For the purpose of embankment design, engineers must often rely on experience when selecting a reinforcement strain for analysis using limit equilibrium methods or resort to complicated numerical methods such as those based on the finite element method.
Presented within this study are the results of comprehensive parametric analysis varying reinforcement spacing, reinforcement strength and footing location, highlighting the stability benefits of top-down and bottom-up reinforcement density approaches.
The prediction of measured time series for slab deflections and strains, measured on the slab surface and on reinforcements, by the analysis remains challenging.
The results can provide theoretical foundations for stability analysis and reinforcement design of complex underground engineering.
The proposed model will help maintenance managers conduct detailed assessments and sequencing of reinforcement work through nonlinear analysis.
In summary, from data processing perspective, supervised learning and unsupervised learning mainly focus on data analysis while reinforcement learning is preferred for decision-making problems.
The variable confinement algorithm enables the explicit computation of relation between the concrete lateral dilation and straining of the transverse reinforcement computed at every analysis step.
The elastic properties of reinforcement assumed in the analysis are: modulus of elasticity (E) 200 GPa, and Poison's ratio (m) 0.30 [4].
