Data-Driven Evaluation of Bearing Capacity for In-Service Pile Foundations Using Dynamic Stiffness and Machine Learning

In the assessment of bearing capacity for in-service bridge pile foundations, static load tests are costly, destructive, and difficult to scale. The traditional dynamic formula approach relies heavily on an empirical dynamic–static conversion coefficient that introduces considerable uncertainty. To address these limitations, this study proposes a non-destructive evaluation method for pile foundation bearing capacity based on measured dynamic stiffness and machine learning algorithms. Using data from a highway bridge inspection project, a dataset comprising 680 piles was compiled, including measured dynamic stiffness, geometric parameters, and design load information. An end-to-end binary classification model was constructed to map multidimensional physical features to an engineering decision target, namely, whether the bearing capacity meets the design requirement. The performance of several algorithms was compared, including logistic regression, random forest, and gradient boosting decision tree (GBDT). Among the evaluated models, the GBDT model demonstrated the best capability for capturing the complex nonlinear pile–soil interactions. On an independent test set, it achieved an accuracy of 96.3% and an F1 score of 0.96, with a very low false-negative rate, satisfying the high precision required for engineering safety screening. Feature importance analysis indicates that measured dynamic stiffness contributed approximately 42% to the classification outcome, establishing it as the dominant indicator for detecting capacity deficiencies and reinforcing its physical relevance as a key health indicator for pile foundations. This study demonstrates that data-driven methods can effectively circumvent the uncertainty associated with traditional empirical coefficients, providing a promising approach to the health monitoring and rapid evaluation of in-service bridge pile foundations.