战时装备管理仿真的马尔柯夫链

介绍了一种解决战时装备管理问题的系统仿真方法,给出了指标,建立了其马尔柯夫链模型,指出了其与上、下层的关联.     

反坦克直升机任务效率评估

军用直升机在初步设计时就需用运筹学（Ｏｐｅｒａｔｉｏｎｓ Ｒｅｓｅａｒｃｈ）方法评估其战斗有效性。直升机与坦克一对一战斗结果，胜负过程符合马尔柯夫随机过程（Ｍａｒｋｏｗｖ Ｐｒｏｃｅｓｓｅｓ）。直升机战斗有效性判据是作战兑换比，即损失一架直升机可击毁敌坦克数。本文分析这个过程，列出随机微分方程组，推导出作战兑换比公式，从百找出提高战斗有效性途径，使战斗有效性评估有数量概念。     

神经网络模型在TDNS准则中的应用研究

时域Neal-Smith（TDNS）准则源于频域Neal-Smith（FDNS）准则和阶跃目标跟踪准则,被广泛应用于纵向驾驶员诱发振荡（PIO）趋势的预测研究。在该准则采用的人机闭环系统中,广泛运用结构简单且能反映飞行员基本行为特征的拟线性驾驶员模型。但在实际情况中,驾驶员的行为通常具有高度的非线性,为了更精确地描述驾驶员的非线性特性,采用神经网络方法建立驾驶员模型。利用某机的试飞数据对神经网络进行了训练和测试,生成了神经网络模型。针对TDNS预测准则,建立了相应的仿真模型,通过仿真运算,得到了该飞机的P10预测结果。研究表明：相对于传统的驾驶员模型,神经网络模型能够更好与真实驾驶员相匹配;在TDNS评估准则中运用神经网络模型具有实际的意义。     

间断Galerkin有限元隐式算法GPU并行化研究

为了提高间断伽辽金（discontinuous Galerkin, DG）有限元方法的计算效率,围绕求解Euler方程,构建了基于图形处理器（graphics processing unit, GPU）并行加速的隐式DG算法。算法结合Roe格式进行空间离散,采用人工黏性法处理激波等间断问题,时间推进选用下上对称高斯-赛德尔（lower-upper symmetric Gauss-Seidel, LU-SGS）隐式格式。为了克服传统隐式格式固有的数据关联依赖问题,借助于本文提出的面向任意网格的单元着色分组技术,先给出了LUSGS隐式格式的并行化改造,使得隐式时间推进能按颜色组别依次并行,由于同一颜色组内算法已不存在数据关联,可以据此实现并行化。在此基础上,再结合DG算法局部紧致等特点,基于统一计算设备架构（compute unified device architecture, CUDA）编程模型,设计了依据单元的核函数,并构建了对应的线程与数据结构,给出了DG有限元隐式GPU并行算法。最后,发展的算法通过了多个二维和三维典型流动算例考核与性能测试,展示出隐式算法GPU加速的效果,且获得...     

基于改进BP网络的手写体汉字识别技术

研究了手写体汉字识别技术，采用改进BP算法进行网络训练，提高了算法的收敛速度。同时，利用神经网络完成了汉字识别系统的实现。实验表明系统较好地回避了汉字结构复杂、变形难以预测等问题，提高了识别效率。     

结合跳点引导的无人机随机搜索避撞决策方法

针对无人机在城市空域环境和密集交通流下的避撞决策问题，提出马尔科夫决策过程（MDP）和蒙特卡洛树搜索（MCTS）算法对该问题进行建模求解。蒙特卡洛树搜索算法在求解过程中为保证实时性而使其搜索深度受限，容易陷入局部最优，导致在含有静态障碍的场景中无法实现避撞的同时保证全局航迹最优。因此结合跳点搜索算法在全局规划上的优势，建立离散路径点引导无人机并改进奖励函数来权衡飞行路线，在进行动态避撞的同时实现对静态障碍的全局避撞。经过多个实验场景仿真，其结果表明改进后的算法均能在不同场景中获得更好的性能表现。特别是在凹形限飞区空域仿真模型中，改进后的算法相对于原始的蒙特卡洛树搜索算法，其冲突概率降低了36%并且飞行时间缩短47.8%。     

一种新的基于可解释性置信规则库的飞轮健康状态评估模型

飞轮系统的稳定运行对于航天器在轨安全影响重大，因而对飞轮系统进行健康状态评估至关重要。在进行飞轮系统健康状态评估建模时，不仅要求模型能够处理各种不确定性以保障评估结果的准确性，同时要求其具有透明合理的评估过程与可解释、可追溯的评估结果。因此，在深入研究置信规则库（BRB）建模方法的基础上，构建了一种新的基于可解释性建模的置信规则库（BRB-e）飞轮系统健康状态评估模型。首先，结合飞轮系统特征对模型的可解释性建模准则进行定义；在此基础上，设计了BRB-e评估模型的推理过程；然后，基于鲸鱼优化算法（WOA），提出了一种具有可解释性约束的BRBBRB-ee模型参数优化方法；最后，通过对某飞轮系统中轴承组件的评估案例研究，验证了模型在飞轮系统健康状态评估中的有效性。对比研究表明，BRBBRB-ee模型在评估结果准确性和评估过程可解释性方面具有一定的优势。     

一种自动化并行重叠网格隐式装配方法

重叠网格装配是处理计算流体力学领域多体相对运动问题的关键技术之一。针对常见重叠网格隐式装配方法中几何分析过程复杂、节点无差别并行查找操作影响并行装配效率等问题,提出一种高度自动化的重叠网格隐式装配方法。首先,基于协方差分析、切割盒子等快速算法,将壁面距离计算与贡献单元存在性判断解耦,实现网格组动态重叠关系的自动化识别;其次,结合集合分析,设计出并行化的自动挖洞算法;最后,通过快速查询方法建立重叠单元与贡献单元的插值关系。针对所实现的并行重叠网格隐式装配工具库,采用某五球体部件验证了自动挖洞逻辑的准确性,并通过机翼-挂架-外挂物（WPFS）模型检验了重叠单元与贡献单元插值关系的准确性。     

边缘图像自适应编码方法

边缘特征常被视作无人机视觉系统中的重要信息（比如在视觉导航时需用边缘特征识别障碍物），在实践中会遇到边缘图像数据量大的情况。针对边缘图像高效压缩问题，提出了边缘图像自适应编码方法。首先以边缘打包法的压缩比和边缘点所占比例为特征，建立Logistic回归模型，然后利用图像数据库对该模型进行离线训练获取模型参数，最后利用Logistic回归模型建立分类器，自适应地在边缘打包法和链码编码法中选择压缩比最高的方法对边缘图像进行压缩。对VOC2012图像数据库的测试结果表明，与常用压缩方法相比，提出的算法能提高压缩比5%左右，有效减少了数据量。     

考虑三维流动效应的自然层流短舱压力分布反设计

针对三维流动效应下非轴对称自然层流（NLF）短舱设计困难的问题，发展了一种基于机器学习技术的压力分布反设计方法。短舱参数化建模使用自由曲面变形技术（FFD），通过求解RANS方程和基于SST(Shear Stress Trans‐port）湍流模型的■转捩模型实现自然转捩预测，利用生成拓扑映射（GTM）模型建立短舱外形及其压力分布数据集与低维隐空间变量的映射关系，全局优化算法在隐空间高效寻优，获得与目标压力分布匹配的短舱气动外形，实现自然层流短舱的反设计。GTM模型建立了数据集在高低维度间的高精度映射关系，优化设计过程中无需反复调用CFD求解器，设计效率大幅提升。利用该方法对通气短舱进行三维优化设计，设计所得非轴对称短舱外表面的自然层流区最大长度达当地弦长的40.5%，比优化前延长了12.2%，验证了该方法在考虑三维流动效应下NLF短舱的优化设计能力。     

Prior-guided GAN-based interactive airplane engine damage image augmentation method

Deep learning-based methods have achieved remarkable success in object detection, but this success requires the availability of a large number of training images. Collecting sufficient training images is difficult in detecting damages of airplane engines. Directly augmenting images by rotation, flipping, and random cropping cannot further improve the generalization ability of existing deep models. We propose an interactive augmentation method for airplane engine damage images using a prior-guide...     

Design and analysis of a knowledge-aided radar detector for doppler processing

In this paper we discuss the combined use of a priori information and adaptive signal processing techniques for the design and the analysis of a knowledge-aided (KA) radar receiver for Doppler processing. To this end, resorting to the generalized likelihood function (GLF) criterion (both one-step and two-step), we design and assess data-adaptive procedures for the selection of training data. Then we introduce a KA radar detector composed of three elements: a geographic-map-based data selector, which exploits some a priori information concerning the topography of the observed scene, a data-adaptive training selector which removes dynamic outliers from the training data, and an adaptive radar detector which performs the final decision about the target presence. The performance of the KA algorithm is analyzed both on simulated as well as on real radar data collected by the McMaster University IPIX radar. The results show that the new KA system achieves a satisfactory performance level and can outperform some previously proposed adaptive detection schemes     

基于滑动时窗策略自适应优化支持向量机的航空发动机性能参数在线预测

针对传统航空发动机性能参数时间序列预测方法存在的不足,提出了基于滑动时窗策略自适应优化支持向量机(Support Vector Machine,SVM)在线预测模型。该方法解决了训练样本动态适应性差的特点和老旧数据信息影响预测模型精度的问题。在该方法中,滑动时窗策略实时更新时窗数据训练样本,最终误差预报准则(Final Prediction Error,FPE)自适应地确定嵌入维数,遗传算法(Genetic Algorithm,GA)则实时自适应优化SVM建模参数。应用航空发动机排气温度偏差值(Delta Exhaust Gas Temperature,DEGT)数据进行实例验证,结果表明基于滑动时窗策略的自适应GA优化的SVM (GASVM)在线预测模型比传统的GASVM预测模型预测精度有显著提高。进一步分析了预测模型不同时窗宽度对短期预测精度的影响,展示了1步～10步预测的效果,结果表明在线预测模型在不同时窗宽度下短中期(5步以内)预测效果良好且稳定。文中提出的在线预测模型可用于航空发动机性能参数的预测,实现对航空发动机未来性能变化的预警。     

Spectral Analysis of Optimal and Suboptimal Gyro Monitoring Filters

Gyro monitoring filters are used to estimate and correct gyro drift rates of local-level inertial navigation systems. Conventional gyro monitoring filters are usually designed based on a simplified model of gyro drift rate. Furthermore, the effectiveness of these filters-and of many filters of the "Kalman" type-is often measured in terms of the root mean square (rms) criterion in contrast to the spectral content criterion typical of classical Wiener filtering theory. This paper has two objectives: to propose a gyro monitoring filter which is based on a more detailed model of gyro drift rate; and to propose a method of filter performance evaluation which uses as criterion a measure of the spectral content of the error process. The proposed gyro monitoring filter is shown to have improved spectral contents resulting in superior navigation performance for the gyro error models used in the calculations (comparable to commercial-grade aircraft gyros).     

A generative deep learning framework for airfoil flow field prediction with sparse data

Deep learning has been probed for the airfoil performance prediction in recent years.Compared with the expensive CFD simulations and wind tunnel experiments, deep learning models can be leveraged to somewhat mitigate such expenses with proper means. Nevertheless, effective training of the data-driven models in deep learning severely hinges on the data in diversity and quantity. In this paper, we present a novel data augmented Generative Adversarial Network(GAN), da GAN, for rapid and accurate fl...     

Conditional self-attention generative adversarial network with differential evolution algorithm for imbalanced data classification

Imbalanced data classification is an important research topic in real-world applications, like fault diagnosis in an aircraft manufacturing system. The over-sampling method is often used to solve this problem. It generates samples according to the distance between minority data. However, the traditional over-sampling method may change the original data distribution, which is harmful to the classification performance. In this paper, we propose a new method called Conditional Self-Attention Generative Adversarial Network with Differential Evolution (CSAGAN-DE) for imbalanced data classification. The new method aims at improving the classification performance of minority data by enhancing the quality of the generation of minority data. In CSAGAN-DE, the minority data are fed into the self-attention generative adversarial network to approximate the data distribution and create new data for the minority class. Then, the differential evolution algorithm is employed to automatically determine the number of generated minority data for achieving a satisfactory classification performance. Several experiments are conducted to evaluate the performance of the new CSAGAN-DE method. The results show that the new method can efficiently improve the classification performance compared with other related methods.     

航空发动机传感器信号重构的K-ELM方法

针对航空发动机传感器信号重构,提出了评价核极限学习机（K ELM）模型性能的一种快速留一交叉验证方法.结果表明:该方法可以避免原始的留一验证方法N次模型的显式训练,将计算复杂度降低为原来的1/N（N为样本数目）.该算法可以快速准确评价核极限学习机的性能,为核极限学习机确定最优的核参数.      

Few-shot electromagnetic signal classification: A data union augmentation method

Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled data are difficult to obtain, which makes the best deep learning methods at present seem almost powerless, because these methods need a large amount of labeled data for training. When the training dataset is small, it is highly possible to fall into overfitting, which causes performance degradation of the deep neural network. For few-shot electromagnetic signal classification, data augmentation is one of the most intuitive countermeasures. In this work, a generative adversarial network based on the data augmentation method is proposed to achieve better classification performance for electromagnetic signals. Based on the similarity principle, a screening mechanism is established to obtain high-quality generated signals. Then, a data union augmentation algorithm is designed by introducing spatiotemporally flipped shapes of the signal. To verify the effectiveness of the proposed data augmentation algorithm, experiments are conducted on the RADIOML 2016.04C dataset and real-world ACARS dataset. The experimental results show that the proposed method significantly improves the performance of few-shot electromagnetic signal classification.     

柔性转子的优化平衡

本文提出一种柔性转子优化平衡准则—有约束的最小应变能准则,它能满足航空燃气涡轮发动机结构强度和性能一体化设计的要求。应用该准则时,平衡校正量(大小和方位)是优化参数,转子—支承系统的总应变能为目标函数;转子若干截面的振动幅值作为约束条件。选用了鲍威尔法和网格随机射线法,进行优化计算。编制了优化全过程的FORTRAN程序,并经算例和实验考核、验证。      

Effect of Noncoherent FSK Versus PSK on Waveform Error in PCM Telemetry

In a recent paper [1] the authors presented an optimization strategy for the transmission of analog data over a PCM telemetry link. Constraints imposed included real-time operation and both average and peak power limitations on the transmitter. The selected strategy used Karhunen-Loeve (KL) sampling, unequal bit assignments, optimum uniform quantizing, the natural code, and PSK reception. In this paper, the performance of the above system will be compared to the same system using noncoherent FSK reception instead of PSK. The performance criterion used for the comparison is the mean integral squared error criterion.