检索结果-内蒙古大学图书馆

21st International Conference on Soft Computing (MENDEL)

作者： Popa, Calin-Adrian Polytech Univ Timisoara Dept Comp & Software Engn Timisoara 300223 Romania

ISBN: (纸本)9783319198248;9783319198231

In this paper, we present the full deduction of the scaled conjugate gradient method for training complex-valued feedforward neural networks. Because this algorithm had better training results for the real-valued case, an extension to the complex-valued case is a natural way to enhance the performance of the complex backpropagation algorithm. The proposed method is exemplified on well-known synthetic and real-world applications, and experimental results show an improvement over the complex gradient descent algorithm.

关键词： Complex-valued neural networks scaled conjugate gradient algorithm Time series prediction

来源：评论

学校读者我要写书评

暂无评论

Air mass flow estimation of diesel engines using neural network

引用

FUEL 2014年第parta期117卷 833-838页

作者： Uzun, Abdullah Sakarya Univ Sakarya Vocat Sch TR-54187 Sakarya Turkey

Air mass management is one of major factors affecting the performance of diesel engines, where experimental studies play a significant role in the performance studies. However, the experimental studies are quite expensive and time consuming. Neural network's (NN) have been used increasingly in a variety of engineering researches. NN based model are generally developed from experimental data. The objective of the study is to investigate the adequacy of neural networks (NN) as a quicker, more secure and more robust method to determine the effects of intercooling process on performance charged diesel engine's air intake mass flow. In this study, a NN model has been developed configured tested for this purpose. The training and test data is obtained from real experimental work delivered earlier. Further details of development of NN are also demonstrated. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Neural networks Intercooling Air mass flow scaled conjugate gradient algorithm Diesel engine

来源：评论

学校读者我要写书评

暂无评论

GPS GDOP classification via improved neural network trainings and principal component analysis

引用

INTERNATIONAL JOURNAL OF ELECTRONICS 2014年第9期101卷 1300-1313页

作者： Azami, Hamed Sanei, Saeid Iran Univ Sci & Technol Dept Elect Engn Tehran *** Iran Univ Surrey Fac Engn & Phys Sci Guildford GU2 5XH Surrey England

Geometric dilution of precision (GDOP) is an engineering expression that denotes how well the constellation of global positioning system (GPS) satellites is organised geometrically. In the analysis of received signals, it is often essential to invert and transform the data matrices. This requires tremendous computational burden on the navigator's processor. Since classification of GPS GDOP is a non-linear problem, neural networks (NNs) can be used as an acceptable solution. Since the back propagation (BP) does not have sufficient speed to train a feed-forward NN, in this paper several improved NN trainings, including Levenberg-Marquardt (LM), modified LM, and resilient BP (RBP), scaled conjugate gradient, one-step secant (OSS) and quasi-Newton methods are proposed to classify the GPS GDOP. In this study, in order to have uncorrelated and informative features of the GPS GDOP, principal component analysis (PCA) is used as a pre-processing step. The simulation results show that using the RBP and PCA leads to greater accuracy and lower calculation time comparing with other existing and proposed methods and it can improve the classification accuracy of GPS satellites to about 99.65%. Moreover, the modified LM is the fastest algorithm that requires only 10 iterations for training the NN and it can be used in online applications.

关键词： GPS GDOP classification neural network resilient back propagation scaled conjugate gradient algorithm Levenberg-Marquardt (LM) algorithm modified LM algorithm one-step secant method quasi-Newton method

来源：评论

学校读者我要写书评

暂无评论

A note on the global convergence theorem of the scaled conjugate gradient algorithms proposed by Andrei

引用

COMPUTATIONAL OPTIMIZATION AND APPLICATIONS 2012年第2期52卷 409-414页

作者： Babaie-Kafaki, Saman Semnan Univ Dept Math Fac Math Stat & Comp Sci Semnan Iran

In (Andrei, Comput. Optim. Appl. 38:402-416, 2007), the efficient scaled conjugate gradient algorithm SCALCG is proposed for solving unconstrained optimization problems. However, due to a wrong inequality used in (Andrei, Comput. Optim. Appl. 38:402-416, 2007) to show the sufficient descent property for the search directions of SCALCG, the proof of Theorem 2, the global convergence theorem of SCALCG, is incorrect. Here, in order to complete the proof of Theorem 2 in (Andrei, Comput. Optim. Appl. 38:402-416, 2007), we show that the search directions of SCALCG satisfy the sufficient descent condition. It is remarkable that the convergence analyses in (Andrei, Optim. Methods Softw. 22:561-571, 2007;Eur. J. Oper. Res. 204:410-420, 2010) should be revised similarly.

关键词： scaled conjugate gradient algorithm Sufficient descent condition Line search Global convergence

来源：评论

学校读者我要写书评

暂无评论

Neural network based model for seismic assessment of existing RC buildings

引用

COMPUTERS AND CONCRETE 2013年第2期12卷 229-241页

作者： Caglar, Naci Garip, Zehra Sule Sakarya Univ Dept Civil Engn Sakarya Turkey Karabuk Univ Dept Civil Engn Karabuk Turkey

The objective of this study is to reveal the sufficiency of neural networks (NN) as a securer, quicker, more robust and reliable method to be used in seismic assessment of existing reinforced concrete buildings. The NN based approach is applied as an alternative method to determine the seismic performance of each existing RC buildings, in terms of damage level. In the application of the NN, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm is employed using a scaled conjugate gradient. NN based model wasd eveloped, trained and tested through a based MATLAB program. The database of this model was developed by using a statistical procedure called P25 method. The NN based model was also proved by verification set constituting of real existing RC buildings exposed to 2003 Bingol earthquake. It is demonstrated that the NN based approach is highly successful and can be used as an alternative method to determine the seismic performance of each existing RC buildings.

关键词： neural networks scaled conjugate gradient algorithm rapid assessment P25 method existing RC buildings

来源：评论

学校读者我要写书评

暂无评论

CRACK LOCALIZATION IN HYDRAULIC TURBINE BLADES BASED ON KERNEL INDEPENDENT COMPONENT ANALYSIS AND WAVELET NEURAL NETWORK

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2013年第6期6卷 1116-1124页

作者： Wang, Xianghong Mao, Hanling Hu, Hongwei Zhang, Zhiyong Changsha Univ Sci & Technol Coll Automobile & Mech Engn Changsha 410004 Hunan Peoples R China Guangxi Univ Coll Mech Engn Nanjing 530003 Guangxi Peoples R China

Hydraulic turbine runner has a complex structure, and traditional location methods can't meet its requirement. This paper describes a source location of cracks in turbine blades by combining kernel independent component analysis (KICA) with wavelet neural network (WNN). The research shows that the location accuracy of WNN combined with KICA feature extraction is the best comparing with the results of WNN and back propagation neural network (BPNN). The method decreases the dimension of input parameters and improves the accuracy of location as well.

关键词： Crack localization acoustic emission (AE) kernel independent component analysis (KICA) scaled conjugate gradient algorithm wavelet neural network (WNN)

来源：评论

学校读者我要写书评

暂无评论

A parametric study for specific fuel consumption of an intercooled diesel engine using a neural network

引用

FUEL 2012年第1期93卷 189-199页

作者： Uzun, Abdullah Sakarya Univ Sakarya Vocat Sch TR-54187 Sakarya Turkey

Turbocharging is a process wherein the amount of oxygen used in a combustion reaction is increased to raise output and decrease specific fuel consumption. On account of this, fuel economy and thermal efficiency are more important for all engines. The use of an intercooler reduces the temperature of intake air to the engine, and this cooler and denser air increases thermal and volumetric efficiency. Most research projects on engineering problems usually take the form of experimental studies. However, experimental research is relatively expensive and time consuming. In recent years, Neural Networks (NNs) have increasingly been used in a diverse range of engineering applications. In this study, various parametric studies are executed to investigate the interrelationship between a single variable and two steadies and two constant parameters on the brake specific fuel consumption (BSFC, g/kW h). The variables selected are engine speed, load and Crankshaft Angel (CA). The data used in the present study were obtained from previous experimental research by the author. These data were used to enhance, train and test a NN model using a MATLAB-based program. The results of the NN based model were found to be convincing and were consistent with the experimental results. The trained NN based model was then used to perform the parametric studies. The performance of the NN based model and the results of parametric studies are presented in graphical form and evaluated. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Neural networks Intercooling Specific fuel consumption scaled conjugate gradient algorithm Diesel engine

来源：评论

学校读者我要写书评

暂无评论

Neural network based approach for determining the shear strength of circular reinforced concrete columns

引用

CONSTRUCTION AND BUILDING MATERIALS 2009年第10期23卷 3225-3232页

作者： Caglar, Naci Sakarya Univ Dept Civil Engn TR-54187 Sakarya Turkey

The objective of this study is to investigate the adequacy of neural networks (NN) as a quicker, more secure and more robust method to determine the shear strength of circular reinforced concrete columns. In the application of the NN model, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm is employed using a scaled conjugate gradient. NN model is developed, trained and tested through a based MATLAB program. The data used for training and testing NN model are gathered from literature. NN based model outputs are compared with ACI, ATC-32, ASCE and CALTRANS codes outcomes on the basis of the experimental results. This comparison demonstrated that the NN based model is highly successful to determine the shear strength of circular reinforced concrete columns. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Circular RC column Shear strength Neural networks scaled conjugate gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings

引用

CONSTRUCTION AND BUILDING MATERIALS 2008年第5期22卷 788-800页

作者： Caglar, Naci Elmas, Muzaffer Yaman, Zeynep Dere Saribiyik, Mehmet Sakarya Univ Dept Civil Engn TR-54187 Sakarya Turkey Sakarya Univ Technol Educ Fac TR-54187 Sakarya Turkey

The objective of this study is to investigate the adequacy of Artificial Neural Networks (ANN) as a securer, quicker and more robust method to determine the dynamic response of buildings in 3D. For this purpose, two ANN models were proposed to estimate the fundamental periods, base shear force, base bending moments and top-floor displacement of buildings in two directions. Total moment of inertia for each storey was defined in order to avoid limitation to describe the structure due to the number of columns, shear-walls and number of bays. The same input layer was submitted to different types of ANN models for various outcomes. In the ANN models, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm was employed using a scaled conjugate gradient. ANN models were developed, trained and tested in a based MATLAB program. A training set of 150 and a validation set of 15 buildings were produced from dynamic response of different buildings. Finite Element Analysis (FEA) was used to generate training and testing set of ANN models. It was demonstrated that the neural network based approach is highly successful to determine response of buildings subjected to earthquake. (C) 2007 Elsevier Ltd. All rights reserved.

关键词： dynamic analysis response of buildings neural networks scaled conjugate gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks

引用

CONSTRUCTION AND BUILDING MATERIALS 2007年第2期21卷 384-394页

作者： Pala, Murat Ozbay, Erdogan Oztas, Ahmet Yuce, M. Ishak Univ Gaziantep Tech Programs Dept Kilis MYO TR-79000 Kilis Turkey Univ Gaziantep Dept Civil Engn TR-27310 Gaziantep Turkey

This study focuses on studying the effects of fly ash and silica fume replacement content on the strength of concrete cured for a long-term period of time by neural networks (NNs). Applicability of NNs to evaluate the effects of FA and SF for a long period of time is investigated. The investigations covered concrete mixes at different water cementitious materials ratio, which contained low and high volumes of FA, and with or without the additional small amount of SF. 24 different mixes with 144 different samples were gathered form the literature for this purpose. These samples consist concretes that were cured for 3, 7, 28, 56 and 180 days. A NN model is constructed trained and tested using these data. The data used in the NN model are arranged in a format of eight input parameters that cover the fly ash replacement ratio (FA), silica fume replacement ratio (SF), total cementitious material (TCM), fine aggregate (ssa), coarse aggregate (ca), water content (W), high rate water reducing agent (HRWRA) and age of samples (AS) and an output parameter which is compressive strength of concrete (f(c)). A NN program was devised in MATLAB and the NN model was constructed in this program. The results showed that NNs have strong potential as a feasible tool for evaluation of the effect of cementitious material on the compressive strength of concrete. It was found that FA content contributed little at early ages but much at later ages to the strength of concrete. It can also be concluded that the enhancement effect of low content of SF on compressive strength was not significant. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： fly ash silica fume long-term cured concrete neural networks compressive strength scaled conjugate gradient algorithm

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：