基于ANFIS的环境激励下桥梁结构应变响应预测分析

为准确预测复杂环境荷载作用下混凝土连续梁桥结构应变响应,基于结构健康监测系统长期实测数据,分析桥梁结构温度场变化规律,进而基于主成分分析及自适应神经网络模糊推理系统,建立桥梁结构温度场与桥梁结构应变响应的复杂非线性关系。首先,利用小波分解技术分离环境荷载及车辆荷载作用下的桥梁结构实测应变响应;然后利用平行坐标轴,分析混凝土连续梁桥结构温度场变化规律,并利用主成分分析提取结构温度场实测温度数据主成分;最后基于自适应神经网络模糊推理系统,以应变测点处温度数据、桥梁结构温度场实测温度数据主成分和采样时间点数据为输入数据,分别建立不同输入变量组合与应变响应的复杂非线性关系,并对比分析不同工况下结构应变响应的预测精度。结果表明：桥梁结构各测点处实测温度数据变化趋势基本一致,同侧测点实测温度数据高度相关,但桥梁结构上、下表面测点温度变化存在明显差异,仅考虑应变测点处温度变化,难以准确预测桥梁结构应变响应;当考虑桥梁结构温度场变化时,能更精确地建立温度与应变响应之间的关系模型,进而基于实测温度数据准确预测桥梁结构应变响应;当缺乏结构温度场实测温度数据时,将采样时间点作为反映桥梁结构温度场变化规律的参数,可取得较好效果。     

价值工程理论在沥青混合料碳排放减排措施中的应用

沥青混合料碳排放减排措施是降低碳排放的有效手段,而对减排措施的选择将直接影响工程的质量和经济效益。本文运用价值工程理论的基本原理与方法,论述价值工程在减排措施选择中的应用方法和步骤,并结合工程实例,对减排措施方案的选择进行研究。结果表明,运用价值工程理论的方法可以择优确定沥青混合料碳排放减排措施。     

基于层次分析法的交通运输节能减排示范项目绩效评价研究

交通运输是国家节能减排工作的重点领域,为促进交通运输节能减排技术发展,开展交通运输节能减排示范项目是政府部门一项重要的政策措施。对示范项目进行绩效评价工作能衡量财政资金投入政策实施效果,也是交通运输主管部门非常关注的问题。在交通运输节能减排示范项目绩效评价的逻辑框架下,运用层次分析法建立交通运输节能减排示范项目绩效评价指标体系及权重值,具有较好的实操性,能为开展同类型项目的绩效评价工作提供参考。     

Using GPS-data to determine optimum electric vehicle ranges: A Michigan case study

Fuel-switching personal transportation from gasoline to electricity offers many advantages, including lower noise, zero local air pollution, and petroleum-independence. But alleviations of greenhouse gas (GHG) emissions are more nuanced, due to many factors, including the car’s battery range. We use GPS-based trip data to determine use type-specific, GHG-optimized ranges. The dataset comprises 412 cars and 384,869 individual trips in Ann Arbor, Michigan, USA. We use previously developed algorithms to determine driver types, such as using the car to commute or not. Calibrating an existing life cycle GHG model to a forecast, low-carbon grid for Ann Arbor, we find that the optimum range varies not only with the drive train architecture (plugin-hybrid versus battery-only) and charging technology (fast versus slow) but also with the driver type. Across the 108 scenarios we investigated, the range that yields lowest GHG varies from 65 km (55+ year old drivers, ultrafast charging, plugin-hybrid) to 158 km (16–34 year old drivers, overnight charging, battery-only). The optimum GHG reduction that electric cars offer – here conservatively measured versus gasoline-only hybrid cars – is fairly stable, between 29% (16–34 year old drivers, overnight charging, battery-only) and 46% (commuters, ultrafast charging, plugin-hybrid). The electrification of total distances is between 66% and 86%. However, if cars do not have the optimum range, these metrics drop substantially. We conclude that matching the range to drivers’ typical trip distances, charging technology, and drivetrain is a crucial pre-requisite for electric vehicles to achieve their highest potential to reduce GHG emissions in personal transportation.     

基于RFID电子车牌数据的公交行程时间预测方法

为了给公交优先信号配时系统提供足够的"思考"时间和准确的控制依据,基于重庆市RFID电子车牌数据提出了一种采用自适应渐消卡尔曼滤波和小波神经网络组合模型动态预测公交行程时间的方法。综合分析公交行程时间的动态和静态影响因素,选取的模型输入参量为标准车流量、路段车辆平均行程时间、平均车速离散性和前班次公交行程时间。利用RFID电子车牌系统采集重庆市鹅公岩大桥路段车辆行驶数据,选取3 000组实际运行数据完成公交行程时间预测模型的训练,另筛选50组数据验证模型的有效性和准确性。研究结果表明：组合模型可动态自适应预测公交行程时间,预测值平均相对误差为3.23%,绝对误差集中在8 s左右,明显优于2种单一模型和基于传统GPS数据的公交行程时间预测模型,可认为选择RFID电子车牌数据作为组合模型的输入,能够明显改善模型预测精度;组合模型预测值的残差分布更为集中、鲁棒性较好,泛化能力强。选择平均绝对误差值、均方根误差值和平均绝对百分比误差作为模型评价指标,结果进一步表明,组合模型的综合预测效果明显优于单一的自适应渐消卡尔曼滤波和小波神经网络。研究方案可为先进公交信息化系统提供良好的技术支撑。     

基于LSTM网络的驾驶意图识别及车辆轨迹预测

自动驾驶汽车需具备预测周围车辆轨迹的能力,以便做出合理的决策规划,提高行驶安全性和乘坐舒适性。运用深度学习方法,设计了一种基于长短时记忆（LSTM）网络的驾驶意图识别及车辆轨迹预测模型,该模型由意图识别模块和轨迹输出模块组成。意图识别模块负责识别驾驶意图,其利用Softmax函数计算出驾驶意图分别为向左换道、直线行驶、向右换道的概率;轨迹输出模块由编码器-解码器结构和混合密度网络（MDN）层组成,其中的编码器将历史轨迹信息编码为上下文向量,解码器结合上下文向量和已识别的驾驶意图信息预测未来轨迹;引入MDN层的目的是利用概率分布来表示车辆未来位置,而非仅仅预测一条确定的轨迹,以提高预测结果的可靠性和模型的鲁棒性。此外,将被预测车辆及其周围车辆组成的整体视为研究对象,使模型能够理解车-车间的交互式行为,响应交通环境的变化,动态地预测车辆位置。使用基于真实路况信息的NGSIM（Next Generation SIMulation）数据集对模型进行训练、验证与测试。研究结果表明：与传统的基于模型的方法相比,基于LSTM网络的轨迹预测方法在预测长时域轨迹上具有明显的优势,考虑交互式信息的意图识别模块具备更高的预判性和准确率,且基于意图识别的轨迹预测能降低预测轨迹与真实轨迹间的均方根误差,显著提高轨迹预测精度。     

Bayesian network for red-light-running prediction at signalized intersections

Abstract

Red-light-running (RLR) is an important reason for the large number of intersection-related fatalities, injuries, and other losses. The accurate RLR prediction can effectively reduce crashes caused by RLR behavior. The RLR prediction is usually composed of two parts: the vehicle’s stop-or-go behavior and the arrival time when the vehicle reaches the stop line. Previous stop-or-go prediction models are usually based on embedded traffic sensors using machine learning algorithms. While based on the continuous trajectories collected by radar sensors, RLR prediction can be conducted more effectively. In this paper, a probabilistic stop-or-go prediction model based on the Bayesian network (BN) is proposed for RLR prediction. We extend the deterministic output into the probabilistic output, which provides decision-makers with greater autonomy. The causality of BN improves the interpretability of the prediction model. The BN model is calibrated and tested by the continuous trajectories data measured by radar sensors installed at a signalized intersection. We not only consider the movement measurements of individual vehicles (e.g., speed and acceleration), but also take into account the car-following behavior. As a comparison, different machine learning models and the model based on the inductive loop detection (ILD) are adopted. The results show that the proposed BN model has a high prediction accuracy and performs better in the feature interpretation. This paper provides a new way for probabilistic RLR prediction based on continuous trajectories, which will significantly improve traffic safety of signalized intersections.     

The Alternative Motor Fuels Act, alternative-fuel vehicles, and greenhouse gas emissions

The corporate average fuel economy (CAFE) standard is the major policy tool to improve the fleet average miles per gallon of automobile manufacturers in the US. The Alternative Motor Fuels Act (AMFA) provides special treatment in calculating the fuel economy of alternative-fuel vehicles to give manufacturers CAFE incentives to produce more alternative-fuel vehicles. AMFA has as its goals an increase in the production of alternative-fuel vehicles and a decrease in gasoline consumption and greenhouse gas emissions. This paper examines theoretically the effects of the program set up under AMFA. It finds that, under some conditions, this program may actually increase the production of fuel-inefficient gasoline vehicles, gasoline consumption and greenhouse gas emissions.     

基于桥梁挠度长期监测值的动态预测

文章针对重庆高家花园嘉陵江大桥实时健康监测系统的挠度长期监测数据,根据监测信息的时间序列呈季节、循环等非平稳状态特点,介绍采用ARMA时间序列预测模型,对挠度监测数据中所包含的外荷载的变化趋势及结构抗力的衰变信息进行动态预测,同时建立了结构外效应的预测函数。结果表明,采用低阶模型能对挠度监测值进行较好的动态预测。     

汶川地震震中区高速公路隧道超前地质预报方法

映汶高速公路公路位于四川汶川大地震震中,受地震强烈构造作用影响,隧址区岩体裂隙发育,松散破碎,存在构造富水,地震垮塌堆积体众多,地质条件极为复杂。文章根据本工程隧道的工程地质问题,通过对国内外隧道超前地质预报常用方法的分析,提出了针对本工程的隧道超前地质预报方案,并对地质预报的实施应用及效果进行了举例说明。