A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
CPT-based Seismic Liquefaction Potential Evaluation Using Multi-gene Genetic Programming Approach
Abstract This study examines the potential of multi-gene genetic programming (MGGP) based classification approach to evaluate liquefaction potential of soil in terms liquefaction index (LI) using a large database from post liquefaction cone penetration test (CPT) measurements and field manifestations. The database consists of CPT measurements; cone tip resistance (q c ), friction ratio (R f ), vertical total stress (σ v ) and vertical effective stress of soil (σ v ′ ), seismic parameters; peak horizontal ground surface acceleration (a max ) and earthquake moment magnitude (M w), and the depth under consideration (z). The MGGP models (Model-I and Model-II) are developed for predicting occurrence and non-occurrence of liquefaction on basis of combination of above input parameters. The performance of the Model-I (95 %) is found to be more efficient compared to available artificial neural network model (91 %) and that of the Model-II (97 %) is found to be at par with the available support vector machine model (97 %) in terms of rate of successful prediction of liquefied and non-liquefied cases for testing data. Using an independent database of 96 cases, the overall classification accuracies are found to be 87 and 86 % for Model-I and Model-II respectively. Sensitivity analyses are made to identify the important parameters contributing to the prediction of LI.
CPT-based Seismic Liquefaction Potential Evaluation Using Multi-gene Genetic Programming Approach
Abstract This study examines the potential of multi-gene genetic programming (MGGP) based classification approach to evaluate liquefaction potential of soil in terms liquefaction index (LI) using a large database from post liquefaction cone penetration test (CPT) measurements and field manifestations. The database consists of CPT measurements; cone tip resistance (q c ), friction ratio (R f ), vertical total stress (σ v ) and vertical effective stress of soil (σ v ′ ), seismic parameters; peak horizontal ground surface acceleration (a max ) and earthquake moment magnitude (M w), and the depth under consideration (z). The MGGP models (Model-I and Model-II) are developed for predicting occurrence and non-occurrence of liquefaction on basis of combination of above input parameters. The performance of the Model-I (95 %) is found to be more efficient compared to available artificial neural network model (91 %) and that of the Model-II (97 %) is found to be at par with the available support vector machine model (97 %) in terms of rate of successful prediction of liquefied and non-liquefied cases for testing data. Using an independent database of 96 cases, the overall classification accuracies are found to be 87 and 86 % for Model-I and Model-II respectively. Sensitivity analyses are made to identify the important parameters contributing to the prediction of LI.
CPT-based Seismic Liquefaction Potential Evaluation Using Multi-gene Genetic Programming Approach
Muduli, Pradyut Kumar (author) / Das, Sarat Kumar (author)
Indian Geotechnical Journal ; 44 ; 86-93
2013-03-09
8 pages
Article (Journal)
Electronic Resource
English
CPT-based Seismic Liquefaction Potential Evaluation Using Multi-gene Genetic Programming Approach
| Online Contents | 2014
| Taylor & Francis Verlag | 2014
| British Library Online Contents | 2015