Abstract:The implementation of efficient maintenance strategies of thin-walled structural components require reliable damage detection and localization techniques. In particular, guided ultrasonic waves technology represent an auspicious approach when implemented in a structural health monitoring system. The method is usually based on distributed sensing with piezoelectric elements that act in turn as ultrasound transmitter and receiver. This work aims at a unifying framework for damage localization considering algorit… Show more
“…Sample neural networks, like MLP, convolutional neural network, and recurrent neural network, only contain an input layer, some hidden layers, and an output layer. They are good at solving the problems of “one-to-one” or “many-to-one”, such as damage detection, 34,35 strength prediction, 36 and health monitoring, 37,38 but it is difficult for them to handle the problems of “one-to-many”, namely, one input corresponding to many labels or outputs. Design is a typical “one-to-many” problem where one target corresponds to multiple designed results.…”
This study presents an approach based on deep learning to design layered periodic wave barriers with consideration of typical range of soil parameters. Three cases are considered where P wave and S wave exist separately or simultaneously. The deep learning model is composed of an autoencoder with a pretrained decoder which has three branches to output frequency attenuation domains for three different cases. A periodic activation function is used to improve the design accuracy, and condition variables are applied in the code layer of the autoencoder to meet the requirements of practical multi working conditions. Forty thousand sets of data are generated to train, validate, and test the model, and the designed results are highly consistent with the targets. The presented approach has great generality, feasibility, rapidity, and accuracy on designing layered periodic wave barriers which exhibit good performance in wave suppression in targeted frequency range.
“…Sample neural networks, like MLP, convolutional neural network, and recurrent neural network, only contain an input layer, some hidden layers, and an output layer. They are good at solving the problems of “one-to-one” or “many-to-one”, such as damage detection, 34,35 strength prediction, 36 and health monitoring, 37,38 but it is difficult for them to handle the problems of “one-to-many”, namely, one input corresponding to many labels or outputs. Design is a typical “one-to-many” problem where one target corresponds to multiple designed results.…”
This study presents an approach based on deep learning to design layered periodic wave barriers with consideration of typical range of soil parameters. Three cases are considered where P wave and S wave exist separately or simultaneously. The deep learning model is composed of an autoencoder with a pretrained decoder which has three branches to output frequency attenuation domains for three different cases. A periodic activation function is used to improve the design accuracy, and condition variables are applied in the code layer of the autoencoder to meet the requirements of practical multi working conditions. Forty thousand sets of data are generated to train, validate, and test the model, and the designed results are highly consistent with the targets. The presented approach has great generality, feasibility, rapidity, and accuracy on designing layered periodic wave barriers which exhibit good performance in wave suppression in targeted frequency range.
“…They actively induce a forced local excitation in order to inspect a particular region of a structure. Studies using active piezoelectric elements include the EMI spectroscopy of grouted connections which are widely seen in offshore structures (Moll, 2019), sensor fault detection using the EMI method (Mueller and Fritzen, 2017), EMI-based sensing of bones in medical settings (Moll et al, 2019a; Srivastava et al, 2017) as well as GEW-based identification of delaminations in composites (Migot et al, 2021), multi-site damage imaging with GEW (Neubeck et al, 2020) or GEW-based defect localization including size assessment (Memmolo et al, 2018).…”
Active piezoelectric transducers are successfully deployed in recent years for structural health monitoring using guided elastic waves or electro-mechanical impedance (EMI). In both domains, damage detection can be hampered by operational/environmental conditions and low-power constraints. In both domains, processing can be divided into approaches (i) taking into account baselines of the pristine structure as reference, (ii) ingesting an extensive measurement history for clustering to explore anomalies, (iii) incorporating additional information to label a state. The latter approach requires data from complementary sensors, learning from laboratory/field experiments or knowledge from simulations which may be infeasible for complex structures. Semi-supervised approaches are thus gaining popularity: few initial annotations are needed, because labels emerge through clustering and are subsequently used for state classification. In our work, bending and combined bending/torsion studies on rudder stocks are considered regarding EMI-based damage detection in the presence of load. We discuss the underpinnings of our processing. Then, we follow strategy (i) by introducing frequency warping to derive an improved damage indicator (DI). Finally, in a semi-supervised manner, we develop simple rules which even in presence of varying loads need only two frequency points for reliable damage detection. This sparsity-enforcing low-complexity approach is particularly beneficial in energy-aware SHM scenarios.
“…Structural health monitoring (SHM) has been considered a revolutionary technology for the operation and maintenance of aircraft structures [ 1 ]. At present, some SHM technologies, such as acoustic emission [ 2 , 3 ], eddy current [ 4 , 5 , 6 ], Lamb wave [ 7 , 8 ], impedance [ 9 , 10 ], vibration [ 11 , 12 ], and comparative vacuum [ 13 ] monitoring, have received greatly focused research and development for damage detection in aircraft structures. Lamb wave-based damage imaging, which is an active detection technology suitable for large-scale structures, is a promising technology for the health monitoring of aircraft plate structures [ 14 , 15 ].…”
Lamb wave-based damage imaging is a promising technique for aircraft structural health monitoring, as enhancing the resolution of damage detection is a persistent challenge. In this paper, a damage imaging technique based on the Time Reversal-MUltiple SIgnal Classification (TR-MUSIC) algorithm is developed to detect damage in plate-type structures. In the TR-MUSIC algorithm, a transfer matrix is first established by exciting and sensing signals. A TR operator is constructed for eigenvalue decomposition to divide the data space into signal and noise subspaces. The structural space spectrum of the algorithm is calculated based on the orthogonality of the two subspaces. A local TR-MUSIC algorithm is proposed to enhance the image quality of multiple damages by using a moving time window to establish the local space spectrum at different times or different distances. The multidamage detection capability of the proposed enhanced TR-MUSIC algorithm is verified by simulations and experiments. The results reveal that the local TR-MUSIC algorithm can not only effectively detect multiple damages in plate-type structures with good image quality but also has a superresolution ability for detecting damage with distances smaller than half the wavelength.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.