增强神经网络辨识模型泛化能力的研究

神经网络(Artificial Neural Network,ANN)辨识模型的泛化能力是其最主要的性能之一,增强ANN模型的泛化能力也是近年来国内外有关专家学者研究的重点问题。大量研究表明,ANN模型泛化能力的改善与很多因素相关联,其中恰当的性能指标函数设计是一个重要影响因素。文中在分析常见的基于均方误差最小原则的性能指标函数基础上,通过加入ANN辨识模型权值间的延迟信息,进而获得一种改进型性能指标函数。通过仿真,验证了所设计的改进型性能指标函数对增强ANN辨识模型的泛化能力是有效的。     

Hail impact responses and residual tensile properties of CFRP T-joints

Hail impact is a major challenge encountered by aircraft in flight, and thus is a key concern in the design of damage-tolerant composite T-joints in aviation. The study uses the Z-pinning technique(the pre-hole insertion technology) in combination with fillets of two radiuses to manufacture four types of Carbon Fiber Reinforced Polymers(CFRP) T-joints. The T-joints are then subjected to hail impact tests at two energy levels, as well as post-impact quasi-static tensile tests.The results show tha...     

Parameter optimization for torsion spring of deployable solar array system with multiple clearance joints considering rigid–flexible coupling dynamics

In this paper, four novel evaluation indices and corresponding hierarchical optimization strategies are proposed for a deployable solar array system considering panel flexibility and joint clearance. The deployable solar array model consists of a rigid main-body, two panels and four key mechanisms, containing torsion spring mechanism, closed cable loop mechanism, latch mechanism and attitude adjustment mechanism. Rigid and flexible components are established by Nodal Coordinate Formulation and A...     

Selective thermal emission and infrared camouflage based on layered media

Infrared camouflage based on artificial thermal metasurfaces has recently attracted significant attention. By eliminating thermal radiation differences between the object and the background, it is possible to hide a given object from infrared detection. Infrared camouflage is an important element that increases the survivability of aircraft and missiles, by reducing target susceptibility to infrared guided threats. Herein, a simple and practicable design is theoretically presented based on a multilayer film for infrared stealth, with distinctive advantages of scalability, flexible fabrication, and structural simplicity. The multilayer medium consists of silicon substrate, carbon layer and zinc sulfide film, the optical properties of which are determined by transfer matrix method. By locally changing the thickness of the coating film, the spatial tunability and continuity in thermal emission are demonstrated. A continuous change of emissive power is further obtained and consequently implemented to achieve thermal camouflage functionality. In addition, other functionalities, like thermal illusion and thermal coding, are demonstrated by thickness-engineered multilayer films.     

Nightside 135.6 nm emission enhancements of mid/low latitudes during geomagnetic storms as observed by the ionosphere PhotoMeter (IPM) on the Chinese meteorological satellite FY-3D

IPM has detected nightside 135.6 nm emission enhancements over a wide latitude range, from the sub-auroral latitudes to the equatorial regions during geomagnetic storms. Our work, presented in this paper, uses the data of IPM to understand these 135.6 nm emission enhancements during of geomagnetic storms and studies the variations of total electron content (TEC) and the F₂ layer peak electron density (NmF2) in the region of enhanced emissions. Middle and low latitude emission enhancements are presented during several medium storms in 2018. The variations of both the integrated electron content (IEC) derived from the nighttime OI 135.6 nm emission by IPM and TEC from the International GNSS Service (IGS) relative to the daily mean of magnetically quiet days of per each latitude bin (30°≦geographic latitude < 40°, 15°≦geographic latitude < 30°, 0°≦geographic latitude < 15°, ?15°≦geographic latitude < 0°, ?30°≦geographic latitude < -15°, ?40°≦geographic latitude < -30°) are investigated and show that on magnetically storm day, IEC by IPM always increases, while TEC from IGC may increase or decrease. Even if both increase, the increase of IEC is greater than that of TEC. From the comparison of IEC and TEC during magnetic storms, it can be seen that the enhancement of the nighttime 135.6 nm emissions is not entirely due to the ionospheric change. The time of IEC enhancements at each latitude bin is in good agreement, which mainly corresponds to the main phase time of the geomagnetic storm event and lasts until the recovery phase. The available ground-based ionosonde stations provide the values of NmF2 which match the 135.6 nm emissions measured by IPM in space and time. The variations of NmF2 squared can characterize the variations of the OI 135.6 nm emissions caused by O⁺ ions and electrons radiative recombination. The study results show that the OI 135.6 nm emission enhancements caused by O⁺ ions and electrons radiative recombination (where NmF2 squared increases) are obviously a contribution to the measured 135.6 nm emission enhancements by IPM. The contribution accounts for at least one of all contributions to the measured 135.6 nm emission enhancements by IPM. However, where the NmF2 squared provided by ionosonde decrease or change little (where the OI 135.6 nm emissions cause by O⁺ ions and electrons radiative recombination also decrease or change little), the emission enhancements measured by IPM at storm-time appear to come from the contributions of other mechanisms, such as energetic neutral atoms precipitation, or the mutual neutralization emission (O+ + O-→2O + h? (135.6 nm)) which also occupies a certain proportion in 135.6 nm airglow emission at night.     

Optimum alternate material selection methodology for an aircraft skin

Weight penalty has been a challenge for design engineers of aerospace vehicles. Today’s high-efficiency combat aircraft undergoes intense stress and strain during flying missions, which require stronger and stiffer materials to retain structural integrity. Though metallic materials have been successfully used for the construction of aircraft structures and components, metals still have a low strength-to-weight ratio. This paper aims to develop an alternate optimised material selection methodolog...     

一种针对多光谱遥感图像的桥梁快速识别算法

提出了一种针对多光谱图像中桥梁的识别算法。首先,根据水体和背景地物在不同光谱波段的亮度差异,计算多光谱图像的水体指数得到水体增强图,搜索其具有明显双峰的直方图得到最优阈值,实现河流的完整提取；其次,利用桥梁的存在会导致局部水体的光谱异常,沿河流中间线进行潜在桥梁区域的快速提取；再进一步利用桥梁长度以及与河流的空间关系进行鉴别,有效剔除虚警。利用 SPOT4遥感影像进行实验,结果表明本文算法运算量小,对于多个桥梁的识别具有很好的实用性。     

固态激光武器系统指标设计与分析

针对固态激光武器技术的发展,利用其非相干合束的能量叠加作用机理,通过将激光束衍射、光束质量、湍流、跟瞄误差等因素归一化成远场光斑的扩展,对子口径发射时的指标进行仿真分析,并根据仿真结果、子口径与系统发射口径间的关系,对固态激光武器系统的单台激光器功率、合束数量、发射口径,以及光束质量、跟瞄误差等因素进行了综合分析,给出了一定输入条件下的武器系统指标备选方案。     

宜香1A及宜香品种成熟期倒伏指数研究

以籼型三系不育系宜香1A、Ⅱ-32A、冈46A和恢复系宜恢7633、宜恢7008、宜恢1525等为材料,研究了亲本和杂交后代的倒伏指数.结果表明,Ⅱ-32A的倒3节间抗倒能力极显著强于宜香1A;冈46A倒3节间的抗倒能力显著强于宜香1A;宜香1A和Ⅱ-32A所配品种倒3节间抗倒能力相当,都极显著优于冈46A 所配品种倒3节间抗倒能力.母本及其所配品种的倒2节间和倒1节间倒伏指数无明显差异.     

基于机器学习的二次电子发射唯象模型

基于机器学习和深度人工神经网络（artificial neural network，ANN）提出一种二次电子发射唯象模型。利用Vaughan模型生成先验数据集，用于训练生成描述二次电子发射一般规律的先验知识ANN模型，并在不同参数条件下验证了先验知识ANN模型的正确性。然后，分别利用银和铝合金材料的二次电子发射系数实验数据修正先验知识ANN模型，分别得到了描述两种材料的特异ANN模型。测试结果表明，特异ANN模型计算结果与实验结果相比的平均绝对误差较Vaughan模型和Furman模型降低了30%以上，与复合唯象模型精度相当或更高。在小样本条件下测试了二次电子发射ANN模型的正确性，验证了分步训练方式的有效性和二次电子发射ANN模型对于小样本集的适应性。提出的基于机器学习的二次电子发射唯象模型能够避免复杂的参数修正过程，能够基于先验知识提升模型对于小样本的适应性，能够实现二次电子发射系数的连续插值，适于在数值模拟软件中使用。