基于改进粒子群优化和极限学习机的网络安全态势预测

针对网络安全态势预测模型预测精度不高、收敛较慢等问题,提出了一种基于改进粒子群优化极限学习机（IPSO-ELM）算法的预测方法。首先,通过改进粒子群优化（PSO）算法中的惯性权重和学习因子来实现两种参数随着迭代次数增加的自适应调整,使PSO初期搜索范围大、速度高,后期收敛能力强、稳定。其次,针对PSO易陷入局部最优的问题,提出一种粒子停滞扰动策略,将陷入局部最优的粒子重新引导至全局最优飞行。改进粒子群优化（IPSO）算法既保证了全局寻优的能力,又对局部搜索能力有所增强。最后,将IPSO与极限学习机（ELM）结合来优化ELM的初始权值及阈值。与ELM相比,结合IPSO的ELM的预测精度提高了44.25%。实验结果表明,与PSO-ELM相比,IPSO-ELM的预测结果拟合度可达到0.99,收敛速度提升了47.43%。所提算法在预测精度和收敛速度等指标上明显优于对比算法。     

混沌精英哈里斯鹰优化算法

针对哈里斯鹰优化（HHO）算法存在的收敛精度低、收敛速度慢、易于陷入局部最优的不足,提出了一种混沌精英哈里斯鹰优化（CEHHO）算法。首先,引入精英等级制度策略,以充分利用优势种群来增强种群多样性以及提升算法收敛速度和精度;其次,利用Tent混沌映射调整算法关键参数;然后,使用一种非线性能量因子调节策略来平衡算法的开发与探索;最后,使用高斯随机游走策略对最优个体施加扰动,并在算法停滞时,利用随机游走策略使算法有效跳出局部最优。通过对20个基准测试函数在不同维度下进行仿真实验,来评估算法的寻优能力。实验结果表明,改进算法的表现优于鲸鱼优化算法（WOA）、灰狼优化（GWO）算法、粒子群优化（PSO）算法和生物地理优化（BBO）算法,性能较原始HHO算法有明显提升,验证了改进算法的有效性。     

无人机遥控指令加密方式的研究

介绍了无人机遥控指令的特点,提出对遥控指令进行加密的方式以实现更高的安全性;设计了基于序列密码的一次一密加密方案,通过分析遥控指令加解密的过程,给出了一种遥控指令的帧结构,更好地满足遥控指令高安全性、高可靠性的需求。     

Intelligent analysis method of dam material gradation for asphalt-core rock-fill dam based on enhanced Cascade Mask R-CNN and GCNet

Reasonable dam materials’ gradation design for asphalt-core rock-fill dams is one of the main ways to control permeability. It is a challenge to test whether it can meet the requirements of dam construction. The computer vision method provides a new idea for asphalt-core rock-fill dam material gradation testing. However, due to the characteristics of densely overlapping and multi-scale sizes of dam material particles, the traditional image segmentation methods and algorithms cannot achieve accurate segmentation of dam materials’ images, and it is hard to apply the segmentation result to quantify the gradation curve. In this research, the enhanced Cascade Mask R-CNN with ResNet and PAFPN (Path Aggregation Feature Pyramid Networks) is proposed. Multi-scale features extracted by ResNet and feature ensemble can be realized using PAFPN. Data augmentation (DA) and online hard example mining (OHEM) are also applied in segmentation model training. Moreover, the GCNet is proposed to calibrate the gradation curve. The nonlinear relationship between the real gradation and the one based on the segmentation results can be revealed and the model of dam materials’ gradation analysis can be established. In the research, the enhanced Cascade Mask R-CNN can achieve 84.2 mAP, which is higher than that of Cascade Mask R-CNN with 74.9 mAP. The effectiveness of the proposed module and training strategies is proved using ablation experiments. The average error of each level for the gradation calibration using GCNet is 0.55%, 1.87%, 2.22%, 1.18%, and 2.42% respectively. The accuracy can meet the requirements of hydraulic engineering construction, which verifies the effectiveness of the GCNet network for gradation calibration, and the research provides a new method and technology for intelligent gradation testing of the asphalt-core rock-fill dam.     

基于KELM-SAPSO的开关磁阻电机优化设计

开关磁阻电机由于其双凸极结构和铁芯磁通密度的高度饱和性,使得建立准确的非线性模型极其困难,传统的设计方法难以设计出最优方案。为了优化在起动过程中开关磁阻起动/发电机的转矩特性,缩短起动时间,首先采用传统设计方法设计了一台开关磁阻电机,并且选取了设计参数;然后针对非参数建模结构简单,容易辨识的特点利用核极限学习机进行非参数建模;最后使用模拟退火粒子群算法对平均转矩和转矩脉动进行多目标寻优。仿真结果表明,建立的非参数模型拟合精度高,优化后电机的平均转矩增加了3.95 N·m,转矩脉动减少0.23。仿真实验表明,核极限学习机和模拟退火粒子群相结合的算法适合于电机的设计与优化过程,具有参数设置少、泛化能力强、不易陷入局部最优解、耗时较少等优点。     

DNA-CTMA/a-Si:H bio-hybrid photodiode: A light-sensitive photosensor

Recently, considerable interest have occurred in the development of an organic-inorganic-based bio-hybrid photodiodes (Bio-HPDs) with metal-free, eco-friendly, and cost-competitive features for light-sensitive devices. This paper reports a bio-inspired optical absorber material for the fabrication of Bio-HPDs using n-type hydrogenated amorphous silicon (a-Si:H) and a natural deoxyribonucleic acid (DNA)-cetyltrimethylammonium chloride (CTMA) biomaterial. a-Si:H is inexpensive and abundant, and DNA-CTMA is metal-free and eco-friendly. A DNA-CTMA coating on n-type a-Si:H leads to a chemically stable material with increased absorption and effective ties of dangling bonds and interface state density. Analysis results showed that the rectification ratio (RR) of the Bio-HPD is found to be 4 times higher than reference PD. This indicates that the effective RR is improved by the DNA-CTMA layer since it creates molecular charge interactions between DNA-CTMA layer and a-Si:H substrate. Moreover, Bio-HPD shows a light photosensitivity (I_photo/I_dark) of 474 with more reliable and has longer life time. In addition, the formation and feasible charge transport mechanisms are discussed. This biomaterial can be used for the development of commercially viable and environmentally safe large-scale Bio-HPDs applications.     

Imitation of ancient black-glazed Jian bowls (Yohen Tenmoku): Fabrication and characterization

Yohen Tenmoku is a kind of famous black glazed Jian bowls made in ancient China. Here, imitations of Oil Spot Yohen Tenmoku were sintered at about 1280 °C in a shuttle kiln with oxygen flow. Microstructure characteristics and chemical compositions were investigated by a combination of X-ray based and photon based characterization methods. The results showed that quartz and mullite were the main crystalline phases in the bowl bodies. At the glaze surface of the bowl, the highly reflective red iridescence and the silvery appearance of Oil Spot patterns were resulted from the precipitation of hematite (α-Fe₂O₃) crystals. A detailed study has revealed the partially ordered microstructure within one Oil Spot which produced the striking optical effects.     

A novel codification and modified heuristic approaches for optimal reconfiguration of distribution networks considering losses cost and cost benefit from voltage profile improvement

Network reconfiguration is the process of changing the topology of distribution systems by altering the open/closed status of switches. Because there are many candidate-switching combinations in the distribution system, network reconfiguration is a complicated combinatorial, non-differentiable constrained optimization problem. In addition, the radiality constraint typically increases the intricacy of the problem. In this paper, to avoid create infeasible configuration, a new codification is proposed. The proposed codification is computationally efficient and guarantees to generate only feasible radial topologies all times. Also, in this paper, a modified heuristic approach for optimal reconfiguration in radial distribution systems is presented. Additionally, in order to economize voltage profile improvement, a number of new formulas have been represented. The effectiveness of the proposed method is demonstrated on balanced and unbalanced test distribution systems.     

基于一维卷积特征与手工特征融合的集成超限学习机心跳分类方法

融合手工特征和深度特征,提出了一种集成超限学习机心跳分类方法。手工提取的特征明确地表征了心电信号的特定特性,如相邻心跳时间间隔反映了心跳信号的时域特性,小波系数反映了心跳信号的时频特性。同时设计了一维卷积神经网络对心跳信号特征进行自动提取。基于超限学习机（Extreme leaning machine,ELM）,将上述特征融合进行心跳分类。由于ELM初始参数的随机给定可能导致其性能不稳定,进一步提出了一种基于袋装（Bagging）策略的多个ELM集成方法,使分类结果更加稳定且模型泛化能力更强。利用麻省理工心律失常公开数据集对所提方法进行了验证,分类准确率达到了99.02%,实验结果也表明基于融合特征的分类准确率高于基于单独特征的分类准确率。      

Fabrication and mechanical properties of laminated HfC–SiC/BN ceramics

Laminated HfC–SiC/BN ceramics were successfully fabricated by tape casting and hot pressing. Fully dense HfC–SiC ultra-high temperature ceramics with homogeneous structure were obtained. The introduction of the weak BN layer resulted in a slight decrease of the flexural strength but significantly improved the fracture toughness compared with monolithic HfC–SiC ceramics. The fracture toughness of laminated HfC–SiC/BN ceramics in the parallel direction peaked at 8.06 ± 0.46 MPa m^1/2, which increased by 115% than that of monolithic HfC–SiC ceramics. The composites showed non-catastrophic fracture behaviors in both parallel and perpendicular directions. It indicates that laminated structure design is a promising approach to obtain full density HfC–SiC ceramics with high fracture toughness.