학술논문

Moment-rotational analysis of soil during mining induced ground movements by hybrid machine learning assisted quantification models of ELM-SVM
Document Type
Article
Source
Steel and Composite Structures, An International Journal, 41(6), pp.831-850 Dec, 2021
Subject
토목공학
Language
English
ISSN
1598-6233
1229-9367
Abstract
Surface subsidence caused by mining subsidence has an impact on neighboring structures and utilities. In other words, subsurface voids created by mining or tunneling activities induce soil movement, exposing buildings to physical and/or functional destruction. Soil-structure is evaluated employing probability distribution laws to account for their uncertainty and complexity to estimate structural vulnerability. In this study, to investigate the displacement field and surface settlement profile caused by mining subsidence, on the basis of a Winkler soil model, analytical equations for the moment–rotation response of soil during mining induced ground movements are developed. To define the full static moment–rotation response, an equation for the uplift-yield state is constructed and integrated with equations for the uplift- and yield-only conditions. The constructed model's findings reveal that the inverse of the factor of safety (x) has a considerable influence on the moment–rotation curve. The maximal moment–rotation response of the footing is defined by X = 0:6. Despite the use of Winkler model, the computed moment–rotation response results derived from the literature were analyzed through the ELM-SVM hybrid of Extreme Learning Machine (ELM) and Support Vector Machine (SVM). Also, Monte Carlo simulations are used to apply continuous random parameters to assess the transmission of ground motions to structures. Following the findings of RMSE and R2, the results show that the choice of probabilistic laws of input parameters has a substantial impact on the outcome of analysis performed.