سیویلیکا را در شبکه های اجتماعی دنبال نمایید.

Predicting Liquefaction Resistance of Soils Using Random Artificial Neural Network

Publish Year: 1402
Type: Conference paper
Language: English
View: 111

This Paper With 7 Page And PDF Format Ready To Download

این Paper در بخشهای موضوعی زیر دسته بندی شده است:

Export:

Link to this Paper:

Document National Code:

CENAF02_002

Index date: 8 April 2024

Predicting Liquefaction Resistance of Soils Using Random Artificial Neural Network abstract

This paper presents an approach to address structural uncertainties existing in Artificial Neural Network (ANN) modeling. This probabilistic approach is implemented to predict the liquefaction potential of soils based on Cone Penetration Test data. For this purpose, the number of hidden layers and the number of neurons in each layer are chosen as the random variables of interest. The concept of Monte Carlo simulation is employed, and random networks are constructed through 10,000 simulations. By conducting multiple simulations, it has been determined that the highest prediction accuracy (95.6%) is associated with a network having 15 hidden layers, while the lowest prediction accuracy (25%) is related to a network with 13 hidden layers. The results lead to the conclusion that the network structure of ANN does not follow a specific pattern, highlighting the inherent stochastic nature of the network. It is also illustrated that the prediction accuracy of the ANN model can be efficiently expressed with a certain probability, through the proposed probabilistic approach.

Predicting Liquefaction Resistance of Soils Using Random Artificial Neural Network Keywords:

Predicting Liquefaction Resistance of Soils Using Random Artificial Neural Network authors

Hasti Sepehrynasab

پژوهشگر آزاد

Amir Gholampour

Assistant professor, Apadana Institute of Higher Education, Shiraz, Iran