1
|
Beskopylny AN, Stel'makh SA, Shcherban' EM, Razveeva I, Kozhakin A, Meskhi B, Chernil'nik A, Elshaeva D, Ananova O, Girya M, Nurkhabinov T, Beskopylny N. Computer Vision Method for Automatic Detection of Microstructure Defects of Concrete. SENSORS (BASEL, SWITZERLAND) 2024; 24:4373. [PMID: 39001152 PMCID: PMC11244612 DOI: 10.3390/s24134373] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Revised: 06/16/2024] [Accepted: 07/03/2024] [Indexed: 07/16/2024]
Abstract
The search for structural and microstructural defects using simple human vision is associated with significant errors in determining voids, large pores, and violations of the integrity and compactness of particle packing in the micro- and macrostructure of concrete. Computer vision methods, in particular convolutional neural networks, have proven to be reliable tools for the automatic detection of defects during visual inspection of building structures. The study's objective is to create and compare computer vision algorithms that use convolutional neural networks to identify and analyze damaged sections in concrete samples from different structures. Networks of the following architectures were selected for operation: U-Net, LinkNet, and PSPNet. The analyzed images are photos of concrete samples obtained by laboratory tests to assess the quality in terms of the defection of the integrity and compactness of the structure. During the implementation process, changes in quality metrics such as macro-averaged precision, recall, and F1-score, as well as IoU (Jaccard coefficient) and accuracy, were monitored. The best metrics were demonstrated by the U-Net model, supplemented by the cellular automaton algorithm: precision = 0.91, recall = 0.90, F1 = 0.91, IoU = 0.84, and accuracy = 0.90. The developed segmentation algorithms are universal and show a high quality in highlighting areas of interest under any shooting conditions and different volumes of defective zones, regardless of their localization. The automatization of the process of calculating the damage area and a recommendation in the "critical/uncritical" format can be used to assess the condition of concrete of various types of structures, adjust the formulation, and change the technological parameters of production.
Collapse
Affiliation(s)
- Alexey N Beskopylny
- Department of Transport Systems, Faculty of Roads and Transport Systems, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Sergey A Stel'makh
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Evgenii M Shcherban'
- Department of Engineering Geometry and Computer Graphics, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Irina Razveeva
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Alexey Kozhakin
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
- OOO VDK, SKOLKOVO, Bolshoi Boulevard, 42, 121205 Moscow, Russia
| | - Besarion Meskhi
- Department of Life Safety and Environmental Protection, Faculty of Life Safety and Environmental Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Andrei Chernil'nik
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Diana Elshaeva
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Oksana Ananova
- Department of Marketing and Engineering Economics, Faculty of Innovative Business and Management, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Mikhail Girya
- Department of Unique Buildings and Constructions Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia
| | - Timur Nurkhabinov
- Department of Mathematical Theory of Intelligent Systems, Faculty of Mechanics and Mathematics, Lomonosov Moscow State University, Leninskiye Gory, 1, 119991 Moscow, Russia
| | - Nikita Beskopylny
- Department of Hardware and Software Engineering, Faculty of IT-Systems and Technology, Don State Technical University, 344003 Rostov-on-Don, Russia
| |
Collapse
|
2
|
Yang F, Huo J, Cheng Z, Chen H, Shi Y. An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts. SENSORS (BASEL, SWITZERLAND) 2023; 24:62. [PMID: 38202924 PMCID: PMC10780529 DOI: 10.3390/s24010062] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Revised: 11/19/2023] [Accepted: 11/23/2023] [Indexed: 01/12/2024]
Abstract
Micro-crack detection is an essential task in critical equipment health monitoring. Accurate and timely detection of micro-cracks can ensure the healthy and stable service of equipment. Aiming at improving the low accuracy of the conventional target detection model during the task of detecting micro-cracks on the surface of metal structural parts, this paper built a micro-cracks dataset and explored a detection performance optimization method based on Mask R-CNN. Firstly, we improved the original FPN structure, adding a bottom-up feature fusion path to enhance the information utilization rate of the underlying feature layer. Secondly, we added the methods of deformable convolution kernel and attention mechanism to ResNet, which can improve the efficiency of feature extraction. Lastly, we modified the original loss function to optimize the network training effect and model convergence rate. The ablation comparison experiments shows that all the improvement schemes proposed in this paper have improved the performance of the original Mask R-CNN. The integration of all the improvement schemes can produce the most significant performance improvement effects in recognition, classification, and positioning simultaneously, thus proving the rationality and feasibility of the improved scheme in this paper.
Collapse
Affiliation(s)
| | - Junzhou Huo
- School of Mechanical Engineering, Dalian University of Technology, Dalian 116024, China; (F.Y.); (Z.C.); (H.C.); (Y.S.)
| | | | | | | |
Collapse
|