Application of artificial neural networks for slope stability analysis in geotechnical practice
Апстракт
In present paper, authors develop a model for estimation of earth slope stability based on the artificial neural networks. For this purpose, authors engage multi-layer feed-forward network with Levenberg-Marquardt learning algorithm and 14 hidden nodes, using existing experimental data, and the results of traditional limit equilibrium analyzes of 57 different cases according to the predefined experimental plan. The results obtained indicate high level of statistical reliability (R=0.95 and MSE=0.0035 for testing set of scaled values) and similar estimation accuracy as the existing mathematical expression for calculation of slope safety factor.
Кључне речи:
artificial neural network / safety factor / slope stability / verificationИзвор:
2016 13th Symposium on Neural Networks and Applications, NEUREL 2016, 2016, 89-94Издавач:
- IEEE, New York
Финансирање / пројекти:
- Магматизам и геодинамика Балканског полуострва од мезозоика до данас: значај за образовање металичних и неметаличних рудних лежишта (RS-MESTD-Basic Research (BR or ON)-176016)
Институција/група
PharmacyTY - CONF AU - Kostić, Srđan AU - Vasović, Nebojša AU - Todorović, Kristina AU - Samčović, Andreja PY - 2016 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/2672 AB - In present paper, authors develop a model for estimation of earth slope stability based on the artificial neural networks. For this purpose, authors engage multi-layer feed-forward network with Levenberg-Marquardt learning algorithm and 14 hidden nodes, using existing experimental data, and the results of traditional limit equilibrium analyzes of 57 different cases according to the predefined experimental plan. The results obtained indicate high level of statistical reliability (R=0.95 and MSE=0.0035 for testing set of scaled values) and similar estimation accuracy as the existing mathematical expression for calculation of slope safety factor. PB - IEEE, New York C3 - 2016 13th Symposium on Neural Networks and Applications, NEUREL 2016 T1 - Application of artificial neural networks for slope stability analysis in geotechnical practice SP - 89 EP - 94 DO - 10.1109/NEUREL.2016.7800125 ER -
@conference{ author = "Kostić, Srđan and Vasović, Nebojša and Todorović, Kristina and Samčović, Andreja", year = "2016", abstract = "In present paper, authors develop a model for estimation of earth slope stability based on the artificial neural networks. For this purpose, authors engage multi-layer feed-forward network with Levenberg-Marquardt learning algorithm and 14 hidden nodes, using existing experimental data, and the results of traditional limit equilibrium analyzes of 57 different cases according to the predefined experimental plan. The results obtained indicate high level of statistical reliability (R=0.95 and MSE=0.0035 for testing set of scaled values) and similar estimation accuracy as the existing mathematical expression for calculation of slope safety factor.", publisher = "IEEE, New York", journal = "2016 13th Symposium on Neural Networks and Applications, NEUREL 2016", title = "Application of artificial neural networks for slope stability analysis in geotechnical practice", pages = "89-94", doi = "10.1109/NEUREL.2016.7800125" }
Kostić, S., Vasović, N., Todorović, K.,& Samčović, A.. (2016). Application of artificial neural networks for slope stability analysis in geotechnical practice. in 2016 13th Symposium on Neural Networks and Applications, NEUREL 2016 IEEE, New York., 89-94. https://doi.org/10.1109/NEUREL.2016.7800125
Kostić S, Vasović N, Todorović K, Samčović A. Application of artificial neural networks for slope stability analysis in geotechnical practice. in 2016 13th Symposium on Neural Networks and Applications, NEUREL 2016. 2016;:89-94. doi:10.1109/NEUREL.2016.7800125 .
Kostić, Srđan, Vasović, Nebojša, Todorović, Kristina, Samčović, Andreja, "Application of artificial neural networks for slope stability analysis in geotechnical practice" in 2016 13th Symposium on Neural Networks and Applications, NEUREL 2016 (2016):89-94, https://doi.org/10.1109/NEUREL.2016.7800125 . .