Share Email Print
cover

Proceedings Paper

Direct waveform extraction via a deep recurrent denoising autoencoder
Author(s): Meng Ma; Yang Qin; Mulugeta Haile; Zhu Mao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The localization of structural defects is of great interest in structure health monitoring (SHM). While acoustic emission signals are collected in the practice of SHM, the acquired waveforms inevitably include direct wave as well as reflection and reverberation waveforms. The direct wave actually contains more straightforward information in localizing the sources, so in this work, a deep recurrent denoising autoencoder (DRDA) network is developed. In general, waveform signals are highly correlated at different timescales, so temporally recurrent connections are added to the network structure, which have the memory of recent inputs. Consequently, the proposed DRDA model captures the dependencies across data points, while carrying out denoisng process, and combines the advantages of denoising autoencoders and recurrent neural networks. As the output of the proposed DRDA, direct waveforms are extracted and validated through finite element simulations. A contrived structure with nontrivial shape is excited by simulated pencil break excitations under the ABAQUS environment, then the simulated responses provide training data for the DRDA. The proposed algorithm is effective in filtering the reflected wave and outperforms the conventional denoising autoencoders.

Paper Details

Date Published: 1 April 2019
PDF: 9 pages
Proc. SPIE 10971, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XIII, 109711R (1 April 2019); doi: 10.1117/12.2515537
Show Author Affiliations
Meng Ma, Univ. of Massachusetts Lowell (United States)
Yang Qin, Univ. of Massachusetts Lowell (United States)
Mulugeta Haile, U.S. Army Research Lab. (United States)
Zhu Mao, Univ. of Massachusetts Lowell (United States)


Published in SPIE Proceedings Vol. 10971:
Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XIII
Andrew L. Gyekenyesi, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray