Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Prediction of Liquefaction Susceptibility of Subsoil Layers Using Artificial Neural Networks
In the recent past, more focus has been given to the practical utilization of Artificial Neural Networks (ANN) in solving diverse geotechnical engineering prob-lems. The present study mainly aims to evaluate liquefaction potential for Visakhapatnam city based on IS 1893 Part-1 2016 method using an artificial neural network. Earlier researchers have developed back propagation artificial neural networks to predict the liquefaction potential of subsoil and concluded that modeling of any com-plex relationship between seismic, soil parameters, and liquefaction potential is possi-ble with neural networks. These models are reported to be simpler and more reliable than conventional methods of evaluating liquefaction potential. In the above context, an attempt has been made on a total of 10 boreholes data in the city premises of Visakhapatnam at different locations, which spreads over the coast-line. The most critical input parameter identified in the modelling of the network is the Standard Penetration N-Value. The data set in the model was trained, validated, and tested in the ratio of 60:20:20. The final results showed that neural networks are a powerful tool in predicting the occurrence of liquefaction potential. These predictions are almost 90% similar with an acceptable confidence level to the IS 1893 Part-1 2016 method.
Prediction of Liquefaction Susceptibility of Subsoil Layers Using Artificial Neural Networks
In the recent past, more focus has been given to the practical utilization of Artificial Neural Networks (ANN) in solving diverse geotechnical engineering prob-lems. The present study mainly aims to evaluate liquefaction potential for Visakhapatnam city based on IS 1893 Part-1 2016 method using an artificial neural network. Earlier researchers have developed back propagation artificial neural networks to predict the liquefaction potential of subsoil and concluded that modeling of any com-plex relationship between seismic, soil parameters, and liquefaction potential is possi-ble with neural networks. These models are reported to be simpler and more reliable than conventional methods of evaluating liquefaction potential. In the above context, an attempt has been made on a total of 10 boreholes data in the city premises of Visakhapatnam at different locations, which spreads over the coast-line. The most critical input parameter identified in the modelling of the network is the Standard Penetration N-Value. The data set in the model was trained, validated, and tested in the ratio of 60:20:20. The final results showed that neural networks are a powerful tool in predicting the occurrence of liquefaction potential. These predictions are almost 90% similar with an acceptable confidence level to the IS 1893 Part-1 2016 method.
Prediction of Liquefaction Susceptibility of Subsoil Layers Using Artificial Neural Networks
Lecture Notes in Civil Engineering
Jose, Babu T. (Herausgeber:in) / Sahoo, Dipak Kumar (Herausgeber:in) / Vanapalli, Sai K. (Herausgeber:in) / Solanki, Chandresh H. (Herausgeber:in) / Balan, K. (Herausgeber:in) / Pillai, Anitha G. (Herausgeber:in) / Eswara Rao, S. (Autor:in) / Satyanarayana Reddy, C. N. V (Autor:in)
Indian Geotechnical Conference ; 2022 ; Kochi, India
Proceedings of the Indian Geotechnical Conference 2022 Volume 9 ; Kapitel: 16 ; 179-189
25.09.2024
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Prediction of Liquefaction-Induced Settlement Using Artificial Neural Network
| Springer Verlag | 2024
Liquefaction Mitigation Measures for Weak Subsoil of Earthen Embankments
| Springer Verlag | 2024