A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Intelligent prediction of the stress–strain response of intact and jointed rocks
AbstractAn application of Artificial Neural Networks for predicting the stress–strain response of jointed rocks under different confining pressures is presented in this paper. Rocks of different compressive strength with different joint properties (frequency, orientation and strength of joints) are considered in this study. The database for training the neural network is formed from the results of triaxial compression tests on different intact and jointed rocks with different joint properties tested at different confining pressures reported by various researchers in the literature. The network was trained using a three-layered network with the feed-forward back propagation algorithm. About 85% of the data was used for training and the remaining 15% was used for testing the network. Results from the analyses demonstrated that the neural network approach is effective in capturing the stress–strain behaviour of intact rocks and the complex stress–strain behaviour of jointed rocks. A single neural network is demonstrated to be capable of predicting the stress–strain response of different jointed rocks, whose intact strength varies from 11.32MPa to 123MPa, spacing of joints varies from 10cm to 100cm, and confining pressures range from 0 to 13.8MPa.
Intelligent prediction of the stress–strain response of intact and jointed rocks
AbstractAn application of Artificial Neural Networks for predicting the stress–strain response of jointed rocks under different confining pressures is presented in this paper. Rocks of different compressive strength with different joint properties (frequency, orientation and strength of joints) are considered in this study. The database for training the neural network is formed from the results of triaxial compression tests on different intact and jointed rocks with different joint properties tested at different confining pressures reported by various researchers in the literature. The network was trained using a three-layered network with the feed-forward back propagation algorithm. About 85% of the data was used for training and the remaining 15% was used for testing the network. Results from the analyses demonstrated that the neural network approach is effective in capturing the stress–strain behaviour of intact rocks and the complex stress–strain behaviour of jointed rocks. A single neural network is demonstrated to be capable of predicting the stress–strain response of different jointed rocks, whose intact strength varies from 11.32MPa to 123MPa, spacing of joints varies from 10cm to 100cm, and confining pressures range from 0 to 13.8MPa.
Intelligent prediction of the stress–strain response of intact and jointed rocks
Garaga, Arunakumari (author) / Latha, Gali Madhavi (author)
Computers and Geotechnics ; 37 ; 629-637
2010-04-06
9 pages
Article (Journal)
Electronic Resource
English
Intelligent prediction of the stress–strain response of intact and jointed rocks
| Online Contents | 2010
A classification for intact and jointed rocks
| British Library Conference Proceedings | 1993
| British Library Online Contents | 2016