基于增量式孤立森林的液体火箭发动机异常检测方法

为解决液体火箭发动机故障标签缺失条件下流数据无监督检测问题,以及满足不同发动机台次和不同工况的自适应检测需求,基于增量学习思想,提出了基于增量式孤立森林的异常检测算法。设计了多工况流数据检测条件下的在线更新策略、异常分数表达式,并通过更新停止策略避免故障数据对模型的污染。利用多台次试车数据对该模型进行验证,并与传统方法进行比较,结果表明,该算法能够对样本异常程度进行量化评价,能够有效检测早期缓变故障,其F₁指标较原始孤立森林算法提高了43%,检测及时性优于红线算法和自适应阈值算法。     

澳大利亚东南部森林山火HJ卫星遥感监测

以2009年2月发生在澳大利亚东南部的森林山火为研究对象,利用HJ-1B遥感影像识别森林山火,分析HJ-1B在林火灾害事故中的监测能力,通过对HJ-1B IRS B07设计参数及数据特点进行分析,提出适用于HJ-1B卫星林火监测的归一化火点指数(Ku)算法.研究表明:Ku值大于0.40为潜在可能的火点像元,云耀斑和地表虚假高温点是影响林火监测的主要噪声.由于HJ-1B没有获取到研究区域未着火前的影像数据,利用MODIS(Moderate-resolution Imaging Spectroradiometer)空间分辨率为250 m的通道1和通道2计算植被指数,其结果能较好的应用于HJ-1B林火监测算法中.通过对比分析HJ-1B林火监测结果和MODIS林火产品MOD14认为,HJ-1B能更好的监测出澳大利亚东南部森林火灾,反映出火灾的局部空间分布和细节特征.     

Neural network-based model predictive control with fuzzy-SQP optimization for direct thrust control of turbofan engine

A nonlinear model predictive control method based on fuzzy-Sequential Quadratic Programming(SQP) for direct thrust control is proposed in this paper for the sake of improving the accuracy of thrust control. The designed control system includes four parts, namely a predictive model, rolling optimization, online correction, and feedback correction. Considering the strong nonlinearity of engine, a predictive model is established by Back Propagation(BP) neural network for the entire flight envelope,...     

一种多波段组合的孤立噪声去除方法

首次提出了一种多波段组合的孤立噪声去除方法.文章在对图像进行中值滤波处理之前,先进行门限法的孤立噪声初步定位,设定孤立噪声为候选点;然后结合多波段图像数据对候选孤立噪声进行最终定位,只有当像元判断为真实的孤立噪声时,进行中值滤波处理;最后以中国一颗传输型卫星图像为例,检验了算法的有效性.     

基于随机森林的航天器电信号多分类识别方法

针对航天器电特性信号数据存在数据量大、特征维数高、计算复杂度大和识别率低等问题,提出基于主成分分析(PCA)的特征提取方法和随机森林(RF)算法,对原始数据进行降维,提高计算效率和识别率,实现对航天器电信号数据的快速、准确识别分类。随机森林算法在处理高维数据上具有优越的性能,但是考虑到时间复杂度问题,利用主成分分析方法对数据进行压缩和降维,在保证准确率的同时提高了计算效率。实验结果表明:与其他算法相比,针对航天器电特性信号数据,本文方法在准确率、计算效率和稳定性等方面均显示出优异的性能。     

利用孤立导体建立等离子体探测载荷参考电位方法

研究讨论了一种利用孤立导体在空间等离子体环境中建立探测器参考电位的技术.将一个金属导体与航天器进行电隔离,利用电路将孤立导体电位引入探测器电源模块,为探测器建立参考电位.该技术可安全方便地应用于卫星等航天器,使探测器的地电位与空间等离子体电位基本一致,避免航天器本体电位对探测器的影响.该技术将应用于中国空间站等离子体原位探测器,通过测试验证了该技术方法可以建立-210～+210V的参考电位,满足空间站等离子体原位探测器-200～+200V的参考电位技术需求.      

Evaluating the statistical performance of less applied algorithms in classification of worldview-3 imagery data in an urbanized landscape

In recent decade, analyzing the remotely sensed imagery is considered as one of the most common and widely used procedures in the environmental studies. In this case, supervised image classification techniques play a central role. Hence, taking a high resolution Worldview-3 over a mixed urbanized landscape in Iran, three less applied image classification methods including Bagged CART, Stochastic gradient boosting model and Neural network with feature extraction were tested and compared with two prevalent methods: random forest and support vector machine with linear kernel. To do so, each method was run ten time and three validation techniques was used to estimate the accuracy statistics consist of cross validation, independent validation and validation with total of train data. Moreover, using ANOVA and Tukey test, statistical difference significance between the classification methods was significantly surveyed. In general, the results showed that random forest with marginal difference compared to Bagged CART and stochastic gradient boosting model is the best performing method whilst based on independent validation there was no significant difference between the performances of classification methods. It should be finally noted that neural network with feature extraction and linear support vector machine had better processing speed than other.     

A comparative study of decision tree,random forest,and convolutional neural network for spread-F identification

Ionospheric spread-F (SF) is a commonly observed phenomenon of electron density perturbation in the F-layer. The ionospheric irregularities structure has an adverse effect on the propagation of electromagnetic waves in the ionosphere. The automatic identification of ionospheric spread-F and statistical study of the formation of spread-F are of great significance to the study of the physical mechanism of ionospheric inhomogeneity and for prediction of ionospheric irregularities. In this paper, we describe and implement three automatic identification methods of spread-F based on machine learning: decision tree, random forest, and convolutional neural network (CNN). The performance of these automatic identification methods was verified using a large set of test data. Results show that the accuracy of all three methods on identifying ionograms with spread-F exceeded 90%. After comparing the results of the three methods, we found that the decision tree method was the simplest and with the structure easiest to be understood, and it required the shortest interpretation time. In terms of the identification results, the random forest method provided better results than the decision tree method, and the CNN method was the best at accurately identifying ionograms with spread-F.     

地磁测量数据野值的辨识与剔除

针对地磁测量野值的辨识与剔除方法进行了深入研究。分析了野值辨识与剔除的基本原理,基于孤立型野值和斑点型野值模型分析比较了不同的野值剔除方法。利用地磁场实测信息,优化了野值剔除方法的参数,并从不同角度验证了方法的野值修复效果。仿真结果表明,在观测信息为总强度地磁信息条件下,优化的最小二乘B样条逼近法能够有效地辨识野值,具有较好的野值修复效果。     

小功率DC/DC模块隔离阻抗分析

从 DC/ DC功能引出隔离阻抗概念 ,进而介绍隔离阻抗的内涵及阻抗三角形分析方法。通过实例验证理论分析的合理性 ,指出提高隔离阻抗是增强 DC/ DC模块共模抑制能力的主要途径 ,减小分布电容是最有效的措施。