Related Concept Videos
Microcracking in Concrete
Types of Non-structural Cracks in Concrete
Plastic shrinkage cracks typically form within hours after the concrete is poured. The concrete's surface dries faster than the bottom, creating tensile stress that the still-plastic concrete cannot withstand, leading to diagonal or randomly patterned cracks on the concrete surface.
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Structure of yeast regulatory subunit: a glimpse into the evolution of PKA signaling.
Related Experiment Video
Updated: Sep 10, 2025

Crack Monitoring in Resonance Fatigue Testing of Welded Specimens Using Digital Image Correlation
Published on: September 29, 2019
A crack detection model fusing local details and global context for nuclear cladding coating surfaces.
Wei Quan1, Xiwen Li2, Jie Yang2
1School of Electrical Engineering, Southwest Jiaotong University, No. 999, Xi'an Road, Pidu District, Chengdu, Sichuan, 611756, China. wquan@swjtu.edu.cn.
This study introduces CrackCTFuse, a new AI model for detecting cracks on nuclear cladding surfaces. The model significantly improves crack detection accuracy, crucial for nuclear power plant safety.
Area of Science:
- Materials Science
- Nuclear Engineering
- Computer Vision
Background:
- Surface crack detection in nuclear cladding is vital for safe nuclear power plant operation.
- Existing methods struggle with imbalanced data, complex crack morphology, and subtle crack features.
Purpose of the Study:
- To develop a novel and effective crack detection model for nuclear cladding coating surfaces.
- To address limitations in current crack detection techniques for nuclear applications.
Main Methods:
- Proposed a novel crack detection model named CrackCTFuse.
- Incorporated a local feature enhancement module for edge details.
- Integrated a feature fusion module for combining local and global information.
- Utilized a multi-scale convolutional attention module for enhanced feature representation.
Main Results:
- CrackCTFuse effectively captures local and global features in crack images.
- The model demonstrated superior performance on a dedicated nuclear cladding dataset.
- Achieved a Mean Intersection over Union (MIoU) of 92.70% and an F1-score of 92.54%.
Conclusions:
- The CrackCTFuse model offers a significant advancement in nuclear cladding surface crack detection.
- The proposed architecture enhances the perception and representation of crack features at multiple scales.
- This improved detection capability contributes to enhanced safety and operational integrity of nuclear power plants.

