检索结果-内蒙古大学图书馆

Modeling Method of Data-driven Model Combined with A Priori Knowledge and Its Application in Average Particle Size Estimation of Composite Colloidal Sols

Modeling Method of Data-driven Model Combined with A Priori ...

引用

第28届中国过程控制会议（CPCC 2017）暨纪念中国过程控制会议30周年

作者： Yang Zhou Wenxi Xu Shaojun Li Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and TechnologyMinistry of Education

We present a universally applicable hybrid modeling method for nonlinear industrial processes that combine the a priori process knowledge with a data-driven *** method constructs a unified framework for the modeling process by integrating a data-driven modeling technique,sampling detection technique,constraint optimization problem,and an evolutionary *** the modeling process,a swarm intelligence algorithm is used to optimize the model parameters under the circumstances of satisfying the constraints of a priori *** adding the constraints of process a priori knowledge,we can obtain more information about the actual process and avoid the over-fitting problem to some extent,especially when modeling a system with a small quantity of *** order to show the effectiveness of the method proposed in this paper,two general data-driven models,the polynomial regression model and radial basis function network model,are used as case ***,a function simulation experiment is designed to test effectiveness,and applied to estimate average particle size of ZrO2-TiO2 composite colloidal sols.

关键词： Data-driven modeling A priori knowledge Constraint handling Intelligence algorithm Hybrid model

来源：评论

学校读者我要写书评

暂无评论

A novel fault diagnosis approach using hidden Markov model for a multimode process

A novel fault diagnosis approach using hidden Markov model f...

引用

第28届中国过程控制会议（CPCC 2017）暨纪念中国过程控制会议30周年

作者： Fan Wang Hongbo Shi Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology

chemical processes 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.

关键词： Hidden Markov model Fault diagnosis Multimode process Fault detection

来源：评论

学校读者我要写书评

暂无评论

Non-Gaussian dynamic batch process monitoring based on ICA-JITL-MSSVDD

Non-Gaussian dynamic batch process monitoring based on ICA-J...

引用

第28届中国过程控制会议（CPCC 2017）暨纪念中国过程控制会议30周年

作者： Zhaomin Lv Xuefeng Yan Qingchao Jiang .Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology

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.

关键词： Batch process monitoring Independent component analysis Just in time learning Multiple subspace Support vector data description

来源：评论

学校读者我要写书评

暂无评论

Total Plant Performance Evaluation based on Big Data:Visualization Analysis of TE Process

Total Plant Performance Evaluation based on Big Data:Visuali...

引用

第28届中国过程控制会议（CPCC 2017）暨纪念中国过程控制会议30周年

作者： Li Mengyao Du Wenli Qian Feng Zhong Weiming Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology

The performance evaluation of the process industry,which has been a popular topic nowadays,can not only find the weakness and verify the resilience and reliability of the process,but also provide some suggestions to improve the process benefits and ***,the performance assessment principally concentrate upon some parts of the entire system at present,for example the controller *** some researches focus on the whole process,they aim at discovering the relationships between profit,society,policies and so forth,instead of relations between overall performance and some manipulated variables,that is,the total plant *** this basis,this paper propose a hierarchical framework to select some structured logic rules from monitored variables to estimate the current state of the *** variables related to safety and profits are regarded as key factors to performance *** better monitor the process state and observe the performance variation trend of the process,a classification-visualization method based on kernel principal component analysis(KPCA) and self-organizing map(SOM) is *** monitoring method is applied to Tennessee Eastman *** results indicate that off-line and on-line performance status can be well detected in a two-dimensional diagram.

关键词： performance evaluation structured logic rules hierarchical framework multidimensional visualization KPCA-SOM

来源：评论

学校读者我要写书评

暂无评论

Early Stopping Criterion Combining Probability Density Function with Validation Error for Improving the Generalization Capability of the Backpropagation Neural Network

Early Stopping Criterion Combining Probability Density Funct...

引用

2017 2nd International Conference on Applied Mechanics and Mechatronics Engineering(AMME 2017)

作者： Wei WANG Xue-feng YAN The Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology

A new early stopping criterion that combines the probability density function error and the validation error was designed to evaluate a training process. In this new criterion, the real status of the backpropagation neural network(BPNN) was jointly evaluated by the validation error, the probability density error of the traditional training data, and the unlabeled data that was not considered in the traditional training process to determine the appropriate stopping time. The proposed approach was tested on three classes of automatic stopping criteria. In addition, it was compared with the stopping criteria based solely on the validation error and the probability density error with the use of four different data sets selected from the UCI Machine Learning *** showed that the new early stopping criterion is beneficial for enhancing the generalization capability of the BPNN, demonstrating an improved forecasting precision by 2%-3%.

关键词： Backpropagation neural network Early stopping criterion Generalization capability Probability density function

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Estimation-based control for Stochastic Time Delays in Networked Micorgrid 36

Sliding Mode Estimation-based Control for Stochastic Time De...

引用

第36届中国控制会议

作者： Xuping Zhou Huaicheng Yan Chen Peng Fuwen Yang Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology School of Mechatronic Engineering and Automation Shanghai University School of Engineering Griffith University

ISBN: (纸本)9781538629185

This paper proposes a sliding mode estimation-based control to solve the stochastic time delay problem in networked microgrid,because stochastic delay has a great impact on the stability and performance of large power grids（LPG）.To analyze the delay effects,the microgrid system model is derived according to the characteristics of the inverter in grid-connected *** on the microgrid system model,the stochastic delay estimation with learning parameter and delayed states are *** control signal designed by sliding mode control（SMC） and the learning parameter of delay estimation are adaptively changed in the sliding mode estimation-based control *** reaching law（ERL） is proposed to solve the chattering issues of *** 3.3 KW microgrid parameters are added into simulation to verify the effectiveness and performance of the proposed control strategy.

关键词： Networked Microgrid Sliding Mode control（SMC） Stochastic Delay Estimation

来源：评论

学校读者我要写书评

暂无评论

Design of fractional order control using predictive functional control structure 35

Design of fractional order control using predictive function...

引用

第35届中国控制会议

作者： ZOU Qin ZHANG Junfeng LU Renquan ZHANG Ridong Information and Control Institute Hangzhou Dianzi University Key Laboratory of Advanced Control and Optimization for Chemical Processes

ISBN: (纸本)9781509009107

In practical processes,lots of phenomena are unable to be accurately described by conventional integer order models,while fractional order models can describe the characteristics more *** this paper,a new fractional order predictive functional control(FPFC) method is presented for the fractional order *** Oustaloup approximation is employed to derive the approximate model of the original ***,the Griinwald-Letnikov definition and fractional operator are used to extend the integer order predictive functional control to the *** with traditional predictive functional control,simulation results reveal that the fractional order controller can achieve improved control performance.

关键词： Fractional order calculus Oustaloup approximation fractional order system predictive functional control

来源：评论

学校读者我要写书评

暂无评论

Study on co-cracking performance of different hydrocarbon mixture in a steam pyrolysis furnace

引用

Chinese Journal of chemical Engineering 2016年第9期24卷 1252-1262页

作者： Benfeng Yuan Jinlong Li Wenli Du Feng Qian Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology School of Information Science and Technology East China University of Science and Technology

Co-cracking is a process where the mixtures of different hydrocarbon feedstocks are cracked in a steam pyrolysis furnace, and widely adopted in chemical industries. In this work, the simulations of the co-cracking of ethane and propane, and LPG and naphtha mixtures have been conducted, and the software packages of COILSIM1 D and Sim CO are used to account for the cracking process in a tube reactor. The effects of the mixing ratio, coil outlet temperature, and pressure on cracking performance have been discussed in detail. The co-cracking of ethane and propane mixture leads to a lower profitability than the cracking of single ethane or single propane. For naphtha, cracking with LPG leads to a higher profitability than single cracking of naphtha, and more LPG can produce a higher profitability.

关键词： Co-cracking Mixing ratio Coil outlet temperature（COT） Coil outlet pressure（COP） Pyrolysis furnace

来源：评论

学校读者我要写书评

暂无评论

Differences in motor imagery activity between the paretic and non-paretic hands in stroke patients using an EEG BCI 11th

Differences in motor imagery activity between the paretic an...

引用

11th International Conference on Augmented Cognition, AC 2017, held as part of the 19th International Conference on Human-Computer Interaction, HCI 2017

作者： Qiu, Zhaoyang Chen, Shugeng Allison, Brendan Z. Jia, Jie Wang, Xingyu Jin, Jing Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai China Department of Neurology Huashan Hospital Fudan University Shanghai China Department of Cognitive Science University of California at San Diego La JollaCA United States

Stroke is the leading cause of serious and long-term disability worldwide. Stroke survivors may recover some motor function after rehabilitation therapy. Many studies have shown that motor imagery (MI) based brain-computer Interface (BCI) can improve upper limb stroke rehabilitation. However, as stroke patients have suffered neurological damage, the brain regions associated with motor function might be compromised, thus impairing BCI performance. In this paper, we tried to explore whether stroke patients’ imagination of hand movement differed between paretic versus non-paretic hands. Ten stroke patients (5 male, aged 21–69 years, mean 48.4 ± 15.4) participated in this study. They imagined moving either the left or the right hand according to cues. The common spatial patterns (CSP) approach was used to extract MI features, and a support vector machine (SVM) was used for classification. Results did not show that motor imagery accuracy for paretic hands was not substantially worse than with non-paretic hands. In tandem with other work assessing motor accuracy in healthy participants versus stroke patients, these results suggest that possible concerns about stroke patients’ use of BCI-based motor imagery systems may not present serious obstacles to wider research and implementation. © Springer International Publishing AG 2017.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Neural Component Analysis for Fault Detection

arXiv

引用

arXiv 2017年

作者： Zhao, Haitao Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education School of Information Science and Engineering East China University of Science and Technology

Principal component analysis (PCA) is largely adopted for chemical process monitoring and numerous PCA-based systems have been developed to solve various fault detection and diagnosis problems. Since PCA-based methods assume that the monitored process is linear, nonlinear PCA models, such as autoencoder models and kernel principal component analysis (KPCA), has been proposed and applied to nonlinear process monitoring. However, KPCA-based methods need to perform eigen-decomposition (ED) on the kernel Gram matrix whose dimensions depend on the number of training data. Moreover, prefixed kernel parameters cannot be most effective for different faults which may need different parameters to maximize their respective detection performances. Autoencoder models lack the consideration of orthogonal constraints which is crucial for PCA-based algorithms. To address these problems, this paper proposes a novel nonlinear method, called neural component analysis (NCA), which intends to train a feedforward neural work with orthogonal constraints such as those used in PCA. NCA can adaptively learn its parameters through backpropagation and the dimensionality of the nonlinear features has no relationship with the number of training samples. Extensive experimental results on the Tennessee Eastman (TE) benchmark process show the superiority of NCA in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of NCA can be found in https://***/haitaozhao/***. Note to Practitioner: Online monitoring for chemical process has been considered as a critical and hard task in real industrial applications. In this paper, an innovative method called neural component analysis (NCA) is proposed for fault detection. NCA is a unified model including a nonlinear encoder and a linear decoder. Due to its simple and intuitive format, NCA has superior performance in both computational efficiency and fault detection which makes it suitable for proces

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：