Title: Evolutionary artificial intelligence in the Industry 4.0 to simulate static loads in railway tracks for geosynthetic-reinforced soil structures based geogrid
Authors: M.A. Balasubramani; R. Venkatakrishnaiah; K.V.B. Raju
Addresses: Department of Civil Engineering, Bharath Institute of Higher Education and Research, Tamil Nadu, India ' Department of Civil Engineering, Bharath Institute of Higher Education and Research, Tamil Nadu, India ' Department of Civil Engineering, Bharath Institute of Higher Education and Research, Tamil Nadu, India
Abstract: In order to evaluate the internal stabilities of geogrid-reinforced pile-supported foundation (GRPSF) constructions, a precise estimation of the reinforcing tensile stresses is essential. In this study, we use experimental research and finite element modelling to examine the effects of geogrid on the stability and settlement of elevated railway embankments. The first embankments were not geogrid reinforced. An adaptive metaheuristic intelligence model was created to estimate reinforcement loads effectively and accurately. The proposed model improves the prediction ability of the artificial neural network (ANN) technology by adding the intelligent components of neurons. Using a range of acknowledged statistical markers, the model's predictive power was assessed and confirmed against several independent scientific studies published in the literature. A sensitivity analysis was used to further test the model's dependability and robustness. The suggested ANN model can intelligently and accurately estimate the maximum settling of GRPSF under service loads, making it a useful prediction tool for early GRPSF design. Engineers conducted computer simulations to place geogrid layers on the second through fifth embankments. The settlements of these berms were compared after being loaded with anywhere from one to four layers of geogrid.
Keywords: geogrid-reinforced pile-supported foundation; GRPSF; settlement; testing; settlement; geosynthetic-reinforced soil; ballasted; Sslab track; predictive modelling; artificial intelligence in the Industry 4.0; artificial neural network; ANN.
DOI: 10.1504/IJANS.2024.137160
International Journal of Applied Nonlinear Science, 2024 Vol.4 No.2, pp.106 - 121
Received: 19 Apr 2023
Accepted: 12 Jul 2023
Published online: 04 Mar 2024 *