Physics-trained artificial intelligence framework to detect chloride induced degradation in concrete

Abstract

Numerous critical infrastructures in the United States, including bridges, dams, and nuclear plants, are aging and prone to concrete degradation, compromising their performance and structural integrity. One of the leading causes of degradation is chloride-induced corrosion, where chloride ions diffuse into the concrete, leading to reinforcement corrosion, spalling, and cracking. Detecting chloride degradation at an early stage is crucial for ensuring the safety of these vital structures. However, the visible signs of degradation, such as spalling and cracking, often appear only after significant damage has occurred. Degradation occurs gradually over many years, making it impractical to collect real-time non-destructive testing (NDT) data over extended periods while allowing the structure to continue deteriorating. To overcome this challenge, an integrated structural health monitoring framework is proposed that combines advanced finite element modeling, sensor data, and deep learning techniques. This framework follows a multi-step approach to simulate chloride degradation over the service life of the structure. Subsequently, finite element analyses are performed to numerically simulate non-destructive testing at various stages of degradation to generate corresponding sensor data. By leveraging these simulated data and insights, a physics-driven artificial intelligence framework is developed. The proposed framework offers a state-of-the-art solution to mitigate the challenges associated with long-term degradation monitoring by utilizing high-fidelity simulations and data-driven techniques to achieve detection of chloride-induced concrete damage.