检索结果-内蒙古大学图书馆

Prediction of plasmons in silver nanorods using artificial neural networks with back propagation algorithm

OPTIK 2018年 172卷 721-729页

作者： Rekha, C. R. Nayar, V. U. Gopchandran, K. G. Univ Kerala Dept Optoelect Thiruvananthapuram 695581 Kerala India

This work presents the prediction of plasmon positions in the optical absorption spectra of silver nanorods using artificial neural networks. Silver nanorods were prepared using a modified seed mediated strategy. At first, seed particles were synthesized by reducing silver ions with sodium borohydride in the presence of a stabilizer viz., cetyltrimethylammonium bromide (CTAB). In order to produce silver nanorods, the seeds were added to a growth solution containing a metal salt (AgNO3), a weak reducing agent (ascorbic acid) and a structure directing agent (CTAB). Four parameters viz., volume of metal seed, concentrations of silver nitrate, ascorbic acid and CTAB, which are found to be highly sensitive to plasmon characteristics are varied and grouped into 45 different sets of experiments. Herein, we report a model to predict the transverse and longitudinal plasmon band wavelengths, using a 4-input artificial neural network, having five neurons in the hidden layer and two neurons in the output layer. Levenberg Marquardt back-propagation algorithm was used for the design. The network architecture has been trained with the 45 sets of experimental data collected and the regression plots with good correlation coefficient values were obtained for training, testing and validation stages.

关键词： Silver nanorods Seed mediated synthesis Artificial neural networks back propagation algorithm Feed-forward network Hidden layers Training Regression plot

来源：评论

学校读者我要写书评

暂无评论

Full-Parameter Identification Model Based on back propagation algorithm for Brushless Doubly Fed Induction Generator

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2020年第10期35卷 9953-9958页

作者： Su, Jingyuan Chen, Yu Zhang, Debin Kang, Yong State Key Lab Adv Electromagnet Engn & Technol Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan 430074 Hubei Peoples R China

Brushless doubly fed induction generator (BDFIG) has great potential due to its high reliability and low maintenance cost. To achieve high-performance modeling and control, BDFIG resistances and inductances are necessary. However, the existing identification methods either required professional structure knowledge or special excitations and setups, or only estimated part of parameters. Thus, this letter proposes a multilayer full-parameter identification model based on the back-propagation (BP) algorithm for BDFIG, which is constructed with electric quantities as nodes and parameters as adjustable weights, and utilizes the electric quantities measured from regular operations as data. According to the fitting error obtained by comparing the model outputs with the easily measured references, the BP algorithm is applied to update the weights until the error is sufficiently small. Then, all resistances and inductances can be extracted directly from the weights. Such an identification methodology can be easily embedded into existing BDFIG systems. The simulations and experiments verify its feasibility and accuracy.

关键词： Mathematical model Fitting Electrical resistance measurement Data models Voltage measurement Power electronics Parameter estimation back propagation algorithm brushless doubly fed induction generator (BDFIG) parameter identification

来源：评论

学校读者我要写书评

暂无评论

Green lighting intelligent control system with web services based on back propagation algorithm

引用

INTERNATIONAL JOURNAL OF WEB AND GRID SERVICES 2020年第3期16卷 273-286页

作者： Wang, Xiaokan Wang, Qiong Henan Mech & Elect Vocat Coll Xinzheng 451191 Peoples R China

In order to solve the problems of large energy consumption in many stations, confusion lines and lighting source not accord with environmental protection requirement in the present, we put forward the scheme of automatic control system of green lighting based on PROFIBUS and PLC. In order to realise the inherent limitation of lighting control system in information sharing, remote control and other aspects, web services technology is combined with the original system to make full use of its technical advantages in distribution, openness and flexibility, so as to explore a better way for the development of industrial lighting network application. By constructing the communication network of the station lighting system with the PROFIBUS communication protocol and designing the hardware circuit and software program of the system bottom with programmable controller technology;simultaneously, the proposed BP neural network algorithm in the control system can realise intelligent control. Simulating with MATLAB of green computing for multimedia big data, the result shows that the station green lighting control system has very important significance of energy saving and provide the passenger for healthy, comfortable environment.

关键词： green lighting illumination intensity web services back propagation algorithm saving-energy

来源：评论

学校读者我要写书评

暂无评论

PREDICTION OF FROSTING PROCESS ON COLD WALL SURFACE BASED ON ANN WITH back propagation algorithm

引用

THERMAL SCIENCE 2023年第5B期27卷 4135-4144页

作者： Sun, Jinjuan Ma, Zhiheng Tian, Jianhui Xian Technol Univ Sch Mechatron Engn Xian Peoples R China

The ANN with back propagation algorithm is a multi-layer feed-forward neural network, which is suitable to study unsteady frost formation with multiple factors. The back propagation ANN algorithm is used to study frost layer growth on cold flat surface, where four feature variables including temperature of cold flat sur-face, the velocity, relative humidity, and temperature of air are adopted. The frost growth experiment generates the database, which is good for training frost growth due to its fast speed and high precision based on Levenberg-Marquardt learning rule. The establishment of neural network model in this paper can quickly and accurately predict the frost layer height on cold flat surface of different control variables, which is helpful for the implementation of defrosting.

关键词： Key words: ANN back propagation algorithm ANN frosting process frosting characteristics frost height

来源：评论

学校读者我要写书评

暂无评论

Robust back propagation algorithm as a chemometric tool to prevent the overfitting to outliers

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 1996年第1期34卷 109-115页

作者： Wang, JH Jiang, JH Yu, RQ HUNAN UNIV DEPT CHEM & CHEM ENGNCHANGSHA 410082PEOPLES R CHINA

The ordinary back propagation algorithm for the artificial network is non-robust. It has been shown in a straightforward way that the BP algorithm can be robustified by introducing some kind of transform on the residual term r(p). Using the proposed robust BP algorithm, the problem of overfitting to outlier points can effectively be circumvented. The feasibility of the proposed method has been testified by treating simulated examples and a real chemical data.

关键词： outliers overfitting artificial network back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE ANALYSIS OF THE L(P) NORM back-propagation algorithm FOR ADAPTIVE EQUALIZATION

引用

IEE PROCEEDINGS-F RADAR AND SIGNAL PROCESSING 1993年第1期140卷 43-47页

作者： SIU, S COWAN, CFN LOUGHBOROUGH UNIV TECHNOL DEPT ELECTR & ELECT ENGNLOUGHBOROUGH LE11 3TULEICSENGLAND

A performance analysis of the l(p) norm back propagation algorithm for adaptive equalisation with 1 less-than-or-equal-to p less-than-or-equal-to 2 is presented. Expected learning pins in both training mode and decision directed mode are analysed taking into account the effect of p. Simulation results for convergence properties and bit error rate (BER) performance are consistent with the analysis.

关键词： back propagation algorithm LINEAR EQUALIZER PERFORMANCE ANALYSIS MULTILAYER PERCEPTRON

来源：评论

学校读者我要写书评

暂无评论

4-CBA CONCENTRATION SOFT SENSOR BASED ON MODIFIED back propagation algorithm EMBEDDED WITH RIDGE REGRESSION

引用

INTELLIGENT AUTOMATION AND SOFT COMPUTING 2009年第1期15卷 41-51页

作者： Yan, Xuefeng Zhao, Weixiang E China Univ Sci & Technol Automat Inst Coll Informat Sci & Engn Shanghai 200237 Peoples R China Univ Calif Davis Dept Mech & Aeronaut Engn Davis CA 95616 USA

Considering that there exist many factors having highly nonlinear effects on the concentration of the 4-carboxybenzaldehyde (4-CBA), which is the most important intermediate product of the oxidation of the p-xylene (PX) to terephthalic acid (TA), a modified back propagation algorithm embedded with ridge regression (BP-RR) was proposed to develop a soft sensor of the 4-CBA concentration. To overcome the two main flaws of regular multi-layer neural networks, i.e. the tendency of overfitting and the difficulty to determine the optimal number of neurons for the hidden layer, firstly, a three-layer network is selected and the number of the hidden-layer neurons is determined according to the number of the training samples and the number of the neural network parameters. Then, BP is applied to learn from the training samples. In sequel, the ridge regression is employed to remove the multicollincarity among the hidden-layer-node outputs and obtain the optimal weights (and thresholds) between the hidden layer and the output layer to replace the original values obtained by BP. Thus the neural network model with good prediction ability is developed. In addition, the ridge regression uses heuristic differential evolution algorithm to optimize ridge parameter according to the prediction accuracy of the model. The results show that the optimal value of ridge parameter is adaptively determined according to the degree of multicollinearity among the hidden-layer-node output, and then the good prediction ability model with the robust character is obtained by BP-RR. The best and the mean prediction accuracies of the neural network models developed by BP-RR are higher than those of the neural network models trained by BP alone and obtained by pruning algorithms based on principle component analysis.

关键词： Neural Network back propagation algorithm Ridge Regression 4-Carboxybenzaldehyde Soft Sensor

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machines versus back propagation algorithm for Oil Price Prediction

Support Vector Machines versus Back Propagation Algorithm fo...

引用

8th International Symposium on Neural Networks

作者： Khashman, Adnan Nwulu, Nnamdi I. Near East Univ ISRG Lefkosa Turkey

ISBN: (纸本)9783642211102

The importance of crude oil in the world economy has made it imperative that efficient models be designed for predicting future prices. Neural networks can be used as prediction models, thus, in this paper we investigate and compare the use of a support vector machine and a back propagation neural network for the task of predicting oil prices. We also present a novel method of representing the oil price data as input data to the neural networks by defining input economic and seasonal indicators which could affect the oil price. The oil price database is publicly available online and can be obtained from the West Texas Intermediate crude oil price dataset spanning a period of 24 years. Experimental results suggest the neural networks can be efficiently used to predict future oil prices with minimal computational expense.

关键词： Crude Oil Price Prediction Neural Networks back propagation algorithm Support Vector Machines Radial Basis Function

来源：评论

学校读者我要写书评

暂无评论

Precision manufacturing technology and measurements in steel rolling industry using multi threshold fast fourier transform and back propagation algorithm for analysis of X-ray diffractometry 1

Precision manufacturing technology and measurements in steel...

引用

International Conference and Exposition on Mechanical, Material and Manufacturing Technology (ICE3MT)

作者： Sujatha, K. Ponmagal, R. S. Deepalakshmi, B. Jayachitra, N. Dr MGR Educ & Res Inst EEE Dept Chennai Tamil Nadu India SRM Inst Sci & Technol Dept CSE Chennai Tamil Nadu India Ramco Inst Technol Dept ECE Chennai Tamil Nadu India Dr MGR Educ & Res Inst Dept Chem Engn Chennai Tamil Nadu India

X-ray diffractometry is a unique technique and that the X-ray diffraction patterns which depict the structure of the steel sheets during processing with the features extracted, that they serve directly as a signature which is very complicated. X-ray diffraction (XRD) techniques are a type of non-destructive method of investigation to identify the flaws during the fabrication of steel sheets. X-ray diffraction is comparatively simple and can be effectively used for the examination and identification of flaws during the rolling process of steel sheets. XRD technique finds application in various fields like textile industry, forensic, qualitative and quantitative phase analysis of poly crystalline material, to infer overall properties of the fiber and measure the degree of crystalline nature. It is extensively used to explore areas like material science, chemistry and in industry for research and quality control. This effective method gains novelty by combining the signal processing algorithms like multiple threshold based Fast Fourier Transform (FFT) and Artificial neural network (ANN) trained with back propagation algorithm (BPA) thereby offering an automated system for online monitoring during fabrication of flawless metal sheets. The hot rolled steel sheets for three categories namely, flawless, moderate flaw and extreme flaw conditions are obtained from the XRD pattern. Then multiple thresholds are incorporated to identify the peak position, peak width and peak intensity. The FFT algorithm computes the power spectrum which is used as features to identify the flaws in the steel sheets during cold rolling process. The extracted features are used as inputs to train the ANN with BPA whose performance is evaluated to be 90% efficient. (C) 2020 The Authors. Published by Elsevier Ltd.

关键词： X-ray diffractometry Steel rolling Industry Multi-level threshold Fast fourier transform algorithm back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

An application of Verilog-A to modeling of back propagation algorithm in neural networks

An application of Verilog-A to modeling of back propagation ...

引用

43rd IEEE Midwest Symposium on Circuits and Systems

作者： Suzuki, K Nishio, A Kamo, A Watanabe, T Asai, H Univ Shizouka Fac Engn Dept Syst Engn Hamamatsu Shizuoka 4328561 Japan

ISBN: (纸本)0780364759

This paper describes an application of the Ve rilog-A, which is a hardware description language for analog applications, to modeling of neural networks. We try to simulate the neural networks with the learning algorithm, which has not been designed with electronic circuits. The learning algorithm is modeled with Verilog-A and the suitable synaptic weights are solved by the Verilog-A simulation.

关键词： analog hardware description language Verilog-A analog neural networks back propagation 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：