Extreme learning machine-based surrogate model for analyzing system reliability of soil slopes

Abstract

Geotechnical engineering problems are characterised by many sources of uncertainty, and reliability analysis is needed to take the uncertainties into account. An intelligent surrogate model based on extreme learning machine is proposed for slope system reliability analysis. The weights and bias which play an important role in the performance of ELM are optimised by a nature inspired artificial bee colony algorithm. The system failure probability of soil slopes is estimated by Monte Carlo simulation via the proposed surrogate model. Experimental results show that the proposed method is feasible, effective and simple to implement system reliability analysis of soil slopes.

Keywords:

• slope reliability analysis
• extreme learning machine
• artificial bee colony algorithm
• surrogate model

Additional information

Funding

This research was supported by the Fundamental Research Funds for the Central Universities [grant number DUT15LK11]; the Open Research Fund of the State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology [grant number GZ15207]; National Natural Science Foundation of China [grant number 51109028]; the State Scholarship Fund of China to pursue study in the USA as a visiting scholar [grant number 201208210208].