基于神经网络的导弹制导控制一体化反演设计

针对制导控制一体化(IGC)模型中的不确定性难以进行估计补偿的问题,提出了基于神经网络的IGC反演设计方法。首先,根据弹目相对运动关系以及导弹自动驾驶仪模型建立了三维空间中的IGC模型。其次,针对由目标机动引起的模型不确定性,提出应用高阶滑模微分器(SMD)对导弹导引头获得的弹目相对运动信息进行微分,从而估计出目标加速度的方法,然后考虑导弹自身由于参数摄动以及未建模动态引起的模型不确定性,应用SMD和神经网络模型进行在线逼近补偿,基于反演控制理论设计了带有SMD和神经网络模型的IGC算法,应用李雅普诺夫稳定性理论对所设计的控制算法进行了稳定性证明。最后,进行了导弹六自由度仿真,验证了所设计控制算法的有效性。     

空中交通拥挤的识别与预测方法研究

随着航空运输业的迅猛发展,空中交通拥挤现象日益严重,空中交通拥挤研究已经成为国际民航界的一个研究热点。其中,空中交通拥挤的识别与预测是空中交通拥挤研究的主要内容之一,在此基础上综述了国内外有关空中交通拥挤识别与预测方法的研究状况。首先概述了基于不同拥挤形成因素和拥挤后果的空中交通拥挤概念的研究状况;接着依据所用交通数据时间尺度的不同,分别针对基于短期数据的阈值判别方法、基于长期数据的聚类识别方法以及基于混合数据的综合评价方法综述了空中交通拥挤的主要识别方法;然后分别基于数理算法(统计算法、交通流模型算法和智能算法)和计算机仿真模拟技术综述了空中交通拥挤的主要预测方法;最后指出了空中交通拥挤识别与预测问题的近年研究热点和未来的研究方向。     

基于地面分布式数据中心的天地一体化网络

天地一体化网络通常具有覆盖范围广、数据传输量大等特点。现有的一体化网络研究侧重于网络间传输协议,以及如何有效管理网络资源等。但考虑到当前卫星网络数据处理能力相对较差,而地面网络发展已非常成熟,因此将一体化网络与数据中心网络融合,把数据中心网分布式地接入骨干光网络中,卫星作为网络的传输节点与地面分布式数据中心网络构成统一整体;以中国电信骨干网为基础,针对一体化网络的内部传输代价和外部请求代价等多种因素,进行折中,使用整数线性规划得到网络的最优化部署。所提出的网络架构能很好地满足一体化网络的要求,提供了一种具有竞争力的信息平台设计架构。     

网络图中边集束优化问题

网络规模增大和复杂度提高造成的节点遮挡覆盖和边交叉阻塞等问题成为网络可视化研究的热点.针对网络中出现的视觉凌乱问题,以空间位置和群组关系为出发点,从网络中独立的边和群组两个层次,以边汇合的角度研究边集束技术,将网络中临近的边集聚成束以降低视觉复杂度,提出和改进了分段力导引算法(FDA)简化模型和群组边相容的网络图边集束模型.其中分段集束模型,提出以二次样条曲线表示网络边,通过样条控制点进行迭代汇聚的方法,实现了网络中边的集束;针对分段集束模型中部分连线过度弯曲问题,提出通过CNM聚类算法将网络进行群组划分,在群组结构的基础上对组内连线应用边相容原则,根据连线的匹配系数计算其集束程度的方法,网络图集束后曲线扭曲变形减少,曲线过渡更加平滑.选取国内航空网络作为案例,通过两种边集束模型进行网络图简化,分析结果表明,国内机场的群组结构具有地理属性的相近性,航空网络在整体上呈现出明显的十字脉络,东西走向和南北走向的航线分别汇聚集结成束,表现了航空网络建设在南北和东西方向的总体趋势.本集束简化算法适用性广,绘制的网络图具有良好的视觉效果和可读性.      

基于LSTM的空间机器人系统惯性张量在轨辨识

在空间机器人抓捕目标的过程中,整个系统的惯性张量会随时间变化且在目标被捕获瞬间发生突变,这会严重影响整体姿态控制的精度。针对以上问题,提出了一种基于长短期记忆（LSTM）的系统惯性张量在轨实时辨识方法。首先,对于目标捕获前后的2个阶段,利用拉格朗日方程建立了空间机器人的动力学模型;然后,基于所建空间机器人模型采用域随机化方法生成足量训练数据,并用其对由LSTM网络与多层全连接网络构建的参数辨识网络进行训练;最后,使用训练好的参数辨识网络对系统惯性张量进行辨识。数值仿真结果表明：所提方法能够精确辨识空间机器人抓捕过程中的系统惯性张量,所研究系统的主惯量平均相对辨识误差小于0.001,惯性积的平均相对辨识误差小于0.01。     

基于Deform软件二次开发和BP神经网络的TA15多向锻造微观组织预报

通过热压缩实验构建了TA15合金的热变形真应力-应变曲线,以此为基础分别建立了合金双相区及单相区温度区间的热变形本构方程;基于热压缩试样动态再结晶的统计数据建立了TA15合金的动态再结晶模型。借助Deform提供的二次开发功能实现相关数学模型的程序化,制定正交实验方案,实现了TA15合金多向锻造变形的微观组织仿真。通过正交实验分析得出各项因子的影响对象及强弱差异,提出了双相区及单相区温度区间内的多向锻造最佳因子组合。建立了TA15合金多向锻造变形微观组织的BP （Back Propagation）神经网络预测模型,将预测结果与有限元仿真结果进行比较,结果表明两种方法的预测结果基本一致,但神经网络具备有限元仿真难以实现的良好细节预测能力,能更为细致地实现对微观组织分布状态的划分。     

The impact of orbital errors on the estimation of satellite clock errors and PPP

Precise satellite orbit and clocks are essential for providing high accuracy real-time PPP (Precise Point Positioning) service. However, by treating the predicted orbits as fixed, the orbital errors may be partially assimilated by the estimated satellite clock and hence impact the positioning solutions. This paper presents the impact analysis of errors in radial and tangential orbital components on the estimation of satellite clocks and PPP through theoretical study and experimental evaluation. The relationship between the compensation of the orbital errors by the satellite clocks and the satellite-station geometry is discussed in details. Based on the satellite clocks estimated with regional station networks of different sizes (∼100, ∼300, ∼500 and ∼700 km in radius), results indicated that the orbital errors compensated by the satellite clock estimates reduce as the size of the network increases. An interesting regional PPP mode based on the broadcast ephemeris and the corresponding estimated satellite clocks is proposed and evaluated through the numerical study. The impact of orbital errors in the broadcast ephemeris has shown to be negligible for PPP users in a regional network of a radius of ∼300 km, with positioning RMS of about 1.4, 1.4 and 3.7 cm for east, north and up component in the post-mission kinematic mode, comparable with 1.3, 1.3 and 3.6 cm using the precise orbits and the corresponding estimated clocks. Compared with the DGPS and RTK positioning, only the estimated satellite clocks are needed to be disseminated to PPP users for this approach. It can significantly alleviate the communication burdens and therefore can be beneficial to the real time applications.     

Instantaneous rainfall estimation using neural network from multispectral observations of SEVIRI radiometer and its application in estimation of daily and monthly rainfall

In the present paper, an artificial neural network (ANN) based technique has been developed to estimate instantaneous rainfall by using brightness temperature from the IR sensors of SEVIRI radiometer, onboard Meteosat Second Generation (MSG) satellite. The study is carried out over north of Algeria. For estimation of rainfall, weight matrices of two ANNs namely MLP1 and MLP2 are developed. MLP1 is to identify raining or non-raining pixels. When rainy pixels are identified, then for those pixels, instantaneous rainfall is estimated by using MLP2. For identification of raining and non raining pixels, 7 input parameters from the IR sensors are utilized. Corresponding data of raining/non-raining pixels are taken from radar. For instantaneous rainfall estimation, 14 input parameters are utilized, where 7 parameters are information about raining pixels and 7 parameters are related with cloud features. The results obtained show the neural network performs reasonably well.     

Strong geomagnetic activity forecast by neural networks under dominant southern orientation of the interplanetary magnetic field

The paper deals with the relation of the southern orientation of the north–south component _Bz$B_z$ of the interplanetary magnetic field to geomagnetic activity (GA) and subsequently a method is suggested of using the found facts to forecast potentially dangerous high GA. We have found that on a day with very high GA hourly averages of _Bz$B_z$ with a negative sign occur at least 16 times in typical cases. Since it is very difficult to estimate the orientation of _Bz$B_z$ in the immediate vicinity of the Earth one day or even a few days in advance, we have suggested using a neural-network model, which assumes the worse of the possibilities to forecast the danger of high GA – the dominant southern orientation of the interplanetary magnetic field. The input quantities of the proposed model were information about X-ray flares, type II and IV radio bursts as well as information about coronal mass ejections (CME). In comparing the GA forecasts with observations, we obtain values of the Hanssen–Kuiper skill score ranging from 0.463 to 0.727, which are usual values for similar forecasts of space weather. The proposed model provides forecasts of potentially dangerous high geomagnetic activity should the interplanetary CME (ICME), the originator of geomagnetic storms, hit the Earth under the most unfavorable configuration of cosmic magnetic fields. We cannot know in advance whether the unfavorable configuration is going to occur or not; we just know that it will occur with the probability of 31%.