Xiangyu Kong

Xiangyu Kong
Xi'an Jiaotong University | XJTU · School of Electronic and Information Engineering

About

71
Publications
3,530
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
574
Citations
Citations since 2017
31 Research Items
437 Citations
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
Introduction
Skills and Expertise

Publications

Publications (71)
Article
Projection to latent structure (PLS) is a well-known data-based approach widely used in industrial process monitoring. Kernel PLS (KPLS) was proposed in prior studies to apply the PLS in the nonlinear process. However, KPLS-based methods only consider the nonlinear variation of the input and ignore that of the input and output simultaneously. Once...
Article
In this paper, in order to monitor the slow-time-varying industrial process, an adaptive method is proposed based on the neural network model and fault reconstruction method. Firstly, a unified neural network algorithm is introduced to extract the principal and minor eigen subspace with low computational complexity, and the whole eigenspace is divi...
Article
The partial least squares (PLS) method has been successfully applied for fault diagnosis in industrial production. Compared with the traditional PLS methods, the modified PLS (MPLS) approach is available for slow-time-varying data processing and quality-relevant fault detecting. However, it encounters heavy computational load in model updating, and...
Article
Independent component analysis (ICA) is a commonly used non-Gaussian process fault diagnosis method. A fault detection algorithm of kernel dynamic ICA (KDICA) has been proposed for the non-Gaussian process with dynamic and nonlinear characteristics. However, a lack of studies tackling the fault reconstruction and fault diagnosis algorithm exists. H...
Article
In fault diagnosis, partial least squares (PLS) is a popular data-driven method to identify abnormal key performance indicators (KPI). However, there are two problems in fault diagnosis when using PLS, including inaccurate fault subspace extraction and unidentified false alarms. In the first problem, the improved PLS (IPLS) model is adopted to obta...
Article
As a typical data-driven technology, projection to latent structure (PLS) has been successfully applied in the quality-related fault diagnosis. However, the oblique decomposition induced by PLS results in redundant component in fault subspace, which imposes a negative influence on the reconstruction-based fault diagnosis. Thus, two fault subspace m...
Article
Full-text available
In this paper, we propose an effective neural network algorithm to perform singular value decomposition (SVD) of a cross-correlation matrix between two data streams. Different from traditional algorithms, the newly proposed algorithm can extract not only the principal singular vectors but also the corresponding principal singular values. First, a d...
Article
Generalized eigenvalue decomposition has many advantages when it is applied in modern signal processing. Compared with other methods, neural network model-based algorithms provide an efficient way to solve such problems online. Generalized feature extraction algorithms based on neural network models have been described in the literature. However, t...
Article
Full-text available
A dual-purpose algorithm is capable of estimating the principal component and minor component from input signals by simply switching the sign of some terms in the same learning rule. Compared with single-purpose algorithms, a dual-purpose algorithm has many advantages. In this paper, a novel dual-purpose algorithm is proposed based on the study of...
Article
Full-text available
In the present work, based on the generalized principal component analysis, we propose a new approach to decompose the subspace of fault deviations, which is used for reconstruction-based fault diagnosis through principal component analysis (PCA) monitoring system. The proposed method is advanced since it lightens the computational burden by elimin...
Article
Full-text available
In industrial processes, the quality of the product is crucial. The batch partial least squares (PLS) monitoring model can effectively monitor for quality-related faults. In process monitoring, to overcome time-varying disturbances, the monitoring model needs to be updated regularly. Efficiently updating the monitoring model represents a serious pr...
Article
Full-text available
Modified partial least squares (MPLS) is an efficient tool widely used in multivariate statistical process monitoring. To properly describe slow time-varying processes, the method commonly used in model updating is data expansion. However, when the number of lagged variables grows, the modeling order and computational load increase significantly. A...
Article
Full-text available
The partial least squares (PLS) method has been widely used in quality-related industrial process monitoring because of its ability to extract quality-related information. Generally, online quality monitoring data cannot be obtained in real time, and in this case, updating the online monitoring model is a serious challenge. In this study, an online...
Article
Full-text available
Generalized minor component analysis (GMCA) is of great use in modern signal processing. The GMCA algorithms can be simplified to extract the minor generalized eigenvector of the autocorrelation input matrices pencil. In contrast to batching methods, the Hebbian-rule-based algorithm can extract the minor generalized eigenvector online. Few Hebbian-...
Article
Generalized eigendecomposition, which extracts the generalized eigenvector from a matrix pencil, is a powerful tool and has been widely used in many fields, such as data classification and blind source separation. First, to extract the minor generalized eigenvector (MGE), we propose a deterministic discrete-time (DDT) system. Unlike some existing s...
Article
Full-text available
In this paper, we propose a fast and effective neural network algorithm to perform singular value decomposition (SVD) of a cross-covariance matrix between two high-dimensional data streams. Firstly, we derive a dynamical system from a newly proposed information criterion. This system exhibits a single stable stationary point if and only if the weig...
Article
Full-text available
Neural network algorithms on principal component analysis (PCA) and minor component analysis (MCA) are of importance in signal processing. Unified (dual purpose) algorithm is capable of both PCA and MCA, thus it is valuable for reducing the complexity and the cost of hardware implementations. Coupled algorithm can mitigate the speed-stability probl...
Article
Minor component (MC) plays an important role in signal processing and data analysis, so it is a valuable work to develop MC extraction algorithms. Based on the concepts of weighted subspace and optimum theory, a weighted information criterion is proposed for searching the optimum solution of a linear neural network. This information criterion exhib...
Chapter
Recently, as a powerful feature extraction technique, generalized eigen decomposition (GED) has been attracting great attention and been widely used in many fields, e.g., spectral estimation (Huanqun et al. IEEE Trans Acoust Speech Signal Process 34(2), 272–284, 1986), blind source separation (Chang et al. IEEE Trans Acoust Speech Signal Process 48...
Chapter
From the preceding chapters, we have seen that in the wake of the important initiative work by Oja and Sanger, many neural network learning algorithms for PCA have been developed.
Chapter
In this chapter, we review some basic concepts, properties, and theorems of singular value decomposition (SVD), eigenvalue decomposition (ED), and Rayleigh quotient of a matrix. Moreover, we also introduce some basics of matrix analysis. They are important and useful for our theoretical analysis in subsequent chapters.
Chapter
The minor subspace (MS) is a subspace spanned by all the eigenvectors associated with the minor eigenvalues of the autocorrelation matrix of a high-dimensional vector sequence. The MS, also called the noise subspace (NS), has been extensively used in array signal processing. The NS tracking is a primary requirement in many real-time signal processi...
Chapter
Among neural network-based PCA or MCA algorithms, most previously reviewed do not consider eigenvalue estimates in the update equations of the weights, except an attempt to control the learning rate based on the eigenvalue estimates.
Chapter
PCA is a statistical method, which is directly related to EVD and SVD. Neural networks-based PCA method estimates PC online from the input data sequences, which especially suits for high-dimensional data due to the avoidance of the computation of large covariance matrix, and for the tracking of nonstationary data, where the covariance matrix change...
Chapter
The PS is a subspace spanned by all eigenvectors associated with the principal eigenvalues of the autocorrelation matrix of a high-dimensional vector sequence, and the subspace spanned by all eigenvectors associated with the minor eigenvalues is called the MS.
Chapter
The convergence of neural network-based PCA or MCA learning algorithms is a difficult topic for direct study and analysis. Traditionally, based on the stochastic approximation theorem, the convergence of these algorithms is indirectly analyzed via corresponding DCT systems. The stochastic approximation theorem requires that some restrictive conditi...
Book
This book not only provides a comprehensive introduction to neural-based PCA methods in control science, but also presents many novel PCA algorithms and their extensions and generalizations, e.g., dual purpose, coupled PCA, GED, neural based SVD algorithms, etc. It also discusses in detail various analysis methods for the convergence, stabilizing,...
Article
Generalized minor component analysis (GMCA) is an essential technique in data classification and signal processing. In this paper, we propose an information criterion for GMCA and derive a fast GMCA algorithm for extracting the first generalized minor component (GMC) by using quasi-Newton method to this information criterion. In order to extract mu...
Article
Full-text available
Generalized eigendecomposition problem has been widely employed in many signal processing applications. In this paper, we propose a unified and self-stabilizing algorithm, which is able to extract the first principal and minor generalized eigenvectors of a matrix pencil of two vector sequences adaptively. Furthermore, we extend the proposed algorit...
Article
Full-text available
The generalized Hermitian eigenvalue problem (GHEP) is of great use in modern signal processing. Compared with other methods, neural network model based algorithms provide an efficient way to solve such problems online. Up to now, a class of neural network model based generalized feature extraction algorithms have been reported in the literature. H...
Article
Full-text available
This paper proposes a novel coupled neural network learning algorithm to extract the principal singular triplet (PST) of a cross-correlation matrix between two high-dimensional data streams. We firstly introduce a novel information criterion (NIC), in which the stationary points are singular triplet of the crosscorrelation matrix. Then, based on Ne...
Conference Paper
Full-text available
Coupled learning algorithm, in which the eigenvector and eigenvalue of a covariance matrix are estimated in coupled equations simultaneously, is a solution to the speed-stability problem that plagues most noncoupled learning rules. Moller has proposed a class of well-performed CPCA (coupled principal component analysis) algorithms, but it is a pity...
Conference Paper
Full-text available
A major and common problem, which is the so-called speed-stability problem, exists in most noncoupled neural network based algorithms for principal (PCA) and minor (MCA) component analysis. Coupled PCA or MCA algorithms, in which the principal or minor eigenvector and the corresponding eigenvalue of a covariance matrix are estimated in coupled equa...
Article
Residual lifetime (RL) estimation is a key part in prognostics and health management. This paper addresses the problem of estimating the RL from observed degradation data. A Brownian motion in the framework of a similarity-based model utilizing degradation histories with failure and suspension events is developed to achieve this aim. A novel contri...
Article
This paper considers the problem of robust stability for a class of linear systems with interval time-varying delay and nonlinear perturbations. Less conservative stability criteria was put forward by using delay-partitioning approach. By decomposing the delay interval into multiple equidistant subintervals, new Lyapunov–Krasovskii (L–K) functional...
Article
Prognostics and health management has drawn increasing attention and gained deepening recognition and widening applications during the past decades. Due to offering guidance for sequential managements involving inspection schedule, maintenance, replacement, and spare parts ordering, remaining useful life estimation has been termed as the kernel tec...
Article
This paper considers the problem of delay-dependent non-fragile H ∞ control for a class of linear systems with interval time-varying delay. Based on the direct Lyapunov method, an appropriate Lyapunov-Krasovskii functional (LKF) with triple-integral terms and augment terms is introduced. Then, by using the integral inequalities and convex combinati...
Article
Remaining useful life (RUL) prediction is an important part in prognostics and health management. This paper addresses the problem of estimating RUL from observed degradation data. A Wiener-process-based model for online lifetime prediction is developed to achieve this aim. In this paper a Wiener process with non-linear drift and measurement error...
Article
Full-text available
Prognostics-based spare part ordering and system replacement (PSOSR) policies are at the forefront of the prevalent prognostics and health management discipline. However, almost all of the existing researches in this domain ignore the stochasticity of the lead time. With this in mind, this paper proposes a PSOSR policy based on the real-time health...
Article
This paper concerns the problem of predicting residual storage life for a class of highly critical systems with operation state switches between the working state and storage state. A success of estimating the residual storage life for such systems depends heavily on incorporating their two main characteristics: 1) system operation process could ex...
Article
There are two problems, which should be paid attention to when using kernel partial least squares (KPLS), one is overfitting and another is how to eliminate the useless information mixed in the independent variables X. In this paper, the stochastic gradient boosting (SGB) method is adopted to solve the overfitting problems and a new method called k...
Article
A novel information criterion for principal singular subspace tracking is proposed and a corresponding principal singular subspace gradient flow is derived based on the information criterion in this paper. The information criterion exhibits a unique global minimum attained if and only if the state matrices of the left and right neural networks span...
Article
The minor component analysis (MCA) deals with the recovery of the eigenvector associated with the smallest eigenvalue of the autocorrelation matrix of the input data, and Möller algorithm is a famous self-stability MCA method. In this paper, we present a convergence analysis of Möller algorithm for estimating minor component of an input signal via...
Article
This paper considers the problem of delay-dependent robust stability for uncertain systems with interval time-varying delays. By using the direct Lyapunov method, a new Lyapunov-Krasovskii (L-K) functional is introduced based on decomposition approach, when dealing with the time derivative of L-K functional, a new tight integral inequality is adopt...
Article
This paper considers the delay-dependent robust H∞ control problem for a class of linear systems with interval time-varying delay and norm-bounded uncertainties. An improved delay-dependent bounded real lemma (BRL) for the systems is established based on a new candidate Lyapunov-Krasovskii (L-K) functional and linear matrix inequality (LMI). Then b...
Article
Unified algorithms for principal and minor components analysis can be used to extract principal components and if altered simply by the sign, it can also serve as a minor component extractor. Obviously, the convergence of these algorithms is an essential issue in practical applications. This paper studies the convergence of a unified PCA and MCA al...
Article
For the case where the products have nonlinear performance degradation paths and there is little performance degradation data for each individual, in order to take full advantage of performance degradation data of the same kind of products in individual real-time lifetime prediction, as viewed from the comparability of degradation paths, a class of...
Article
Recently, many unified learning algorithms have been developed for principal component analysis and minor component analysis. These unified algorithms can be used to extract principal components and, if altered simply by the sign, can also serve as a minor component extractor. This is of practical significance in the implementations of algorithms....
Article
The dual purpose principal and minor subspace gradient flow can be used to track principal subspace (PS) and if altered simply by the sign, it can also serve as a minor subspace (MS) trackor. This is of practical significance in the implementations of algorithms. In this paper, a unified information criterion is proposed and a dual purpose principa...
Conference Paper
Singular spectrum analysis (SSA) is a powerful method for separating source signals from the mixed signal. There is an important factor when we use SSA extracting each source signal, i.e. we should select a suitable window length for constructing the trajectory matrix. If the window length were not properly selected, the source signals could not be...
Conference Paper
Flying Wing UAV is attractive in the future because of its aerodynamic characteristic and stealth character. A kind of FTC is provided with sliding mode control and control allocation, with respect to all kinds of fault of effectors. A multi-loop smooth sliding mode control is developed to accommodate to partial loss, partial stick, partial flappin...
Article
For forecasting the gyro drift tendency of a missle, a prediction model based on Volterra series is established by taking the time series of gyro's drift as study object, and a parallel recursive affine projection(AP) algorithm for nonlinear system based on Volterra series is presented in this paper. Taking the minimum norm of the Volterra kernel v...
Article
Minor subspace analysis (MSA) is a statistical method for extracting the subspace spanned by all the eigenvectors associated with the minor eigenvalues of the autocorrelation matrix of a high-dimension vector sequence. In this paper, we propose a self-stabilizing neural network learning algorithm for tracking minor subspace in high-dimension data s...
Article
The minor component analysis (MCA) deals with the recovery of the eigenvector associated to the smallest eigenvalue of the autocorrelation matrix of the input dada, and it is a very important tool for signal processing and data analysis. This brief analyzes the convergence and stability of a class of self-stabilizing MCA algorithms via a determinis...
Article
The minor component (MC) is the eigenvector associated with the smallest eigenvalue of the correlation matrix of input data. In many information processing areas, it is important to online extract MC from high-dimensional input data stream. Usually, MCA learning algorithms are described by stochastic discrete time (SDT) systems and the convergence...
Article
A neural approach for the parameter estimation of adaptive FIR filters for linear system identification is presented in the paper. It is based on a linear neuron with a modified gradient algorithm, capable of resolving the total least squares (TLS) problem present in this kind of estimation, where noisy errors affect not only the observation vector...
Article
Aiming at the nonlinear system identification problem, a parallel recursive affine projection (AP) adaptive algorithm for the nonlinear system based on Volterra series is presented in this paper. The algorithm identifies in parallel the Volterra kernel of each order, recursively estimate the inverse of the autocorrelation matrix for the Volterra in...
Article
For the fault diagnosis of a nonlinear system, the fault diagnosis theory and methods based on the Volterra series model are roundly summarized. Because the Volterra series model can completely describe the transfer characteristics of the nonlinear system, it can be utilized in the fault diagnosis of a nonlinear system. So during the system working...
Article
According to the multimodels combining idea, a new online modeling method based on the preset models combination for Volterra series model is presented to reduce the computation for online modeling of Volterra series model of nonlinear systems. The current Volterra series model of the detected system is online obtained by combining some preset mode...
Conference Paper
Generalized frequency response functions (GFRFs) are a kind of nonparametric model in frequency domain for nonlinear system, which have clear physical signification and application value. Because the direct frequency domain identification of the generalized frequency response functions requires enormous computation, the online engineering applicati...
Article
Aiming at the filter problem that exists when the input and output signal are both corrupted by noise , a robust total least square adaptive algorithm is proposed. Taking the minimum Rayleigh quotient as the loss function , the recur2 sive formula of weight vector is derived , the stochastic discrete laws are applied to the analysis of the rule of...
Article
The decoupling problem for Volterra adaptive filters is researched, and fully decoupled RLS adaptive Volterra filters is presented. According to the pseudo-linear combination structure of Volterra filters, by applying the principle of RLS filter and constrained optimization theory, a fully decoupled Volterra normal equation with block diagonal inpu...
Conference Paper
This paper presents a fault-diagnosis method based on the approaches of phase space reconstruction and generalized frequency response functions (GFRF) for the complex electronic system. The system parameter-evolving induced nonstationary is treated as the studying object. The phase space reconstruction and Gamma-test algorithm are employed to conve...
Article
Full-text available
Aiming at the nonlinear filtering problem that exists when the input and output observation data are both corrupted by noises, a stable total least square adaptive algorithm for the nonlinear Volterra filter is proposed in this paper. Taking the minimum Rayleigh Quotient of the augmented Volterra weight vectors and a constraint to the last element...

Network

Cited By

Projects