An infrastructure maintenance company has implemented one of the first deep-learning artificial intelligence (AI) to allow bridge and tunnel owners detect changes before they can escalate into large-scale failures.
The company, Dynamic Infrastructure, has launched the system that provides live, cloud-based 3D views of a bridge or tunnel that automatically alerts asset managers if faults are detected.
“Medical records” are created for each bridge, tunnel and elevated highway based on existing images taken through periodical inspections on smartphones, drones and laser scanning.
The technology can then compare old and archived images to the new ones to detect maintenance and operations issues.
“The world faces an infrastructure crisis,” said Saar Dickman, co-founder and CEO of Dynamic Infrastructure.
- Adopting artificial intelligence in construction
- Metro Trains signs deal with Laing O’Rourke to deploy AI
- Telstra inspects towers with AI and 3D models
“Specifically, deficient bridges and tunnels represent a severe infrastructure challenge in the US and worldwide and their poor condition leads to life losses and millions in unplanned expenditures.
“Trying to repair America’s deficient infrastructure without adopting new technologies will not work.”
In America, where the company is based, the average age of a structurally deficient bridge is 62 years, with more than 235,000 US bridges being identified as needing repairs. The American Road and Transportation Builders Association estimates the cost of fixing these bridges will cost almost US$171 billion ($250 billion).
“Till recently, there has been no effective system that can quickly and precisely identify defects in bridges throughout their lifetime,” Dickman said.
“We are bringing the data revolution to the decision-making process of bridges and tunnel maintenance based on our cutting-edge imagery analysis.”