基于 GAN 网络的电力设施遥感图像去云算法研究

针对电力设施遥感图像云层遮挡问题,提出了基于生成对抗网络(GAN) 的遥感图像去云算法。以条件生成对抗网络 (cGAN) 为主体结构,在编码器自适应填充卷积,设计了基于 Soft Attention的递归神经网络模块,通过对所有特征节点增加 全局依赖关系来解决网络局部最优问题,通过空间信息转换提取关键信息,提高去云与重建效果。实验结果表明,方法对遥 感图像中云层遮挡去除效果较好,重建图像的结构相似性(SSIM) 与峰值信噪比(PSNR) 分别达到0.983与32.899,分别提高 了23.93%与8.86%,均优于其他改进型GAN 网络。研究的方法不仅为基于遥感图像电力设施识别提供了基础,深度学习 遥感图像处理应用提供了参考。     

对象随型粗糙面近红外单目视觉测量与基准图像自愈

针对复杂应用环境中近红外单目视觉位姿测量系统偏离预置合作目标对象后,无法完成位姿测量的特殊情况,提出一种以合作目标周边随型粗糙面图像为测量对象的单目视觉测量方法,以及图像受损后的动态自愈方法。通过将实时获取的随型粗糙面图像特征与预存基准图像特征进行匹配计算,完成特殊情况下的应急测量。同时,为减少随型粗糙面图像污染或受损后对位姿测量精度的影响,实时计算污染或受损程度并动态自愈基准图像特征。实验结果表明,以随型粗糙面为对象的位姿测量精度稍低于合作目标对象,但能够满足特殊情况下的应急使用需求,提高了测量系统的鲁棒性;当随型粗糙面图像污染或受损达到70%时,采用自愈处理与未做自愈处理相比,方位角测量误差减少72%以上,验证了基准图像自愈方法的有效性。     

Effects of a base coating used for electropolymerization of poly(3,4-ethylenedioxythiophene) on indium tin oxide electrode

Electropolymerization of poly(3,4-ethylenedioxythiophene) (PEDOT) films on indium tin oxide (ITO), using a very thin PEDOT:poly(styrene sulfonate) (PEDOT:PSS) film as a base coating, was carried out in a non-aqueous solution containing the monomer, an electrolyte and propylene carbonate by a two-electrode system. For comparison, PEDOT film electrodeposited on bare ITO substrate under the same condition was also presented. The PEDOT films deposited on these two substrates were characterized by scanning electron microscopy, energy disperse X-ray spectroscopy and Raman spectroscopy. The results indicate that the PEDOT film electrodeposited on bare ITO was not uniform, while the PEDOT film electrodeposited on PEDOT:PSS/ITO has better uniformity. The compositions of the different regions of PEDOT film electrodeposited on bare ITO and PEDOT:PSS/ITO were studied and discussed. Electrochromic devices (ECDs) based on PEDOT films electrodeposited on bare ITO and PEDOT:PSS/ITO were fabricated and characterized by UV-Vis-NIR spectrophotometric study. The results show that the display contrast of the ECD based on PEDOT film electrodeposited on PEDOT:PSS/ITO was improved over that on a bare ITO substrate.     

Ultralow feeding gas flow guiding growth of large-scale horizontally aligned single-walled carbon nanotube arrays

On the basis of the rational analysis about the fluidic property of the system, an ultralow gas flow chemical vapor deposition (CVD) strategy was designed to prepare large-scale horizontally aligned ultralong single-walled carbon nanotube (SWNT) arrays. SWNT arrays could be well obtained under extremely low feeding flow of 1.5 sccm in a 1 in. quartz tube reactor. It was confirmed that the tubes grew floatingly and could cross microtrenches or climb over micro-obstacles in ultraslow gas flow. SWNTs arrays also could be formed no matter the substrate was placed vertically or upside down. The growth mechanism was discussed. Both the buoyancy effect induced by gas temperature/density difference and gas flow stability played dominant roles. More attractively, simultaneous batch-scale preparation of SWNT arrays was realized by the ultralow gas flow strategy. This new strategy turns to be more abstemious, efficient, promising, and flexible compared with the high gas flow rate fast-heating CVD processes.     

Rapid growth of angle-confined large-domain graphene bicrystals

In the chemical vapor deposition growth of large-area graphene polycrystalline thin films,the coalescence of randomly oriented graphene domains results in a high density of uncertain grain boundaries (GBs).The structures and properties of various GBs are highly dependent on the misorientation angles between the graphene domains,which can significantly affect the performance of the graphene films and impede their industrial applications.Graphene bicrystals with a specific type of GB can be synthesized via the controllable growth of graphene domains with a predefined lattice orientation.Although the bicrystal has been widely investigated for traditional bulk materials,no successful synthesis strategy has been presented for growing two-dimensional graphene bicrystals.In this study, we demonstrate a simple approach for growing well-aligned large-domain graphene bicrystals with a confined tilt angle of 30° on a facilely recrystallized single-crystal Cu (100) substrate.Control of the density of the GBs with a misorientation angle of 30° was realized via the controllable rapid growth of subcentimeter graphene domains with the assistance of a cooperative catalytic surface-passivation treatment.The large-area production of graphene bicrystals consisting of the sole specific GBs with a tunable density provides a new material platform for fundamental studies and practical applications.     

DH型离心空压机旋转失速故障诊断及治理

旋转失速是压缩机的常见故障 ,但诊断该故障时易和其他故障相混淆。本文从旋转失速的振动机理出发 ,归纳了旋转失速的故障识别特征。旋转失速的特征频率是成对出现的 ,随流量的减少而降低。该故障特征在现场诊断时得到验证 ,并成功应用于现场诊断     

Growth and characterization of Pb0.97La0.02(Zr0.66Sn0.27Ti0.07)O3 antiferroelectric single crystals

Single crystals of Pb_0.97La_0.02(Zr_0.66Sn_0.27Ti_0.07)O₃ (PLZST) with the composition near the morphotropic phase boundary were grown by the flux method. The PbO–PbF₂–B₂O₃ system was used as a solvent. PLZST single crystals with the size of 4–6 mm are obtained and these crystals are slightly translucent after polishing. The splitting of (200) reflection peak indicates that the obtained crystals are of a single phase with tetragonal perovskite structure. The element contents of the grown crystals were measured by inductively coupled plasma atomic emission spectrometry. The chemical composition of the crystals is Pb_0.979La_0.014(Zr_0.666Sn_0.285Ti_0.049)O₃. Thermal properties and dielectric properties of PLZST single crystals were studied. The results show that flux-grown PLZST single crystals exhibit obvious endothermic processes and relaxor behaviors near the phase transition temperatures.     

A novel de-rusting method with molten salt precleaning and laser cleaning for the recycling of steel parts

Clean Technologies and Environmental Policy - Steel parts are a kind of high recovery value product for which de-rusting is the primary step in the recycling process. Laser cleaning is a popular...     

多智能方法及其融合系统在化工过程故障诊断中的应用

简要介绍了决策树、神经网络、K近邻等五种智能方法,提出了一种将这五种智能方法相融合的故障诊断系统,并将其应用在催化裂化装置上.通过对这五种智能方法及其融合系统的性能考察表明,融合策略发挥了各方法的优点,回避了它们的缺点,提升了系统的整体性能,其召回率为100%,精确度为98%.     

加氢装置加热炉易爆管部位的分析

重点介绍韩国蔚山炼油厂分馏塔底重沸炉火灾事故、中国石油化工股份有限公司洛阳分公司催化裂化柴油加氢装置反应进料加热炉火灾事故、茂名分公司渣油加氢脱硫装置分馏炉火灾事故、镇海炼油化工股份有限公司加氢裂化装置脱丁烷塔底重沸炉火灾事故的情况,找出加氢装置加热炉的易爆管部位,并通过分析总结,提出了易爆管部位的选材原则、设计改进方案及维护措施.