Fatigue crack detection in thick steel structures with piezoelectric wafer active sensors

2011 ◽  
Author(s):  
M. Gresil ◽  
L. Yu ◽  
V. Giurgiutiu
Keyword(s):  
Fatigue Crack ◽  
Crack Detection ◽  
Steel Structures ◽  
Active Sensors ◽  
Piezoelectric Wafer Active Sensors ◽  
Thick Steel ◽  
Fatigue Crack Detection ◽  
Piezoelectric Wafer

P107 Fatigue Crack Detection in Steel Structures by Self-reference Lock-in Thermography

2005 ◽  
Vol 2005 (0) ◽  
pp. 637-638
Author(s):  
Takashi Nishimura ◽  
Takahide Sakagami ◽  
Shiro Kubo ◽  
Kazunari Ishino
Keyword(s):  
Fatigue Crack ◽  
Crack Detection ◽  
Steel Structures ◽  
Fatigue Crack Detection ◽  
Lock In ◽  
Self Reference

Detection of Cracks Using Piezoelectric Wafer Active Sensors

2005 ◽  
Vol 293-294 ◽  
pp. 201-206
Author(s):  
Antoni Blazewicz ◽  
Andrei G. Kotousov ◽  
Frank Wornle
Keyword(s):  
Laboratory Tests ◽  
Crack Detection ◽  
Fatigue Loading ◽  
Structural Elements ◽  
Active Sensors ◽  
Sensor Applications ◽  
Piezoelectric Wafer Active Sensors ◽  
Piezoelectric Wafer ◽  
Pulse Echo ◽  
Pulse Echo Method

The capability of piezoelectric wafer active sensors to identifying cracks which are common to metallic structural elements subjected to fatigue loading were explored. A number of laboratory tests were performed to investigate Lamb wave transmission and reception characteristics as well as the sensitivity of the transmitted and reflected signals to the presence of a through-the-thickness crack of various length and orientation in a thin plate. Based on the laboratory tests an optimum strategy for crack detection with the pulse-echo method was investigated. The method can be used for large areas scanning with a small amount of sensors and is favoured for embedded and leave-in-place sensor applications.

scholarly journals Pixel-Level Fatigue Crack Segmentation in Large-Scale Images of Steel Structures Using an Encoder–Decoder Network

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4135
Author(s):  
Chuanzhi Dong ◽  
Liangding Li ◽  
Jin Yan ◽  
Zhiming Zhang ◽  
Hong Pan ◽  
...  
Keyword(s):  
Fatigue Crack ◽  
Large Scale ◽  
Crack Detection ◽  
Fatigue Cracks ◽  
Steel Structures ◽  
Life Cycles ◽  
Detection Methods ◽  
Destructive Testing ◽  
Existing Structures ◽  
Fatigue Crack Detection

Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 × 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.

Sign in / Sign up

Export Citation Format

Share Document