Defects Identification and Crack Depth Determination in Porous Media on the Brick Masonry Example Using Ultrasonic Methods: Numerical Analysis and Machine Learning DOI Open Access
Alexey N. Beskopylny, Sergey A. Stel’makh, Evgenii M. Shcherban’

et al.

Journal of Composites Science, Journal Year: 2025, Volume and Issue: 9(6), P. 267 - 267

Published: May 28, 2025

Automation of the structural health monitoring process involves use successful methods for detecting defects and determining their critical characteristics. An efficient means crack detection in composite materials is ultrasonic method, but its application to determine parameters, such as depth construction practice, difficult or leads large errors. This article focuses on machine learning usage detect cracks like brickwork. Ceramic bricks with various mechanical properties pre-grown from 2 60 mm are considered. To understand processes occurring during pulse transmission, modeling was performed ANSYS environment. The brick considered a porous medium weakened by crack. Numerical allows identification main features signal response determination amplitude-time range different porosity values. Using made it possible solve two related problems. first, binary classification, i.e., presence absence crack, solved 100% accuracy. second depth. A neural network built using an ensemble decision trees. accuracy prediction R2 = 0.983, error predicted values within 8%.

Language: Английский

Impact and Failure Analysis of U-Shaped Concrete Containing Polyurethane Materials: Deep Learning and Digital Imaging Correlation-Based Approach DOI Open Access

Saleh Ahmad Laqsum,

Han Zhu, Sadi Ibrahim Haruna

et al.

Polymers, Journal Year: 2025, Volume and Issue: 17(9), P. 1245 - 1245

Published: May 2, 2025

This study investigates the use of advanced convolutional neural networks (CNNs) to analyze and classify fracture behavior U-shaped concrete modified with polyurethane (PU) under repeated drop-weight impact loads. A total 17 specimens were tested multiple loads for each PU binder content (0%, 10%, 20%, 30%) by weight cement. By integrating digital image correlation (DIC) dynamic static mechanical testing, this research evaluates concrete’s resistance flexural varying content. Three CNN architectures, InceptionV3, MobileNet, DenseNet121, trained on a dataset comprising 1655 high-resolution crack images failure stages into no crack, initial failure. Experimental results revealed that 20% optimally enhances strength, while properties declined significantly 30% The strain localization in DIC analysis indicated reduced matrix cohesion, which was measured extent concentration material, highlighting importance maintaining below avoid compromising structural integrity. Among models, InceptionV3 demonstrated superior accuracy (96.67%), precision, recall, outperforming MobileNet (94.56%) DenseNet121 (90.03%). combination deep learning offers robust, automated framework assessment, improving efficiency over traditional methods such as visual inspections, are time-consuming reliant expert judgment.

Language: Английский

Citations

0

Defects Identification and Crack Depth Determination in Porous Media on the Brick Masonry Example Using Ultrasonic Methods: Numerical Analysis and Machine Learning DOI Open Access
Alexey N. Beskopylny, Sergey A. Stel’makh, Evgenii M. Shcherban’

et al.

Journal of Composites Science, Journal Year: 2025, Volume and Issue: 9(6), P. 267 - 267

Published: May 28, 2025

Automation of the structural health monitoring process involves use successful methods for detecting defects and determining their critical characteristics. An efficient means crack detection in composite materials is ultrasonic method, but its application to determine parameters, such as depth construction practice, difficult or leads large errors. This article focuses on machine learning usage detect cracks like brickwork. Ceramic bricks with various mechanical properties pre-grown from 2 60 mm are considered. To understand processes occurring during pulse transmission, modeling was performed ANSYS environment. The brick considered a porous medium weakened by crack. Numerical allows identification main features signal response determination amplitude-time range different porosity values. Using made it possible solve two related problems. first, binary classification, i.e., presence absence crack, solved 100% accuracy. second depth. A neural network built using an ensemble decision trees. accuracy prediction R2 = 0.983, error predicted values within 8%.

Language: Английский

Citations

0