In recent years ultrasonic-guided waves (UGWs) have been successfully employed in structural health monitoring (SHM) for damage localization due to their high sensitivity to changes in the mechanical properties of the medium they travel through. Lamb waves (LW) are a particular type of UGW that can be generated by piezoelectric transducers placed on thin-walled structures, such as vehicles in general (terrestrial, naval, and aeronautical), and present characteristics that are favorable to SHM. Damage localization using LWs has been commonly accomplished through tomographic algorithms. However, these methods have unresolved issues such as artifacts generation in damage probability maps and a strong reliance on sensor network configuration for signal acquisition. As a solution, data-driven approaches based on supervised machine learning have been suggested. These methods have demonstrated good performance. However, for reliable results, they require large, labeled datasets, meaning that acquisitions must be performed before and after the structure is damaged. These datasets, especially data from the damaged state, are generally not available for real-life structures, given the cost and complexity to experimentally replicate certain damages. Unsupervised machine learning methods might be a solution to this problem, given that the neural network is trained using data acquired from the un-damaged structure only. To this date, no fully unsupervised damage localization frameworks have been proposed. Hence, in this work, two unsupervised data-driven methods are presented to process LWs to localize damage. Specifically, convolutional auto-associative neural networks (CAANNs) and generative adversarial networks (GANs). Both methods process diagnostic signals without requiring any prior feature extraction. After all signals are processed, a damage probability map is generated. The performance of both methods is tested using an experimental dataset of LW acquisitions using a set of piezoelectric transducers on a full-scale composite wing. Results showed that the proposed methods have good damage localization accuracy.
Damage Localization Frameworks Based on Unsupervised Deep Learning Neural Networks
Junges R.;Lomazzi L.;Giglio M.;Cadini F.
2023-01-01
Abstract
In recent years ultrasonic-guided waves (UGWs) have been successfully employed in structural health monitoring (SHM) for damage localization due to their high sensitivity to changes in the mechanical properties of the medium they travel through. Lamb waves (LW) are a particular type of UGW that can be generated by piezoelectric transducers placed on thin-walled structures, such as vehicles in general (terrestrial, naval, and aeronautical), and present characteristics that are favorable to SHM. Damage localization using LWs has been commonly accomplished through tomographic algorithms. However, these methods have unresolved issues such as artifacts generation in damage probability maps and a strong reliance on sensor network configuration for signal acquisition. As a solution, data-driven approaches based on supervised machine learning have been suggested. These methods have demonstrated good performance. However, for reliable results, they require large, labeled datasets, meaning that acquisitions must be performed before and after the structure is damaged. These datasets, especially data from the damaged state, are generally not available for real-life structures, given the cost and complexity to experimentally replicate certain damages. Unsupervised machine learning methods might be a solution to this problem, given that the neural network is trained using data acquired from the un-damaged structure only. To this date, no fully unsupervised damage localization frameworks have been proposed. Hence, in this work, two unsupervised data-driven methods are presented to process LWs to localize damage. Specifically, convolutional auto-associative neural networks (CAANNs) and generative adversarial networks (GANs). Both methods process diagnostic signals without requiring any prior feature extraction. After all signals are processed, a damage probability map is generated. The performance of both methods is tested using an experimental dataset of LW acquisitions using a set of piezoelectric transducers on a full-scale composite wing. Results showed that the proposed methods have good damage localization accuracy.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.