检索结果-内蒙古大学图书馆

SLIDING MODE CONTROL OF AEROBIC BIOPROCESS USING RECURRENT NEURAL IDENTIFIER

IFAC Proceedings Volumes 2005年第1期38卷 121-126页

作者： Ieroham S. Baruch P. Luis-Alberto Hernandez R. Jesús-Roberto Valle Josefina Barrera-Cortes Dept. of Automatic Control Dept. of Biotechnology and Bioengineering Ave. IPN No 2508 A.P. 14-470 07360 Mexico D.F. MEXICO

The paper proposed a new adaptive control system containing a Recurrent Neural Network (RNN) identifier, a Sliding Mode (SM) controller, and an integral term. The SM control is derived defining the sliding surface with respect to the output tracking error. The state and parameter information to resolve the SM control is obtained from a RNN identifier, which permits the SM control to maintain the sliding regime when the plant parameters changed. The simulation results obtained with a continuous stirred tank reactor plant model confirmed the good quality of the control.

关键词： sliding mode control integral action discrete-time systems adaptive control neural network models backpropagation algorithms identification state estimation biotechnology aerobic continuous stirred tank reactor plant model

来源：评论

学校读者我要写书评

暂无评论

Continuous-time recurrent multilayer perceptrons for nonlinear system identification

Continuous-time recurrent multilayer perceptrons for nonline...

引用

IEEE Conference on Control Technology and Applications (CCTA)

作者： Wen Yu Xiaoou Li Departamento de Control Automatico CINVESTAV Mexicali Mexico Departamento de Ingeniería Eléctrica Sección de Computación CINVESTAV Mexicali Mexico

In this paper continuous-time recurrent multilayer perceptrons (RMLP) are proposed to identify nonlinear systems. Using the function approximation theorem for multilayer perceptrons(MLP), we conclude that RMLP can approximate any dynamic system in any degree of accuracy. By means of a Lyapunov-like analysis, a stable learning algorithm for RMLP is determined. The suggested learning algorithm is similar to the well-known backpropagation rule of the multilayer perceptrons but with an additional term which assure the stability of identification error

关键词： Multilayer perceptrons Nonlinear systems Function approximation Neural networks Nonhomogeneous media Stability Least squares approximation backpropagation algorithms Recurrent neural networks Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

IDENTIFICATION OF SENSOR FAULTS ON COMBINE HARVESTERS USING INTELLIGENT METHODS

引用

IFAC Proceedings Volumes 2005年第1期38卷 75-79页

作者： Geert Craessaerts Tom Coen Josse De Baerdemaeker Laboratory for Agro-Machinery and Processing KULeuven Kasteelpark Arenberg 30 B-3001 Leuven Belgium

Process monitoring and fault diagnosis is of considerable interest from an industrial perspective. In this paper, the general applicability of intelligent methods, like self-organizing maps (SOM) and multilayer feedforward networks with backpropagation, for the identification of sensor failure on combine harvesters will be illustrated. Both neural network types showed comparable results in order to classify normal and faulty sensor conditions.

关键词： fault identification self organizing system feedforward networks backpropagation algorithms agriculture

来源：评论

学校读者我要写书评

暂无评论

Comparison of inverse kinematics solutions using neural network for 6R robot manipulator with offset

Comparison of inverse kinematics solutions using neural netw...

引用

ICSC Congress on Computational Intelligence Methods and Applications, CIMA

作者： Z. Bingul H.M. Ertunc C. Oysu Mechatronics Engineering Kocaeli University Kocaeli Turkey

An artificial neural network (ANN) using backpropagation algorithm is applied to solve inverse kinematics problems of industrial robot manipulator. 6R robot manipulator with offset wrist was chosen as industrial robot manipulator because geometric feature of this robot does not allow solving inverse kinematics problems analytically. In other words, there is no closed form solution for this problem. In order to define orientation of robot end-effector, three different representations are used here: homogeneous transformation matrix, Euler angles and equivalent angle axis. These representations were compared to obtain inverse kinematics solutions for 6R robot manipulator with offset wrist. Simulation results show that prediction performance from the approximation accuracy point of view is satisfactory with low effective errors based on 10 degrees data resolution

关键词： Kinematics Neural networks Manipulators Service robots Artificial neural networks Wrist backpropagation algorithms Algorithm design and analysis Closed-form solution Predictive models

来源：评论

学校读者我要写书评

暂无评论

Comparison of Neural and Evolutionary Approaches to Peak Load Estimation in Distribution Systems

Comparison of Neural and Evolutionary Approaches to Peak Loa...

引用

Eurocon

作者： M. Gavrilas C.V. Sfintes O. Ivanov Gheorghe Asachi Technical University of Iasi Iasi Romania Eximprod S.A. Buzau Romania Gheorghe Asachi Technical University of Iasi Romania

In distribution systems the knowledge of load characteristics at system buses is one of the top requirements for developing a precise analysis and taking good decisions with respect to the optimal operation and planning of the system. This paper presents a comparative study of the peak load estimation in power systems using two approaches based on neural networks and genetic programming. The first approach used the resilient propagation algorithm applied to multi-layer perceptron neural networks, while the second one was based on genetic programming and symbolic regression. A series of case studies were performed to compare the two approaches and to discover the best solution for each method and to evaluate their performances

关键词： Genetic programming Neural networks System buses Power system planning State estimation backpropagation algorithms Multilayer perceptrons Multi-layer neural network Performance evaluation Power systems

来源：评论

学校读者我要写书评

暂无评论

Effective neural network pruning using cross-validation

Effective neural network pruning using cross-validation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： T.Q. Huynh R. Setiono School of Computing National University of Singapore Singapore

This paper addresses the problem of finding neural networks with optimal topology such that their generalization capability is maximized. Our approach is to combine the use of a penalty function during network training and a subset of the training samples for cross-validation. The penalty is added to the error function so that the weights of network connections that are not useful have small magnitude. Such network connections can be pruned if the resulting accuracy of the network does not change beyond a preset level. Training samples in the cross-validation set are used to indicate when network pruning is terminated. Our results on 32 publicly available data sets show that the proposed method outperforms existing neural network and decision tree methods for classification.

关键词： Neural networks backpropagation algorithms Computer networks Electronic mail Network topology Multi-layer neural network Feedforward neural networks Decision trees Classification tree analysis Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Design optimization by functional neural networks

Design optimization by functional neural networks

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Xiyu Liu Huichuan Duan Mingxi Tang School of Information and Management Shandong Normal University Jinan Shandong P.R. China School of Design the Hong Kong Polytechnic University Hong Kong HKSAR Hong Kong China

ISBN: (纸本)184000025

This paper presents a new design optimization technique by artificial neural networks. Based on the theory of partial ordering and cones in Banach spaces, a new kind of neural networks with functional links is proposed. Learning algorithm lies heavily on the ordering structure of the sample space with an alternative feed-forward and backpropagation technique. Experiments are described with comparison with traditional functional link networks and wavelet networks.

关键词： Design optimization Neural networks Biological neural networks Humans backpropagation algorithms Machinery Artificial neural networks Design engineering Robustness Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Host anomaly detection performance analysis based on system call of neuro-fuzzy using Soundex algorithm and N-gram technique

Host anomaly detection performance analysis based on system ...

引用

Proceedings of the Systems Communications, SENET

作者： ByungRae Cha Department of Computer Engineering Honam University South Korea

To improve the anomaly intrusion detection system using system calls, this study focuses on neuro-fuzzy learning using the Soundex algorithm which is designed to change feature selection and variable length data into a fixed length learning pattern. That is, by changing variable length sequential system call data into a fixed length behavior pattern using the Soundex algorithm, this study conducted backpropagation neural networks with fuzzy membership function. The neuro-fuzzy and N-gram techniques are applied for anomaly intrusion detection of system calls using sendmail data of UNM to demonstrate its performance.

关键词： Performance analysis Intrusion detection Change detection algorithms Frequency backpropagation algorithms Neural networks Machine learning Data mining Automata Acoustical engineering

来源：评论

学校读者我要写书评

暂无评论

DWT-based phonetic groups classification using neural networks

DWT-based phonetic groups classification using neural networ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： T.V. Pham G. Kubin Signal Process. & Speech Commun. Lab. Technische Univ. Graz Austria Signal Processing and Speech Communication Laboratory University of Technology Graz Austria

This paper presents an improvement of the discrete wavelet transform (DWT)-based phonetic classification algorithm by using neural networks (NN) to learn optimal thresholds for speech classification. Two feedforward NNs (two layers) operate on input features extracted from speech frames (10 ms length) by DWT and statistical measurement in order to classify these frames as transient, voiced vowel, voiced consonant and unvoiced consonant categories. Hard thresholds in our earlier paper are used to detect silence and voiced closure intervals. The new algorithm is tested with the TIMIT database and compared with other algorithms to demonstrate its superior performance.

关键词： Discrete wavelet transforms Neural networks Signal processing algorithms Speech processing Multiresolution analysis Speech coding backpropagation algorithms Signal processing Oral communication Laboratories

来源：评论

学校读者我要写书评

暂无评论

A memetic accuracy-based neural learning classifier system

A memetic accuracy-based neural learning classifier system

引用

Congress on Evolutionary Computation

作者： T. O'Hara L. Bull School of Computer Science University of West of England Bristol UK

Learning classifier systems (LCS) traditionally use a binary string rule representation with wildcards added to allow for generalizations over the problem encoding. We have presented a neural network-based representation to aid their use in complex problem domains. Here each rule's condition and action are represented by a small neural network, evolved through the actions of the genetic algorithm. In this paper, we present results from the use of backpropagation to provide local search in conjunction with the global search of the genetic algorithm within XCS creating a memetic neural LCS. Significant decreases in the time taken to reach optimal behaviour are obtained from the incorporation of this local learning algorithm.

关键词： Neural networks Genetic algorithms backpropagation algorithms Computer science Multi-layer neural network Neurons Evolutionary computation Encoding Fuzzy logic Multilayer perceptrons

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：