Development of a Near-Neutral pH Stress Corrosion Cracking Growth Model for Pipelines Using Machine Learning Algorithms

Near-neutral pH stress corrosion cracking (NNpHSCC) is one of the leading causes of failure for buried pipelines. Characterizing the NNpHSCC growth rate accurately remains a challenging task for the pipeline industry. In this study, an NNpHSCC growth model for buried pipelines is developed based on experimental data obtained from full-scale tests conducted at the CanmetMATERIALS of Natural Resources Canada of pipe specimens that are in contact with near-neutral pH environment and subjected to cyclic internal pressures. Four machine learning algorithms, namely the random forest (RF), extremely randomized trees (ET), gradient boosting (GB) and extreme gradient boosting (XGB), are employed to estimate the crack growth rates da/dN from input variables characterizing the pipe geometry, internal pressure and environmental condition. The machine learning models are trained through hyperparameter tuning and k-fold cross validation to improve the model robustness. Model performances are validated and compared using an independent test dataset. This study provides an initial step in using machine learning tools to develop robust NNpHSCC growth models suitable for practical applications.