@article{Vedrtnam2026, 
author = {Ajitanshu Vedrtnam and Kishor Kalauni and Shashikant Chaturvedi and Peter Czirak and Martin T. Palou},
title = {Physics-Informed Surrogate Modelling of Concrete Self-Healing via Coupled FEM-ML with Active Learning},
year = {2026},
journal = {Computer Modeling in Engineering & Sciences},
volume = {146},
number = {2},
pages = {10},
keywords = {Self-healing concrete, finite element modelling, machine learning, bio-concrete, healing optimization, microbial calcium carbonate precipitation},
url = {https://www.sciopen.com/article/10.32604/cmes.2026.076651},
doi = {10.32604/cmes.2026.076651},
abstract = {This study presents a physics-informed modelling framework that combines finite element method (FEM) simulations and supervised machine learning (ML) to predict the self-healing performance of microbial concrete. A FEniCS-based FEM platform resolves multiphysics phenomena including nutrient diffusion, microbial CaCO3 precipitation, and stiffness recovery. These simulations, together with experimental data, are used to train ML models (Random Forest yielding normalized RMSE ≈ 0.10) capable of predicting performance over a wide range of design parameters. Feature importance analysis identifies curing temperature, calcium carbonate precipitation rate, crack width, bacterial strain, and encapsulation method as the most influential parameters. The coupled FEM-ML approach enables sensitivity analysis, design optimization, and prediction beyond the training dataset (consistently exceeding 90% healing efficiency). Experimental validation confirms model robustness in both crack closure and strength recovery. This FEM–ML pipeline thus offers a generalizable, interpretable, and scalable strategy for the design of intelligent, self-adaptive construction materials.}
}