Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging

Rotating machinery is widely applied in industrial applications. Fault diagnosis of rotating machinery is vital in manufacturing system, which can prevent catastrophic failure and reduce financial losses. Recently, Deep Learning (DL)-based fault diagnosis method becomes a hot topic. Convolutional Neural Network (CNN) is an effective DL method to extract the features of raw data automatically. This paper develops a fault diagnosis method using CNN for InfRared Thermal (IRT) image. First, IRT technique is utilized to capture the IRT images of rotating machinery. Second, the CNN is applied to extract fault features from the IRT images. In the end, the obtained features are fed into the Softmax Regression (SR) classifier for fault pattern identification. The effectiveness of the proposed method is validated using two different experimental data. Results show that the proposed method has a superior performance in identification various faults on rotor and bearings comparing with other deep learning models and traditional vibration-based method.     

联邦学习安全与隐私保护综述

联邦学习是一种新型的分布式学习框架，它允许在多个参与者之间共享训练数据而不会泄露其数据隐私。但是这种新颖的学习机制仍然可能受到来自各种攻击者的前所未有的安全和隐私威胁。本文主要探讨联邦学习在安全和隐私方面面临的挑战。首先，本文介绍了联邦学习的基本概念和威胁模型，有助于理解其面临的攻击。其次，本文总结了由内部恶意实体发起的3种攻击类型，同时分析了联邦学习体系结构的安全漏洞和隐私漏洞。然后从差分隐私、同态密码系统和安全多方聚合等方面研究了目前最先进的防御方案。最后通过对这些解决方案的总结和比较，进一步讨论了该领域未来的发展方向。     

Ka波段机载双模式干涉SAR系统设计及测量精度分析

为解决传统干涉合成孔径雷达(SAR)系统只能顺轨干涉或交轨干涉,无法兼顾高精度高程测量和速度测量的问题,开展了Ka波段机载双模式干涉SAR系统设计与干涉测量精度分析。基于Ka波段电磁波波长短、干涉相位敏感度好的特点,利用较短的干涉基线在同一干涉SAR系统中实现高精度干涉测高与测速,并介绍了所设计的Ka波段机载双模式干涉SAR验证系统。仿真结果表明:该系统具备高效率、高精度干涉测量能力,可获得亚米级的绝对测高精度和0.1 m/s的测速精度。     

临近空间大气中波红外辐射特性的数值分析研究

介绍了临近空间大气环境特点及其非局域热平衡状态的辐射传输计算方法。利用战略高高度辐亮度代码SHARC（Strategic high-altitude radiance code），计算了3—5 μm波段不同观测条件、光学现象及大气环境下的临近空间大气背景辐射。分析结果表明：临近空间中波红外辐射随观测天顶角的增大而增强，随太阳天顶角的增大而减弱；在38 km及75 km附近，临边背景辐射存在极大值；纬度越高，临边背景辐射的季节变化特征越明显。OH夜气辉和极光对背景辐射有重要增强作用。     

应用后缘装置的跨声速层流翼型多岛优化设计

高雷诺数状态下,自然层流技术(Natural laminar flow,NLF)是减小机翼表面湍流摩擦阻力的有效方法。然而由于层流翼面上大范围顺压梯度的存在使得后缘处的恢复压差更大,产生更强的激波。因此在减小摩擦阻力的同时又增加了激波阻力。本文采用后缘装置(Trailing edge device,TED)来控制翼型后缘处的激波强度,基于线性稳定性理论(Linear stability theory,LST)的eN方法对流动进行转捩判断,进而应用多岛并行多目标进化算法(multi-objective evolutionary algorithm,MOEA)以获得大范围层流区域和弱化激波强度为目标对翼型进行优化设计。优化结果表明合作均衡策略耦合进化算法可以快速地捕捉到该多目标问题的Pareto阵面解,阵面上翼型的波阻力和摩擦阻力性能较初始翼型大大改善。同时,采用后缘装置控制激波强度时,无论在设计点还是偏离设计点时,优化后翼型均具有良好的升阻力特性和鲁棒性。     

类IXV飞行器初期再入制导与姿态控制方法研究

摘要： 针对类IXV飞行器无翼式升力体构型及采用RCS/尾襟翼组合控制特点，研究其初期再入段的高精度制导与姿态控制方法.设计带过程约束的数值预测 校正制导律以提高制导系统的鲁棒性及精确性；根据其执行机构配置特点，设计基于RCS的航向控制律及基于RCS/气动舵的纵、横向复合控制律，并采用鲁棒伺服LQR技术进行控制参数快速设计.通过蒙特卡洛打靶仿真来验证算法的精度及鲁棒性.     

涡轮基组合循环发动机分布式控制系统通信网络混合拓扑结构优化方法

涡轮机组合循环(Turbine based combined cycle,TBCC)发动机控制系统通信网络拓扑结构是其分布式控制系统方案设计的重要部分,优化网络拓扑结构可提高发动机推重比和控制系统可靠性。本文基于智能优化算法提出TBCC分布式控制系统网络拓扑结构优化方法。基于图论建立TBCC几何模型和网格模型,以重量和可靠性为优化性能指标,同时考虑发动机表面高温区域以及控制节点的工作可靠性,分别采用粒子群算法和遗传算法优化星形结构中智能中央节点位置、中央节点的环形拓扑结构,获得星形-环形混合拓扑结构。仿真实例表明,基于本文方法优化所得的混合拓扑结构相较于星形集中式控制结构,系统重量降低了51.9%。     

A comparative study of ionospheric IRIEup and ISP assimilative models during some intense and severe geomagnetic storms

Three-dimensional (3-D) electron density matrices, computed in the Mediterranean area by the IRI climatological model and IRIEup and ISP nowcasting models, during some intense and severe geomagnetic-ionospheric storms, were ingested by the ray tracing software tool IONORT, to synthesize quasi-vertical ionograms. IRIEup model was run in different operational modes: (1) assimilating validated autoscaled electron density profiles only from a limited area which, in our case, is the Mediterranean sector (IRIEup_re(V) mode); (2) assimilating electron density profiles from a larger region including several stations spread across Europe: (a) without taking care of validating the autoscaled data in the assimilation process (IRIEup(NV)); (b) validating carefully the autoscaled electron density profiles before their assimilation (IRIEup(V)).The comparative analysis was carried out comparing IRI, IRIEup_re(V), ISP, IRIEup(NV), and IRIEup(V) foF2 synthesized values, with corresponding foF2 measurements autoscaled by ARTIST, and then validated, at the truth sites of Roquetes (40.80°N, 0.50°E, Spain), San Vito (40.60°N, 17.80°E, Italy), Athens (38.00°N, 23.50°E, Greece), and Nicosia, (35.03°N, 33.16°E, Cyprus). The outcomes demonstrate that: (1) IRIEup_re(V), performs better than ISP in the western Mediterranean (around Roquetes); (2) ISP performs slightly better than IRIEup_re(V) in the central part of Mediterranean (around Athens and San Vito); (3) ISP performance is better than the IRIEup_re(V) one in the eastern Mediterranean (around Nicosia); (4) IRIEup(NV) performance is worse than the IRIEup(V) one; (5) in the central Mediterranean area, IRIEup(V) performance is better than the IRIEup_re(V) one, and it is practically the same for the western and eastern sectors.Concerning the overall performance, nowcasting models proved to be considerably more reliable than the climatological IRI model to represent the ionosphere behaviour during geomagnetic-ionospheric storm conditions; ISP and IRIEup(V) provided the best performance, but neither of them has clearly prevailed over the other one.     

光敏推进剂激光烧蚀过程建模与仿真

相较于传统大卫星,微小卫星具有结构紧凑、质量轻便和成本低廉的特点。然而,受功率和质量负载的限制,微小卫星一般不装备推进系统,其航线也局限于近地轨道。为扩展微小卫星的功能,满足日益复杂的任务需求,需给其配备合适的微推进系统。固体推进系统具有结构简单、寿命长、可靠性高的优点,但无法重复启动。为得到可重复启动的固体微推进系统,设计了一种非自持燃烧的光敏推进剂,采用激光控制其燃烧。在背压为大气压的环境下,利用高速摄像机拍摄燃烧过程并记录燃速。之后,对光敏推进剂的激光烧蚀过程进行建模。分析结果表明:激光可控制光敏推进剂的燃烧,燃速与激光强度成线性关系;该光敏推进剂的最小激光点火强度为0.28 W/mm~2;燃速计算值与实测值的误差在10%以内,证明该数学模型具备工程应用价值。     

热防护系统损伤容限分析

建立了含初始矩形损伤的热防护系统(Thermal protection system,TPS)气动热分析的CFD数值模型,分析结果表明损伤区域侧壁出现了很高的热流密度峰值,并且迎风面侧壁峰值高于背风面,而损伤区域底部热流密度却很低。利用分析获得的热流密度建立了含损伤和无损伤TPS的有限元传热分析模型。分析结果表明:损伤的存在导致防热瓦最高温度急剧上升,超过其材料能承受的极限温度(1 500℃),防热瓦首先失效,而损伤对机体最高温度影响较小。最后进行了TPS损伤容限分析,在防热瓦极限温度约束下,外部热流密度最大值从100kW/m2增加到140kW/m2,矩形损伤宽度最大容许值从22.7mm减小到12.6mm,而弧形损伤宽度最大容许值从34.6mm减小到25.1mm,即随着外部热流密度最大值增加,损伤宽度的最大容许值降低,并且相同外部热流密度水平下弧形损伤宽度的最大容许值大于矩形损伤。