Artificial intelligence to detect structural cracks

US college Purdue University is working on an artificial intelligence system to detect cracks captured in videos, which analyses them frame by frame.

Engineers Australia said a tiny crack in a bridge, dam or building can result in catastrophic consequences however, this system may soon be able to avert disasters.

The potential for unidentified, under-identified or misidentified structural damage is enormous throughout the construction world.

Structural inspection usually involves going through videos captured by automatic crack detection systems which is time-consuming and vulnerable to human error.

This system, developed by the university’s college of engineering will use an algorithm capable of tracking cracks from one frame on a video to the next.

Assistant Professor Mohammad R Jahanshahi believes it’s a “giant leap for inspection technology”, and is set to lead to reductions in accidents, deaths and maintenance costs.

“It lets the computer do the hard work,” Prof. Jahanshahi said. “[It] provides a human operator with quantitative information about the crack, such as the thickness and the length of the crack.”

The operator is then able to review the video and note specific frames referenced by the software to determine what action is needed.

The engineering team has tested the software on 20 nuclear power plant inspection videos.

The results show the method was more robust than any other approach. The system also offers many potential applications such as detecting cracks on large buildings, roads and wind turbines.

Professor Jahanshahi believes the system will become even more useful as robots and drones are deployed to collect large amounts of visual data.