AI-Powered Digital Twins of Concrete Bridges for Enhanced Asset Management
CME Department Seminar
October 17, 2025
11:00 AM - 12:00 PM America/Chicago
Presenter: Gorkem Okudan, Ph.D., Walter P. Moore
Location: ERF 1047
Abstract: Ensuring the long-term sustainability of bridge assets is crucial, but manual inspections are often time-consuming, laborious, and can be hazardous. These issues can be addressed by leveraging autonomous 3D Reality Capture systems, augmented with Artificial Intelligence (AI) and Digital Twin technologies for enhanced monitoring and maintenance. This approach automates defect detection and simplifies post-processing, including generating repair documentation, shifting from traditional to proactive, data-driven asset management. In this study, the condition assessment of concrete bridge decks involves three steps: data acquisition, interpretive analysis, and visualization. Autonomous Unmanned Aerial Vehicles (UAVs) are employed to capture high-quality images of the bridge for visual and thermographic inspection, which are then stitched into a 3D model using photogrammetry. Deep Learning algorithms identify defects such as cracking and spalling in these images, significantly reducing manual inspection time. The 3D model is turned into a Digital Twin and visualized in an Asset Management Portal (AMP), empowering all stakeholders with a clear, interactive representation of the bridge's condition including defects identified by AI. The Digital Twin on AMP enables timely interventions and historical tracking of defects. By coupling autonomous UAVs with AI, the transformative potential of Digital Twins in Structural Health Monitoring can be fully realized.
Speaker Bio: Dr. Gorkem Okudan is an artificial intelligence engineer at Walter P Moore, specializing in artificial intelligence (AI) and machine learning (ML) applications of structural engineering in the built world. Okudan bridges computer vision with 3D Reality Capture, with an emphasis on autonomous unmanned aerial vehicles (UAVs). Having conducted many drone surveys, he logged hundreds of hours of FAA-compliant commercial flight time. He has developed and deployed AI/ML models for automated defect detection in concrete and masonry structures. He has not only played a key role in incorporating minimum viable product into the company workflow, but he has also become one of the pioneers in transforming the AEC industry by facilitating the use of digital twins for condition assessment and maintenance. Before his current position, he worked as a forensic engineer where he performed structural condition assessments, building envelope analyses, post-disaster evaluations, and advanced analysis, with an exposure to forensic R&D using AI/ML. Okudan received his Ph.D. in civil engineering along with an M.Sc. in computer science from University of Illinois Chicago in 2022.
Date posted
Oct 13, 2025
Date updated
Oct 13, 2025