Automatic Crack Classification by Exploiting Statistical Event Descriptors for Deep Learning
Authors:
- Giulio SiracusanoGiulio Siracusano
- Francesca GarescìFGFrancesca Garescì
- Giovanni FinocchioGiovanni Finocchio
- Riccardo TomaselloRTRiccardo Tomasello
- Francesco LamonacaFrancesco Lamonaca
- Carmelo ScuroCSCarmelo Scuro
- Mario CarpentieriMCMario Carpentieri
- Massimo ChiappiniMCMassimo Chiappini
- Aurelio La CorteACAurelio La Corte
Open Access
- 17 December 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (24) , 12059
Abstract
In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven structural health monitoring (SHM) systems is gaining in popularity. This is due to the large availability of big data from low-cost sensors with communication capabilities and advanced modeling tools such as deep learning. A promising method suitable for smart SHM is the analysis of acoustic emissions (AEs), i.e., ultrasonic waves generated by internal ruptures of the concrete when it is stressed. The advantage in respect to traditional ultrasonic measurement methods is the absence of the emitter and the suitability to implement continuous monitoring. The main purpose of this paper is to combine deep neural networks with bidirectional long short term memory and advanced statistical analysis involving instantaneous frequency and spectral kurtosis to develop an accurate classification tool for tensile, shear and mixed modes originated from AE events (cracks). We investigated effective event descriptors to capture the unique characteristics from the different types of modes. Tests on experimental results confirm that this method achieves promising classification among different crack events and can impact on the design of the future of SHM technologies. This approach is effective to classify incipient damages with 92% of accuracy, which is advantageous to plan maintenance.Keywords
All Related Versions
Funding Information
- Ministero dell’Istruzione, dell’Università e della Ricerca (J45F21000460001)
This publication has 88 references indexed in Scilit:
- Static and dynamic analysis of bonded sandwich platesInternational Journal of Adhesion and Adhesives, 2012
- The influence of propagation path on elastic waves as measured by acoustic emission parametersStructural Health Monitoring, 2011
- Evaluation of deterioration in reinforced concrete structures by AE techniqueMaterials and Corrosion, 2010
- Recommendation of RILEM TC 212-ACD: acoustic emission and related NDE techniques for crack detection and damage evaluation in concrete*Materials and Structures, 2010
- Acoustic emission behavior of steel fibre reinforced concrete under bendingConstruction and Building Materials, 2009
- Mixed-mode crack propagation through reinforced concreteEngineering Fracture Mechanics, 2007
- Predicting the ultimate bending capacity of concrete beams from the “relaxation ratio” analysis of AE signalsConstruction and Building Materials, 2005
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Experimental and numerical crack analysis of mixed-mode failure in concrete by acoustic emission and boundary element methodConstruction and Building Materials, 1999
- Mixed mode fatigue crack growth: A literature surveyEngineering Fracture Mechanics, 1996