金属增材制造技术研究热点聚类分析

为深入分析金属增材制造技术分类和发展状况,采集中国期刊全文数据库(CNKI)收录的核心期刊上的768篇科技文献,借助文献分析可视化软件CiteSpace,对关键词聚类进行了全景式描绘,构建金属增材制造技术知识图谱,揭示该技术研究分类以及演化趋势。     

改进的多层感知机在客户流失预测中的应用

针对在传统的客户流失预测数据预处理中，使用one-hot编码处理离散属性导致数据维度增加及数据过于稀疏的问题，提出了两种基于多层感知机的改进后的客户流失预测模型。其主要思想是分别使用堆叠自编码器和实体嵌入两种方法对多层感知机进行改进，通过将离散属性的高维编码数据向低维空间映射，有效地减少了one-hot编码产生的稀疏数据，增加了离散属性值之间的关联度。在对两份公开的数据集进行交叉验证后的实验结果表明，改进后的模型既有效地提高了预测的准确度，又维持了传统多层感知机模型在并行化计算方面的优势。     

H∞ control for uncertain one‐sided Lipschitz nonlinear systems in finite frequency domain

The current article discusses the H_∞ disturbance attenuation control design problem for one‐sided Lipschitz systems in finite frequency domain. Models containing norm‐bounded parameter uncertainties, disturbances, and input nonlinearities are considered. By contrast to existing full frequency methods, the H_∞ controller is computed depending on the frequency ranges of disturbances. The finite frequency disturbance attenuation index is initially defined. Thanks to Finsler's lemma, sufficient and less conservative analysis conditions are also derived for the closed‐loop system. Then, synthesis conditions in the low, middle, and high frequency ranges as well as the whole frequency range, are formulated in terms of linear matrix inequalities. At last, to prove the effectiveness and the superiority of the proposed approach, a physical example is used and a comparative study is done.     

低活化马氏体钢热变形行为及机理型本构建模研究

利用Gleeble-3500热模拟试验机研究了低活化马氏体钢在变形温度为850～950 ℃、应变速率为0.001～1 s^-1条件下的热变形行为。建立了流变应力本构方程，并评估了该方程的预测能力。绘制了低活化马氏体钢在不同应变下的热加工图。结果表明：在较高的应变速率条件下，该材料主要发生动态回复，在较高变形温度和较低应变速率下具有明显的动态再结晶特征；本构方程的预测结果与实验结果符合良好；变形温度870～930 ℃、应变速率0.001～0.01 s^-1和变形温度920～950 ℃、应变速率0.3～1 s^-1分别是真应变为0.4和0.6下最优的热加工区域。     

基于云平台的矿井水害智慧应急救援系统与应用

随着云计算、物联网、大数据、人工智能等技术的发展,智慧应急救援已成为矿山安全生产监察的迫切需求。提出了基于云平台的矿井水害智慧应急救援服务体系,采用混合云架构,提供按需和弹性计算能力及存储资源。通过集成与挖掘所有可能的历史和实时数据,建立云环境下多源异构、大规模、跨领域、动态信息资源"一张图",推动信息资源共享,建设应急救援智库。在此基础上,研发了应急救援系统,实现数值模拟、预测预警、应急疏散、应急评估、人员设备管理等功能,支持矿山应急演练和应急决策,依托现代信息技术为矿井水害应急救援提供智能化的服务和管理,实现矿井水害事故预防、检测、预警、处置、评估等全过程动态管理和控制。     

“电网一张图”时空信息管理系统

文章首先总结了电力企业信息管理系统的现状,提出了多源信息管理系统融合集成的邦联、子集和完全融合3种方式,分析了3种方式的优缺点,以建设企业"互联网搜索"型数字引擎为目标,提出了融合基于本体的图数据库建模,多维关联与路径因果分析,和人机共生互动可视化决策于一体的企业信息管理系统技术发展趋势;在系统分析目前正在快速发展的图数据库技术与传统关系数据库之间的本质区别基础上,总结原创的电力图计算平台技术的特点;在此基础上讨论"电网一张图"在建设能源互联网时空信息管理平台数据关联索引图中的核心作用,提出了支持能源互联网建设的"电网一张图"时空信息管理系统的技术架构与特点,最后总结"电网一张图"时空信息管理系统在提高电网安全运行水平、提升客户服务水平、增强清洁能源消纳水平、改善经营绩效水平、以及为综合能源服务和建设能源生态等提供数据服务方面的广阔应用场景。     

Propagation and termination of an internal crack in continuously cast austenitic stainless steel analyzed by ∑ values and the Schmid factor

The formation mechanism of an internal crack was clarified from the viewpoint of the crystallography and thermal expansion. An inverse pole figure map obtained by EBSD pattern showed that the crack propagated along the grain boundaries having high ∑ values within the columnar zone. After the crack initiation, these positions were considered to undergo cracking followed by propagation toward the equiaxed side. Near the termination position, the grains ahead of crack propagation had a Schmid factor higher than 0.45 consuming elastic strain energy. Thermal expansion measurements showed that the grain with (0 0 1) orientation had the largest expansion while that with (0 1 1) the smallest. The grain boundaries neighboring the combination of (0 0 1) and (0 1 1) grains had the largest thermal stress. Therefore, thermal stress contributed to the initiation of cracking. It was thus proposed to enlarge the equiaxed zone to prevent cracking by discontinuing the crack propagation.     

小尺度交通信号灯的检测与状态识别

交通信号灯识别包括检测和状态识别，在智能交通系统中发挥重要作用。基于YOLOv3算法提出了一种交通信号灯检测与状态识别模型。针对交通信号灯相较于交通场景中其他目标具有尺度小的特性进行了算法的设计：降低骨干网络的下采样倍率以增加小尺度目标的特征描述能力；通过增大特征图的尺度来改进多尺度特征融合；引入广义交并比作为检测任务的损失函数来改进目标边界框的回归效果。同时，根据交通信号灯本身的特性，使用颜色和形状约束的方法对信号灯进行状态识别和类别验证。最后在公开的Bosch交通信号灯数据集上和实际的城区道路进行了实验验证。实验结果表明，所提出的算法能够提升交通信号灯识别的精度和召回率，识别准确率可以达到90%左右。     

Densely connected convolutional network block based autoencoder for panorama map compression

As a novel virtual reality (VR) format, panorama maps are attracting increasing attention, while the compression of panorama images is still a concern. In this paper, a densely connected convolutional network block (dense block) based autoencoder is proposed to compress panorama maps. In the proposed autoencoder, dense blocks are specially designed to reuse feature maps and reduce redundancy of features. Meanwhile, a loss function, which imports a position-dependent weight item for each pixel, is proposed to train and adjust network parameters, in order to make the autoencoder fit to properties of panorama maps. Based on the proposed autoencoder and the weighted loss function, a greedy block-wise training scheme is also designed to avoid gradient vanishing problem and speed up training. During training process, the autoencoder is divided into several sub-nets. After each sub-net is trained separately, the whole network is fine-tuned to achieve the best performance. Experimental results demonstrate that the proposed autoencoder, compared with JPEG, saves up to 79.69 % bit rates, and obtains 7.27dB gain in BD-WS-PSNR or 0.0789 gain in BD-WS-SSIM. The proposed autoencoder also outperforms JPEG 2000, HEVC and VVC in both BD-WS-PSNR and BD-WS-SSIM. Meanwhile, subjective results show that the proposed autoencoder can recover details of panorama images, and reconstruct maps with high visual quality.