This paper introduces two deep learning approaches to localize acoustic emissions (AE) sources within metallic plates with geometric features, such as rivet-connected stiffeners. In particular, a stack of autoencoders and a convolutional neural network are used. The idea is to leverage the reflection and reverberation patterns of AE waveforms as well as their dispersive and multimodal characteristics to localize their sources with only one sensor. Specifically, this paper divides the structure into multiple zones and finds the zone in which each source occurs. To train, validate, and test the deep learning networks, fatigue cracks were experimentally simulated by Hsu–Nielsen pencil lead break tests. The pencil lead breaks were carried out on the surface and at the edges of the plate. The results show that both deep learning networks can learn to map AE signals to their sources. These results demonstrate that the reverberation patterns of AE sources contain pertinent information to the location of their sources.

Conventionally, the assessment of reinforced concrete shear walls relies on manual visual assessment which is time-consuming and depends heavily on the skills of the inspectors. The development of automated assessment employing flying and crawling robots equipped with high-resolution cameras and wireless communications to acquire digital images and advance image processing to extract crack patterns has paved the path toward implementing an automated system which determines structural damage based on visual signals acquired from structures. Since there are few, if any, studies to correlate crack patterns to structural integrity, this article proposes to analyze crack patterns using a multifractal analysis. The approach is initially tested on synthetic crack patterns, and then it is applied to a set of experimental data collected during the testing of two large-scale reinforced concrete shear wall subjected to controlled reversed cyclic loading. The structural response data available for each specimen are used to link the multifractal parameters with the structural performance of the two specimens. A relationship between the multifractal parameters and the crack patterns’ evolution and mechanism is noted. The results show that as the crack patterns extend and grow, multifractal parameters move toward higher values. The parameters jump as the mechanical response shows severe stiffness loss. In this study, no attempt is made to automate the process of mapping cracks from images.

This paper presents a model-based guided ultrasonic waves imaging algorithm, in which multiple ultrasonic echoes caused by reflections from the plate’s boundaries are leveraged to enhance imaging performance. An analytical model is proposed to estimate the envelope of scattered waves. Correlation between the estimated and experimental data is used to generate images. The proposed method is validated through experimental tests on an aluminum plate instrumented with three low profile piezoelectric transducers. Different damage conditions are simulated including through-thickness holes. Results are compared with two other imaging localization methods, that is, delay and sum and minimum variance.

The geometric properties and spatial characteristics of crack patterns are significant indicators of the extent of damage on reinforced concrete structures. However, manual visual assessment is subjective and depends highly on the inspector's skills. The current study proposes an automated approach for the quantification of digitally documented crack patterns on reinforced concrete shell elements subjected to reversed cyclic shear loading. Multifractal analysis is proposed as a feature extractor for images depicting crack patterns and a set of artificial cracks is analyzed, to quantify how the properties of crack patterns vary as a function of cracking inclination. The results of the parametric study motivated the training of a multiclass classification model, which is used to provide damage level estimates for cracked reinforced concrete members. The training of the classifier is performed using experimental data of reinforced concrete shell elements under well‐defined and idealized two‐dimensional pure shear stress loading conditions. A dataset with 119 images from crack patterns of reinforced concrete shells is used for training. The multifractal features successfully translate the shape of the crack patterns into meaningful information about the extent of damage; achieving an overall test accuracy of 89.3%.