基于自适应径向基网络的舰船RCS统计特征识别方法

文章采用舰船RCS频域起伏序列的均值、标准差为识别特征向量,利用提出的基于样本密度的自适应径向基网络,进行舰船分类识别研究。自适应径向基网络采用改进的自适应PSO方法估计样本密度最优邻域半径,实现径向基网络中心的自适应选择。改进的自适应PSO方法采用能反映样本聚类特点的BWP指标为适应度评价函数,采用快慢结合的高斯自适应惯性权重调节策略,提高了最优样本密度邻域半径的搜索速度和精度。实验结果表明,自适应径向基网络能自适应获得径向基网络最优识别率对应的RBF中心及其位置分布,减少了对建模人员经验的依赖,提高了反舰导弹对舰船类型的识别分类能力。     

可拓模式识别算法中经典域的确定方法

可拓模式识别算法是根据各个关联度的对比来识别最终的模式,其中经典域区间的确定有着重要的作用。传统的经典域确定方法是基于数理统计学的,不适用于小样本数据,数据不完全以及数据分布未知等复杂情况。引入Bootstrap算法,并和传统的方法对比,更精确地确定了经典域区间。     

Plastic wrinkling prediction in thin-walled part forming process:A review

The precision forming of thin-walled components has been urgently needed in aviation and aerospace field. However, the wrinkling induced by the compressive instability is one of the major defects in thin-walled part forming. The initiation and growth of the wrinkles are interac-tively affected by many factors such as stress states, mechanical properties of the material, geometry of the workpiece and boundary conditions. Especially when the forming process involves compli-cated boundary conditions such as multi-dies constrains, the perturbation of clearances between workpiece and dies and the contact conditions changing in time and space, etc., the predication of the wrinkling is further complicated. In this paper, the current prediction methods were summa-rized including the static equilibrium method, the energy method, the initial imperfection method, the eigenvalue buckling analysis method, the static-implicit finite element method and the dynamic-explicit finite element method. Then, a systematical comparison and summary of these methods in terms of their advantages and limitations are presented. By using a combination of explicit FE method, initial imperfection and energy conservation, a hybrid method is recommended to predict plastic wrinkling in thin-walled part forming. Finally, considering the urgent requirements of com-plex thin-walled structures’ part in aviation and aerospace field, the trends and challenges in wrin-kling prediction under complicated boundary conditions are presented.     

DME Interference mitigation for L-DACS1 based on system identification and sparse representation

L-band digital aeronautical communication system 1 (L-DACS1) is a promising candi-date data-link for future air-ground communication, but it is severely interfered by the pulse pairs (PPs) generated by distance measure equipment. A novel PP mitigation approach is proposed in this paper. Firstly, a deformed PP detection (DPPD) method that combines a filter bank, correlation detection, and rescanning is proposed to detect the deformed PPs (DPPs) which are caused by mul-tiple filters in the receiver. Secondly, a finite impulse response (FIR) model is used to approximate the overall characteristic of filters, and then the waveform of DPP can be acquired by the original waveform of PP and the FIR model. Finally, sparse representation is used to estimate the position and amplitude of each DPP, and then reconstruct each DPP. The reconstructed DPPs will be sub-tracted from the contaminated signal to mitigate interference. Numerical experiments show that the bit error rate performance of our approach is about 5 dB better than that of recent works and is closer to interference-free environment.     

不同迎角下脊形前体绕流数值模拟研究

脊形前体有较强的背风涡流场,不同的前体形状对前体涡流场和气动力有很大的影响。本文针对脊形前体飞行器大迎角湍流大分离流动计算的困难,采用IDDES混合湍流模型,以及与之匹配的非定常算法,研究了不同来流迎角下脊形前体的气动特性,以及背风涡非定常演化、破裂的细致流动结构。选取了不同脊形角,以及不同上、下高宽比的脊形前体进行计算。计算结果表明,在迎角较小时,随着迎角的增大,前体主涡会逐渐增强,在迎角较大时,前体主涡破裂;在相同迎角下,脊形角较小时,前体涡较强,涡升力也更大;对于相同脊形角的前体,当上半截面高宽比较小时,前体主涡强度较大,前体涡破裂临界迎角较小,即会提前破裂。     

黄渤海晴空像元下雾霾识别的机器学习算法

为实时有效地识别和监测雾霾，选取2013年10月4日与10月5日的两景MODIS遥感图像，利用不同类型像元的光谱差异，基于神经网络模型，建立海上雾霾的遥感识别机器学习算法。经检验表明，在晴空条件下，机器学习算法反演精度相对较高，已超过98%，利用算法可以实现对中国近海上空雾霾的监测。     

存在干扰下的无人机中继站波束成形算法

无人机(UAV)通信具有部署快、使用灵活、通信质量好等优点,在无线通信领域具有广阔的应用前景。采用UAV作为中继站构成的增强型卫星通信网络经常受到各种干扰的影响,导致其性能急剧下降。以信干噪比(SINR)最大化为准则,UAV中继站发射功率满足要求为约束条件的优化问题的基础上,提出了一种基于最大瑞利熵的波束成形(BF)算法,得出最优权矢量。为了降低BF算法的实现复杂度,进一步提出了一种基于迫零(ZF)的次优BF算法。计算机仿真验证了这2种BF算法的有效性。     

简论高校实验课程的改革

实验教学是高等院校教学过程的一个重要环节,应建立新型的实验室管理模式,从开放实验室和改革教学方法两个方面出发,阐述了实验课程改革的必要性。     

基于离散粒子群算法的航空发动机总装工艺优化方法

为了提高航空发动机总装工作的效率与质量,加强对总装工序和总装机件的管控,量化不同总装人员工作任务量,提高发动机总装的一致性和可追溯性,提出了1种发动机总装分区优化方法。以改进的2进制粒子群算法为基础,平衡了发动机总装各区域的工作内容,最小化各总装区域的工作差异,增强了每个区域装配机件的关联度,提高了总装工作的并行度,从而提高了装配质量。以某型发动机总装区域划分工作为实例,通过上述算法进行了总装区域划分,量化了所有装配区域每一工序的具体装配内容,减小了不同装配区域间的机件差异,杜绝了缺件、剩件等装配问题。     

战斗机嵌入式训练系统中的智能虚拟陪练

智能化"实虚"对抗是现代先进战斗机嵌入式训练系统的重要功能需求。自主空战决策控制技术在未来空战装备发展中扮演关键角色。将当前的功能需求和发展中的技术结合起来,得到了空战智能虚拟陪练的概念。先进控制决策技术的引入使得智能虚拟陪练能够帮助飞行员完成复杂的战术训练,而训练中真实的对抗场景为技术的验证提供了理想的环境,大量的训练数据为技术的持续迭代优化提供了保障。作为可学习和进化的空战战术专家,智能陪练在人机对抗和自我对抗中不断优化,当其具备与人相当甚至超越人的战术能力时,可应用于未来的无人空战系统。智能虚拟陪练需要具备4项基本能力：智能决策能力、知识学习能力、对抗自优化能力和参数化表示能力。对其包含的关键技术进行了分析,提出并实现了一个基于模糊推理、神经网络和强化学习的解决方案,展示了其各项基本能力及目前达到的空战水平。未来更多的模型和算法可在智能虚拟陪练的框架中进行验证和优化。