检索结果-内蒙古大学图书馆

Neural network based model for seismic assessment of existing RC buildings

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

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 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 Approximation of Helicopter Turboshaft Engine Parameters for Improved Efficiency

引用

ENERGIES 2024年第9期17卷 2233页

作者： Vladov, Serhii Yakovliev, Ruslan Bulakh, Maryna Vysotska, Victoria Kharkiv Natl Univ Internal Affairs Kremenchuk Flight Coll 17-6 Peremohy St UA-39605 Kremenchuk Ukraine Rzeszow Univ Technol Fac Mech & Technol PL-37450 Stalowa Wola Poland Lviv Polytech Natl Univ Informat Syst & Networks Dept 12 Bandera St UA-79013 Lvov Ukraine Osnabruck Univ Inst Comp Sci 1 Friedrich Janssen St D-49076 Osnabruck Germany

The work is devoted to the development of a method for neural network approximation of helicopter turboshaft engine parameters, which is the basis for researching engine energy characteristics to improve efficiency, reliability, and flight safety. It is proposed to use a three-layer direct propagation neural network with linear neurons in the output layer for training in which the scale conjugate gradient algorithm is modified by introducing a moment coefficient into the analytical expression. This modification helps in calculating new model parameters to avoid falling into a local minimum. The dependence of the energy released during helicopter turboshaft engine compressor rotation on the gas-generator rotor r.p.m. was obtained. This enables the determination of the optimal gas-generator rotor r.p.m. region for a specific type of helicopter turboshaft engine. The optimal ratio of energy consumption and compressor operating efficiency is achieved, thereby ensuring helicopter turboshaft engines' optimal performance and reliability. Experimental data support the high efficiency of using a three-layer feed-forward neural network with linear neurons in the output layer, trained using a modified scale conjugate gradient algorithm, for approximating parameters of helicopter turboshaft engines compared to the analogues. Specifically, this method better predicts the relations between the energy release during compressor rotation and gas-generator rotor r.p.m. The efficiency coefficient of the proposed method was 0.994, which exceeded that of the closest analogue (0.914) by 1.09 times.

关键词： neural network approximation helicopter turboshaft engines energy power efficiency training gas-generator rotor r.p.m. scaled conjugate gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning algorithms for Quaternion-Valued Neural Networks

引用

NEURAL PROCESSING LETTERS 2018年第3期47卷 949-973页

作者： Popa, Calin-Adrian Polytech Univ Timisoara Dept Comp & Software Engn Blvd V Parvan 2 Timisoara 300223 Romania

This paper presents the deduction of the enhanced gradient descent, conjugate gradient, scaled conjugate gradient, quasi-Newton, and Levenberg-Marquardt methods for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. The performances of these algorithms in the real- and complex-valued cases led to the idea of extending them to the quaternion domain, also. Experiments done using the proposed training methods on time series prediction applications showed a significant performance improvement over the quaternion gradient descent algorithm.

关键词： Quaternion-valued neural networks Quickprop Resilient backpropagation Delta-bar-delta SuperSAB conjugate gradient algorithms scaled conjugate gradient algorithm Quasi-Newton algorithms Levenberg-Marquardt algorithm Time series prediction

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

Design of a short tensile coupon for fiber reinforced plastic using artificial neural networks

引用

SCIENCE AND ENGINEERING OF COMPOSITE MATERIALS 2005年第4期12卷 261-271页

作者： Saribiyik, M Caglar, N Firat, S Sakarya Univ Dept Construct TR-54187 Adapazari Turkey Sakarya Univ Dept Civil Engn TR-54187 Adapazari Turkey

The measurement of the mechanical properties of Fibre Reinforced Plastic (FRP) material is necessary for numerical structural analysis and design. The mechanical properties of the FRP materials may be determined by specific coupon test methods or by analytical calculation. However, pultruded or moulded FRP components may not possess the dimensions to permit the extraction of standard length coupons. The shape of the short tensile coupon has been established to circumvent this limitation using a Finite Element (FE) representation and Artificial Neural Network (ANN) including the effect of gripping length, coupon shape, width, length and thickness. The FE results have been used for the learning and testing sets of the ANN. The Multi-Layer Perceptron (MLP) has been employed in the modelling of the ANN. The MLP model has been trained using the scaled conjugate gradient algorithm (SCGA) and tested. The ANN results show that the correlation between targets and outputs are consistent.

关键词： fibre reinforced plastic mechanical properties numerical analysis tensile coupon artificial neural network 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

Short-Term Load Forecasting Based on a Improved Deep Belief Network

Short-Term Load Forecasting Based on a Improved Deep Belief ...

引用

6th International Conference on Smart Grid and Clean Energy Technologies (ICSGCE)

作者： Zhang, Xiaoyu Wang, Rui Zhang, Tao Zha, Yabin Natl Univ Def Technol Coll Informat Syst & Management Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781467389044

Short-term load forecast plays a vital role in the electric power industry. In this paper, a deep belief network is proposed for short-term load forecasting. However, the Back-Propagation (BP) algorithm of deep belief network for fine tuning has some inherent drawbacks and limitations, such as slow convergence rate and easy to fall into local minimum. To overcome the drawbacks, several neural network weight optimizing methods are proposed and compared. Experimental results show that Levenberg-Marquardt (LM) algorithm has the highest accuracy.

关键词： short-term load forecast deep belief network scaled conjugate gradient algorithm one step secant algorithm Levenberg-Marquardt algorithm

来源：评论

学校读者我要写书评

暂无评论

A neuro-fuzzy approach for modelling electricity demand in Victoria

引用

Applied Soft Computing 2001年第2期1.0卷 127-138页

作者： Abraham, Ajith Nath, Baikunth Sch. of Comp. and Info. Technology Monash University Gippsland Campus 3842 Churchill Australia

Neuro-fuzzy systems have attracted growing interest of researchers in various scientific and engineering areas due to the increasing need of intelligent systems. This paper evaluates the use of two popular soft computing techniques and conventional statistical approach based on Box-Jenkins autoregressive integrated moving average (ARIMA) model to predict electricity demand in the State of Victoria, Australia. The soft computing methods considered are an evolving fuzzy neural network (EFuNN) and an artificial neural network (ANN) trained using scaled conjugate gradient algorithm (CGA) and backpropagation (BP) algorithm. The forecast accuracy is compared with the forecasts used by Victorian Power Exchange (VPX) and the actual energy demand. To evaluate, we considered load demand patterns for 10 consecutive months taken every 30 min for training the different prediction models. Test results show that the neuro-fuzzy system performed better than neural networks, ARIMA model and the VPX forecasts. © 2001 Elsevier Science B.V All rights reserved.

关键词： ARIMA model Electricity demand Evolving fuzzy neural network Forecasting Neural networks Neuro-fuzzy 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：