Purdue University (West Lafayette, Indiana) researchers are working on an automated system to detect cracks in the steel components of nuclear power plants.
“Periodic inspection of the components of nuclear power plants is important to avoid accidents and ensure safe operation,” says Mohammad R. Jahanshahi, lead researcher and assistant professor. “However, current practices are time consuming, tedious, and subjective because they involve an operator manually locating cracks in metallic surfaces.”
Some algorithms struggle to detect cracks, the researchers say, because cracks are usually small, have low contrast, and are difficult to distinguish from welds, scratches, and grind marks. The group’s crack recognition and quantification (CRAQ) system, however, uses a technique based on texture changes surrounding the cracks.
“Cracking is an important factor in aging degradation that may cause leaking and result in hazardous incidents,” Jahanshahi says.
But manually inspecting each crack can be challenging. As a result, researchers have turned to video analysis and are searching for ways to improve its reliability.
“Direct manual inspection of reactor internals is not feasible due to high temperatures and radiation hazards,” Jahanshahi says. “So remotely recorded videos at the underwater reactor surface are used for inspection. However, recent testing has identified a need for increased reliability associated with identifying cracks from reviews of live and recorded data.”
The CRAQ method, which has a patent pending, processes multiple video frames at once.
“In contrast to other methods that only focus on detecting cracks in one image, we propose a method called Bayesian data fusion that tracks detected cracks in video frames and fuses the information obtained from multiple frames,” Jahanshahi says. “Moreover, we can filter out falsely detected cracks.”
Future research is aimed at developing a more accurate and fully automated system using advanced software.
To learn more, visit purdue.edu.