检索结果-内蒙古大学图书馆

OUT-OF-STEP PREDICTION BASED ON ARTIFICIAL NEURAL NETWORKS

ELECTRIC POWER SYSTEMS RESEARCH 1995年第2期34卷 135-142页

作者： ABDELAZIZ, AY IRVING, MR ELARABATY, AM MANSOUR, MM Department of Electrical Power and Machines Ain Shams University Cairo Egypt Department of Electrical Engineering and Electronics Brunel University Uxbridge UB8 3PH UK

The application of artificial intelligence to power systems has resulted in an overall improvement of solutions in many generators based implementations. This paper presents a new approach to the prediction (detection) of out-of-step synchronous, on artificial neural networks (ANNs). The paper describes the ANN architecture adopted as well as the selection of input features for training the ANN. A feedforward model of the neural network based on the stochastic back-propagation training algorithm has been used. The capabilities of the developed algorithm for the prediction of the out-of-step condition have been tested through computer simulation for a typical case study. The results of using the proposed algorithm reveal a high classification performance.

关键词： SYNCHRONOUS GENERATOR STABILITY NEURAL NETWORKS backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

A COMPUTER-SIMULATION STUDY OF DIFFRACTION TOMOGRAPHY

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1983年第7期30卷 377-386页

作者： DEVANEY, AJ Schlumberger-Doll Research Center Ridgefield CT USA

The filtered backprojection algorithm of X-ray tomography and the filtered backpropagation algorithm developed recently by the author for diffraction tomography are tested in computer simulations of ultrasonic tomography of two-dimensional objects for which the Rytov approximation is valid. It is found that the filtered backprojection algorithm gives unsatisfactory results even for wavelengths much smaller than the smallest scale over which the object varies. The filtered back-propogation algorithm yields, in all cases studied, high-quality reconstructions which are simply low-pass filtered versions of the actual object profile. It is shown that the filtered backpropagation algorithm can be approximated by a modified backprojection algorithm having essentially the same computation requirements as filtered backprojection, but yielding considerably higher quality object reconstructions.

关键词： Computer simulation backpropagation algorithms X-ray diffraction Ultrasonic imaging X-ray tomography Low pass filters Image reconstruction Acoustic diffraction Reconstruction algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

IMPROVED NUCLEAR-REACTOR TEMPERATURE CONTROL USING DIAGONAL RECURRENT NEURAL NETWORKS

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1992年第6期39卷 2298-2308页

作者： KU, CC LEE, KY EDWARDS, RM PENN STATE UNIV DEPT NUCL ENGNUNIV PKPA 16802

A new approach for wide-range optimal reactor temperature control using diagonal recurrent neural networks (DRNN) with adaptive learning rate scheme is presented. The drawback of the usual feedforward neural network (FNN) is that it is a static mapping and requires a large number of neurons and takes a long training time. The usual fixed learning rate based on empirical trial and error scheme is slow and does not guarantee convergence. The DRNN is for dynamic mapping and requires much fewer number of neurons and weights, and thus converges faster than FNN. A dynamic backpropagation algorithm coupled with adaptive learning rate guarantees even faster convergence. The DRNN controller described here includes both a neurocontroller and a neuroidentifier. A reference model which incorporates an optimal control law with improved reactor temperature response is used for training of the neurocontroller and neuroidentifier. Rapid convergence of this DRNN-based control system is demonstrated when applied to improve reactor temperature performance.

关键词： diagonal recurrent neural network Reactors Temperature control backpropagation algorithms learning rate Neurocontrollers Nuclear reactors control law reference model

来源：评论

学校读者我要写书评

暂无评论

A CONSTRUCTIVE ALGORITHM FOR BINARY NEURAL NETWORKS - THE OIL-SPOT ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 794-797页

作者： MASCIOLI, FMF MARTINELLI, G INFO-COM Department University of Rome Rome Italy

This paper presents a constructive training algorithm for supervised neural networks. The algorithm relies on a topological approach, based on the representation of the mapping of interest onto the binary hypercube of the input space. It dynamically constructs a two-layer neural network by involving successively binary examples. A convenient treatment of real-valued data is possible by means of a suitable real-to-binary codification. In the case of target functions that have efficient halfspace union representations, simulations show that the constructed networks result optimized in terms of number of neurons.

关键词： Neural networks Hypercubes Neurons Computer architecture backpropagation algorithms Computational efficiency Graph theory Approximation algorithms NP-hard problem Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

USE OF A QUASI-NEWTON METHOD IN A FEEDFORWARD NEURAL-NETWORK CONSTRUCTION ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第1期6卷 273-277页

作者： SETIONO, R HUI, LCK Department of Information Systems and ComputerScience National University of Singapore Singapore

Interest in algorithms which dynamically construct neural networks has been growing in recent years. This paper describes an algorithm for constructing a single hidden layer feedforward neural network. A distinguishing feature of this algorithm is that it uses the quasi-Newton method to minimize the sequence of error functions associated with the growing network. Experimental results indicate that the algorithm if very efficient and robust. The algorithm was tested on two test problems. The first was the n-bit parity problem and the second was the breast cancer diagnosis problem from the University of Wisconsin Hospitals. For the n-bit parity problem, the algorithm was able to construct neural network having less than n hidden units that solved the problem for n = 4,...,7. For the cancer diagnosis problem, the neural networks constructed by the algorithm had small number of hidden units and high accuracy rates on both the training data and the testing data.

关键词： Intelligent networks Neural networks Feedforward neural networks Testing Heuristic algorithms Robustness Breast cancer Hospitals backpropagation algorithms Training data

来源：评论

学校读者我要写书评

暂无评论

Hierarchical fuzzy controllers

引用

Annual Reviews in Control 1997年 21卷 93-101页

作者： Horacek, Petr Binder, Zdenek Czech Technical University of Prague Faculty of Electrical Engineering Dept. of Control Engineering CZ-121 35 Prague 2 Karlovo nam.13 Czech Republic Inst. Natl. Polytech. de Grenoble ENSIEG Lab. d'Automatique de Grenoble 38402 Saint-Martin-d'Hères B.P.46 France

The paper presents Fuzzy Logic Controllers (FLC) with hierarchically structured rule base as nonlinear blocks used in a control system for direct control or supervision of standard controllers. Unified approach based on Fuzzy Logic Neural Networks (FLNN) is used to reveal the essential functions of a FLC. The FLNN is then extended to the case where decomposition of a rule base leads to simplification of controller design and tuning. Two structures of hierarchically organized groups of rules are discussed. Single-stage decision making structure with groups of rules organized hierarchically according to their specificity and a multi-stage decision making architecture with chained rules. Data induced error backpropagation technique for fine tuning of parameters of the second structure is derived.

关键词： backpropagation algorithms Fuzzy control Fuzzy inputs Hierarchical control Neural networks

来源：评论

学校读者我要写书评

暂无评论

An orthogonal neural network for function approximation

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1996年第5期26卷 779-785页

作者： Yang, SS Tseng, CS Department of Mechanical Engineering National Central University Chungli Taiwan

This paper presents a new single-layer neural network which is based on orthogonal functions. This neural network is developed to avoid the problems of traditional feedforward neural networks such as the determination of initial weights and the numbers of layers and processing elements, The desired output accuracy determines the required number of processing elements, Because weights are unique, the training of the neural network converges rapidly, An experiment in approximating typical continuous and discrete functions is given, The results show that the neural network has excellent performance in convergence time and approximation error.

关键词： Neural networks Function approximation Feedforward neural networks Convergence Multi-layer neural network Polynomials backpropagation algorithms Approximation error Control system synthesis Control systems

来源：评论

学校读者我要写书评

暂无评论

DATA-COMPRESSION OF THE ECG USING NEURAL NETWORK FOR DIGITAL HOLTER MONITOR

引用

IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE 1990年第3期9卷 53-57页

作者： IWATA, A NAGASAKA, Y SUZUMURA, N Department of Electrical and Computer Engineering Nagoya Institute of Technology Japan

A data-compression algorithm for digital Holter recording using artificial neural networks (ANNs) is described. A three-layer ANN that has a hidden layer with a few units is used to extract features of the ECG (electrocardiogram) waveform as a function of the activation levels of the hidden layer units. The number of output and input units is the same. The backpropagation algorithm is used for learning. The network is tuned with supervised signals that are the same as the input signals. One network (network 1) is used for data compression and another (network 2) is used for learning with current signals. Once the network is tuned, the common waveform features are encoded by the interconnecting weights of the network. The activation levels of the hidden units then express the respective features of the waveforms for each consecutive heartbeat.< >

关键词： Data compression Electrocardiography Neural networks Monitoring Artificial neural networks Heart beat Electrodes Thorax Digital signal processors backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE NEAREST NEIGHBOR PATTERN-CLASSIFICATION

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1991年第2期2卷 318-322页

作者： GEVA, S SITTE, J Faculty of Information Technology Queensland University of Technology Brisbane QLD Australia

We describe a variant of nearest neighbor pattern classification (NN) [1] and supervised learning by learning vector quantization (LVQ) [2], [3]. The decision surface mapping method, which we call DSM, is a fast supervised learning algorithm, and is a member of the LVQ family of algorithms. A relatively small number of prototypes are selected from a training set of correctly classified samples. The training set is then used to adapt these prototypes to map the decision surface separating the classes. This algorithm is compared with NN pattern classification, learning vector quantization (LVQ1) [2], and a two-layer perception trained by error backpropagation [4]. When the class boundaries are sharply defined (i.e., no classification error in the training set) the DSM algorithm outperforms these methods with respect to error rates, learning rates, and the number of prototypes required to describe class boundaries.

关键词： Nearest neighbor searches Pattern classification Prototypes Neural networks Books Computer networks Supervised learning backpropagation algorithms Vector quantization Error analysis

来源：评论

学校读者我要写书评

暂无评论

MULTILAYER FEEDFORWARD NEURAL NETWORKS WITH SINGLE POWERS-OF-2 WEIGHTS

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1993年第8期41卷 2724-2727页

作者： TANG, CZ KWAN, HK Department of Electrical Engineering University of Windsor Windsor ONT Canada

A new algorithm for designing multilayer feedforward neural networks with single powers-of-two weights is presented in this correspondence. By applying this algorithm, the digital hardware implementation of such networks becomes easier as a result of the elimination of multipliers. This proposed algorithm consists of two stages. First, the network is trained by using the standard backpropagation algorithm. Weights are then quantized to single powers-of-two values, and weights and slopes of activation functions are adjusted adaptively to reduce sum of squared output errors to a specified level. Simulation results indicate that the multilayer feedforward neural networks with single powers-of-two weights obtained using the proposed algorithm have similar generalization performance as the original networks with continuous weights.

关键词： Multi-layer neural network Neural networks Feedforward neural networks backpropagation algorithms Neurons Quantization Algorithm design and analysis Neural network hardware Artificial neural networks Computer networks

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：