1. Wavelet-based multiresolution analysis coupled with deep learning to efficiently monitor cracks in concrete
- Author
-
Sébastien Jacques, Ahcene Arbaoui, Abdeldjalil Ouahabi, Madina Hamiane, Université Mohamed Akli Ouelhadj de Bouira (UMAOB), Imagerie et cerveau (iBrain - Inserm U1253 - UNIV Tours ), Université de Tours-Institut National de la Santé et de la Recherche Médicale (INSERM), GREMAN (matériaux, microélectronique, acoustique et nanotechnologies) (GREMAN - UMR 7347), Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Tours-Centre National de la Recherche Scientifique (CNRS), Royal University for Women (RUW), Université de Tours (UT)-Institut National de la Santé et de la Recherche Médicale (INSERM), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Tours (UT)-Centre National de la Recherche Scientifique (CNRS), Jacques, Sebastien, Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)
- Subjects
Identification scheme ,010504 meteorology & atmospheric sciences ,Computer science ,Multiresolution analysis ,0211 other engineering and technologies ,TA630-695 ,02 engineering and technology ,01 natural sciences ,Convolutional neural network ,Wavelet ,crack monitoring ,TJ1-1570 ,Mechanical engineering and machinery ,[SPI.MECA.GEME] Engineering Sciences [physics]/Mechanics [physics.med-ph]/Mechanical engineering [physics.class-ph] ,wavelet-based multiresolution analysis ,021101 geological & geomatics engineering ,0105 earth and related environmental sciences ,[SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph] ,[SPI.ACOU] Engineering Sciences [physics]/Acoustics [physics.class-ph] ,Artificial neural network ,Structural engineering (General) ,business.industry ,Mechanical Engineering ,Deep learning ,Ultrasonic testing ,deep learning ,Pattern recognition ,non-destructive ultrasonic testing ,[SPI.MECA.GEME]Engineering Sciences [physics]/Mechanics [physics.med-ph]/Mechanical engineering [physics.class-ph] ,[SPI.GCIV]Engineering Sciences [physics]/Civil Engineering ,Mechanics of Materials ,Pattern recognition (psychology) ,[SPI.GCIV] Engineering Sciences [physics]/Civil Engineering ,concrete ,Artificial intelligence ,business - Abstract
International audience; This paper proposes an efficient methodology to monitor the formation of cracks in concrete after non-destructive ultrasonic testing of a structure. The objective is to be able to automatically detect the initiation of cracks early enough, i.e. well before they are visible on the concrete surface, in order to implement adequate maintenance actions on civil engineering structures. The key element of this original approach is the wavelet-based multiresolution analysis of the ultrasonic signal received from a sample or a specimen of the studied material subjected to several types of solicitation. This analysis is finally coupled to an automatic identification scheme of the types of cracks based on artificial neural networks (ANNs), and in particular deep learning by convolutional neural networks (CNNs); a technology today at the cutting edge of machine learning, in particular for all applications of pattern recognition. Wavelet-based multiresolution analysis does not add any value in detecting fractures in concrete visible by optical inspection. However, the results of its implementation coupled with different CNN architectures show cracks in concrete can be identified at an early stage with a very high accuracy, i.e. around 98%, and a loss function of less than 0.1, regardless of the implemented learning architecture.
- Published
- 2021