Filtering and feature extraction are very important in the analysis and study of EEG signal under +Gz acceleration. In this study, a new filter of different frequency characteristics of EEG signal under +Gz accelerati...
详细信息
In this paper, a quantized H_∞ control problem for networked control systems (NCSs) subject to randomly multi-step transmission delays is investigated. A quantizer is used before the measurement signal enters the com...
详细信息
ISBN:
(纸本)9781479940318
In this paper, a quantized H_∞ control problem for networked control systems (NCSs) subject to randomly multi-step transmission delays is investigated. A quantizer is used before the measurement signal enters the communication network and the randomly multi-step transmission delays which are described by a mathematical model are considered during the transmission through the network. Sufficient conditions are derived for the considered system to satisfy the H_∞ norm constraint subject to the randomly multi-step transmission delays. Simulation results demonstrate the effectiveness of the proposed method.
Common spatial pattern(CSP) has been one of the most popular methods for EEG feature extraction in brain-computer interface(BCI) application. Although the CSP usually provides good discriminant features for classifica...
详细信息
Common spatial pattern(CSP) has been one of the most popular methods for EEG feature extraction in brain-computer interface(BCI) application. Although the CSP usually provides good discriminant features for classification,it is also known to be sensitive to overfitting and *** study introduces a shrinkage technique to regularize estimation of the covariance matrices in the CSP and hence a novel shrinkage CSP(SCSP) method,which could effectively alleviate the effects of small training sample size and unbalanced data on classification. The proposed SCSP is validated on feature extraction of P300 that has been widely adopted for BCI *** accuracies are evaluated by using linear discriminant analysis(LDA) with experimental EEG data from seven *** results indicate that the proposed SCSP extracts more effective features that yield higher classification accuracy than that by the traditional CSP.
the Molecular weight distribution(MWD)is an important quality index for the polymer material,but detecting the MWD in real-time is still difficult by *** rapid real-time detection method for MWD with good accuracy is ...
详细信息
the Molecular weight distribution(MWD)is an important quality index for the polymer material,but detecting the MWD in real-time is still difficult by *** rapid real-time detection method for MWD with good accuracy is the current hotspot in the polymer *** from the method other literatures have described,in this work the reaction mechanism and the industrial information will be merged to build a hybrid model for the MWD to solve the prediction accuracy and real-time problems,using the weighted superposition of the distribution function on each active center of catalyst to fit the MWD and applying the multi-output support vector machine regression(MSVR)algorithm to describe the relationship between process conditions and the parameters of distribution *** the unconstrained nonlinear optimization method has been used to optimize the process conditions based on the hybrid ***,the application of the above-mentioned approach in the ethylene polymerization process has verified the feasibility.
Intelligent procedure expert system was developed to select appropriate GTAW procedure in this ***,the function design and implementation methods of the welding procedure expert system were *** expert system can prese...
详细信息
Intelligent procedure expert system was developed to select appropriate GTAW procedure in this ***,the function design and implementation methods of the welding procedure expert system were *** expert system can present the welding procedure card,multimedia display of welding process,and output function to makes the data sharing more ***,the database design of the welding procedure expert system based on C/S mode was presented where the expert knowledge was *** last,the neural network model was established to realize procedure selection based on the neural network learning ability and the welding case from the *** the BPNN model,the welding parameters can be obtained based on the input welding conditions.
Gasoline blending is a critical process in petroleum refineries. Real-time optimization(RTO) techniques have been popular with the applications for the blending process for optimization purpose. However the dependency...
详细信息
Gasoline blending is a critical process in petroleum refineries. Real-time optimization(RTO) techniques have been popular with the applications for the blending process for optimization purpose. However the dependency of RTO on the measurement of the component impairs its applicability. Therefore how to utilize the blending model and the product measurement to free RTO from the component measurement is the major research topic in this paper. Unscented Kalman Filter, due to its ability to estimate the parameter for nonlinear model, is chosen to estimate component properties based on the product measurement. The RTO strategy is then proposed with the UKF method for the recipe calculation periodically. Furthermore, the proposed RTO is tested with the gasoline blending benchmark problem, while the results are compared with the ideal blending case. The accuracy of the component estimation and the efficiency of the RTO are verified with the results.
Probabilistic model has already been widely used for process monitoring. However, the obtained factors may contain quality-unrelated information, which is harmful to the quality-related process monitoring. Meanwhile, ...
详细信息
Probabilistic model has already been widely used for process monitoring. However, the obtained factors may contain quality-unrelated information, which is harmful to the quality-related process monitoring. Meanwhile, considering the situation of unequal sample rates of process and quality variables, a semi-supervised orthogonal factor analysis(Semi-SOFA) model is presented, further, to improve robustness, Semi-SOFA is extended to weighted form(WSemi-SOFA). This paper performs orthogonal decomposition on the obtained factors, which divides them into two parts: quality-related one and quality-unrelated one. Based on it, the corresponding T statistics are designed to offer quality-related process monitoring, respectively. Besides, SPE statistics are constructed as supplement to monitor residuals. For effectiveness demonstration of the proposed method, TE benchmark is utilized.
To solve the non-Gaussian and time-varying dynamics problems of batch process,a new monitoring method called Independent component analysis and Just-in-time learning multiple subspace support vector data description(I...
详细信息
To solve the non-Gaussian and time-varying dynamics problems of batch process,a new monitoring method called Independent component analysis and Just-in-time learning multiple subspace support vector data description(ICA-JITL-MSSVDD) is *** offline,a new multiple variable subspaces division method used for batch process based on Independent component analysis(ICA) is *** proposed multiple subspace division method is used as a global non-Gaussian modeling *** online,Just-in-time learning multiple(JITL) is employed to extract similar samples,and multiple subspace support vector data description(MSSVDD) models are *** method can solve the time-varying dynamics problem and MSSVDD is used as a local non-Gaussian modeling *** the integration of global and local non-Gaussian modeling methods,the non-Gaussian and time-varying dynamics problems of batch process can be *** fault detection effectiveness of ICA-JITL-MSSVDD can be demonstrated by simulating the fed-batch penicillin fermentation process.
For probabilistic monitoring of multimode processes,this paper introduced a monitoring scheme that integrates joint probability density and weighted probabilistic principal component analysis based on coefficient of v...
详细信息
For probabilistic monitoring of multimode processes,this paper introduced a monitoring scheme that integrates joint probability density and weighted probabilistic principal component analysis based on coefficient of variation(CV-WPPCA). A joint probability based on 2 statistic was constructed for mode identification. After it concentrated maximum fault-relevant information into dominant subspace by identifying and extracting important noise factors from the residual subspace,the new approach utilized a weighting strategy based on coefficient of variation method to highlight the useful information in the reconstructed dominant subspace. A case study on the Tennessee Eastman process was applied to demonstrate the efficiency of the proposed method.
chemicalprocesses with multiple operational modes are common in modern process *** fault diagnosis methods meet challenges when facing multimodal complex data *** order to tackle this challenge,a new fault diagnosis ...
详细信息
chemicalprocesses with multiple operational modes are common in modern process *** fault diagnosis methods meet challenges when facing multimodal complex data *** order to tackle this challenge,a new fault diagnosis approach utilizing hidden Markov model(HMM) is developed in this paper.A HMM trained by normal process data with multimodal feature has several hidden *** operating mode is represented by a hidden state which should be described via a finite Gaussian mixture *** multivariate Gaussian mixture distribution targets complex data distribution within each individual ***,for a monitored sample,the Mahalanobis distance(MD) inside each Gaussian component is constructed as monitoring *** contribution index is obtained through the differential decomposition along every variable direction to MD-based monitoring *** last,the hidden state Gaussian component probability strategy is used to integrate local monitoring index and local variable contribution index across all Gaussian components into a global monitoring indicator and a global variable contribution *** derived variable contribution index with probabilistic feature is employed to locate faulty *** to a numerical simulation and the Tennessee Eastman(TE) process display the fault detection and diagnosis performance of our proposed method.
暂无评论