Accounting for traffic speed dynamics when calculating COPERT and PHEM pollutant emissions at the urban scale

Coupling a traffic microsimulation with an emission model is a means of assessing fuel consumptions and pollutant emissions at the urban scale. Dealing with congested states requires the efficient capture of traffic dynamics and their conditioning for the emission model. Two emission models are investigated here: COPERT IV and PHEM v11. Emission calculations were performed at road segments over 6 min periods for an area of Paris covering 3 km². The resulting network fuel consumption (FC) and nitrogen oxide (NOx) emissions are then compared. This article investigates: (i) the sensitivity of COPERT to the mean speed definition, and (ii) how COPERT emission functions can be adapted to cope with vehicle dynamics related to congestion. In addition, emissions are evaluated using detailed traffic output (vehicle trajectories) paired with the instantaneous emission model, PHEM.COPERT emissions are very sensitive to mean speed definition. Using a degraded speed definition leads to an underestimation ranging from −13% to −25% for fuel consumption during congested periods (from −17% to −36% respectively for NOx emissions). Including speed distribution with COPERT leads to higher emissions, especially under congested conditions (+13% for FC and +16% for NOx). Finally, both these implementations are compared to the instantaneous modeling chain results. Performance indicators are introduced to quantify the sensitivity of the coupling to traffic dynamics. Using speed distributions, performance indicators are more or less doubled compared to traditional implementation, but remain lower than when relying on trajectories paired with the PHEM emission model.     

Evaluation of eco-driving training for vehicle fuel use and emission reduction: A case study in Australia

This study evaluates effectiveness of driver education teaching greater fuel efficiency (Eco-Driving) in a real world setting in Australia. The driving behaviour, measured in fuel use (litres per 100 km of travel) of a sample of 1056 private drivers was monitored over seven months. 853 drivers received education in eco-driving techniques and 203 were monitored as a control group. A simple experimental design was applied comparing the pre and post training fuel use of the treated sample compared to a control sample. This study found the driver education led to a statistically significant reduction in fuel use of 4.6% or 0.51 litres per 100 km compared to the control group.     

Traffic conflict models to evaluate the safety of signalized intersections at the cycle level

The safety of signalized intersections has often been evaluated at an aggregate level relating collisions to annual traffic volume and the geometric characteristics of the intersection. However, for many safety issues, it is essential to understand how changes in traffic parameters and signal control affect safety at the signal cycle level. This paper develops conflict-based safety performance functions (SPFs) for signalized intersections at the signal cycle level. Traffic video-data was recorded for six signalized intersections located in two cities in Canada. A video analysis procedure is proposed to collect rear-end conflicts and various traffic variables at each signal cycle from the recorded videos. The traffic variables include: traffic volume, maximum queue length, shock wave characteristics (e.g. shock wave speed and shock wave area), and the platoon ratio. The SPFs are developed using the generalized linear models (GLM) approach. The results show that all models have good fit and almost all the explanatory variables are statistically significant leading to better prediction of conflict occurrence beyond what can be expected from the traffic volume only. Furthermore, space-time conflict heat maps are developed to investigate the distribution of the traffic conflicts. The heat maps illustrate graphically the association between rear-end conflicts and various traffic parameters. The developed models can give insight about how changes in the signal cycle design affect the safety of signalized intersections. The overall goal is to use the developed models for the real-time optimization of signalized intersection safety by changing the signal design.     

Soft Radial Basis Cellular Neural Network (SRB-CNN) based robust low-cost truck detection using a single presence detection sensor

This paper does present a comprehensive concept for a robust and reliable truck detection involving solely one single presence sensor (e.g. an inductive loop, but also any other presence sensor) at a signalized traffic junction. Hereby, two operations modes are distinguished: (a) during green traffic light phases, and (b) a much challenging case, during red traffic light phases. First, it is shown how difficult the underlying classification task is, this mainly due to strongly overlapped classes, which cannot be easily separated by simple hyper-planes. Then, a novel soft radial basis cellular neural/nonlinear network (SRB-CNN) based concept is developed, validated and extensively benchmarked with a selection of the best representatives of the current related state-of-the-art classification concepts (namely the following: support vector machines with radial basis function, artificial neural network, naive Bayes, and decision trees). For benchmarking purposes, all selected competing classifiers do use the same features and the superiority of the novel CNN based classifier is thereby underscored, as it strongly outperforms the other ones. This novel SRB-CNN based concept does satisfactorily fulfill the hard industrial requirements regarding robustness, low-cost, high processing speed, low memory consumption, and the capability to be deployed in low cost embedded systems.     

Analysis of fuel consumption and pollutant emissions of regulated and alternative driving cycles based on real-world measurements

Discrepancies between real-world use of vehicles and certification cycles are a known issue. This paper presents an analysis of vehicle fuel consumption and pollutant emissions of the European certification cycle (NEDC) and the proposed worldwide harmonized light vehicles test procedure (WLTP) Class 3 cycle using data collected on-road. Sixteen light duty vehicles equipped with different propulsion technologies (spark-ignition engine, compression-ignition engine, parallel hybrid and full hybrid) were monitored using a portable emission measurement system under real-world driving conditions. The on-road data obtained, combined with the Vehicle Specific Power (VSP) methodology, was used to recreate the dynamic conditions of the NEDC and WLTP Class 3 cycle. Individual vehicle certification values of fuel consumption, CO₂, HC and NO_x emissions were compared with test cycle estimates based on road measurements. The fuel consumption calculated from on-road data is, on average, 23.9% and 16.3% higher than certification values for the recreated NEDC and WLTP Class 3 cycle, respectively. Estimated HC emissions are lower in gasoline and hybrid vehicles than certification values. Diesel vehicles present higher estimated NO_x emissions compared to current certification values (322% and 326% higher for NO_x and 244% and 247% higher for HC + NO_x for NEDC and WLTP Class 3 cycle, respectively).     

膨胀土边坡护岸组合结构施工应用

针对因膨胀土胀缩性而引发的航道护岸变形问题,研究处理措施。将"多级放坡+浅层改性换填+表层隔排水+深层桩基"组合型护岸结构应用于某航道工程,达到无变形、无裂缝的工程效果,验证了该种组合结构措施抵抗膨胀土胀缩的能力,适用于有桥梁等交叉建筑物的重点航段。     

Vehicle classification from low-frequency GPS data with recurrent neural networks

The categorization of the type of vehicles on a road network is typically achieved using external sensors, like weight sensors, or from images captured by surveillance cameras. In this paper, we leverage the nowadays widespread adoption of Global Positioning System (GPS) trackers and investigate the use of sequences of GPS points to recognize the type of vehicle producing them (namely, small-duty, medium-duty and heavy-duty vehicles). The few works which already exploited GPS data for vehicle classification rely on hand-crafted features and traditional machine learning algorithms like Support Vector Machines. In this work, we study how performance can be improved by deploying deep learning methods, which are recently achieving state of the art results in the classification of signals from various domains. In particular, we propose an approach based on Long Short-Term Memory (LSTM) recurrent neural networks that are able to learn effective hierarchical and stateful representations for temporal sequences. We provide several insights on what the network learns when trained with GPS data and contextual information, and report experiments on a very large dataset of GPS tracks, where we show how the proposed model significantly improves upon state-of-the-art results.     

Methods using belief functions to manage imperfect information concerning events on the road in VANETs

Different models using belief functions are proposed and compared in this article to share and manage imperfect information about events on the road in vehicular networks. In an environment without infrastructure, the goal is to provide to driver the synthesis of the situation on the road from all acquired information. Different strategies are considered: discount or reinforce towards the absence of the event to take into account messages agings, keep the original messages or only the fusion results in vehicles databases, consider the world update, manage the spatiality of traffic jams by taking into account neighborhood. Methods are tested and compared using a Matlab™ simulator. Two strategies are introduced to tackle fog blankets spatiality; they are compared through an example.     

智能温度控制系统

本文主要研究对特定空间(电阻炉)的温度进行高精度控制。电阻炉是一种具有纯滞后的大惯性系统,本文将模糊控制算法引入传统的加热炉控制系统构成智能模糊控制系统,利用模糊控制规则对PID参数进行修改,借此提高其控制效果。本文提出的基于模糊的自整定PID控制算法的控制系统控制精度高,对高质量热处理件的具有实际意义。