Analyzing Coating Conditions of Steel Bridges at Florida: A Data-Driven Approach

Abstract

Even with the continuous development of coating technologies, coating systems are susceptible to corrosion-induced premature failures and unable to meet the anticipated service life. Coating premature failures will negatively impact the safety, integrity, and longevity of steel bridge structural elements. The advancement of the data analytics approach (e.g., machine learning) offers an opportunity to leverage the wealth of historical bridge inspection and maintenance data collected by Departments of Transportation to evaluate coating conditions of steel bridges effectively and efficiently. This paper focuses on presenting a data-driven study that analyzes the conditions of coating systems of steel bridges in the state of Florida. Three machine learning algorithms were used in developing models that can be used to analyze steel bridge coating conditions based on data collected from the Bridge Management System of the Florida Department of Transportation. The result showed that the machine learning–based models were able to effectively predict steel bridge coating conditions. The k-nearest neighbor (KNN) regression algorithm offered the best performance. Although the approach was currently applied to the steel bridges of Florida, it can be easily replicable for similar data sets from other states. The research contributes to the body of knowledge by offering a data-driven understanding of coating performance of steel bridge elements. The research has the potential to offer a valuable decision-making tool for transportation agencies to effectively and easily analyze or predict steel bridge coating conditions.