Comparative Analysis of Wavelet Transform for Time-Frequency Analysis and Transient Localization in Structural Health Monitoring

Silik, Ahmed; Noori, Mohammad; Altabey, Wael A.; Ghiasi, Ramin; Wu, Zhishen

doi:10.32604/sdhm.2021.012751

Cited by 60 publications

(44 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The analytic Morse wavelet with the default values of the symmetry parameter and time-bandwidth product was used in the filter bank [62][63][64]. More details on the parametric study of the effect of the parameters of wavelet transform can be found in the references [65][66][67]. The filter bank was used to transform all the time series from the simulation models to scalograms.…”

Section: Deep Learning Model For Simulation Datamentioning

confidence: 99%

Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer

Khan

Kim

2021

Mathematics

View full text Add to dashboard Cite

A simulation model can provide insight into the characteristic behaviors of different health states of an actual system; however, such a simulation cannot account for all complexities in the system. This work proposes a transfer learning strategy that employs simple computer simulations for fault diagnosis in an actual system. A simple shaft-disk system was used to generate a substantial set of source data for three health states of a rotor system, and that data was used to train, validate, and test a customized deep neural network. The deep learning model, pretrained on simulation data, was used as a domain and class invariant generalized feature extractor, and the extracted features were processed with traditional machine learning algorithms. The experimental data sets of an RK4 rotor kit and a machinery fault simulator (MFS) were employed to assess the effectiveness of the proposed approach. The proposed method was also validated by comparing its performance with the pre-existing deep learning models of GoogleNet, VGG16, ResNet18, AlexNet, and SqueezeNet in terms of feature extraction, generalizability, computational cost, and size and parameters of the networks.

show abstract

Section: Deep Learning Model For Simulation Datamentioning

confidence: 99%

Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer

Khan

Kim

2021

Mathematics

View full text Add to dashboard Cite

show abstract

“…Over the past few decades, vibration-based methods have been developed for structural damage identification [ 17 , 18 , 19 , 20 , 21 , 22 , 23 ]. The underlying idea behind these methods comes from the fact that modal parameters are linked to physical parameters of the structure.…”

Section: Introductionmentioning

confidence: 99%

Visible Particle Series Search Algorithm and Its Application in Structural Damage Identification

Mohebian

Aval

Noori

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Identifying structural damage is an essential task for ensuring the safety and functionality of civil, mechanical, and aerospace structures. In this study, the structural damage identification scheme is formulated as an optimization problem, and a new meta-heuristic optimization algorithm, called visible particle series search (VPSS), is proposed to tackle that. The proposed VPSS algorithm is inspired by the visibility graph technique, which is a technique used basically to convert a time series into a graph network. In the proposed VPSS algorithm, the population of candidate solutions is regarded as a particle series and is further mapped into a visibility graph network to obtain visible particles. The information captured from the visible particles is then utilized by the algorithm to seek the optimum solution over the search space. The general performance of the proposed VPSS algorithm is first verified on a set of mathematical benchmark functions, and, afterward, its ability to identify structural damage is assessed by conducting various numerical simulations. The results demonstrate the high accuracy, reliability, and computational efficiency of the VPSS algorithm for identifying the location and the extent of damage in structures.

show abstract

“…Most structural health monitoring (SHM) strategies in mechanical and civil engineering use dynamic response information via signal processing to design an integrated intelligent monitoring system 1–12 . Wavelet is a time–frequency analysis tool that can play a vital role in a variety of signal processing schemes 13–15 and provides detailed information, which other methods such as Fourier transform and Hilbert–Huang transform are not able to capture 16 . Wavelet has the ability to analyze sensor collected data where it is time‐varying, noise contaminated, and has discontinuities 17 .…”

Section: Introductionmentioning

confidence: 99%

Selecting optimum levels of wavelet multi‐resolution analysis for time‐varying signals in structural health monitoring

Noori

Altabey

Ghiasi

2021

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

Summary Although the effectiveness of discrete wavelet transform (DWT) for analyzing time‐varying measurements has been studied for mechanical and civil engineering applications, a few fundamental questions still need to be answered, such as how to choose an optimal decomposition level (DL) for a specific task. Selection of the optimal DL still remains a question that has not been adequately explored and not thoroughly investigated. Vast majority of wavelet based methods in mechanical and civil engineering applications have been associated with nonstationary measurements and do not offer detail information on how DL should be selected or linked to useful features that can identify anomalies in a structure. This study proposes a new detailed framework for choosing the optimal DL to guarantee an effective wavelet analysis for time‐varying structural responses. The approach proposed in this paper uses various wavelets and theoretical levels to decompose the signal and to identify those aspects that interact to affect the DL, such as data characteristics, frequency band features, noise reduction, similarity, sharing information, and reconstruction quality. To show the effectiveness of our proposed method, we considered a comparative study using various mother wavelets on El Centro earthquake and acceleration responses from shaking table results of physical experiment. Experimental results show that the optimal DL for El Centro earthquake is 4 and for the acceleration data is 6. These results obviously demonstrate the stability and the robustness of the proposed method in the analysis of contaminated time‐varying signals.

show abstract

Comparative Analysis of Wavelet Transform for Time-Frequency Analysis and Transient Localization in Structural Health Monitoring

Cited by 60 publications

References 44 publications

Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer

Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer

Visible Particle Series Search Algorithm and Its Application in Structural Damage Identification

Selecting optimum levels of wavelet multi‐resolution analysis for time‐varying signals in structural health monitoring

Contact Info

Product

Resources

About