Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects
Researchers have developed a new framework using physics-informed neural networks (PINNs) to model radial consolidation in geotechnical engineering. This framework, which includes standard, modified gated, and modified gated with hard-constraint boundary encoding models, accurately simulates complex loading conditions like vacuum and surcharge preloading. The modified hard-constraint PINN model demonstrated particular effectiveness, achieving low mean absolute error values for various time-dependent loading scenarios and showing robustness across different parameter ranges. AI
IMPACT This research advances the application of AI in complex engineering simulations, potentially improving predictive accuracy for soil consolidation.