Abstract
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.
Highlights
The present time is without doubt the most appropriate for the development of robust and reliable structural damage detection systems as ageing civil engineering structures, such as bridges, are being used past their life expectancy and well beyond their original design loads
As civil engineering structures are growing in dimension and longevity, there is an associated increase in concern regarding the maintenance of such structures
49 input neurons: the number of neurons equals the number of features, which are the 30 accelerations antÀi registered by the 6 sensors n 2 f1; . . .; 6g in the last 5 samplings i 2 f1; . . .; 5g, the 18 axle loads and 1 axle position relative to a reference point;
Summary
The present time is without doubt the most appropriate for the development of robust and reliable structural damage detection systems as ageing civil engineering structures, such as bridges, are being used past their life expectancy and well beyond their original design loads. One can mention as disadvantages the fact that the technique may not be practicable if the structure has restricted accessibility or if the traffic is excessively disturbed, its application is time-discrete and the conclusion of the visual inspection is inevitably subjective In this sense, effort was placed in developing damage detection techniques that handle measurement data to find structural changes [10]. Structural properties like damping, modal shapes and frequencies are not directly measurable, they can be inferred from other measured data These properties have somewhat clear definitions and allow the relatively easy design of algorithms that define them, being good candidates for parameters of a damage detection technique
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
