Experimental testing and predictive machine learning to determine the mechanical characteristics of corroded reinforcing steel

Chloride-induced deterioration of reinforcing steel bars has become a densely researched topic over the past several decades because of the severe ramifications to the structural reliability of aging infrastructure. The ever-growing volume of experimental and field data continually enables advances in the field through deeper micro-macro analyses and various modeling applications. The purpose of this paper is twofold. First, an experimental program is introduced, describing the tensile testing of 284 artificially corroded, 25 mm diameter deformed Grade500E reinforcing bars. Secondly, the mechanical characteristics of corroded bars are predicted through a collection of regression-based machine learning algorithms. Models are trained and tested on a database of 1387 tensile tests compiled from 25 other experimental programs available in the literature. The complete database includes 19 input parameters used to predict nine key mechanical properties of the corroded steel bars. Nine machine learning models were selected from a balanced assortment of algorithm typologies to determine the most appropriate methodology for each response variable. The adaptive-neuro fuzzy inference system (ANFIS) model was found to have the strongest individual predictive ability across all models. Meanwhile, ensemble tree-based learning algorithms categorically provided the most consistently high-performing models over the selected response variables.