According to EPFL, researchers at the Swiss Federal Institute of Technology Lausanne have created an automated inspection framework designed to help engineers evaluate damage to critical steel infrastructure more consistently while lowering the risks faced by field inspectors.

The framework, developed by Dimitrios Lignos and his team at EPFL's Resilient Steel Structures Laboratory, was published in the journal Computers and Structures. It combines laser scanning technology, computer simulations, and artificial intelligence models to assess structural damage in a more evidence-based way, complementing rather than replacing human expertise.

Steel infrastructure such as telecommunication lines, electric transmission towers, bridges, and ski lifts is regularly exposed to natural hazards like strong winds and ice accretion, as well as general aging. Ensuring these structures remain safe depends on regular inspections by trained experts, who currently rely on visual assessments and specific reporting protocols to detect deformations, corrosion, flaws, or cracks. However, reaching these sites can be challenging, conditions may be dangerous, and the consequences of a partial evaluation can be costly.

The inspection process begins with detailed 3D scans of structural elements using laser technology, capturing their geometry and any visible deformation. The point-cloud techniques transform the scanned data, which is then evaluated by computer models developed from thousands of lab tests and reinforced with virtual samples verified by physics-based simulations. The system calculates the remaining safe load capacity of a damaged component and determines if it can function normally or needs repair..

"The methodological developments do not attempt to replace human inspectors but to guide them to make more informed decisions," Lignos said, according to EPFL.

This approach proves most useful when inspection teams encounter obstacles that could postpone assessments, extend service outages, and raise upkeep expenses. Consequently, the scientists concentrated on electricity pylons and structures featuring uniform steel cross-section shapes. These elements form an essential component of Switzerland's infrastructure, often located in remote areas and challenging to access after extreme weather events such as snowstorms.

One of the framework's most distinctive features, EPFL reported, is its ability to account for uncertainty in data acquired in the field. Measurements collected through scanners are never perfect — factors such as scan resolution and environmental conditions can introduce errors during acquisition, known as measurement noise. This can influence how damage is interpreted and potentially affect the reliability of predictions. The proposed methodology quantifies this uncertainty and evaluates its impact on the final assessment, allowing inspectors to better understand the confidence they can place in the results.

The methodological framework can extend to a wide range of structures, including conventional steel buildings and steel-concrete composite bridges, including railway infrastructure. It could also assist in determining whether decommissioned structures or components may be safely reused.

Researchers are now seeking pilot projects to take the technology from the laboratory into everyday infrastructure management. "The feedback obtained from inspection companies can provide essential information about how to improve and refine the established workflow before its eventual commercialization," Lignos said.

Lignos and his team have also been exploring, alongside Alcherio Martinoli, a professor at the Distributed Intelligent Systems and Algorithms Laboratory, the implementation of drone technology to reach structures in remote locations or those that pose a risk for human inspectors. Another ongoing project, in collaboration with Olga Fink, an associate professor from the Laboratory of Intelligent Maintenance and Operations Systems, aims to extend this framework to develop predictive algorithms for potential identification of members in steel structures to be reused after the end of their service life.

The work was supported by the Swiss National Science Foundation.