Abstract
High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks. Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens is performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN-based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks) with an overall accuracy of 77%. The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%.
Highlights
There is an agreement that diffuse ultrasonic waves are very sensitive to changes in the micro/mesostructure of concrete subjected to external loadings, reliable identification and classification of the wave measurements with the state of the material, i.e., the level of damage is challenging and far from established science
We explore a methodology for identifying damage in realistic virtual concrete specimens with the help of ultrasonic waves simulations and discrete element based simulations
A computational methodology for detection of damage in concrete under compression loading using synthetic Coda waves has been proposed in this paper
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. There is an agreement that diffuse ultrasonic waves are very sensitive to changes in the micro/mesostructure of concrete subjected to external loadings, reliable identification and classification of the wave measurements with the state of the material, i.e., the level of damage is challenging and far from established science. Numerical simulations are increasingly deployed as predictive models but as tools that can be used to virtually test hypotheses and gain new insight Such a methodology can significantly support experimental observations and provide insights into the plausible limits and potential of coda waves for damage detection (see e.g., [25,26]). Given the simulated wave data, we train a convolution neural network to identify the state of damage of the concrete specimen. The accuracy of the classifier is improved by performing feature analysis and data refinement
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
