Promptly assessing probability of barge–bridge collision damage of piers through probabilistic-based classification of machine learning

This paper presents a novel probabilistic classification framework for promptly assessing the probability of barge–bridge collision damage of piers based on Bayesian inference with Transitional Markov Chain Monte Carlo simulations. The main idea is to divide the potential damage region into multiple discrete sub-regions and train a probabilistic classifier for each sub-region using data from a set of computationally simulated events or real events or combination of both. The novelty of the presented framework includes: (1) intensive computation of dynamic responses of a structure at different damage scenarios is conducted prior to collision events to generate data for training the probabilistic classifiers; (2) the optimal threshold for reliably triggering damage alarm is determined historically based on all previously known events in the training dataset; (3) uncertainties of the classification model and extracted dynamic features are considered based on the Bayesian model selection and the rate of correction classification and quantified into the probabilities of damage occurrence in different sub-regions. Furthermore, the presented framework can be implemented recursively with different levels of hierarchical divisions of sub-regions to more precisely locate damage in a structure. The applicability of the presented framework is demonstrated through the numerical simulation of identifying barge–bridge collision damage locations in one pier of a prototype bridge. Finally, limitations and future research directions are also discussed.