Structure Health Monitoring in Extreme Events from Machine Learning Perspective

Structure health monitoring utilizes the statistical signal information gathered from sensors implemented on structures to detect the building behavior. This information is more accurate and easier to analyze than traditional structural analysis method, which detects the building damage using dynamic properties directly. In this project, acceleration time history records of a Benchmark structure subjected to certain excitations obtained from sensors on the structure were analyzed, several Damage Sensitive Features were extracted, and different machine learning algorithms were used to predict the future behavior of the structure in extreme events like earthquakes.