Slope reliability analysis by updated support vector machine and Monte Carlo simulation
This paper presents a new methodology for slope reliability analysis by integrating the technologies of updated support vector machine (SVM) and Monte Carlo simulation (MCS). MCS is a powerful tool that may be used to solve a broad range of reliability problems and has therefore become widely used in slope reliability analysis. However, MCS often involves a great number of slope stability analysis computations, a process that requires excessive time consumption. The updated SVM is introduced in order to build the relationship between factor of safety and random variables of slope, contributing to reducing a large number of normal computing tasks and enlarging the problem scale and sample size of MCS. In the algorithm of the updated SVM, the particle swarm optimization method is adopted in order to seek the optimal SVM parameters, enhancing the performance of SVM for solving complex problems in slope stability analysis. Finally, the integrating method is applied to a classic slope for addressing the problem of reliability analysis. The results of this study indicate that the new methodology is capable of obtaining positive results that are consistent with the results of classic solutions; therefore, the methodology is proven to be a powerful and effective tool in slope reliability analysis. Copyright Springer Science+Business Media B.V. 2013
Year of publication: |
2013
|
---|---|
Authors: | Li, Shaojun ; Zhao, Hong-Bo ; Ru, Zhongliang |
Published in: |
Natural Hazards. - International Society for the Prevention and Mitigation of Natural Hazards. - Vol. 65.2013, 1, p. 707-722
|
Publisher: |
International Society for the Prevention and Mitigation of Natural Hazards |
Subject: | Slope | Reliability analysis | Monte Carlo simulation | Support vector machine | Particle swarm optimization |
Saved in:
Online Resource
Saved in favorites
Similar items by subject
-
A loan default discrimination model using cost-sensitive support vector machine improved by PSO
Cao, Jie, (2013)
-
Zhu, Bangzhu, (2022)
-
Forecasting inflection points : hybrid methods with multiscale machine learning algorithms
Chevallier, Julien, (2021)
- More ...
Similar items by person