检索结果-内蒙古大学图书馆

Ventilated cavity flows behind a backward facing step with a combination computational fluid dynamics and error back propagation algorithm

引用

OCEAN ENGINEERING 2022年 260卷

作者： He, Zanyang Sun, Tiezhi Zou, Li Jiang, Yichen Duan, Lei Shanghai Jiao Tong Univ Sch Naval Architecture Ocean & Civil Engn Shanghai 200240 Peoples R China Dalian Univ Technol Sch Naval Architecture State Key Lab Struct Anal Ind Equipment Dalian 116024 Peoples R China Shanghai Jiao Tong Univ State Key Lab Ocean Engn Shanghai 200240 Peoples R China

Ventilated cavity flow is of a great practical interest for the features that may reduce the drag around the area near the cavity. The present paper demonstrates the prediction of ventilated cavity flows on the backward facing step, which establishes the prediction model of drag reduction by the numerical simulation and artificial intelligence algorithm. The results of the computational fluid dynamics are compared with available experimental data to validate the precision, which shows good agreement. This paper numerically analyzes the influence of the number, location and part ventilation volume of injectors on the drag reduction of ventilated cavity flows. With the same air-entrant coefficient, the number and location of injectors both have a significant impact on drag reduction performance. And the part ventilation volume of the injectors may also have a limited impact. Accordingly, the prediction model of drag reduction is established by the error back propagation algorithm (BP algorithm) that has accurate algorithms and fast calculation to save time and computing resources. Meanwhile, the results indicate that BP algorithm can reasonably predict the performance of ventilated cavity flows, which means the model can optimize the drag reduction on ventilated cavity flows and it can be useful in engineering.

关键词： Ventilated cavity flows backward facing step error back propagation algorithm DES model Optimize drag reduction

来源：评论

学校读者我要写书评

暂无评论

A New Constructing Rational Functions Method For Solving Lane-Emden Type Equations

引用

NEURAL PROCESSING LETTERS 2023年第2期55卷 1889-1918页

作者： He, Jilong Zheng, Zhoushun Du, Changfa Cent South Univ Sch Math & Stat Changsha 410083 Hunan Peoples R China

In this paper, a new construction machine learning method is proposed based on Rational Chebyshev polynomials to solve Lane-Emden type differential equations. The method is used for training, and the parameters are obtained by the error back propagation principle. By comparing with Chebyshev neural network proposed in [Appl. Math. Comp. 247:100-114(2014)][Appl. Soft. Comp. 43:347-356(2016)], our results are more accurate.

关键词： Rational Chebyshev polynomials Lane-Emden equation error back propagation algorithm Machine learning

来源：评论

学校读者我要写书评

暂无评论

Single layer Chebyshev neural network model with regression-based weights for solving nonlinear ordinary differential equations

引用

EVOLUTIONARY INTELLIGENCE 2020年第4期13卷 687-694页

作者： Chakraverty, S. Mall, Susmita Natl Inst Technol Rourkela Dept Math Rourkela 769008 Odisha India

In this investigation, a novel single layer Functional Link Neural Network namely, Chebyshev artificial neural network (ChANN) model with regression-based weights has been developed to handle ordinary differential equations. In ChANN, the hidden layer is removed by an artificial expansion block of the input patterns by using Chebyshev polynomials. Thus the technique is more effectual than the multilayer ANN. Initial weights from the input layer to the output layer are taken by a regression-based model. Here, feed-forward structure and back-propagation algorithm of the unsupervised version have been utilized to make the error values minimal. Numerical examples and comparisons with other methods exhibit the superior behavior of this technique.

关键词： Chebyshev neural network Regression based weights error back propagation algorithm Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Multi-modality image fusion based on enhanced fuzzy radial basis function neural networks

引用

PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS 2018年 48卷 11-20页

作者： Chao, Zhen Kim, Dohyeon Kim, Hee-Joung Yonsei Univ Coll Hlth Sci Dept Radiat Convergence Engn 1 Yonseidae Gil Wonju 220710 Gangwon South Korea Yonsei Univ Coll Hlth Sci Dept Radiol Sci 1 Yonseidae Gil Wonju 220710 Gangwon South Korea

In clinical applications, single modality images do not provide sufficient diagnostic information. Therefore, it is necessary to combine the advantages or complementarities of different modalities of images. Recently, neural network technique was applied to medical image fusion by many researchers, but there are still many deficiencies. In this study, we propose a novel fusion method to combine multi-modality medical images based on the enhanced fuzzy radial basis function neural network (Fuzzy-RBFNN), which includes five layers: input, fuzzy partition, front combination, inference, and output. Moreover, we propose a hybrid of the gravitational search algorithm (GSA) and error back propagation algorithm (EBPA) to train the network to update the parameters of the network. Two different patterns of images are used as inputs of the neural network, and the output is the fused image. A comparison with the conventional fusion methods and another neural network method through subjective observation and objective evaluation indexes reveals that the proposed method effectively synthesized the information of input images and achieved better results. Meanwhile, we also trained the network by using the EBPA and GSA, individually. The results reveal that the EBPGSA not only outperformed both EBPA and GSA, but also trained the neural network more accurately by analyzing the same evaluation indexes.

关键词： Multi-modality medical images Image fusion Enhanced radial basis function neural network error back propagation algorithm Gravitational search algorithm A hybrid of error back propagation and gravity search algorithm

来源：评论

学校读者我要写书评

暂无评论

The influence of parameter initialization on the training time and accuracy of a nonlinear regression model

引用

JOURNAL OF COMMUNICATIONS TECHNOLOGY AND ELECTRONICS 2016年第6期61卷 646-660页

作者： Burnaev, E. V. Erofeev, P. D. Russian Acad Sci Kharkevich Inst Informat Transmiss Problems Bolshoi Karetnyi Per 19Str 1 Moscow 127051 Russia

In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed comparison of several widely used methods and several newly developed approached for initialization of parameters of a regression model, represented as a decomposition in a linear dictionary of some parametric functions (sigmoids). We proposed a general deterministic approach for initialization, providing repeatability of results, reduction of a learning time and in some cases increase of a regression model accuracy;we developed two new algorithms (based on a piecewise-linear approximation and based on local properties of approximable dependency) in the framework of the proposed approach;we developed randomized initialization algorithm (spherical initialization) for effective approximation of high-dimensional dependencies;we improved the classical initialization method SCAWI (by locating centers of sigmoids in sample points), providing a regression model accuracy improvement on specific classes of dependencies (smooth functions and discontinuous functions with a number of local peculiarities in an input domain) when using RProp algorithm for learning;we performed comparison of classical and newly proposed initialization methods and highlighted the most efficient ones.

关键词： nonlinear regression approximation neural networks parameter initialization SCAWI algorithm RProp algorithm error back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Modular implementation of artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2015年 45卷 57-70页

作者： Choudhury, T. A. Berndt, C. C. Man, Zhihong Federat Univ Australia Sch Engn & Informat Technol Fac Sci & Technol Churchill Vic 3841 Australia Swinburne Univ Technol IRIS Hawthorn Vic 3122 Australia SUNY Stony Brook Dept Mat Sci & Engn Stony Brook NY 11794 USA Swinburne Univ Technol Fac Sci Engn & Technol Hawthorn Vic 3122 Australia

This paper presents a modular implementation of an artificial neural network to model the atmospheric plasma spray process in predicting the in-flight particle characteristics from the input processing parameters. The in-flight particle characteristics influence the structure and properties of the thermal spray coating and, thus, are considered important parameters to comprehend, simulate and predict the manufacturing process. The modular implementation allows simplification of the optimized model structure with enhanced ability to generalise the network. As well, the underlying relationship between each of the output in-flight characteristics with respect to the input processing parameters is explored. Smaller networks are constructed that achieves better, or in some cases, similar results. The training process is found to be more robust and stable along with fewer fluctuations in the values of the network parameters. The networks also respond to the variations of the number of hidden layer neurons with some definite trend. The predictable trend enhances reliability of the application of the artificial neural network in modelling the atmospheric plasma spray process and overcomes the variability and nonlinearity associated with the process. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Atmospheric plasma spray In-flight particle characteristics Multi-net system Modular combination Artificial neural network error back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Chebyshev Neural Network based model for solving Lane-Emden type equations

引用

APPLIED MATHEMATICS AND COMPUTATION 2014年 247卷 100-114页

作者： Mall, Susmita Chakraverty, S. Natl Inst Technol Dept Math Rourkela 769008 Odisha India

The objective of this paper is to solve second order non-linear ordinary differential equations of Lane-Emden type using Chebyshev Neural Network (ChNN) model. These equations are categorized as singular initial value problems. Artificial Neural Network (ANN) model is used here to overcome the difficulty of the singularity. A single layer neural network is used and the hidden layer is eliminated by expanding the input pattern by Chebyshev polynomials. Here we have used feed forward neural network model and principle of error back propagation. Homogeneous and non-homogeneous Lane-Emden equations are considered to show effectiveness of Chebyshev Neural Network model. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Non-linear second order ordinary differential equation Lane-Emden equation Feed forward neural network error back propagation algorithm Chebyshev Neural Network

来源：评论

学校读者我要写书评

暂无评论

BP Neural Network-Based Web Service Selection algorithm in the Smart Distribution Grid 16

BP Neural Network-Based Web Service Selection Algorithm in t...

引用

16th Asia-Pacific Network Operations and Management Symposium (APNOMS)

作者： Rui, Lanlan Xiong, Yinglin Xiao, Ke Qiu, Xuesong Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9784885522888

A good web selection algorithm can provide the most suitable service for users. However, known for its slow convergence rate and proneness of oscillation in its learning process, the traditional error back propagation neural network algorithm cannot be applied in the service selection scenarios of actual smart distribution grid. In order to meet the requirements of telecommunication technology for smart distribution grid and improve the quality of telecommunication service, this paper proposes an improved error back propagation algorithm, in which the learning factor can be self-adjusted with every iteration. The simulation results show an optimization of the training speed and an oscillation reduction in the learning process with the new algorithm, thus obvious optimizing the web services selection in smart distribution grid.

关键词： error back propagation algorithm web services selection gentle factor UPS smart distribution grid

来源：评论

学校读者我要写书评

暂无评论

Optical correlator-neural networks hybrid system for automatic angle measurement of two-dimensional objects

引用

OPTICAL ENGINEERING 2012年第5期51卷

作者： Manivannan, Nadarajah Neil, Mark A. A. Balachandran, Wamadeva Brunel Univ Ctr Elect Syst Res Sch Engn & Design Uxbridge UB8 3PH Middx England Univ London Imperial Coll Sci Technol & Med Dept Phys London SW7 2AZ England

A new interpolation algorithm is proposed and demonstrated to perform automatic angle measurement of two-dimensional (2D) objects. The proposed algorithm works in conjunction with optical correlator neural network hybrid architecture (OCNN). The OCNN is trained with a combined algorithm of direct binary search and error back propagation. Input of the OCNN is presented with an image whose angle of rotation is to be measured, and output from the OCNN is fed into the proposed interpolation algorithm, which finally produces the rotation angle of the input image. Results of both computer simulation and experimental set-up are presented for an English alphabetic character as a 2D object. The experimental set-up consists of a real optical correlator using two spatial light modulators for both input and frequency plane representations and a PC based model of a single layer neural network. We obtained very low experimental mean absolute error of 3.18 deg with standard deviation of 2.9 deg. (C) 2012 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/***.51.5.057201] Subject terms: rotation

关键词： rotation angle measurement optical correlator binary phase-only matched filter multiplexed filter neural networks direct binary search algorithm error back propagation algorithm optical information processing

来源：评论

学校读者我要写书评

暂无评论

Study of Improved Genetic algorithm Based on Neural Network

Study of Improved Genetic Algorithm Based on Neural Network

引用

1st International Conference on Communications and Information Processing (ICCIP 2012)

作者： Chan, Xin Liu, Baiming Yang, Guoyan Heilongjiang Univ Sch Informat Sci & Technol Harbin 150001 Peoples R China Beijing Sci Technol Management Coll Dept Comp & Informat Engn Beijing 102206 Peoples R China

ISBN: (纸本)9783642319679

In order to overcome these disadvantages such as low rate of convergence in neural network back propagation (BP) algorithm, the likeliness to fall into local minima, the absent foundations for selecting initial weight values and threshold values as well as great randomness, the neural network optimization method is developed based on adaptive genetic algorithm. This technique combines advantages on both neural network BP algorithm and neural network optimization method. However, it proves to be unsatisfactory due to the slow evolution of population in early stage. The proposed algorithm is applied in the optimized design of weight values and threshold in neural network. The algorithm model is employed to make forecasts about unfathomable SVI parameters in a sewage plant in one city. The simulation experiment suggests that the aforesaid algorithm can not only eliminate shortcomings in BP algorithm, but also can improve remarkably convergence speed and precision through the comparison of its model with BP and GA-BP network models, obtaining good results.

关键词： genetic algorithm (GA) neural network error back propagation algorithm sewage parameter soft measurement

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：