One‐shot radical polymerization of vinyl monomers with different reactivity accompanying spontaneous delay of polymerization for the synthesis of double‐network hydrogels

Double‐network hydrogels were conveniently synthesized by the one‐shot radical polymerization of an ionic monomer for the first network and a non‐ionic monomer for the second network in the presence of crosslinkers by simultaneous addition of the monomers, that is, one‐shot and spontaneous two‐step polymerization accompanying the delay of polymerization of a second network monomer. We analyzed the polymerization process based on the conversion of each monomer during the reaction in the absence of crosslinkers. Then we fabricated the double‐network hydrogels using several polymerization systems consisting of a conjugated monomer and a non‐conjugated monomer in the presence of the dual crosslinkers. We analyzed the swelling, mechanical and viscoelastic properties of hydrogels synthesized by one‐shot radical polymerization to confirm the production mechanism and the network structure of the hydrogels. © 2020 Society of Chemical Industry     

基于高斯混合隐马尔科夫模型与人工神经网络的紧急换道行为预测方法

为了有效降低因驾驶员紧急换道行为而诱发的交通事故，提高道路交通事故链阻断效率，提出一种基于高斯混合隐马尔科夫模型（GMM-HMM）和人工神经网络（ANN）的紧急换道行为预测方法。首先利用GMM-HMM对车辆行驶状态以及驾驶行为连续观察序列进行换道意图辨识，采用ANN预测下一时段的驾驶行为，再预测换道过程中的横向加速度变化率，从而判断紧急换道的危险程度。驾驶员在环仿真实验及实车实验结果表明，该方法预测避险成功率达92.83%，实验避险成功率达90.32%。该方法能有效地对紧急换道行为进行提前警告与干预。     

基于网络数据统计的食品欺诈研究分析

目的 建立符合我国国情的食品欺诈数据库, 补充国际上已建立的经济利益驱动型掺假(economically motivated adulteration, EMA)数据库空白。方法 搜集2001~2019年发生的食品欺诈行为, 初步建立具有中国国情的食品欺诈数据库。对数据库中信息完备的454条欺诈数据进行分析。结果 媒体报道数据占食品欺诈信息总数的71.6%; 食用农产品、酒类、乳制品、肉制品等11类产品是欺诈事件发生较多的食品类别; 产品欺诈(72.2%)高居食品欺诈类型的首位; 2001~2019年食品欺诈事件数量呈现出先上升后降低, 再上升再降低的“M”状趋势; 目前食品欺诈检测技术主要以理化分析技术为主, 针对的食品类别还有限; 食品欺诈信息以中国为主(89.0%), 涉及到世界各个地区。结论 食品欺诈是广泛存在的全球性问题, 本研究建立的食品欺诈数据库为预防食品安全风险起到了重要的技术支撑作用。     

Zone model predictive control for pressure management of water distribution network

In the water distribution network (WDN), although the water demand of the node is changing constantly, the water quantity and water pressure of the node need to be met at each moment. To realize energy saving and consumption reduction, it is proposed to control the nodal water head of WDN in an appropriate narrow range. The frequent large fluctuation of the water demand, which may lead the water pressure exceed the expected range, increases the difficulty of the zone control. To realize optimized WND control, a novel zone predictive control is proposed, where two switching cases are considered. The switching condition is whether there are feasible solutions to keep the pressure within the expected region over the prediction horizon. When the condition is satisfied, the controller minimizes the variation of inputs with constraints of pressure range for ensuring the tank level staying within the expected zone and obtaining optimal economic cost. When the current pressure is out of the expected region or the condition is not satisfied due to the large variation of water demand, a reference trajectory of outputs is introduced, which is combined with the inputs as an optimization variable, and the constraints of expected zone are moved from the output to the introduced reference trajectory. Through minimizing the distance between reference trajectory and output, the controller will keep the tank level from deviating too far from the expected zone and will drive the tank level rapidly into the expected zone once the tank level exceeds the expected range. An application of the proposed zone MPC to WDN in Shinan District of Shanghai is given to illustrate its effectiveness.     

SFEP文本因果关系提取及其与SFN转化研究

为将系统故障演化过程(system fault evolution process，SFEP)的文本描述转化为空间故障网络(space fault network，SFN)结构，用于故障分析，本文提出SFEP文本因果关系提取方法，及其与SFN基本结构的转化方法。首先给出SFEP中事件的几种典型因果关系。随后提出因果关系与SFN基本结构的转化流程。本文方法围绕着关键字和因果关系组模式展开，通过模型的不断学习补充和丰富关键字和组模式。最终使方法具备将SFEP文本转化为SFN结构的能力。以飞机起落架故障发生过程文本为例进行了应用，实验结果表明该方法可用于SFEP文本中的因果关系分析，并得到了理想的SFN。完善的关键字和组模式有利于使用计算机智能处理SFEP的SFN。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

基于多元神经网络融合的分布式资源空间文本分类研究

针对实体产业对科技资源的服务需求,以服务效应作为资源文本分类标准,提出一种基于多元神经网络融合的分布式资源空间文本分类模型。设计了包含词嵌入层、卷积层、双向门控循环单元层、注意力机制层和softmax层的多元神经网络通路;在此基础上采用基于需求—效应—资源分类策略,完成了从定性科技资源需求到定量资源服务效应求解,再到定性科技资源输出的映射变换,重点解决了分布式科技资源局部和全局语义特征形式多样、文本长距离依赖特征显著、重要资源信息难以准确识别的问题,进而从分布式科技资源空间中快速准确地获取效应知识,提升实体产业产品研发效率和创新能力;通过万方专利科技资源数据集验证了所提方法的可行性和有效性,为更加全面地挖掘资源文本特征和按需服务实体产业提供了一种新的思路和手段。     

Microscopic investigation of the formation of a thermoset wheat gluten network in a model system relevant for bread making

Although the impact of heat on molecular properties of wheat gluten is well understood, changes in its microstructure have rarely been studied. Here, formation of the thermoset gluten network in a model system relevant for bread baking was studied with confocal laser scanning microscopy and protein network analysis. From 65 °C onwards, gluten converts from thick aligned protein strands in a highly branched and homogeneous network of small thin protein threads. Neither gliadin incorporation in the network nor application of aqualysin 1, the thermo-active serine peptidase from Thermus aquaticus which recently has been reported to hydrolyse gluten proteins in dough only at temperatures exceeding 80 °C, impacts on the gluten microstructure. As starch causes structure setting itself and thereby decreases protein mobility, molecular scale changes in the gluten network at temperatures exceeding 80 °C brought about by aqualysin 1 do not impact its microstructure.     

基于稳定连接的配电网边缘划分方法及应用研究

随着能源互联网的建设,为了应对配电主站所面临的数据接入和计算压力,文章提出了二级配电网边缘架构,以分布式边缘智能架构缓解主站压力。主要从边缘定义、划分方法、边缘功能描述与交互描述4个方面对所提边缘架构进行介绍。提出电网稳定连接区域概念及其生成方法,并结合南京地区电网实例,说明了以电网稳定连接区域作为边缘划分的合理性。最后,对所提边缘架构在配电网中的实际应用场景进行了设计和展望。     

基于混合时间序列卷积神经网络的轴承故障诊断

在传统滚动轴承故障诊断中,绝大多数方法采用了从振动信号提取特征的诊断模式,但是这种模式必然会使原始信号降维进而导致故障信息的丢失。卷积神经网络(CNN)通过权重共享和稀疏连接直接对原始信号进行操作,实现自适应特征提取,最大化保留故障信息。受CNN原理启发,开发出了一种基于工业振动信号特征的新型诊断框架,称之为混合时间序列CNN(HTS-CNN)。首先,利用估计总体比例的方法自适应确定模型训练样本数目;其次,通过对时间序列片段进行随机组合的方式,使模型能够提取非相邻信号特征;最后,利用Softmax激活函数在模型输出端执行多分类任务。通过对凯斯西储大学及CUT-2平台轴承数据进行分析,实验结果表明:该方法能够准确、有效的对滚动轴承故障进行分类。