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

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

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

Hybrid short path evaporation as an option to lactic acid recovery from fermentation broth

引用

chemical Engineering Transactions 2017年 57卷 37-42页

作者： Oliveira, Regiane A. Komesu, Andrea Rossell, Carlos E. Vaz Maciel, Maria R. Wolf Filho, Rubens Maciel Laboratory of Optimization Design and Advanced Process Control School of Chemical Engineering University of Campinas Brazil National Laboratory of Science and Technology of Bioethanol National Center for Research in Energy and Materials Brazil

ISBN: (纸本)9788895608488

Hybrid short path evaporation (HSPE) is proposed as an alternative separation process with potentiality for recovery and concentration of thermally unstable molecules such as lactic acid. This work aimed to analyze the influence of HSPE process variables on the concentration of lactic acid from sugarcane molasses. Through 22 factorial experimental design, the influence of evaporator temperature (from 115 to 135 °C) and internal condenser temperature (from 13 to 22 °C) on lactic acid concentration and mass percentage of residue and distillate stream were studied. The results showed that it is possible to increase the lactic acid concentration greater than twice from fermentation broth by HSPE. In addition, the effect of each variable studied and interactions between them were demonstrated. © Copyright 2017, AIDIC Servizi S.r.l.

关键词： Lactic acid

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

Detection and Diagnosis of Multiple Faults with Uncertain Modeling Parameters

Detection and Diagnosis of Multiple Faults with Uncertain Mo...

引用

作者： Zhao, Shunyi Huang, Biao Liu, Fei Department of Chemical and Materials Engineering University of Alberta EdmontonABT6G2G6 Canada Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi214122 China

In this brief, a fault-detection and diagnosis method is proposed for the stochastic hybrid system with the consideration of model parameter uncertainty. To negate the effect of model uncertainty, a compensation step is introduced, which uses a compensation parameter to adjust the degree of dependence of the filtering on the model or the measurements. To determine the compensator parameter governing the degree of dependence, an orthogonality principle between the estimation error and the residual is applied. Numerical simulations with a second-order tracking system and a pilot-scale experiment study on a quadruple water tank system are conducted to demonstrate the effectiveness of the proposed approach. © 2017 IEEE.

关键词： Water tanks

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

H∞ Fault Detection Filter Design for Networked Nonlinear Systems under Event-triggered Mechanism

H∞ Fault Detection Filter Design for Networked Nonlinear Sy...

引用

第36届中国控制会议

作者： Yuwei Zhao Huaicheng Yan Xisheng Zhan Congzhi Huang Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology College of Mechatronics and Control Engineering Hubei Normal University School of Control and Computer Engineering North China Electric Power University

The problem of H fault detection filtering for a class of discrete-time nonlinear system based on T-S fuzzy model is investigated in this *** the filtering network system,packet dropout and networked time-delay are considered *** event-triggered communication scheme is constructed to determine whether or not the current instant data should be *** detection filter is designed to guarantee the prescribed H performance for the filtering ***,a numerical example is given to illustrate the effectiveness of the proposed design method.

关键词： Fault detection filtering T-S fuzzy model event-triggered communication scheme

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Output Feedback H∞ control for Networked control Systems with Time-varying Sampling and Packet Losses

Event-triggered Output Feedback H∞ Control for Networked Co...

引用

第36届中国控制会议

作者： Chenyang Hu Huaicheng Yan Hao Zhang Shiming Chen Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology Department of Control Science and Engineering Tongji University School of Electrical and Electrical Engineering East China Jiaotong University

This paper is concerned with the event-triggered H control for the networked control systems with non-uniform sampling and packet losses via dynamic output feedback controller(DOFC).By proposing the event-triggered mechanism,in which the output of the system is sampled by a time-varying sampling period and only the necessary sampled data is transmitted through the communication network,and the network-induced delay and the packet losses are considered *** the proposed event-triggering mechanism,the closed-loop system is modelled as a time-delay *** on the model,some novel criteria in terms of linear matrix inequalities(LMIs) for co-designing both the desired DOFC and the event-triggered parameters are ***,a simulation example is employed to demonstrate the effectiveness of the proposed method.

关键词： Event-triggered H∞ control Networked control systems Time-varying sampling Packet losses

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：