Applying Fuzzy Decision-Making and Markov Chain Modelling for Detecting Life Cycle of RC Bridges

Artificial Intelligence (AI) has recently played a crucial role in improving bridge assessment through diverse methodologies to optimize maintenance strategies and reduce costs. Therefore, the current study proposed two different methods to estimate the current condition rating of R.C. bridges by 1) Fuzzy Decision-Making; and 2) Markov Chain Modelling. The purpose of this study is to investigate the more applicable and accurate technique due to AI for reinforced concrete bridge assessment. The current study focused on corrosion as the main defect used to estimate the bridge condition rating. The dual methods depend on visual inspection, applying field and laboratory tests, and reviewing the historical data of the inspected bridge to estimate its condition rating. The fuzzy decision model is applied to find a correlation between corrosion degree and concrete surface condition to estimate the condition rating. The Markov chain model is used to predict the future condition rating for the whole bridge and when it will reach the critical condition. The service life for each bridge element is calculated due to carbonation and chloride attack. The Life 365 model is applied to estimate the service life due to chloride ingress. The proposed system is validated through a real case study, and the results show that the fuzzy is less accurate compared to the Markov Chain. The introduced models are expected to provide proper Maintenance, Repair, and Replacement (MRR) decisions for the bridges.