Key points are not available for this paper at this time.
Corrosion, particularly pitting corrosion, represents a prominent form of deterioration in large infrastructure, characterized by its gradual and continuous capacity-reducing nature. As structures age, the need for assessing and monitoring corrosion status becomes increasingly crucial for system life-cycle management and optimal maintenance. However, the intricacies of the corrosion process pose challenges to effective diagnosis and prognosis. These challenges include the insufficient integration of mechanical stress into existing corrosion simulations, the computational intensity of most physics-based corrosion simulations hindering probabilistic studies and real-time predictions, and the difficulty in detecting pitting corrosion due to its localized nature, making it impractical to measure individual pits. This paper introduces a comprehensive prognosis and diagnosis framework applied to a miter gate case study. The framework seamlessly integrates multi-scale simulation, including mesoscale Phase-Field (PF) simulation and macroscale structural analysis, with Machine Learning (ML) methods to enable real-time corrosion diagnosis and prognosis. It facilitates efficient structural health monitoring (SHM) through a digital twin (DT) for corrosion damage. The core components of this framework encompass the development of multiscale simulation for simulating pitting corrosion in large structures, the construction of ML-based surrogate models to expedite simulations, image-based diagnosis, and the updating engine for prognosis.
Qian et al. (Sat,) studied this question.