动态环境中多帧点云融合算法及三维目标检测算法研究

低线束激光雷达扫描的点云数据较为稀疏,导致无人驾驶环境感知系统中三维目标检测效果欠佳,通过多帧点云配准可实现稀疏点云稠密化,但动态环境中的行人与移动车辆会降低激光雷达的定位精度,也会造成融合帧中运动目标上的点云偏移较大。针对上述问题,提出了一种动态环境中多帧点云融合算法,利用该算法在园区道路实况下进行三维目标检测,提高了低线束激光雷达的三维目标检测精度。利用16线和40线激光雷达采集的行驶路况数据进行实验,结果表明该算法能够增强稀疏点云密度,改善低成本激光雷达的环境感知能力。     

Viscosity of binary mixtures. I. mono-, di-, and tri-n-butyl and -n-octylamine with cyclohexane

Viscosities for six binary mixtures of n-butylamine, di-n-butylamine, tri-n-butylamine, n-octylamine, di-n-octylamine, and tri-n-octylamine with cyclohexane have been measured at 303.15 K with an Ubbelohde suspendedlevel viscometer. Deviations of viscosities from a rectilinear dependence on mole fraction are attributed to H-bonding and to the size of alkylamine compounds. The application of the Eyring's theory of activation energy is examined. The free volume theory of Prigogine-Flory-Patterson (PFP) and the experimental excess enthalpy have been used to estimate excess viscosity ln = (ln / ₁ ⁰ – x ₂ ln ₂ ⁰ / ₁ ⁰ ) and corresponding free volume, enthalpy, and entropy contributions for five binary mixtures of tri-n-alkylamine: triethyl, tripropyl, tributyl, trihexyl, and trioctylamine with cyclohexane. A comparison of experimental and theoretical excess viscosities indicates a failure of the PFP theory when two components of the mixture differ considerably in size. The size difference contribution to excess viscosity is related to (V ₂ ^*1/2 – V ₁ ^*1/2 ), where V ₁ ^* and V ₂ ^* are hard-core volumes of two components of the mixture.     

汽车轮胎胎面磨损程度检测系统

汽车轮胎的安全性直接关乎交通安全和乘客的出行安全, 轮胎异常磨损容易导致爆胎, 严重磨损的轮胎时刻威胁着乘客的生命安全, 汽车在道路上飞驰的过程中主要磨损的是轮胎的胎面, 因此实现自动化的轮胎磨损检测很有必要. 本研究借助Visual Studio 2017开发平台, 采用C++编程, 使用OpenCV计算机视觉库的API接口结合自主编程的处理顺序, 实现了对轮胎图像的自动采集传输和处理分析, 该系统能精准提取轮胎胎面图像, 并通过分析胎面图像的灰度共生矩阵的特征值判定轮胎的磨损程度, 实现了针对轮胎胎面磨损的自动化检测系统.     

自适应序列生成的建筑能耗预测

提出一种基于强化学习的生成对抗网络(Reinforcement learning-based Generative Adversarial Networks,Re-GAN)能耗预测方法.该算法将强化学习与生成对抗网络相结合,将GAN(Generative Adversarial Nets)中的生成器以及判别器分别构建为强化学习中Agent(生成器)以及奖赏函数.在训练过程中,将当前的真实能耗序列作为Agent的输入状态,构建一组固定长度的生成序列,结合判别器及蒙特卡洛搜索方法进一步构建当前序列的奖赏函数,并以此作为真实样本序列后续第一个能耗值的奖赏.在此基础之上,构建关于奖赏的目标函数,并求解最优参数.最后使用所提算法对唐宁街综合大楼公开的建筑能耗数据进行预测试验,实验结果表明,所提算法比多层感知机、门控循环神经网络和卷积神经网络具有更高的预测精度.     

时空双仿射微分不变量及骨架动作识别

目的 人体骨架的动态变化对于动作识别具有重要意义。从关节轨迹的角度出发,部分对动作类别判定具有价值的关节轨迹传达了最重要的信息。在同一动作的每次尝试中,相应关节的轨迹一般具有相似的基本形状,但其具体形式会受到一定的畸变影响。基于对畸变因素的分析,将人体运动中关节轨迹的常见变换建模为时空双仿射变换。方法 首先用一个统一的表达式以内外变换的形式将时空双仿射变换进行描述。基于变换前后轨迹曲线的微分关系推导设计了双仿射微分不变量,用于描述关节轨迹的局部属性。基于微分不变量和关节坐标在数据结构上的同构特点,提出了一种通道增强方法,使用微分不变量将输入数据沿通道维度扩展后,输入神经网络进行训练与评估,用于提高神经网络的泛化能力。结果 实验在两个大型动作识别数据集NTU（Nanyang Technological University）RGB+D（NTU 60）和NTU RGB+D 120（NTU 120）上与若干最新方法及两种基线方法进行比较,在两种实验设置（跨参与者识别与跨视角识别）中均取得了明显的改进结果。相比于使用原始数据的时空图神经卷积网络（spatio-temporal graph convolutional networks,ST-GCN）,在NTU 60数据集中,跨参与者与跨视角的识别准确率分别提高了1.9%和3.0%;在NTU 120数据集中,跨参与者与跨环境的识别准确率分别提高了5.6%和4.5%。同时对比于数据增强,基于不变特征的通道增强方法在两种实验设置下都能有明显改善,更为有效地提升了网络的泛化能力。结论 本文提出的不变特征与通道增强,直观有效地综合了传统特征和深度学习的优点,有效提高了骨架动作识别的准确性,改善了神经网络的泛化能力。     

A synthetical development approach for rehabilitation assistive smart product–service systems: A case study

Digital transformation (DT), the combination of information, computing, communication and connectivity technologies, which has triggered an effective upgrade of different aspects of market strategy, customer experience etc. Nowadays, rehabilitation assistive devices (RADs) are evolving to be more digital, intelligent and personalized. Digitalization and servitization have fostered to an emerging business model—the smart product–service system (Smart PSS). Therefore, DT of the RADs’ industry advocates not only the design of products and functions, the more important is the management of service processes and resource integration. With the increase in the elderly and disabled population, the requirement for RADs is becoming more urgent. However, research on Smart PSS for RAD is still limited. The rehabilitation assistive smart product–service systems (RASPSS) was introduced into the development of RADs based on the “Design and Management of DT” strategy through the service design of assistive devices and user requirements analysis. Further, an integrated design of RAD and Smart PSS has been created, a development method of RASPSS proposed, the theoretical model of the Smart PSS based on RADs built. To specify the service framework, this case study discusses the development of a home rehabilitation assistive system for femoral stem fracture patients. This paper evaluates the usability of the system, the results of which prove usability and effectiveness of the RASPSS development method. The RASPSS development model is designed to meet needs of stakeholders, improve the user rehabilitation experience, promote the service innovation of Smart PSS, bring certain market benefits of rehabilitation aids and create social value.     

无线可充能传感器网络的锚点算法与移动设备调度研究

由于传感器的电池容量和存储容量有限,导致无法持续对传感器进行能量补充并收集传感器生成的感测数据。针对该问题,研究了周期性能量补充和数据收集问题,提出了一种用于充能和数据收集的方法,包括基于网格的算法(GBA)、基于支配集的算法(DSBA)和基于圆相交的算法(CIBA)。通过这三种方法或两两相结合的方法找到锚点集合,通过移动设备调度算法调度最小数量的移动设备来访问生成的锚点。仿真结果验证了所提方法的有效性。与联合能量数据采集(JEDA)算法、最小覆盖圆(SEC)算法相比,所提CIBA需要的移动设备数量最少,总移动距离也最短,具有良好的综合性能。     

基于余弦相似度的改进蝴蝶优化算法

针对蝴蝶优化算法（BOA）容易陷入局部最优和收敛性差等问题,提出一种多策略改进的蝴蝶优化算法（MSBOA）。首先引入余弦相似度位置调整策略,通过旋转变化算子和伸缩变换算子进行位置更新,从而有效地保持BOA的种群多样性;其次引入动态切换概率,来平衡BOA局部阶段和全局阶段的转换;最后增加混合惯性权重策略,以提高BOA的收敛速度。使用16个基准测试函数、Wilcoxon检验以及部分CEC2014函数来验证MSBOA的有效性和鲁棒性。仿真实验结果表明,与BOA和其他改进策略BOA及其他群智能算法相比,MSBOA在收敛精度和收敛速度上有明显的提升。     

航运物流企业数字化转型设计与效果分析

近年来航运业数字化的加速,凸显出传统航运物流企业日常运营中存在的服务匹配与结算缺乏自动化、业务数据因缺乏透明度而不作为可信证据采信等问题。区块链具有的透明化与可信等特点可以结合物联网与数字货币等技术帮助航运物流企业以数字化转型针对性地解决问题。因此,通过分析合理转型路径,设计基于“蚁群-智能合约”算法作航运服务自动化匹配、基于区块链与物联网提供运输进程可靠追踪服务及基于数字货币实现海运运费高效结算。以太坊测试链上的模拟结果表明了转型方案的有效性,其对内降低运营与结算成本、对外增强业务信息透明度与可信度的价值,提高了航运物流企业的竞争力。     

Fault estimation for aero‐engine LPV systems based on LFT

In this paper, a fault estimator with linear fractional transformation (LFT) parameter dependency is designed for the linear parameter‐varying (LPV) system of the aero‐engine with both sensor and actuator faults under disturbances. After an aero‐engine affine parameter‐dependent LPV model is derived by the linear fitting method and matrix pseudo‐inverse method, the LPV model with disturbances and fault signals is transformed into a LFT structure. Based on the full block S‐procedure, the sufficient condition for the existence of the fault estimator is proposed, which can lead to less conservative results. Then the fault estimator design algorithm which can adjust to the current system dynamic adaptively is presented. Finally, a fault estimator is designed for a turbofan aero‐engine under multiple types of faults and disturbances to demonstrate the effectiveness of the proposed method.