Monitoring Bridge and Building Safety with New Technologies

Researchers at the University of Central Florida have developed four new inventions that use artificial intelligence and virtual reality to improve the structural health monitoring of buildings, bridges, roads, and other civil structures. "Structural health monitoring is a demanding field internationally," said Necati Catbas. "It's almost like monitoring human health. As we age, monitoring our health becomes very important." Catbas, who leads the development of structural health monitoring technology, stated that civil infrastructure systems in developed countries are aging, but these new technologies can help. "By better understanding their condition, we can predict risks and better plan infrastructure investments," he said. According to Catbas, traditional monitoring methods involve on-site manual inspections, which are time-consuming, expensive, and can cause traffic congestion on roads and bridges. In addition to time and cost, on-site inspections of structurally aged or damaged sites can pose risks to personnel, even with personal protective equipment. Catbas and his research team have developed these technologies to help address these issues. "Over the years, I have been fortunate to collaborate with many individuals who have expertise in structural health monitoring, and I must thank them for their contributions," he said. "This is not a one-person effort." Using computer vision and augmented/virtual reality for structural health monitoring One of the inventions developed by Catbas and his team uses computer vision, while another utilizes augmented reality (AR) and virtual reality (VR). According to Catbas, computer vision can replace sensors and visual inspections for structural health, making it practical as it does not require access to structures such as bridges, buildings, or towers. "We can use cameras, and by analyzing the images, we can extract meaningful information about these bridges and buildings," he said. This technology is a comprehensive structural health monitoring system that allows inspectors to safely view and accurately assess the load performance and availability of structures without being on-site. Catbas explained that the UCF invention uses cameras around bridges to collect relevant images and location data. In the case of bridges, the data is related to vehicles passing through the bridge. The data can include vertical or horizontal displacement of the bridge caused by the movement, vibration effects, and speed of the beams. While the cameras continuously monitor the site, computer vision software processes and analyzes the collected data, providing safety assessments to system users, including information about structural changes, weaknesses, and direct damage. The second invention developed by the team is an immersive visualization system that uses VR and AR to analyze structures through "virtual visits." VR provides a fully computer-simulated environment, while AR can generate content or overlay content onto the actual view of the real-world environment. "With this technology, you can virtually bring experts to disaster areas, such as damaged buildings and bridges after hurricanes," Catbas said. "I can virtually be on a damaged bridge in Florida discussing and making decisions with colleagues in California." Similar to the first invention, the visualization system uses cameras and sensors to provide damage detection and other information about the structure. Additionally, it utilizes other tools such as robots, drones, laser scanners, and infrared thermography. With its visualization platform, the technology provides collected data and images through a user interface and sophisticated computer graphics. The results can be viewed in real-time on a website and allow interaction and communication with individuals from different locations. Using artificial intelligence to enhance structural damage diagnosis Two other inventions developed by Catbas and his team also incorporate artificial intelligence technology. The first invention combines human-centered artificial intelligence and mixed reality technology to help accelerate the inspection process, reduce costs, and ensure accuracy. With this invention, an inspector standing outside a damaged building can wear a headset and/or use handheld devices integrated with the technology. The inspector uses these devices to scan the damaged areas, and the system analyzes these areas in real-time without the need for manual measurements by the inspector. It then calculates or evaluates the condition of the building, speeding up the inspection process. During the evaluation, the inspector interacts with artificial intelligence and can adjust its defects and detection boundaries. The system uses the inspector's changes to retrain the artificial intelligence model, improving its accuracy over time. One major advantage of this invention is its ability to combine the professional judgment of inspectors or engineers with the analytical capabilities of artificial intelligence. The other invention, called Generative Adversarial Networks (GAN), enables a more proactive approach to managing and maintaining the health and safety of structures. It uses artificial intelligence to predict damage and minimize the need for collecting extensive structural data. "We don't need to place sensors and devices on all structures; we can collect data from some of them," Catbas said. He explained that collecting useful data about damaged structures from sensors is expensive and challenging. "The data from damaged areas is not sufficient to train detection models. However, machine learning (ML) and deep learning (DL) algorithms used in conjunction with artificial intelligence using large datasets can produce better and more accurate outputs," he said. As a solution to the scarcity of data in civil structural health monitoring applications, this invention utilizes data collected from structures. It uses a variant of the GAN architecture model to generate a large number of accurate synthetic data samples to train the damage diagnosis system. "Then, by using artificial intelligence, we can better understand the conditions of similar structures and make more effective decisions on how to address them," he said. These inventions can be used independently or in combination, according to Catbas. Future project plans Catbas stated that his team's future research plans include a framework for building smart and resilient communities capable of withstanding extreme events. "This framework enhances community resilience by providing valuable insights for disaster preparedness, resource allocation, and evacuation planning. It improves emergency management by enabling informed decision-making during crises," he said. They are also developing infrastructure asset "digital twins" similar to the ones NASA uses for spacecraft components. "They have these components on the ground, and if something happens, they use these replicas," he said. "So, in a way, these twins allow us to collect data simultaneously and study different structural scenarios using predictive analytics."