Development of software to interpretate radiographs of F5 wing spars

• Main Author: Koh, Chen Ming.
• Other Authors: Wong, Brian Stephen
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Aeronautical engineering::Accidents and air safety
• Online Access: http://hdl.handle.net/10356/44968
• Institution: Nanyang Technological University

The Republic of Singapore Air Force (RSAF) is developing an automated digital radiography system, part of which is an automated crack detection software. It will be an important development as it reduces the workload of inspectors in detecting crack on a complicated radiograph. A crack detection software was already developed by Dr Wang Xin, which mainly makes use of functions in the Matlab Image Processing Toolbox. Tests were conducted on 8 images using the software, and some flaws of the software were investigated. Suggested improvements were to remove the rivet holes from the region of inspection (ROI), as well as using thresholds instead of edge detection to find rivet holes. A section of the original algorithm was also made automated to cater to various image sizes. The new algorithms were incorporated into the original code and tested using the same images. Results obtained were generally positive, but more still have to be done to make the software fully automated.