Prediction of liquefaction and the resulting lateral displacement is a complex engineering problem due to heterogeneous nature of soils and participation of a large number of factors involved. In this paper new models are developed, based on evolutionary polynomial regression (EPR), for assessment of liquefaction potential and lateral spreading. The models developed for liquefaction and lateral spreading are compared to those obtained from neural network and linear regression based techniques. It is shown that the developed models are able to learn the complex relationship between either of these problems and their contributing factors in the form of a function with high level of accuracy (mostly in excess of 90%). The results of the EPR model developed for the liquefaction determination are used to find a novel 3-D boundary surface that discriminates between the cases of occurrence and non-occurrence of liquefaction. The developed boundary surface is employed to calculate the factor of safety against liquefaction occurrence.
|Number of pages||12|
|Journal||Engineering Applications of Artificial Intelligence|
|Publication status||Published - Feb 2011|
- lateral displacement
- artificial neural networks
- cone penetration test
- evolutionary regression