Modelling soil behaviour in uniaxial strain conditions by neural networks

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

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

• Language: English
• Keywords: oedometer tests, artificial neural network, soil characteristics
• Typology: 1.01 - Original Scientific Article
• Organization: FGG - Faculty of Civil and Geodetic Engineering
• Publisher: Elsevier
• Year: 2001
• Number of pages: Str. 805-812
• Numbering: Vol. 32, Vol. 32
• PID: 20.500.12556/RUL-32125
• UDC: 624.131.37
• ISSN on article: 0965-9978
• DOI: 10.1016/S0965-9978(01)00032-1
• COBISS.SI-ID: 1475681
• Publication date in RUL: 10.07.2015

Record is a part of a journal

• Title: Advances in engineering software
• Shortened title: Adv. eng. softw.
• Publisher: Elsevier Applied Science
• ISSN: 0965-9978
• COBISS.SI-ID: 34540032

Secondary language

• Language: English
• Keywords: edometrski poskusi, neuronske mreže, umetne neuronske mreže, lastnosti zemljin