非平稳信号特征提取在航空发动机故障诊断中的应用

在航空发动机早期故障诊断中,特征提取是早期诊断的重要过程之一.文中以航空发动机转子故障为研究对象,给出了基于经验模式分解、小波分析为核心的故障特征提取方法,并作了针对性的比较研究.在matlab7.0环境下开发了一个故障特征提取软件系统.研究结果表明:基于经验模式分解的时频分析方法可以很有效地提取到非平稳故障特征信号,是一种适合于非线性信号处理的方法.     

基于自组织拓扑映射图的发动机故障诊断研究

根据SOM自组织网络的高维数据矢量量化、快速聚类、信息融合和拓扑映射等特征,建立了发动机故障诊断可视拓扑映射图模型,给出了映射模式误差测度和拓扑误差测度,并通过拓扑映射图对发动机故障进行诊断,获得了很好的效果。同时,进一步通过建立的故障模式的测量参数灰度图,可以清晰地观察到故障模式矢量特征、测量参数相关性特征、参数变化趋势,并可进行更深层次故障机理分析。     

基于滑动时间窗主成分分析的液体火箭发动机传感器故障诊断方法

安装在发动机上的各种传感器是发动机状态监测的主要依据,由于工作环境恶劣,传感器失效时有发生。由于发动机运行过程中的性能蜕变和台次差异,现有基于主成分分析（PCA）的传感器故障隔离方法应用条件苛刻且诊断效果有限。针对这些问题,在对发动机数据分析的基础上,将滑动时间窗方法与PCA方法结合,提出双滑动时间窗的PCA方法用于故障传感器的隔离,并基于发动机试车数据进行了方法验证。结果表明：该方法能降低发动机性能蜕变和台次差异对发动机传感器故障诊断的影响,没有参数相关性的限制,可以实现对四种常见传感器故障的有效隔离,以及对两种发动机试验过程中故障的准确检测。研究证明了高速运转系统性能蜕变和强耦合复杂大系统台次差异对基于数据的故障诊断方法效果的影响,验证了在线学习/训练算法对这两种现象的鲁棒性。     

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.     

An analysis and enhanced proposal of atmospheric boundary layer wind modelling techniques for automation of air traffic management

The air traffic management automation imposes stringent requirements on the weather models, in such a way that they should be able to provide reliable short-time forecasts in digital formats in almost real time. The atmospheric boundary layer is one of the regions where aircraft operation and coordination are critical and therefore atmospheric model performance is also vital. This paper presents conventional and innovative techniques to improve the accuracy in the forecasting of winds in the lower atmospheric layer, proposing mechanisms to develop better models including deterministic and stochastic simulations. Accuracy is improved by optimizing the grid, assimilating observations in cycling simulations and managing a number of ensemble members. An operation-driven post-processing stage helps to incorporate detailed terrain definitions and real-time observations without re-running the model. The improvements are checked against mesoscale weather simulations at different scales and a dedicated flight campaign. The results show good performance of the model without sensitively increasing the required throughput.     

基于试飞数据的航空发动机状态监测与故障诊断

在航空发动机飞行试验阶段,发动机技术状态变化快、故障频发,为了实时监控发动机工作参数变化情况,快速及时地预测并诊断发动机故障,本文研究了试飞数据驱动的航空发动机状态监控与故障诊断技术。文章基于实际试飞数据建立了航空发动机ANN-NARX参数预测模型,考虑到建模样本量大、模型结构复杂、训练时间长、输入输出延迟等因素,采用遗传算法对模型的最小数据样本需求和结构进行了改进优化,并利用蒙特卡洛方法确立了参数预测模型的自适应告警门限,同时基于构建奇偶空间残差模型实现了航空发动机典型故障诊断。结果表明：实际试飞中只需有限架次试飞数据的训练学习,即可得到发动机参数预测模型,高压转子转速、压气机后压力、涡轮后总温及滑油总回油温度预测相对误差最大值分别为：1.0%、1.7%、0.2%和1.2%,综合模型建模误差和参数测量误差后的自适应告警门限有效降低了模型预测结果的不确定性,在已有数据样本集上的典型故障识别率达到95.2%。     

基于ReliefF-LMBP算法的涡轴发动机气路故障模式识别—两机专刊

针对涡轴发动机气路故障模式识别精度不高的问题,提出了一种基于ReliefF-LMBP故障特征提取的发动机故障模式识别方法。应用ReliefF算法对发动机传感器参数赋予权值,对传感器参数特征权重值进行迭代更新和排序,聚集好的特征样本,离散异类样本。根据筛选出的特征子集,利用LMBP神经网络算法进行发动机故障模式识别。以涡轴发动机为对象进行气路故障诊断验证,结果表明所提方法能提取特征传感器参数并实现有效的故障模式识别。     

ATM performance measurement in Europe,the US and China

Air traffic management (ATM) performance and the metrics used in its assessment are investigated for the first time across the three largest ATM world regions: Europe, the US and China. The market structure and flow management practices of each region are presented. A wide range of performance data across these three regions is synthesised. For topological and performance assessment, the notion of a 'sufficient' sample is often non-intuitive: many metrics may behave non-monotonically as a function of sampling fraction. Missing and under-developed metrics are identified, and the need for a balance between standardisation and flexibility is proposed. Longitudinal and cross-sectional metric trade-offs are identified.     

基于正则化多核判别分析的航空发动机滚动轴承早期故障融合诊断方法

针对基于机匣测点信号的航空发动机滚动轴承早期故障诊断问题,提出了一种基于正则化多核判别分析的融合诊断方法.该方法首先提取多种类型的滚动轴承故障特征;然后采用相同的一组核参数为不同类型的特征分别构造一组核矩阵,并将所有核矩阵组合在一起;最后通过求解一个半无限线性规划得到该组核矩阵关于正则化核判别分析的目标函数的最优线性组合系数,进一步采用该系数计算所有核矩阵的线性组合,从而实现多种类型特征信息的融合.实验结果表明:该方法诊断正确率与采用单一类型特征诊断的最高正确率相比提高了9.25%,同时可以避免核矩阵需要人工选择的问题,从而进一步提高了故障诊断的自动化水平.      

基于分层传递系统模型的航天器故障诊断方法

 针对传统的传递系统模型在航天器自主诊断系统中只能表示单一粒度诊断知识,知识表示的完备性差,导致诊断结果的分辨率不高,且诊断系统执行效率低的问题,提出了分层传递系统模型和诊断方法。为了保证不同粒度诊断知识的完备性表示,将系统模型按不同粒度和结构关系进行分层。通过自顶向下的递归搜索,先监测系统异常,再匹配故障类型,逐层缩小搜索空间,最终找出故障候选集和故障的层次关系。同时为了减小计算规模,在诊断过程中引入了分离策略,降低实时诊断计算量。应用该方法建立了某卫星测控分系统模型并进行故障仿真,结果表明该方法可以增加模型知识表示的完备性,并能有效提高诊断效率和结果的分辨率。