Deep neural networks for crack detection inside structures
Authors:
Open Access
- 23 February 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-15
Abstract
Crack detection is a long-standing topic in structural health monitoring. Conventional damage detection techniques rely on intensive, time-consuming, resource-intensive intervention. The current trend of crack detection emphasizes using deep neural networks to build an automated pipeline from measured signals to damaged areas. This work focuses on the seismic-wave-based technique of crack detection for plate structures. Previous work proposed an encoder–decoder network to extract crack-related wave patterns from measured wave signals and predict crack existence on the plate. We extend previous work with extensive experiments on different network components and a data preprocessing strategy. The proposed methods are tested on an expanded crack detection dataset. We found that a robust backbone network, such as Densely Connected Convolutional Network (DenseNet) can effectively extract the features characterizing cracks of wave signals, and by using the reference wave field for normalization, the accuracy of detecting small cracks can be further improved.Keywords
All Related Versions
Funding Information
- European Union - European Regional Development Fund (Das Kompetenzzentrum Geo-Energie)
- Federal Ministry of Economic Affairs and Industry - BMWI and the German Federation of Industrial Research Associations - ZIM/ AIF (ZF4016813FF8)
- Christian-Albrechts-Universität zu Kiel
This publication has 63 references indexed in Scilit:
- Real-time vibration-based structural damage detection using one-dimensional convolutional neural networksJournal of Sound and Vibration, 2017
- Learning Deconvolution Network for Semantic Segmentation2015
- Fault diagnosis on beam-like structures from modal parameters using artificial neural networksMeasurement, 2015
- Fully convolutional networks for semantic segmentation2015
- Deep learningNature, 2015
- Identification of cracks in thin-walled structures by means of wavenumber filteringMechanical Systems and Signal Processing, 2015
- Acoustic emission monitoring of a reinforced concrete shear wall by b-value–based outlier analysisStructural Health Monitoring, 2012
- Detection of defects in thin-walled structures by means of Lamb wavesAIP Conference Proceedings, 2012
- Neural network method based on a new damage signature for structural health monitoringThin-Walled Structures, 2005
- A Summary Review of Vibration-Based Damage Identification MethodsThe Shock and Vibration Digest, 1998