改进的子空间方法及其在时变结构参数辨识中的应用

本文给出了一种可用于时变结构参数辨识的子空间跟踪方法。子空间方法运用特征分析理论,通过矩阵分解来得到信号子空间。首先将要跟踪的矩阵变换为一种适合在线跟踪的格式,将新的数据信息组合成一个维数不变的矩阵,通过对该矩阵的奇异值分解来更新上一步的信号子空间。这样就避免了对一个不断增长的Hankle阵做奇异值分解,有效的缩减了计算量。将该方法用于机械臂系统,通过施加一个随时间变化的力来改变机械臂的固有频率。选择合适的遗忘因子以协调跟踪能力和辨识仿真结果证实了算法跟踪时变参数的能力。     

基于STUKF的非线性结构系统时变参数识别

针对非线性结构系统时变参数识别问题,传统无迹卡尔曼滤波(Unscented Kalman Filter,UKF)难以有效跟踪结构参数的变化。将强跟踪滤波原理引入无迹卡尔曼滤波,提出一种强跟踪无迹卡尔曼滤波(Strong Tracking Unscented Kalman Filter,STUKF)算法,以识别结构参数的变化。在UKF量测更新后,依据输出残差计算渐消因子矩阵;引入两个渐消因子矩阵实时调整状态预测协方差矩阵,使残差序列强行正交,快速修正结构参数估计值,使STUKF具有对结构参数变化的跟踪能力;此外,为节省计算时间,调整状态预测协方差矩阵后不再进行sigma点采样,保证了算法的高效性。数值分析结果表明,该算法能有效识别非线性结构系统的参数及其变化,并具有较强的抗噪性。     

基于遗忘因子和LMBP神经网络的混合试验在线模型更新方法

目前将神经网络应用于混合试验的在线模型更新是一个重要的研究方向,如何提高神经网络在线模型更新算法的自适应性、稳定性和抗噪声能力是一个关键问题,提出了一种基于遗忘因子和LMBP神经网络的混合试验在线模型更新方法,即每时步利用试验子结构的历史试验数据形成带有遗忘因子的动态窗口样本,并采用增量训练方式训练LMBP神经网络,同步预测具有相同本构模型的数值子结构的恢复力。对一个两自由度非线性结构进行模型更新混合试验数值模拟,数值子结构恢复力预测值的RMSD最终为0.0230。结果表明,基于遗忘因子和LMBP神经网络的混合试验在线模型更新方法具有良好的自适应性、稳定性和抗噪声能力。     

扩展卡尔曼滤波器在冷水机组传感器故障诊断中的应用

围绕暖通空调系统中冷水机组传感器的故障诊断,基于扩展卡尔曼滤波器(EKF)提出一种冷水机组传感器故障检测方法。首先对数据进行预处理,根据诊断阈值范围与异常变化整定2个误差协方差矩阵。然后分为单参数和双参数自适应阈值诊断,双参数的诊断效果不好故舍弃,而在单参数方法中,对正常样本与异常样本均值进行加权平均,根据诊断效率和误报率认为最优模型对应的正常样本均值与异常样本均值权重比为0.8:0.2。     

基于固定尺度欧氏距离的变因子递推子空间辨识算法

针对传统的子空间辨识算法采用固定遗忘因子出现跟踪能力不足或效果易受噪声影响等问题,提出了一种新的变因子递推子空间辨识算法.该算法分为3个步骤:首先引入变因子构造与更新Hankel矩阵和观测向量;其次为保证广义能观测阵的列向量收敛于主子空间的正交基上,采用OPAST算法递推估计广义能观测矩阵,并由广义能观测矩阵估计系统参数矩阵;最后用A的特征值空间距离信息实现变因子,因此,算法具有自适应能力.应用于一类时变系统,仿真结果表明改进算法具有较好的快速跟踪能力和跟踪效果.     

邻域自适应增量式PCA-LPP在齿轮箱故障诊断中的应用EI北大核心CSCD

针对流形学习算法的增量处理问题,提出一种邻域自适应增量式PCA-LPP流形学习算法,阐述了算法的基本原理以及增量样本处理方法。对新增样本的引入,首先根据已有样本对协方差矩阵和相似矩阵进行增量更新,而后结合已有样本降维结果对新增样本降维结果进行估计,最后采用子空间迭代法实现新旧样本降维结果的更新。采用齿轮箱故障信号特征向量对邻域自适应增量式PCA-LPP流形学习算法进行检验,结果表明,邻域自适应增量式PCA-LPP流形学习算法降维后特征具有良好的故障分类识别效果。     

邻域自适应增量式PCA-LPP在齿轮箱故障诊断中的应用

针对流形学习算法的增量处理问题,提出一种邻域自适应增量式PCA-LPP流形学习算法,阐述了算法的基本原理以及增量样本处理方法。对新增样本的引入,首先根据已有样本对协方差矩阵和相似矩阵进行增量更新,而后结合已有样本降维结果对新增样本降维结果进行估计,最后采用子空间迭代法实现新旧样本降维结果的更新。采用齿轮箱故障信号特征向量对邻域自适应增量式PCA-LPP流形学习算法进行检验,结果表明,邻域自适应增量式PCA-LPP流形学习算法降维后特征具有良好的故障分类识别效果。     

一种在线学习的目标跟踪与检测方法

针对现有在线学习跟踪方法缺乏监督机制的缺点,提出一种新的跟踪框架。以随机森林在线学习理论构造分类器作为目标检测器,用SURF特征点匹配方法作为目标跟踪器,跟踪过程中用可靠跟踪的结果形成对检测结果的监督机制,不对低置信度样本或错误样本进行学习,避免了分类器分类精度的逐渐下降,同时在跟踪失败时用目标检测器对目标进行重新捕获,形成跟踪、学习、检测三者有机结合的跟踪框架。对不同视频序列的测试结果表明,本文算法能有效避免目标出现较大外观变化或被大面积遮挡等复杂情况下的跟踪失败问题。     

基于协方差矩阵拟合的宽带无网格波达角估计

宽带波达角(Direction of Arrival,DOA)估计是声呐系统阵列信号处理中一个重要的研究方向。文章提出了一种基于相干子空间的改进稀疏与参数方法(Coherent Signal-subspace based Modified Sparse and Parameter Approach,C-MSPA),以实现高精度和高空间方位分辨能力的宽带DOA估计。算法利用聚焦矩阵将各子带上的采样协方差矩阵投影至聚焦频率上。完成聚焦后,文章基于频率选择的范德蒙分解理论对协方差矩阵拟合准则进行改进,使重构的协方差矩阵中包含的DOA信息严格限制在聚焦区域内,最终对重构的协方差矩阵进行范德蒙分解,得到DOA估计值。所提出的算法无需选取正则参数,同时避免了基不匹配问题。仿真和湖上实测数据分析结果表明,所提出的方法实现了高空间方位分辨能力且提高了DOA估计精度。     

基于粒子滤波的多模态振动信号在线跟踪

针对多模态振动信号的在线监测和跟踪,提出基于随机子空间（SSI）和粒子滤波（PF）算法的仿真振动信号在线监测和跟踪方法。通过SSI算法提取得到振动系统的模态主频和阻尼比,根据振动系统模型模态主频和阻尼比的计算公式,得到系统的状态矩阵和输出矩阵。将计算所得状态矩阵和输出矩阵代入状态方程,利用PF算法进行信号的在线监测和跟踪,实现信号的降噪处理和预测分析。对于大型机械、桥梁等建筑物,对其进行在线监测保障其正常营运对社会经济发展具有深远影响。文中利用SSI算法提取系统的模态参数,进一步构建振动系统的状态矩阵和输出矩阵,并利用PF算法进行信号滤波抑噪和预测,在此基础上可以对结构状态实施在线监测及预警控制,实际大桥斜拉索振动信号测试也表明本文算法可以提供稳定可靠的信号跟踪与预测技术。     

Eigenspace-based blind pattern optimisations of steerable antenna array for interference cancellation

A novel adaptive algorithm for an array using directional elements called a hybrid smart antenna system is proposed. The algorithm controls the element patterns on the basis of an objective function composed of eigenvalues of a covariance matrix. A high and stable array output signal-to-interference-plus-noise ratio is achieved by improving both the received powers and the spatial correlation coefficient between incident waves, without prior knowledge such as directions-of-arrival, channel state information or training signals. The characteristics of the proposed algorithm are theoretically and numerically clarified for a simple case involving two incident waves. Convergence with least mean squares algorithm is found to be as fast as that with recursive least squares algorithm in this system. Also, simulation for statistical performance evaluation is carried out in comparison with a conventional system. Furthermore, a method to implement the proposed eigenspace control algorithm without having to solve the eigenvalue problem is shown.     

Multibaseline InSAR height estimation through joint covariance matrix fitting

A new joint processing method based on joint covariance matrix fitting is presented for the multibaseline synthetic aperture radar interferometry. This method can make full use of the interferometric information embedded in the joint covariance matrix to estimate the terrain height without eigendecomposition and eigenspace division, and is insensitive to the rank variation of the joint signal subspace. By fitting the sample joint covariance matrix tapered with the coherence matrix, this method can work robustly with a finite sample support, which also makes it possible to recover the detail of terrain profile with a small neighbouring sample support. The results of numerical simulations demonstrate the validation of the proposed method.     

Robust T2 control chart using median-based estimators

One of the most widely used multivariate control charts is the Hotelling T². In order to construct a Hotelling T² control chart, the mean vector (μ) and the variance–covariance matrix (Σ) must be first estimated. The classical estimators of μ and Σ are usually used to design Hotelling T² control chart. The classical estimators are sensitive to the presence of outliers. One way to deal with outliers is to use robust estimators. In this study, a robust T² control chart is proposed. The mean vector is obtained from the sample median. The median absolute deviation and the comedian are used as the estimates of the elements of the variance–covariance matrix. The proposed robust estimators of the mean vector and the variance–covariance matrix are compared with the sample mean vector and the sample variance–covariance matrix, and the M estimator of these parameters, through efficiency and robustness measures. The performances of the proposed robust T² control chart and the classical and the M estimators are also compared by means of average run length. Simulation results reveal that the proposed robust T² control chart has much better performance than the traditional Hotelling T² and similar performance to the M estimator in detecting shifts in process mean vector. Use of other robust estimators to estimate the process parameters is an area for further research.     

Vehicle sound signature recognition by frequency vector principalcomponent analysis

The sound of a working vehicle provides an important clue to the vehicle type. In this paper, we introduce the “eigenfaces method,” originally used in human face recognition, to model the sound frequency distribution features. We show that it can be a simple and reliable acoustic identification method if the training samples can be properly chosen and categorized. We treat the frequency spectrum in a 200 ms time interval (a “frame”) as a vector in a high-dimensional frequency feature space. In this space, we study the vector distribution for each kind of vehicle sound produced under similar working conditions. A collection of typical sound samples is used as the training data set. The mean vector and the most important principal component eigenvectors of the covariance matrix of the zero-mean-adjusted samples together characterize its sound signature. When a new zero-mean-adjusted sample is projected into the principal component eigenvector directions, a small residual vector indicates that the unknown vehicle sound can be well characterized in terms of the training data set     

A fast method for robust principal components with applications to chemometrics

When faced with high-dimensional data, one often uses principal component analysis (PCA) for dimension reduction. Classical PCA constructs a set of uncorrelated variables, which correspond to eigenvectors of the sample covariance matrix. However, it is well-known that this covariance matrix is strongly affected by anomalous observations. It is therefore necessary to apply robust methods that are resistant to possible outliers.

Li and Chen [J. Am. Stat. Assoc. 80 (1985) 759] proposed a solution based on projection pursuit (PP). The idea is to search for the direction in which the projected observations have the largest robust scale. In subsequent steps, each new direction is constrained to be orthogonal to all previous directions. This method is very well suited for high-dimensional data, even when the number of variables p is higher than the number of observations n. However, the algorithm of Li and Chen has a high computational cost. In the references [C. Croux, A. Ruiz-Gazen, in COMPSTAT: Proceedings in Computational Statistics 1996, Physica-Verlag, Heidelberg, 1996, pp. 211–217; C. Croux and A. Ruiz-Gazen, High Breakdown Estimators for Principal Components: the Projection-Pursuit Approach Revisited, 2000, submitted for publication.], a computationally much more attractive method is presented, but in high dimensions (large p) it has a numerical accuracy problem and still consumes much computation time.

In this paper, we construct a faster two-step algorithm that is more stable numerically. The new algorithm is illustrated on a data set with four dimensions and on two chemometrical data sets with 1200 and 600 dimensions.     

基于迁移学习与深度残差网络的滚动轴承快速故障诊断算法EI北大核心CSCD

针对现有基于深度学习的滚动轴承故障诊断算法训练参数量大,训练时间长且需要大量训练样本的缺点,提出了一种基于迁移学习(TL)与深度残差网络(ResNet)的快速故障诊断算法(TL-ResNet)。首先开发了一种将短时傅里叶变换(STFT)与伪彩色处理相结合的振动信号转三通道图像数据的方法;然后将在ImageNet数据集上训练的ResNet18模型作为预训练模型,通过迁移学习的方法,应用到滚动轴承故障诊断领域当中;最后对滚动轴承在不同工况下的故障诊断问题,提出了采用小样本迁移的方法进行诊断。在凯斯西储大学(CWRU)与帕德博恩大学(PU)数据集上进行了试验,TL-ResNet的诊断准确率分别为99.8%与95.2%,且在CWRU数据集上TL-ResNet的训练时间仅要1.5 s,这表明本算法优于其他的基于深度学习的故障诊断算法与经典算法,可用于实际工业环境中的快速故障诊断。