Impedance-based structural health monitoring using neural networks for autonomousfrequency range selection

Abstract

The impedance-based structural health monitoring (SHM) method has come to theforefront in the SHM community due to its practical potential for real applications. In theimpedance-based SHM method, the selection of optimal frequency ranges plays animportant role in improving the sensitivity of damage detection, since an improperfrequency range can lead to erroneous damage detection results and provide false positivedamage alarms. To tackle this issue, this paper proposes an innovative technique forautonomous selection of damage-sensitive frequency ranges using artificial neural networks(ANNs). First, the impedance signals are obtained in a wide frequency band, and thesignals are split into multiple sub-ranges of this wide band. Then, the predefined damageindex is evaluated for each sub-range by comparing impedance signals between the intactand the concurrent cases. Here, the cross correlation coefficients (CCs) are used as thepredefined damage index. The ANN is constructed and trained using all CC valuesat multiple frequency ranges as multi-inputs and the real damage severity asthe single output for various preselected damage scenarios, so that subsequentdamage estimations may be carried out by selecting the governing frequency rangesautonomously. The performance of the proposed approach has been examinedvia a series of experimental studies to detect loose bolts and cracks induced onreal steel bridge and building structures. It is found that the proposed approachautonomously determines the damage-sensitive frequency ranges and can be used foreffective evaluation of damage severity in a wide variety of damage cases in realstructures.