Modelling soil behaviour in uniaxial strain conditions by neural networks

Turk, Goran (avtor), Logar, Janko (avtor), Majes, Bojan (avtor)

The feed-forward neural network was used to simulate the behaviour of soil samples in uniaxial strain conditions, i.e., to predict the oedometer test results only on the basic soil properties. Artificial neural network was trained using the database of 217 samples of different cohesive soils from various location in Slovenia. Good agreement between neural network predictions and laboratory test results was observd for the test samples. This study confirms the link between basic soil properties and stress-strain soil behaviour and demonstrates that artificial neural network successfully predicts soil stiffnes in uniaxial strain conditions. The comparison between the neural network prediction and empirical formulae shows that the neural network gives more accurate as well as more general solution of the problem

• Jezik: Angleški jezik
• Ključne besede: oedometer tests, artificial neural network, soil characteristics
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FGG - Fakulteta za gradbeništvo in geodezijo
• Založnik: Elsevier
• Leto izida: 2001
• Št. strani: Str. 805-812
• Številčenje: Vol. 32, Vol. 32
• PID: 20.500.12556/RUL-32125
• UDK: 624.131.37
• ISSN pri članku: 0965-9978
• DOI: 10.1016/S0965-9978(01)00032-1
• COBISS.SI-ID: 1475681
• Datum objave v RUL: 10.07.2015

Gradivo je del revije

• Naslov: Advances in engineering software
• Skrajšan naslov: Adv. eng. softw.
• Založnik: Elsevier Applied Science
• ISSN: 0965-9978
• COBISS.SI-ID: 34540032

Sekundarni jezik

• Jezik: Angleški jezik
• Ključne besede: edometrski poskusi, neuronske mreže, umetne neuronske mreže, lastnosti zemljin