检索结果-内蒙古大学图书馆

American control Conference (ACC)

作者： Zhihua Xiong Jie Zhang Centre for Process Analytics and Control Technology Department of Chemical and Process Engineering University of Newcastle UK

ISBN: (纸本)0780372980

Many fed-batch processes can be considered as a class of control-affine nonlinear systems. In this paper, a new methodology of neural networks, called the control Affine Feedforward Neural Network (CAFNN), is proposed. It can be trained easily. For constrained nonlinear optimization problems, it offers an effective and simple optimal control strategy by sequential quadratic programming in which the analytic gradient information can be computed directly. The proposed modeling and optimal control schemes are illustrated on an ethanol fermentation process. Compared with a general multilayer neural network, the nonlinear programming problem based on a CAFNN model is solved more accurately and efficiently.

关键词： Optimal control process control Neural networks Feedforward neural networks Multi-layer neural network Nonlinear control systems control systems Nonlinear systems Constraint optimization Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Sequential training of bootstrap aggregated neural networks for nonlinear systems modelling

Sequential training of bootstrap aggregated neural networks ...

引用

American control Conference (ACC)

作者： Jie Zhang Centre for Process Analytics and Control Technology Department of Chemical & Process Engineering University of Newcastle Newcastle-upon-Tyne UK

ISBN: (纸本)0780372980

A sequential training method for developing bootstrap aggregated neural network models is proposed in this paper. In this method, individual networks within a bootstrap aggregated neural network model are trained sequentially. The first network is trained to minimise its prediction error on the training data. In the training of subsequent networks, the training objective is not only to minimise the individual networks' prediction errors but also to minimise the correlation among the individual networks. Training data sets for the individual networks are different and are generated through bootstrap re-sampling of the original training data set. Training is terminated when the aggregated network prediction performance cannot be further improved. An application example demonstrates the superior performance of this neural network training strategy.

关键词： Neural networks Nonlinear systems Training data chemical analysis chemical technology Jacobian matrices control system analysis process control chemical processes chemical engineering

来源：评论

学校读者我要写书评

暂无评论

A training method for enhancing neural network model generalisation

A training method for enhancing neural network model general...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： J. Zhang Centre for Process Analytics and Control Technology Department of Chemical & Process Engineering University of Newcastle Newcastle-upon-Tyne UK

A training method for enhancing neural network model generalisation is proposed. In this method, a neural network is trained and tested alternatively on a training data set and a testing data set. Unlike in conventional neural network training where the training and testing data sets are fixed, the training and testing data sets swap roles continuously during network training. Training is terminated when the network prediction errors on both data sets cannot be further reduced. Application examples demonstrate that this neural network training strategy can significantly improve the neural tu network model prediction accuracy, especially the long range prediction accuracy.

关键词： Neural networks Testing Training data chemical analysis process control chemical technology Accuracy Partitioning algorithms chemical processes chemical engineering

来源：评论

学校读者我要写书评

暂无评论

Improved on-line process fault diagnosis using stacked neural networks

Improved on-line process fault diagnosis using stacked neura...

引用

IEEE Conference on control technology and Applications (CCTA)

作者： Jie Zhang Department of Chemical & Process Engineering Centre for Process Analytics and Control Technology University of Newcastle Newcastle-upon-Tyne UK

Since it is generally difficult, if not impossible, to develop a perfect neural network, a single neural network can lack reliability. Therefore a single neural network based fault diagnosis system may not give reliable fault diagnosis. Neural network model reliability or robustness can be improved by combining several non-perfect neural networks. Each individual network is trained on a bootstrap re-sample of the original training data. The outputs from the individual networks are averaged to give the final diagnosis results. Applications of the proposed method to a continuous stirred tank reactor demonstrate that a stacked neural network can give more reliable diagnosis than a single neural network.

关键词： Fault diagnosis Neural networks Fault detection Data analysis chemical technology Training data Parameter estimation State estimation Predictive models Data mining

来源：评论

学校读者我要写书评

暂无评论

Improving long range prediction for nonlinear process modelling through combining multiple neural networks

Improving long range prediction for nonlinear process modell...

引用

IEEE Conference on control technology and Applications (CCTA)

作者： Z. Ahmad Jie Zhang Department of Chemical and Process Engineering Centre for Process Analytics and Control Technology University of Newcastle Newcastle-upon-Tyne UK

Different methods for combining multiple neural networks in order to improve model long range prediction performance are compared in this paper. It is shown that combining multiple non-perfect neural networks can improve model predictions, especially long range predictions. Among the different approaches, the principal component regression based approaches generally give very good performance. Selective combination is also very beneficial to the improvement of model predictions.

关键词： Predictive models Neural networks Artificial neural networks Robustness Training data chemical analysis chemical technology process control Fitting Performance analysis

来源：评论

学校读者我要写书评

暂无评论

NEURAL NETWORK BASED ON-LINE RE-OPTIMISATION OF FED-BATCH processES USING ITERATIVE DYNAMIC PROGRAMMING FOR DISCRETE-TIME SYSTEMS

引用

IFAC Proceedings Volumes 2002年第1期35卷 289-294页

作者： Zhihua Xiong Jie Zhang Centre for Process Analytics and Control Technology Department of Chemical and Process Engineering University of Newcastle Newcastle upon Tyne NE1 7RU U. K.

Optimisation of fed-batch processes can be described as a constrained nonlinear end-point dynamic optimisation problem. Although iterative dynamic programming (IDP) is feasible, it is usually very time-consuming and very difficult to apply to on-line optimisation because of solving the non-linear differential-algebraic equations of the process model in each iteration. The replacement of a rigorous mechanistic model by an equivalent neural network (NN) model takes the advantage of high speed processing, since simulation with a NN model involves only a few non-iterative algebraic calculations. To use IDP algorithm for NN model based on-line re-optimisation, a modified algorithm is proposed and is called as iterative dynamic programming for discrete-time system ( IDP/DTS ). The novel IDP/DTS algorithm can obtain a reduction of many times in computational time compared to the conventional IDP algorithm. In this paper, an effective optimisation and control scheme for on-line re-optimisation of fed-batch processes is proposed based on NN models and the novel IDP/DTS algorithm. The proposed scheme is illustrated using simulation studies of an ethanol fermentation process.

关键词： neural networks on-line re-optimisation IDP IDP/DTS algorithm fed-batch processes

来源：评论

学校读者我要写书评

暂无评论

The interactions of design, control and operability in reactive distillation systems

The interactions of design, control and operability in react...

引用

作者： Georgiadis, Michael C Schenk, Myrian Pistikopoulos, Efstratios N Gani, Rafiqul Centre for Research and Technology-Hellas Chemical Process Engineering Research Institute P.O. Box 361 Thermi-Thessaloniki 57001 Greece Department of Chemical Engineering Centre for Process Systems Engineering Imperial College London SW7 2BY United Kingdom Department of Chemical Engineering CAPEC Technical University of Denmark DK-2800 Lyngby Denmark

In this work the design and control of a reactive distillation column, described by a rigorous dynamic model, is tackled via two different optimization approaches. In the first, the steady-state process design and the control system are optimized sequentially. It is shown that operability is a strong function of the process design and potential operability bottlenecks are identified. In the second approach, the process design and the control system are optimized simultaneously leading to a more economically beneficial and better controlled system than that obtained using the sequential approach. © 2002 Elsevier Science Ltd. All rights reserved.

关键词： Distillation columns

来源：评论

学校读者我要写书评

暂无评论

A comparison of different methods for combining multiple neural networks models

A comparison of different methods for combining multiple neu...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Z. Ahmad J. Zhang Centre for Process Analaytics and Contorl Technology Department of Chemical & Process Engineering University of Newcastle Newcastle-upon-Tyne UK

A single neural network model developed from a limited amount of data usually lacks robustness. Neural network model robustness can be enhanced by combining multiple neural networks. There are several approaches for combining neural networks. A comparison of these methods on three nonlinear dynamic system modelling case studies is carried out in this paper. It is shown that selective combination and combining networks of various structures generally improve model performance. The principal component regression approaches generally give quite consistent good performance.

关键词： Neural networks Robustness Training data chemical analysis process control chemical technology Robust control Artificial neural networks chemical processes chemical engineering

来源：评论

学校读者我要写书评

暂无评论

Closed loop identification based on quantization 15th

Closed loop identification based on quantization

引用

15th World Congress of the International Federation of Automatic control, 2002

作者： Wang, M. Thornhill, N.F. Huang, B. Centre for Process Systems Engineering Imperial College of Science and Technology Prince Consort Road LondonSW7 2BY United Kingdom Centre for Process Systems Engineering Department of Electronic and Electronic Engineering University College London Torrington Place LondonWC1E 7JE United Kingdom Department of Chemical and Materials Engineering University of Alberta EdmontonABT6G 2G6 Canada

ISBN: (纸本)9783902661746

This paper proposes a new closed-loop identification scheme for a single-input-single-output control loop. It is based upon a quantizer inserted into the feedback path. The quantizer can be used to generate an equivalent persistently exciting signal with which the well known two-stage and/or two-step method can be used directly. Simulation examples and an experimental demonstration are used to illustrate the proposed scheme. Copyright © 2002 IFAC.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

CLOSED LOOP IDENTIFICATION BASED ON QUANTIZATION

引用

IFAC Proceedings Volumes 2002年第1期35卷 319-324页

作者： M. Wang N.F. Thornhill B. Huang Centre for Process Systems Engineering Imperial College of Science and Technology Prince Consort Road London SW7 2BY Centre for Process Systems Engineering Department of Electronic and Electronic Engineering Torrington Place University College London London WC1E 7JE (corresponding author) Department of Chemical and Materials Engineering University of Alberta Edmonton Alberta Canada T6G 2G6

关键词： chemical industry closed-loop identification process control quantization time-series 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：