基于激光多普勒测速法的2×106m/s2高冲击校准技术

在高冲击传感器动态性能校准中,实现高量程、宽脉冲激励是目前高冲击校准急需解决的问题。采用速度改变法校准原理,以气炮为激励源,利用激光多普勒测速方法测量砧体运动速度,建立高冲击校准系统。分析碰撞系统的作用原理,提出调整和控制激励脉宽的方法;分析测速误差,提出双光束差动侧向测速方法。实验结果表明:高冲击校准系统校准量程为2×106m/s2,激励脉宽在2×106m/s2时大于100μs,校准冲击灵敏度的扩展不确定度小于5%(k=2)。     

一种基于光照变化补偿的颜色识别方法

针对RoboCup中型组足球机器人比赛中光照变化会使颜色发生色彩漂移,影响颜色识别的准确性问题,提出一种基于光照变化补偿的颜色识别方法。该方法首先利用球的历史信息预测球的位置,然后在较小的区域内用基于色调直方图反向投影的方法找到球后,通过球的亮度直方图的变化计算出光照变化率,用于动态补偿颜色查找表。实验表明该方法能提高颜色识别的光照自适应性。     

基于神经网络的电子地图最优路径研究

现阶段电子地图的应用已经深入到各行各业,最优路径的查找及规划作为GIS的一个关键问题,成为研究的一个难点,本文提出一种基于Hopfield神经网络的方法来解决地图最优路径问题。以物流配送中的车辆路径最优化为例,先根据Hopfield神经网络模型研究基于Hopfield的最优路径算法,然后探讨和验证该算法的可行性、实用性,最后通过算例分析对该方法进行验证。     

图形图像制作软件中的色彩模式分析

色彩模式是在数字处理过程中处理色彩的基本标准,其是以颜色模型为基础,利用数字定量对颜色进行描述的方法。针对图形图像制作软件中的色彩模式进行分析。     

土石坝工程领域的若干创新与发展

我国高土石坝数量居世界之首,保证高坝大库建设与长期运行安全是国家经济和公共安全保障的重大需求。系统总结了长江科学院近年来在土石坝工程领域的若干创新与发展。提出了基于“旁压模量当量密度法”的粗粒料级配相似理论试验方法;介绍了研发的系列CT三轴仪,实现了粗粒料组构要素的定量测量;提出了三轴试验中加载板与试样之间由滑动摩擦变为滚动摩擦、整体式接触变为分散式接触的减摩新方法,研发了相关减摩装置;研制了大尺寸、高压力、微摩擦、刚柔复合加载的土工真三轴仪;揭示了粗粒料真实三维应力条件下的强度与变形变化规律、湿化与蠕变变形特性;构建了粗粒料三参量非线性K-K-G剪胀模型、六参数湿化模型、九参数蠕变数学模型及相应的参数确定方法;基于当量密度法的原创思想,提出了利用旁压试验间接确定超百米级深厚覆盖层现场密度的试验方法。上述研究成果可为高土石坝工程建设提供重要科技支撑。     

广东省东江流域显著水问题类型识别

通过构建流域水资源、水环境与水生态功能评价指标体系,采用ArcGIS自然间断点分级法分析广东省东江流域水资源、水环境与水生态3类涉水功能的空间格局特征,采用Spearman等级相关系数定量分析3类涉水功能间的交互作用,识别各地区显著水问题类型,并提出相应管控策略。结果表明：广东省东江流域水资源、水环境与水生态功能评价等级空间格局体现出显著的空间差异性;流域水资源、水环境与水生态功能间的交互作用类型为兼容;基于3类涉水功能评价等级及功能间交互作用类型,将广东省东江流域10个评价单元划分为水资源、水环境、水生态、水资源-水环境、水生态-水环境及非显著型6个显著水问题类型。     

白河、潮河底栖动物分布与特征研究

在对潮河和白河北京境内段底栖动物调查基础上,采用群落分析法并运用BI指数和Shannon-Wiener多样性指数进行水质评价.结果表明:本次共采集底栖动物44种,水生昆虫及幼虫占比最大.底栖动物种类丰富度白河优于潮河.河流评价结果显示,潮河和白河水质整体为优.BI指数法评价中,潮河和白河以清洁为主.Shannon-Wiener多样性指数评价结果中,白河以轻污染为主,潮河以中污染为主.BI指数法适用性较好,而且评价结果较为准确,评价结果对潮河、白河水质判别具有借鉴作用.     

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier.     

A Hybrid Planning Approach for Accompanying Information-gathering in Plan Execution Monitoring

Journal of Intelligent & Robotic Systems - In this work, we present a new mathematic model for the flight of a bird-scale flapping-wing aerial vehicle, in which the impacts of the wing inertia...     

Observer‐based Reliable Control for Discrete Time Systems: An Average Dwell Time Approach

This paper deals with the problem of reliable control for discrete time systems with actuator failures. The actuator is assumed to fail occasionally and can recover over a time interval. During the time of suffering failures, the considered closed‐loop system is assumed unstable. Using an average dwell time method and under the condition that the activation time ratio between the system without actuator failures and the system with actuator failures is not less than a specified constant, an observer‐based feedback controller is developed in terms of linear matrix inequalities such that the resulting closed‐loop system is exponentially stable. An example is included to demonstrate the effectiveness of the proposed approach.