Next Article in Journal
Monitoring and Analysis of Expansion Relief Grooves to Control the Arch Expansion Disease
Previous Article in Journal
Research on the Bending Behavior of Concrete Beams Reinforced with CFRP Sheets Bonded Using BMSC
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Buildings
Volume 15
Issue 12
10.3390/buildings15121982
buildings-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Crushed Stone Grain Shapes Classification Using Convolutional Neural Networks

by
Alexey N. Beskopylny
1,*,
Evgenii M. Shcherban’
2,
Sergey A. Stel’makh
3,
Irina Razveeva
3,
Alexander L. Mailyan
4,
Diana Elshaeva
3,
Andrei Chernil’nik
3,
Nadezhda I. Nikora
3 and
Gleb Onore
5
1
Department of Transport Systems, Faculty of Roads and Transport Systems, Don State Technical University, 344003 Rostov-on-Don, Russia
2
Department of Engineering Geometry and Computer Graphics, Don State Technical University, 344003 Rostov-on-Don, Russia
3
Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
4
Department of Urban Construction and Economy, Don State Technical University, 344003 Rostov-on-Don, Russia
5
Institute of Applied Computer Science, University ITMO, Kronverksky Pr. 49, 197101 Saint Petersburg, Russia
*
Author to whom correspondence should be addressed.
Buildings 2025, 15(12), 1982; https://doi.org/10.3390/buildings15121982
Submission received: 8 May 2025 / Revised: 1 June 2025 / Accepted: 6 June 2025 / Published: 8 June 2025
(This article belongs to the Section Building Materials, and Repair & Renovation)
Versions Notes

Abstract

Currently, intelligent technologies are becoming both a topical subject for theoretical discussions and a proper tool for transforming traditional industries, including the construction industry. The construction industry intensively uses innovative methods based on intelligent algorithms of various natures. As practice shows, modern intelligent technologies based on AI surpass traditional ones in accuracy and speed of information processing. This study implements methods using convolutional neural networks, which solve an important problem in the construction industry—to classify crushed stone grains by their shape. Rapid determination of the crushed stone grain class will allow determining the content of lamellar and acicular grains, which in turn is a characteristic that affects the strength, adhesion, and filler placement. The classification algorithms were based on the ResNet50, MobileNetV3 Small, and DenseNet121 architectures. Three-dimensional images of acicular, lamellar, and cuboid grains were converted into single-channel digital tensor format. During the laboratory experiment, the proposed intelligent algorithms demonstrated high stability and efficiency. The total processing time for 200 grains, including the photo recording stage, averaged 16 min 41 s, with the accuracy reaching 92%, which is comparable to the results of manual classification by specialists. These models provide for the complete automation of crushed stone grain typing, leading to reduced labor costs and a decreased likelihood of human error.
Keywords: crushed stone; computer vision; convolutional neural network; image classification; crushed stone grains shape crushed stone; computer vision; convolutional neural network; image classification; crushed stone grains shape

Share and Cite

MDPI and ACS Style

Beskopylny, A.N.; Shcherban’, E.M.; Stel’makh, S.A.; Razveeva, I.; Mailyan, A.L.; Elshaeva, D.; Chernil’nik, A.; Nikora, N.I.; Onore, G. Crushed Stone Grain Shapes Classification Using Convolutional Neural Networks. Buildings 2025, 15, 1982. https://doi.org/10.3390/buildings15121982

AMA Style

Beskopylny AN, Shcherban’ EM, Stel’makh SA, Razveeva I, Mailyan AL, Elshaeva D, Chernil’nik A, Nikora NI, Onore G. Crushed Stone Grain Shapes Classification Using Convolutional Neural Networks. Buildings. 2025; 15(12):1982. https://doi.org/10.3390/buildings15121982

Chicago/Turabian Style

Beskopylny, Alexey N., Evgenii M. Shcherban’, Sergey A. Stel’makh, Irina Razveeva, Alexander L. Mailyan, Diana Elshaeva, Andrei Chernil’nik, Nadezhda I. Nikora, and Gleb Onore. 2025. "Crushed Stone Grain Shapes Classification Using Convolutional Neural Networks" Buildings 15, no. 12: 1982. https://doi.org/10.3390/buildings15121982

APA Style

Beskopylny, A. N., Shcherban’, E. M., Stel’makh, S. A., Razveeva, I., Mailyan, A. L., Elshaeva, D., Chernil’nik, A., Nikora, N. I., & Onore, G. (2025). Crushed Stone Grain Shapes Classification Using Convolutional Neural Networks. Buildings, 15(12), 1982. https://doi.org/10.3390/buildings15121982

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop