Pitting Degradation Modeling of Ocean Steel Structures Using Bayesian Network

Abstract

Modeling depth of long-term pitting corrosion is of interest for engineers in predicting the structural longevity of ocean infrastructures. Conventional models demonstrate poor quality in predicting the long-term pitting corrosion depth. Recently developed phenomenological models provide a strong understanding of the pitting process; however, they have limited engineering applications. In this study, a novel probabilistic model is developed for predicting the long-term pitting corrosion depth of steel structures in marine environment using Bayesian network (BN). The proposed BN model combines an understanding of corrosion phenomenological model and empirical model calibrated using real-world data. A case study, which exemplifies the application of methodology to predict the pit depth of structural steel in long-term marine environment, is presented. The result shows that the proposed methodology succeeds in predicting the time-dependent, long-term anaerobic pitting corrosion depth of structural steel in different environmental and operational conditions.

An overview of maintenance management strategies for corroded steel structures in extreme marine environments

“…Then the long-term corrosion takes place, which is led by biological activities and nutrients in seawater [117]. Some researchers have shown that the duration of short-term and long-term corrosions depends on the constituents of seawater (biological and chemical) and its physical properties, temperature in particular [118].…”

“…The standard fluctuation of pH in seawaters lies between 7.8 and 8.2 and it has been reported by several researchers that this variation does not have significant impact on corrosion rate. However, it can indirectly influence accumulation of calcium carbonate on cathode protected structures [118,144]. The pH variations may exert an active influence on pitting and crevice corrosion of active-passive metals [145].…”

“…These methods have been instrumental to develop the relations between various dependent/independent process variables and estimate the likelihood of occurrence of events. The statistical/stochastic techniques that are commonly adopted by researchers include: multivariate analysis, regression models, Copulas, Markov process, Poisson process, Monte-Carlo simulation, Cox's approximation, and Weibull analysis [35,56,118,217]. Detailed deliberation on the maintenance procedures, their planning, inspection and prediction trends using various statistical models and methodologies are explained in details in [33,66,[218][219][220].…”

Machine Learning and Digital Twin Driven Diagnostics and Prognostics of Light‐Emitting Diodes

“…[ 218,219 ] Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high‐speed trains, [ 219 ] solar‐powered unmanned aerial vehicles, [ 220 ] and pitting degradation structural steel in marine systems. [ 221 ]…”

“…[218,219] Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains, [219] solar-powered unmanned aerial vehicles, [220] and pitting degradation structural steel in marine systems. [221] In this section, a BN method that considers the intricacies of the high-power LED lamp system and the functional interaction among components for reliability assessment and lifetime prediction is briefly introduced. This approach considers the parametric (degradation based) and catastrophic failure modes of each component in order to assess the system level reliability, and it also requires the design of experiments to gather the required data.…”