Life cycle cost of conventional,battery electric,and fuel cell electric vehicles considering traffic and environmental policies in China

Electric vehicles (EVs) are considered a promising alternative to conventional vehicles (CVs) to alleviate the oil crisis and reduce urban air pollution and carbon emissions. Consumers usually focus on the tangible cost when choosing an EV or CV but overlook the time cost for restricting purchase or driving and the environmental cost from gas emissions, falling to have a comprehensive understanding of the economic competitiveness of CVs and EVs. In this study, a life cycle cost model for vehicles is conducted to express traffic and environmental policies in monetary terms, which are called intangible cost and external cost, respectively. Battery electric vehicles (BEVs), fuel cell electric vehicles (FCEVs), and CVs are compared in four first-tier, four new first-tier, and 4 s-tier and below cities in China. The comparison shows that BEVs and FCEVs in most cities are incomparable with CVs in terms of tangible cost. However, the prominent traffic and environmental policies in first-tier cities, especially in Beijing and Shanghai, greatly increase the intangible and external costs of CVs, making consumers more inclined to purchase BEVs and FCEVs. The main policy benefits of BEVs and FCEVs come from three aspects: government subsidies, purchase and driving restrictions, and environmental taxes. With the predictable reduction in government subsidies, traffic and environmental policies present important factors influencing the competitiveness of BEVs and FCEVs. In first-tier cities, BEVs and FCEVs already have a competitive foundation for large-scale promotion. In new first-tier and second-tier and below cities, stricter traffic and environmental policies need to be formulated to offset the negative impact of the reduction in government subsidies on the competitiveness of BEVs and FCEVs. Additionally, a sensitivity analysis reveals that increasing the mileage and reducing fuel prices can significantly improve the competitiveness of BEVs and FCEVs, respectively.     

Experimental investigation of supercapacitor based regenerative energy storage for a fuel cell vehicle equipped with an alternator

Recently, researchers have devoted more attention to supercapacitors (SCs) to integrate with batteries in energy storage systems (ESSs) for vehicle applications. In this study, we attempted to characterize the use of SCs in the ESS for a PEM fuel cell vehicle equipped with an alternator to maximize the performance of regenerative braking. We applied lithium-ion batteries (LIBs) and SCs as energy storage devices to examine their effect on ESS. Then we used a hysteresis brake to apply controllable braking force on the flywheel to form hybrid braking (HB) and made efforts to study its behavior to suggest a braking control strategy. We also ran the whole system over the rotational speed to cover the range of driving speed. At last, we sized the SCs for the most commonly used fuel cell electric vehicle (FCEV) in Korea, i.e., Hyundai NEXO, based on the results obtained from the above study by alternator efficiencies.     

基于词性特征的明喻识别及要素抽取方法

比喻是一种利用事物之间的相似点建立关系的修辞方式。明喻是比喻中最常见的形式,具有明显的喻词,例如"像",用于关联本体和喻体。近年来高考语文散文类鉴赏题中多有考查明喻句的试题,为了解答此类鉴赏题,需要识别比喻句中的本体和喻体要素。该文提出了基于词性特征的明喻识别及要素抽取方法。首先将句子中词向量化表示与词性特征向量化表示进行融合,将融合后的向量输入到BiLSTM中进行训练,然后利用CRF解码出全局最优标注序列;最后得到明喻识别和要素抽取的结果。公开数据集上的实验结果表明,该方法优于已有的单任务方法;同时也将该文方法应用于北京高考语文鉴赏题中比喻句的识别与要素抽取,验证了方法的可行性。     

Deep reinforcement learning-based cooperative interactions among heterogeneous vehicular networks

Most real-world vehicle nodes can be structured into an interconnected network of vehicles. Through structuring these services and vehicle device interactions into multiple types, such internet of vehicles becomes multidimensional heterogeneous overlay networks. The heterogeneousness of the overlays makes it difficult for the overlay networks to coordinate with each other to improve their performance. Therefore, it poses an interesting but critical challenge to the effective analysis of heterogeneous virtual vehicular networks. A variety of virtual vehicular networks can be easily deployed onto the native network by applying the concept of SDN (Software Defined Networking). These virtual networks reflect their heterogeneousness due to their different performance goals, and they compete for the same physical resources of the underlying network, so that a sub-optimal performance of the virtual networks may be achieved. Therefore, we propose a Deep Reinforcement Learning (DRL) approach to make the virtual networks cooperate with each other through the SDN controller. A cooperative solution based on the asymmetric Nash bargaining is proposed for co-existing virtual networks to improve their performance. Moreover, the Markov Chain model and DRL resolution are introduced to leverage the heterogeneous performance goals of virtual networks. The implementation of the approach is introduced, and simulation results confirm the performance improvement of the latency sensitive, loss-rate sensitive and throughput sensitive heterogeneous vehicular networks using our cooperative solution.     

An agile model for the eco-design of electric vehicle Li-ion batteries

Numerous design choices need to be made at several levels when designing high-tech products: technology, processes, architecture, components, materials… and these choices need to be made in relation to the product life cycle with the corresponding experts for each stage of the life cycle. At the same time, to ensure product sustainability, a specific focus on the future potential environmental impacts is highly recommended. In this research, an agile model is proposed to help designers make decisions while monitoring environmental performance indicators of high-tech solutions. The concept of Critical Product Life Cycle Parameters had to be introduced to facilitate the eco-design of the final product. The approach is illustrated by the Electric Vehicle Li-Ion Batteries case study.     

基于多尺度双线性卷积神经网络的多角度下车型精细识别

针对多角度下车辆出现一定的尺度变化和形变导致很难被准确识别的问题，提出基于多尺度双线性卷积神经网络（MS-B-CNN）的车型精细识别模型。首先，对双线性卷积神经网络（B-CNN）算法进行改进，提出MS-B-CNN算法对不同卷积层的特征进行了多尺度融合，以提高特征表达能力；此外，还采用基于中心损失函数与Softmax损失函数联合学习的策略，在Softmax损失函数基础上分别对训练集每个类别在特征空间维护一个类中心，在训练过程中新增加样本时，网络会约束样本的分类中心距离，以提高多角度情况下的车型识别的能力。实验结果显示，该车型识别模型在CompCars数据集上的正确率达到了93.63%，验证了模型在多角度情况下的准确性和鲁棒性。     

低碳时变城配送车辆路径-发车调度集成优化

针对交通拥挤环境下日益增长的城市配送需求，通过分析时序依赖对成本和碳排放的影响，引入车辆在节点等待和离散调度策略，研究基于时序依赖的低碳城市配送车辆路径与离散调度问题。为求解该问题，设计基于遗传算法与局部搜索相结合的混合进化搜索算法对模型求解，用积极的局部搜索机制替代随机的变异操作，并通过可行解构造算法、变概率交叉和多种局部搜索策略来提高算法求解质量和求解效率。通过对比仿真实验对算法和模型的有效性进行了验证。     

A terrain risk assessment method for military surveillance applications for mobile assets

This study proposes an analytical and flexible terrain risk assessment method for military surveillance applications for mobile assets. Considering the risk as the degree of possibility of insurgent presence, the assessment method offers an efficient evaluation of risk in the surrounding terrain for military combat operating posts or observation posts. The method is designed for unmanned aerial vehicles as the surveillance assets of choice to improve the effectiveness of their use. Starting with the area map and geographical data, the target terrain is first digitized for space representation. Then the data of nine geographical parameters are used to formulate five contributing risk factors. These factors are incorporated in an analytical framework to generate a composite map with risk scores that reveal the potential high-risk spots in the terrain. The proposed method is also applied to a real-life case study of COP Kahler in Afghanistan, which was a target for insurgent attacks in 2008. The results confirm that when evaluated with the developed method, the region that the insurgents used to approach COP Kahler has high concentration of high-risk cells.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

Active disturbance rejection based trajectory linearization control for hypersonic reentry vehicle with bounded uncertainties

This paper investigates a novel compound control scheme combined with the advantages of trajectory linearization control (TLC) and alternative active disturbance rejection control (ADRC) for hypersonic reentry vehicle (HRV) attitude tracking system with bounded uncertainties. Firstly, in order to overcome actuator saturation problem, nonlinear tracking differentiator (TD) is applied in the attitude loop to achieve fewer control consumption. Then, linear extended state observers (LESO) are constructed to estimate the uncertainties acting on the LTV system in the attitude and angular rate loop. In addition, feedback linearization (FL) based controllers are designed using estimates of uncertainties generated by LESO in each loop, which enable the tracking error for closed-loop system in the presence of large uncertainties to converge to the residual set of the origin asymptotically. Finally, the compound controllers are derived by integrating with the nominal controller for open-loop nonlinear system and FL based controller. Also, comparisons and simulation results are presented to illustrate the effectiveness of the control strategy.