RETRACTED ARTICLE: Modeling the correlation between Charpy impact energy and chemical composition of functionally graded steels by artificial neural networks

2012 ◽  
Vol 31 (S2) ◽  
pp. 707-721 ◽  
Author(s):  
Ali Nazari
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Chemical Composition ◽  
Impact Energy ◽  
Charpy Impact ◽  
Functionally Graded ◽  
Charpy Impact Energy ◽  
Retracted Article ◽  
Artificial Neural

scholarly journals Atmospheric Pollutant Flow and Precipitation: Modeling Effects on the Vegetation Ecosystem

2018 ◽  
Vol 7 (3) ◽  
pp. 157-161
Author(s):  
Allag Fateh ◽  
Saddek Bouharati ◽  
Lamri Tedjar ◽  
Mohamed Fenni
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Chemical Composition ◽  
Wide Distribution ◽  
Climatic Conditions ◽  
Mathematical Methods ◽  
Atmospheric Pollutant ◽  
Artificial Neural ◽  
Precipitation Modeling ◽  
The Impact

Because of their fixed life and wide distribution, plants are the first victims of air pollution. The atmosphere is considered polluted when the increase of the rate of certain components causes harmful effects on the different constituents of the ecosystems. The study of the flow of air near a polluting source (cement plant in our case), allows to predict its impact on the surrounding plant ecosystem. Different factors are to be considered. The chemical composition of the air, the climatic conditions, and the impacted plant species are complex parameters to be analyzed using conventional mathematical methods. In this study, we propose a system based on artificial neural networks. Since artificial neural networks have the capacity to treat different complex parameters, their application in this domain is adequate. The proposed system makes it possible to match the input and output spaces. The variables that constitute the input space are the chemical composition, the concentration of the latter in the rainwater, their duration of deposition on the leaves and stems, the climatic conditions characterizing the environment, as well as the species of plant studied. The output variable expresses the rate of degradation of this species under the effect of pollution. Learning the system makes it possible to establish the transfer function and thus predict the impact of pollutants on the vegetation.

Application of Artificial Neural Networks to Predict Chemical Composition of Electrodeposited Nanocrystalline Ni-Mo Thin Films

2013 ◽  
Vol 50 (52) ◽  
pp. 63-71
Author(s):  
M. H. Allahyarzadeh ◽  
A. Ashrafi ◽  
T. Shahrabi ◽  
A. Seddighian ◽  
M. Aliofkhazraei ◽  
...  
Keyword(s):  
Thin Films ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Chemical Composition ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document