检索结果-内蒙古大学图书馆

1995 International Conference on Energy Management and Power Delivery (EMPD 95)

作者： Li, RM Chen, YP Guo, JB UMIST MANCHESTER M60 1QDLANCSENGLAND

ISBN: (纸本)0780329813

An artificial neural network (ANN) based optimization method in scheduling pumped-storage is proposed in the paper. Short-term scheduling as well as real-time dispatch of a pumped-storage station is a constrained optimization problem. It becomes more complicated when coordinated with other generation resources. The computation time is often long and the operation conditions may change unpredictably. A fast and practical way is expected. The ANN is used as a signal processing device, which represents mapping functions from input space to output space. Through a training process, multi-layered feedforward and neural networks can be used to approximate the continuous functions with a given accuracy and real-time solution can be achieved. In this paper three layer feedforward ANN and improved BP algorithm are adopted to solve the problem of pumped-storage scheduling. A set of ANN training data are obtained by running an optimization software. The paper describes how to select and organize the input data and how to train the ANN. A work example is presented and a comparison with traditional method is made. It shows that a fast and accurate solution for pumped-storage scheduling can be achieved with ANN.

关键词： pumped-storage power stations multilayer perceptrons scheduling load dispatching feedforward neural nets backpropagation optimisation power engineering computing pumped-storage station real-time dispatch artificial neural network ANN optimization method short-term scheduling signal processing device mapping functions input space output space multi-layered feedforward neural networks three layer feedforward ANN pumped-storage scheduling optimization software backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

A Neural - Sliding Mode Controller

引用

IFAC Proceedings Volumes 1995年第24期28卷 371-376页

作者： Rodica Mihaela Cistelecan Technical University of Cluj-Napoca Dept. of Automation 15 C Daicoviciu St. 3400 CLUJ-NAPOCA ROMANIA

The paper proposes an adaptive version for sliding mode control system, to reduce the chatter without losing the robustness. An extension of the conventional sliding mode control to a new concept, called the neural - sliding mode control, is presented. The control law parameters are adapted continuously, by an artificial neural network, to estimate the optimal sliding mode control function. The artificial neural network is trained by the backpropagation learning algorithm to extract the necessary control information from the plant. Conclusion is that the two control theories - neural control and sliding mode control - complete each other. The theoretical assertions are sustained by numerical simulation results.

关键词： nonlinear systems state space neural control sliding mode control neural networks backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Neural Nets as another Paradigm for Decision Support *

引用

IFAC Proceedings Volumes 1995年第7期28卷 117-125页

作者： Feng Shan Cai Jun Zhai Fan Huazhong University of Science and Technology Department of Automatic Control Engineering Institute of Systems Engineering Wuhan Hubei PRC 430074

The paper presents the second generation artificial neural nets ANN II applied as another paradigm for decision support. The underlying decision selection task is comprehensive evaluation of the social—economic development level of Chinese large cities, which previously supported by conventional knowledge-based approach KB-CEDSS. With the KB-CEDSS generated input-output pairs, the ANNs can be trained to emulate the whole systems function. Some foundamental technologies of ANN design and implementation are discussed and several points on ANN applications are concluded.

关键词： Group Multicriterion Decision Making GMDM Assessment and Evaluation Knowledge-based Systems Neural nets and configuration Decision Support System backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC RANKING OF FUZZY NUMBERS WITH THE CRITERION OF A DECISION-MAKER LEARNT BY AN ARTIFICIAL NEURAL-NETWORK

引用

FUZZY SETS AND SYSTEMS 1994年第1期64卷 1-19页

作者： REQUENA, I DELGADO, M VERDEGAY, JL Departamento de Ciencias de la Computacion e I.A. Facultad de Ciencias Universidad de Granada 18071-Granada Spain

In a previous work, we indicated that Artificial Neural Networks (ANN) would be able to learn to compare fuzzy numbers as a real decision maker does. In this paper, we describe in detail the experiment that we have developed to that goal, and in which we have obtained good results. We apply this trained ANN to some decision problems with fuzzy environment, by means of the automatic ranking of the decision problem utilities, performed as trapezoidal fuzzy numbers. So, we use the trained ANN as a personal method to compare fuzzy numbers. We have trained a multilayer feedforward ANN with the criterions (to compare fuzzy numbers) of three people, each with different characteristic, using the backpropagation algorithm and different structures. Then we use this trained ANN to rank a set of fuzzy numbers which can be considered as utilities of decision problems with fuzzy environment, hence enabling us to make the best choice. Several examples are shown also.

关键词： FUZZY NUMBERS COMPARISON backpropagation algorithm DECISION MAKING FUZZY ENVIRONMENT DECISIONS

来源：评论

学校读者我要写书评

暂无评论

THE EFFECT OF WEIGHT PRECISION AND RANGE ON NEURAL-NETWORK CLASSIFIER PERFORMANCE

引用

NEUROCOMPUTING 1994年第5-6期6卷 541-549页

作者： YOO, H PIMMEL, RL UNIV ALABAMA TUSCALOOSAAL 35401 UNIV MISSOURI COLUMBIAMO 65201

This study investigates the precision and range requirements for weights in feed-forward neural network classifiers using backpropagation training with simulated signals where we could control the difficulty of the problem. We found that a precision of five bits and a range equal to four times the mean weight magnitude produced the same performance as continuous weights. However, we noted that the required precision and range depended strongly on the problem difficulty, the network complexity, and the relationship between these two factors. We also found that uniformly distributed discrete weights produced better performance than non-uniformly distributed ones.

关键词： PATTERN CLASSIFICATION DISCRETE WEIGHTS FEEDFORWARD NETWORKS backpropagation algorithm COMPANDING WEIGHTS

来源：评论

学校读者我要写书评

暂无评论

NEURAL NETWORKS WITH INTERVAL WEIGHTS FOR NONLINEAR MAPPINGS OF INTERVAL VECTORS

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 1994年第4期E77D卷 409-417页

作者： KWON, K ISHIBUCHI, H TANAKA, H Univ of Osaka Prefecture Sakai-shi Japan

This paper proposes an approach for approximately realizing nonlinear mappings of interval vectors by interval neural networks. Interval neural networks in this paper are characterized by interval weights and interval biases. This means that the weights and biases are given by intervals instead of real numbers. First, an architecture of interval neural networks is proposed for dealing with interval input vectors. Interval neural networks with the proposed architecture map interval input vectors to interval output vectors by interval arithmetic. Some characteristic features of the nonlinear mappings realized by the interval neural networks are described. Next, a learning algorithm is derived. In the derived learning algorithm, training data are the pairs of interval input vectors and interval target vectors. Last, using a numerical example, the proposed approach is illustrated and compared with other approaches based on the standard back-propagation neural networks with real number weights.

关键词： INTERVAL ARITHMETIC NONLINEAR MAPPING OF INTERVAL VECTORS FEEDFORWARD NEURAL NETWORKS backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Design of layered‐neural nonlinear filters using backpropagation algorithm

引用

Electronics and Communications in Japan (Part III: Fundamental Electronic Science) 1992年第1期75卷 9-19页

作者： Arakawa, Kaoru Harashima, Hiroshi School of Science and Technology Meiji University Kawasaki 214 Japan Faculty of Engineering The University of Tokyo Tokyo 113 Japan

The signal such as an image signal is a non‐Gaussian signal with an abrupt change. When a random noise is superposed on such a signal, it is impossible to eliminate the noise effectively by using the traditional linear filter. Then it is desired to develop a nonlinear filter. From such a viewpoint, this paper proposes a nonlinear digital filter using a layered neural network, aiming at the elimination of such a noise. By thus introducing the nonlinearity and the learning ability of the layered neural network, the noise can effectively be eliminated. In this paper, the noise elimination is shown for the case of a one‐dimensional test signal and a two‐dimensional image signal indicating the usefulness. Copyright © 1992 Wiley Periodicals, Inc., A Wiley Company

关键词： backpropagation algorithm digital signal processing image restoration neural network Nonlinear digital filter signal estimation

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTATION WITH A backpropagation NEURAL NETWORK - AN APPLICATION TO PLANNING END USER SYSTEM-DEVELOPMENT

引用

INFORMATION & MANAGEMENT 1993年第1期24卷 1-8页

作者： LODEWYCK, RW DENG, PS CALIF STATE UNIV STANISLAUS TURLOCKCA

Neural networks utilize the paradigm of the human brain to acquire knowledge through a training process. The knowledge base is stored in the form of weighted interconnections between layer nodes;this allows the network to generalize. Computational experimentation with a back-propagation algorithm yielded useful information concerning the effect of several key model parameters on network training and performance. These findings are illustrated through the application of a modest sized three layer neural network to the planning of end user involvement in the development of information systems.

关键词： backpropagation algorithm NEURAL NETWORKS CONNECTIONIST MODELS UNSTRUCTURED DECISION MAKING END USER SYSTEM DEVELOPMENT INFORMATION SYSTEM PLANNING

来源：评论

学校读者我要写书评

暂无评论

NEW TRENDS IN STRUCTURE-BIODEGRADABILITY RELATIONSHIPS

引用

QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS 1993年第1期12卷 49-56页

作者： CAMBON, B DEVILLERS, J CTR TRAITEMENT INFORMAT SCI 21 RUE BANNIEREF-69003 LYONFRANCE

Problems related to structure-biodegradation models are discussed. They deal with the homogeneity of the data sets, the selection of an adequate statistical method, and the choice of the molecular descriptors. This short review shows that the Boolean backpropagation neural networks are promising tools to model biodegradation. To confirm this hypothesis, a heterogeneous learning set of 47 molecules and two testing sets of 23 and 17 chemicals weakly (0) or highly (1) biodegradable are described by means of 11 Boolean structural descriptors. A supervised neural network using the backpropagation algorithm generates 100% and 85% of good predictions for the learning and testing sets, *** results obtained are compared with those obtained from classical regression analysis. Advantages of this new approach are given. A particular application of correspondence factor analysis is presented to transform the Boolean variables before their introduction in the neural network. Advantages of this statistical transformation are stressed.

关键词： backpropagation algorithm BIODEGRADATION BOOLEAN DESCRIPTORS CORRESPONDENCE FACTOR ANALYSIS NEURAL NETWORKS STRUCTURE-BIODEGRADABILITY RELATIONSHIPS

来源：评论

学校读者我要写书评

暂无评论

COMPARISON OF CONVERGENCE BEHAVIOR AND GENERALIZATION ABILITY IN backpropagation LEARNING WITH LINEAR AND SIGMOID OUTPUT UNITS

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 1993年第6期E76A卷 1035-1042页

作者： KAMRUZZAMAN, J KUMAGAI, Y HIKITA, H Bangladesh Univ of Engineering and Technology Dhaka Bangladesh

The most commonly used activation function in backpropagation learning is sigmoidal while linear function is also sometimes used at the output layer with the view that choice between these activation functions does not make considerable differences in network's performance. In this letter, we show distinct performance between a network with linear output units and a similar network with sigmoid output units in terms of convergence behavior and generalization ability.(10) We experimented with two types of cost functions, namely, sum-squared error used in standard backpropagation and log-likelihood recently reported.(3),(4) We find that, with sum-squared error cost function and hidden units with nonsteep sigmoid function, use of linear units at the output layer instead of sigmoidal ones accelerates the convergence speed considerably while generalization ability is slightly degraded. Network with sigmoid output units trained by log-likelihood cost function yields even faster convergence and better generalization but does not converge at all with linear output units. It is also shown that a network with linear output units needs more hidden units for convergence.

关键词： backpropagation algorithm ACTIVATION FUNCTION LOG-LIKELIHOOD COST FUNCTION CONVERGENCE BEHAVIOR GENERALIZATION ABILITY

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：