检索结果-内蒙古大学图书馆

Neural Approaches to Observer-Based Diagnosis of Faults in Dynamic Systems

IFAC Proceedings Volumes 1997年第11期30卷 1129-1134页

作者： Teodor Marcu Letiti Mirea Michel Mensler “Gheorghe Asachi᾿ Technical University of Iasi Department of Automatic Control Str. Horia 7-9 RO-6600 Iasi 1 ROMANIA Centre de Recherche en Automatique de Nancy Université “Henri Poincaré᾿ Nancy 1 BP 239 F-54506 Vandoeuvre Cedex FRANCE

The problem of robust model-based diagnosis of process faults is addressed by means of artificial neural networks. They are investigated for both approaches to function approximation and pattern classification. Main emphasis is placed upon generalized dynamic neural nets used as predictors of nonlinear models for symptom generation. Application to a laboratory process is presented. A diagnosis subsystem is designed to detect incipient faults in the components of a Three-Tank System. It is implemented in real-time using the SIMULINK/MATLAB environment.

关键词： Fault diagnosis robustness neural networks dynamic models backpropagation algorithms system identification pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Adjustable neural network controller: application to a large segmented reflector

Adjustable neural network controller: application to a large...

引用

American Control Conference (ACC)

作者： J.-A. Luzardo A. Chassiakos H. Ryaciotaki-Boussalis California State University Long Beach Long Beach CA USA California State University Los Angeles Los Angeles CA USA

A neural network controller (NNC) whose parameters are adjusted online is presented to control a class of multivariable linear systems. The plant to be controlled is assumed to be square (p inputs, p outputs) and almost strictly positive real (ASPR). The NNC is applied to a linear model of a large segmented space reflector and simulation results are presented. The ASPR condition is a strong condition, in general, but for the specific application of interest, i.e. control of flexible structures, the ASPR condition can be satisfied by an appropriate combination of the output variables (positions and velocities). As compared to other adaptive NNC reported in the literature, the proposed NNC is simpler and more suitable for real time applications.

关键词： Neural networks Control systems Flexible structures Adaptive control Neurons backpropagation algorithms Stability Sections Linear systems Velocity control

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network for Ultrashort-Term Load Forecasting

引用

IFAC Proceedings Volumes 1997年第17期30卷 541-544页

作者： Wang Feng Yu ErKeng Dong Bo Liu Xiao Electric Power Research Institute Beijing 100085 China Central China Power System Dispatch and Communication Bureau Wuhan 430077 China

This paper presents a method for ultrashort-tenn load forecasting (USTLF) based on artificial neural network, which is training and forecasting on-line by selecting typical sample sets and thereby improves the quality of sample sets. Extensive studies have been performed about the effect of various factors such as learning rate, moméntum, etc. on the efficiency and accuracy of the backpropagation algorithm which are employed in the training of neural networks. The proposed method has been implemented in Central China Electric Power Network. It is found that the forecasting result is very accurate.

关键词： Power system Load forecasting Neural networks backpropagation algorithms On-line

来源：评论

学校读者我要写书评

暂无评论

ECG events detection and classification using wavelet and neural networks

ECG events detection and classification using wavelet and ne...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Ming-Yao Yang Wei-Chih Hu Liang-Yu Shyu Department of Biomedical Engineering Chung Yuan Christian University Chungli Taiwan

An integrated system for ECG diagnosis that combines the wavelet transform (WT) for feature extraction and artificial neural network (ANN) models for the classification is proposed. By using the dyadic wavelet transform, the limitations of other methods in detecting ECG features such as QRS complex, the onsets and offsets of P and T waves are overcame. The ECG baseline is approximated using discrete least squares approximation. On classification, two paradigms of learning, supervised and unsupervised, for training the ANN modes are investigated. The backpropagation algorithm and the Kohonen's self-organizing feature map algorithm were used for supervised and unsupervised learning, respectively. The system is evaluated using the MITBIH database. The result indicates that the accuracy of diagnosing cardiac disease is above 97.77%. ECG signals can be classified, even with noise and baseline drift.

关键词： Electrocardiography Event detection Artificial neural networks Least squares approximation backpropagation algorithms Wavelet transforms Feature extraction Discrete wavelet transforms Computer vision Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Superior training of artificial neural networks using weight-space partitioning

Superior training of artificial neural networks using weight...

引用

International Conference on Neural Networks

作者： H.V. Gupta Kuo-lin Hsu S. Sorooshian Department of Hydrology and Water Resources University of Arizona Tucson Tucson AZ USA

Linear least squares simplex (LLSSIM) is a new algorithm for batch training of three-layer feedforward artificial neural networks (ANN), based on a partitioning of the weight space. The input-hidden weights are trained using a "multi-start downhill simplex" global search algorithm, and the hidden-output weights are estimated using "conditional linear least squares". Monte-Carlo testing shows that LLSSIM provides globally superior weight estimates with significantly fewer function evaluations than the conventional backpropagation, adaptive backpropagation, and conjugate gradient strategies.

关键词： Artificial neural networks Partitioning algorithms Neurons Least squares methods Testing backpropagation algorithms Convergence Joining processes Transfer functions Logistics

来源：评论

学校读者我要写书评

暂无评论

An incremental parallel tangent learning algorithm for artificial neural networks

An incremental parallel tangent learning algorithm for artif...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： A.R. Nezami V.C. Bhavsar A.A. Ghorbani Faculty of Computer Science University of New Brunswick Fredericton NB Canada Faculty of Computer Engineering Iran University of Science and Technology Tehran Iran

Ghorbani and Bhavasar (1993) proposed a modified backpropagation training algorithm using a deflecting gradient method-parallel tangent (Partan) gradient method-to accelerate convergence. We have also proposed the incremental inter-neuron communication method. In the incremental communication method, instead of communicating the full magnitude of the output value of a node, only the (reduced precision) increment or decrement to its previous value is sent on a communication link. In this paper, Partan is modified to incorporate incremental communication. The effects of the limited precision incremental communication method on the convergence behaviour and performance of the Partan backpropagation algorithm are investigated with the sonar problem discussed in literature. It is found through simulation that the communication costs during the training process decrease by a factor of 1.6. The application of the incremental reduced precision Partan method to larger networks is expected to result into even higher savings in communication costs.

关键词： Artificial neural networks backpropagation algorithms Convergence Costs Gradient methods Sonar Optimization methods Acceleration Computer science Niobium

来源：评论

学校读者我要写书评

暂无评论

A note on the effective number of parameters in nonlinear learning systems

A note on the effective number of parameters in nonlinear le...

引用

International Conference on Neural Networks

作者： Jianchang Mao A.K. Jain IBM Almaden Research Center San Jose CA USA Department of Computer Science Michigan State University East Lansing MI USA

ISBN: (纸本)0780341228

Moody's notion of effective number of parameters in a nonlinear learning system has been used for studying the generalization ability of feedforward neural networks. It is more meaningful than the number of free parameters in a nonlinear learning system because the former explains explicitly how the generalization error is related to the expected training set error. In this paper, we extend Moody's model to include a more general noise model. We show that the addition of noise in both sampling points in test data and observations increases the deviation of the expected test set mean-squared-error (MSE) from the expected training set MSE, and also increases the effective number of parameters. Our extension makes less restrictive assumptions about the data generation process than in the original Moody's notion. Monte Carlo experiments have been conducted to verify our extension, and to demonstrate the role of the weight-decay regularization in improving the generalization ability of feedforward networks.

关键词： Learning systems Testing Virtual colonoscopy backpropagation algorithms Neural networks Supervised learning Computer errors Nonhomogeneous media Iterative algorithms Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Artificial neural classification of clustered microcalcifications on digitized mammograms

Artificial neural classification of clustered microcalcifica...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： S. Sehad S. Desarnaud A. Strauss Research Group in Biomedical Imaging University of Pierre and Marie Curie Paris France

Investigates the potential utility of artificial neural networks as a decision-making aid to radiologists in the analysis of mammograms. Multi-layer neural networks with a backpropagation algorithm were trained for differentiating malignant from benign microcalcification clusters on the basis of both the clinical parameter "age" and radiological features extracted from digitized mammographic images. Radiological features associated with clustered microcalcifications were extracted from digitized images using mathematical morphology and image analysis. These parameters were analyzed using statistical analysis. The most relevant shape parameters were then given as input to the artificial neural network. Successful experimental results obtained by a three-layer neural network indicate that such an approach may provide a potentially useful tool to radiologists in the clustered microcalcification classification task.

关键词： Artificial neural networks Decision making Multi-layer neural network backpropagation algorithms Cancer Feature extraction Morphology Image analysis Statistical analysis Shape

来源：评论

学校读者我要写书评

暂无评论

Neural cognitive maps (NCMs)

Neural cognitive maps (NCMs)

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： T. Obata M. Hagiwara Department of Electrical Engineering Faculty of Science and Technology Keio University Yokohama Japan

In this paper, we propose novel cognitive maps using neural networks named neural cognitive maps (NCMs). Owing to the usage of neural networks, the modeling and prediction abilities of the NCMs are greatly improved compared with those of the conventional fuzzy cognitive maps (FCMs). In order to treat time series inputs effectively, each network receives the latest and the past outputs from all of the networks and is trained by backpropagation algorithm. In addition, a novel pruning method is employed to eliminate useless nodes and weights in each neural network. The pruning has two important effects: one is to improve the performance of the neural network; the other is to give useful information for users to estimate causal relations from the pruned neural network. Computer simulation results indicate the validity and effectiveness of the proposed NCMs.

关键词： Neural networks Predictive models backpropagation algorithms Computer simulation Collision mitigation Fuzzy cognitive maps Automatic control Multi-layer neural network Information science Diseases

来源：评论

学校读者我要写书评

暂无评论

A fuzzy control based algorithm to train perceptrons

A fuzzy control based algorithm to train perceptrons

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： M. Delgado C.J. Mantas M.C. Pegalajar Universidad de Granada Granada AndalucÃa ES

In this paper a method to train perceptrons using a fuzzy controller is presented. When the first layer of a perceptron is trained, the fuzzy rules try for each connection of a neuron that the weight is similar to the input of the connection if the desired output of the neuron is high, otherwise the fuzzy rules try the one that the weight is different to the input of the connection. When the rest of the connections of a perceptron are trained, the fuzzy rules try, besides modifying the weights, to return the desired outputs for the neurons of the previous layer in the perceptron. The training of multilayer perceptrons with neurons whose activation function is not differentiable has been attained with this method.

关键词： Fuzzy control Neurons Multilayer perceptrons Computer science Artificial intelligence backpropagation algorithms

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：