Using Deep Learning for Accurate Detection of Bridge Performance Anomalies
Dr. Farnoush Banei-Kashani, PI, University of Colorado Denver
Dr. Jimmy Kim, Co-PI, University of Colorado Denver
Dr. Chris Pantelides, Co-PI, University of Utah
With this project, building on our prior work, our main goal is to introduce improved deep learning based anomaly detection methods for timely and accurate management and monitoring of bridge performance. Such methods can be used to perform predictive analysis of the bridge performance by accurate prediction of quantitative descriptors for the structure deterioration state (e.g., condition ratings) as well as any possible anomalies in the deterioration pattern of the bridge structure. Accurate prediction of these descriptors and anomalies are not only crucial in establishing maintenance priorities and performing proactive bridge monitoring with optimized resource allocation, but also more importantly essential for failure prevention.