Damage degree evaluation of masonry using optimized SVM-based acoustic emission monitoring and rate process theory

Abstract

Evaluation of masonry damage is considerably challenging because of the non-homogeneous nature of masonry materials and the rapid attenuation of signals. To this end, a methodology combining qualitative analysis employing support vector machine-based acoustic emission (AE) monitoring and quantitative analysis using AE rate process theory was proposed. In this work, firstly, the propagation attenuation characteristics of the AE amplitude and frequency were studied using pencil-lead break tests. The hybrid PSO-SVM model was employed to automatically identify the damage stages of the AE signals based on the field in-situ axial compression test data. Then, laboratory compression and shear tests on small-scale specimens were performed with AE monitoring. The Boltzmann sigmoidal modified function between relative stress and AE hits was established. Based on qualitative and quantitative analysis, a damage index-based early warning range was proposed, which can help to decide the damage level of masonry structures. The results of this paper can provide some new insight for the analysis of masonry damage.