检索结果-内蒙古大学图书馆

Influence of Process Parameters and Electrode Geometry on Feature Micro-Accuracy in Electro Discharge Machining of Tool Steel

引用

MATERIALS AND MANUFACTURING PROCESSES 2009年第12期24卷 1282-1289页

作者： Pellicer, N. Ciurana, J. Ozel, T. Univ Girona Dept Mech Engn & Ind Construct Girona 17071 Spain Rutgers State Univ Dept Ind & Syst Engn Piscataway NJ USA

Agile manufacturing capabilities require fast responses in workshops to cope with different demands in product geometrical features and qualities in fabricating moulds. Therefore, direct machining of complex mould features using simple shape machined electrodes with the electro-discharge machining (EDM) process, empowers the flexibility and the capacity of the enterprises and dramatically reduces lead times resulting in much more efficient production processes. In the case of machining geometrical features with characteristic dimensions in the order of few millimeters, the EDM process requires further understanding. This article focuses on investigating the influence of EDM parameters and electrode geometry on feature micro-accuracy in tool steel for mould fabrication purposes. A set of designed experiments with varying EDM process parameters such as pulsed current, open voltage, pulse time, and pulse pause time is carried out in H13 steel using differently shaped copper electrodes. Microdimensional and geometrical accuracies are the measures of response. artificial neural network and regression models have been constructed to capture the influence of the process parameters on the geometrical feature quality such as flatness, depth, slope, width, and dimension variation between the entrance and the exit (DVEE).

关键词： artificial neural network modeling EDM technology Mould making Process parameters

来源：评论

学校读者我要写书评

暂无评论

artificial neural network modeling to predict the plasma concentration of aminoglycosides in burn patients

引用

BIOMEDICINE & PHARMACOTHERAPY 2004年第4期58卷 239-244页

作者： Yamamura, S Kawada, K Takehira, R Nishizawa, K Katayama, S Hirano, M Momose, Y Toho Univ Sch Pharmaceut Sci Chiba 2748510 Japan Nippon Med Coll Hosp Dept Pharm Serv Bunkyo Ku Tokyo 1138603 Japan

The goal was to use an artificial neural network model to predict the plasma concentration of aminoglycosides in burn patients and identify patients whose plasma antibiotic concentration would be sub-therapeutic based on the patients' physiological data and taking into account burn severity. Physiological data and some indicators of burn severity were collected from 30 burn patients who received arbekacin. A three-layer artificial neural network with five neurons in the hidden layer was used to predict the plasma concentration of arbekacin. Linear modeling for prediction of plasma concentration and logistic regression modeling for the classification of patients were also used and the predictive performance was compared to results from the artificial neural network model. Dose, body mass index, serum creatinine concentration and amount of parenteral fluid were selected as covariates for the plasma concentration of arbekacin. Area of burn after skin graft was a good covariate for indicating burn severity. Predictive performance of the artificial neural network model including burn severity was much better than linear modeling and logistic regression analysis. An artificial neural network model should be helpful for the prediction of plasma concentration using patients' physiological data, and burn severity should be included for improved prediction in burn patients. Because the relationship between burn severity and plasma concentration of aminoglycosides is thought to be nonlinear, it is not surprising that the artificial neural network model showed better predictive performance compared to the linear or logistic regression models. (C) 2004 Elsevier SAS. All rights reserved.

关键词： artificial neural network modeling aminoglycoside antibiotics burn severity pharmacokinetic modeling

来源：评论

学校读者我要写书评

暂无评论

Response surface methodology (RSM) as a tool for optimization in analytical chemistry

引用

TALANTA 2008年第5期76卷 965-977页

作者： Bezerra, Marcos Almeida Santelli, Ricardo Erthal Oliveira, Eliane Padua Villar, Leonardo Silveira Escaleira, Luciane Amlia Univ Estadual Sudoeste Bahia Lab Quim Analit Rua Jose Moreira Sobrinho S-N BR-45206190 Jequie BA Brazil Univ Fed Fluminense Dept Geoquim BR-24020150 Niteroi RJ Brazil

A review about the application of response surface methodology (RSM) in the optimization of analytical methods is presented. The theoretical principles of RSM and steps for its application are described to introduce readers to this multivariate statistical technique. Symmetrical experimental designs (three-level factorial, Box-Behnken, central composite, and Doehlert designs) are compared in terms of characteristics and efficiency. Furthermore, recent references of their uses in analytical chemistry are presented. Multiple response optimization applying desirability functions in RSM and the use of artificial neural networks for modeling are also discussed. (C) 2008 Published by Elsevier B.V.

关键词： response surface methodology three-level factorial design Box-Behnken design central composite design Doehlert design desirability function artificial neural network modeling

来源：评论

学校读者我要写书评

暂无评论

Prediction of coal hydrogen content for combustion control in power utility using neural network approach

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2008年第2期94卷 149-159页

作者： Saptoro, A. Yao, H. M. Tade, M. O. Vuthaluru, H. B. Curtin Univ Technol Dept Chem Engn Perth WA 6845 Australia

The solid nature of coal presents greater difficulties in measuring and controlling the combustion process compared to gas and oil fired power plants. Knowing the composition and energy content of coal can be very useful for combustion control in coal-fired power utilities. In this work, an attempt is made to establish relationships between the hydrogen composition of coal and available data from the proximate analysis. In the present work, artificial neural network based model is developed for the prediction of hydrogen content. For practical implications, a combustion control system utilising the neural network based model is also proposed to show the potential for coal-fired utilities. (C) 2008 Elsevier B.V. All rights reserved.

关键词： artificial neural network modeling pc-fired boilers Coal elemental prediction Hydrogen Proximate analysis

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Swarm Intelligence Optimization and Behavioral Learning Concepts Using artificial neural networks (An over view)

Comparison Between Swarm Intelligence Optimization and Behav...

引用

12th World Multi-Conference on Systemics, Cybernetics and Informatics/14th International Conference on Information Systems Analysis and Synthesis

作者： Hassan, H. M. Al-Hammadi, Ayoub Al-Saleem, Saleb M. Banha University Egypt Arab Open University (KSA) Saudi Arabia IESK Otto-Von-Guericke University Magdburg Germany Riyadh College of Technology Saudi Arabia

ISBN: (纸本)9781934272312

Generally, in nature, non-human creatures perform adaptive behaviors to external environment they are living in. i.e. animals have to keep alive by improving there behavioral ability to be adaptable to there living environmental conditions. This paper presents an investigational comparative overview on adaptive behaviors associated with two diverse (neural and Non-neural) biological systems. Namely, intelligent behavioral performance of Ant Colony System (ACS) to reach optimal solution of Traveling Sales-man Problem (TSP). That is investigated versus concepts of adaptive behavioral learning concerned with some animals (cats, dogs and rats), in order to keep survive. More precisely, investigations of behavioral observations tightly related to suggested animals, supposed to obey discipline of biological information processing. So, artificial neural network (ANN) modeling is a relevant tool to investigate such biological system observations. Moreover, an illustrative brief of ACS optimal intelligent behaviors to solve TSP is presented. Additionally, considering effect of noisy environment on learning convergence an interesting analogy between both proposed biological systems is introduced. Finally, performance of three learning algorithms shown to be analogously in agreement with behavioral concepts of both suggested biological systems' performance.

关键词： artificial neural network modeling Animal learning ant colony system traveling salesman problem and computational biology

来源：评论

学校读者我要写书评

暂无评论

Evaluation of memorization brain function using a spatio-temporal artificial neural network (ANN) model

Evaluation of memorization brain function using a spatio-tem...

引用

4th International Conference on Cybernetics and Information Technologies, Systems and Applications/5th Int Conf on Computing, Communications and Control Technologies

作者： Hassan, Hassan M. Al-Hammadi, Ayoub Michaaelis, Bernd Computer Dept. Faculty of Teachers Hail University Saudi Arabia IESK Otto-Von-Guericke Univ. Magdburg Germany

ISBN: (纸本)9781934272244

Recent biological experimental findings have announced so, me interesting results concerned with evaluation of brain functions (teaming an it memory). Herein main attention delivered to Construct an ANN model to simulate the activity of transference short term memory (STM) into long term memory (LTM). This memorization function basically depends upon the adaptation and selectivity of synaptic plasticity. That observed as two phenomena of long term potentiation LTP, and long term depression LTD. This paper introduces a modified version model of an over- simplified memorization function model (Grand mother cells network). The proposed model is spatial- temporal and characterized by some biological features such as dynamical adaptation, selectivity and fault tolerance. So, it seems to simulate realistically the role performed by transcription gene factor namely CREB. That as it selects some synapses to be strengthened and neglect others on the basis of LTP and LTD respectively. More over, the effect of forgetting factor on presented model performance is evaluated. Finally, However, the proposed model seems to be will inspired by biology, this paper opens future research work to construct more biologically plausible models based on pulsed neural networks or equivalently spike- timing- dependent- plasticity.

关键词： synaptic plasticity artificial neural network modeling grand mother cells behavioral brain functions

来源：评论

学校读者我要写书评

暂无评论

Application of artificial neural networks and DFT-based parameters for prediction of reaction kinetics of ethylbenzene dehydrogenase

引用

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN 2006年第3期20卷 145-157页

作者： Szaleniec, Maciej Witko, Malgorzata Tadeusiewicz, Ryszard Goclon, Jakub Polish Acad Sci Inst Catalysis & Surface Chem PL-30239 Krakow Poland AGH Univ Sci & Technol PL-30059 Krakow Poland

artificial neural networks (ANNs) are used for classification and prediction of enzymatic activity of ethylbenzene dehydrogenase from EbN1 Azoarcus sp. bacterium. Ethylbenzene dehydrogenase (EBDH) catalyzes stereo-specific oxidation of ethylbenzene and its derivates to alcohols, which find its application as building blocks in pharmaceutical industry. ANN systems are trained based on theoretical variables derived from Density Functional Theory (DFT) modeling, topological descriptors, and kinetic parameters measured with developed spectrophotometric assay. Obtained models exhibit high degree of accuracy (100% of correct classifications, correlation between predicted and experimental values of reaction rates on the 0.97 level). The applicability of ANNs is demonstrated as useful tool for the prediction of biochemical enzyme activity of new substrates basing only on quantum chemical calculations and simple structural characteristics. Multi Linear Regression and Molecular Field Analysis (MFA) are used in order to compare robustness of ANN and both classical and 3D-quantitative structure-activity relationship (QSAR) approaches.

关键词： artificial neural network modeling DFT enzyme activity ethylbenzene dehydrogenase multiple linear regression QSAR

来源：评论

学校读者我要写书评

暂无评论

On learning performance evaluation for some psycho-learning experimental work versus an optimal swarm intelligent system

On learning performance evaluation for some psycho-learning ...

引用

5th IEEE International Symposium on Signal Processing and Information Technology

作者： Hassan, HM Educ Tech Dept Fac Specif Educ Banha Egypt

ISBN: (纸本)0780393139

Some models closely related to animal psycho-learning, and a swarm intelligent system, are comparatively presented. More specifically, three introduced models are inspired by creatures' behavioral learning phenomenon, observed in nature. Two of presented models based on Pavlov's and Thorndike's excremental work. Pavlov's dog learns how to associate two inputs sensory stimuli (audible, and visual signals). Thorndike's cat behavioral learning that to get out from a cage for obtaining food. Each of behavioral learning models improves its performance by minimizing response time period. Additionally, other third model motivated by ant colony system ACS. optimized performance. That model simulates a swarm (ant) intelligent system used for solving optimally traveling sales man problem TSP. That by bringing food from different food sources to store (in cycles) at ant's nest. Moreover, three other learning models based on pulsed neurons criterion, parallel genetic algorithmic programming, and modified Hebbian learning paradigm (Oja's rule). Interestingly, those models shown to behave analogously to previously suggested;Pavlov's, Thorndike's and ACS models.

关键词： artificial neural network modeling swarm intelligence ant colony system traveling salesman problem and computational biology

来源：评论

学校读者我要写书评

暂无评论

An artificial neural network approach to Escherichia coli O157:H7 growth estimation

引用

JOURNAL OF FOOD SCIENCE 2003年第2期68卷 639-645页

作者： García-Gimeno, RM Hervás-Martínez, C Barco-Alcalá, E Zurera-Cosano, G Sanz-Tapia, E Univ Cordoba Dept Food Sci & Technol Cordoba Spain Univ Cordoba Dept Comp Sci & Numer Anal Cordoba Spain

artificial neural networks (ANN) was evaluated and compared with Response Surface Model (RSM) results using growth response data for E. coli O157:H7 as affected by 5 variables: pH, sodium chloride, and nitrite concentrations, temperature, and aerobic/anaerobic conditions. The best ANN obtained, where the 2 kinetic parameters, growth rate and lag-time, were estimated jointly, contained 17 parameters and displayed a slightly lower Standard Error of Prediction (% SEP) than those obtained with RSM. Mathematical lag-time validation with additional data gave a lower %SEP for ANN (18%) than for RSM (27%), although growth-rate values were the same (22%). ANN thus should provide the innovative possibility of obtaining a single predictive model for the estimation of several kinetic parameters.

关键词： microbial growth Escherichia coli O157 : H7 artificial neural network modeling genetic 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：