Purdue University researchers have developed a new AI system that detects cracks captured in videos of nuclear reactors, buildings, bridges and dams.
According to the researchers, the new system detects cracks in each video frame while the algorithm scheme has been programmed to track the crack from one frame to the next.
“This is a giant leap for inspection technology and being able to reduce accidents, deaths and maintenance costs,” says team lead and assistant professor Mohammad R. Jahanshahi.
“It lets the computer do the hard work, and then provides a human operator with quantitative information about the crack such as the thickness and the length of the crack.”
This information is then gleaned by the operator who reviews the videos and goes to the specific frames referenced by the software system to examine the cracks and determine what action may be necessary.
Jahanshahi notes that the AI method has already been tested on 20 nuclear power plant inspection videos so far, with results showing that this method is more robust than any other approach.
The system can also be used for detecting cracks on large buildings, roads and wind turbines.
“Our system is smart and adaptive to allow an operator to use their own data,” says Jahanshahi. “The computer can be reprogrammed based on that data to detect cracks within various structures and different materials.”
Unidentified or under-identified structural damage in nuclear reactors can be cataclysmic. Inspection of critical systems such as nuclear reactors is complicated and time-consuming.
Moreover, videos captured by an automatic crack detection system can easily misidentify small scratches or welds as cracks.
This forces technicians to review videos frame by frame which ends up being a time-consuming process with numerous opportunities for human error.
The Purdue team believes that their system will become even more useful as robots and drones are used to collect large amounts of visual data.
They contend that the AI detection system can also be used to detect damage and determine the structural health of buildings, roads and dams after earthquakes and other natural disasters.
Image and content: BBC Scotland/Purdue University