融合多通道CNN与BiGRU的字词级文本错误检测模型

文本校对是自然语言处理领域的重要分支。深度学习技术因强大的特征提取与学习能力被广泛应用于中文文本校对任务。针对现有中文文本错误检测模型忽略句子连续词间的局部信息、对于长文本的上下文语义信息提取不充分等问题,提出一种基于多通道卷积神经网络（CNN）与双向门控循环单元（BiGRU）的字词级文本错误检测模型。利用Word2vec向量化待检错文本,采用CNN挖掘待检错文本的局部特征,使用BiGRU学习待检错文本的上下文语义信息及长时依赖关系,并通过Softmax处理后输出文本分类结果以判断文本中是否含有字词错误,同时采取L2正则化和dropout策略防止模型过拟合。在SIGHAN2014和SIGHAN2015中文拼写检查任务数据集上的实验结果表明,与基于长短时记忆网络的文本错误检测模型相比,该模型的检错F₁值提升了3.01个百分点,具有更优的字词级文本错误检测效果。     

Research on lease and sale of electric vehicles based on value engineering

Electric vehicles (EVs) acknowledged as potential means of transportation tools in the near future are widely accepted as the development trend of automobile industry due to its environment protection and fuel energy saving properties. As a product containing new technologies and concepts with little market experience and consumer identification, studying its life cycle operation modes will help to figure out an optimal approach to conduct EVs manufacturing and service. The two common operation modes, lease and sale of EVs, have their own advantages and weaknesses under different scenarios and consumer psychological status. Research and comparisons on the function, cost and value of two operation modes in full life cycle will simulate the rapid development of EVs forming a mature and dynamic operation mechanism. This paper utilised approaches in value engineering, putting forward customer requirements and technical elements of EV lease and sale based on quality assessment and customer-perceived value, proposing the metric method of function and cost coefficient by mathematical modelling, and conducting value coefficient analysis and comparison based on customer’s risk aversion psychology. An illustrative example raised for studying operation mode of three different kinds of EVs based on the analysis of value coefficient, providing guideline for manufacturer and servicers of EVs.     

车型意象认知与侧轮廓造型特征关联研究

目的基于感性工学(KE)原理与方法,以各车型侧轮廓为对象,研究意象认知与车型造型要素的关联性,比较并分析在意象差异下所对应各车型侧轮廓的关键造型特征。方法选取目前市场的15款典型车型为研究样本,收集并筛选获取代表性感性意象词汇,结合语义差分法(SD法)与形态分析法,利用贝塞尔曲线对车身侧轮廓进行了简化并提取其造型特征线,在构建车身侧轮廓评价参考模型基础上,对样本侧轮廓进行直接与间接的量化分析。结论综合语义差分法(SD法)与形态对比分析法,提取影响车型意象定位的关键造型特征,获取用户针对不同车型在侧轮廓特征上的识别程度等级,构建车型侧轮廓特征—感性意象的关联模型,辅助汽车车型造型设计与研究,提高车型造型与用户感性需求间的匹配度。     

我国报废汽车回收利用现状分析与对策建议

从资源节约、环境保护、交通安全三方面论述提高我国报废汽车回收利用水平的重要意义。从报废汽车回收率、法律法规、监督管理、回收拆解等方面分析我国报废汽车回收利用的现状与问题,并提出解决问题的若干对策与建议,最后给出汽车报废回收阶段的生态效益评价模型。     

Additive Manufacturing of Porous Structures for Unmanned Aerial Vehicles Applications

Unmanned aerial vehicles (UAVs) have shown promising benefits in many applications. This has been enabled by the emergence of additive manufacturing (AM), which give the designers a large amount of geometrical freedom. In this paper, a novel design process of fused deposition modeling (FDM) combining both topology and infill optimization is introduced for AM of high performance porous structures. Tensile testing of FDM printed samples is first carried out to study the effect of the build orientation on the mechanical properties of acrylonitrile butadiene styrene (ABS) samples. It is found that samples built perpendicular to the load axis are the weakest with a tensile strength of 29 MPa and Young's modulus of 1960 MPa. The materials properties are fed to the finite elements analysis (FEA) for geometrical topology optimization, aiming to maximize stiffness and reduce weight of those parts. Afterwards, an infill optimization is carried out on the topology optimized parts using different mesostructures such as honeycomb, triangular, and rectangular to achieve high structural performance. The results showed that triangular pattern with 50% infill density had the lowest developed stresses, less mass, and strain energy when compared to other structures. Optimum UAVs parts of a quadcopter are successfully manufactured, assembled, and tested.

     

Modeling and Analysis of UAV-Assisted Mobile Network with Imperfect Beam Alignment

With the rapid development of emerging 5G and beyond (B5G), Unmanned Aerial Vehicles (UAVs) are increasingly important to improve the performance of dense cellular networks. As a conventional metric, coverage probability has been widely studied in communication systems due to the increasing density of users and complexity of the heterogeneous environment. In recent years, stochastic geometry has attracted more attention as a mathematical tool for modeling mobile network systems. In this paper, an analytical approach to the coverage probability analysis of UAV-assisted cellular networks with imperfect beam alignment has been proposed. An assumption was considered that all users are distributed according to Poisson Cluster Process (PCP) around base stations, in particular, Thomas Cluster Process (TCP). Using this model, the impact of beam alignment errors on the coverage probability was investigated. Initially, the Probability Density Function (PDF) of directional antenna gain between the user and its serving base station was obtained. Then, association probability with each tier was achieved. A tractable expression was derived for coverage probability in both Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) condition links. Numerical results demonstrated that at low UAVs altitude, beam alignment errors significantly degrade coverage performance. Moreover, for a small cluster size, alignment errors do not necessarily affect the coverage performance.     

Container-Based Internet of Vehicles Edge Application Migration Mechanism

Internet of Vehicles (IoV) applications integrating with edge computing will significantly drive the growth of IoV. However, the contradiction between the high-speed mobility of vehicles, the delay sensitivity of corresponding IoV applications and the limited coverage and resource capacity of distributed edge servers will pose challenges to the service continuity and stability of IoV applications. IoV application migration is a promising solution that can be supported by application containerization, a technology forseamless cross-edge-server application migration without user perception. Therefore, this paper proposes the container-based IoV edge application migration mechanism, consisting of three parts. The first is the migration trigger determination algorithm for cross-border migration and service degradation migration, respectively, based on trajectory prediction and traffic awareness to improve the determination accuracy. The second is the migration target decision calculation model for minimizing the average migration time and maximizing the average service time to reduce migration times and improve the stability and adaptability of migration decisions. The third is the migration decision algorithm based on the improved artificial bee colony algorithm to avoid local optimal migration decisions. Simulation results show that the proposed migration mechanism can reduce migration times, reduce average migration time, improve average service time and enhance the stability and adaptability of IoV application services.     

Stature and seat position as factors affecting fractionated response time in motor vehicle drivers

Motor vehicle accident fatalities are a cause for concern internationally; all drivers need to selectively attend to environmental changes, and to react swiftly and appropriately. The focus of the present paper was to investigate the effect of stature and seat positioning on fractionated response time. Eighty four young South African adults spanning a range of statures from 1.48 m to 2.00 m were tested in two extreme seat positions (near and far) using a European designed car-shell. Significant differences (p < 0.05) in knee flexion angle, but not in reaction or movement times were identified. Separation of tallest (X 1.93 m) and shortest (X 1.56 m) subjects (n = 20) revealed no significant stature-related differences in response times. However, the tall group showed significantly improved results when seated in the far position and the short group when seated in the near position. The results indicate that correct seat positioning will exert a significant effect on the overall response time of the driver, which in turn will affect the braking distance whilst driving.     

大型点焊机器人特种作业程序镜像修正技术研究

以不锈钢列车车体点焊机器人作业路径规划编程为研究对象,针对车体对称部件,如左右侧墙点焊的的问题,提出点焊路径规划编程镜像的方法,引入X,Y,Z主轴以及龙门架E1轴系统偏差的修正和A,B,C旋转轴镜像处理的方法来调整焊钳位姿同时对焊接路径点焊位置修正镜像,并依据镜像规则在Windows环境下使用VC++语言开发了镜像程序生成器.通过仿真结果表明,该软件生成的镜像程序可与作业基准点完美衔接,最后在车间复杂环境下的实际运行验证了该方法的有效性.     

超空泡水下航行器定深控制研究

极高的航速使得对超空泡水下航行器的控制变得异常复杂. 为了对其深度进行有效控制, 必须对其纵平面运动特性进行研究. 本文首先建立了超空泡水下航行器的纵平面运动模型, 分析了其纵平面运动特性; 然后进行了控制算法的综合; 最后, 仿真及试验结果均验证了所设计的航行器纵平面运动控制算法的有效性. 试验结果表明该控制系统具有较高的控制精度. 本文的研究成果为进一步研究水下超空泡航行器的运动控制提供了必要的理论基础.