) setting, which has been found to have direct impact on airlines’ on-time performance and operating cost, have received little attention. In this paper, we assess this impact using an econometric model of airline SBT combined with a before/after analysis of the implementation of surface congestion management (SCM) at John F. Kennedy International Airport (JFK) in 2010. Since airlines do not consider gate delay in setting SBT, we find that reduction in taxi-out time variability resulting from SCM leads to more predictable taxi-out times and thus decreases in SBT. The JFK SCM implementation is used as a case study to validate model prediction performance. The observed SBT decrease between 2009 and 2011 at JFK is 4.8 min and our model predicts a 4.2 min decrease. In addition, Charlotte Douglas International Airport (CLT) is used as an example to demonstrate how different surface operations improvements scenarios can be evaluated in terms of SBT reduction.     

关于深度学习的综述与讨论

  目的  针对传统有限元数值计算方法耗时长、占用计算资源多等缺点,提出基于机器学习算法对船舶结构强度进行评估的回归预测模型。  方法  以已有的有限元数值计算数据为样本,以外部载荷和结构尺寸为特征,以应力和变形为目标,引入4种传统机器学习算法和4种集成机器学习算法,对船舶上吊杆处的局部结构响应进行预测分析。  结果  与传统有限元数值模拟方法相比,机器学习算法在保证结果准确性的同时大幅度提升了计算效率,其中Light Gradient Boosting Machine（LightGBM）算法与其他算法相比,其准确度和计算效率的表现更好。  结论  为进一步研究更复杂的船体结构设计提供了一条可行且高效的技术途径。