Vibration-based multiclass damage detection and localization using long short-term memory networks

Sony, Sandeep; Gamage, Sunanda; Sadhu, Ayan; Samarabandu, Jagath

doi:10.1016/j.istruc.2021.10.088

Cited by 55 publications

(17 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A unique feature vector is then extracted through the overlapped windowing of the data resulting in a large number of statistical features (442 in total). A similar approach is taken in [17], [33], [34] where it is expected that windowing data in this manner will allow LSTM to learn temporal dependencies between windows that provide complete information at a given time, in the case of gait identification information regarding a complete gait cycle is provided by a window.…”

Section: Methodsmentioning

confidence: 99%

Gait Identification Using Limb Joint Movement and Deep Machine Learning

et al. 2022

View full text Add to dashboard Cite

Person identification is a key problem in the security domain and may be used to automatically identify criminals or missing persons. The traditional face matching approaches adopted by the police and security services across the world have recently been shown to produce a high rate of false positive identification. Alternatively, gait-based person identification has shown to be a convenient method particularly as it can be performed at a distance, without the cooperation of the subject, and is a biometric trait which cannot be easily disguised. In this work, we propose a gait-based person identification approach which uses limb joint motion data and deep machine learning models to identify the individuals. Distinct statistical features are identified and extracted from limb movement using a fixed width sliding window to train a Long Short-Term Memory model. The proposed solution outperforms the existing methods producing 98.87% accuracy when evaluated over unseen samples. In addition, we propose a simple two-stage filtering approach to increase the prediction accuracy up to 100% when identifying individuals from larger sequences of samples. This finding may improve the current solutions in controlled environments such as airports. In the future, this approach may help to overcome the problem of occlusion in gait-based identification, as unlike the existing works, it does not require information regarding the entire body. The study also presents a primary dataset comprising limb joint movement acquired from a diverse range of participants during casual walking captured through two digital goniometers.

show abstract

Section: Methodsmentioning

confidence: 99%

Gait Identification Using Limb Joint Movement and Deep Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A semi‐supervised fault diagnosis approach called hybrid classification autoencoder to minimize the fault diagnostic method's reliance on labeled data and make full use of the more plentiful unlabeled data was proposed by Wu et al (2021). Using a windowed LSTM network, Sony et al (2022) introduced a unique civil structure damage detection and localization approach. In an unique data preprocessing pipeline, a sequence of windowed samples is retrieved from acceleration responses, and an LSTM network is created to categorize the signals into several classes.…”

Section: Applications Of ML In Solving Dynamical Problemsmentioning

confidence: 99%

Machine intelligence in dynamical systems: \A state‐of‐art review

Sahoo

Chakraverty

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

This article is dedicated to study the impact of machine intelligence (MI) methods viz. various types of Neural models for investigating dynamical systems arising in interdisciplinary areas. Different types of artificial neural network (ANN) methods, viz., recurrent neural network, functional‐link neural network, convolutional neural network, symplectic artificial neural network, genetic algorithm neural network, and so on, are addressed by different researchers to investigate these problems. Although various traditional methods have been developed by researchers to solve these dynamical problems but the existing traditional methods may sometimes be problem dependent, require repetitions of the simulations, and fail to solve nonlinearity behavior. In this regard, neural network model based methods are more general and solutions are continuous over the given domain of integration, self‐adaptive and can be used as a black box. As such, in this article, we have reviewed and analyzed different MI methods, which are applied to investigate these problems. This article is categorized under: Technologies > Computational Intelligence Technologies > Machine Learning Application Areas > Science and Technology

show abstract

“…The adoption of reliable and rigorous monitoring systems is fundamental to reducing maintenance costs and at the same time extending the service life of the existing structures. In particular, to properly define the health state of existing structures, many techniques for identifying and locating damage have been developed in literature [ 9 , 10 ]. The acoustic emission (AE) techniques are widely adopted among the monitoring methods because they are non-destructive techniques that allow the passive monitoring of structures [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Acoustic Emission and Artificial Intelligence Procedure for Crack Source Localization

Melchiorre

Bertetto

Rosso

et al. 2023

Sensors

View full text Add to dashboard Cite

The acoustic emission (AE) technique is one of the most widely used in the field of structural monitoring. Its popularity mainly stems from the fact that it belongs to the category of non-destructive techniques (NDT) and allows the passive monitoring of structures. The technique employs piezoelectric sensors to measure the elastic ultrasonic wave that propagates in the material as a result of the crack formation’s abrupt release of energy. The recorded signal can be investigated to obtain information about the source crack, its position, and its typology (Mode I, Mode II). Over the years, many techniques have been developed for the localization, characterization, and quantification of damage from the study of acoustic emission. The onset time of the signal is an essential information item to be derived from waveform analysis. This information combined with the use of the triangulation technique allows for the identification of the crack location. In the literature, it is possible to find many methods to identify, with increasing accuracy, the onset time of the P-wave. Indeed, the precision of the onset time detection affects the accuracy of identifying the location of the crack. In this paper, two techniques for the definition of the onset time of acoustic emission signals are presented. The first method is based on the Akaike Information Criterion (AIC) while the second one relies on the use of artificial intelligence (AI). A recurrent convolutional neural network (R-CNN) designed for sound event detection (SED) is trained on three different datasets composed of seismic signals and acoustic emission signals to be tested on a real-world acoustic emission dataset. The new method allows taking advantage of the similarities between acoustic emissions, seismic signals, and sound signals, enhancing the accuracy in determining the onset time.

show abstract

Vibration-based multiclass damage detection and localization using long short-term memory networks

Cited by 55 publications

References 40 publications

Gait Identification Using Limb Joint Movement and Deep Machine Learning

Gait Identification Using Limb Joint Movement and Deep Machine Learning

Machine intelligence in dynamical systems: \A state‐of‐art review

Acoustic Emission and Artificial Intelligence Procedure for Crack Source Localization

Contact Info

Product

Resources

About