Brain computer interface (BCI) offers disabled people a nonmuscular communication pathway. Event-related potential (ERP) is an efficient way to achieve the BCI system. One of important issues for ERP classification is...
详细信息
ISBN:
(纸本)9781509012251
Brain computer interface (BCI) offers disabled people a nonmuscular communication pathway. Event-related potential (ERP) is an efficient way to achieve the BCI system. One of important issues for ERP classification is the under sample problem, that is the feature dimension is very high while the sample number is very strictly limited. In this paper, we introduce a P300 feature extraction and classification framework using the sparse optimal score method for discriminative analysis by generalized elastic net model. In order to break the curse of dimension, regularized estimation of within-class covariance matrix is achieved and ℓ1 penalty is applied to learn sparse discriminant vectors. The optimization problem is solved by the alternating least square procedure. We test the proposed framework on P300 target detection task and experimental results indicate that it is able to improve the classification accuracy in P300-based BCI system. The efficient features extracted by our proposed framework provide overall better P300 classification accuracy than several baseline methods especially in the single trial and few training samples case.
This paper investigates the uniformly ultimate boundedness(UUB) of an identifier-based adaptive dynamic programming(ADP) algorithm proposed in [7]. It is demonstrated that the estimation errors of weights in both crit...
详细信息
ISBN:
(纸本)9781467374439
This paper investigates the uniformly ultimate boundedness(UUB) of an identifier-based adaptive dynamic programming(ADP) algorithm proposed in [7]. It is demonstrated that the estimation errors of weights in both critic and action networks are UUB during iteration learning. Moreover, a selection method on learning rates is also given.
This paper focuses on the H ∞ fault detection (FD) problem for spring-mass systems (SMSs) over networks with distributed state delays, random packet losses, sensor saturation as well as multiplicative noises via unr...
详细信息
This paper focuses on the H ∞ fault detection (FD) problem for spring-mass systems (SMSs) over networks with distributed state delays, random packet losses, sensor saturation as well as multiplicative noises via unreliable communication channels. The output measurements are affected by sensor saturation which is described by sector-nonlinearities. The multiplicative noises are described as a form of Gaussian white noises multiplied by the states. A series of stochastic variables are introduced to describe the randomly occurring distributed state delays. Random packet losses are also introduced in unreliable communications. The purpose of this paper is to design an FD filter such that: 1) The FD dynamic system is exponentially stable in the mean square. 2) The error between the fault signal and the residual signal is controlled to the minimum. 3) The optimal H ∞ filtering performance index is achieved. A sufficient condition for the FD filter design is derived in terms of the solution to a linear matrix inequality (LMI). When the LMI has a feasible solution, the explicit parameters of the desired FD filter can be obtained. Finally, a simulation experiment is illustrated to show the effectiveness and application of the designed method.
Conventional principal component analysis(PCA) can obtain low-dimensional representations of original data space, but the selection of principal components(PCs) based on variance is subjective, which may lead to infor...
详细信息
Conventional principal component analysis(PCA) can obtain low-dimensional representations of original data space, but the selection of principal components(PCs) based on variance is subjective, which may lead to information loss and poor monitoring performance. To address dimension reduction and information preservation simultaneously, this paper proposes a novel PC selection scheme named full variable expression. On the basis of the proposed relevance of variables with each principal component, key principal components can be *** the key principal components serve as a low-dimensional representation of the entire original variables, preserving the information of original data space without information loss. A squared Mahalanobis distance, which is introduced as the monitoring statistic, is calculated directly in the key principal component space for fault detection. To test the modeling and monitoring performance of the proposed method, a numerical example and the Tennessee Eastman benchmark are used.
作者:
Bingyong YanHousheng SuWei MaSchool of Automation
Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology 130 Meilong Road Shanghai 200237 China School of Automation
Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory for Advanced Materials & Institute of Fine Chemicals
East China University of Science and Technology 130 Meilong Road Shanghai 200237 China
In this paper, we present a novel fault detection and identification (FDI) scheme for a class of nonlinear systems with model uncertainty. At the heart of this approach is an on-line approximator, referred to as fault...
详细信息
In this paper, we present a novel fault detection and identification (FDI) scheme for a class of nonlinear systems with model uncertainty. At the heart of this approach is an on-line approximator, referred to as fault tracking approximator (FTA). Differently from the other approximators, the FTA uses iterative algorithms to detect and identify nonlinear system faults, even in the presence of model uncertainty, which is motivated by predictive control theory and iterative learning control theory. The FTA can simultaneously detect and identify the shape and magnitude of the faults. The rigorous stability analysis and fault tracking properties of the FTA are also proved. Finally, two examples are given to illustrate the feasibility and effectiveness of the proposed approach.
control and regulation of furnace firing is essential to extend the runiength of new and existing furnaces. Accurate Computational Fluid Dynamic simulations of the furnace are essential for this purpose. This requires...
详细信息
ISBN:
(纸本)9781510806924
control and regulation of furnace firing is essential to extend the runiength of new and existing furnaces. Accurate Computational Fluid Dynamic simulations of the furnace are essential for this purpose. This requires among others accounting for the detailed geometry of the burners. Also the so-called "shadow effect" 6 arising from the projected shadows between adjacent reactors leads to significant heat flux non-uniformities. This phenomenon is important but its effect on product yields is often ignored as only a single reactor is simulated. For the USC furnace simulated in this work, shadow effects cause a maximum difference in COT of 29 K and a difference in P/E-ratioof 0.1 between two different U-coils in the furnace. In order to obtain more uniform TMT's, COTs and olefin yields for the individual reactors, different furnace optimization methods were compared and their results are discussed. Full furnace CFD simulations prove to be essential in design and during debottlenecking, when aiming for a more uniform COT distribution to the reactors by fuel distribution.
Synthesis and optimization of utility system usually involve grassroots design, retrofitting and operation optimization, which should be considered in modeling process. This paper presents a general method for synthes...
详细信息
Synthesis and optimization of utility system usually involve grassroots design, retrofitting and operation optimization, which should be considered in modeling process. This paper presents a general method for synthesis and optimization of a utility system. In this method, superstructure based mathematical model is established, in which different modeling methods are chosen based on the application. A binary code based parameter adaptive differential evolution algorithm is used to obtain the optimal con figuration and operation conditions of the system. The evolution algorithm and models are interactively used in the calculation, which ensures the feasibility of con figuration and improves computational ef ficiency. The capability and effectiveness of the proposed approach are demonstrated by three typical case studies.
Brain computer interface (BCI) could help patients to manipulate external devices based on the specific brain activities. One of the most popular BCI systems is the visual-based BCI system. Mostly, users were asked to...
详细信息
ISBN:
(纸本)9781467376808
Brain computer interface (BCI) could help patients to manipulate external devices based on the specific brain activities. One of the most popular BCI systems is the visual-based BCI system. Mostly, users were asked to pay attention not only to the target stimulus, but also to the real control target which would bring high workload to users and affect the control efficiency of BCI systems. In this paper, a real-time monitoring system was developed to solve this problem by showing the environment information from the camera on the computer screen. Five subjects took part in this experiment and all of them were asked to control a small car to the target position. Our result showed that all subjects could finish the task within two or three minutes. In this study, subject did not need to switch their attention on the car which was out of their sight, and it would help to improve the usability of BCI in the practical application.
The p-xylene (PX) oxidation process is of great industrial importance because of the strong demand of the global polyester fiber. A steady-state model of the PX oxidation has been studied by many researchers. In our p...
详细信息
The computation burden in the model-based predictive control algorithm is heavy when solving QR optimization with a limited sampling step, especially for a complicated system with large dimension. A fast algorithm is ...
详细信息
暂无评论