基于知识图谱和自动机器学习的软件缺陷预测

不稳定和召回率低效的软件缺陷预测模型难以在行业领域应用，为解决稳定和高效各项性能评价指标的软件缺陷预测模型在工程实践应用的问题，提出了一种基于知识图谱和自动化机器学习的软件缺陷预测方法AutoKGGAS，首先获取软件缺陷预测模型数据，对知识建模、知识获取、知识融合、知识储存与知识计算等知识图谱构建技术研究，实现知识图谱推荐优质软件缺陷预测模型作为自动化搜索的热启动输入条件，根据不同的软件缺陷预测评价指标，优化不同最佳的模型结构.其次实证研究采用NASA开源数据集实验对象和六种性能评价指标，实验结果表明， AutoKGGAS自动化软件缺陷预测模型在不同数据集不同评价指标方面，性能优于知识图谱推荐的传统经典软件缺陷预测模型.自动化软件缺陷预测模型为航天软件缺陷预测辅助代码审查测试提供了原型，在工程实践应用方面具有重要的意义.     

一种基于元路径拥塞模式挖掘的移动对象位置预测方法

路网上移动对象位置预测是许多位置相关服务的基础。目前移动对象位置预测方法没有充分考虑到轨迹数据中所蕴含的道路拥塞信息,而路网上的道路拥塞状态对移动对象的位置更新会产生巨大影响。提出基于元路径拥塞模式挖掘的方法(Meta-congestion-pattern mining,MCPM)。在离线挖掘阶段,从历史轨迹的频繁路径(元路径)的紧集中挖掘当地的拥塞模式,并对运动模式进行建模,其中采用基于k均值的聚类算法解决数据稀疏性问题。在线预测阶段根据挖掘的拥塞模式和运动模式依概率进行预测。最后通过理论分析和实验验证得出了算法的有效性,与相同条件下的精度预测(WhereNext,WN)方法相比,平均预测准确性提高了近20%,预测时间平均缩短了近50%。     

Atmospheric reentry hemisphere prediction for prograde orbits using logical disjunction

A unique logic-based algorithm for atmospheric reentry hemisphere prediction is presented for spacecraft in low-eccentricity, prograde low Earth orbits at altitudes of 300 km and lower. Using two-line element (TLE) data for initial orbit conditions, coupled with coarse estimates for spacecraft aerodynamic characteristics, the algorithm relies on logical disjunction operations based on a dual analysis of histogram and two-weighted Gaussian probability density function (PDF) fits of predicted reentry latitude data. The algorithm requires the execution of a series of parametric simulations to determine the reentry hemisphere for variations in spacecraft aerodynamic coefficients and drag reference area. When implemented, the algorithm yields accurate hemisphere predictions on average 15 days from reentry as demonstrated by historical reentry cases from 1979 to 2018. All reentry cases were selected to demonstrate the algorithm’s ability to deliver accurate reentry hemisphere predictions for spacecraft with varying physical size and mass, and reentering during different periods of solar cycle activity.     

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。     

A progressive approach to predict shot peening process parameters for forming integral panel of Al7050-T7451

In this paper, a progressive approach to predict the multiple shot peening process parameters for complex integral panel is proposed. Firstly, the invariable parameters in the forming process including shot size, mass flow, peening distance and peening angle are determined according to the empirical and machine type. Then, the optimal value of air pressure for the whole shot peening is selected by the experimental data. Finally, the feeding speed for every shot peening path is predicted by regression equation. The integral panel part with thickness from 2 mm to 5 mm and curvature radius from 3200 mm to 16000 mm is taken as a research object, and four experiments are conducted. In order to design specimens for acquiring the forming data, one experiment is conducted to compare the curvature radius of the plate and stringer-structural specimens, which were peened along the middle of the two stringers. The most striking finding of this experiment is that the outer shape error range is below 3.9%, so the plate specimens can be used in predicting feeding speed of the integral panel. The second experiment is performed and results show that when the coverage reaches the limit of 80%, the minimum feeding speed is 50 mm/s. By this feeding speed, the forming curvature radius of the specimens with different thickness from the third experiment is measured and compared with the research object, and the optimal air pressure is 0.15 MPa. Then, the plate specimens with thickness from 2 mm to 5 mm are peened in the fourth experiment, and the measured curvature radius data are used to calculate the feeding speed of different shot peening path by regressive analysis method. The algorithm is validated by forming a test part and the average deviation is 0.496 mm. It is shown that the approach can realize the forming of the integral panel precisely.     

循环电载荷下大功率LED金引线疲劳断裂寿命预测

随着大功率发光二极管（LED）在照明领域的普及与广泛应用，可靠性逐渐成为研究的重点。大功率LED封装器件中金引线疲劳断裂失效一直是制约其可靠性的重要因素。通过针对大功率LED封装器件中的金引线力学仿真与功率循环试验相结合的方法，首先确定循环电载荷条件下该型LED的主要失效原因为金引线疲劳断裂，其次提出基于电流加速模型的加速因子提取方法和基于应变幅值的Coffin-Manson解析寿命预测方法，最终完成对LED金引线疲劳断裂寿命的预测和试验验证。研究结果表明:所提方法具有较高的寿命预测精度，可以满足大功率LED封装器件可靠性快速、准确评估的要求。      

飞机封闭腔室减重降噪优化方法

噪声水平是现代飞机封闭腔室设计的重要指标,设计中单纯地对壁板进行加肋处理虽能显著降低噪声但会大大增加结构质量,为此对由封闭腔室构成的结构-声耦合系统进行了减重降噪优化研究。基于结构-声耦合有限元模型,利用有限元软件ACTRAN计算了频谱加载时舱内的声压响应。通过试验对简化处理及数值计算进行了验证,并修正了相关模型参数。为了降低结构质量,以加强肋为边界对舱门壁板进行了分区,通过对各个区域壁板厚度及肋条截面积的优化设计,使系统动刚度分配更趋合理,降低了声辐射能量以及结构-声腔的耦合性,从而实现了在满足噪声约束条件下减轻结构质量的目标。本文的工作对实际工程中由加肋壁板所构成的类似结构的减重降噪设计有着较好的工程指导价值。     

Orbit determination and prediction of GEO satellite of BeiDou during repositioning maneuver

In order to establish a continuous GEO satellite orbit during repositioning maneuvers, a suitable maneuver force model has been established associated with an optimal orbit determination method and strategy. A continuous increasing acceleration is established by constructing a constant force that is equivalent to the pulse force, with the mass of the satellite decreasing throughout maneuver. This acceleration can be added to other accelerations, such as solar radiation, to obtain the continuous acceleration of the satellite. The orbit determination method and strategy are illuminated, with subsequent assessment of the orbit being determined and predicted accordingly. The orbit of the GEO satellite during repositioning maneuver can be determined and predicted by using C-Band pseudo-range observations of the BeiDou GEO satellite with COSPAR ID 2010-001A in 2011 and 2012. The results indicate that observations before maneuver do affect orbit determination and prediction, and should therefore be selected appropriately. A more precise orbit and prediction can be obtained compared to common short arc methods when observations starting 1 day prior the maneuver and 2 h after the maneuver are adopted in POD (Precise Orbit Determination). The achieved URE (User Range Error) under non-consideration of satellite clock errors is better than 2 m within the first 2 h after maneuver, and less than 3 m for further 2 h of orbit prediction.     

低排放燃烧室NO_x排放试验及预测方法研究

为了研究中心分级贫油低排放燃烧室的排放特性和排放预测方法,针对一个低排放头部方案,在单头部燃烧室试验件上,在不同的温度、压力、油气比、供油模式和分级比条件下,测量其排放性能。以Lefebvre排放经验预测公式为基础,采用经验分析方法拟合排放试验数据,归纳出适用于本头部方案的排放预测公式。表征预测好坏的判定系数R2在小工况下和大工况下分别为0.95和0.93,表明预测结果与试验结果符合度较好。小工况和大工况排放特性不同,对仅预燃级喷油的小工况工作模式,NO_x排放主要受化学恰当燃烧温度和预燃级局部当量比的影响;对预燃级和主燃级同时喷油的大工况工作模式,NO_x排放主要受燃烧区温度和主燃级燃油比例的影响。     

J2轨道模型对月地激光通信预瞄准精度影响研究

基于J_2轨道预测模型,设计了不同倾角和轨道高度圆轨道月球卫星,通过将J_2轨道预测模型预瞄准仿真结果与直接积分RKF7(8)法仿真结果相对比,研究了不同类型月球卫星轨道对-Y面卫星舱板激光通信终端瞄准精度的影响。仿真结果表明,J_2轨道预测模型可以满足月球极地卫星月地激光通信要求,当轨道高度为1 000 km和2 000 km的时候,10 min方位角偏差不超过40μrad,而俯仰角偏差仅为7μrad时,在一定程度上J2轨道预测模型可以满足月地激光通信预瞄准要求。