Team Builds Infrastructure Assessment AI

FRIDAY, DECEMBER 1, 2023


Researchers at the University of Central Florida have reportedly developed four new artificial intelligence and virtual reality systems to maintain and repair aging infrastructure.

According to a release from the university, the new developments can help improve the structural health monitoring of buildings, bridges, roads and other civil structures.

About the Research

“Structural health monitoring is an area of need internationally,” said Necati Catbas, a Lockheed Martin St. Laurent Professor in UCF’s Department of Civil, Environmental and Construction Engineering.

“It’s almost like human health monitoring. As we get older, monitoring our health becomes very, very critical.”
Catbas, is reportedly leading the development of the structural health monitoring technologies. He stated that civil infrastructure systems in developed countries are getting older and could use the help of these new technologies.

“By better understanding their conditions, we can anticipate risks and better prioritize infrastructure investments,” he stated.

Catbas added that traditional methods for monitoring these structures usually involves onsite visual inspections, which can be lengthy and expensive and can create traffic closures.

On top of time and expense, sites with aging or damaged structures can reportedly create potential dangers for those at the site, even if wearing protective equipment. Catbas and his research team reportedly built these technologies in an attempt to help fix these specific issues.

“I am very lucky to have collaborated with many people who have expertise in structural health monitoring over the years, and I have to acknowledge their contribution,” he said. “It’s not a one-person effort.”

According to the release, one invention that Catbas and his team developed uses computer vision, while another uses augmented reality and virtual reality.

Catbas stated that computer vision can aid sensors and visual inspections for structural health without the need for direct access to the structures.

“We can use the camera, and by analyzing the images, we can extract meaningful information about these bridges and buildings,” he said.

The technology, called a Comprehensive Structural Health Monitoring System, can reportedly allow inspectors to view and accurately study the load-worthiness and serviceability of structures without having to be onsite.

The development reportedly utilizes cameras that are mounted on and around a structure to gather image and location data pertaining to the structure’s use. In the example of a bridge, the data would relate to vehicles crossing it.

The gathered data can also reportedly be used for the vertical or horizontal displacement of girders caused by their movement, vibrational effects and velocity. While the cameras monitor the site, computer vision software reportedly analyzes the collected data, giving system users a safety assessment, including structural changes and weaknesses and immediate damage.

The second invention, the team stated, is an Immersive Visualization System using VR and AR to analyze structures through “virtual visits.”

The VR aspect is meant to give users a fully computer-simulated environment, while the AR should overlay content onto the views of a real-world environment.

“With this technology, you can virtually bring experts to disaster areas, such as buildings and bridges, like after a hurricane,” Catbas said. “I can virtually be on a damaged bridge in Florida discussing decisions with colleagues who might be in California.”

Similar to the first invention, the visualization system gives damage detection and load-carrying information about a structure with cameras and sensors, also using robots, unmanned aerial vehicles or drones, LiDAR scanners and infrared thermography cameras.

With its visualization platform, the technology can reportedly relay the collected data and images through a user interface and computer graphics, giving users a real-time view of a site and the ability to interact and communicate with people from different locations.

Enhancing the Inspections

The other two inventions developed by the team reportedly utilize AI. The release states that the team's Collective Intelligence Framework technology can blend “human-centric AI” with mixed reality to help speed up inspections and reduce costs while also improving accuracy.

With this invention, an inspector standing outside a damaged building, the team stated, could wear a headset or use a hand-held device integrated with the technology.

The inspector would reportedly utilize the items to scan damaged areas, having the system study it in real-time to help save the inspector from manual measurements. The technology can then reportedly assess the building’s condition, potentially speeding the inspection process.

During the assessment, the inspector works with the AI and is able to adjust its defect and detection boundaries. The system uses the inspector’s alterations to retrain the AI model so that accuracy improves over time.

The release states that a major advantage of the invention is its ability to “combine the professional judgment of an inspector/engineer with the AI’s analytical power.”

Additionally, the Generative Adversarial Network (GAN) invention can reportedly allow for a more proactive approach to managing and maintaining the health and safety of structures. The team stated that this technology uses AI to predict damage and reduce the need for data collection from many structures.

“Instead of putting sensors and devices on all structures, we can collect data from just a few of them,” Catbas said.

Catbas explained that collecting useful data from sensors about damaged structures is expensive and challenging.

“There is not enough data from damaged areas to train detection models,” Catbas stated. “Yet, machine learning (ML) and deep learning (DL) algorithms used with AI yield better, more accurate output using big data sets.

“As a solution to the data scarcity in civil structural health monitoring applications, the invention takes data collected from structures. It uses model variants of the GAN architecture to generate large, accurate synthetic data samples to train damage diagnostics systems. Then, by using AI, we can better understand what’s going on with other similar structures and more effectively decide how to respond,” he added.

The technology can reportedly help users estimate the dynamic response of a structure change before damage conditions actually happen, reportedly making it possible to create potential future conditions of structures.

The team states that an examples of this would be generating data to show what a healthy bridge’s response would be after damage compared to the response of an unhealthy bridge.

Catbas also added that in the future, he and his team plan to include a framework for smart and resilient communities to withstand extreme events.

“It enhances community resilience by providing valuable insights for disaster preparedness, resource allocation and evacuation planning,” he said. “The framework improves emergency management by enabling informed decision-making during crises.”

Additionally, the team is reportedly building a “digital twin” of infrastructure assets, much like how NASA uses replicas of spacecraft components.

“They have those components on the ground, and if something happens, they work with these replicas,” he said. “So, this twin, in a sense, allows us to collect data simultaneously and work on different structure scenarios using predictive analysis.”

Catbas says that the inventions can be used independently or together. More information on the technology sheets can be found here.

   

Tagged categories: Asia Pacific; Colleges and Universities; Construction; EMEA (Europe, Middle East and Africa); Failure analysis; Infrastructure; Infrastructure; Inspection; Inspection equipment; Latin America; North America; Paint analysis; Program/Project Management; Quality Control; Research; Research and development; Technology; Testing + Evaluation; Tools & Equipment; Z-Continents

Join the Conversation:

Sign in to our community to add your comments.