As civil engineering structures are growing in dimension and longevity, there is an associated increase in concern regarding the maintenance of such structures. Bridges, in particular, are critical links in today's transportation networks and hence fundamental for the development of society. In this context, the demand for novel damage detection techniques and reliable structural health monitoring systems is currently high. This paper presents a model-free damage detection approach based on machine learning techniques. The method is applied to data on the structural condition of a fictitious railway bridge gathered in a numerical experiment using a three-dimensional finite element model. Data are collected from the dynamic response of the structure, which is simulated in the course of the passage of a train, considering the bridge in healthy and two different damaged scenarios. In the first stage of the proposed method, artificial neural networks are trained with an unsupervised learning approach with input data composed of accelerations gathered on the healthy bridge. Based on the acceleration values at previous instants in time, the networks are able to predict future accelerations. In the second stage, the prediction errors of each network are statistically characterized by a Gaussian process that supports the choice of a damage detection threshold. Subsequent to this, by comparing damage indices with said threshold, it is possible to discriminate between different structural conditions, namely between healthy and damaged. From here and for each damage case scenario, receiver operating characteristic curves that illustrate the trade-off between true and false positives can be obtained. Lastly, based on the Bayes' Theorem, a simplified method for the calculation of the expected total cost of the proposed strategy, as a function of the chosen threshold, is suggested.
Adverse situations such as prolonged downtime of a structure, unnecessary inspections, expensive allocation of personal and equipment, deficient structural performance, or failure can be avoided by using structural health monitoring (SHM). Enhanced structural safety is the leading reason for its implementation, but one of the remaining obstacles to fully implement SHM systems deals with justifying their economic benefit. At any point in time, the preference towards one particular action depends on factors such as the probability of the triggered events and their consequences. All the possible decisions and relevant information can be illustrated by decision tree models, and the optimal decision corresponds to the one with the highest utility. Applying the Bayesian Theorem, the assumed prior probabilities of the structural state are updated in the light of new information provided by a system and the optimal decision is revised. This paper proposes a dynamic decisionmaking framework to manage civil engineering structures, where the ultimate goal is to achieve greater overall economy without jeopardizing safety. This paper covers a case study of a bridge where the optimal SHM and maintenance decisions are determined in the context of different scenarios in which the event probabilities and associated costs are made-up.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.