A monitoring platform based on electrical impedance and AI techniques to enhance the resilience of the built environment

Structural Health Monitoring (SHM) and early warning systems (EWSs) play a pivotal role in enhancing seismic resilience for both buildings and occupants. This paper introduces a monitoring platform that collects electrical impedance data from scaled concrete beams undergoing load and accelerated degradation tests. Artificial Intelligence (AI) algorithms are employed for predictive analysis, scrutinizing historical impedance data, and forecasting future trends. These algorithms adapt to environmental parameters, becoming valuable tools in data-driven decision-making processes. In particular, the study investigates concrete specimens in different test conditions, utilizing a distributed sensor network based on electrical impedance as well as temperature and relative humidity sensors. Real-time data are transmitted to a cloud infrastructure during accelerated degradation tests (both in water and in chloride-rich solution) and in room conditions. An AI-based forecasting approach using Prophet is proposed, ingesting electrical impedance and temperature data, and tested to predict electrical impedance corresponding to approximately 10 % of the time series balancing responsiveness with predictive accuracy, crucial for effective EWS operations and management requirements. The performance of the tested models is evaluated employing metrics such as Mean Average Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and correlation. The proposed approach surpasses statistical methods and deep learning techniques, reporting a MAPE always lower than 3.20 % and a correlation higher than 81.65 % (in wet-dry cycles in water these values are 0.65 Ω and 91.85 %, respectively). This proves to be a promising step towards transparent SHM, which integrates AI models facilitating self-monitoring and early maintenance prediction, thus enhancing the resilience of the built environment.