改进的基于隐马尔可夫模型的自适应IMM算法

针对机动目标跟踪中交互式多模型算法(IMM)的马尔可夫转移概率矩阵固定不变造成跟踪精度降低的问题,在已有的基于隐马尔科夫模型(HMM)的自适应IMM算法的基础上,对隐马尔可夫链的长度和Baum-Welch算法迭代次数的2个参数对该算法跟踪性能的影响,进行了深入研究分析,进一步明确了这2个参数选择的依据;并针对该算法在目标机动转换时峰值误差增大的问题,给出了2种修正方法,从而提出了改进的基于HMM的自适应IMM算法。最后,通过仿真分析了算法的参数和修正方法对跟踪性能的影响,并与传统IMM算法进行对比,证明了文章提出算法的有效性。     

部分可观测信息条件下装备剩余寿命预测

 针对部分可观测信息条件下退化系统的剩余寿命(RUL)预测问题,综合利用装备的历史寿命信息和性能退化信息,采用隐马尔可夫模型(HMM)对系统进行状态评估,得到系统的转移概率矩阵和观测概率矩阵;采用Bayes方法不断更新系统状态空间的条件概率分布;利用比例故障率模型(PHM)对系统进行可靠性分析,得到系统的故障率和可靠度函数,进而得到装备的剩余寿命分布。研究表明,该方法可较准确地预测装备的剩余寿命,为保障人员提供科学的维修决策依据。     

人-机系统飞行安全可靠性问题的研究

在分析飞机电传操纵系统（FBW）特点的基础上，建立了习行器和电传操纵系统的数学模型，建立了电传操纵系统故障及飞行员干预的概率模型。应用马尔可夫链建立了人－机产行安全可靠性的数学模型，采用伊万诺夫法评估了某型第三代飞机在电传操纵系统故障报的排除的条件概率，并计算了电传操纵系统故障后该型飞机的飞行风险，最后提出了使用建议及技术改进建议。     

基于VBGMM-DCNN的列车卫星定位欺骗干扰检测方法

面向基于全球导航卫星系统的铁路列车定位实施欺骗干扰的主动检测，在卫星定位解算层次，运用深度学习建模学习方法的优势，提出一种基于变分贝叶斯高斯混合模型-深度卷积神经网络（variational Bayesian Gaussian mixture model-deep convolutional neural network, VBGMM-DCNN）的列车卫星定位欺骗干扰检测方法。该方法首先提取能够充分体现欺骗干扰对定位解算过程作用影响的卫星观测特征参数，构建干扰检测特征矢量；然后，采用VBGMM模型拟合经过预处理的特征向量的概率分布，得到二维概率密度图；最后，将概率密度图用于DCNN模型实施欺骗干扰的检测决策。结合现场实验所得运行场景数据，利用实验室搭建的欺骗干扰测试环境实施了干扰注入测试与检验，结果表明,欺骗干扰检测性能随着DCNN网络深度的增加而提升，相对于常规有监督决策方法F1值最高提升44.68%。基于VBGMM-DCNN的欺骗干扰检测能够适应测试验证中运用的列车运行特征及定位观测条件，所达到的检测性能优于对比算法。     

基于隐马尔科夫模型的故障诊断系统研究

在制造行业中,机械设备的状态检测技术能提供关于设备运行状态的实时信息,为避免生产损失和减少设备的致命故障提供保障。提出了一套基于小波变换和隐马尔科夫模型(Hidden Markov Models,HMMs)的故障检测系统。提出了小波模极大值分布(Wavelet Modulus Maxima Distribution),并将之定义为诊断系统的观察量加以验证。同时该系统采用在线模型参数估计和培训算法,通过选取能最大化对数似然度的HMM模型,确定设备所处状态。     

Multiaspect classification of airborne targets via physics-basedHMMs and matching pursuits

Wideband electromagnetic fields scattered from N distinct target-sensor orientations are employed for classification of airborne targets. Each of the scattered waveforms is parsed via physics-based matching pursuits, yielding N feature vectors. The feature vectors are submitted to a hidden Markov model (HMM), each state of which is characterized by a set of target-sensor orientations over which the associated feature vectors are relatively stationary. The N feature vectors extracted from the multiaspect scattering data implicitly sample N states of the target (some states may be sampled more than once), with the state sequence modeled statistically as a Markov process, resulting in an HMM due to the “hidden” or unknown target orientation. In the work presented here, the state-dependent probability of observing a given feature vector is modeled via physics-motivated linear distributions, in lieu of the traditional Gaussian mixtures applied in classical HMMs. Further, we develop a scheme that yields autonomous definitions for the aspect-dependent HMM states. The paradigm is applied to synthetic scattering data for two simple targets     

Neural network directed Bayes decision rule for moving targetclassification

In this paper, a new neural network directed Bayes decision rule is developed for target classification exploiting the dynamic behavior of the target. The system consists of a feature extractor, a neural network directed conditional probability generator and a novel sequential Bayes classifier. The velocity and curvature sequences extracted from each track are used as the primary features. Similar to hidden Markov model scheme, several hidden states are used to train the neural network, the output of which is the conditional probability of occurring the hidden states given the observations. These conditional probabilities are then used as the inputs to the sequential Bayes classifier to make the classification. The classification results are updated recursively whenever a new scan of data is received. Simulation results on multiscan images containing heavy clutter are presented to demonstrate the effectiveness of the proposed methods     

三维随机图象模型及其空间关系

为了用随机的方法对三维图象进行处理,在二维 Markov场图象模型的基础上,建立了三维 Markov场图象模型。把定义在平面域上随机场的邻域系、集簇和势函数等概念推广到三维空间域,给出了三维邻域系、集簇的空间分布规律和势函数的具体表达式,解释了其空间关系和概率分布,从理论上解决了三维建模的问题,并为三维图象的计算机处理,提供了一种可以实际进行操作的随机方法。     

基于马尔科夫链模型的脉动装配线运行状态预测

分析了影响脉动生产线运行的因素和状态预测的必要性,提出了基于马尔科夫链模型的状态预测方法。基于马尔科夫链预测理论,对脉动生产线运行状态划分,确定状态转移矩阵,建立马尔科夫预测模型,并对模型准确性进行验证。     

基于优化最小二乘支持向量机的小样本预测研究

统计学中的预测问题主要是通过对已知数据的分析,找到数据内在的相互依赖关系,从而获得对未知数据的预测能力。该文提出了最小二乘支持向量机参数优化方法———多层动态自适应优化算法,构建了基于最小二乘支持向量机的预测模型,并对Ti 26合金的性能预测进行了研究。结果表明:优化的最小二乘支持向量机具有优秀的小样本数据学习能力和预测能力。     

改进的MMPHD机动目标跟踪方法

基于序列蒙特卡罗方法的经典多模概率假设密度滤波方法及其各种衍生方法,在预测过程中依据多个并行的状态转移模型,通过将大量粒子散布到下一时刻目标所有可能出现的状态空间实现目标状态的捕获,造成计算量大、目标跟踪精度差。为此,提出一种改进的多模粒子概率假设密度机动目标跟踪方法。该方法利用最新量测信息估计目标运动模型概率及模型参数,并将估计得到的目标模型应用到粒子概率假设密度滤波方法的预测过程中生成预测粒子,从而将大部分粒子聚合在目标最可能出现的状态空间邻域中,实现粒子的有效利用。数值仿真表明,所提方法不仅显著地减少了目标丢失个数,而且提高了目标跟踪精度。     

飞机纵向摆动及飞行安全评估

 在分析飞机纵向摆动特性的基础上,建立了考虑非线性与随机性的人机闭环系统模型;提出了用双指数函数分布法确定驾驶员排除某事件引发纵向摆动的条件概率的计算方法,采用马尔可夫链建立了飞行安全评估模型;最后给出了算例。     

基于马尔可夫链的飞机刹车片检查时间确定

为结合飞机实际运行工况,科学合理地制定刹车片检查时间,提出了一种基于马尔可夫链理论的预测模型。以某一机群刹车片检查时间确定为例,分别论述了刹车片磨损状态的划分,以及转移概率矩阵的构造与估计,并对该机群刹车片磨损状态进行了预测,其预测结果与实际检查情况较吻合。根据刹车片磨损状况的预测结果,制定了该机群在实际运行工况下的刹车片检查时间。实际运行情况表明,所制定的刹车片查检时间可行、有效。     

基于DBN效能拟合的舰艇编队作战效能敏感性分析

针对传统的舰艇编队作战效能分析方法中存在的对数据利用不充分、对数据完整性要求较高的问题,提出了基于深度学习的效能拟合方法。从最具有代表性的敏感性分析方法Sobol指数法入手,利用深度学习方法优越的特征学习能力,基于深度信念网络（DBN）构建了效能拟合网络,结合无监督预训练和有监督调优实现了网络训练和参数优化,构建出效能拟合模型。将产生的数据应用于效能分析模型并与完全数据条件下的效能分析结果进行对比,验证了所提出的效能拟合模型对于不完全数据下的作战系统敏感性分析的有效性。     

数字式飞机起落架转弯控制器设计

针对某型飞机起落架转弯控制系统,本文设计了一种以DSP和双口RAM为核心的双余度数字式控制器.控制器采用硬件冗余的方法搭建双通道热备份系统,制定了余度管理策略.借助自检测和比较监控技术实现一次故障工作、两次故障安全的目标.运用马尔可夫过程建立了系统的可靠度模型,利用MATLAB求解可靠度模型的微分方程组,并对系统的可靠度进行了仿真分析.     

An online ensemble semi-supervised classification framework for air combat target maneuver recognition

Online target maneuver recognition is an important prerequisite for air combat situation recognition and maneuver decision-making. Conventional target maneuver recognition methods adopt mainly supervised learning methods and assume that many sample labels are available. However, in real-world applications, manual sample labeling is often time-consuming and laborious. In addition, airborne sensors collecting target maneuver trajectory information in data streams often cannot process information in real time. To solve these problems, in this paper, an air combat target maneuver recognition model based on an online ensemble semi-supervised classification framework based on online learning, ensemble learning, semi-supervised learning, and Tri-training algorithm, abbreviated as Online Ensemble Semi-supervised Classification Framework (OESCF), is proposed. The framework is divided into four parts: basic classifier offline training stage, online recognition model initialization stage, target maneuver online recognition stage, and online model update stage. Firstly, based on the improved Tri-training algorithm and the fusion decision filtering strategy combined with disagreement, basic classifiers are trained offline by making full use of labeled and unlabeled sample data. Secondly, the dynamic density clustering algorithm of the target maneuver is performed, statistical information of each cluster is calculated, and a set of micro-clusters is obtained to initialize the online recognition model. Thirdly, the ensemble K-Nearest Neighbor (KNN)-based learning method is used to recognize the incoming target maneuver trajectory instances. Finally, to further improve the accuracy and adaptability of the model under the condition of high dynamic air combat, the parameters of the model are updated online using error-driven representation learning, exponential decay function and basic classifier obtained in the offline training stage. The experimental results on several University of California Irvine (UCI) datasets and real air combat target maneuver trajectory data validate the effectiveness of the proposed method in comparison with other semi-supervised models and supervised models, and the results show that the proposed model achieves higher classification accuracy.     

Variable slip window technology in transition detection on pitching airfoil

In the pitching motion, the unsteady transition and relaminarization position plays an important role in the dynamic characteristics of the airfoil. In order to facilitate the computer to automatically and accurately calculate the position of the transition and relaminarization, a Variable Slip Window Technology (VSWT) suitable for airfoil dynamic data processing was developed using the S809 airfoil experimental data in this paper and two calculation strategies, i.e., global strategy and single point strategy, were proposed: global strategy and single point strategy. The core of the VSWT is the selection of the window function h and the parameters setting in the h function. The effect of the VSWT was evaluated using the dimensionless pulse strength value (INB), which can be used to evaluate the signal characteristics, of the root mean square (RMS) value of the fluctuating pressure. It is found that: the h function characteristics have a significant influence on the VSWT. The suitable functions are H_n function constructed in this paper and step function. For the left boundary of the magnified area, the step function can obtain the largest INB value, but the robustness is not good. The H₁ function (Gaussian-like function, n = 1) can show higher robustness while ensuring a large INB value. The two computing strategies, which are single point strategy and global strategy, have their own advantages and disadvantages. The former strategy, that is the single point strategy, can achieve a higher INB value, but the RMS magnification at the feature position needs to be known in advance. Although the INB value obtained by the latter strategy, that is the global strategy, is slightly smaller than the calculation results of the former strategy, it is not necessary to know the RMS magnification at the feature position in advance. So the global strategy has better robustness. The experimental data of NACA0012 airfoil was used to further validate the developed VSWT in this paper, and the results show that the VSWT developed in this paper can still double the INB value of the transition/relaminarization position. The VSWT developed in this paper has certain practicability, which is convenient for the computer to automatically determine the transition/relaminarization characteristics.     

Probabilistic inference of fatigue damage propagation with limited and partial information

A general method of probabilistic fatigue damage prognostics using limited and partial information is developed.Limited and partial information refers to measurable data that are not enough or cannot directly be used to statistically identify model parameter using traditional regression analysis.In the proposed method, the prior probability distribution of model parameters is derived based on the principle of maximum entropy(Max Ent) using the limited and partial information as constraints.The posterior distribution is formulated using the principle of maximum relative entropy(MRE) to perform probability updating when new information is available and reduces uncertainty in prognosis results.It is shown that the posterior distribution is equivalent to a Bayesian posterior when the new information used for updating is point measurements.A numerical quadrature interpolating method is used to calculate the asymptotic approximation for the prior distribution.Once the prior is obtained, subsequent measurement data are used to perform updating using Markov chain Monte Carlo(MCMC) simulations.Fatigue crack prognosis problems with experimental data are presented for demonstration and validation.     

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

A common necessity for prior unsupervised domain adaptation methods that can improve the domain adaptation in unlabeled target domain dataset is access to source domain dataset and target domain dataset simultaneously. However, data privacy makes it not always possible to access source domain dataset and target domain dataset in actual industrial equipment simultaneously, especially for aviation component like Electro-Mechanical Actuator (EMA) whose dataset are often not shareable due to the data copyright and confidentiality. To address this problem, this paper proposes a source free unsupervised domain adaptation framework for EMA fault diagnosis. The proposed framework is a combination of feature network and classifier. Firstly, source domain datasets are only applied to train a source model. Secondly, the well-trained source model is transferred to target domain and classifier is frozen based on source domain hypothesis. Thirdly, nearest centroid filtering is introduced to filter the reliable pseudo labels for unlabeled target domain dataset, and finally, supervised learning and pseudo label clustering are applied to fine-tune the transferred model. In comparison with several traditional unsupervised domain adaptation methods, case studies based on low- and high-frequency monitoring signals on EMA indicate the effectiveness of the proposed method.     

基于深度学习的航空器异常飞行状态识别

飞行设备快速存取记录仪(Quick Access Recorder,以下简称QAR)保留了原始航班各类重要飞行参数在内的航行信息,使研究分析航空器实时状况和保障飞行质量成为可能。针对QAR数据高维大样本的特点,在如今大数据背景下,除了传统机理建模分析航空器飞行状态外,采用深度学习的方式建立基于数据驱动的航空器飞行状态识别模型,理论与实用意义兼具。通过对真实QAR飞行数据的研究,开发了基于深度稀疏受限玻尔兹曼机的异常飞行状态识别程序。首先利用小波降噪技术对原始飞行数据进行预处理清洗,在一系列典型飞行参数上提取经典时域特征以及小波奇异熵等信息熵特征构成特征集。在此基础上,分别利用经典的线性主元分析技术和深度稀疏玻尔兹曼机对特征集进行有效降维,最后采用四折交叉验证方式,通过高斯过程分类器实现对飞行状态的辨识。实验结果显示,基于深度受限玻尔兹曼机-高斯过程分类的飞行状态识别具有较高分类准确性。