Computational and training requirements for interatomic potential based on artificial neural network for estimating low thermal conductivity of silver chalcogenides

2020 ◽  
Vol 153 (23) ◽  
pp. 234301
Author(s):  
Kohei Shimamura ◽  
Yusuke Takeshita ◽  
Shogo Fukushima ◽  
Akihide Koura ◽  
Fuyuki Shimojo
Keyword(s):  
Neural Network ◽  
Thermal Conductivity ◽  
Artificial Neural Network ◽  
Interatomic Potential ◽  
Low Thermal Conductivity ◽  
Training Requirements ◽  
Silver Chalcogenides ◽  
Artificial Neural ◽  
And Training

scholarly journals ANNETT-O: an ontology for describing artificial neural network evaluation, topology and training

2019 ◽  
Vol 13 (3) ◽  
pp. 179
Author(s):  
Iraklis A. Klampanos ◽  
Athanasios Davvetas ◽  
Antonis Koukourikos ◽  
Vangelis Karkaletsis
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Artificial Neural ◽  
Network Evaluation ◽  
And Training

Prediction of the Density & Thermal Conductivity of Light Bricks on the Effect of Aluminium Elements Using Artificial Neural Network (ANN)

2019 ◽  
Vol 964 ◽  
pp. 270-279
Author(s):  
Zulkifli ◽  
Gede Panji
Keyword(s):  
Neural Network ◽  
Thermal Conductivity ◽  
Artificial Neural Network ◽  
Raw Materials ◽  
Simulation Method ◽  
Acoustic Properties ◽  
Main Element ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Element Variation

Indonesia with abundant limestone raw materials, lightweight brick is the most important component in building construction, so it needs a light brick product that qualifies in thermal, mechanical and acoustic properties. In this paper raised the lightweight brick domains that qualify on the properties of thermal conductivity as building wall components.The advantage of low light density brick (500-650 kg/m3), more economical, suitable for high rise building can reduce the weight of 30-40% in compared to conventional brick (clay brick). To obtain AAC type lightweight brick product that qualifies for low thermal and density properties to the effect of Aluminum (Al) additive element variation using artificial neural network (ANN). The composition of the main elements of lightweight brick O (29-45 % wt), Si (25-35% wt) and Ca (20-40 % wt). Mixing ratio of the main element of light brick (Ca, O and Si) with Aluminum additive element (Al), is done by simulation method of artificial neural network (ANN), Al additive element as a porosity regulator is formed. The simulation of thermal conductivity to the influence of main element variation: Ca (22-32 % wt), Si (12-33 % wt). Simulation of thermal conductivity to effect of additive Al variation (1-7 % wt). Simulation of thermal conductivity to density variation (500-1200 kg/m3). The simulated results of four AAC brick samples showed the thermal conductivity (0.145-0.192 W/m.K) to the influence of qualified Aluminum additives (2.10-6.75 % wt). Additive Al the higher the lower density value (higher porosity) additive Al smaller than 2.10 % wt does not meet the requirements in the simulation.Thermal conductivity of AAC light brick sample (0.184 W/m.K) the influence of the main elements that qualify Ca (20.32-30.35 % wt) and Si (26.57 % wt). Simulation of artificial neural network (ANN) of light brick shows that maximum allowable Si content of 26.57 % wt, Ca content is in the range 20.32-30.35 % wt, and the minimum content of aluminum in brick is light at 2.10 % wt. ANN tests performed to predict the thermal conductivity of light brick samples obtained results of the average AAC light brick thermal conductivity of 0.151 W/m.K. The best performance with Artificial Neural Network (ANN) characteristics has a validation MSE of 0.002252.

Sign in / Sign up

Export Citation Format

Share Document