计及用电行为模式的区域商业建筑负荷预测方法

为充分利用智能电表采集的细粒负荷数据并提高区域商业建筑负荷预测的精确度,提出一种基于用电行为模式的区域商业建筑负荷预测方法。首先,基于均值方差归一化方法对采集到的负荷数据进行标准化处理,通过肘方法确定聚类数目后进行k-Shape聚类,实现区域商业建筑负荷不同用电行为模式的提取;其次,针对大规模商业建筑负荷预测问题,考虑区域内大量商业建筑负荷预测时耗费大量内存资源却难以实现较准确预测问题,提出一种改进的Informer模型,该模型通过聚类算法识别具有相似用电行为模式的商业建筑,并充分考虑智能电表采集的异常负荷数据对模型训练结果的影响,能够良好的解决大规模商业建筑负荷预测精度不高问题;最后,采用加利福尼亚州商业建筑负荷进行实验,实验结果表明所提方法能够有效提高区域商业建筑负荷预测精度。     

Solar-Driven Interfacial Evaporation Accelerated Electrocatalytic Water Splitting on 2D Perovskite Oxide/MXene Heterostructure

The rational design of economic and high-performance electrocatalytic water-splitting systems is of great significance for energy and environmental sustainability. Developing a sustainable energy conversion-assisted electrocatalytic process provides a promising novel approach to effectively boost its performance. Herein, a self-sustained water-splitting system originated from the heterostructure of perovskite oxide with 2D Ti₃C₂T_x MXene on Ni foam (La_1-xSr_xCoO₃/Ti₃C₂T_x MXene/Ni) that shows high activity for solar-powered water evaporation and simultaneous electrocatalytic water splitting is presented. The all-in-one interfacial electrocatalyst exhibits highly improved oxygen evolution reaction (OER) performance with a low overpotential of 279 mV at 10 mA cm⁻² and a small Tafel slope of 74.3 mV dec⁻¹, superior to previously reported perovskite oxide-based electrocatalysts. Density functional theory calculations reveal that the integration of La_0.9Sr_0.1CoO₃ with Ti₃C₂T_x MXene can lower the energy barrier for the electron transfer and decrease the OER overpotential, while COMSOL simulations unveil that interfacial solar evaporation could induce OH⁻ enrichment near the catalyst surfaces and enhance the convection flow above the catalysts to remove the generated gas, remarkably accelerating the kinetics of electrocatalytic water splitting.     

一种多塔中波天线的设计与仿真

占地面积大、征地成本高、场地限制不好布设等问题一直严重制约中波天线的建设。 为了减少中波天线占地面积,提高铁塔的利用率,对天线布局和天馈网络进行优化设计,研究双频共塔匹配网络、阻塞网络和共址多塔天线辐射特性,给出三塔六频率的解决方案。最后,通过仿真论证,给出对应的网络、天线几何结构和辐射性能参数。     

Face aging with pixel-level alignment GAN

Applied Intelligence - Face aging is of great significance in cross-time identity verification problem. However, there is still a huge gap between the synthesized face image and the real face in...     

Effects of microstructure on fatigue crack propagation behavior in a bi-modal TC11 titanium alloy fabricated via laser additive manufacturing

In this study, the crack propagation behaviors in the equiaxed and equiaxed-columnar grain regions of a heat-treated laser additive manufacturing (LAM) TC11 alloy with a special bi-modal microstructure are investigated. The results indicate that the alloy presents a special bi-modal microstructure that comprises a fork-like primary α (α_p) phase surrounded by a secondary α colony (α_s) in the β phase matrix after the heat treatment is completed. The samples demonstrate a fast crack growth rate with larger da/dN values through the equiaxed grain sample versus across the equiaxed-columnar grain sample at low ΔK values (<13.8). The differences that are observed between the crack propagation behaviors (in the crack initiation stage) of the samples can be mostly attributed to the different size and morphology of the α_p lamellae and α_s colony within the grains in the equiaxed and columnar grain regions rather than the grain boundaries. The cracks prefer to grow along the α/β boundary with a smooth propagation route and a fast propagation rate in the equiaxed grain region, where the α_p and α clusters have a large size. However, in the columnar grain region, small and randomly distributed α_p lamellae generate a zigzag-shaped propagation path with a reduction in the da/dN value. Additionally, the change in the size of the α_p lamellae in the equiaxed grains (heat affected bands, HAB) is also observed to influence the propagation behavior of the crack during the crack initiation stage.     

一种新型的无线网络入侵检测方法-动态自适应模板法

为了能够检测到无线网络系统中的已知和未知类型的入侵者,提高无线网络系统的安全性,本文提出了动态自适应模板法。该方法的基本思想是原有模板(分类结果)在聚类过程中不断更新,并且允许在聚类分析过程中构成新的模板。实验表明用该方法检测无线网络系统中的新型入侵者,准确率可达到98%。     

一种基于个体中心论的局部优化社区发现算法

随着社会网络网站的流行,虚拟社会网络中的社区发现成为一个热门研究领域.针对虚拟网络中总是以一个或多个个体为中心特点,提出了一个针对大规模社区网络的局部优化社区发现的算法,在一定程度上弥补了传统算法无法适应大规模网络的不足.实验表明与我们直观想象不同,虚拟网络中那些度最大的点并不一定适合于作为社区中心.     

基于免疫算法和反向传播神经元网络的无线网络入侵检测研究

为了能够检测到无线网络系统中已知和未知类型的入侵者,提高无线网络系统的安全性,在对网络数据分析和研究的基础上,提出一种基于免疫算法和反向传播神经元网络的入侵检测方法。首先利用免疫算法对网络数据进行预处理,再运用反向传播神经元网络对处理后的数据(程序)进行识别。实验表明用该方法检测无线网络系统中的新型入侵者是可行、有效的,检测入侵者的准确率可达到97%。     

吞吐量和延时约束下的片上通信结构的Pareto空间优化

SoC中各IP核之间的互连结构是决定片上系统性能的关键因素.近年来,片上互连通信结构的配置与优化成为SoC通信综合的研究重点和热点,而已有方法优化SoC互连通信结构的仿真速度较慢,支持设计自动化的能力较差,使用的单目标优化算法无法解决多个性能目标之间的冲突.针对以上不足提出了吞吐量和延时约束下的片上互连通信结构的自动配置与优化的方法,该方法提出了片上总线互连通信结构模板,使用事务级通信仿真和多目标演化算法,探索吞吐量和延时约束下的多目标Pareto空间.与已有的先进Srinivasan方法相比,该方法的吞吐量提高10%,传输延迟降低17%,有效提高了SoC互连通信结构的优化质量.