基于改进HMM和LS-SVM的机载设备故障预测研究

针对传统故障预测方法不能直接预测设备状态的不足,提出了将改进隐马尔科夫模型（HMM）和最小二乘支持向量机（LS—SVM）相结合的机载设备故障预测方法。首先,采用多智能体遗传算法对HMM参数进行训练优化,克服了B-W算法易陷入局部最优解的缺陷;其次,分别研究设计了设备是否具有使用阶段状态退化过程数据2种情况下的故障预测算法流程;最后,以飞机发动机温控放大器为应用对象进行仿真计算。结果表明,该算法不仅预测精度高,而且预测结果直接与设备状态相关,易于理解分析。     

构建航空气象和用户一体化实训平台的设想

本文结合多年对航空气象专业及飞行管制等用户的培训经验,提出了培训平台搭建的思路,进行了平台框架设计,并对今后实用训练模块进行了策划研究,为平台培训软件开发提供了理论参考。     

利用人工神经网络提前1h预报电离层TEC

提出了一种利用人工神经网络提前1h预报电离层TEC的简便方法. 考虑到实际工程应用要求, 没有使用其他空间天气参数, 而是选择电离层TEC观测数据本身作为输入参数. 输入参数为当前时刻TEC、一阶差分、相对差分和时间, 输出参数为预报时刻TEC. 利用文中介绍的GPS/TEC处理方法解算厦门站2004年电离层TEC观测数据, 对预报方法进行评估, 全年平均相对误差为9.3744%, 预报结果与观测值相关性达到了0.96678. 结果表明, 利用人工神经网络方法提前1h预报电离层TEC有很好的应用前景.      

基于可靠性增长预测模型的航空发动机可靠性评估

通过可靠性增长预测模型充分利用定型前内场台架试验及外场试飞提供的大量数据对技术状态不断变化的发动机进行可靠性评估,并与经典的累计平均故障间隔时间(MTBF)估算值作了比较,结果表明:传统的累计MTBF评估方法没有考虑研制过程中技术状态的不断变化和可靠性不断增长的情况,故评估的可靠性值不符合实际情况;而可靠性增长预测模型合理、有效、实用.      

军机两级维修费用效益预测

维修费用估算是军用飞机寿命周期费用估算的重要组成部分。将三级维修体制简化为两级维修,可节省维修财力并提高战备完好性。引入灰色系统GM（1,1）模型理论,建立了转换维修体制后的财力节省预测模型,以美空军实际节省的财力数据为例进行预测,经多种精度检验表明,模型的可信性较高。     

灰色系统理论在年用电量预测中的应用

年用电量系统具有灰色系统的特征,因此,可以用灰色系统模型对年用电量进行预测.运用灰色模型(GM(1,1))对年用电量做出预测,并与传统方法进行比较,结果证明GM(1,1)模型优于传统方法,是一种有效的预测年用电量的模型。     

航空发动机摩擦磨损油液监测实验系统

阐述了工业摩擦磨损油液监测的意义及油液监测分析技术，介绍了国内外的应用情况。提出建立包括油料光谱分析，磨粒铁谱分析，润滑油品理化性能分析的综合实验系统是实施航空发动机摩擦磨损油液监测行之有效的方法。     

防空导弹尾追拦截目标的遭遇点预测方法

为充分发挥导弹武器系统的全向拦截能力,防空导弹需要面对拦截发射时即处于尾追逃逸态势目标的问题。结合防空导弹任务特点,设计了一种兼顾迎击、尾追拦截态势的遭遇点预测方法。根据导弹与目标在发弹时刻和拦截过程中的相对运动关系,建立常规迎击态势下的遭遇点预测模型。针对尾追拦截的特殊情况,分析预测模型对弹目相对运动关系描述的适用性,并进一步研究目标初始参数对预测模型收敛性的影响。在此基础上优化运动几何关系描述模型,结合收敛条件设计迭代算法,形成尾追拦截态势下遭遇点的预测方法。该方法修正了目标穿越发射点上空引起的模型适用性问题。仿真结果表明:迭代算法对迎击、尾追目标态势均快速收敛,预测精度满足工程应用要求,为导弹全向拦截时的遭遇点预测提供了有效的解决途径。     

A geomagnetic activity forecast for improving the efficiency of aeromagnetic surveys in Greenland

In recent years several aeromagnetic surveys were carried out in Greenland and more will be carried out in the future. We describe some of the characteristics pertinent to surveys in Greenland and the problems faced and experiences made by the survey teams working there, with special emphasis on the west coast where most surveys were conducted. Both unfavorable terrestrial weather and space weather appear to complicate survey planning. We discuss possible options available to the survey teams for mitigating the adverse effect of part of the problems, namely survey data contamination by intense geomagnetic activity. The implementation of a prototype geomagnetic activity forecast service as an aid to planning survey flights is discussed in more detail. The forecast service was tested by an independent observer, and the performance of the scheme is evaluated by a subsequent comparison between forecast and actual measurements. The comparison rendered largely acceptable results, but their validity is limited by the fact that the two-month test interval was characterized by a mostly relatively quiet magnetic field.     

Forecast of recurrent geomagnetic storms

Long-term forecast of space weather allows in achieving a longer lead time for taking the necessary precautions against disturbances. Hence, there is a need for long-term forecasting of space weather. We studied the possibility for a long-term forecast of recurrent geomagnetic storms. Geomagnetic storms recur with an approximate 27-day period during the declining phase of a solar cycle. These disturbances are caused by the passage of corotating interaction regions, which are formed by interactions between the background slow-speed solar wind and high-speed solar wind streams from a coronal hole. In this study, we report on the performance of 27-day-ahead forecasts of the recurrent geomagnetic disturbances using Kp index. The methods of the forecasts are on the basis of persistence, autoregressive model, and categorical forecast using occurrence probability. The forecasts show better performance during the declining phase of a solar cycle than other phases. The categorical forecast shows the probability of detection (POD) more than 0.5 during the declining phase. Transition of the performance occurs sharply among the declining phases and other phases.