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。     

Platoon based cooperative driving model with consideration of realistic inter-vehicle communication

Recent developments of information and communication technologies (ICT) have enabled vehicles to timely communicate with each other through wireless technologies, which will form future (intelligent) traffic systems (ITS) consisting of so-called connected vehicles. Cooperative driving with the connected vehicles is regarded as a promising driving pattern to significantly improve transportation efficiency and traffic safety. Nevertheless, unreliable vehicular communications also introduce packet loss and transmission delay when vehicular kinetic information or control commands are disseminated among vehicles, which brings more challenges in the system modeling and optimization. Currently, no data has been yet available for the calibration and validation of a model for ITS, and most research has been only conducted for a theoretical point of view. Along this line, this paper focuses on the (theoretical) development of a more general (microscopic) traffic model which enables the cooperative driving behavior via a so-called inter-vehicle communication (IVC). To this end, we design a consensus-based controller for the cooperative driving system (CDS) considering (intelligent) traffic flow that consists of many platoons moving together. More specifically, the IEEE 802.11p, the de facto vehicular networking standard required to support ITS applications, is selected as the IVC protocols of the CDS, in order to investigate how the vehicular communications affect the features of intelligent traffic flow. This study essentially explores the relationship between IVC and cooperative driving, which can be exploited as the reference for the CDS optimization and design.     

艇体变形对轴系校中的影响

艇体变形是影响轴系校中质量的重要因素,以深水潜器为研究对象,通过建立潜器的三维有限元模型,提出利用弹簧约束调节潜器重力与浮力平衡的方法,分析潜器处于正浮状态时,在重力、浮力和静水压力作用下的艇体变形,得出潜器轴系各个轴承的位移数据,并分析轴承位移造成的轴承负荷变化。为艇体变形影响下的潜器轴系校中提供依据。分析结果表明：耐压艇体内的轴承位移要小于耐压艇体外,支撑轴承的艇体结构的差异会导致轴承位移大小的不同,从而导致各个轴承负荷变化也不一样,艇内液舱的不对称布置会导致位于该液舱上轴承产生较大的横向位移和横向轴承负荷。     

某集装箱船上层建筑振动控制方法

文中对某集装箱船上层建筑出现的振动问题进行模态分析,找出引起其振动的主要激励源,提出几种增强其刚度的振动控制方案,并将其计算频率结果与激励频率进行对比,采用避开激励频率的方法,给出了上层建筑振动控制的优化方案。经实船振动测试,优化方案的上层建筑振动响应有了显著减少,验证了振动控制方法的有效性。