基于HHT的航空直流串行电弧特征提取方法

由于飞机内部布线空间有限、电弧故障存在发生时间地点随机以及特征不明显等问题，导致检测困难。本文基于航空270 V高压直流（HVDC）系统开展直流串行电弧故障特征提取方法研究，采用希尔伯特黄变换（HHT）提取电弧电流交流分量的时域和频域特征量。选择HHT的固有模态函数IMF5瞬时幅值的峰峰值和标准差作为识别电弧故障的时域特征，与原始信号中提取的时域特征量对比，正常和电弧特征量的区分度更大；选择HHT的固有模态函数IMF1+IMF2、一定频带范围内的瞬时幅值计算得到的谐波功率和作为区分正常和电弧情况的频域特征量。与常用的快速傅里叶变换（FFT）方法相比，HHT三维时频谱能够反映信号的局部特征，HHT方法计算得到的正常和电弧特征量之间的区分度更大，电弧和正常特征量的比值最高可达346。基于HHT的电弧故障特征提取方法能够更好地区分正常和电弧情况，有助于提高电弧故障的检测率，降低虚警率，具有重要的工程应用价值。     

基于卷积门控循环网络的滚动轴承故障诊断

针对许多基于深度学习的滚动轴承故障诊断方法在小样本数据集下诊断性能下降的问题,提出一种基于卷积门控循环神经网络的轴承故障诊断模型。该模型使用两层的卷积网络来从输入信号中提取特征,同时使用tanh函数作为激活函数,且池化层使用大池化核来进行重叠下采样。将所提取得到的高层特征连接到双向门控循环网络。合并循环网络正向和逆向的最后一个状态,并连接一层全连接层进行输出。选用凯斯西储大学的轴承故障数据集来验证模型在小样本数据集下的诊断性能,实验结果表明,相比于其他类型的模型,该模型在仅有20个训练样本的情况下依然保持97%的识别准确率。      

A new bearing fault diagnosis method based on modified convolutional neural networks

Fault diagnosis is vital in manufacturing system. However, the first step of the traditional fault diagnosis method is to process the signal, extract the features and then put the features into a selected classifier for classification. The process of feature extraction depends on the experimenters’ experience, and the classification rate of the shallow diagnostic model does not achieve satisfactory results. In view of these problems, this paper proposes a method of converting raw signals into two-dimensional images. This method can extract the features of the converted two-dimensional images and eliminate the impact of expert’s experience on the feature extraction process. And it follows by proposing an intelligent diagnosis algorithm based on Convolution Neural Network (CNN), which can automatically accomplish the process of the feature extraction and fault diagnosis. The effect of this method is verified by bearing data. The influence of different sample sizes and different load conditions on the diagnostic capability of this method is analyzed. The results show that the proposed method is effective and can meet the timeliness requirements of fault diagnosis.     

一种机载航电设备软件故障监控技术的设计与实现

机载航电设备软件故障监控技术是通过调用操作系统钩子函数、板级支持包中插装代码的方式实现的,可以为设备提供更加全面的故障监控能力,为故障快速定位提供重要依据,提升产品的可维护性.该技术可兼容多种处理器和多种操作系统,具有一定通用性.     

液体火箭发动机健康监控技术研究现状

液体火箭发动机健康监控技术是改进和提高运载火箭、航天器可靠性与安全性的核心技术之一,对其进行研究具有重要的学术价值和工程应用价值。液体火箭发动机健康监控技术的研究主要包括液体火箭发动机故障检测与诊断理论方法、液体火箭发动机健康监控系统两方面。该文介绍了基于模型驱动的方法、基于数据驱动的方法和基于人工智能的方法,阐明了液体火箭发动机故障检测与诊断理论方法的研究现状,通过对美国液体火箭发动机典型健康监控系统的介绍,阐明了液体火箭发动机健康监控系统研究的若干进展及现状,并对液体火箭推进系统健康监控技术的演变趋势作了简要评述。     

某型装备能源电池异常爆破故障分析

对一起因电池设计缺陷引发装备战训失利的故障进行分析,重点对电池工作机理和设计缺陷展开解析,明确故障定位,并对国内外装备弹上不同体系电池的优缺点进行比较,旨在为产品维护保障、国产化科研等工作提供参考。     

基于AFI混合聚类算法的轴承故障诊断方法

针对滚动轴承振动信号标记数据量小、故障模式多样的现状，提出了一种基于AFI混合聚类算法的半监督式轴承振动信号故障诊断方法。利用小波包分解方法提取了信号的能量特征谱，并通过主成分分析方法增强了信号的特征；参考迭代自组织数据分析的“分裂”和“合并”的思想，为人工鱼群算法中的个体鱼增加了“分裂进化”和“合并进化”行为；采用模糊C均值方法定义了隶属度矩阵和目标函数，并利用改进的人工鱼群算法，迭代搜寻了目标函数的全局最优解，得到了各故障模式的聚类中心；通过计算测试数据的最近邻聚类中心，实现了故障模式识别。结果表明，该方法无需指定聚类簇数，能在标记数据量小的情况下完成训练，较同类方法表现出了更优的故障模式识别性能。     

Multi-faults diagnosis of rolling bearings via adaptive customization of flexible analytical wavelet bases

Multi-faults detection is a challenge for rolling bearings due to the mode mixture and coupling of multiple fault features, as well as its easy burying in the complex, non-stationary structural vibrations and strong background noises. In this paper, a method based on the flexible analytical wavelet transform (FAWT) possessing fractional scaling and translation factors is proposed to identify multiple faults occurred in different components of rolling bearings. During the route of the proposed method, the proper FAWT bases are constructed via genetic optimization algorithm (GA) based on maximizing the spectral correlated kurtosis (SCK) which is firstly presented and proved to be efficient and effective in indicating interested fault mode. Via using the customized FAWT bases for each interested fault mode, the original vibration measurements are decomposed into fine frequency subbands, and the sensitive subband which enhances the signal-to-noise ratio (SNR) is selected to exhibit the fault signature on its envelope spectrum. The proposed method is tested via simulated signals, and applied to analyze the experimental vibration measurements from the running roller bearings subjected to outrace, inner-race and roller defects. The analysis results validate the effectiveness of the proposed method in identifying multi-faults occurred in different components of rolling bearings.     

Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning

In aerospace industry, gears are the most common parts of a mechanical transmission system. Gear pitting faults could cause the transmission system to crash and give rise to safety disaster. It is always a challenging problem to diagnose the gear pitting condition directly through the raw signal of vibration. In this paper, a novel method named augmented deep sparse autoencoder (ADSAE) is proposed. The method can be used to diagnose the gear pitting fault with relatively few raw vibration signal data. This method is mainly based on the theory of pitting fault diagnosis and creatively combines with both data augmentation ideology and the deep sparse autoencoder algorithm for the fault diagnosis of gear wear. The effectiveness of the proposed method is validated by experiments of six types of gear pitting conditions. The results show that the ADSAE method can effectively increase the network generalization ability and robustness with very high accuracy. This method can effectively diagnose different gear pitting conditions and show the obvious trend according to the severity of gear wear faults. The results obtained by the ADSAE method proposed in this paper are compared with those obtained by other common deep learning methods. This paper provides an important insight into the field of gear fault diagnosis based on deep learning and has a potential practical application value.     

卷积神经网络和峭度在轴承故障诊断中的应用

针对传统智能诊断方法依靠专家知识和人工提取数据特征工作量大的问题,结合深度学习方法在特征提取和处理大数据方面的优势,研究了一种基于卷积神经网络和振动信号峭度指标的滚动轴承故障诊断方法。该方法将深度学习应用于轴承故障诊断,提取滚动轴承正常状态、内圈故障、外圈故障和滚动体故障4种状态的振动信号,将振动信号分段处理得到峭度指标,使用数据到图像的转换方法将峭度指标转换为灰度图,送入卷积神经网络模型完成故障分类。在进行滚动轴承故障诊断的实验时,所提的模型诊断准确率达到99.5%,高于传统支持向量机(SVM)算法的95.8%。