This audio is automatically generated. Please let us know if you have any comments.
Dive brief:
- A team of researchers at Drexel University in Philadelphia created an AI-based system to inspect roads and bridges that can spot and control cracks before they develop into bigger problems.
- The research team wants to augment visual inspection technologies with a new approach to machine learning that combines computer vision, which allows machines to recognize and understand objects, with a deep learning algorithm to identify problem areas, according to a Drexel press release. Combined with autonomous robots, the researchers said the approach could help efficiently inspect and identify problem areas in infrastructure.
- Once a problem is detected, the process performs a series of laser scans of the region to create a digital twin of the structure that humans can use to assess and monitor damage, including tracking crack growth along the time, according to the statement.
Diving knowledge:
Drexel’s method, which the researchers published in the journal Automation in Constructionuses a high-resolution stereo depth camera to record images of a structure before feeding them into a deep learning program called a convolutional neural network.
Such systems can spot the finest patterns and discrepancies in massive volumes of data, the researchers said, with applications previously used in drug development, deep counterfeit detection and facial recognition technology.
Arvin Ebrahimkhanlou, an assistant professor in Drexel’s College of Engineering and a member of the research team, told Construction Dive that the team has been in contact with the National Academy of Building Inspection Engineers for the whole design process.
“The neural network has been trained on a sample crack dataset and can identify crack-like patterns in the images the robotic system collects of the surface of a concrete structure,” Ebrahimkhanlou said in the statement. “We call regions that contain these patterns regions of interest.”
While the technology has been tested in a lab environment, Ebrahimkhanlou told Construction Dive that the team needs a partner to test it in the field, which will take at least a few years.
In its latest assessment of U.S. infrastructure, the American Society of Civil Engineers found $786 billion in arrears only in road and bridge repairs.
