Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring
Acoustic emission (AE) is one of the most effective nondestructive testing (NDT) techniques for the identification and characterization of stress waves originated at the uprising of acoustic-related defects (e.g., cracks). To this end, the estimation of the time of arrival (ToA) is crucial. In this...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10734354/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536201978281984 |
|---|---|
| author | Federica Zonzini Wenliang Xiang Luca de Marchi |
| author_facet | Federica Zonzini Wenliang Xiang Luca de Marchi |
| author_sort | Federica Zonzini |
| collection | DOAJ |
| description | Acoustic emission (AE) is one of the most effective nondestructive testing (NDT) techniques for the identification and characterization of stress waves originated at the uprising of acoustic-related defects (e.g., cracks). To this end, the estimation of the time of arrival (ToA) is crucial. In this work, a novel processing flow which shifts the identification process from the time to the time-frequency domain via wavelet transform (WT) is proposed, allowing to better capture transient behaviors typical of the originated AE signals. More specifically, both the continuous and the discrete WT alternatives have been explored to find the best compromise between time-frequency resolution and computational complexity in view of extreme edge deployments. Furthermore, the event-driven capabilities of neuromorphic architectures (and spiking neural networks (SNNs) in particular) in processing spiky and sparse temporal information are exploited to retrieve ToA in a beyond state-of-the-art power-efficient manner and negligible loss of performance with respect to standard models. Therefore, we aim at combining the superior performances in ToA identification enabled by the WT operator with the unique energy saving disclosed by spiking hardware and software. Experimental tests executed on a metallic plate structure demonstrated that WT combined with SNN can achieve high precision (median values less than 5 cm) in ToA estimation and AE source localization even in the presence of relevant noise (signal-to-noise ratio down to 2 dB), while its deployment on dedicated neuromorphic architectures can reduce by six orders of magnitude the power expenditure per inference when compared to standard convolutional architectures. |
| format | Article |
| id | doaj-art-b6b6a39dfe0c4760903d96340619f1d9 |
| institution | Kabale University |
| issn | 2768-7236 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-b6b6a39dfe0c4760903d96340619f1d92025-01-15T00:04:21ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362024-01-01311310.1109/OJIM.2024.348561810734354Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based MonitoringFederica Zonzini0https://orcid.org/0000-0002-2429-1469Wenliang Xiang1https://orcid.org/0009-0008-2521-727XLuca de Marchi2https://orcid.org/0000-0003-0637-9472Department of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, ItalySchool of Mathematics and Statistics, University of Melbourne, Melbourne, VIC, AustraliaDepartment of Electrical, Electronic and Information Engineering, University of Bologna, Bologna, ItalyAcoustic emission (AE) is one of the most effective nondestructive testing (NDT) techniques for the identification and characterization of stress waves originated at the uprising of acoustic-related defects (e.g., cracks). To this end, the estimation of the time of arrival (ToA) is crucial. In this work, a novel processing flow which shifts the identification process from the time to the time-frequency domain via wavelet transform (WT) is proposed, allowing to better capture transient behaviors typical of the originated AE signals. More specifically, both the continuous and the discrete WT alternatives have been explored to find the best compromise between time-frequency resolution and computational complexity in view of extreme edge deployments. Furthermore, the event-driven capabilities of neuromorphic architectures (and spiking neural networks (SNNs) in particular) in processing spiky and sparse temporal information are exploited to retrieve ToA in a beyond state-of-the-art power-efficient manner and negligible loss of performance with respect to standard models. Therefore, we aim at combining the superior performances in ToA identification enabled by the WT operator with the unique energy saving disclosed by spiking hardware and software. Experimental tests executed on a metallic plate structure demonstrated that WT combined with SNN can achieve high precision (median values less than 5 cm) in ToA estimation and AE source localization even in the presence of relevant noise (signal-to-noise ratio down to 2 dB), while its deployment on dedicated neuromorphic architectures can reduce by six orders of magnitude the power expenditure per inference when compared to standard convolutional architectures.https://ieeexplore.ieee.org/document/10734354/Acoustic emission (AE)impact localizationnondestructive testing (NDT)spiking neural network (SNN)time-frequency transform |
| spellingShingle | Federica Zonzini Wenliang Xiang Luca de Marchi Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring IEEE Open Journal of Instrumentation and Measurement Acoustic emission (AE) impact localization nondestructive testing (NDT) spiking neural network (SNN) time-frequency transform |
| title | Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring |
| title_full | Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring |
| title_fullStr | Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring |
| title_full_unstemmed | Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring |
| title_short | Spiking Neural Networks for Energy-Efficient Acoustic Emission-Based Monitoring |
| title_sort | spiking neural networks for energy efficient acoustic emission based monitoring |
| topic | Acoustic emission (AE) impact localization nondestructive testing (NDT) spiking neural network (SNN) time-frequency transform |
| url | https://ieeexplore.ieee.org/document/10734354/ |
| work_keys_str_mv | AT federicazonzini spikingneuralnetworksforenergyefficientacousticemissionbasedmonitoring AT wenliangxiang spikingneuralnetworksforenergyefficientacousticemissionbasedmonitoring AT lucademarchi spikingneuralnetworksforenergyefficientacousticemissionbasedmonitoring |