检索结果-内蒙古大学图书馆

A HIERARCHICAL ARTIFICIAL NEURAL NETWORK FOR TRANSPORT ENERGY DEMAND FORECAST: IRAN CASE STUDY

NEURAL NETWORK WORLD 2010年第6期20卷 761-772页

作者： Kazemi, Aliyeh Shakouri G, Hamed Menhaj, M. Bagher Mehregan, M. Reza Neshat, Najmeh Univ Tehran Dept Ind Management Fac Management Tehran Iran Univ Tehran Dept Ind Engn Fac Engn Tehran Iran Amirkabir Univ Technol Dept Elect Engn Tehran Iran Sharif Univ Technol Dept Ind Engn Tehran Iran

This paper presents a neuro-based approach for annual transport energy demand forecasting by several socio-economic indicators. In order to analyze the influence of economic and social indicators on the transport energy demand, gross domestic product (GDP), population and total number of vehicles are selected. This approach is structured as a hierarchical artificial neural networks (ANNs) model based on the supervised multi-layer perceptron (MLP), trained with the back-propagation (bp) algorithm. This hierarchical ANNs model is designed properly. The input variables are transport energy demand in the last year, GDP, population and total number of vehicles. The output variable is the energy demand of the transportation sector in Million Barrels Oil Equivalent (MBOE). This paper proposes a hierarchical artificial neural network by which the inputs to the ending level are obtained as outputs of the starting levels. Actual data of Iran from 1968-2007 is used to train the hierarchical ANNs and to illustrate capability of the approach in this regard. Comparison of the model predictions with conventional regression model predictions shows its superiority. Furthermore, the transport energy demand of Iran for the period of 2008 to 2020 is estimated.

关键词： ANNs MLP bp algorithm forecasting transport energy demand

来源：评论

学校读者我要写书评

暂无评论

Research on a Vibrating Mill Control System Based on a Fuzzy Neural Network

引用

International Journal of Plant Engineering and Management 2010年第3期15卷 164-170页

作者： ZHANG Jin-hua YUAN Si-cong ZHANG Xiao-zhong LU Di College of Mechanical and Electronic Engineering Xi'an University of Architecture and Technology Xi'an Shaanxi 710055 P.R. China

Vibrating mills play an important role in the field of preparation of ultrafine powder. The purpose of a vibrating mill load control system is to increase productivity and ensure the mill runs smoothly. In this paper, we first summarized prior knowledge of control rules on the basis of analysis after repeated experiments, and realized fuzzy automation taking advantage of fuzzy theory. Since fuzzy control systems not only over rely on experience but also lack a self-learning function, we design a fuzzy neural network control system （FNNC） in order to improve the control system self-learning function and adaptive capacity while working conditions change. We adjust and optimize network *** using a back propagation（bp） algorithm. Simulation results show the control system dynamic performance is significantly improved, overshoot reduced from 23 % to 8 % and rise time shortened 0. 4 min.

关键词： vibration mill fuzzy control FNNC bp algorithm

来源：评论

学校读者我要写书评

暂无评论

A Particle Swarm Optimization algorithm for Storage Environments

A Particle Swarm Optimization Algorithm for Storage Environm...

引用

2010 International Conference on Circuit and Signal Processing (ICCSP 2010) & 2010 Second IITA International Joint Conference on Artificial Intelligence (IITA-JCAI 2010)

作者： Bao Zhan Biao Henan University of Economics and Law Zhengzhou,China Wu Jianjun Henan University of Technology,Zhengzhou,China

In order to guarantee safety,which need storage environment humidity,strictly control the temperature inside and outside *** PSO-bp neural network technology was applied to the control system of grain situation,the different positions of the granary of temperature and humidity,which provide data fusion processing parameters to improve the accuracy of measurement and ***,the bp neural network to initial data fusion of food,and then the PSO to the fusion results of *** new algorithm has coordinated contradictions between learning efficiency and convergence rate,and improved skilled speed and convergence *** the results of experiment,the new algorithm has some advantages,such as quickly,validity and practicability.

关键词： Particle Swarm Optimization bp algorithm expert system measurement and control for grain storage

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Fault Diagnoses System on the Basis of Fuzzy Neural Network

Research on Intelligent Fault Diagnoses System on the Basis ...

引用

2010 Second ETP/IITA World Congress in Applied Computing, Computer Science, and Computer Engineering(ACC 2010)

作者： Chen Xiaohong Software Institute Dalian Jiaotong University Dalian, Liaoning 116052 CHINA

Artificial neural networks can simulate human intelligent behavior in the absence of the mathematical model. Therefore, in the traditional studies it is often used for diagnosis of fault type. However, the traditional neural network's convergence was slow, and easy to fall into local minimum value. In this paper, we proposed an improved fuzzy neural network model;we added an anti-fuzzy layer in the traditional network model. The improved model customer overcame the shortcomings of traditional neural network. It had fast learning speed and good fault tolerance. Then, we also proved the validity and feasibility of the method with the example of the steam turbine vibration failures.

关键词： Fault diagnoses Neural network Fuzzy control bp algorithm Improved fuzzy neural network Mechanical fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

The Short-Term Traffic Flow Prediction Based on Neural Network

The Short-Term Traffic Flow Prediction Based on Neural Netwo...

引用

The 2010 2nd International Conference on Future Computer and Communication(第二届未来计算机与通信国际会议 ICFCC 2010)

作者： Yuanlin LIU Wusheng HU Li LI Shujie XIN Transportation College Southeast University Nanjing China The second institute of road and bridge design Jiangsu transportation research institute CO. LTD Na

ISBN: (纸本)9781424458219;9781424458240

As we all know, to predict the short-term traffic flow accurately and efficiently is the premise and key of traffic management and control. Based on these existing study, this paper selected bp neural network model in which the traffic flow difference was taken as the input parameter, applied the thought of dynamic rolling prediction to design a new short-term traffic flow prediction method, and wrote the corresponding program. Then using the actual observation data of traffic flow presented the model structure, thought and calculation steps of this new method. The results show this method is feasibility, reliability, and of some practical value.

关键词： Short-term Traffic Flow Neural Network bp algorithm Dynamic Rolling Prediction

来源：评论

学校读者我要写书评

暂无评论

An Accelerating Method of Training Neural Networks Based on Vector Epsilon algorithm

An Accelerating Method of Training Neural Networks Based on ...

引用

Third International Conference on Information and Computing(第三届信息与计算科学国际会议 ICIC 2010)

作者： Lian Lian Jianliang Li Yong Jiang School of Science Nanjing University of Science & Technology Nanjing 210094 P.R. China College of Math & Physics Nanjing University of Information Science & Technology Nanjing 210044P.R.

ISBN: (纸本)9781424470815;9780769540474

This paper studied the accelerating convergence of the vector sequences generated by bp algorithm with vector epsilon algorithm, and presented the conclusion that the algorithms is not only convergent but also accelerated. Finally, we tested them for three classical artificial neural network problems. By numerical experiments, results shown that can reduce CPU time for computation and improve the learning efficiency.

关键词： artificial neural networks bp algorithm epsilon algorithm accelerated convergence numerical analysis

来源：评论

学校读者我要写书评

暂无评论

GA Neural Network of The Cost of The Building Graphic of The Analysis and Understanding

GA Neural Network of The Cost of The Building Graphic of The...

引用

2010 International Conference on Computer,Mechatronics,Control and Electronic Engineering(2010计算机、机电、控制与电子工程国际会议 CMCE 2010)

作者： Kuancheng Zou Ye Qian Yafei Li Pengfei Zhang School of Computer Science and Engineering Changchun University of Technology Changchun China

ISBN: (纸本)9781424479573

The costs of pre-building graphic in the construction project management is a very important job, based on neural network theory and the characteristics of the costs of building graphic, raised GA neural network to solve the cost of building graphic problem, applied bp network model and used GA to optimize the weight based on bp algorithm. The calculation examples showed that the accuracy of the cost estimation met the requirements basically.

关键词： the cost of building graphic Neural network bp algorithm GA

来源：评论

学校读者我要写书评

暂无评论

A Low-Complexity Decoding algorithm for RA Code with Chebyshev Polynomial Fitting

A Low-Complexity Decoding Algorithm for RA Code with Chebysh...

引用

2010 3rd IEEE International Conference on Computer Science and Information Technology—ICCSIT 2010

作者： Lei Li, Qin Wang, Li Xu School of Information Engineering University of Science and Technology Beijing Beijing, China

RA (Repeat Accumulate) code has been widely used in wireless communication systems. But the bp (Belief Propagation) decoding algorithm which is commonly used in RA Code has high complexity. In order to reduce the complexity of bp algorithm while maintaining coding performance, we proposed Chebyshev-Polynomial-Fitting based bp (CPF-bp) decoding algorithm. In CPF-bp decoding algorithm, we used polynomial which is generated by chebyshev fitting algorithm instead of hyperbolic tangent operation in bp decoding algorithm to reduce the implementation complexity. Experiment and simulation results show that this low-complexity algorithm removes hyperbolic tangent operation in conventional bp algorithm with same amount of multiplier under the parameters setting in the paper. The performance degradation of CPF-bp algorithm is negligible which is less than 0.6dB at BER of 4 10 compared with conventional bp algorithm.

关键词： Repeat Accumulate Code Polynomial Fitting Chebyshev bp algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence in the Logistics Enterprise Performance Evaluation

Application of Artificial Intelligence in the Logistics Ente...

引用

2010 Second ETP/IITA World Congress in Applied Computing, Computer Science, and Computer Engineering(ACC 2010)

作者： CHENG-DONG SHI , DUN-XIN BIAN School of Electrical and Electronic Engineering, Shandong University of Technology Zibo,255091 CHINA

In order to evaluate the performance of the logistics enterprise scientifically, and by using of advantage of artificial intelligence (bp neural network) with self-organizing, self-learning, anti-interference, etc., a performance evaluation model of logistics enterprise was established. Then the step of the model was introduced in detail, bp neural network was constructed and bp algorithm was designed. Finally, an example was given for testing the effectiveness and feasibility of the model, the example shows that the evaluation results are basically consistent with the actual situation.

关键词： logistics enterprise performance evaluation bp neural network bp algorithm

来源：评论

学校读者我要写书评

暂无评论

GA Neural Network of The Cost of The Building Graphic of The Analysis and Understanding

GA Neural Network of The Cost of The Building Graphic of The...

引用

2010 International Conference on Computer,Mechatronics, Control and Electronic Engineering (CMCE 2010)

作者： Kuancheng Zou Ye Qian School of Computer Science and Engineering Changchun University of Technology Changchun,China Yafei Li Pengfei Zhang School of Computer Science and Engineering Changchun University of Technology Changchun,China

The costs of pre-building graphic in the construction project management is a very important job,based on neural network theory and the characteristics of the costs of building graphic,raised GA neural network to solve the cost of building graphic problem,applied bp network model and used GA to optimize the weight based on bp *** calculation examples showed that the accuracy of the cost estimation met the requirements basically.

关键词： the cost of building graphic Neural network bp algorithm GA

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：