What is it about?
Using traditional image processing techniques (IPT) in conjunction with deep-learning based computer vision techniques helps to exploit necessary features for detecting cracks on structures, including gas turbines.
Featured Image
Photo by mahdis mousavi on Unsplash
Why is it important?
Automatic detection of cracks on turbines can add another layer of assurance in turbine health monitoring, to reduce the failure chance. Our method also increases the accuracy of the automatic detection of cracks on noisy surfaces.
Perspectives
In this project, we had the chance to develop various tools and methods to improve the accuracy of automatic crack detection for health monitoring and evaluate the usefulness of our work in real-world environments and data with the support of the General Electric company.
Mahtab Mohtashamkhani
Istanbul Teknik Universitesi
Read the Original
This page is a summary of: Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines, Structural Health Monitoring, November 2019, SAGE Publications,
DOI: 10.1177/1475921719883202.
You can read the full text:
Contributors
The following have contributed to this page
