Wavelet packet transform for detection of single events in acoustic emission signals

Bianchi, Davide; Mayrhofer, Erwin; Gröschl, Martin; Betz, G.; Vernes, A.

doi:10.1016/j.ymssp.2015.04.014

Cited by 82 publications

(52 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to approach these mechanisms in micro-scale [5], more sophisticated analytical methods have been developed, allowing for clustering of AE signals and their pattern recognition [6]. Many authors use wavelet transform for more detailed damage identification and localization [7]. Due to time/frequency uncertainty [3] precise definition of the time of occurrence of specific damage process described by acoustic emission is difficult.…”

Section: Introductionmentioning

confidence: 99%

Acoustic Emission from Microcrack Initiation in Polymer Matrix Composites in Short Beam Shear Test

et al. 2018

View full text Add to dashboard Cite

Acoustic emission (AE) was applied for detection of microcrack initiation in carbon fiber reinforced polymer composites subjected to shear stresses. Experimental materials were prepared from polyester bonded unidirectional (1D) non-crimp fabric and 2D plain-weave carbon fiber fabrics, using the resin transfer moulding technology. Control of epoxy resin/carbon textile proportions enabled variation of fiber volume content from small (34/35% for 2D/1D), through medium (51%) to high (68%). Rectangular samples (45 × 4 × 2 mm) were cut from 1D plates along [0] and across [90] fibers. Similar size samples from 2D plates were cut along warp/weft axes as well as in two orthogonal bias directions. Selected side surfaces were polished for microscopic (SEM) observations. Short-beam-strength tests were performed in 3-point bending (l/h=4), with two AE sensors attached for damage monitoring, which allowed to interrupt loading sequence before final failure. The acoustic emission historic index was the most effective AE parameter in damage initiation control. Microcracks developing on polished composite side-surfaces were observed under the SEM and direct microscopic evidence confirmed fiber debonding to be the principal mechanism of crack initiation in these materials and testing conditions before any further damage.

show abstract

Section: Introductionmentioning

confidence: 99%

Acoustic Emission from Microcrack Initiation in Polymer Matrix Composites in Short Beam Shear Test

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Bartlett's theory [7,43] mentioned that if a neural network is used for a pattern recognition problem, the smaller size of weights brings a smaller square error during the training process, and then realizes a better generalization performance, which doesn't relate directly to the number of nodes. In order to reach smaller training error, the smaller the norms of weights tend to have a better generalization performance.…”

Section: Elm For Classificationmentioning

confidence: 99%

“…The data processing method simplifies the computational expense and benefits the improvement of the generation performance. Some typical feature extraction methods, such as wavelet packet transform (WPT) [7][8][9][10], empirical mode decomposition (EMD) [11], time-domain statistical features (TDSF) [12,13] and independent component analysis (ICA) [14][15][16][17] have been proved to be equivalent to a large-scale matrix factorization problem (i.e., there may be still some irrelevant or redundant noise in the extracted features) [18]. In order to resolve this problem, a feature selection method could be employed to wipe off irrelevant and redundant information so that the dimension of extracted feature is reduced.…”

Section: Introductionmentioning

confidence: 99%

Representational Learning for Fault Diagnosis of Wind Turbine Equipment: A Multi-Layered Extreme Learning Machines Approach

2016

View full text Add to dashboard Cite

Reliable and quick response fault diagnosis is crucial for the wind turbine generator system (WTGS) to avoid unplanned interruption and to reduce the maintenance cost. However, the conditional data generated from WTGS operating in a tough environment is always dynamical and high-dimensional. To address these challenges, we propose a new fault diagnosis scheme which is composed of multiple extreme learning machines (ELM) in a hierarchical structure, where a forwarding list of ELM layers is concatenated and each of them is processed independently for its corresponding role. The framework enables both representational feature learning and fault classification. The multi-layered ELM based representational learning covers functions including data preprocessing, feature extraction and dimension reduction. An ELM based autoencoder is trained to generate a hidden layer output weight matrix, which is then used to transform the input dataset into a new feature representation. Compared with the traditional feature extraction methods which may empirically wipe off some "insignificant' feature information that in fact conveys certain undiscovered important knowledge, the introduced representational learning method could overcome the loss of information content. The computed output weight matrix projects the high dimensional input vector into a compressed and orthogonally weighted distribution. The last single layer of ELM is applied for fault classification. Unlike the greedy layer wise learning method adopted in back propagation based deep learning (DL), the proposed framework does not need iterative fine-tuning of parameters. To evaluate its experimental performance, comparison tests are carried out on a wind turbine generator simulator. The results show that the proposed diagnostic framework achieves the best performance among the compared approaches in terms of accuracy and efficiency in multiple faults detection of wind turbines.

show abstract

“…However, TOA-based techniques require a relatively large number of receiver transducers measuring the coherent part of the wave field (ballistic wave). Advanced signal processing methods such as peak detection (Castro et al, 2018;Das and Leung, 2018;Zhou et al, 2019), cross-correlation (Kim et al, 2015;Li et al, 2018), Hilbert (Chen et al, 2018;Kim and Yuan, 2018), and wavelet transformation (Bianchi et al, 2015;Zhu et al, 2017) have been employed to extract physical parameters from measured data in order detect AE waves. Nevertheless, the dispersive nature of guided waves, as well as boundary reflections and mode conversion in geometrically complex components can all alter the acquired signal resulting in incorrect TOA estimations (Ciampa and Meo, 2011).…”

Section: Introductionmentioning

confidence: 99%

Impact Localization in Composites Using Time Reversal, Embedded PZT Transducers, and Topological Algorithms

Coles

Castro

Andreades

et al. 2020

Front. Built Environ.

View full text Add to dashboard Cite

Time reversal is a powerful imaging processing technique that focuses waves at their original source using a single receiver transducer when diffusive wave field conditions are met. This has been successfully proved on various engineering components and materials using elastic waves with surface bonded transducers. This paper investigates the performance of time reversal for the localization of impact sources on fiber reinforced plastic composite structures with embedded piezoelectric sensors. A topologic approach, here named as minimum average method, is proposed to enhance the accuracy of time reversal in retrieving the impact location. Experimental tests were carried out to validate the robustness and reliability of time reversal against traditional topological approaches by altering impulsive responses contained in the baseline signals. Impact localization results revealed that time reversal and the new topological approach provided high accuracy in identifying the impact location, particularly in the presence of double impacts and material damage, which were not accounted during the initial training process. Results indicate that time reversal with embedded transducers has potential to be effective in real operating conditions, where alterations of acoustic emission responses in the baseline signals are less predictable.

show abstract

Wavelet packet transform for detection of single events in acoustic emission signals

Cited by 82 publications

References 19 publications

Acoustic Emission from Microcrack Initiation in Polymer Matrix Composites in Short Beam Shear Test

Acoustic Emission from Microcrack Initiation in Polymer Matrix Composites in Short Beam Shear Test

Representational Learning for Fault Diagnosis of Wind Turbine Equipment: A Multi-Layered Extreme Learning Machines Approach

Impact Localization in Composites Using Time Reversal, Embedded PZT Transducers, and Topological Algorithms

Contact Info

Product

Resources

About