Next Article in Journal
Validity of Calculating Continuous Relative Phase during Cycling from Measures Taken with Skin-Mounted Electro-Goniometers
Previous Article in Journal
Resistive-Based Gas Sensors Using Quantum Dots: A Review
 
 
Article

Deep Learning Approach to Impact Classification in Sensorized Panels Using Self-Attention

Department of Aeronautics, Imperial College London, Exhibition Road, South Kensington, London SW7 2AZ, UK
*
Author to whom correspondence should be addressed.
Academic Editors: Gui Yun Tian and Simon Laflamme
Sensors 2022, 22(12), 4370; https://doi.org/10.3390/s22124370
Received: 24 March 2022 / Revised: 27 May 2022 / Accepted: 1 June 2022 / Published: 9 June 2022
(This article belongs to the Section Physical Sensors)
This paper proposes a new method of impact classification for a Structural Health Monitoring system through the use of Self-Attention, the central building block of the Transformer neural network. As a topical and highly promising neural network architecture, the Transformer has the potential to greatly improve the speed and robustness of impact detection. This paper investigates the suitability of this new network, confronting the advantages and disadvantages offered by the Transformer and a well-known and established neural network for impact detection, the Convolutional Neural Network (CNN). The comparison is undertaken on performance, scalability, and computational time. The inputs to the networks were created using a data transformation technique, which transforms the raw time series data collected from the network of piezoelectric sensors, installed on a composite panel, through the use of Fourier Transform. It is demonstrated that the Transformer method reduces the computational complexity of the impact detection significantly, while achieving excellent prediction results. View Full-Text
Keywords: structural health monitoring; impact classification; passive sensing; composite materials; deep learning; transformer; convolutional neural network structural health monitoring; impact classification; passive sensing; composite materials; deep learning; transformer; convolutional neural network
Show Figures

Figure 1

MDPI and ACS Style

Karmakov, S.; Aliabadi, M.H.F. Deep Learning Approach to Impact Classification in Sensorized Panels Using Self-Attention. Sensors 2022, 22, 4370. https://doi.org/10.3390/s22124370

AMA Style

Karmakov S, Aliabadi MHF. Deep Learning Approach to Impact Classification in Sensorized Panels Using Self-Attention. Sensors. 2022; 22(12):4370. https://doi.org/10.3390/s22124370

Chicago/Turabian Style

Karmakov, Stefan, and M. H. Ferri Aliabadi. 2022. "Deep Learning Approach to Impact Classification in Sensorized Panels Using Self-Attention" Sensors 22, no. 12: 4370. https://doi.org/10.3390/s22124370

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop