Investigating the irregularity of bus routes: highlighting how underlying assumptions of bus models impact the regularity results

A bus route is inherently unstable: when the system is uncontrolled, buses fail to maintain their time‐headways and tend to bunch. Several mathematical bus motion models were proposed to reproduce the bus behavior and assess management strategies. However, no work has established how the choice of a model impacts the irregularity of modeled bus systems, that is, the non‐respect of scheduled headways. Because of this gap, a large body of existing works assumes that the ability of these models to reproduce instability comes only from stochasticity, although the link between stochastic inputs and the level of irregularity remains unknown. Moreover, some recognized phenomena such as a change of travel conditions during a day or delays at signalized intersections are ignored. To address these shortcomings, this paper provides an overview of existing dynamic bus‐focused models and proposes a simple way to classify them. Commonly used deterministic and stochastic models are compared, which allows quantifying the relative influence of stochasticity of each model component on outputs. Moreover, we show that a change in the system equilibrium in a full deterministic system can lead to irregularity. Finally, this paper proposes a refinement of travel time models to account for non‐dynamic signals. In presence of traffic signals, we show that a bus system can be self‐regulated. Especially, these insights could help to calibrate bus model inputs to better reproduce real data. Copyright © 2014 John Wiley & Sons, Ltd.     

沥青路面智能压实技术研究动态

随着道路施工机械化、信息化与数字化集成水平的提高，沥青路面智能压实技术也成为研究与应用热点。有效检测沥青路面压实状态，并且能够准确判别与控制压实质量是实现压实“智能化”的关键，也是实现科学提升路面路用性能和使用寿命的基础。从沥青路面智能压实质量控制原理上进行分类讨论，主要包括机械振动响应、雷达反射波以及智能颗粒细观响应。紧密结合工程实际分析优缺点，为后续沥青路面智能压实的技术发展方向提供借鉴。     

基于可解释极端随机树模型的 DCT 液压响应预测

为解决传统湿式双离合器变速器 （Dual Clutch Transmission， DCT） 控制策略在硬件误差以及复杂工况下液压响应预测精度不完全可控的问题，提出了一种基于 SHAP 图可解释极端随机树预测模型，使用机器学习方法结合某汽车公司 DCT 实验室采集的真实离合器数据对 DCT 液压响应进行预测。模型利用 SHAP 算法对于重要特征选择的可解释性，筛选并保留对液压响应影响较大的特征，将时间切片和升降压判定作为特征加入训练数据，训练预测模型。结果表明，该模型训练结果的均方误差 MSE 为 0.670 3，可决系数 R2为 1.000 0，并且在测试集上预测值与实际值之间的平均误差为12.99 kPa，远低于设计误差 25 kPa，具有较高的预测精度，特征选择较准确，可以很好地解决传统物理模型无法计算不同工况下液压响应的问题，为下阶段基于数据和物理双驱动的DCT控制策略优化提供较准确的预测结果。