小型电动无人机航程航时估算模型

小型电动无人机通常采用锂电池、无刷电机和螺旋桨组成能源动力系统，飞行过程中锂电池的实际工作电压发生变化，但飞机的总重量不变，其航程航时的估算方法与传统的燃油飞机有所不同。为了准确评估动力系统对飞机设计的影响，建立了以锂电池为动力的电动飞机推进系统模型，通过与实验数据比较，验证了各部分模型的准确性。利用该动力系统模型，对某款小型电动无人机进行了航程和航时估算，结果表明本文的建模方法准确有效，航程航时估算接近实验数据，可作为小型电动无人机设计的重要参考。     

基于机器学习的空间翻滚目标实时运动预测

借助监督式机器学习（ML）方法，对空间翻滚目标的运动状态预测问题进行研究，为空间机器人抓捕空间翻滚目标提供可靠的数据依据。基于物理模型的运动预测方法依赖理想的建模假设，需要连续的视觉反馈信息，解决目标预测问题的能力有限。因此，本文采用机器学习中纯数据驱动方式的稀疏伪输入高斯过程（SPGP）回归方法进行空间翻滚目标的运动预测。给定空间翻滚目标运动状态的历史观测数据，通过连续优化真实观测数据，得到稀疏的伪训练数据集，进而在线快速预测目标的运动状态，预测的计算效率达到毫秒级。此外，利用马尔科夫链蒙特卡洛（MCMC）法处理连续优化过程，克服由于随机初始值造成的优化过程陷入局部极小值问题。利用Snelson数据验证了所提稀疏伪输入高斯过程回归方法的正确性，并通过4组仿真算例验证了所提方法对于空间翻滚目标运动预测的有效性和鲁棒性。     

复杂时变激励下失谐叶盘瞬态强迫响应分析

提出一种高效的失谐叶盘瞬态强迫响应分析方法，不同于传统的数值积分方法，该方法推导出瞬态强迫响应的解析表达式，能更为高效地预测失谐叶盘的瞬态强迫响应。首先，对叶盘的高保真有限元模型进行减缩建模，在精确地描述叶盘结构的动力学特性的前提下，极大的减少了模型的自由度数目。其次，模拟加速旋转的涡轮叶盘经过复杂流场时叶片表面上的气动载荷，并建立叶盘固有频率和振型随转速变化的数学函数；通过共振分析确定叶盘共振的转速区间并分析引起共振的激励阶次成分。最后，计算了不同旋转加速度和阻尼下叶盘的瞬态强迫响应，并对叶盘的失谐幅值放大因子进行研究。应用本办法对某86个叶片的涡轮叶盘进行了数值分析，结果表明，相同阻尼水平下，叶盘的瞬态强迫响应幅值随旋转加速度增加而降低，失谐幅值放大因子在瞬态条件下大于稳态条件下，最高可达30%。     

基于有向图模型的民机航空电子系统故障诊断

结合民机航电系统外场可更换单元或模块（LRU/LRM）的故障模式及影响分析（FMEA）、故障树 分析和实时性要求，设计了基于时间故障传播图（TFPG）的系统故障诊断元模型和领域模型，研究了基于逻 辑和时间一致性检验的故障诊断算法，使用后向推理和可信度度量列出候选故障集。以飞行管理系统为例，构 造了其功能失效的TFPG 模型，并通过仿真验证了基于TFPG 的诊断在滤除级联效应和关联驾驶舱效应中的有 效性。     

基于测试数据的卡箍非线性等效建模方法

为了快速准确地计算卡箍管路系统的振动响应，提出了基于测试数据的卡箍非线性等效建模方法。对卡箍直管系统进行低幅值激励的模态测试，利用试验数据对有限元模型进行修正，识别卡箍线性刚度、线性阻尼参数。对卡箍直管系统开展不同激励水平下的恒力测试，通过样条插值多项式法将恒力频响函数转换为恒位移、恒速度频响函数，并进一步识别卡箍非线性等效刚度、非线性等效阻尼，建立了考虑卡箍非线性的等效动力学模型。研究表明:该卡箍等效动力学模型的预测频响函数与试验频响函数的最大误差仅为-6.9%，可以有效地反映卡箍实际的刚度、阻尼特性，对解决卡箍管路系统的振动响应分析具有重要的指导意义。      

Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning

In aerospace industry, gears are the most common parts of a mechanical transmission system. Gear pitting faults could cause the transmission system to crash and give rise to safety disaster. It is always a challenging problem to diagnose the gear pitting condition directly through the raw signal of vibration. In this paper, a novel method named augmented deep sparse autoencoder (ADSAE) is proposed. The method can be used to diagnose the gear pitting fault with relatively few raw vibration signal data. This method is mainly based on the theory of pitting fault diagnosis and creatively combines with both data augmentation ideology and the deep sparse autoencoder algorithm for the fault diagnosis of gear wear. The effectiveness of the proposed method is validated by experiments of six types of gear pitting conditions. The results show that the ADSAE method can effectively increase the network generalization ability and robustness with very high accuracy. This method can effectively diagnose different gear pitting conditions and show the obvious trend according to the severity of gear wear faults. The results obtained by the ADSAE method proposed in this paper are compared with those obtained by other common deep learning methods. This paper provides an important insight into the field of gear fault diagnosis based on deep learning and has a potential practical application value.     

离心压缩机密封及空腔流动的一维/三维耦合建模研究

为了在保证数值预测精度的同时降低离心压缩机的建模复杂度,以一维密封泄漏计算替代完整的密封及空腔建模,开展了离心压缩机盖盘密封及空腔流动的源项建模方法研究。结果表明:基于源项方法的密封及空腔简化建模仅需在主流道建模基础上施加泄漏质量流量、总温和摩擦损失源项边界条件,即可较高精度地还原完整的盖盘密封及空腔建模的性能和关键流动细节。与完整建模相比,在全工况下源项建模预测的等熵效率的绝对偏差小于0.65%,总压比和等熵效率的相对性能偏差小于1%。该方法可在满足下游部件匹配设计精度需求的同时,减少50%以上的网格数量,并显著提高计算的经济性和收敛性。泄漏流量的计算精确度是影响源项建模法性能预测准确性的最关键因素,耦合建模可以采用一维计算中推荐的密封泄漏系数值。      

熔融沉积成型连续碳纤维增强尼龙蜂窝芯材的压缩特性

采用熔融沉积成型方法成形了连续碳纤维增强尼龙复合材料蜂窝芯材,并对不同测试方向的静态单轴压缩特性进行了表征分析,着重关注不同测试方向熔融沉积成形蜂窝芯材平面静态压缩破碎行为和能量吸收行为,并与纯聚合物基体进行对比。结果表明:X_1方向的压缩平台区域的力-位移曲线更加平滑稳定,且载荷值稍高于X_2方向,因此X_1方向更适用于能量吸收应用;此外,连续纤维的增强作用可使蜂窝芯材的平台载荷值得到明显提升。研究结果为连续纤维增强聚合物复合材料的空间增材制造提供理论基础。     

Modeling irregular small bodies gravity field via extreme learning machines and Bayesian optimization

Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Feedforward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELM-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for asteroid 25143 Itokawa and comet 67/P Churyumov-Gerasimenko show that ELM-based SLFN are able learn the desired functional relationship both globally and in selected localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for guidance and control in close-proximity operations near the asteroid surface.     

Simulating planetary wave propagation to the upper atmosphere during stratospheric warming events at different mountain wave scenarios

Parameterization schemes of atmospheric normal modes (NMs) and orographic gravity waves (OGWs) have been implemented into the mechanistic Middle and Upper Atmosphere Model (MUAM) simulating atmospheric general circulation. Based on the 12-members ensemble of runs with the MUAM, a composite of the stratospheric warming (SW) has been constructed using the UK Met Office data as the lower boundary conditions. The simulation results show that OGW amplitudes increase at altitudes above 30 km in the Northern Hemisphere after the SW event. At altitudes of about 50 km, OGWs have largest amplitudes over North American and European mountain systems before and during the composite SW, and over Himalayas after the SW. Simulations demonstrate substantial (up to 50–70%) variations of amplitudes of stationary planetary waves (PWs) during and after the SW in the mesosphere-lower thermosphere of the Northern Hemisphere. Westward travelling NMs have amplitude maxima not only in the Northern, but also in the Southern Hemisphere, where these modes have waveguides in the middle and upper atmosphere. Simulated variations of PW and NM amplitudes correspond to changes in the mean zonal wind, EP-fluxes and wave refractive index at different phases of the composite SW events. Inclusion of the parameterization of OGW effects leads to decreases in amplitudes (up to 15%) of almost all SPWs before and after the SW event and their increase (up to 40–60%) after the SW in the stratosphere and mesosphere at middle and high northern latitudes. It is suggested that observed changes in NM amplitudes in the Southern Hemisphere during SW could be caused by divergence of increased southward EP-flux. This EP-flux increases due to OGW drag before SW and extends into the Southern Hemisphere.