Scholarly record

ALGORITHM FOR ASSESSING THE STABILITY OF A GEOTECHNICAL SYSTEM

Nikolay V. Dorofeev, А В Греченева, E S Pankina

Abstract

In this paper, we consider an algorithm for assessing the stability of a geotechnical system and its individual sections based on a basic model. As a basic model, it is proposed to use a set of models used at the design stage of sections of the geotechnical system. When assessing the stability of individual links of the geotechnical system, and the group stability of the analyzed area of the geotechnical system, the approaches of the theory of automatic control are used, taking into account bifurcation parameters and the modular approach. Bifurcation parameters are determined at the design and monitoring stage. The paper describes an algorithm for identifying bifurcation parameters and dangerous processes in a geotechnical system and subsequent assessment of key bifurcation zones. The assessment of key bifurcation zones is carried out on the basis of the method of identifying key monitoring zones. The final data processing was carried out using a neural network. The number of inputs in the neural network for each control point was 3016, the number of hidden layers was 2, with the number of neurons 1500, 700, 100, respectively. A sigmoid was used as activation functions for the intermediate layers, and a normalized exponential function was used for the output layer. The practical verification of the proposed approaches is carried out on the example of a three-storey building. The developed algorithm made it possible to predict the development of internal deformations in advance. In the future, research is needed to interpret the results of the neural network and match the value of the output of the neural network to the level of risk or possible damage.

Publication Impact Profile

No metrics available.

PLUMX see details

DOI resolver: doi.org/10.5593/sgem2021/1.1/s02.020

Publication details

Back to publication list