A method for satellite time series anomaly detection based on fast-DTW and improved-KNN

In satellite anomaly detection, there are some problems such as unbalanced sample distribution, fewer fault samples, and unobvious anomaly characteristics. These problems cause the extisted anomaly detection methods are difficult to train accurate classification model, and the accuracy of anomaly detection is hard to improve. At the same time, the monitoring data of satellite has high dimension and is difficult to extract effective features. Based on the DTW over-sampling method, this paper realizes the over-sampling of fault samples in satellite time series, and constructs a distributed and balanced time series data set. The Fast-DTW method is applied to calculate the distance between different time series, which can improve the speed of similarity calculation. KNN (K-Nearest Neighbor) method is applied for classification and the best classification result is obtained by search the optimal hyper-parameters k. The results show that the proposed method has high anomaly detection accuracy and consumes short calculation time.     

基于核的K近邻法

将核学习方法的思想应用于K近邻法中,提出了一种核K近邻算法,算法的主要思想是:首先将原空间中待分类的样本经过一个非线性映射,映射到一个高维的核空间中,突出各类样本之间的特征差异,然后在这个核空间中进行K近邻分类.为了验证算法的有效性,分别利用人工和实际数据进行K近邻分类和核K近邻分类,实验结果显示对于一些特殊的类分布数据,核K近邻分类比K近邻分类具有更好的分类效果.     

An unsupervised classification method of flight states for hypersonic targets based on hyperspectral features

In response to the challenges of aerospace defense caused by the rapid development of hypersonic targets in recent years, the research on the unsupervised classification of flight states for hypersonic targets is carried out in this paper, which is based on the Hyperspectral Features (HFs) of hypersonic targets covered with plasma sheath during high-speed flight. First, a new concept of the super node is defined to improve classification accuracy by alleviating the intraclass variability of HFs. Then, the frequency domain information of the curve of HFs is utilized to reduce the feature redundancy according to the prior theoretical knowledge that the fluctuation characteristics of HFs of the same flight states are similar. Finally, an unsupervised classification method based on the Density Peak Clustering (DPC) for HFs is designed to class flight states after eliminating the impact of intraclass variability and feature dimension redundancy. The proposal is compared with the traditional classification algorithms on simulated hyperspectral data sets of typical flight states of the hypersonic vehicle and an actual-observation hyperspectral data set. The results indicate that the performance of our proposal has competitive advantages in terms of Overall Accuracy (OA), Average Accuracy (AA) and Kappa coefficient.     

Few-shot electromagnetic signal classification: A data union augmentation method

Deep learning has been fully verified and accepted in the field of electromagnetic signal classification. However, in many specific scenarios, such as radio resource management for aircraft communications, labeled data are difficult to obtain, which makes the best deep learning methods at present seem almost powerless, because these methods need a large amount of labeled data for training. When the training dataset is small, it is highly possible to fall into overfitting, which causes performance degradation of the deep neural network. For few-shot electromagnetic signal classification, data augmentation is one of the most intuitive countermeasures. In this work, a generative adversarial network based on the data augmentation method is proposed to achieve better classification performance for electromagnetic signals. Based on the similarity principle, a screening mechanism is established to obtain high-quality generated signals. Then, a data union augmentation algorithm is designed by introducing spatiotemporally flipped shapes of the signal. To verify the effectiveness of the proposed data augmentation algorithm, experiments are conducted on the RADIOML 2016.04C dataset and real-world ACARS dataset. The experimental results show that the proposed method significantly improves the performance of few-shot electromagnetic signal classification.     

多测速系统应答信标数据实时分类算法

为了提高目标轨迹解算的稳定性,针对多测速系统在应答模式下的测量数据分类问题,提出了一种新的实时分类算法。首先分析了现有方法的缺陷;其次设计了一种能够将应答数据、信标数据与异常数据进行分类的新算法。该算法的关键是选择适当的分类参考,采用目标理论轨迹与已经分类的历史测量数据等2种分类参考相结合的方法,以适应不同的应用情形;最后,利用2类主站配置模式下的典型实测数据对新算法进行验证,结果表明新算法能够将3类数据正确分类。在此基础上,解算出的实时轨迹平稳且连续,测量数据的利用率明显提高。因此新分类算法的性能优于现有方法,对改善其他测量系统中的实时数据分类效果也具有借鉴意义。     

飞机性能参数预测的不确定性处理

 利用飞机的性能参数对飞机进行故障预报和状态监控是非常重要的。飞机的性能参数不仅具有非线性而且往往包含噪声,使得故障预测结果具有不确定性。针对这些问题,研究了利用非线性支持向量机处理飞机性能参数的预测问题,通过增加线性约束的方式解决了噪声带来的不确定性问题。此种方法不仅提高了预测的精度,而且模型可以利用适用于处理大规模二次规划的序列最小最优化算法进行求解,使得其可以解决大数据量的预测问题。利用仿真数据以及实际飞机性能参数对该方法进行了实验分析,实验结果表明此方法在精度上较不考虑噪声影响的模型有所提高,对于进一步提高飞机故障预测的精度,从而提高飞机的安全性具有重要意义。     

一种适用于进近尾流间隔缩减的机型聚类方法

目前,我国广泛使用的尾流间隔标准过于保守,导致机场跑道容量受限。以进近航空器的尾流遭遇问题为研究对象,首先研究进近尾流安全间隔缩减方法,获取缩减后的临界尾流间隔;然后基于主成分分析法（PCA）对 BADA 数据库中的航空器性能数据降维,提出一种适用于进近尾流间隔缩减的机型层次聚类方法;最后采用该方法得到新的机型分类结果并构建缩减后的尾流安全间隔标准。结果表明：本文所使用的机型层次聚类方法与国内外航空器分类方法具有较好的一致性,在长沙黄花国际机场的主流配对机型间,所获取的进近航空器尾流间隔标准与传统尾流间隔标准相比可以缩减 0.8 km 以上。     

Combination of classifiers with incomplete frames of discernment

The methods for combining multiple classifiers based on belief functions require to work with a common and complete(closed) Frame of Discernment(Fo D) on which the belief functions are defined before making their combination. This theoretical requirement is however difficult to satisfy in practice because some abnormal(or unknown) objects that do not belong to any predefined class of the Fo D can appear in real classification applications. The classifiers learnt using different attributes inform...     

Adaptive learning approach to landmine detection

We consider landmine detection using forward-looking ground penetrating radar (FLGPR). The two main challenging tasks include extracting intricate structures of target signals and adapting a classifier to the surrounding environment through learning. Through the time-frequency (TF) analysis, we find that the most discriminant information is TF localized. This observation motivates us to use the over-complete wavelet packet transform (WPT) to sparsely represent signals with the discriminant information encoded into several bases. Then the sequential floating forward selection method is used to extract these components and thereby a neural network (NNW) classifier is designed. To further improve the classification performance and deal with the problem of detecting mines in an unconstraint environment, the AdaBoost algorithm is used. We integrate the feature selection process into the original AdaBoost algorithm. In each iteration, AdaBoost identifies the hard-to-learn examples and a new set of features which provide the specific discriminant information for these hard samples is extracted adaptively and a new classifier is trained. Experimental results based on measured data are presented, showing that a significant improvement on the classification performance can be achieved.     

CFD Study of NO_x Emissions in a Model Commercial Aircraft Engine Combustor

Air worthiness requirements of the aircraft engine emission bring new challenges to the combustor research and design. With the motivation to design high performance and clean combustor, computational fluid dynamics (CFD) is utilized as the powerful design approach. In this paper, Reynolds averaged Navier-Stokes (RANS) equations of reactive two-phase flow in an experimental low emission combustor is performed. The numerical approach uses an implicit compressible gas solver together with a Lagrangian liquid-phase tracking method and the extended coherent flamelet model for turbulence-combustion interaction. The NOx formation is modeled by the concept of post-processing, which resolves the NOx transport equation with the assumption of frozen temperature distribution. Both turbulence-combustion interaction model and NOx formation model are firstly evaluated by the comparison of experimental data published in open literature of a lean direct injection (LDI) combustor. The test rig studied in this paper is called low emission stirred swirl (LESS) combustor, which is a two-stage model combustor, fueled with liquid kerosene (RP-3) and designed by Beihang University (BUAA). The main stage of LESS combustor employs the principle of lean prevaporized and premixed (LPP) concept to reduce pollutant, and the pilot stage depends on a diffusion flame for flame stabili-zation. Detailed numerical results including species distribution, turbulence performance and burning performance are qualita-tively and quantitatively evaluated. Numerical prediction of NOx emission shows a good agreement with test data at both idle condition and full power condition of LESS combustor. Preliminary results of the flame structure are shown in this paper. The flame stabilization mechanism and NOx reduction effort are also discussed with in-depth analysis.     

区间数据整体估计方法

提出了一种区间数据整体估计方法, 给出整体分布参数的最佳线性无偏估计量及其协方差矩阵, 得到了正态分布、Weibull分布等位置-尺度分布族区间数据百分位值和百分率的置信限估计.该方法可以将不同条件下的试验数据作为一个整体进行统计推断, 将传统的只适用于完全数据的回归分析推广到工程中常见的区间数据的情况.      

基于平衡核函数聚类的飞行航迹数据分析方法

目前,使用数据挖掘的方法对目标的飞行航迹进行分析来确定航迹类别具有许多应用价值。飞行航迹数据具有维数高、交连多、可分类性能差等特点,要做到尽可能精确的聚类和分类十分困难。文章立足提高飞行航迹数据聚类分析的准确性,在航迹特征数据的预处理阶段,提出了一种平衡核函数的K-均值聚类方法,可以解决高维特征数据带来的奇异性,还能提高交叠样本的聚类性能;设计了一种模糊支持向量机的算法框架实现航迹的分类。通过实际飞行航迹数据集测试了设计框架下航迹聚类和分类识别的有效性,在实际工程上具有广泛的应用前景。     

A generalized rough set-based information filling technique for failure analysis of thruster experimental data

Interval-valued data and incomplete data are two key problems for failure analysis of thruster experimental data and have been basically solved by the proposed methods in this paper. Firstly, information data acquired from the simulation and evaluation system formed as intervalvalued information system （IIS） is classified by the interval similarity relation. Then, as an improvement of the classical rough set, a new kind of generalized information entropy called ＂H＇-information entropy＂ is suggested for the measurement of uncertainty and the classification ability of IIS. There is an innovative information filling technique using the properties of H＇-information entropy to replace missing data by some smaller estimation intervals. Finally, an improved method of failure analysis synthesized by the above achievements is presented to classify the thruster experimental data, complete the information, and extract the failure rules. The feasibility and advantage of this method is testified by an actual application of failure analysis, whose performance is evaluated by the quantification of E-condition entropy.     

基于高分辨距离间隔像的频率步进单脉冲雷达测角技术研究

 频率步进雷达合成高分辨距离像时对速度补偿的精度要求很高,而采用高分辨距离间隔像处理则可以大大降低这种要求。首先分析了高分辨距离间隔像成像的一些问题;然后阐述了基于高分辨距离间隔像的单脉冲雷达测角机理,并且提出了3 种过采样条件下的单脉冲雷达距离间隔像测角算法,进行了计算机仿真,结果表明距离间隔像交叉项选大测角方法性能优于其它两种方法。     

Adjoint boundary sensitivity method to assess the effect of nonuniform boundary conditions

The performance of turbomachinery is largely affected by the nonuniform boundary conditions caused by the coupling between neighboring parts, such as the inlet distortion and hot streak. Existing works study this problem by comparing the flow fields with uniform and nonuniform boundary conditions, which is cost extensive. In this work a new and efficient method is developed by computing the sensitivities of arbitrary performance metric relative to the boundary conditions and this method quantita...     

一种基于证据距离的多分类器差异性度量

 多分类器系统因其能够显著提升分类精度而引发了广泛关注。多分类器系统中各子分类器间的差异性是提升融合分类精度的先决条件。提出了一种基于证据距离的分类器系统差异性度量,同时基于该度量提出一种多分类器系统构造方法。综合了既有差异性度量、所提新差异性度量以及在训练样本集上的分类性能等多个指标,实现了多分类器系统的有效构造。实验结果表明,所提差异性度量及多分类器系统构造方法是合理的,能有效提升融合分类精度。     

Radar target classification using doppler signatures of human locomotion models

The problem of target classification for ground surveillance Doppler radars is addressed. Two sources of knowledge are presented and incorporated within the classification algorithms: 1) statistical knowledge on radar target echo features, and 2) physical knowledge, represented via the locomotion models for different targets. The statistical knowledge is represented by distribution models whose parameters are estimated using a collected database. The physical knowledge is represented by target locomotion and radar measurements models. Various concepts to incorporate these sources of knowledge are presented. These concepts are tested using real data of radar echo records, which include three target classes: one person, two persons and vehicle. A combined approach, which implements both statistical and physical prior knowledge provides the best classification performance, and it achieves a classification rate of 99% in the three-class problem in high signal-to-noise conditions.     

Pressure distribution guided supercritical wing optimization

Pressure distribution is important information for engineers during an aerodynamic design process. Pressure Distribution Oriented (PDO) optimization design has been proposed to introduce pressure distribution manipulation into traditional performance dominated optimization. In previous PDO approaches, constraints or manual manipulation have been used to obtain a desirable pressure distribution. In the present paper, a new Pressure Distribution Guided (PDG) method is developed to enable better pressure distribution manipulation while maintaining optimization efficiency. Based on the RBF-Assisted Differential Evolution (RADE) algorithm, a surrogate model is built for target pressure distribution features. By introducing individuals suggested by sub-optimization on the surrogate model into the population, the direction of optimal searching can be guided. Pressure distribution expectation and aerodynamic performance improvement can be achieved at the same time. The improvements of the PDG method are illustrated by comparing its design results and efficiency on airfoil optimization test cases with those obtained using other methods. Then the PDG method is applied on a dual-aisle airplane’s inner-board wing design. A total drag reduction of 8 drag counts is achieved.     

基于幂律退化轨道的小样本性能可靠性评定

结合航空航天领域高可靠、长寿命产品试验小子样的特点,运用性能退化可靠性理论和Bayes方法,对系统可靠性的统计推断方法进行了研究.首先对基于Bayes方法幂律退化轨道参数的计算模型进行研究,然后结合随机变量函数的分布的计算,推导出系统可靠性后验估计和置信下限估计的计算公式.在理论推导的基础上,结合工程实例说明该方法的有效性.     

Superresolution HRR ATR with high definition vector imaging

A new 1-D template-based automatic target recognition (ATR) algorithm is developed and tested on high range resolution (HRR) profiles formed from synthetic aperture radar (SAR) images of targets taken from the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set. In this work, a superresolution technique known as High Definition Vector Imaging (HDVI) is applied to the HRR profiles before the profiles are passed through ATR classification. The new I-D ATR system using HDVI demonstrates significantly improved target recognition compared with previous I-D ATR systems that use conventional image processing techniques. This improvement in target recognition is quantified by improvement in probability of correct classification (PCC). More importantly, the application of HDVI to HRR profiles helps to maintain the same ATR performance with reduced radar resource requirements